* [PATCH RFC v2 net-next 18/21] net/ipv6: introduce fib6_info struct and helpers
From: David Ahern @ 2018-03-19 3:36 UTC (permalink / raw)
To: netdev
Cc: davem, idosch, roopa, eric.dumazet, weiwan, kafai, yoshfuji,
David Ahern
In-Reply-To: <20180319033622.16693-1-dsahern@gmail.com>
Add fib6_info struct and alloc, destroy, hold and release helpers.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/net/ip6_fib.h | 55 ++++++++++++++++++++++++++++++++++++++++++++++
net/ipv6/ip6_fib.c | 60 +++++++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 115 insertions(+)
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 159f651dee55..630392ae12d8 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -38,6 +38,7 @@
#endif
struct rt6_info;
+struct fib6_info;
struct fib6_config {
u32 fc_table;
@@ -132,6 +133,46 @@ struct fib6_nh {
int nh_weight;
};
+struct fib6_info {
+ struct fib6_table *rt6i_table;
+ struct fib6_info __rcu *rt6_next;
+ struct fib6_node __rcu *rt6i_node;
+
+ /* Multipath routes:
+ * siblings is a list of fib6_info that have the the same metric/weight,
+ * destination, but not the same gateway. nsiblings is just a cache
+ * to speed up lookup.
+ */
+ struct list_head rt6i_siblings;
+ unsigned int rt6i_nsiblings;
+
+ atomic_t rt6i_ref;
+ struct inet6_dev *rt6i_idev;
+ unsigned long expires;
+ struct dst_metrics *fib6_metrics;
+#define fib6_pmtu fib6_metrics->metrics[RTAX_MTU-1]
+
+ struct rt6key rt6i_dst;
+ u32 rt6i_flags;
+ struct rt6key rt6i_src;
+ struct rt6key rt6i_prefsrc;
+
+ struct rt6_info * __percpu *rt6i_pcpu;
+ struct rt6_exception_bucket __rcu *rt6i_exception_bucket;
+
+ u32 rt6i_metric;
+ u8 rt6i_protocol;
+ u8 fib6_type;
+ u8 exception_bucket_flushed:1,
+ should_flush:1,
+ dst_nocount:1,
+ dst_nopolicy:1,
+ dst_host:1,
+ unused:3;
+
+ struct fib6_nh fib6_nh;
+};
+
struct rt6_info {
struct dst_entry dst;
struct rt6_info __rcu *rt6_next;
@@ -291,6 +332,20 @@ static inline void ip6_rt_put(struct rt6_info *rt)
void rt6_free_pcpu(struct rt6_info *non_pcpu_rt);
+struct rt6_info *fib6_info_alloc(gfp_t gfp_flags);
+void fib6_info_destroy(struct rt6_info *f6i);
+
+static inline void fib6_info_hold(struct rt6_info *f6i)
+{
+ atomic_inc(&f6i->rt6i_ref);
+}
+
+static inline void fib6_info_release(struct rt6_info *f6i)
+{
+ if (f6i && atomic_dec_and_test(&f6i->rt6i_ref))
+ fib6_info_destroy(f6i);
+}
+
static inline void rt6_hold(struct rt6_info *rt)
{
atomic_inc(&rt->rt6i_ref);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index e27a01aa64f4..fe3ddbe36af4 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -145,6 +145,66 @@ static __be32 addr_bit_set(const void *token, int fn_bit)
addr[fn_bit >> 5];
}
+struct rt6_info *fib6_info_alloc(gfp_t gfp_flags)
+{
+ struct rt6_info *f6i;
+
+ f6i = kzalloc(sizeof(*f6i), gfp_flags);
+ if (!f6i)
+ return NULL;
+
+ f6i->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, gfp_flags);
+ if (!f6i->rt6i_pcpu) {
+ kfree(f6i);
+ return NULL;
+ }
+
+ INIT_LIST_HEAD(&f6i->rt6i_siblings);
+ f6i->fib6_metrics = (struct dst_metrics *)&dst_default_metrics;
+
+ atomic_inc(&f6i->rt6i_ref);
+
+ return f6i;
+}
+
+void fib6_info_destroy(struct rt6_info *f6i)
+{
+ struct rt6_exception_bucket *bucket;
+
+ WARN_ON(f6i->rt6i_node);
+
+ bucket = rcu_dereference_protected(f6i->rt6i_exception_bucket, 1);
+ if (bucket) {
+ f6i->rt6i_exception_bucket = NULL;
+ kfree(bucket);
+ }
+
+ if (f6i->rt6i_pcpu) {
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ struct rt6_info **ppcpu_rt;
+ struct rt6_info *pcpu_rt;
+
+ ppcpu_rt = per_cpu_ptr(f6i->rt6i_pcpu, cpu);
+ pcpu_rt = *ppcpu_rt;
+ if (pcpu_rt) {
+ dst_dev_put(&pcpu_rt->dst);
+ dst_release(&pcpu_rt->dst);
+ *ppcpu_rt = NULL;
+ }
+ }
+ }
+
+ if (f6i->rt6i_idev)
+ in6_dev_put(f6i->rt6i_idev);
+ if (f6i->fib6_nh.nh_dev)
+ dev_put(f6i->fib6_nh.nh_dev);
+
+ kfree(f6i);
+}
+EXPORT_SYMBOL_GPL(fib6_info_destroy);
+
static struct fib6_node *node_alloc(struct net *net)
{
struct fib6_node *fn;
--
2.11.0
^ permalink raw reply related
* [PATCH RFC v2 net-next 17/21] net/ipv6: Cleanup exception and cache route handling
From: David Ahern @ 2018-03-19 3:36 UTC (permalink / raw)
To: netdev
Cc: davem, idosch, roopa, eric.dumazet, weiwan, kafai, yoshfuji,
David Ahern
In-Reply-To: <20180319033622.16693-1-dsahern@gmail.com>
IPv6 FIB will only contain FIB entries with exception routes added to
the FIB entry. Once this transformation is complete, FIB lookups will
return a fib6_info with the lookup functions still returning a dst
based rt6_info. The current code uses rt6_info for both paths and
overloads the rt6_info variable usually called 'rt'.
This patch introduces a new 'f6i' variable name for the result of the FIB
lookup and keeps 'rt' as the dst based return variable. 'f6i' becomes a
fib6_info in a later patch which is why it is introduced as f6i now;
avoids the additional churn in the later patch.
In addition, remove RTF_CACHE and dst checks from fib6 add and delete
since they can not happen now and will never happen after the data
type flip.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/net/ip6_route.h | 1 -
net/ipv6/ip6_fib.c | 16 +-----
net/ipv6/route.c | 137 ++++++++++++++++++++++++++----------------------
3 files changed, 75 insertions(+), 79 deletions(-)
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 76d2c31e18b7..d722fa843f31 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -106,7 +106,6 @@ int ip6_ins_rt(struct net *net, struct rt6_info *rt);
int ip6_del_rt(struct net *net, struct rt6_info *rt);
void rt6_flush_exceptions(struct rt6_info *rt);
-int rt6_remove_exception_rt(struct rt6_info *rt);
void rt6_age_exceptions(struct rt6_info *rt, struct fib6_gc_args *gc_args,
unsigned long now);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 90df1589a6c2..e27a01aa64f4 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1065,7 +1065,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
static void fib6_start_gc(struct net *net, struct rt6_info *rt)
{
if (!timer_pending(&net->ipv6.ip6_fib_timer) &&
- (rt->rt6i_flags & (RTF_EXPIRES | RTF_CACHE)))
+ (rt->rt6i_flags & RTF_EXPIRES))
mod_timer(&net->ipv6.ip6_fib_timer,
jiffies + net->ipv6.sysctl.ip6_rt_gc_interval);
}
@@ -1116,8 +1116,6 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
if (WARN_ON_ONCE(!atomic_read(&rt->dst.__refcnt)))
return -EINVAL;
- if (WARN_ON_ONCE(rt->rt6i_flags & RTF_CACHE))
- return -EINVAL;
if (info->nlh) {
if (!(info->nlh->nlmsg_flags & NLM_F_CREATE))
@@ -1641,8 +1639,6 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
RT6_TRACE("fib6_del_route\n");
- WARN_ON_ONCE(rt->rt6i_flags & RTF_CACHE);
-
/* Unlink it */
*rtp = rt->rt6_next;
rt->rt6i_node = NULL;
@@ -1711,21 +1707,11 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info)
struct rt6_info __rcu **rtp;
struct rt6_info __rcu **rtp_next;
-#if RT6_DEBUG >= 2
- if (rt->dst.obsolete > 0) {
- WARN_ON(fn);
- return -ENOENT;
- }
-#endif
if (!fn || rt == net->ipv6.fib6_null_entry)
return -ENOENT;
WARN_ON(!(fn->fn_flags & RTN_RTINFO));
- /* remove cached dst from exception table */
- if (rt->rt6i_flags & RTF_CACHE)
- return rt6_remove_exception_rt(rt);
-
/*
* Walk the leaf entries looking for ourself
*/
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index d14dbf5ff1db..8eda7d09729b 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1013,8 +1013,8 @@ static void rt6_set_from(struct rt6_info *rt, struct rt6_info *from)
BUG_ON(from->from);
rt->rt6i_flags &= ~RTF_EXPIRES;
- dst_hold(&from->dst);
- rt->from = from;
+ if (dst_hold_safe(&from->dst))
+ rt->from = from;
dst_init_metrics(&rt->dst, from->fib6_metrics->metrics, true);
if (from->fib6_metrics != &dst_default_metrics) {
rt->dst._metrics |= DST_METRICS_REFCOUNTED;
@@ -1098,42 +1098,36 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net,
const struct sk_buff *skb,
int flags)
{
- struct rt6_info *rt, *rt_cache;
+ struct rt6_info *f6i;
struct fib6_node *fn;
+ struct rt6_info *rt;
rcu_read_lock();
fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
restart:
- rt = rcu_dereference(fn->leaf);
- if (!rt) {
- rt = net->ipv6.fib6_null_entry;
+ f6i = rcu_dereference(fn->leaf);
+ if (!f6i) {
+ f6i = net->ipv6.fib6_null_entry;
} else {
- rt = rt6_device_match(net, rt, &fl6->saddr,
+ f6i = rt6_device_match(net, f6i, &fl6->saddr,
fl6->flowi6_oif, flags);
- if (rt->rt6i_nsiblings && fl6->flowi6_oif == 0)
- rt = rt6_multipath_select(net, rt, fl6, fl6->flowi6_oif,
- skb, flags);
+ if (f6i->rt6i_nsiblings && fl6->flowi6_oif == 0)
+ f6i = rt6_multipath_select(net, f6i, fl6,
+ fl6->flowi6_oif, skb, flags);
}
- if (rt == net->ipv6.fib6_null_entry) {
+ if (f6i == net->ipv6.fib6_null_entry) {
fn = fib6_backtrack(fn, &fl6->saddr);
if (fn)
goto restart;
}
+
/* Search through exception table */
- rt_cache = rt6_find_cached_rt(rt, &fl6->daddr, &fl6->saddr);
- if (rt_cache) {
- rt = rt_cache;
+ rt = rt6_find_cached_rt(f6i, &fl6->daddr, &fl6->saddr);
+ if (rt) {
if (ip6_hold_safe(net, &rt, true))
dst_use_noref(&rt->dst, jiffies);
- } else if (dst_hold_safe(&rt->dst)) {
- struct rt6_info *nrt;
-
- nrt = ip6_create_rt_rcu(rt);
- dst_release(&rt->dst);
- rt = nrt;
} else {
- rt = net->ipv6.ip6_null_entry;
- dst_hold(&rt->dst);
+ rt = ip6_create_rt_rcu(f6i);
}
rcu_read_unlock();
@@ -1216,9 +1210,6 @@ static struct rt6_info *ip6_rt_cache_alloc(struct rt6_info *ort,
* Clone the route.
*/
- if (ort->rt6i_flags & (RTF_CACHE | RTF_PCPU))
- ort = ort->from;
-
rcu_read_lock();
dev = ip6_rt_get_dev_rcu(ort);
rt = __ip6_dst_alloc(dev_net(dev), dev, 0);
@@ -1444,11 +1435,6 @@ static int rt6_insert_exception(struct rt6_info *nrt,
struct rt6_exception *rt6_ex;
int err = 0;
- /* ort can't be a cache or pcpu route */
- if (ort->rt6i_flags & (RTF_CACHE | RTF_PCPU))
- ort = ort->from;
- WARN_ON_ONCE(ort->rt6i_flags & (RTF_CACHE | RTF_PCPU));
-
spin_lock_bh(&rt6_exception_lock);
if (ort->exception_bucket_flushed) {
@@ -1587,7 +1573,7 @@ static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt,
}
/* Remove the passed in cached rt from the hash table that contains it */
-int rt6_remove_exception_rt(struct rt6_info *rt)
+static int rt6_remove_exception_rt(struct rt6_info *rt)
{
struct rt6_exception_bucket *bucket;
struct rt6_info *from = rt->from;
@@ -1828,7 +1814,8 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
const struct sk_buff *skb, int flags)
{
struct fib6_node *fn, *saved_fn;
- struct rt6_info *rt, *rt_cache;
+ struct rt6_info *f6i;
+ struct rt6_info *rt;
int strict = 0;
strict |= flags & RT6_LOOKUP_F_IFACE;
@@ -1845,10 +1832,10 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
oif = 0;
redo_rt6_select:
- rt = rt6_select(net, fn, oif, strict);
- if (rt->rt6i_nsiblings)
- rt = rt6_multipath_select(net, rt, fl6, oif, skb, strict);
- if (rt == net->ipv6.fib6_null_entry) {
+ f6i = rt6_select(net, fn, oif, strict);
+ if (f6i->rt6i_nsiblings)
+ f6i = rt6_multipath_select(net, f6i, fl6, oif, skb, strict);
+ if (f6i == net->ipv6.fib6_null_entry) {
fn = fib6_backtrack(fn, &fl6->saddr);
if (fn)
goto redo_rt6_select;
@@ -1860,18 +1847,17 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
}
}
- /*Search through exception table */
- rt_cache = rt6_find_cached_rt(rt, &fl6->daddr, &fl6->saddr);
- if (rt_cache)
- rt = rt_cache;
-
- if (rt == net->ipv6.fib6_null_entry) {
+ if (f6i == net->ipv6.fib6_null_entry) {
rt = net->ipv6.ip6_null_entry;
rcu_read_unlock();
dst_hold(&rt->dst);
trace_fib6_table_lookup(net, rt, table, fl6);
return rt;
- } else if (rt->rt6i_flags & RTF_CACHE) {
+ }
+
+ /*Search through exception table */
+ rt = rt6_find_cached_rt(f6i, &fl6->daddr, &fl6->saddr);
+ if (rt) {
if (ip6_hold_safe(net, &rt, true))
dst_use_noref(&rt->dst, jiffies);
@@ -1879,7 +1865,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
trace_fib6_table_lookup(net, rt, table, fl6);
return rt;
} else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) &&
- !(rt->rt6i_flags & RTF_GATEWAY))) {
+ !(f6i->rt6i_flags & RTF_GATEWAY))) {
/* Create a RTF_CACHE clone which will not be
* owned by the fib6 tree. It is for the special case where
* the daddr in the skb during the neighbor look-up is different
@@ -1888,16 +1874,16 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
struct rt6_info *uncached_rt;
- if (ip6_hold_safe(net, &rt, true)) {
- dst_use_noref(&rt->dst, jiffies);
+ if (ip6_hold_safe(net, &f6i, true)) {
+ dst_use_noref(&f6i->dst, jiffies);
} else {
rcu_read_unlock();
- uncached_rt = rt;
+ uncached_rt = f6i;
goto uncached_rt_out;
}
rcu_read_unlock();
- uncached_rt = ip6_rt_cache_alloc(rt, &fl6->daddr, NULL);
+ uncached_rt = ip6_rt_cache_alloc(f6i, &fl6->daddr, NULL);
dst_release(&rt->dst);
if (uncached_rt) {
@@ -1920,18 +1906,18 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
struct rt6_info *pcpu_rt;
- dst_use_noref(&rt->dst, jiffies);
+ dst_use_noref(&f6i->dst, jiffies);
local_bh_disable();
- pcpu_rt = rt6_get_pcpu_route(rt);
+ pcpu_rt = rt6_get_pcpu_route(f6i);
if (!pcpu_rt) {
/* atomic_inc_not_zero() is needed when using rcu */
- if (atomic_inc_not_zero(&rt->rt6i_ref)) {
+ if (atomic_inc_not_zero(&f6i->rt6i_ref)) {
/* No dst_hold() on rt is needed because grabbing
* rt->rt6i_ref makes sure rt can't be released.
*/
- pcpu_rt = rt6_make_pcpu_route(net, rt);
- rt6_release(rt);
+ pcpu_rt = rt6_make_pcpu_route(net, f6i);
+ rt6_release(f6i);
} else {
/* rt is already removed from tree */
pcpu_rt = net->ipv6.ip6_null_entry;
@@ -2376,7 +2362,8 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
int flags)
{
struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6;
- struct rt6_info *rt, *rt_cache;
+ struct rt6_info *ret = NULL, *rt_cache;
+ struct rt6_info *rt;
struct fib6_node *fn;
/* Get the "current" route for this destination and
@@ -2415,7 +2402,7 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
if (rt_cache &&
ipv6_addr_equal(&rdfl->gateway,
&rt_cache->rt6i_gateway)) {
- rt = rt_cache;
+ ret = rt_cache;
break;
}
continue;
@@ -2426,7 +2413,7 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
if (!rt)
rt = net->ipv6.fib6_null_entry;
else if (rt->rt6i_flags & RTF_REJECT) {
- rt = net->ipv6.ip6_null_entry;
+ ret = net->ipv6.ip6_null_entry;
goto out;
}
@@ -2437,12 +2424,15 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
}
out:
- ip6_hold_safe(net, &rt, true);
+ if (ret)
+ dst_hold(&ret->dst);
+ else
+ ret = ip6_create_rt_rcu(rt);
rcu_read_unlock();
- trace_fib6_table_lookup(net, rt, table, fl6);
- return rt;
+ trace_fib6_table_lookup(net, ret, table, fl6);
+ return ret;
};
static struct dst_entry *ip6_route_redirect(struct net *net,
@@ -3133,6 +3123,22 @@ static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg)
return err;
}
+static int ip6_del_cached_rt(struct rt6_info *rt, struct fib6_config *cfg)
+{
+ int rc = -ESRCH;
+
+ if (cfg->fc_ifindex && rt->dst.dev->ifindex != cfg->fc_ifindex)
+ goto out;
+
+ if (cfg->fc_flags & RTF_GATEWAY &&
+ !ipv6_addr_equal(&cfg->fc_gateway, &rt->rt6i_gateway))
+ goto out;
+ if (dst_hold_safe(&rt->dst))
+ rc = rt6_remove_exception_rt(rt);
+out:
+ return rc;
+}
+
static int ip6_route_del(struct fib6_config *cfg,
struct netlink_ext_ack *extack)
{
@@ -3157,11 +3163,16 @@ static int ip6_route_del(struct fib6_config *cfg,
if (fn) {
for_each_fib6_node_rt_rcu(fn) {
if (cfg->fc_flags & RTF_CACHE) {
+ int rc;
+
rt_cache = rt6_find_cached_rt(rt, &cfg->fc_dst,
&cfg->fc_src);
- if (!rt_cache)
- continue;
- rt = rt_cache;
+ if (rt_cache) {
+ rc = ip6_del_cached_rt(rt_cache, cfg);
+ if (rc != -ESRCH)
+ return rc;
+ }
+ continue;
}
if (cfg->fc_ifindex &&
(!rt->fib6_nh.nh_dev ||
@@ -3278,7 +3289,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
NEIGH_UPDATE_F_ISROUTER)),
NDISC_REDIRECT, &ndopts);
- nrt = ip6_rt_cache_alloc(rt, &msg->dest, NULL);
+ nrt = ip6_rt_cache_alloc(rt->from, &msg->dest, NULL);
if (!nrt)
goto out;
--
2.11.0
^ permalink raw reply related
* [PATCH RFC v2 net-next 16/21] net/ipv6: Add gfp_flags to route add functions
From: David Ahern @ 2018-03-19 3:36 UTC (permalink / raw)
To: netdev
Cc: davem, idosch, roopa, eric.dumazet, weiwan, kafai, yoshfuji,
David Ahern
In-Reply-To: <20180319033622.16693-1-dsahern@gmail.com>
Most FIB entries can be added using memory allocated with GFP_KERNEL.
Add gfp_flags to ip6_route_add and addrconf_dst_alloc. Code paths that
can be reached from the packet path (e.g., ndisc and autoconfig) or
atomic notifiers use GFP_ATOMIC; paths from user context (adding
addresses and routes) use GFP_KERNEL.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/net/ip6_route.h | 6 ++++--
net/ipv6/addrconf.c | 39 +++++++++++++++++++++++----------------
net/ipv6/anycast.c | 2 +-
net/ipv6/route.c | 18 ++++++++++--------
4 files changed, 38 insertions(+), 27 deletions(-)
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 8e50e9f10158..76d2c31e18b7 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -100,7 +100,8 @@ void ip6_route_cleanup(void);
int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg);
-int ip6_route_add(struct fib6_config *cfg, struct netlink_ext_ack *extack);
+int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags,
+ struct netlink_ext_ack *extack);
int ip6_ins_rt(struct net *net, struct rt6_info *rt);
int ip6_del_rt(struct net *net, struct rt6_info *rt);
@@ -138,7 +139,8 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, struct flowi6 *fl6);
void fib6_force_start_gc(struct net *net);
struct rt6_info *addrconf_dst_alloc(struct net *net, struct inet6_dev *idev,
- const struct in6_addr *addr, bool anycast);
+ const struct in6_addr *addr, bool anycast,
+ gfp_t gfp_flags);
struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev,
int flags);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 5772c71ef610..de485b0a90d5 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1049,7 +1049,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
goto out;
}
- rt = addrconf_dst_alloc(net, idev, addr, false);
+ rt = addrconf_dst_alloc(net, idev, addr, false, gfp_flags);
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
rt = NULL;
@@ -2332,7 +2332,7 @@ static void ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpad
static void
addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev,
- unsigned long expires, u32 flags)
+ unsigned long expires, u32 flags, gfp_t gfp_flags)
{
struct fib6_config cfg = {
.fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_PREFIX,
@@ -2357,7 +2357,7 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev,
cfg.fc_flags |= RTF_NONEXTHOP;
#endif
- ip6_route_add(&cfg, NULL);
+ ip6_route_add(&cfg, gfp_flags, NULL);
}
@@ -2413,7 +2413,7 @@ static void addrconf_add_mroute(struct net_device *dev)
ipv6_addr_set(&cfg.fc_dst, htonl(0xFF000000), 0, 0, 0);
- ip6_route_add(&cfg, NULL);
+ ip6_route_add(&cfg, GFP_ATOMIC, NULL);
}
static struct inet6_dev *addrconf_add_dev(struct net_device *dev)
@@ -2698,7 +2698,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
expires = jiffies_to_clock_t(rt_expires);
}
addrconf_prefix_route(&pinfo->prefix, pinfo->prefix_len,
- dev, expires, flags);
+ dev, expires, flags, GFP_ATOMIC);
}
ip6_rt_put(rt);
}
@@ -2913,7 +2913,7 @@ static int inet6_addr_add(struct net *net, int ifindex,
if (!IS_ERR(ifp)) {
if (!(ifa_flags & IFA_F_NOPREFIXROUTE)) {
addrconf_prefix_route(&ifp->addr, ifp->prefix_len, dev,
- expires, flags);
+ expires, flags, GFP_KERNEL);
}
/*
@@ -3061,7 +3061,8 @@ static void sit_add_v4_addrs(struct inet6_dev *idev)
if (addr.s6_addr32[3]) {
add_addr(idev, &addr, plen, scope);
- addrconf_prefix_route(&addr, plen, idev->dev, 0, pflags);
+ addrconf_prefix_route(&addr, plen, idev->dev, 0, pflags,
+ GFP_ATOMIC);
return;
}
@@ -3086,7 +3087,7 @@ static void sit_add_v4_addrs(struct inet6_dev *idev)
add_addr(idev, &addr, plen, flag);
addrconf_prefix_route(&addr, plen, idev->dev, 0,
- pflags);
+ pflags, GFP_ATOMIC);
}
}
}
@@ -3126,7 +3127,8 @@ void addrconf_add_linklocal(struct inet6_dev *idev,
ifp = ipv6_add_addr(idev, addr, NULL, 64, IFA_LINK, addr_flags,
INFINITY_LIFE_TIME, INFINITY_LIFE_TIME, true, NULL);
if (!IS_ERR(ifp)) {
- addrconf_prefix_route(&ifp->addr, ifp->prefix_len, idev->dev, 0, 0);
+ addrconf_prefix_route(&ifp->addr, ifp->prefix_len, idev->dev,
+ 0, 0, GFP_ATOMIC);
addrconf_dad_start(ifp);
in6_ifa_put(ifp);
}
@@ -3241,7 +3243,8 @@ static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route)
addrconf_add_linklocal(idev, &addr,
IFA_F_STABLE_PRIVACY);
else if (prefix_route)
- addrconf_prefix_route(&addr, 64, idev->dev, 0, 0);
+ addrconf_prefix_route(&addr, 64, idev->dev,
+ 0, 0, GFP_KERNEL);
break;
case IN6_ADDR_GEN_MODE_EUI64:
/* addrconf_add_linklocal also adds a prefix_route and we
@@ -3251,7 +3254,8 @@ static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route)
if (ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) == 0)
addrconf_add_linklocal(idev, &addr, 0);
else if (prefix_route)
- addrconf_prefix_route(&addr, 64, idev->dev, 0, 0);
+ addrconf_prefix_route(&addr, 64, idev->dev,
+ 0, 0, GFP_ATOMIC);
break;
case IN6_ADDR_GEN_MODE_NONE:
default:
@@ -3354,7 +3358,8 @@ static int fixup_permanent_addr(struct net *net,
if (!ifp->rt || !ifp->rt->rt6i_node) {
struct rt6_info *rt, *prev;
- rt = addrconf_dst_alloc(net, idev, &ifp->addr, false);
+ rt = addrconf_dst_alloc(net, idev, &ifp->addr, false,
+ GFP_ATOMIC);
if (IS_ERR(rt))
return PTR_ERR(rt);
@@ -3369,7 +3374,7 @@ static int fixup_permanent_addr(struct net *net,
if (!(ifp->flags & IFA_F_NOPREFIXROUTE)) {
addrconf_prefix_route(&ifp->addr, ifp->prefix_len,
- idev->dev, 0, 0);
+ idev->dev, 0, 0, GFP_ATOMIC);
}
if (ifp->state == INET6_IFADDR_STATE_PREDAD)
@@ -4581,8 +4586,9 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags,
ipv6_ifa_notify(0, ifp);
if (!(ifa_flags & IFA_F_NOPREFIXROUTE)) {
- addrconf_prefix_route(&ifp->addr, ifp->prefix_len, ifp->idev->dev,
- expires, flags);
+ addrconf_prefix_route(&ifp->addr, ifp->prefix_len,
+ ifp->idev->dev, expires, flags,
+ GFP_KERNEL);
} else if (had_prefixroute) {
enum cleanup_prefix_rt_t action;
unsigned long rt_expires;
@@ -5631,7 +5637,8 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
addrconf_join_anycast(ifp);
if (!ipv6_addr_any(&ifp->peer_addr))
addrconf_prefix_route(&ifp->peer_addr, 128,
- ifp->idev->dev, 0, 0);
+ ifp->idev->dev, 0, 0,
+ GFP_KERNEL);
break;
case RTM_DELADDR:
if (ifp->idev->cnf.forwarding)
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index 7ecdbabb16dd..1d9ccc815e0b 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -267,7 +267,7 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr)
}
net = dev_net(idev->dev);
- rt = addrconf_dst_alloc(net, idev, addr, true);
+ rt = addrconf_dst_alloc(net, idev, addr, true, GFP_ATOMIC);
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
goto out;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 0eadef74c815..d14dbf5ff1db 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2823,6 +2823,7 @@ static int ip6_validate_gw(struct net *net, struct fib6_config *cfg,
}
static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg,
+ gfp_t gfp_flags,
struct netlink_ext_ack *extack)
{
struct net *net = cfg->fc_nlinfo.nl_net;
@@ -3037,12 +3038,13 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg,
return ERR_PTR(err);
}
-int ip6_route_add(struct fib6_config *cfg, struct netlink_ext_ack *extack)
+int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags,
+ struct netlink_ext_ack *extack)
{
struct rt6_info *rt;
int err;
- rt = ip6_route_info_create(cfg, extack);
+ rt = ip6_route_info_create(cfg, gfp_flags, extack);
if (IS_ERR(rt))
return PTR_ERR(rt);
@@ -3369,7 +3371,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net,
if (!prefixlen)
cfg.fc_flags |= RTF_DEFAULT;
- ip6_route_add(&cfg, NULL);
+ ip6_route_add(&cfg, GFP_ATOMIC, NULL);
return rt6_get_route_info(net, prefix, prefixlen, gwaddr, dev);
}
@@ -3420,7 +3422,7 @@ struct rt6_info *rt6_add_dflt_router(struct net *net,
cfg.fc_gateway = *gwaddr;
- if (!ip6_route_add(&cfg, NULL)) {
+ if (!ip6_route_add(&cfg, GFP_ATOMIC, NULL)) {
struct fib6_table *table;
table = fib6_get_table(dev_net(dev), cfg.fc_table);
@@ -3518,7 +3520,7 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg)
rtnl_lock();
switch (cmd) {
case SIOCADDRT:
- err = ip6_route_add(&cfg, NULL);
+ err = ip6_route_add(&cfg, GFP_KERNEL, NULL);
break;
case SIOCDELRT:
err = ip6_route_del(&cfg, NULL);
@@ -3590,7 +3592,7 @@ static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff
struct rt6_info *addrconf_dst_alloc(struct net *net,
struct inet6_dev *idev,
const struct in6_addr *addr,
- bool anycast)
+ bool anycast, gfp_t gfp_flags)
{
u32 tb_id;
struct net_device *dev = idev->dev;
@@ -4251,7 +4253,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
r_cfg.fc_encap_type = nla_get_u16(nla);
}
- rt = ip6_route_info_create(&r_cfg, extack);
+ rt = ip6_route_info_create(&r_cfg, GFP_KERNEL, extack);
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
rt = NULL;
@@ -4404,7 +4406,7 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
if (cfg.fc_mp)
return ip6_route_multipath_add(&cfg, extack);
else
- return ip6_route_add(&cfg, extack);
+ return ip6_route_add(&cfg, GFP_KERNEL, extack);
}
static size_t rt6_nlmsg_size(struct rt6_info *rt)
--
2.11.0
^ permalink raw reply related
* [PATCH RFC v2 net-next 15/21] net/ipv6: Create a neigh_lookup for FIB entries
From: David Ahern @ 2018-03-19 3:36 UTC (permalink / raw)
To: netdev
Cc: davem, idosch, roopa, eric.dumazet, weiwan, kafai, yoshfuji,
David Ahern
In-Reply-To: <20180319033622.16693-1-dsahern@gmail.com>
The router discovery code has a FIB entry and wants to validate the
gateway has a neighbor entry. Refactor the existing dst_neigh_lookup
for IPv6 and create a new function that takes the gateway and device
and returns a neighbor entry. Use the new function in
ndisc_router_discovery to validate the gateway.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/net/ip6_route.h | 3 +++
net/ipv6/ndisc.c | 8 ++++++--
net/ipv6/route.c | 33 ++++++++++++++++++++-------------
3 files changed, 29 insertions(+), 15 deletions(-)
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 8b07c3fcd32d..8e50e9f10158 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -273,4 +273,7 @@ static inline bool rt6_duplicate_nexthop(struct rt6_info *a, struct rt6_info *b)
!lwtunnel_cmp_encap(a->fib6_nh.nh_lwtstate, b->fib6_nh.nh_lwtstate);
}
+struct neighbour *ip6_neigh_lookup(const struct in6_addr *gw,
+ struct net_device *dev, struct sk_buff *skb,
+ const void *daddr);
#endif
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 848f518d48d4..9ae194cb400a 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1276,7 +1276,9 @@ static void ndisc_router_discovery(struct sk_buff *skb)
rt = rt6_get_dflt_router(net, &ipv6_hdr(skb)->saddr, skb->dev);
if (rt) {
- neigh = dst_neigh_lookup(&rt->dst, &ipv6_hdr(skb)->saddr);
+ neigh = ip6_neigh_lookup(&rt->fib6_nh.nh_gw,
+ rt->fib6_nh.nh_dev, NULL,
+ &ipv6_hdr(skb)->saddr);
if (!neigh) {
ND_PRINTK(0, err,
"RA: %s got default router without neighbour\n",
@@ -1304,7 +1306,9 @@ static void ndisc_router_discovery(struct sk_buff *skb)
return;
}
- neigh = dst_neigh_lookup(&rt->dst, &ipv6_hdr(skb)->saddr);
+ neigh = ip6_neigh_lookup(&rt->fib6_nh.nh_gw,
+ rt->fib6_nh.nh_dev, NULL,
+ &ipv6_hdr(skb)->saddr);
if (!neigh) {
ND_PRINTK(0, err,
"RA: %s got default router without neighbour\n",
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index d2c146790d70..0eadef74c815 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -182,12 +182,10 @@ static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev)
}
}
-static inline const void *choose_neigh_daddr(struct rt6_info *rt,
+static inline const void *choose_neigh_daddr(const struct in6_addr *p,
struct sk_buff *skb,
const void *daddr)
{
- struct in6_addr *p = &rt->rt6i_gateway;
-
if (!ipv6_addr_any(p))
return (const void *) p;
else if (skb)
@@ -195,18 +193,27 @@ static inline const void *choose_neigh_daddr(struct rt6_info *rt,
return daddr;
}
-static struct neighbour *ip6_neigh_lookup(const struct dst_entry *dst,
- struct sk_buff *skb,
- const void *daddr)
+struct neighbour *ip6_neigh_lookup(const struct in6_addr *gw,
+ struct net_device *dev,
+ struct sk_buff *skb,
+ const void *daddr)
{
- struct rt6_info *rt = (struct rt6_info *) dst;
struct neighbour *n;
- daddr = choose_neigh_daddr(rt, skb, daddr);
- n = __ipv6_neigh_lookup(dst->dev, daddr);
+ daddr = choose_neigh_daddr(gw, skb, daddr);
+ n = __ipv6_neigh_lookup(dev, daddr);
if (n)
return n;
- return neigh_create(&nd_tbl, daddr, dst->dev);
+ return neigh_create(&nd_tbl, daddr, dev);
+}
+
+static struct neighbour *ip6_dst_neigh_lookup(const struct dst_entry *dst,
+ struct sk_buff *skb,
+ const void *daddr)
+{
+ const struct rt6_info *rt = container_of(dst, struct rt6_info, dst);
+
+ return ip6_neigh_lookup(&rt->rt6i_gateway, dst->dev, skb, daddr);
}
static void ip6_confirm_neigh(const struct dst_entry *dst, const void *daddr)
@@ -214,7 +221,7 @@ static void ip6_confirm_neigh(const struct dst_entry *dst, const void *daddr)
struct net_device *dev = dst->dev;
struct rt6_info *rt = (struct rt6_info *)dst;
- daddr = choose_neigh_daddr(rt, NULL, daddr);
+ daddr = choose_neigh_daddr(&rt->rt6i_gateway, NULL, daddr);
if (!daddr)
return;
if (dev->flags & (IFF_NOARP | IFF_LOOPBACK))
@@ -239,7 +246,7 @@ static struct dst_ops ip6_dst_ops_template = {
.update_pmtu = ip6_rt_update_pmtu,
.redirect = rt6_do_redirect,
.local_out = __ip6_local_out,
- .neigh_lookup = ip6_neigh_lookup,
+ .neigh_lookup = ip6_dst_neigh_lookup,
.confirm_neigh = ip6_confirm_neigh,
};
@@ -269,7 +276,7 @@ static struct dst_ops ip6_dst_blackhole_ops = {
.update_pmtu = ip6_rt_blackhole_update_pmtu,
.redirect = ip6_rt_blackhole_redirect,
.cow_metrics = dst_cow_metrics_generic,
- .neigh_lookup = ip6_neigh_lookup,
+ .neigh_lookup = ip6_dst_neigh_lookup,
};
static const u32 ip6_template_metrics[RTAX_MAX] = {
--
2.11.0
^ permalink raw reply related
* [PATCH RFC v2 net-next 14/21] net/ipv6: Move dst flags to booleans in fib entries
From: David Ahern @ 2018-03-19 3:36 UTC (permalink / raw)
To: netdev
Cc: davem, idosch, roopa, eric.dumazet, weiwan, kafai, yoshfuji,
David Ahern
In-Reply-To: <20180319033622.16693-1-dsahern@gmail.com>
Continuing to wean FIB paths off of dst_entry, use a bool to hold
requests for certain dst settings. Add a helper to convert the
flags to DST flags when a FIB entry is converted to a dst_entry.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/net/ip6_fib.h | 5 ++++-
net/ipv6/addrconf.c | 4 ++--
net/ipv6/route.c | 29 ++++++++++++++++++++++++-----
3 files changed, 30 insertions(+), 8 deletions(-)
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index c73b985734f5..159f651dee55 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -177,7 +177,10 @@ struct rt6_info {
u8 fib6_type;
u8 exception_bucket_flushed:1,
should_flush:1,
- unused:6;
+ dst_nocount:1,
+ dst_nopolicy:1,
+ dst_host:1,
+ unused:3;
unsigned long expires;
struct dst_metrics *fib6_metrics;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 23834864adb5..5772c71ef610 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1058,7 +1058,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
if (net->ipv6.devconf_all->disable_policy ||
idev->cnf.disable_policy)
- rt->dst.flags |= DST_NOPOLICY;
+ rt->dst_nopolicy = true;
neigh_parms_data_state_setall(idev->nd_parms);
@@ -5998,7 +5998,7 @@ void addrconf_disable_policy_idev(struct inet6_dev *idev, int val)
int cpu;
rcu_read_lock();
- addrconf_set_nopolicy(ifa->rt, val);
+ ifa->rt->dst_nopolicy = val ? true : false;
if (rt->rt6i_pcpu) {
for_each_possible_cpu(cpu) {
struct rt6_info **rtp;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 39fd9f88912f..d2c146790d70 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -937,6 +937,20 @@ static int ip6_rt_type_to_error(u8 fib6_type)
return fib6_prop[fib6_type];
}
+static unsigned short fib6_info_dst_flags(struct rt6_info *rt)
+{
+ unsigned short flags = 0;
+
+ if (rt->dst_nocount)
+ flags |= DST_NOCOUNT;
+ if (rt->dst_nopolicy)
+ flags |= DST_NOPOLICY;
+ if (rt->dst_host)
+ flags |= DST_HOST;
+
+ return flags;
+}
+
static void ip6_rt_init_dst_reject(struct rt6_info *rt, struct rt6_info *ort)
{
rt->dst.error = ip6_rt_type_to_error(ort->fib6_type);
@@ -961,6 +975,8 @@ static void ip6_rt_init_dst_reject(struct rt6_info *rt, struct rt6_info *ort)
static void ip6_rt_init_dst(struct rt6_info *rt, struct rt6_info *ort)
{
+ rt->dst.flags |= fib6_info_dst_flags(ort);
+
if (ort->rt6i_flags & RTF_REJECT) {
ip6_rt_init_dst_reject(rt, ort);
return;
@@ -970,7 +986,6 @@ static void ip6_rt_init_dst(struct rt6_info *rt, struct rt6_info *ort)
rt->dst.output = ip6_output;
if (ort->fib6_type == RTN_LOCAL) {
- rt->dst.flags |= DST_HOST;
rt->dst.input = ip6_input;
} else if (ipv6_addr_type(&ort->rt6i_dst.addr) & IPV6_ADDR_MULTICAST) {
rt->dst.input = ip6_mc_input;
@@ -1058,11 +1073,12 @@ static bool ip6_hold_safe(struct net *net, struct rt6_info **prt,
/* called with rcu_lock held */
static struct rt6_info *ip6_create_rt_rcu(struct rt6_info *rt)
{
+ unsigned short flags = fib6_info_dst_flags(rt);
struct net_device *dev;
struct rt6_info *nrt;
dev = ip6_rt_get_dev_rcu(rt);
- nrt = __ip6_dst_alloc(dev_net(dev), dev, 0);
+ nrt = __ip6_dst_alloc(dev_net(dev), dev, flags);
if (nrt)
ip6_rt_copy_init(nrt, rt);
@@ -1227,12 +1243,13 @@ static struct rt6_info *ip6_rt_cache_alloc(struct rt6_info *ort,
static struct rt6_info *ip6_rt_pcpu_alloc(struct rt6_info *rt)
{
+ unsigned short flags = fib6_info_dst_flags(rt);
struct net_device *dev;
struct rt6_info *pcpu_rt;
rcu_read_lock();
dev = ip6_rt_get_dev_rcu(rt);
- pcpu_rt = __ip6_dst_alloc(dev_net(dev), dev, rt->dst.flags);
+ pcpu_rt = __ip6_dst_alloc(dev_net(dev), dev, flags);
rcu_read_unlock();
if (!pcpu_rt)
return NULL;
@@ -2922,7 +2939,7 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg,
ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len);
rt->rt6i_dst.plen = cfg->fc_dst_len;
if (rt->rt6i_dst.plen == 128)
- rt->dst.flags |= DST_HOST;
+ rt->dst_host = true;
#ifdef CONFIG_IPV6_SUBTREES
ipv6_addr_prefix(&rt->rt6i_src.addr, &cfg->fc_src, cfg->fc_src_len);
@@ -3576,10 +3593,12 @@ struct rt6_info *addrconf_dst_alloc(struct net *net,
if (!rt)
return ERR_PTR(-ENOMEM);
+ rt->dst_nocount = true;
+
in6_dev_hold(idev);
rt->rt6i_idev = idev;
- rt->dst.flags |= DST_HOST;
+ rt->dst_host = true;
rt->rt6i_protocol = RTPROT_KERNEL;
rt->rt6i_flags = RTF_UP | RTF_NONEXTHOP;
if (anycast) {
--
2.11.0
^ permalink raw reply related
* [PATCH RFC v2 net-next 13/21] net/ipv6: Add rt6_info create function for ip6_pol_route_lookup
From: David Ahern @ 2018-03-19 3:36 UTC (permalink / raw)
To: netdev
Cc: davem, idosch, roopa, eric.dumazet, weiwan, kafai, yoshfuji,
David Ahern
In-Reply-To: <20180319033622.16693-1-dsahern@gmail.com>
ip6_pol_route_lookup is the lookup function for ip6_route_lookup and
rt6_lookup. At the moment it returns either a reference to a FIB entry
or a cached exception. To move FIB entries to a separate struct, this
lookup function needs to convert FIB entries to an rt6_info that is
returned to the caller.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
net/ipv6/route.c | 30 ++++++++++++++++++++++++++----
1 file changed, 26 insertions(+), 4 deletions(-)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 86ee78633697..39fd9f88912f 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1055,6 +1055,20 @@ static bool ip6_hold_safe(struct net *net, struct rt6_info **prt,
return false;
}
+/* called with rcu_lock held */
+static struct rt6_info *ip6_create_rt_rcu(struct rt6_info *rt)
+{
+ struct net_device *dev;
+ struct rt6_info *nrt;
+
+ dev = ip6_rt_get_dev_rcu(rt);
+ nrt = __ip6_dst_alloc(dev_net(dev), dev, 0);
+ if (nrt)
+ ip6_rt_copy_init(nrt, rt);
+
+ return nrt;
+}
+
static struct rt6_info *ip6_pol_route_lookup(struct net *net,
struct fib6_table *table,
struct flowi6 *fl6,
@@ -1084,18 +1098,26 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net,
}
/* Search through exception table */
rt_cache = rt6_find_cached_rt(rt, &fl6->daddr, &fl6->saddr);
- if (rt_cache)
+ if (rt_cache) {
rt = rt_cache;
+ if (ip6_hold_safe(net, &rt, true))
+ dst_use_noref(&rt->dst, jiffies);
+ } else if (dst_hold_safe(&rt->dst)) {
+ struct rt6_info *nrt;
- if (ip6_hold_safe(net, &rt, true))
- dst_use_noref(&rt->dst, jiffies);
+ nrt = ip6_create_rt_rcu(rt);
+ dst_release(&rt->dst);
+ rt = nrt;
+ } else {
+ rt = net->ipv6.ip6_null_entry;
+ dst_hold(&rt->dst);
+ }
rcu_read_unlock();
trace_fib6_table_lookup(net, rt, table, fl6);
return rt;
-
}
struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6,
--
2.11.0
^ permalink raw reply related
* [PATCH RFC v2 net-next 12/21] net/ipv6: Add fib6_null_entry
From: David Ahern @ 2018-03-19 3:36 UTC (permalink / raw)
To: netdev
Cc: davem, idosch, roopa, eric.dumazet, weiwan, kafai, yoshfuji,
David Ahern
In-Reply-To: <20180319033622.16693-1-dsahern@gmail.com>
ip6_null_entry will stay a dst based return for lookups that fail to
match an entry.
Add a new fib6_null_entry which constitutes the root node and leafs
for fibs. Replace existing references to ip6_null_entry with the
new fib6_null_entry when dealing with FIBs.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/net/netns/ipv6.h | 3 ++-
net/ipv6/ip6_fib.c | 26 ++++++++++----------
net/ipv6/route.c | 62 +++++++++++++++++++++++++++++++++---------------
3 files changed, 58 insertions(+), 33 deletions(-)
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index 5b51110435fc..7996b19c8a6d 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -60,7 +60,8 @@ struct netns_ipv6 {
#endif
struct xt_table *ip6table_nat;
#endif
- struct rt6_info *ip6_null_entry;
+ struct rt6_info *fib6_null_entry;
+ struct rt6_info *ip6_null_entry;
struct rt6_statistics *rt6_stats;
struct timer_list ip6_fib_timer;
struct hlist_head *fib_table_hash;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 70eca9cb551f..90df1589a6c2 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -231,7 +231,7 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id)
if (table) {
table->tb6_id = id;
rcu_assign_pointer(table->tb6_root.leaf,
- net->ipv6.ip6_null_entry);
+ net->ipv6.fib6_null_entry);
table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
inet_peer_base_init(&table->tb6_peers);
}
@@ -369,7 +369,7 @@ struct fib6_dump_arg {
static void fib6_rt_dump(struct rt6_info *rt, struct fib6_dump_arg *arg)
{
- if (rt == arg->net->ipv6.ip6_null_entry)
+ if (rt == arg->net->ipv6.fib6_null_entry)
return;
call_fib6_entry_notifier(arg->nb, arg->net, FIB_EVENT_ENTRY_ADD, rt);
}
@@ -658,7 +658,7 @@ static struct fib6_node *fib6_add_1(struct net *net,
/* remove null_entry in the root node */
} else if (fn->fn_flags & RTN_TL_ROOT &&
rcu_access_pointer(fn->leaf) ==
- net->ipv6.ip6_null_entry) {
+ net->ipv6.fib6_null_entry) {
RCU_INIT_POINTER(fn->leaf, NULL);
}
@@ -1162,9 +1162,9 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
if (!sfn)
goto failure;
- atomic_inc(&info->nl_net->ipv6.ip6_null_entry->rt6i_ref);
+ atomic_inc(&info->nl_net->ipv6.fib6_null_entry->rt6i_ref);
rcu_assign_pointer(sfn->leaf,
- info->nl_net->ipv6.ip6_null_entry);
+ info->nl_net->ipv6.fib6_null_entry);
sfn->fn_flags = RTN_ROOT;
/* Now add the first leaf node to new subtree */
@@ -1203,7 +1203,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
if (fn->fn_flags & RTN_TL_ROOT) {
/* put back null_entry for root node */
rcu_assign_pointer(fn->leaf,
- info->nl_net->ipv6.ip6_null_entry);
+ info->nl_net->ipv6.fib6_null_entry);
} else {
atomic_inc(&rt->rt6i_ref);
rcu_assign_pointer(fn->leaf, rt);
@@ -1242,7 +1242,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
if (!pn_leaf) {
WARN_ON(!pn_leaf);
pn_leaf =
- info->nl_net->ipv6.ip6_null_entry;
+ info->nl_net->ipv6.fib6_null_entry;
}
#endif
atomic_inc(&pn_leaf->rt6i_ref);
@@ -1485,7 +1485,7 @@ static struct rt6_info *fib6_find_prefix(struct net *net,
struct fib6_node *child_left, *child_right;
if (fn->fn_flags & RTN_ROOT)
- return net->ipv6.ip6_null_entry;
+ return net->ipv6.fib6_null_entry;
while (fn) {
child_left = rcu_dereference_protected(fn->left,
@@ -1522,7 +1522,7 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
/* Set fn->leaf to null_entry for root node. */
if (fn->fn_flags & RTN_TL_ROOT) {
- rcu_assign_pointer(fn->leaf, net->ipv6.ip6_null_entry);
+ rcu_assign_pointer(fn->leaf, net->ipv6.fib6_null_entry);
return fn;
}
@@ -1567,7 +1567,7 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
#if RT6_DEBUG >= 2
if (!new_fn_leaf) {
WARN_ON(!new_fn_leaf);
- new_fn_leaf = net->ipv6.ip6_null_entry;
+ new_fn_leaf = net->ipv6.fib6_null_entry;
}
#endif
atomic_inc(&new_fn_leaf->rt6i_ref);
@@ -1717,7 +1717,7 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info)
return -ENOENT;
}
#endif
- if (!fn || rt == net->ipv6.ip6_null_entry)
+ if (!fn || rt == net->ipv6.fib6_null_entry)
return -ENOENT;
WARN_ON(!(fn->fn_flags & RTN_RTINFO));
@@ -2078,7 +2078,7 @@ static int __net_init fib6_net_init(struct net *net)
net->ipv6.fib6_main_tbl->tb6_id = RT6_TABLE_MAIN;
rcu_assign_pointer(net->ipv6.fib6_main_tbl->tb6_root.leaf,
- net->ipv6.ip6_null_entry);
+ net->ipv6.fib6_null_entry);
net->ipv6.fib6_main_tbl->tb6_root.fn_flags =
RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
inet_peer_base_init(&net->ipv6.fib6_main_tbl->tb6_peers);
@@ -2090,7 +2090,7 @@ static int __net_init fib6_net_init(struct net *net)
goto out_fib6_main_tbl;
net->ipv6.fib6_local_tbl->tb6_id = RT6_TABLE_LOCAL;
rcu_assign_pointer(net->ipv6.fib6_local_tbl->tb6_root.leaf,
- net->ipv6.ip6_null_entry);
+ net->ipv6.fib6_null_entry);
net->ipv6.fib6_local_tbl->tb6_root.fn_flags =
RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
inet_peer_base_init(&net->ipv6.fib6_local_tbl->tb6_peers);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index fc3ddcbe8899..86ee78633697 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -276,6 +276,15 @@ static const u32 ip6_template_metrics[RTAX_MAX] = {
[RTAX_HOPLIMIT - 1] = 0,
};
+static const struct rt6_info fib6_null_entry_template = {
+ .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP),
+ .rt6i_protocol = RTPROT_KERNEL,
+ .rt6i_metric = ~(u32)0,
+ .rt6i_ref = ATOMIC_INIT(1),
+ .fib6_type = RTN_UNREACHABLE,
+ .fib6_metrics = (struct dst_metrics *)&dst_default_metrics,
+};
+
static const struct rt6_info ip6_null_entry_template = {
.dst = {
.__refcnt = ATOMIC_INIT(1),
@@ -522,10 +531,10 @@ static inline struct rt6_info *rt6_device_match(struct net *net,
return local;
if (flags & RT6_LOOKUP_F_IFACE)
- return net->ipv6.ip6_null_entry;
+ return net->ipv6.fib6_null_entry;
}
- return rt->fib6_nh.nh_flags & RTNH_F_DEAD ? net->ipv6.ip6_null_entry : rt;
+ return rt->fib6_nh.nh_flags & RTNH_F_DEAD ? net->ipv6.fib6_null_entry : rt;
}
#ifdef CONFIG_IPV6_ROUTER_PREF
@@ -758,8 +767,8 @@ static struct rt6_info *rt6_select(struct net *net, struct fib6_node *fn,
bool do_rr = false;
int key_plen;
- if (!leaf || leaf == net->ipv6.ip6_null_entry)
- return net->ipv6.ip6_null_entry;
+ if (!leaf || leaf == net->ipv6.fib6_null_entry)
+ return net->ipv6.fib6_null_entry;
rt0 = rcu_dereference(fn->rr_ptr);
if (!rt0)
@@ -776,7 +785,7 @@ static struct rt6_info *rt6_select(struct net *net, struct fib6_node *fn,
key_plen = rt0->rt6i_src.plen;
#endif
if (fn->fn_bit != key_plen)
- return net->ipv6.ip6_null_entry;
+ return net->ipv6.fib6_null_entry;
match = find_rr_leaf(fn, leaf, rt0, rt0->rt6i_metric, oif, strict,
&do_rr);
@@ -797,7 +806,7 @@ static struct rt6_info *rt6_select(struct net *net, struct fib6_node *fn,
}
}
- return match ? match : net->ipv6.ip6_null_entry;
+ return match ? match : net->ipv6.fib6_null_entry;
}
static bool rt6_is_gw_or_nonexthop(const struct rt6_info *rt)
@@ -1060,7 +1069,7 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net,
restart:
rt = rcu_dereference(fn->leaf);
if (!rt) {
- rt = net->ipv6.ip6_null_entry;
+ rt = net->ipv6.fib6_null_entry;
} else {
rt = rt6_device_match(net, rt, &fl6->saddr,
fl6->flowi6_oif, flags);
@@ -1068,7 +1077,7 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net,
rt = rt6_multipath_select(net, rt, fl6, fl6->flowi6_oif,
skb, flags);
}
- if (rt == net->ipv6.ip6_null_entry) {
+ if (rt == net->ipv6.fib6_null_entry) {
fn = fib6_backtrack(fn, &fl6->saddr);
if (fn)
goto restart;
@@ -1793,7 +1802,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
rt = rt6_select(net, fn, oif, strict);
if (rt->rt6i_nsiblings)
rt = rt6_multipath_select(net, rt, fl6, oif, skb, strict);
- if (rt == net->ipv6.ip6_null_entry) {
+ if (rt == net->ipv6.fib6_null_entry) {
fn = fib6_backtrack(fn, &fl6->saddr);
if (fn)
goto redo_rt6_select;
@@ -1810,7 +1819,8 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
if (rt_cache)
rt = rt_cache;
- if (rt == net->ipv6.ip6_null_entry) {
+ if (rt == net->ipv6.fib6_null_entry) {
+ rt = net->ipv6.ip6_null_entry;
rcu_read_unlock();
dst_hold(&rt->dst);
trace_fib6_table_lookup(net, rt, table, fl6);
@@ -2368,13 +2378,13 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
}
if (!rt)
- rt = net->ipv6.ip6_null_entry;
+ rt = net->ipv6.fib6_null_entry;
else if (rt->rt6i_flags & RTF_REJECT) {
rt = net->ipv6.ip6_null_entry;
goto out;
}
- if (rt == net->ipv6.ip6_null_entry) {
+ if (rt == net->ipv6.fib6_null_entry) {
fn = fib6_backtrack(fn, &fl6->saddr);
if (fn)
goto restart;
@@ -3001,7 +3011,7 @@ static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info)
struct fib6_table *table;
int err;
- if (rt == net->ipv6.ip6_null_entry) {
+ if (rt == net->ipv6.fib6_null_entry) {
err = -ENOENT;
goto out;
}
@@ -3031,7 +3041,7 @@ static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg)
struct fib6_table *table;
int err = -ENOENT;
- if (rt == net->ipv6.ip6_null_entry)
+ if (rt == net->ipv6.fib6_null_entry)
goto out_put;
table = rt->rt6i_table;
spin_lock_bh(&table->tb6_lock);
@@ -3583,7 +3593,7 @@ static int fib6_remove_prefsrc(struct rt6_info *rt, void *arg)
struct in6_addr *addr = ((struct arg_dev_net_ip *)arg)->addr;
if (((void *)rt->fib6_nh.nh_dev == dev || !dev) &&
- rt != net->ipv6.ip6_null_entry &&
+ rt != net->ipv6.fib6_null_entry &&
ipv6_addr_equal(addr, &rt->rt6i_prefsrc.addr)) {
spin_lock_bh(&rt6_exception_lock);
/* remove prefsrc entry */
@@ -3738,7 +3748,7 @@ static int fib6_ifup(struct rt6_info *rt, void *p_arg)
const struct arg_netdev_event *arg = p_arg;
struct net *net = dev_net(arg->dev);
- if (rt != net->ipv6.ip6_null_entry && rt->fib6_nh.nh_dev == arg->dev) {
+ if (rt != net->ipv6.fib6_null_entry && rt->fib6_nh.nh_dev == arg->dev) {
rt->fib6_nh.nh_flags &= ~arg->nh_flags;
fib6_update_sernum_upto_root(net, rt);
rt6_multipath_rebalance(rt);
@@ -3822,7 +3832,7 @@ static int fib6_ifdown(struct rt6_info *rt, void *p_arg)
const struct net_device *dev = arg->dev;
struct net *net = dev_net(dev);
- if (rt == net->ipv6.ip6_null_entry)
+ if (rt == net->ipv6.fib6_null_entry)
return 0;
switch (arg->event) {
@@ -4579,7 +4589,7 @@ int rt6_dump_route(struct rt6_info *rt, void *p_arg)
struct rt6_rtnl_dump_arg *arg = (struct rt6_rtnl_dump_arg *) p_arg;
struct net *net = arg->net;
- if (rt == net->ipv6.ip6_null_entry)
+ if (rt == net->ipv6.fib6_null_entry)
return 0;
if (nlmsg_len(arg->cb->nlh) >= sizeof(struct rtmsg)) {
@@ -4768,6 +4778,8 @@ static int ip6_route_dev_notify(struct notifier_block *this,
return NOTIFY_OK;
if (event == NETDEV_REGISTER) {
+ net->ipv6.fib6_null_entry->fib6_nh.nh_dev = dev;
+ net->ipv6.fib6_null_entry->rt6i_idev = in6_dev_get(dev);
net->ipv6.ip6_null_entry->dst.dev = dev;
net->ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(dev);
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
@@ -4781,6 +4793,7 @@ static int ip6_route_dev_notify(struct notifier_block *this,
/* NETDEV_UNREGISTER could be fired for multiple times by
* netdev_wait_allrefs(). Make sure we only call this once.
*/
+ in6_dev_put_clear(&net->ipv6.fib6_null_entry->rt6i_idev);
in6_dev_put_clear(&net->ipv6.ip6_null_entry->rt6i_idev);
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
in6_dev_put_clear(&net->ipv6.ip6_prohibit_entry->rt6i_idev);
@@ -4964,11 +4977,17 @@ static int __net_init ip6_route_net_init(struct net *net)
if (dst_entries_init(&net->ipv6.ip6_dst_ops) < 0)
goto out_ip6_dst_ops;
+ net->ipv6.fib6_null_entry = kmemdup(&fib6_null_entry_template,
+ sizeof(*net->ipv6.fib6_null_entry),
+ GFP_KERNEL);
+ if (!net->ipv6.fib6_null_entry)
+ goto out_ip6_dst_entries;
+
net->ipv6.ip6_null_entry = kmemdup(&ip6_null_entry_template,
sizeof(*net->ipv6.ip6_null_entry),
GFP_KERNEL);
if (!net->ipv6.ip6_null_entry)
- goto out_ip6_dst_entries;
+ goto out_fib6_null_entry;
net->ipv6.ip6_null_entry->dst.ops = &net->ipv6.ip6_dst_ops;
dst_init_metrics(&net->ipv6.ip6_null_entry->dst,
ip6_template_metrics, true);
@@ -5015,6 +5034,8 @@ static int __net_init ip6_route_net_init(struct net *net)
out_ip6_null_entry:
kfree(net->ipv6.ip6_null_entry);
#endif
+out_fib6_null_entry:
+ kfree(net->ipv6.fib6_null_entry);
out_ip6_dst_entries:
dst_entries_destroy(&net->ipv6.ip6_dst_ops);
out_ip6_dst_ops:
@@ -5023,6 +5044,7 @@ static int __net_init ip6_route_net_init(struct net *net)
static void __net_exit ip6_route_net_exit(struct net *net)
{
+ kfree(net->ipv6.fib6_null_entry);
kfree(net->ipv6.ip6_null_entry);
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
kfree(net->ipv6.ip6_prohibit_entry);
@@ -5096,6 +5118,8 @@ void __init ip6_route_init_special_entries(void)
/* Registering of the loopback is done before this portion of code,
* the loopback reference in rt6_info will not be taken, do it
* manually for init_net */
+ init_net.ipv6.fib6_null_entry->fib6_nh.nh_dev = init_net.loopback_dev;
+ init_net.ipv6.fib6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
init_net.ipv6.ip6_null_entry->dst.dev = init_net.loopback_dev;
init_net.ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
--
2.11.0
^ permalink raw reply related
* [PATCH RFC v2 net-next 09/21] net/ipv6: Defer initialization of dst to data path
From: David Ahern @ 2018-03-19 3:36 UTC (permalink / raw)
To: netdev
Cc: davem, idosch, roopa, eric.dumazet, weiwan, kafai, yoshfuji,
David Ahern
In-Reply-To: <20180319033622.16693-1-dsahern@gmail.com>
Defer setting dst input, output and error until fib entry is copied.
The reject path from ip6_route_info_create is moved to a new function
ip6_rt_init_dst_reject with a helper doing the conversion from fib6_type
to dst error.
The remainder of the new ip6_rt_init_dst is an amalgamtion of dst code
from addrconf_dst_alloc and the non-reject path of ip6_route_info_create.
The dst output function is always ip6_output and the input function is
either ip6_input (local routes), ip6_mc_input (multicast routes) or
ip6_forward (anything else).
A couple of places using dst.error are updated to look at rt6i_flags.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
net/ipv6/route.c | 115 +++++++++++++++++++++++++++++++++++--------------------
1 file changed, 74 insertions(+), 41 deletions(-)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 43e1ab7cdf4f..adff60c07ae9 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -920,6 +920,75 @@ static struct net_device *ip6_rt_get_dev_rcu(struct rt6_info *rt)
return dev;
}
+static const int fib6_prop[RTN_MAX + 1] = {
+ [RTN_UNSPEC] = 0,
+ [RTN_UNICAST] = 0,
+ [RTN_LOCAL] = 0,
+ [RTN_BROADCAST] = 0,
+ [RTN_ANYCAST] = 0,
+ [RTN_MULTICAST] = 0,
+ [RTN_BLACKHOLE] = -EINVAL,
+ [RTN_UNREACHABLE] = -EHOSTUNREACH,
+ [RTN_PROHIBIT] = -EACCES,
+ [RTN_THROW] = -EAGAIN,
+ [RTN_NAT] = -EINVAL,
+ [RTN_XRESOLVE] = -EINVAL,
+};
+
+static int ip6_rt_type_to_error(u8 fib6_type)
+{
+ return fib6_prop[fib6_type];
+}
+
+static void ip6_rt_init_dst_reject(struct rt6_info *rt, struct rt6_info *ort)
+{
+ rt->dst.error = ip6_rt_type_to_error(ort->fib6_type);
+
+ switch (ort->fib6_type) {
+ case RTN_BLACKHOLE:
+ rt->dst.output = dst_discard_out;
+ rt->dst.input = dst_discard;
+ break;
+ case RTN_PROHIBIT:
+ rt->dst.output = ip6_pkt_prohibit_out;
+ rt->dst.input = ip6_pkt_prohibit;
+ break;
+ case RTN_THROW:
+ case RTN_UNREACHABLE:
+ default:
+ rt->dst.output = ip6_pkt_discard_out;
+ rt->dst.input = ip6_pkt_discard;
+ break;
+ }
+}
+
+static void ip6_rt_init_dst(struct rt6_info *rt, struct rt6_info *ort)
+{
+ if (ort->rt6i_flags & RTF_REJECT) {
+ ip6_rt_init_dst_reject(rt, ort);
+ return;
+ }
+
+ rt->dst.error = 0;
+ rt->dst.output = ip6_output;
+
+ if (ort->fib6_type == RTN_LOCAL) {
+ rt->dst.flags |= DST_HOST;
+ rt->dst.input = ip6_input;
+ } else if (ipv6_addr_type(&ort->rt6i_dst.addr) & IPV6_ADDR_MULTICAST) {
+ rt->dst.input = ip6_mc_input;
+ } else {
+ rt->dst.input = ip6_forward;
+ }
+
+ if (ort->fib6_nh.nh_lwtstate) {
+ rt->dst.lwtstate = lwtstate_get(ort->fib6_nh.nh_lwtstate);
+ lwtunnel_set_redirect(&rt->dst);
+ }
+
+ rt->dst.lastuse = jiffies;
+}
+
static void rt6_set_from(struct rt6_info *rt, struct rt6_info *from)
{
BUG_ON(from->from);
@@ -932,14 +1001,12 @@ static void rt6_set_from(struct rt6_info *rt, struct rt6_info *from)
static void ip6_rt_copy_init(struct rt6_info *rt, struct rt6_info *ort)
{
- rt->dst.input = ort->dst.input;
- rt->dst.output = ort->dst.output;
+ ip6_rt_init_dst(rt, ort);
+
rt->rt6i_dst = ort->rt6i_dst;
- rt->dst.error = ort->dst.error;
rt->rt6i_idev = ort->rt6i_idev;
if (rt->rt6i_idev)
in6_dev_hold(rt->rt6i_idev);
- rt->dst.lastuse = jiffies;
rt->rt6i_gateway = ort->fib6_nh.nh_gw;
rt->rt6i_flags = ort->rt6i_flags;
rt6_set_from(rt, ort);
@@ -2283,7 +2350,7 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
continue;
if (rt6_check_expired(rt))
continue;
- if (rt->dst.error)
+ if (rt->rt6i_flags & RTF_REJECT)
break;
if (!(rt->rt6i_flags & RTF_GATEWAY))
continue;
@@ -2311,7 +2378,7 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
if (!rt)
rt = net->ipv6.ip6_null_entry;
- else if (rt->dst.error) {
+ else if (rt->rt6i_flags & RTF_REJECT) {
rt = net->ipv6.ip6_null_entry;
goto out;
}
@@ -2854,15 +2921,6 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg,
addr_type = ipv6_addr_type(&cfg->fc_dst);
- if (addr_type & IPV6_ADDR_MULTICAST)
- rt->dst.input = ip6_mc_input;
- else if (cfg->fc_flags & RTF_LOCAL)
- rt->dst.input = ip6_input;
- else
- rt->dst.input = ip6_forward;
-
- rt->dst.output = ip6_output;
-
if (cfg->fc_encap) {
struct lwtunnel_state *lwtstate;
@@ -2872,7 +2930,6 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg,
if (err)
goto out;
rt->fib6_nh.nh_lwtstate = lwtstate_get(lwtstate);
- lwtunnel_set_redirect(&rt->dst);
}
ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len);
@@ -2912,27 +2969,6 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg,
}
}
rt->rt6i_flags = RTF_REJECT|RTF_NONEXTHOP;
- switch (cfg->fc_type) {
- case RTN_BLACKHOLE:
- rt->dst.error = -EINVAL;
- rt->dst.output = dst_discard_out;
- rt->dst.input = dst_discard;
- break;
- case RTN_PROHIBIT:
- rt->dst.error = -EACCES;
- rt->dst.output = ip6_pkt_prohibit_out;
- rt->dst.input = ip6_pkt_prohibit;
- break;
- case RTN_THROW:
- case RTN_UNREACHABLE:
- default:
- rt->dst.error = (cfg->fc_type == RTN_THROW) ? -EAGAIN
- : (cfg->fc_type == RTN_UNREACHABLE)
- ? -EHOSTUNREACH : -ENETUNREACH;
- rt->dst.output = ip6_pkt_discard_out;
- rt->dst.input = ip6_pkt_discard;
- break;
- }
goto install_route;
}
@@ -3570,12 +3606,9 @@ struct rt6_info *addrconf_dst_alloc(struct net *net,
return ERR_PTR(-ENOMEM);
in6_dev_hold(idev);
-
- rt->dst.flags |= DST_HOST;
- rt->dst.input = ip6_input;
- rt->dst.output = ip6_output;
rt->rt6i_idev = idev;
+ rt->dst.flags |= DST_HOST;
rt->rt6i_protocol = RTPROT_KERNEL;
rt->rt6i_flags = RTF_UP | RTF_NONEXTHOP;
if (anycast) {
--
2.11.0
^ permalink raw reply related
* [PATCH RFC v2 net-next 10/21] net/ipv6: move metrics from dst to rt6_info
From: David Ahern @ 2018-03-19 3:36 UTC (permalink / raw)
To: netdev
Cc: davem, idosch, roopa, eric.dumazet, weiwan, kafai, yoshfuji,
David Ahern
In-Reply-To: <20180319033622.16693-1-dsahern@gmail.com>
Similar to IPv4, add fib metrics to the fib struct, which at the moment
is rt6_info. Will be moved to fib6_info in a later patch. Copy metrics
into dst by reference using refcount.
To make the transition:
- add dst_metrics to rt6_info. Default to dst_default_metrics if no
metrics are passed during route add. No need for a separate pmtu
entry; it can reference the MTU slot in fib6_metrics
- ip6_convert_metrics allocates memory in the FIB entry and uses
ip_metrics_convert to copy from netlink attribute to metrics entry
- the convert metrics call is done in ip6_route_info_create simplifying
the route add path
+ fib6_commit_metrics and fib6_copy_metrics and the temporary
mx6_config are no longer needed
- add fib6_metric_set helper to change the value of a metric in the
fib entry since dst_metric_set can no longer be used
- cow_metrics for IPv6 can drop to dst_cow_metrics_generic
- rt6_dst_from_metrics_check is no longer needed
- rt6_fill_node needs the FIB entry and dst as separate arguments to
keep compatibility with existing output. Current dst address is
renamed to dest.
(to be consistent with IPv4 rt6_fill_node really should be split
into 2 functions similar to fib_dump_info and rt_fill_info)
- rt6_fill_node no longer needs the temporary metrics variable
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/net/ip6_fib.h | 17 ++--
net/core/dst.c | 1 +
net/ipv6/ip6_fib.c | 67 +++++--------
net/ipv6/ndisc.c | 10 +-
net/ipv6/route.c | 262 +++++++++++++++++++-------------------------------
5 files changed, 134 insertions(+), 223 deletions(-)
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index f0a88370ba95..1f8dc9d12abb 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -94,11 +94,6 @@ struct fib6_gc_args {
#define FIB6_SUBTREE(fn) (rcu_dereference_protected((fn)->subtree, 1))
#endif
-struct mx6_config {
- const u32 *mx;
- DECLARE_BITMAP(mx_valid, RTAX_MAX);
-};
-
/*
* routing information
*
@@ -176,7 +171,6 @@ struct rt6_info {
struct rt6_exception_bucket __rcu *rt6i_exception_bucket;
u32 rt6i_metric;
- u32 rt6i_pmtu;
/* more non-fragment space at head required */
unsigned short rt6i_nfheader_len;
u8 rt6i_protocol;
@@ -185,6 +179,8 @@ struct rt6_info {
should_flush:1,
unused:6;
+ struct dst_metrics *fib6_metrics;
+#define fib6_pmtu fib6_metrics->metrics[RTAX_MTU-1]
struct fib6_nh fib6_nh;
};
@@ -390,8 +386,7 @@ void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
void *arg);
int fib6_add(struct fib6_node *root, struct rt6_info *rt,
- struct nl_info *info, struct mx6_config *mxc,
- struct netlink_ext_ack *extack);
+ struct nl_info *info, struct netlink_ext_ack *extack);
int fib6_del(struct rt6_info *rt, struct nl_info *info);
void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info,
@@ -420,6 +415,12 @@ int fib6_tables_dump(struct net *net, struct notifier_block *nb);
void fib6_update_sernum(struct net *net, struct rt6_info *rt);
void fib6_update_sernum_upto_root(struct net *net, struct rt6_info *rt);
+void fib6_metric_set(struct rt6_info *f6i, int metric, u32 val);
+static inline bool fib6_metric_locked(struct rt6_info *f6i, int metric)
+{
+ return !!(f6i->fib6_metrics->metrics[RTAX_LOCK - 1] & (1 << metric));
+}
+
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
int fib6_rules_init(void);
void fib6_rules_cleanup(void);
diff --git a/net/core/dst.c b/net/core/dst.c
index 007aa0b08291..2d9b37f8944a 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -58,6 +58,7 @@ const struct dst_metrics dst_default_metrics = {
*/
.refcnt = REFCOUNT_INIT(1),
};
+EXPORT_SYMBOL(dst_default_metrics);
void dst_init(struct dst_entry *dst, struct dst_ops *ops,
struct net_device *dev, int initial_ref, int initial_obsolete,
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 7326edab2acb..f3f284c3a486 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -578,6 +578,24 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
return res;
}
+void fib6_metric_set(struct rt6_info *f6i, int metric, u32 val)
+{
+ if (!f6i)
+ return;
+
+ if (f6i->fib6_metrics == &dst_default_metrics) {
+ struct dst_metrics *p = kzalloc(sizeof(*p), GFP_ATOMIC);
+
+ if (!p)
+ return;
+
+ refcount_set(&p->refcnt, 1);
+ f6i->fib6_metrics = p;
+ }
+
+ f6i->fib6_metrics->metrics[metric - 1] = val;
+}
+
/*
* Routing Table
*
@@ -801,38 +819,6 @@ static struct fib6_node *fib6_add_1(struct net *net,
return ln;
}
-static void fib6_copy_metrics(u32 *mp, const struct mx6_config *mxc)
-{
- int i;
-
- for (i = 0; i < RTAX_MAX; i++) {
- if (test_bit(i, mxc->mx_valid))
- mp[i] = mxc->mx[i];
- }
-}
-
-static int fib6_commit_metrics(struct dst_entry *dst, struct mx6_config *mxc)
-{
- if (!mxc->mx)
- return 0;
-
- if (dst->flags & DST_HOST) {
- u32 *mp = dst_metrics_write_ptr(dst);
-
- if (unlikely(!mp))
- return -ENOMEM;
-
- fib6_copy_metrics(mp, mxc);
- } else {
- dst_init_metrics(dst, mxc->mx, false);
-
- /* We've stolen mx now. */
- mxc->mx = NULL;
- }
-
- return 0;
-}
-
static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn,
struct net *net)
{
@@ -866,7 +852,7 @@ static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn,
*/
static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
- struct nl_info *info, struct mx6_config *mxc,
+ struct nl_info *info,
struct netlink_ext_ack *extack)
{
struct rt6_info *leaf = rcu_dereference_protected(fn->leaf,
@@ -881,7 +867,6 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
int found = 0;
bool rt_can_ecmp = rt6_qualify_for_ecmp(rt);
u16 nlflags = NLM_F_EXCL;
- int err;
if (info->nlh && (info->nlh->nlmsg_flags & NLM_F_APPEND))
nlflags |= NLM_F_APPEND;
@@ -923,7 +908,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
rt6_clean_expires(iter);
else
rt6_set_expires(iter, rt->dst.expires);
- iter->rt6i_pmtu = rt->rt6i_pmtu;
+ fib6_metric_set(iter, RTAX_MTU, rt->fib6_pmtu);
return -EEXIST;
}
/* If we have the same destination and the same metric,
@@ -1002,9 +987,6 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
add:
nlflags |= NLM_F_CREATE;
- err = fib6_commit_metrics(&rt->dst, mxc);
- if (err)
- return err;
rcu_assign_pointer(rt->rt6_next, iter);
atomic_inc(&rt->rt6i_ref);
@@ -1031,10 +1013,6 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
return -ENOENT;
}
- err = fib6_commit_metrics(&rt->dst, mxc);
- if (err)
- return err;
-
atomic_inc(&rt->rt6i_ref);
rcu_assign_pointer(rt->rt6i_node, fn);
rt->rt6_next = iter->rt6_next;
@@ -1127,8 +1105,7 @@ void fib6_update_sernum_upto_root(struct net *net, struct rt6_info *rt)
*/
int fib6_add(struct fib6_node *root, struct rt6_info *rt,
- struct nl_info *info, struct mx6_config *mxc,
- struct netlink_ext_ack *extack)
+ struct nl_info *info, struct netlink_ext_ack *extack)
{
struct fib6_table *table = rt->rt6i_table;
struct fib6_node *fn, *pn = NULL;
@@ -1236,7 +1213,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
}
#endif
- err = fib6_add_rt2node(fn, rt, info, mxc, extack);
+ err = fib6_add_rt2node(fn, rt, info, extack);
if (!err) {
__fib6_update_sernum_upto_root(rt, sernum);
fib6_start_gc(info->nl_net, rt);
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 4c6444a16d92..33768b72f674 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1323,9 +1323,8 @@ static void ndisc_router_discovery(struct sk_buff *skb)
ra_msg->icmph.icmp6_hop_limit) {
if (in6_dev->cnf.accept_ra_min_hop_limit <= ra_msg->icmph.icmp6_hop_limit) {
in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit;
- if (rt)
- dst_metric_set(&rt->dst, RTAX_HOPLIMIT,
- ra_msg->icmph.icmp6_hop_limit);
+ fib6_metric_set(rt, RTAX_HOPLIMIT,
+ ra_msg->icmph.icmp6_hop_limit);
} else {
ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than minimum\n");
}
@@ -1477,10 +1476,7 @@ static void ndisc_router_discovery(struct sk_buff *skb)
ND_PRINTK(2, warn, "RA: invalid mtu: %d\n", mtu);
} else if (in6_dev->cnf.mtu6 != mtu) {
in6_dev->cnf.mtu6 = mtu;
-
- if (rt)
- dst_metric_set(&rt->dst, RTAX_MTU, mtu);
-
+ fib6_metric_set(rt, RTAX_MTU, mtu);
rt6_mtu_change(skb->dev, mtu);
}
}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index adff60c07ae9..0f290c75905e 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -96,12 +96,11 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu);
static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb);
-static void rt6_dst_from_metrics_check(struct rt6_info *rt);
static int rt6_score_route(struct rt6_info *rt, int oif, int strict);
static size_t rt6_nlmsg_size(struct rt6_info *rt);
-static int rt6_fill_node(struct net *net,
- struct sk_buff *skb, struct rt6_info *rt,
- struct in6_addr *dst, struct in6_addr *src,
+static int rt6_fill_node(struct net *net, struct sk_buff *skb,
+ struct rt6_info *rt, struct dst_entry *dst,
+ struct in6_addr *dest, struct in6_addr *src,
int iif, int type, u32 portid, u32 seq,
unsigned int flags);
static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt,
@@ -183,23 +182,6 @@ 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->from->dst);
-}
-
-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_PCPU)
- return rt6_pcpu_cow_metrics(rt);
- else if (rt->rt6i_flags & RTF_CACHE)
- return NULL;
- else
- return dst_cow_metrics_generic(dst, old);
-}
-
static inline const void *choose_neigh_daddr(struct rt6_info *rt,
struct sk_buff *skb,
const void *daddr)
@@ -249,7 +231,7 @@ static struct dst_ops ip6_dst_ops_template = {
.check = ip6_dst_check,
.default_advmss = ip6_default_advmss,
.mtu = ip6_mtu,
- .cow_metrics = ipv6_cow_metrics,
+ .cow_metrics = dst_cow_metrics_generic,
.destroy = ip6_dst_destroy,
.ifdown = ip6_dst_ifdown,
.negative_advice = ip6_negative_advice,
@@ -353,6 +335,7 @@ static void rt6_info_init(struct rt6_info *rt)
memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst));
INIT_LIST_HEAD(&rt->rt6i_siblings);
INIT_LIST_HEAD(&rt->rt6i_uncached);
+ rt->fib6_metrics = (struct dst_metrics *)&dst_default_metrics;
}
/* allocate dst with ip6_dst_ops */
@@ -395,6 +378,7 @@ static void ip6_dst_destroy(struct dst_entry *dst)
struct rt6_exception_bucket *bucket;
struct rt6_info *from = rt->from;
struct inet6_dev *idev;
+ struct dst_metrics *m;
dst_destroy_metrics_generic(dst);
free_percpu(rt->rt6i_pcpu);
@@ -411,6 +395,10 @@ static void ip6_dst_destroy(struct dst_entry *dst)
kfree(bucket);
}
+ m = rt->fib6_metrics;
+ if (m != &dst_default_metrics && refcount_dec_and_test(&m->refcnt))
+ kfree(m);
+
rt->from = NULL;
dst_release(&from->dst);
}
@@ -996,7 +984,11 @@ static void rt6_set_from(struct rt6_info *rt, struct rt6_info *from)
rt->rt6i_flags &= ~RTF_EXPIRES;
dst_hold(&from->dst);
rt->from = from;
- dst_init_metrics(&rt->dst, dst_metrics_ptr(&from->dst), true);
+ dst_init_metrics(&rt->dst, from->fib6_metrics->metrics, true);
+ if (from->fib6_metrics != &dst_default_metrics) {
+ rt->dst._metrics |= DST_METRICS_REFCOUNTED;
+ refcount_inc(&from->fib6_metrics->refcnt);
+ }
}
static void ip6_rt_copy_init(struct rt6_info *rt, struct rt6_info *ort)
@@ -1137,7 +1129,6 @@ EXPORT_SYMBOL(rt6_lookup);
*/
static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info,
- struct mx6_config *mxc,
struct netlink_ext_ack *extack)
{
int err;
@@ -1145,7 +1136,7 @@ static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info,
table = rt->rt6i_table;
spin_lock_bh(&table->tb6_lock);
- err = fib6_add(&table->tb6_root, rt, info, mxc, extack);
+ err = fib6_add(&table->tb6_root, rt, info, extack);
spin_unlock_bh(&table->tb6_lock);
return err;
@@ -1154,11 +1145,10 @@ static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info,
int ip6_ins_rt(struct net *net, struct rt6_info *rt)
{
struct nl_info info = { .nl_net = net, };
- struct mx6_config mxc = { .mx = NULL, };
/* Hold dst to account for the reference from the fib6 tree */
dst_hold(&rt->dst);
- return __ip6_ins_rt(rt, &info, &mxc, NULL);
+ return __ip6_ins_rt(rt, &info, NULL);
}
static struct rt6_info *ip6_rt_cache_alloc(struct rt6_info *ort,
@@ -1229,8 +1219,8 @@ static struct rt6_info *rt6_get_pcpu_route(struct rt6_info *rt)
p = this_cpu_ptr(rt->rt6i_pcpu);
pcpu_rt = *p;
- if (pcpu_rt && ip6_hold_safe(NULL, &pcpu_rt, false))
- rt6_dst_from_metrics_check(pcpu_rt);
+ if (pcpu_rt)
+ ip6_hold_safe(NULL, &pcpu_rt, false);
return pcpu_rt;
}
@@ -1251,7 +1241,6 @@ static struct rt6_info *rt6_make_pcpu_route(struct net *net,
prev = cmpxchg(p, NULL, pcpu_rt);
BUG_ON(prev);
- rt6_dst_from_metrics_check(pcpu_rt);
return pcpu_rt;
}
@@ -1381,6 +1370,16 @@ __rt6_find_exception_rcu(struct rt6_exception_bucket **bucket,
return NULL;
}
+static unsigned int fib6_mtu(const struct rt6_info *rt)
+{
+ unsigned int mtu;
+
+ mtu = rt->fib6_pmtu ? : rt->rt6i_idev->cnf.mtu6;
+ mtu = min_t(unsigned int, mtu, IP6_MAX_MTU);
+
+ return mtu - lwtunnel_headroom(rt->fib6_nh.nh_lwtstate, mtu);
+}
+
static int rt6_insert_exception(struct rt6_info *nrt,
struct rt6_info *ort)
{
@@ -1433,7 +1432,7 @@ static int rt6_insert_exception(struct rt6_info *nrt,
* Only insert this exception route if its mtu
* is less than ort's mtu value.
*/
- if (nrt->rt6i_pmtu >= dst_mtu(&ort->dst)) {
+ if (dst_metric_raw(&nrt->dst, RTAX_MTU) >= fib6_mtu(ort)) {
err = -EINVAL;
goto out;
}
@@ -1643,13 +1642,15 @@ static void rt6_exceptions_update_pmtu(struct rt6_info *rt, int mtu)
for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) {
hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) {
struct rt6_info *entry = rt6_ex->rt6i;
+ u32 dst_mtu = dst_metric(&entry->dst, RTAX_MTU);
+
/* For RTF_CACHE with rt6i_pmtu == 0
* (i.e. a redirected route),
- * the metrics of its rt->dst.from has already
+ * the metrics of its rt->from has already
* been updated.
*/
- if (entry->rt6i_pmtu && entry->rt6i_pmtu > mtu)
- entry->rt6i_pmtu = mtu;
+ if (dst_mtu && dst_mtu > mtu)
+ dst_metric_set(&entry->dst, RTAX_MTU, mtu);
}
bucket++;
}
@@ -1815,10 +1816,9 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
trace_fib6_table_lookup(net, rt, table, fl6);
return rt;
} else if (rt->rt6i_flags & RTF_CACHE) {
- if (ip6_hold_safe(net, &rt, true)) {
+ if (ip6_hold_safe(net, &rt, true))
dst_use_noref(&rt->dst, jiffies);
- rt6_dst_from_metrics_check(rt);
- }
+
rcu_read_unlock();
trace_fib6_table_lookup(net, rt, table, fl6);
return rt;
@@ -2118,13 +2118,6 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
* Destination cache support functions
*/
-static void rt6_dst_from_metrics_check(struct rt6_info *rt)
-{
- if (rt->from &&
- dst_metrics_ptr(&rt->dst) != dst_metrics_ptr(&rt->from->dst))
- dst_init_metrics(&rt->dst, dst_metrics_ptr(&rt->from->dst), true);
-}
-
static struct dst_entry *rt6_check(struct rt6_info *rt, u32 cookie)
{
u32 rt_cookie = 0;
@@ -2159,8 +2152,6 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
* into this function always.
*/
- rt6_dst_from_metrics_check(rt);
-
if (rt->rt6i_flags & RTF_PCPU ||
(unlikely(!list_empty(&rt->rt6i_uncached)) && rt->from))
return rt6_dst_from_check(rt, cookie);
@@ -2213,8 +2204,8 @@ static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu)
{
struct net *net = dev_net(rt->dst.dev);
+ dst_metric_set(&rt->dst, RTAX_MTU, mtu);
rt->rt6i_flags |= RTF_MODIFIED;
- rt->rt6i_pmtu = mtu;
rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires);
}
@@ -2260,10 +2251,10 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
} else if (daddr) {
struct rt6_info *nrt6;
- nrt6 = ip6_rt_cache_alloc(rt6, daddr, saddr);
+ nrt6 = ip6_rt_cache_alloc(rt6->from, daddr, saddr);
if (nrt6) {
rt6_do_update_pmtu(nrt6, mtu);
- if (rt6_insert_exception(nrt6, rt6))
+ if (rt6_insert_exception(nrt6, rt6->from))
dst_release_immediate(&nrt6->dst);
}
}
@@ -2487,12 +2478,8 @@ static unsigned int ip6_default_advmss(const struct dst_entry *dst)
static unsigned int ip6_mtu(const struct dst_entry *dst)
{
- const struct rt6_info *rt = (const struct rt6_info *)dst;
- unsigned int mtu = rt->rt6i_pmtu;
struct inet6_dev *idev;
-
- if (mtu)
- goto out;
+ unsigned int mtu;
mtu = dst_metric_raw(dst, RTAX_MTU);
if (mtu)
@@ -2576,60 +2563,24 @@ static int ip6_dst_gc(struct dst_ops *ops)
return entries > rt_max_size;
}
-static int ip6_convert_metrics(struct mx6_config *mxc,
- const struct fib6_config *cfg)
+static int ip6_convert_metrics(struct net *net, struct rt6_info *rt,
+ struct fib6_config *cfg)
{
- struct net *net = cfg->fc_nlinfo.nl_net;
- bool ecn_ca = false;
- struct nlattr *nla;
- int remaining;
- u32 *mp;
-
- if (!cfg->fc_mx)
- return 0;
-
- mp = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
- if (unlikely(!mp))
- return -ENOMEM;
-
- nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
- int type = nla_type(nla);
- u32 val;
-
- if (!type)
- continue;
- if (unlikely(type > RTAX_MAX))
- goto err;
-
- if (type == RTAX_CC_ALGO) {
- char tmp[TCP_CA_NAME_MAX];
+ int err = 0;
- nla_strlcpy(tmp, nla, sizeof(tmp));
- val = tcp_ca_get_key_by_name(net, tmp, &ecn_ca);
- if (val == TCP_CA_UNSPEC)
- goto err;
- } else {
- val = nla_get_u32(nla);
- }
- if (type == RTAX_HOPLIMIT && val > 255)
- val = 255;
- if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK))
- goto err;
+ if (cfg->fc_mx) {
+ rt->fib6_metrics = kzalloc(sizeof(*rt->fib6_metrics),
+ GFP_KERNEL);
+ if (unlikely(!rt->fib6_metrics))
+ return -ENOMEM;
- mp[type - 1] = val;
- __set_bit(type - 1, mxc->mx_valid);
- }
+ refcount_set(&rt->fib6_metrics->refcnt, 1);
- if (ecn_ca) {
- __set_bit(RTAX_FEATURES - 1, mxc->mx_valid);
- mp[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA;
+ err = ip_metrics_convert(net, cfg->fc_mx, cfg->fc_mx_len,
+ rt->fib6_metrics->metrics);
}
- mxc->mx = mp;
- return 0;
- err:
- kfree(mp);
- return -EINVAL;
+ return err;
}
static struct rt6_info *ip6_nh_lookup_table(struct net *net,
@@ -2909,6 +2860,10 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg,
goto out;
}
+ err = ip6_convert_metrics(net, rt, cfg);
+ if (err < 0)
+ goto out;
+
if (cfg->fc_flags & RTF_EXPIRES)
rt6_set_expires(rt, jiffies +
clock_t_to_jiffies(cfg->fc_expires));
@@ -3026,32 +2981,16 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg,
return ERR_PTR(err);
}
-int ip6_route_add(struct fib6_config *cfg,
- struct netlink_ext_ack *extack)
+int ip6_route_add(struct fib6_config *cfg, struct netlink_ext_ack *extack)
{
- struct mx6_config mxc = { .mx = NULL, };
struct rt6_info *rt;
int err;
rt = ip6_route_info_create(cfg, extack);
- if (IS_ERR(rt)) {
- err = PTR_ERR(rt);
- rt = NULL;
- goto out;
- }
+ if (IS_ERR(rt))
+ return PTR_ERR(rt);
- err = ip6_convert_metrics(&mxc, cfg);
- if (err)
- goto out;
-
- err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, &mxc, extack);
-
- kfree(mxc.mx);
-
- return err;
-out:
- if (rt)
- dst_release_immediate(&rt->dst);
+ err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, extack);
return err;
}
@@ -3105,7 +3044,7 @@ static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg)
if (skb) {
u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0;
- if (rt6_fill_node(net, skb, rt,
+ if (rt6_fill_node(net, skb, rt, NULL,
NULL, NULL, 0, RTM_DELROUTE,
info->portid, seq, 0) < 0) {
kfree_skb(skb);
@@ -3296,7 +3235,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
* a cached route because rt6_insert_exception() will
* takes care of it
*/
- if (rt6_insert_exception(nrt, rt)) {
+ if (rt6_insert_exception(nrt, rt->from)) {
dst_release_immediate(&nrt->dst);
goto out;
}
@@ -3973,15 +3912,15 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg)
also have the lowest MTU, TOO BIG MESSAGE will be lead to
PMTU discovery.
*/
- if (rt->fib6_nh.nh_dev == arg->dev &&
- dst_metric_raw(&rt->dst, RTAX_MTU) &&
- !dst_metric_locked(&rt->dst, RTAX_MTU)) {
+ if (rt->fib6_nh.nh_dev == arg->dev && rt->fib6_pmtu &&
+ !fib6_metric_locked(rt, RTAX_MTU)) {
+ u32 mtu = rt->fib6_pmtu;
+
+ if (mtu >= arg->mtu ||
+ (mtu < arg->mtu && mtu == idev->cnf.mtu6))
+ fib6_metric_set(rt, RTAX_MTU, arg->mtu);
+
spin_lock_bh(&rt6_exception_lock);
- if (dst_mtu(&rt->dst) >= arg->mtu ||
- (dst_mtu(&rt->dst) < arg->mtu &&
- dst_mtu(&rt->dst) == idev->cnf.mtu6)) {
- dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu);
- }
rt6_exceptions_update_pmtu(rt, arg->mtu);
spin_unlock_bh(&rt6_exception_lock);
}
@@ -4142,7 +4081,6 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
struct rt6_nh {
struct rt6_info *rt6_info;
struct fib6_config r_cfg;
- struct mx6_config mxc;
struct list_head next;
};
@@ -4157,7 +4095,8 @@ static void ip6_print_replace_route_err(struct list_head *rt6_nh_list)
}
}
-static int ip6_route_info_append(struct list_head *rt6_nh_list,
+static int ip6_route_info_append(struct net *net,
+ struct list_head *rt6_nh_list,
struct rt6_info *rt, struct fib6_config *r_cfg)
{
struct rt6_nh *nh;
@@ -4173,7 +4112,7 @@ static int ip6_route_info_append(struct list_head *rt6_nh_list,
if (!nh)
return -ENOMEM;
nh->rt6_info = rt;
- err = ip6_convert_metrics(&nh->mxc, r_cfg);
+ err = ip6_convert_metrics(net, rt, r_cfg);
if (err) {
kfree(nh);
return err;
@@ -4263,7 +4202,8 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
rt->fib6_nh.nh_weight = rtnh->rtnh_hops + 1;
- err = ip6_route_info_append(&rt6_nh_list, rt, &r_cfg);
+ err = ip6_route_info_append(info->nl_net, &rt6_nh_list,
+ rt, &r_cfg);
if (err) {
dst_release_immediate(&rt->dst);
goto cleanup;
@@ -4281,7 +4221,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
err_nh = NULL;
list_for_each_entry(nh, &rt6_nh_list, next) {
rt_last = nh->rt6_info;
- err = __ip6_ins_rt(nh->rt6_info, info, &nh->mxc, extack);
+ err = __ip6_ins_rt(nh->rt6_info, info, extack);
/* save reference to first route for notification */
if (!rt_notif && !err)
rt_notif = nh->rt6_info;
@@ -4330,7 +4270,6 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, next) {
if (nh->rt6_info)
dst_release_immediate(&nh->rt6_info->dst);
- kfree(nh->mxc.mx);
list_del(&nh->next);
kfree(nh);
}
@@ -4504,16 +4443,15 @@ static int rt6_add_nexthop(struct sk_buff *skb, struct rt6_info *rt)
return -EMSGSIZE;
}
-static int rt6_fill_node(struct net *net,
- struct sk_buff *skb, struct rt6_info *rt,
- struct in6_addr *dst, struct in6_addr *src,
+static int rt6_fill_node(struct net *net, struct sk_buff *skb,
+ struct rt6_info *rt, struct dst_entry *dst,
+ struct in6_addr *dest, struct in6_addr *src,
int iif, int type, u32 portid, u32 seq,
unsigned int flags)
{
- u32 metrics[RTAX_MAX];
struct rtmsg *rtm;
struct nlmsghdr *nlh;
- long expires;
+ long expires = 0;
u32 table;
nlh = nlmsg_put(skb, portid, seq, type, sizeof(*rtm), flags);
@@ -4541,8 +4479,8 @@ static int rt6_fill_node(struct net *net,
if (rt->rt6i_flags & RTF_CACHE)
rtm->rtm_flags |= RTM_F_CLONED;
- if (dst) {
- if (nla_put_in6_addr(skb, RTA_DST, dst))
+ if (dest) {
+ if (nla_put_in6_addr(skb, RTA_DST, dest))
goto nla_put_failure;
rtm->rtm_dst_len = 128;
} else if (rtm->rtm_dst_len)
@@ -4570,9 +4508,9 @@ static int rt6_fill_node(struct net *net,
#endif
if (nla_put_u32(skb, RTA_IIF, iif))
goto nla_put_failure;
- } else if (dst) {
+ } else if (dest) {
struct in6_addr saddr_buf;
- if (ip6_route_get_saddr(net, rt, dst, 0, &saddr_buf) == 0 &&
+ if (ip6_route_get_saddr(net, rt, dest, 0, &saddr_buf) == 0 &&
nla_put_in6_addr(skb, RTA_PREFSRC, &saddr_buf))
goto nla_put_failure;
}
@@ -4584,10 +4522,7 @@ static int rt6_fill_node(struct net *net,
goto nla_put_failure;
}
- memcpy(metrics, dst_metrics_ptr(&rt->dst), sizeof(metrics));
- if (rt->rt6i_pmtu)
- metrics[RTAX_MTU - 1] = rt->rt6i_pmtu;
- if (rtnetlink_put_metrics(skb, metrics) < 0)
+ if (rtnetlink_put_metrics(skb, rt->fib6_metrics->metrics) < 0)
goto nla_put_failure;
if (nla_put_u32(skb, RTA_PRIORITY, rt->rt6i_metric))
@@ -4619,9 +4554,10 @@ static int rt6_fill_node(struct net *net,
goto nla_put_failure;
}
- expires = (rt->rt6i_flags & RTF_EXPIRES) ? rt->dst.expires - jiffies : 0;
+ if (rt->rt6i_flags & RTF_EXPIRES && dst)
+ expires = dst->expires - jiffies;
- if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, rt->dst.error) < 0)
+ if (rtnl_put_cacheinfo(skb, dst, 0, expires, dst ? dst->error : 0) < 0)
goto nla_put_failure;
if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->rt6i_flags)))
@@ -4655,10 +4591,9 @@ int rt6_dump_route(struct rt6_info *rt, void *p_arg)
}
}
- return rt6_fill_node(net,
- arg->skb, rt, NULL, NULL, 0, RTM_NEWROUTE,
- NETLINK_CB(arg->cb->skb).portid, arg->cb->nlh->nlmsg_seq,
- NLM_F_MULTI);
+ return rt6_fill_node(net, arg->skb, rt, NULL, NULL, NULL, 0,
+ RTM_NEWROUTE, NETLINK_CB(arg->cb->skb).portid,
+ arg->cb->nlh->nlmsg_seq, NLM_F_MULTI);
}
static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
@@ -4772,13 +4707,14 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
skb_dst_set(skb, &rt->dst);
if (fibmatch)
- err = rt6_fill_node(net, skb, rt, NULL, NULL, iif,
+ err = rt6_fill_node(net, skb, rt, NULL, NULL, NULL, iif,
RTM_NEWROUTE, NETLINK_CB(in_skb).portid,
nlh->nlmsg_seq, 0);
else
- err = rt6_fill_node(net, skb, rt, &fl6.daddr, &fl6.saddr, iif,
- RTM_NEWROUTE, NETLINK_CB(in_skb).portid,
- nlh->nlmsg_seq, 0);
+ err = rt6_fill_node(net, skb, rt, dst, &fl6.daddr, &fl6.saddr,
+ iif, RTM_NEWROUTE,
+ NETLINK_CB(in_skb).portid, nlh->nlmsg_seq,
+ 0);
if (err < 0) {
kfree_skb(skb);
goto errout;
@@ -4804,8 +4740,8 @@ void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info,
if (!skb)
goto errout;
- err = rt6_fill_node(net, skb, rt, NULL, NULL, 0,
- event, info->portid, seq, nlm_flags);
+ err = rt6_fill_node(net, skb, rt, NULL, NULL, NULL, 0,
+ event, info->portid, seq, nlm_flags);
if (err < 0) {
/* -EMSGSIZE implies BUG in rt6_nlmsg_size() */
WARN_ON(err == -EMSGSIZE);
--
2.11.0
^ permalink raw reply related
* [PATCH RFC v2 net-next 11/21] net/ipv6: move expires into rt6_info
From: David Ahern @ 2018-03-19 3:36 UTC (permalink / raw)
To: netdev
Cc: davem, idosch, roopa, eric.dumazet, weiwan, kafai, yoshfuji,
David Ahern
In-Reply-To: <20180319033622.16693-1-dsahern@gmail.com>
Add expires to rt6_info for FIB entries, and add fib6 helpers to
manage it. Data path use of dst.expires remains.
The transition is fairly straightforward: when working with fib entries,
rt->dst.expires is just rt->expires, rt6_clean_expires is replaced with
fib6_clean_expires, rt6_set_expires becomes fib6_set_expires, and
rt6_check_expired becomes fib6_check_expired, where the fib6 versions
are added by this patch.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/net/ip6_fib.h | 27 +++++++++++++++++++++++----
net/ipv6/addrconf.c | 6 +++---
net/ipv6/ip6_fib.c | 8 ++++----
net/ipv6/ndisc.c | 2 +-
net/ipv6/route.c | 20 +++++++++++---------
5 files changed, 42 insertions(+), 21 deletions(-)
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 1f8dc9d12abb..c73b985734f5 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -179,6 +179,7 @@ struct rt6_info {
should_flush:1,
unused:6;
+ unsigned long expires;
struct dst_metrics *fib6_metrics;
#define fib6_pmtu fib6_metrics->metrics[RTAX_MTU-1]
struct fib6_nh fib6_nh;
@@ -197,6 +198,26 @@ static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst)
return ((struct rt6_info *)dst)->rt6i_idev;
}
+static inline void fib6_clean_expires(struct rt6_info *f6i)
+{
+ f6i->rt6i_flags &= ~RTF_EXPIRES;
+ f6i->expires = 0;
+}
+
+static inline void fib6_set_expires(struct rt6_info *f6i,
+ unsigned long expires)
+{
+ f6i->expires = expires;
+ f6i->rt6i_flags |= RTF_EXPIRES;
+}
+
+static inline bool fib6_check_expired(const struct rt6_info *f6i)
+{
+ if (f6i->rt6i_flags & RTF_EXPIRES)
+ return time_after(jiffies, f6i->expires);
+ return false;
+}
+
static inline void rt6_clean_expires(struct rt6_info *rt)
{
rt->rt6i_flags &= ~RTF_EXPIRES;
@@ -211,11 +232,9 @@ static inline void rt6_set_expires(struct rt6_info *rt, unsigned long expires)
static inline void rt6_update_expires(struct rt6_info *rt0, int timeout)
{
- struct rt6_info *rt;
+ if (!(rt0->rt6i_flags & RTF_EXPIRES) && rt0->from)
+ rt0->dst.expires = rt0->from->expires;
- for (rt = rt0; rt && !(rt->rt6i_flags & RTF_EXPIRES); rt = rt->from);
- if (rt && rt != rt0)
- rt0->dst.expires = rt->dst.expires;
dst_set_expires(&rt0->dst, timeout);
rt0->rt6i_flags |= RTF_EXPIRES;
}
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 7d92c6e48d2e..23834864adb5 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1202,7 +1202,7 @@ cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, bool del_r
ip6_del_rt(dev_net(ifp->idev->dev), rt);
else {
if (!(rt->rt6i_flags & RTF_EXPIRES))
- rt6_set_expires(rt, expires);
+ fib6_set_expires(rt, expires);
ip6_rt_put(rt);
}
}
@@ -2685,9 +2685,9 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
rt = NULL;
} else if (addrconf_finite_timeout(rt_expires)) {
/* not infinity */
- rt6_set_expires(rt, jiffies + rt_expires);
+ fib6_set_expires(rt, jiffies + rt_expires);
} else {
- rt6_clean_expires(rt);
+ fib6_clean_expires(rt);
}
} else if (valid_lft) {
clock_t expires = 0;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index f3f284c3a486..70eca9cb551f 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -905,9 +905,9 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
if (!(iter->rt6i_flags & RTF_EXPIRES))
return -EEXIST;
if (!(rt->rt6i_flags & RTF_EXPIRES))
- rt6_clean_expires(iter);
+ fib6_clean_expires(iter);
else
- rt6_set_expires(iter, rt->dst.expires);
+ fib6_set_expires(iter, rt->expires);
fib6_metric_set(iter, RTAX_MTU, rt->fib6_pmtu);
return -EEXIST;
}
@@ -1994,8 +1994,8 @@ static int fib6_age(struct rt6_info *rt, void *arg)
* Routes are expired even if they are in use.
*/
- if (rt->rt6i_flags & RTF_EXPIRES && rt->dst.expires) {
- if (time_after(now, rt->dst.expires)) {
+ if (rt->rt6i_flags & RTF_EXPIRES && rt->expires) {
+ if (time_after(now, rt->expires)) {
RT6_TRACE("expiring %p\n", rt);
return -1;
}
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 33768b72f674..848f518d48d4 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1318,7 +1318,7 @@ static void ndisc_router_discovery(struct sk_buff *skb)
}
if (rt)
- rt6_set_expires(rt, jiffies + (HZ * lifetime));
+ fib6_set_expires(rt, jiffies + (HZ * lifetime));
if (in6_dev->cnf.accept_ra_min_hop_limit < 256 &&
ra_msg->icmph.icmp6_hop_limit) {
if (in6_dev->cnf.accept_ra_min_hop_limit <= ra_msg->icmph.icmp6_hop_limit) {
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 0f290c75905e..fc3ddcbe8899 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -435,7 +435,7 @@ static bool rt6_check_expired(const struct rt6_info *rt)
return true;
} else if (rt->from) {
return rt->dst.obsolete != DST_OBSOLETE_FORCE_CHK ||
- rt6_check_expired(rt->from);
+ fib6_check_expired(rt->from);
}
return false;
}
@@ -687,7 +687,7 @@ static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict,
!(strict & RT6_LOOKUP_F_IGNORE_LINKSTATE))
goto out;
- if (rt6_check_expired(rt))
+ if (fib6_check_expired(rt))
goto out;
m = rt6_score_route(rt, oif, strict);
@@ -871,9 +871,9 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
if (rt) {
if (!addrconf_finite_timeout(lifetime))
- rt6_clean_expires(rt);
+ fib6_clean_expires(rt);
else
- rt6_set_expires(rt, jiffies + HZ * lifetime);
+ fib6_set_expires(rt, jiffies + HZ * lifetime);
ip6_rt_put(rt);
}
@@ -2339,7 +2339,7 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
for_each_fib6_node_rt_rcu(fn) {
if (rt->fib6_nh.nh_flags & RTNH_F_DEAD)
continue;
- if (rt6_check_expired(rt))
+ if (fib6_check_expired(rt))
continue;
if (rt->rt6i_flags & RTF_REJECT)
break;
@@ -2865,10 +2865,10 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg,
goto out;
if (cfg->fc_flags & RTF_EXPIRES)
- rt6_set_expires(rt, jiffies +
+ fib6_set_expires(rt, jiffies +
clock_t_to_jiffies(cfg->fc_expires));
else
- rt6_clean_expires(rt);
+ fib6_clean_expires(rt);
if (cfg->fc_protocol == RTPROT_UNSPEC)
cfg->fc_protocol = RTPROT_BOOT;
@@ -4554,8 +4554,10 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
goto nla_put_failure;
}
- if (rt->rt6i_flags & RTF_EXPIRES && dst)
- expires = dst->expires - jiffies;
+ if (rt->rt6i_flags & RTF_EXPIRES) {
+ expires = dst ? dst->expires : rt->expires;
+ expires -= jiffies;
+ }
if (rtnl_put_cacheinfo(skb, dst, 0, expires, dst ? dst->error : 0) < 0)
goto nla_put_failure;
--
2.11.0
^ permalink raw reply related
* [PATCH RFC v2 net-next 08/21] net/ipv6: Move nexthop data to fib6_nh
From: David Ahern @ 2018-03-19 3:36 UTC (permalink / raw)
To: netdev
Cc: davem, idosch, roopa, eric.dumazet, weiwan, kafai, yoshfuji,
David Ahern
In-Reply-To: <20180319033622.16693-1-dsahern@gmail.com>
Introduce fib6_nh structure and move nexthop related data from
rt6_info and rt6_info.dst to fib6_nh. References to dev, gateway or
lwtstate from a FIB lookup perspective are converted to use fib6_nh;
datapath references to dst version are left as is.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
.../net/ethernet/mellanox/mlxsw/spectrum_router.c | 32 ++--
include/net/ip6_fib.h | 16 +-
include/net/ip6_route.h | 6 +-
net/ipv6/addrconf.c | 2 +-
net/ipv6/ip6_fib.c | 6 +-
net/ipv6/route.c | 162 +++++++++++----------
6 files changed, 125 insertions(+), 99 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 921bd1075edf..47ddcc2fd242 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -2704,9 +2704,9 @@ mlxsw_sp_nexthop6_group_cmp(const struct mlxsw_sp_nexthop_group *nh_grp,
struct in6_addr *gw;
int ifindex, weight;
- ifindex = mlxsw_sp_rt6->rt->dst.dev->ifindex;
- weight = mlxsw_sp_rt6->rt->rt6i_nh_weight;
- gw = &mlxsw_sp_rt6->rt->rt6i_gateway;
+ ifindex = mlxsw_sp_rt6->rt->fib6_nh.nh_dev->ifindex;
+ weight = mlxsw_sp_rt6->rt->fib6_nh.nh_weight;
+ gw = &mlxsw_sp_rt6->rt->fib6_nh.nh_gw;
if (!mlxsw_sp_nexthop6_group_has_nexthop(nh_grp, gw, ifindex,
weight))
return false;
@@ -2772,7 +2772,7 @@ mlxsw_sp_nexthop6_group_hash(struct mlxsw_sp_fib6_entry *fib6_entry, u32 seed)
struct net_device *dev;
list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) {
- dev = mlxsw_sp_rt6->rt->dst.dev;
+ dev = mlxsw_sp_rt6->rt->fib6_nh.nh_dev;
val ^= dev->ifindex;
}
@@ -3770,9 +3770,9 @@ mlxsw_sp_rt6_nexthop(struct mlxsw_sp_nexthop_group *nh_grp,
struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i];
struct rt6_info *rt = mlxsw_sp_rt6->rt;
- if (nh->rif && nh->rif->dev == rt->dst.dev &&
+ if (nh->rif && nh->rif->dev == rt->fib6_nh.nh_dev &&
ipv6_addr_equal((const struct in6_addr *) &nh->gw_addr,
- &rt->rt6i_gateway))
+ &rt->fib6_nh.nh_gw))
return nh;
continue;
}
@@ -3829,7 +3829,7 @@ mlxsw_sp_fib6_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry)
if (fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_LOCAL) {
list_first_entry(&fib6_entry->rt6_list, struct mlxsw_sp_rt6,
- list)->rt->rt6i_nh_flags |= RTNH_F_OFFLOAD;
+ list)->rt->fib6_nh.nh_flags |= RTNH_F_OFFLOAD;
return;
}
@@ -3839,9 +3839,9 @@ mlxsw_sp_fib6_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry)
nh = mlxsw_sp_rt6_nexthop(nh_grp, mlxsw_sp_rt6);
if (nh && nh->offloaded)
- mlxsw_sp_rt6->rt->rt6i_nh_flags |= RTNH_F_OFFLOAD;
+ mlxsw_sp_rt6->rt->fib6_nh.nh_flags |= RTNH_F_OFFLOAD;
else
- mlxsw_sp_rt6->rt->rt6i_nh_flags &= ~RTNH_F_OFFLOAD;
+ mlxsw_sp_rt6->rt->fib6_nh.nh_flags &= ~RTNH_F_OFFLOAD;
}
}
@@ -3856,7 +3856,7 @@ mlxsw_sp_fib6_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry)
list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) {
struct rt6_info *rt = mlxsw_sp_rt6->rt;
- rt->rt6i_nh_flags &= ~RTNH_F_OFFLOAD;
+ rt->fib6_nh.nh_flags &= ~RTNH_F_OFFLOAD;
}
}
@@ -4752,8 +4752,8 @@ static bool mlxsw_sp_nexthop6_ipip_type(const struct mlxsw_sp *mlxsw_sp,
const struct rt6_info *rt,
enum mlxsw_sp_ipip_type *ret)
{
- return rt->dst.dev &&
- mlxsw_sp_netdev_ipip_type(mlxsw_sp, rt->dst.dev, ret);
+ return rt->fib6_nh.nh_dev &&
+ mlxsw_sp_netdev_ipip_type(mlxsw_sp, rt->fib6_nh.nh_dev, ret);
}
static int mlxsw_sp_nexthop6_type_init(struct mlxsw_sp *mlxsw_sp,
@@ -4763,7 +4763,7 @@ static int mlxsw_sp_nexthop6_type_init(struct mlxsw_sp *mlxsw_sp,
{
const struct mlxsw_sp_ipip_ops *ipip_ops;
struct mlxsw_sp_ipip_entry *ipip_entry;
- struct net_device *dev = rt->dst.dev;
+ struct net_device *dev = rt->fib6_nh.nh_dev;
struct mlxsw_sp_rif *rif;
int err;
@@ -4806,11 +4806,11 @@ static int mlxsw_sp_nexthop6_init(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_nexthop *nh,
const struct rt6_info *rt)
{
- struct net_device *dev = rt->dst.dev;
+ struct net_device *dev = rt->fib6_nh.nh_dev;
nh->nh_grp = nh_grp;
- nh->nh_weight = rt->rt6i_nh_weight;
- memcpy(&nh->gw_addr, &rt->rt6i_gateway, sizeof(nh->gw_addr));
+ nh->nh_weight = rt->fib6_nh.nh_weight;
+ memcpy(&nh->gw_addr, &rt->fib6_nh.nh_gw, sizeof(nh->gw_addr));
mlxsw_sp_nexthop_counter_alloc(mlxsw_sp, nh);
list_add_tail(&nh->router_list_node, &mlxsw_sp->router->nexthop_list);
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 0165820bbafb..f0a88370ba95 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -127,6 +127,16 @@ struct rt6_exception {
#define FIB6_EXCEPTION_BUCKET_SIZE (1 << FIB6_EXCEPTION_BUCKET_SIZE_SHIFT)
#define FIB6_MAX_DEPTH 5
+struct fib6_nh {
+ struct in6_addr nh_gw;
+ struct net_device *nh_dev;
+ struct lwtunnel_state *nh_lwtstate;
+
+ unsigned int nh_flags;
+ atomic_t nh_upper_bound;
+ int nh_weight;
+};
+
struct rt6_info {
struct dst_entry dst;
struct rt6_info __rcu *rt6_next;
@@ -149,12 +159,9 @@ struct rt6_info {
*/
struct list_head rt6i_siblings;
unsigned int rt6i_nsiblings;
- atomic_t rt6i_nh_upper_bound;
atomic_t rt6i_ref;
- unsigned int rt6i_nh_flags;
-
/* These are in a separate cache line. */
struct rt6key rt6i_dst ____cacheline_aligned_in_smp;
u32 rt6i_flags;
@@ -171,13 +178,14 @@ struct rt6_info {
u32 rt6i_metric;
u32 rt6i_pmtu;
/* more non-fragment space at head required */
- int rt6i_nh_weight;
unsigned short rt6i_nfheader_len;
u8 rt6i_protocol;
u8 fib6_type;
u8 exception_bucket_flushed:1,
should_flush:1,
unused:6;
+
+ struct fib6_nh fib6_nh;
};
#define for_each_fib6_node_rt_rcu(fn) \
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index e486eb939f99..8b07c3fcd32d 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -267,10 +267,10 @@ static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt,
static inline bool rt6_duplicate_nexthop(struct rt6_info *a, struct rt6_info *b)
{
- return a->dst.dev == b->dst.dev &&
+ return a->fib6_nh.nh_dev == b->fib6_nh.nh_dev &&
a->rt6i_idev == b->rt6i_idev &&
- ipv6_addr_equal(&a->rt6i_gateway, &b->rt6i_gateway) &&
- !lwtunnel_cmp_encap(a->dst.lwtstate, b->dst.lwtstate);
+ ipv6_addr_equal(&a->fib6_nh.nh_gw, &b->fib6_nh.nh_gw) &&
+ !lwtunnel_cmp_encap(a->fib6_nh.nh_lwtstate, b->fib6_nh.nh_lwtstate);
}
#endif
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 2313d74ccf46..7d92c6e48d2e 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2381,7 +2381,7 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
goto out;
for_each_fib6_node_rt_rcu(fn) {
- if (rt->dst.dev->ifindex != dev->ifindex)
+ if (rt->fib6_nh.nh_dev->ifindex != dev->ifindex)
continue;
if ((rt->rt6i_flags & flags) != flags)
continue;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 29a9e835faac..7326edab2acb 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -2214,6 +2214,7 @@ static int ipv6_route_seq_show(struct seq_file *seq, void *v)
{
struct rt6_info *rt = v;
struct ipv6_route_iter *iter = seq->private;
+ const struct net_device *dev;
seq_printf(seq, "%pi6 %02x ", &rt->rt6i_dst.addr, rt->rt6i_dst.plen);
@@ -2223,14 +2224,15 @@ static int ipv6_route_seq_show(struct seq_file *seq, void *v)
seq_puts(seq, "00000000000000000000000000000000 00 ");
#endif
if (rt->rt6i_flags & RTF_GATEWAY)
- seq_printf(seq, "%pi6", &rt->rt6i_gateway);
+ seq_printf(seq, "%pi6", &rt->fib6_nh.nh_gw);
else
seq_puts(seq, "00000000000000000000000000000000");
+ dev = rt->fib6_nh.nh_dev;
seq_printf(seq, " %08x %08x %08x %08x %8s\n",
rt->rt6i_metric, atomic_read(&rt->dst.__refcnt),
rt->dst.__use, rt->rt6i_flags,
- rt->dst.dev ? rt->dst.dev->name : "");
+ dev ? dev->name : "");
iter->w.leaf = NULL;
return 0;
}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 8c3b26c42bd4..43e1ab7cdf4f 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -466,12 +466,15 @@ static struct rt6_info *rt6_multipath_select(const struct net *net,
if (!fl6->mp_hash)
fl6->mp_hash = rt6_multipath_hash(net, fl6, skb, NULL);
- if (fl6->mp_hash <= atomic_read(&match->rt6i_nh_upper_bound))
+ if (fl6->mp_hash <= atomic_read(&match->fib6_nh.nh_upper_bound))
return match;
list_for_each_entry_safe(sibling, next_sibling, &match->rt6i_siblings,
rt6i_siblings) {
- if (fl6->mp_hash > atomic_read(&sibling->rt6i_nh_upper_bound))
+ int nh_upper_bound;
+
+ nh_upper_bound = atomic_read(&sibling->fib6_nh.nh_upper_bound);
+ if (fl6->mp_hash > nh_upper_bound)
continue;
if (rt6_score_route(sibling, oif, strict) < 0)
break;
@@ -495,13 +498,14 @@ static inline struct rt6_info *rt6_device_match(struct net *net,
struct rt6_info *local = NULL;
struct rt6_info *sprt;
- if (!oif && ipv6_addr_any(saddr) && !(rt->rt6i_nh_flags & RTNH_F_DEAD))
+ if (!oif && ipv6_addr_any(saddr) &&
+ !(rt->fib6_nh.nh_flags & RTNH_F_DEAD))
return rt;
for (sprt = rt; sprt; sprt = rcu_dereference(sprt->rt6_next)) {
- struct net_device *dev = sprt->dst.dev;
+ const struct net_device *dev = sprt->fib6_nh.nh_dev;
- if (sprt->rt6i_nh_flags & RTNH_F_DEAD)
+ if (sprt->fib6_nh.nh_flags & RTNH_F_DEAD)
continue;
if (oif) {
@@ -533,7 +537,7 @@ static inline struct rt6_info *rt6_device_match(struct net *net,
return net->ipv6.ip6_null_entry;
}
- return rt->rt6i_nh_flags & RTNH_F_DEAD ? net->ipv6.ip6_null_entry : rt;
+ return rt->fib6_nh.nh_flags & RTNH_F_DEAD ? net->ipv6.ip6_null_entry : rt;
}
#ifdef CONFIG_IPV6_ROUTER_PREF
@@ -558,7 +562,10 @@ static void rt6_probe_deferred(struct work_struct *w)
static void rt6_probe(struct rt6_info *rt)
{
struct __rt6_probe_work *work;
+ const struct in6_addr *nh_gw;
struct neighbour *neigh;
+ struct net_device *dev;
+
/*
* Okay, this does not seem to be appropriate
* for now, however, we need to check if it
@@ -569,8 +576,11 @@ static void rt6_probe(struct rt6_info *rt)
*/
if (!rt || !(rt->rt6i_flags & RTF_GATEWAY))
return;
+
+ nh_gw = &rt->fib6_nh.nh_gw;
+ dev = rt->fib6_nh.nh_dev;
rcu_read_lock_bh();
- neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway);
+ neigh = __ipv6_neigh_lookup_noref(dev, nh_gw);
if (neigh) {
if (neigh->nud_state & NUD_VALID)
goto out;
@@ -592,9 +602,9 @@ static void rt6_probe(struct rt6_info *rt)
if (work) {
INIT_WORK(&work->work, rt6_probe_deferred);
- work->target = rt->rt6i_gateway;
- dev_hold(rt->dst.dev);
- work->dev = rt->dst.dev;
+ work->target = *nh_gw;
+ dev_hold(dev);
+ work->dev = dev;
schedule_work(&work->work);
}
@@ -612,7 +622,8 @@ static inline void rt6_probe(struct rt6_info *rt)
*/
static inline int rt6_check_dev(struct rt6_info *rt, int oif)
{
- struct net_device *dev = rt->dst.dev;
+ const struct net_device *dev = rt->fib6_nh.nh_dev;
+
if (!oif || dev->ifindex == oif)
return 2;
if ((dev->flags & IFF_LOOPBACK) &&
@@ -623,15 +634,16 @@ static inline int rt6_check_dev(struct rt6_info *rt, int oif)
static inline enum rt6_nud_state rt6_check_neigh(struct rt6_info *rt)
{
- struct neighbour *neigh;
enum rt6_nud_state ret = RT6_NUD_FAIL_HARD;
+ struct neighbour *neigh;
if (rt->rt6i_flags & RTF_NONEXTHOP ||
!(rt->rt6i_flags & RTF_GATEWAY))
return RT6_NUD_SUCCEED;
rcu_read_lock_bh();
- neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway);
+ neigh = __ipv6_neigh_lookup_noref(rt->fib6_nh.nh_dev,
+ &rt->fib6_nh.nh_gw);
if (neigh) {
read_lock(&neigh->lock);
if (neigh->nud_state & NUD_VALID)
@@ -679,11 +691,11 @@ static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict,
bool match_do_rr = false;
struct inet6_dev *idev = rt->rt6i_idev;
- if (rt->rt6i_nh_flags & RTNH_F_DEAD)
+ if (rt->fib6_nh.nh_flags & RTNH_F_DEAD)
goto out;
if (idev->cnf.ignore_routes_with_linkdown &&
- rt->rt6i_nh_flags & RTNH_F_LINKDOWN &&
+ rt->fib6_nh.nh_flags & RTNH_F_LINKDOWN &&
!(strict & RT6_LOOKUP_F_IGNORE_LINKSTATE))
goto out;
@@ -888,7 +900,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
/* called with rcu_lock held */
static struct net_device *ip6_rt_get_dev_rcu(struct rt6_info *rt)
{
- struct net_device *dev = rt->dst.dev;
+ struct net_device *dev = rt->fib6_nh.nh_dev;
if (rt->rt6i_flags & (RTF_LOCAL | RTF_ANYCAST)) {
/* for copies of local routes, dst->dev needs to be the
@@ -928,7 +940,7 @@ static void ip6_rt_copy_init(struct rt6_info *rt, struct rt6_info *ort)
if (rt->rt6i_idev)
in6_dev_hold(rt->rt6i_idev);
rt->dst.lastuse = jiffies;
- rt->rt6i_gateway = ort->rt6i_gateway;
+ rt->rt6i_gateway = ort->fib6_nh.nh_gw;
rt->rt6i_flags = ort->rt6i_flags;
rt6_set_from(rt, ort);
rt->rt6i_metric = ort->rt6i_metric;
@@ -937,7 +949,7 @@ static void ip6_rt_copy_init(struct rt6_info *rt, struct rt6_info *ort)
#endif
rt->rt6i_prefsrc = ort->rt6i_prefsrc;
rt->rt6i_table = ort->rt6i_table;
- rt->dst.lwtstate = lwtstate_get(ort->dst.lwtstate);
+ rt->dst.lwtstate = lwtstate_get(ort->fib6_nh.nh_lwtstate);
}
static struct fib6_node* fib6_backtrack(struct fib6_node *fn,
@@ -1305,7 +1317,7 @@ __rt6_find_exception_rcu(struct rt6_exception_bucket **bucket,
static int rt6_insert_exception(struct rt6_info *nrt,
struct rt6_info *ort)
{
- struct net *net = dev_net(ort->dst.dev);
+ struct net *net = dev_net(nrt->dst.dev);
struct rt6_exception_bucket *bucket;
struct in6_addr *src_key = NULL;
struct rt6_exception *rt6_ex;
@@ -2267,7 +2279,7 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
restart:
for_each_fib6_node_rt_rcu(fn) {
- if (rt->rt6i_nh_flags & RTNH_F_DEAD)
+ if (rt->fib6_nh.nh_flags & RTNH_F_DEAD)
continue;
if (rt6_check_expired(rt))
continue;
@@ -2275,14 +2287,14 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
break;
if (!(rt->rt6i_flags & RTF_GATEWAY))
continue;
- if (fl6->flowi6_oif != rt->dst.dev->ifindex)
+ if (fl6->flowi6_oif != rt->fib6_nh.nh_dev->ifindex)
continue;
/* rt_cache's gateway might be different from its 'parent'
* in the case of an ip redirect.
* So we keep searching in the exception table if the gateway
* is different.
*/
- if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway)) {
+ if (!ipv6_addr_equal(&rdfl->gateway, &rt->fib6_nh.nh_gw)) {
rt_cache = rt6_find_cached_rt(rt,
&fl6->daddr,
&fl6->saddr);
@@ -2859,7 +2871,7 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg,
&lwtstate, extack);
if (err)
goto out;
- rt->dst.lwtstate = lwtstate_get(lwtstate);
+ rt->fib6_nh.nh_lwtstate = lwtstate_get(lwtstate);
lwtunnel_set_redirect(&rt->dst);
}
@@ -2874,7 +2886,7 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg,
#endif
rt->rt6i_metric = cfg->fc_metric;
- rt->rt6i_nh_weight = 1;
+ rt->fib6_nh.nh_weight = 1;
rt->fib6_type = cfg->fc_type;
@@ -2929,7 +2941,7 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg,
if (err)
goto out;
- rt->rt6i_gateway = cfg->fc_gateway;
+ rt->fib6_nh.nh_gw = rt->rt6i_gateway = cfg->fc_gateway;
}
err = -ENODEV;
@@ -2958,9 +2970,9 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg,
install_route:
if (!(rt->rt6i_flags & (RTF_LOCAL | RTF_ANYCAST)) &&
!netif_carrier_ok(dev))
- rt->rt6i_nh_flags |= RTNH_F_LINKDOWN;
- rt->rt6i_nh_flags |= (cfg->fc_flags & RTNH_F_ONLINK);
- rt->dst.dev = dev;
+ rt->fib6_nh.nh_flags |= RTNH_F_LINKDOWN;
+ rt->fib6_nh.nh_flags |= (cfg->fc_flags & RTNH_F_ONLINK);
+ rt->fib6_nh.nh_dev = rt->dst.dev = dev;
rt->rt6i_idev = idev;
rt->rt6i_table = table;
@@ -3119,11 +3131,11 @@ static int ip6_route_del(struct fib6_config *cfg,
rt = rt_cache;
}
if (cfg->fc_ifindex &&
- (!rt->dst.dev ||
- rt->dst.dev->ifindex != cfg->fc_ifindex))
+ (!rt->fib6_nh.nh_dev ||
+ rt->fib6_nh.nh_dev->ifindex != cfg->fc_ifindex))
continue;
if (cfg->fc_flags & RTF_GATEWAY &&
- !ipv6_addr_equal(&cfg->fc_gateway, &rt->rt6i_gateway))
+ !ipv6_addr_equal(&cfg->fc_gateway, &rt->fib6_nh.nh_gw))
continue;
if (cfg->fc_metric && cfg->fc_metric != rt->rt6i_metric)
continue;
@@ -3285,11 +3297,11 @@ static struct rt6_info *rt6_get_route_info(struct net *net,
goto out;
for_each_fib6_node_rt_rcu(fn) {
- if (rt->dst.dev->ifindex != ifindex)
+ if (rt->fib6_nh.nh_dev->ifindex != ifindex)
continue;
if ((rt->rt6i_flags & (RTF_ROUTEINFO|RTF_GATEWAY)) != (RTF_ROUTEINFO|RTF_GATEWAY))
continue;
- if (!ipv6_addr_equal(&rt->rt6i_gateway, gwaddr))
+ if (!ipv6_addr_equal(&rt->fib6_nh.nh_gw, gwaddr))
continue;
ip6_hold_safe(NULL, &rt, false);
break;
@@ -3346,9 +3358,9 @@ struct rt6_info *rt6_get_dflt_router(struct net *net,
rcu_read_lock();
for_each_fib6_node_rt_rcu(&table->tb6_root) {
- if (dev == rt->dst.dev &&
+ if (dev == rt->fib6_nh.nh_dev &&
((rt->rt6i_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) &&
- ipv6_addr_equal(&rt->rt6i_gateway, addr))
+ ipv6_addr_equal(&rt->fib6_nh.nh_gw, addr))
break;
}
if (rt)
@@ -3574,6 +3586,8 @@ struct rt6_info *addrconf_dst_alloc(struct net *net,
rt->rt6i_flags |= RTF_LOCAL;
}
+ rt->fib6_nh.nh_gw = *addr;
+ rt->fib6_nh.nh_dev = dev;
rt->rt6i_gateway = *addr;
rt->rt6i_dst.addr = *addr;
rt->rt6i_dst.plen = 128;
@@ -3596,7 +3610,7 @@ static int fib6_remove_prefsrc(struct rt6_info *rt, void *arg)
struct net *net = ((struct arg_dev_net_ip *)arg)->net;
struct in6_addr *addr = ((struct arg_dev_net_ip *)arg)->addr;
- if (((void *)rt->dst.dev == dev || !dev) &&
+ if (((void *)rt->fib6_nh.nh_dev == dev || !dev) &&
rt != net->ipv6.ip6_null_entry &&
ipv6_addr_equal(addr, &rt->rt6i_prefsrc.addr)) {
spin_lock_bh(&rt6_exception_lock);
@@ -3628,7 +3642,7 @@ static int fib6_clean_tohost(struct rt6_info *rt, void *arg)
struct in6_addr *gateway = (struct in6_addr *)arg;
if (((rt->rt6i_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) &&
- ipv6_addr_equal(gateway, &rt->rt6i_gateway)) {
+ ipv6_addr_equal(gateway, &rt->fib6_nh.nh_gw)) {
return -1;
}
@@ -3676,8 +3690,8 @@ static struct rt6_info *rt6_multipath_first_sibling(const struct rt6_info *rt)
static bool rt6_is_dead(const struct rt6_info *rt)
{
- if (rt->rt6i_nh_flags & RTNH_F_DEAD ||
- (rt->rt6i_nh_flags & RTNH_F_LINKDOWN &&
+ if (rt->fib6_nh.nh_flags & RTNH_F_DEAD ||
+ (rt->fib6_nh.nh_flags & RTNH_F_LINKDOWN &&
rt->rt6i_idev->cnf.ignore_routes_with_linkdown))
return true;
@@ -3690,11 +3704,11 @@ static int rt6_multipath_total_weight(const struct rt6_info *rt)
int total = 0;
if (!rt6_is_dead(rt))
- total += rt->rt6i_nh_weight;
+ total += rt->fib6_nh.nh_weight;
list_for_each_entry(iter, &rt->rt6i_siblings, rt6i_siblings) {
if (!rt6_is_dead(iter))
- total += iter->rt6i_nh_weight;
+ total += iter->fib6_nh.nh_weight;
}
return total;
@@ -3705,11 +3719,11 @@ static void rt6_upper_bound_set(struct rt6_info *rt, int *weight, int total)
int upper_bound = -1;
if (!rt6_is_dead(rt)) {
- *weight += rt->rt6i_nh_weight;
+ *weight += rt->fib6_nh.nh_weight;
upper_bound = DIV_ROUND_CLOSEST_ULL((u64) (*weight) << 31,
total) - 1;
}
- atomic_set(&rt->rt6i_nh_upper_bound, upper_bound);
+ atomic_set(&rt->fib6_nh.nh_upper_bound, upper_bound);
}
static void rt6_multipath_upper_bound_set(struct rt6_info *rt, int total)
@@ -3752,8 +3766,8 @@ static int fib6_ifup(struct rt6_info *rt, void *p_arg)
const struct arg_netdev_event *arg = p_arg;
struct net *net = dev_net(arg->dev);
- if (rt != net->ipv6.ip6_null_entry && rt->dst.dev == arg->dev) {
- rt->rt6i_nh_flags &= ~arg->nh_flags;
+ if (rt != net->ipv6.ip6_null_entry && rt->fib6_nh.nh_dev == arg->dev) {
+ rt->fib6_nh.nh_flags &= ~arg->nh_flags;
fib6_update_sernum_upto_root(net, rt);
rt6_multipath_rebalance(rt);
}
@@ -3781,10 +3795,10 @@ static bool rt6_multipath_uses_dev(const struct rt6_info *rt,
{
struct rt6_info *iter;
- if (rt->dst.dev == dev)
+ if (rt->fib6_nh.nh_dev == dev)
return true;
list_for_each_entry(iter, &rt->rt6i_siblings, rt6i_siblings)
- if (iter->dst.dev == dev)
+ if (iter->fib6_nh.nh_dev == dev)
return true;
return false;
@@ -3805,11 +3819,12 @@ static unsigned int rt6_multipath_dead_count(const struct rt6_info *rt,
struct rt6_info *iter;
unsigned int dead = 0;
- if (rt->dst.dev == down_dev || rt->rt6i_nh_flags & RTNH_F_DEAD)
+ if (rt->fib6_nh.nh_dev == down_dev ||
+ rt->fib6_nh.nh_flags & RTNH_F_DEAD)
dead++;
list_for_each_entry(iter, &rt->rt6i_siblings, rt6i_siblings)
- if (iter->dst.dev == down_dev ||
- iter->rt6i_nh_flags & RTNH_F_DEAD)
+ if (iter->fib6_nh.nh_dev == down_dev ||
+ iter->fib6_nh.nh_flags & RTNH_F_DEAD)
dead++;
return dead;
@@ -3821,11 +3836,11 @@ static void rt6_multipath_nh_flags_set(struct rt6_info *rt,
{
struct rt6_info *iter;
- if (rt->dst.dev == dev)
- rt->rt6i_nh_flags |= nh_flags;
+ if (rt->fib6_nh.nh_dev == dev)
+ rt->fib6_nh.nh_flags |= nh_flags;
list_for_each_entry(iter, &rt->rt6i_siblings, rt6i_siblings)
- if (iter->dst.dev == dev)
- iter->rt6i_nh_flags |= nh_flags;
+ if (iter->fib6_nh.nh_dev == dev)
+ iter->fib6_nh.nh_flags |= nh_flags;
}
/* called with write lock held for table with rt */
@@ -3840,12 +3855,12 @@ static int fib6_ifdown(struct rt6_info *rt, void *p_arg)
switch (arg->event) {
case NETDEV_UNREGISTER:
- return rt->dst.dev == dev ? -1 : 0;
+ return rt->fib6_nh.nh_dev == dev ? -1 : 0;
case NETDEV_DOWN:
if (rt->should_flush)
return -1;
if (!rt->rt6i_nsiblings)
- return rt->dst.dev == dev ? -1 : 0;
+ return rt->fib6_nh.nh_dev == dev ? -1 : 0;
if (rt6_multipath_uses_dev(rt, dev)) {
unsigned int count;
@@ -3861,10 +3876,10 @@ static int fib6_ifdown(struct rt6_info *rt, void *p_arg)
}
return -2;
case NETDEV_CHANGE:
- if (rt->dst.dev != dev ||
+ if (rt->fib6_nh.nh_dev != dev ||
rt->rt6i_flags & (RTF_LOCAL | RTF_ANYCAST))
break;
- rt->rt6i_nh_flags |= RTNH_F_LINKDOWN;
+ rt->fib6_nh.nh_flags |= RTNH_F_LINKDOWN;
rt6_multipath_rebalance(rt);
break;
}
@@ -3925,7 +3940,7 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg)
also have the lowest MTU, TOO BIG MESSAGE will be lead to
PMTU discovery.
*/
- if (rt->dst.dev == arg->dev &&
+ if (rt->fib6_nh.nh_dev == arg->dev &&
dst_metric_raw(&rt->dst, RTAX_MTU) &&
!dst_metric_locked(&rt->dst, RTAX_MTU)) {
spin_lock_bh(&rt6_exception_lock);
@@ -4213,7 +4228,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
goto cleanup;
}
- rt->rt6i_nh_weight = rtnh->rtnh_hops + 1;
+ rt->fib6_nh.nh_weight = rtnh->rtnh_hops + 1;
err = ip6_route_info_append(&rt6_nh_list, rt, &r_cfg);
if (err) {
@@ -4370,7 +4385,7 @@ static size_t rt6_nlmsg_size(struct rt6_info *rt)
nexthop_len = nla_total_size(0) /* RTA_MULTIPATH */
+ NLA_ALIGN(sizeof(struct rtnexthop))
+ nla_total_size(16) /* RTA_GATEWAY */
- + lwtunnel_get_encap_size(rt->dst.lwtstate);
+ + lwtunnel_get_encap_size(rt->fib6_nh.nh_lwtstate);
nexthop_len *= rt->rt6i_nsiblings;
}
@@ -4388,38 +4403,38 @@ static size_t rt6_nlmsg_size(struct rt6_info *rt)
+ nla_total_size(sizeof(struct rta_cacheinfo))
+ nla_total_size(TCP_CA_NAME_MAX) /* RTAX_CC_ALGO */
+ nla_total_size(1) /* RTA_PREF */
- + lwtunnel_get_encap_size(rt->dst.lwtstate)
+ + lwtunnel_get_encap_size(rt->fib6_nh.nh_lwtstate)
+ nexthop_len;
}
static int rt6_nexthop_info(struct sk_buff *skb, struct rt6_info *rt,
unsigned int *flags, bool skip_oif)
{
- if (rt->rt6i_nh_flags & RTNH_F_DEAD)
+ if (rt->fib6_nh.nh_flags & RTNH_F_DEAD)
*flags |= RTNH_F_DEAD;
- if (rt->rt6i_nh_flags & RTNH_F_LINKDOWN) {
+ if (rt->fib6_nh.nh_flags & RTNH_F_LINKDOWN) {
*flags |= RTNH_F_LINKDOWN;
if (rt->rt6i_idev->cnf.ignore_routes_with_linkdown)
*flags |= RTNH_F_DEAD;
}
if (rt->rt6i_flags & RTF_GATEWAY) {
- if (nla_put_in6_addr(skb, RTA_GATEWAY, &rt->rt6i_gateway) < 0)
+ if (nla_put_in6_addr(skb, RTA_GATEWAY, &rt->fib6_nh.nh_gw) < 0)
goto nla_put_failure;
}
- *flags |= (rt->rt6i_nh_flags & RTNH_F_ONLINK);
- if (rt->rt6i_nh_flags & RTNH_F_OFFLOAD)
+ *flags |= (rt->fib6_nh.nh_flags & RTNH_F_ONLINK);
+ if (rt->fib6_nh.nh_flags & RTNH_F_OFFLOAD)
*flags |= RTNH_F_OFFLOAD;
/* not needed for multipath encoding b/c it has a rtnexthop struct */
- if (!skip_oif && rt->dst.dev &&
- nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex))
+ if (!skip_oif && rt->fib6_nh.nh_dev &&
+ nla_put_u32(skb, RTA_OIF, rt->fib6_nh.nh_dev->ifindex))
goto nla_put_failure;
- if (rt->dst.lwtstate &&
- lwtunnel_fill_encap(skb, rt->dst.lwtstate) < 0)
+ if (rt->fib6_nh.nh_lwtstate &&
+ lwtunnel_fill_encap(skb, rt->fib6_nh.nh_lwtstate) < 0)
goto nla_put_failure;
return 0;
@@ -4431,6 +4446,7 @@ static int rt6_nexthop_info(struct sk_buff *skb, struct rt6_info *rt,
/* add multipath next hop */
static int rt6_add_nexthop(struct sk_buff *skb, struct rt6_info *rt)
{
+ const struct net_device *dev = rt->fib6_nh.nh_dev;
struct rtnexthop *rtnh;
unsigned int flags = 0;
@@ -4438,8 +4454,8 @@ static int rt6_add_nexthop(struct sk_buff *skb, struct rt6_info *rt)
if (!rtnh)
goto nla_put_failure;
- rtnh->rtnh_hops = rt->rt6i_nh_weight - 1;
- rtnh->rtnh_ifindex = rt->dst.dev ? rt->dst.dev->ifindex : 0;
+ rtnh->rtnh_hops = rt->fib6_nh.nh_weight - 1;
+ rtnh->rtnh_ifindex = dev ? dev->ifindex : 0;
if (rt6_nexthop_info(skb, rt, &flags, true) < 0)
goto nla_put_failure;
--
2.11.0
^ permalink raw reply related
* [PATCH RFC v2 net-next 07/21] net/ipv6: Save route type in rt6_info
From: David Ahern @ 2018-03-19 3:36 UTC (permalink / raw)
To: netdev
Cc: davem, idosch, roopa, eric.dumazet, weiwan, kafai, yoshfuji,
David Ahern
In-Reply-To: <20180319033622.16693-1-dsahern@gmail.com>
The RTN_ type for IPv6 FIB entries is currently embedded in rt6i_flags
and dst.error. Since dst is going to be removed, it can no longer be
relied on for FIB dumps so save the route type as fib6_type.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/net/ip6_fib.h | 1 +
net/ipv6/addrconf.c | 2 ++
net/ipv6/route.c | 46 ++++++++++++++++++++--------------------------
3 files changed, 23 insertions(+), 26 deletions(-)
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index f0aaf1c8f1a8..0165820bbafb 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -174,6 +174,7 @@ struct rt6_info {
int rt6i_nh_weight;
unsigned short rt6i_nfheader_len;
u8 rt6i_protocol;
+ u8 fib6_type;
u8 exception_bucket_flushed:1,
should_flush:1,
unused:6;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 2b0aa6d7eb17..2313d74ccf46 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2343,6 +2343,7 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev,
.fc_flags = RTF_UP | flags,
.fc_nlinfo.nl_net = dev_net(dev),
.fc_protocol = RTPROT_KERNEL,
+ .fc_type = RTN_UNICAST,
};
cfg.fc_dst = *pfx;
@@ -2406,6 +2407,7 @@ static void addrconf_add_mroute(struct net_device *dev)
.fc_ifindex = dev->ifindex,
.fc_dst_len = 8,
.fc_flags = RTF_UP,
+ .fc_type = RTN_UNICAST,
.fc_nlinfo.nl_net = dev_net(dev),
};
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 662798496720..8c3b26c42bd4 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -307,6 +307,7 @@ static const struct rt6_info ip6_null_entry_template = {
.rt6i_protocol = RTPROT_KERNEL,
.rt6i_metric = ~(u32) 0,
.rt6i_ref = ATOMIC_INIT(1),
+ .fib6_type = RTN_UNREACHABLE,
};
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
@@ -324,6 +325,7 @@ static const struct rt6_info ip6_prohibit_entry_template = {
.rt6i_protocol = RTPROT_KERNEL,
.rt6i_metric = ~(u32) 0,
.rt6i_ref = ATOMIC_INIT(1),
+ .fib6_type = RTN_PROHIBIT,
};
static const struct rt6_info ip6_blk_hole_entry_template = {
@@ -339,6 +341,7 @@ static const struct rt6_info ip6_blk_hole_entry_template = {
.rt6i_protocol = RTPROT_KERNEL,
.rt6i_metric = ~(u32) 0,
.rt6i_ref = ATOMIC_INIT(1),
+ .fib6_type = RTN_BLACKHOLE,
};
#endif
@@ -2756,6 +2759,11 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg,
goto out;
}
+ if (cfg->fc_type > RTN_MAX) {
+ NL_SET_ERR_MSG(extack, "Invalid route type");
+ goto out;
+ }
+
if (cfg->fc_dst_len > 128) {
NL_SET_ERR_MSG(extack, "Invalid prefix length");
goto out;
@@ -2868,6 +2876,8 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg,
rt->rt6i_metric = cfg->fc_metric;
rt->rt6i_nh_weight = 1;
+ rt->fib6_type = cfg->fc_type;
+
/* We cannot add true routes via loopback here,
they would result in kernel looping; promote them to reject routes
*/
@@ -3302,6 +3312,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net,
.fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO |
RTF_UP | RTF_PREF(pref),
.fc_protocol = RTPROT_RA,
+ .fc_type = RTN_UNICAST,
.fc_nlinfo.portid = 0,
.fc_nlinfo.nlh = NULL,
.fc_nlinfo.nl_net = net,
@@ -3358,6 +3369,7 @@ struct rt6_info *rt6_add_dflt_router(struct net *net,
.fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT |
RTF_UP | RTF_EXPIRES | RTF_PREF(pref),
.fc_protocol = RTPROT_RA,
+ .fc_type = RTN_UNICAST,
.fc_nlinfo.portid = 0,
.fc_nlinfo.nlh = NULL,
.fc_nlinfo.nl_net = net,
@@ -3433,6 +3445,7 @@ static void rtmsg_to_fib6_config(struct net *net,
cfg->fc_dst_len = rtmsg->rtmsg_dst_len;
cfg->fc_src_len = rtmsg->rtmsg_src_len;
cfg->fc_flags = rtmsg->rtmsg_flags;
+ cfg->fc_type = rtmsg->rtmsg_type;
cfg->fc_nlinfo.nl_net = net;
@@ -3553,10 +3566,13 @@ struct rt6_info *addrconf_dst_alloc(struct net *net,
rt->rt6i_protocol = RTPROT_KERNEL;
rt->rt6i_flags = RTF_UP | RTF_NONEXTHOP;
- if (anycast)
+ if (anycast) {
+ rt->fib6_type = RTN_ANYCAST;
rt->rt6i_flags |= RTF_ANYCAST;
- else
+ } else {
+ rt->fib6_type = RTN_LOCAL;
rt->rt6i_flags |= RTF_LOCAL;
+ }
rt->rt6i_gateway = *addr;
rt->rt6i_dst.addr = *addr;
@@ -4467,30 +4483,8 @@ static int rt6_fill_node(struct net *net,
rtm->rtm_table = table;
if (nla_put_u32(skb, RTA_TABLE, table))
goto nla_put_failure;
- if (rt->rt6i_flags & RTF_REJECT) {
- switch (rt->dst.error) {
- case -EINVAL:
- rtm->rtm_type = RTN_BLACKHOLE;
- break;
- case -EACCES:
- rtm->rtm_type = RTN_PROHIBIT;
- break;
- case -EAGAIN:
- rtm->rtm_type = RTN_THROW;
- break;
- default:
- rtm->rtm_type = RTN_UNREACHABLE;
- break;
- }
- }
- else if (rt->rt6i_flags & RTF_LOCAL)
- rtm->rtm_type = RTN_LOCAL;
- else if (rt->rt6i_flags & RTF_ANYCAST)
- rtm->rtm_type = RTN_ANYCAST;
- else if (rt->dst.dev && (rt->dst.dev->flags & IFF_LOOPBACK))
- rtm->rtm_type = RTN_LOCAL;
- else
- rtm->rtm_type = RTN_UNICAST;
+
+ rtm->rtm_type = rt->fib6_type;
rtm->rtm_flags = 0;
rtm->rtm_scope = RT_SCOPE_UNIVERSE;
rtm->rtm_protocol = rt->rt6i_protocol;
--
2.11.0
^ permalink raw reply related
* [PATCH RFC v2 net-next 06/21] net/ipv6: Move support functions up in route.c
From: David Ahern @ 2018-03-19 3:36 UTC (permalink / raw)
To: netdev
Cc: davem, idosch, roopa, eric.dumazet, weiwan, kafai, yoshfuji,
David Ahern
In-Reply-To: <20180319033622.16693-1-dsahern@gmail.com>
Code move only.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
net/ipv6/route.c | 119 +++++++++++++++++++++++++++----------------------------
1 file changed, 59 insertions(+), 60 deletions(-)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 049bb5c3a824..662798496720 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -78,7 +78,6 @@ enum rt6_nud_state {
RT6_NUD_SUCCEED = 1
};
-static void ip6_rt_copy_init(struct rt6_info *rt, struct rt6_info *ort);
static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie);
static unsigned int ip6_default_advmss(const struct dst_entry *dst);
static unsigned int ip6_mtu(const struct dst_entry *dst);
@@ -879,6 +878,65 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
}
#endif
+/*
+ * Misc support functions
+ */
+
+/* called with rcu_lock held */
+static struct net_device *ip6_rt_get_dev_rcu(struct rt6_info *rt)
+{
+ struct net_device *dev = rt->dst.dev;
+
+ if (rt->rt6i_flags & (RTF_LOCAL | RTF_ANYCAST)) {
+ /* for copies of local routes, dst->dev needs to be the
+ * device if it is a master device, the master device if
+ * device is enslaved, and the loopback as the default
+ */
+ if (netif_is_l3_slave(dev) &&
+ !rt6_need_strict(&rt->rt6i_dst.addr))
+ dev = l3mdev_master_dev_rcu(dev);
+ else if (!netif_is_l3_master(dev))
+ dev = dev_net(dev)->loopback_dev;
+ /* last case is netif_is_l3_master(dev) is true in which
+ * case we want dev returned to be dev
+ */
+ }
+
+ return dev;
+}
+
+static void rt6_set_from(struct rt6_info *rt, struct rt6_info *from)
+{
+ BUG_ON(from->from);
+
+ rt->rt6i_flags &= ~RTF_EXPIRES;
+ dst_hold(&from->dst);
+ rt->from = from;
+ dst_init_metrics(&rt->dst, dst_metrics_ptr(&from->dst), true);
+}
+
+static void ip6_rt_copy_init(struct rt6_info *rt, struct rt6_info *ort)
+{
+ rt->dst.input = ort->dst.input;
+ rt->dst.output = ort->dst.output;
+ rt->rt6i_dst = ort->rt6i_dst;
+ rt->dst.error = ort->dst.error;
+ rt->rt6i_idev = ort->rt6i_idev;
+ if (rt->rt6i_idev)
+ in6_dev_hold(rt->rt6i_idev);
+ rt->dst.lastuse = jiffies;
+ rt->rt6i_gateway = ort->rt6i_gateway;
+ rt->rt6i_flags = ort->rt6i_flags;
+ rt6_set_from(rt, ort);
+ rt->rt6i_metric = ort->rt6i_metric;
+#ifdef CONFIG_IPV6_SUBTREES
+ rt->rt6i_src = ort->rt6i_src;
+#endif
+ rt->rt6i_prefsrc = ort->rt6i_prefsrc;
+ rt->rt6i_table = ort->rt6i_table;
+ rt->dst.lwtstate = lwtstate_get(ort->dst.lwtstate);
+}
+
static struct fib6_node* fib6_backtrack(struct fib6_node *fn,
struct in6_addr *saddr)
{
@@ -1021,29 +1079,6 @@ int ip6_ins_rt(struct net *net, struct rt6_info *rt)
return __ip6_ins_rt(rt, &info, &mxc, NULL);
}
-/* called with rcu_lock held */
-static struct net_device *ip6_rt_get_dev_rcu(struct rt6_info *rt)
-{
- struct net_device *dev = rt->dst.dev;
-
- if (rt->rt6i_flags & (RTF_LOCAL | RTF_ANYCAST)) {
- /* for copies of local routes, dst->dev needs to be the
- * device if it is a master device, the master device if
- * device is enslaved, and the loopback as the default
- */
- if (netif_is_l3_slave(dev) &&
- !rt6_need_strict(&rt->rt6i_dst.addr))
- dev = l3mdev_master_dev_rcu(dev);
- else if (!netif_is_l3_master(dev))
- dev = dev_net(dev)->loopback_dev;
- /* last case is netif_is_l3_master(dev) is true in which
- * case we want dev returned to be dev
- */
- }
-
- return dev;
-}
-
static struct rt6_info *ip6_rt_cache_alloc(struct rt6_info *ort,
const struct in6_addr *daddr,
const struct in6_addr *saddr)
@@ -3218,42 +3253,6 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
neigh_release(neigh);
}
-/*
- * Misc support functions
- */
-
-static void rt6_set_from(struct rt6_info *rt, struct rt6_info *from)
-{
- BUG_ON(from->from);
-
- rt->rt6i_flags &= ~RTF_EXPIRES;
- dst_hold(&from->dst);
- rt->from = from;
- dst_init_metrics(&rt->dst, dst_metrics_ptr(&from->dst), true);
-}
-
-static void ip6_rt_copy_init(struct rt6_info *rt, struct rt6_info *ort)
-{
- rt->dst.input = ort->dst.input;
- rt->dst.output = ort->dst.output;
- rt->rt6i_dst = ort->rt6i_dst;
- rt->dst.error = ort->dst.error;
- rt->rt6i_idev = ort->rt6i_idev;
- if (rt->rt6i_idev)
- in6_dev_hold(rt->rt6i_idev);
- rt->dst.lastuse = jiffies;
- rt->rt6i_gateway = ort->rt6i_gateway;
- rt->rt6i_flags = ort->rt6i_flags;
- rt6_set_from(rt, ort);
- rt->rt6i_metric = ort->rt6i_metric;
-#ifdef CONFIG_IPV6_SUBTREES
- rt->rt6i_src = ort->rt6i_src;
-#endif
- rt->rt6i_prefsrc = ort->rt6i_prefsrc;
- rt->rt6i_table = ort->rt6i_table;
- rt->dst.lwtstate = lwtstate_get(ort->dst.lwtstate);
-}
-
#ifdef CONFIG_IPV6_ROUTE_INFO
static struct rt6_info *rt6_get_route_info(struct net *net,
const struct in6_addr *prefix, int prefixlen,
--
2.11.0
^ permalink raw reply related
* [PATCH RFC v2 net-next 05/21] net/ipv6: Pass net namespace to route functions
From: David Ahern @ 2018-03-19 3:36 UTC (permalink / raw)
To: netdev
Cc: davem, idosch, roopa, eric.dumazet, weiwan, kafai, yoshfuji,
David Ahern
In-Reply-To: <20180319033622.16693-1-dsahern@gmail.com>
Pass network namespace reference into route add, delete and get
functions.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/net/ip6_route.h | 12 ++++++-----
net/ipv6/addrconf.c | 33 ++++++++++++++++--------------
net/ipv6/anycast.c | 10 +++++----
net/ipv6/ndisc.c | 12 ++++++-----
net/ipv6/route.c | 54 +++++++++++++++++++++++++------------------------
5 files changed, 66 insertions(+), 55 deletions(-)
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index ce2abc0ff102..e486eb939f99 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -101,8 +101,8 @@ void ip6_route_cleanup(void);
int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg);
int ip6_route_add(struct fib6_config *cfg, struct netlink_ext_ack *extack);
-int ip6_ins_rt(struct rt6_info *);
-int ip6_del_rt(struct rt6_info *);
+int ip6_ins_rt(struct net *net, struct rt6_info *rt);
+int ip6_del_rt(struct net *net, struct rt6_info *rt);
void rt6_flush_exceptions(struct rt6_info *rt);
int rt6_remove_exception_rt(struct rt6_info *rt);
@@ -137,7 +137,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, struct flowi6 *fl6);
void fib6_force_start_gc(struct net *net);
-struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
+struct rt6_info *addrconf_dst_alloc(struct net *net, struct inet6_dev *idev,
const struct in6_addr *addr, bool anycast);
struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev,
@@ -147,9 +147,11 @@ struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev,
* support functions for ND
*
*/
-struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr,
+struct rt6_info *rt6_get_dflt_router(struct net *net,
+ const struct in6_addr *addr,
struct net_device *dev);
-struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr,
+struct rt6_info *rt6_add_dflt_router(struct net *net,
+ const struct in6_addr *gwaddr,
struct net_device *dev, unsigned int pref);
void rt6_purge_dflt_routers(struct net *net);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 6fd4bbdc444f..2b0aa6d7eb17 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1049,7 +1049,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
goto out;
}
- rt = addrconf_dst_alloc(idev, addr, false);
+ rt = addrconf_dst_alloc(net, idev, addr, false);
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
rt = NULL;
@@ -1199,7 +1199,7 @@ cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, bool del_r
0, RTF_GATEWAY | RTF_DEFAULT);
if (rt) {
if (del_rt)
- ip6_del_rt(rt);
+ ip6_del_rt(dev_net(ifp->idev->dev), rt);
else {
if (!(rt->rt6i_flags & RTF_EXPIRES))
rt6_set_expires(rt, expires);
@@ -2679,7 +2679,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
if (rt) {
/* Autoconf prefix route */
if (valid_lft == 0) {
- ip6_del_rt(rt);
+ ip6_del_rt(net, rt);
rt = NULL;
} else if (addrconf_finite_timeout(rt_expires)) {
/* not infinity */
@@ -3341,7 +3341,8 @@ static void addrconf_gre_config(struct net_device *dev)
}
#endif
-static int fixup_permanent_addr(struct inet6_dev *idev,
+static int fixup_permanent_addr(struct net *net,
+ struct inet6_dev *idev,
struct inet6_ifaddr *ifp)
{
/* !rt6i_node means the host route was removed from the
@@ -3351,7 +3352,7 @@ static int fixup_permanent_addr(struct inet6_dev *idev,
if (!ifp->rt || !ifp->rt->rt6i_node) {
struct rt6_info *rt, *prev;
- rt = addrconf_dst_alloc(idev, &ifp->addr, false);
+ rt = addrconf_dst_alloc(net, idev, &ifp->addr, false);
if (IS_ERR(rt))
return PTR_ERR(rt);
@@ -3375,7 +3376,7 @@ static int fixup_permanent_addr(struct inet6_dev *idev,
return 0;
}
-static void addrconf_permanent_addr(struct net_device *dev)
+static void addrconf_permanent_addr(struct net *net, struct net_device *dev)
{
struct inet6_ifaddr *ifp, *tmp;
struct inet6_dev *idev;
@@ -3388,7 +3389,7 @@ static void addrconf_permanent_addr(struct net_device *dev)
list_for_each_entry_safe(ifp, tmp, &idev->addr_list, if_list) {
if ((ifp->flags & IFA_F_PERMANENT) &&
- fixup_permanent_addr(idev, ifp) < 0) {
+ fixup_permanent_addr(net, idev, ifp) < 0) {
write_unlock_bh(&idev->lock);
in6_ifa_hold(ifp);
ipv6_del_addr(ifp);
@@ -3457,7 +3458,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
if (event == NETDEV_UP) {
/* restore routes for permanent addresses */
- addrconf_permanent_addr(dev);
+ addrconf_permanent_addr(net, dev);
if (!addrconf_link_ready(dev)) {
/* device is not ready yet. */
@@ -3743,7 +3744,7 @@ static int addrconf_ifdown(struct net_device *dev, int how)
spin_unlock_bh(&ifa->lock);
if (rt)
- ip6_del_rt(rt);
+ ip6_del_rt(net, rt);
if (state != INET6_IFADDR_STATE_DEAD) {
__ipv6_ifa_notify(RTM_DELADDR, ifa);
@@ -3861,6 +3862,7 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
struct inet6_dev *idev = ifp->idev;
struct net_device *dev = idev->dev;
bool bump_id, notify = false;
+ struct net *net;
addrconf_join_solict(dev, &ifp->addr);
@@ -3871,8 +3873,9 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
if (ifp->state == INET6_IFADDR_STATE_DEAD)
goto out;
+ net = dev_net(dev);
if (dev->flags&(IFF_NOARP|IFF_LOOPBACK) ||
- (dev_net(dev)->ipv6.devconf_all->accept_dad < 1 &&
+ (net->ipv6.devconf_all->accept_dad < 1 &&
idev->cnf.accept_dad < 1) ||
!(ifp->flags&IFA_F_TENTATIVE) ||
ifp->flags & IFA_F_NODAD) {
@@ -3908,8 +3911,8 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
* Frames right away
*/
if (ifp->flags & IFA_F_OPTIMISTIC) {
- ip6_ins_rt(ifp->rt);
- if (ipv6_use_optimistic_addr(dev_net(dev), idev)) {
+ ip6_ins_rt(net, ifp->rt);
+ if (ipv6_use_optimistic_addr(net, idev)) {
/* Because optimistic nodes can use this address,
* notify listeners. If DAD fails, RTM_DELADDR is sent.
*/
@@ -5621,7 +5624,7 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
* to do it again
*/
if (!rcu_access_pointer(ifp->rt->rt6i_node))
- ip6_ins_rt(ifp->rt);
+ ip6_ins_rt(net, ifp->rt);
if (ifp->idev->cnf.forwarding)
addrconf_join_anycast(ifp);
if (!ipv6_addr_any(&ifp->peer_addr))
@@ -5638,11 +5641,11 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
rt = addrconf_get_prefix_route(&ifp->peer_addr, 128,
ifp->idev->dev, 0, 0);
if (rt)
- ip6_del_rt(rt);
+ ip6_del_rt(net, rt);
}
if (ifp->rt) {
if (dst_hold_safe(&ifp->rt->dst))
- ip6_del_rt(ifp->rt);
+ ip6_del_rt(net, ifp->rt);
}
rt_genid_bump_ipv6(net);
break;
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index d580d4d456a5..7ecdbabb16dd 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -247,6 +247,7 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr)
{
struct ifacaddr6 *aca;
struct rt6_info *rt;
+ struct net *net;
int err;
ASSERT_RTNL();
@@ -265,7 +266,8 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr)
}
}
- rt = addrconf_dst_alloc(idev, addr, true);
+ net = dev_net(idev->dev);
+ rt = addrconf_dst_alloc(net, idev, addr, true);
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
goto out;
@@ -286,7 +288,7 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr)
aca_get(aca);
write_unlock_bh(&idev->lock);
- ip6_ins_rt(rt);
+ ip6_ins_rt(net, rt);
addrconf_join_solict(idev->dev, &aca->aca_addr);
@@ -329,7 +331,7 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr)
addrconf_leave_solict(idev, &aca->aca_addr);
dst_hold(&aca->aca_rt->dst);
- ip6_del_rt(aca->aca_rt);
+ ip6_del_rt(dev_net(idev->dev), aca->aca_rt);
aca_put(aca);
return 0;
@@ -357,7 +359,7 @@ void ipv6_ac_destroy_dev(struct inet6_dev *idev)
addrconf_leave_solict(idev, &aca->aca_addr);
dst_hold(&aca->aca_rt->dst);
- ip6_del_rt(aca->aca_rt);
+ ip6_del_rt(dev_net(idev->dev), aca->aca_rt);
aca_put(aca);
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 10024eb0c521..4c6444a16d92 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1156,6 +1156,7 @@ static void ndisc_router_discovery(struct sk_buff *skb)
struct neighbour *neigh = NULL;
struct inet6_dev *in6_dev;
struct rt6_info *rt = NULL;
+ struct net *net;
int lifetime;
struct ndisc_options ndopts;
int optlen;
@@ -1253,9 +1254,9 @@ static void ndisc_router_discovery(struct sk_buff *skb)
/* Do not accept RA with source-addr found on local machine unless
* accept_ra_from_local is set to true.
*/
+ net = dev_net(in6_dev->dev);
if (!in6_dev->cnf.accept_ra_from_local &&
- ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr,
- in6_dev->dev, 0)) {
+ ipv6_chk_addr(net, &ipv6_hdr(skb)->saddr, in6_dev->dev, 0)) {
ND_PRINTK(2, info,
"RA from local address detected on dev: %s: default router ignored\n",
skb->dev->name);
@@ -1272,7 +1273,7 @@ static void ndisc_router_discovery(struct sk_buff *skb)
pref = ICMPV6_ROUTER_PREF_MEDIUM;
#endif
- rt = rt6_get_dflt_router(&ipv6_hdr(skb)->saddr, skb->dev);
+ rt = rt6_get_dflt_router(net, &ipv6_hdr(skb)->saddr, skb->dev);
if (rt) {
neigh = dst_neigh_lookup(&rt->dst, &ipv6_hdr(skb)->saddr);
@@ -1285,7 +1286,7 @@ static void ndisc_router_discovery(struct sk_buff *skb)
}
}
if (rt && lifetime == 0) {
- ip6_del_rt(rt);
+ ip6_del_rt(net, rt);
rt = NULL;
}
@@ -1294,7 +1295,8 @@ static void ndisc_router_discovery(struct sk_buff *skb)
if (!rt && lifetime) {
ND_PRINTK(3, info, "RA: adding default router\n");
- rt = rt6_add_dflt_router(&ipv6_hdr(skb)->saddr, skb->dev, pref);
+ rt = rt6_add_dflt_router(net, &ipv6_hdr(skb)->saddr,
+ skb->dev, pref);
if (!rt) {
ND_PRINTK(0, err,
"RA: %s failed to add default route\n",
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 8e4f0995e95a..049bb5c3a824 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -850,13 +850,13 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
}
if (rinfo->prefix_len == 0)
- rt = rt6_get_dflt_router(gwaddr, dev);
+ rt = rt6_get_dflt_router(net, gwaddr, dev);
else
rt = rt6_get_route_info(net, prefix, rinfo->prefix_len,
gwaddr, dev);
if (rt && !lifetime) {
- ip6_del_rt(rt);
+ ip6_del_rt(net, rt);
rt = NULL;
}
@@ -1011,9 +1011,9 @@ static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info,
return err;
}
-int ip6_ins_rt(struct rt6_info *rt)
+int ip6_ins_rt(struct net *net, struct rt6_info *rt)
{
- struct nl_info info = { .nl_net = dev_net(rt->dst.dev), };
+ struct nl_info info = { .nl_net = net, };
struct mx6_config mxc = { .mx = NULL, };
/* Hold dst to account for the reference from the fib6 tree */
@@ -1118,14 +1118,13 @@ static struct rt6_info *rt6_get_pcpu_route(struct rt6_info *rt)
return pcpu_rt;
}
-static struct rt6_info *rt6_make_pcpu_route(struct rt6_info *rt)
+static struct rt6_info *rt6_make_pcpu_route(struct net *net,
+ struct rt6_info *rt)
{
struct rt6_info *pcpu_rt, *prev, **p;
pcpu_rt = ip6_rt_pcpu_alloc(rt);
if (!pcpu_rt) {
- struct net *net = dev_net(rt->dst.dev);
-
dst_hold(&net->ipv6.ip6_null_entry->dst);
return net->ipv6.ip6_null_entry;
}
@@ -1758,7 +1757,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
/* No dst_hold() on rt is needed because grabbing
* rt->rt6i_ref makes sure rt can't be released.
*/
- pcpu_rt = rt6_make_pcpu_route(rt);
+ pcpu_rt = rt6_make_pcpu_route(net, rt);
rt6_release(rt);
} else {
/* rt is already removed from tree */
@@ -2059,7 +2058,7 @@ static struct dst_entry *ip6_negative_advice(struct dst_entry *dst)
if (rt) {
if (rt->rt6i_flags & RTF_CACHE) {
if (rt6_check_expired(rt)) {
- ip6_del_rt(rt);
+ ip6_del_rt(dev_net(dst->dev), rt);
dst = NULL;
}
} else {
@@ -2080,7 +2079,7 @@ static void ip6_link_failure(struct sk_buff *skb)
if (rt) {
if (rt->rt6i_flags & RTF_CACHE) {
if (dst_hold_safe(&rt->dst))
- ip6_del_rt(rt);
+ ip6_del_rt(dev_net(rt->dst.dev), rt);
} else {
struct fib6_node *fn;
@@ -2966,9 +2965,9 @@ int ip6_route_add(struct fib6_config *cfg,
static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info)
{
- int err;
+ struct net *net = info->nl_net;
struct fib6_table *table;
- struct net *net = dev_net(rt->dst.dev);
+ int err;
if (rt == net->ipv6.ip6_null_entry) {
err = -ENOENT;
@@ -2985,11 +2984,10 @@ static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info)
return err;
}
-int ip6_del_rt(struct rt6_info *rt)
+int ip6_del_rt(struct net *net, struct rt6_info *rt)
{
- struct nl_info info = {
- .nl_net = dev_net(rt->dst.dev),
- };
+ struct nl_info info = { .nl_net = net };
+
return __ip6_del_rt(rt, &info);
}
@@ -3324,13 +3322,15 @@ static struct rt6_info *rt6_add_route_info(struct net *net,
}
#endif
-struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_device *dev)
+struct rt6_info *rt6_get_dflt_router(struct net *net,
+ const struct in6_addr *addr,
+ struct net_device *dev)
{
u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT;
struct rt6_info *rt;
struct fib6_table *table;
- table = fib6_get_table(dev_net(dev), tb_id);
+ table = fib6_get_table(net, tb_id);
if (!table)
return NULL;
@@ -3347,7 +3347,8 @@ struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_dev
return rt;
}
-struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr,
+struct rt6_info *rt6_add_dflt_router(struct net *net,
+ const struct in6_addr *gwaddr,
struct net_device *dev,
unsigned int pref)
{
@@ -3360,7 +3361,7 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr,
.fc_protocol = RTPROT_RA,
.fc_nlinfo.portid = 0,
.fc_nlinfo.nlh = NULL,
- .fc_nlinfo.nl_net = dev_net(dev),
+ .fc_nlinfo.nl_net = net,
};
cfg.fc_gateway = *gwaddr;
@@ -3373,10 +3374,11 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr,
table->flags |= RT6_TABLE_HAS_DFLT_ROUTER;
}
- return rt6_get_dflt_router(gwaddr, dev);
+ return rt6_get_dflt_router(net, gwaddr, dev);
}
-static void __rt6_purge_dflt_routers(struct fib6_table *table)
+static void __rt6_purge_dflt_routers(struct net *net,
+ struct fib6_table *table)
{
struct rt6_info *rt;
@@ -3387,7 +3389,7 @@ static void __rt6_purge_dflt_routers(struct fib6_table *table)
(!rt->rt6i_idev || rt->rt6i_idev->cnf.accept_ra != 2)) {
if (dst_hold_safe(&rt->dst)) {
rcu_read_unlock();
- ip6_del_rt(rt);
+ ip6_del_rt(net, rt);
} else {
rcu_read_unlock();
}
@@ -3411,7 +3413,7 @@ void rt6_purge_dflt_routers(struct net *net)
head = &net->ipv6.fib_table_hash[h];
hlist_for_each_entry_rcu(table, head, tb6_hlist) {
if (table->flags & RT6_TABLE_HAS_DFLT_ROUTER)
- __rt6_purge_dflt_routers(table);
+ __rt6_purge_dflt_routers(net, table);
}
}
@@ -3530,12 +3532,12 @@ static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff
* Allocate a dst for local (unicast / anycast) address.
*/
-struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
+struct rt6_info *addrconf_dst_alloc(struct net *net,
+ struct inet6_dev *idev,
const struct in6_addr *addr,
bool anycast)
{
u32 tb_id;
- struct net *net = dev_net(idev->dev);
struct net_device *dev = idev->dev;
struct rt6_info *rt;
--
2.11.0
^ permalink raw reply related
* [PATCH RFC v2 net-next 04/21] net/ipv6: Pass net to fib6_update_sernum
From: David Ahern @ 2018-03-19 3:36 UTC (permalink / raw)
To: netdev
Cc: davem, idosch, roopa, eric.dumazet, weiwan, kafai, yoshfuji,
David Ahern
In-Reply-To: <20180319033622.16693-1-dsahern@gmail.com>
Pass net namespace to fib6_update_sernum. It can not be marked const
as fib6_new_sernum will change ipv6.fib6_sernum.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/net/ip6_fib.h | 2 +-
net/ipv6/ip6_fib.c | 3 +--
net/ipv6/route.c | 10 +++++-----
3 files changed, 7 insertions(+), 8 deletions(-)
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 5e86fd9dc857..f0aaf1c8f1a8 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -408,7 +408,7 @@ void __net_exit fib6_notifier_exit(struct net *net);
unsigned int fib6_tables_seq_read(struct net *net);
int fib6_tables_dump(struct net *net, struct notifier_block *nb);
-void fib6_update_sernum(struct rt6_info *rt);
+void fib6_update_sernum(struct net *net, struct rt6_info *rt);
void fib6_update_sernum_upto_root(struct net *net, struct rt6_info *rt);
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 2f995e9e3050..29a9e835faac 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -105,9 +105,8 @@ enum {
FIB6_NO_SERNUM_CHANGE = 0,
};
-void fib6_update_sernum(struct rt6_info *rt)
+void fib6_update_sernum(struct net *net, struct rt6_info *rt)
{
- struct net *net = dev_net(rt->dst.dev);
struct fib6_node *fn;
fn = rcu_dereference_protected(rt->rt6i_node,
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 939d122e71b4..8e4f0995e95a 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1349,7 +1349,7 @@ static int rt6_insert_exception(struct rt6_info *nrt,
/* Update fn->fn_sernum to invalidate all cached dst */
if (!err) {
spin_lock_bh(&ort->rt6i_table->tb6_lock);
- fib6_update_sernum(ort);
+ fib6_update_sernum(net, ort);
spin_unlock_bh(&ort->rt6i_table->tb6_lock);
fib6_force_start_gc(net);
}
@@ -3733,11 +3733,11 @@ void rt6_multipath_rebalance(struct rt6_info *rt)
static int fib6_ifup(struct rt6_info *rt, void *p_arg)
{
const struct arg_netdev_event *arg = p_arg;
- const struct net *net = dev_net(arg->dev);
+ struct net *net = dev_net(arg->dev);
if (rt != net->ipv6.ip6_null_entry && rt->dst.dev == arg->dev) {
rt->rt6i_nh_flags &= ~arg->nh_flags;
- fib6_update_sernum_upto_root(dev_net(rt->dst.dev), rt);
+ fib6_update_sernum_upto_root(net, rt);
rt6_multipath_rebalance(rt);
}
@@ -3816,7 +3816,7 @@ static int fib6_ifdown(struct rt6_info *rt, void *p_arg)
{
const struct arg_netdev_event *arg = p_arg;
const struct net_device *dev = arg->dev;
- const struct net *net = dev_net(dev);
+ struct net *net = dev_net(dev);
if (rt == net->ipv6.ip6_null_entry)
return 0;
@@ -3839,7 +3839,7 @@ static int fib6_ifdown(struct rt6_info *rt, void *p_arg)
}
rt6_multipath_nh_flags_set(rt, dev, RTNH_F_DEAD |
RTNH_F_LINKDOWN);
- fib6_update_sernum(rt);
+ fib6_update_sernum(net, rt);
rt6_multipath_rebalance(rt);
}
return -2;
--
2.11.0
^ permalink raw reply related
* [PATCH RFC v2 net-next 03/21] vrf: Move fib6_table into net_vrf
From: David Ahern @ 2018-03-19 3:36 UTC (permalink / raw)
To: netdev
Cc: davem, idosch, roopa, eric.dumazet, weiwan, kafai, yoshfuji,
David Ahern
In-Reply-To: <20180319033622.16693-1-dsahern@gmail.com>
A later patch removes rt6i_table from rt6_info. Save the ipv6
table for a VRF in net_vrf. fib tables can not be deleted so
no reference counting or locking is required.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
drivers/net/vrf.c | 25 ++++++-------------------
1 file changed, 6 insertions(+), 19 deletions(-)
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index c6be49d3a9eb..c0ffe20772f3 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -48,6 +48,9 @@ static unsigned int vrf_net_id;
struct net_vrf {
struct rtable __rcu *rth;
struct rt6_info __rcu *rt6;
+#if IS_ENABLED(CONFIG_IPV6)
+ struct fib6_table *fib6_table;
+#endif
u32 tb_id;
};
@@ -496,7 +499,6 @@ static int vrf_rt6_create(struct net_device *dev)
int flags = DST_HOST | DST_NOPOLICY | DST_NOXFRM;
struct net_vrf *vrf = netdev_priv(dev);
struct net *net = dev_net(dev);
- struct fib6_table *rt6i_table;
struct rt6_info *rt6;
int rc = -ENOMEM;
@@ -504,8 +506,8 @@ static int vrf_rt6_create(struct net_device *dev)
if (!ipv6_mod_enabled())
return 0;
- rt6i_table = fib6_new_table(net, vrf->tb_id);
- if (!rt6i_table)
+ vrf->fib6_table = fib6_new_table(net, vrf->tb_id);
+ if (!vrf->fib6_table)
goto out;
/* create a dst for routing packets out a VRF device */
@@ -513,7 +515,6 @@ static int vrf_rt6_create(struct net_device *dev)
if (!rt6)
goto out;
- rt6->rt6i_table = rt6i_table;
rt6->dst.output = vrf_output6;
rcu_assign_pointer(vrf->rt6, rt6);
@@ -945,22 +946,8 @@ static struct rt6_info *vrf_ip6_route_lookup(struct net *net,
int flags)
{
struct net_vrf *vrf = netdev_priv(dev);
- struct fib6_table *table = NULL;
- struct rt6_info *rt6;
-
- rcu_read_lock();
-
- /* fib6_table does not have a refcnt and can not be freed */
- rt6 = rcu_dereference(vrf->rt6);
- if (likely(rt6))
- table = rt6->rt6i_table;
-
- rcu_read_unlock();
-
- if (!table)
- return NULL;
- return ip6_pol_route(net, table, ifindex, fl6, skb, flags);
+ return ip6_pol_route(net, vrf->fib6_table, ifindex, fl6, skb, flags);
}
static void vrf_ip6_input_dst(struct sk_buff *skb, struct net_device *vrf_dev,
--
2.11.0
^ permalink raw reply related
* [PATCH RFC v2 net-next 02/21] net: Handle null dst in rtnl_put_cacheinfo
From: David Ahern @ 2018-03-19 3:36 UTC (permalink / raw)
To: netdev
Cc: davem, idosch, roopa, eric.dumazet, weiwan, kafai, yoshfuji,
David Ahern
In-Reply-To: <20180319033622.16693-1-dsahern@gmail.com>
Need to keep expires time for IPv6 routes in a dump of FIB entries.
Update rtnl_put_cacheinfo to allow dst to be NULL in which case
rta_cacheinfo will only contain non-dst data.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
net/core/rtnetlink.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 87079eaa871b..33d6ee808155 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -780,13 +780,15 @@ int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id,
long expires, u32 error)
{
struct rta_cacheinfo ci = {
- .rta_lastuse = jiffies_delta_to_clock_t(jiffies - dst->lastuse),
- .rta_used = dst->__use,
- .rta_clntref = atomic_read(&(dst->__refcnt)),
.rta_error = error,
.rta_id = id,
};
+ if (dst) {
+ ci.rta_lastuse = jiffies_delta_to_clock_t(jiffies - dst->lastuse);
+ ci.rta_used = dst->__use;
+ ci.rta_clntref = atomic_read(&dst->__refcnt);
+ }
if (expires) {
unsigned long clock;
--
2.11.0
^ permalink raw reply related
* [PATCH RFC v2 net-next 01/21] net: Move fib_convert_metrics to metrics file
From: David Ahern @ 2018-03-19 3:36 UTC (permalink / raw)
To: netdev
Cc: davem, idosch, roopa, eric.dumazet, weiwan, kafai, yoshfuji,
David Ahern
In-Reply-To: <20180319033622.16693-1-dsahern@gmail.com>
Move logic of fib_convert_metrics into ip_metrics_convert. This allows
the code that converts netlink attributes into metrics struct to be
re-used in a later patch by IPv6.
This is mostly a code move with the following changes to variable names:
- fi->fib_net becomes net
- fc_mx and fc_mx_len are passed as inputs pulled from fib_config
- metrics array is passed as an input from fi->fib_metrics->metrics
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/net/ip.h | 3 +++
net/ipv4/Makefile | 3 ++-
net/ipv4/fib_semantics.c | 43 ++-------------------------------------
net/ipv4/metrics.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++++
4 files changed, 60 insertions(+), 42 deletions(-)
create mode 100644 net/ipv4/metrics.c
diff --git a/include/net/ip.h b/include/net/ip.h
index fe63ba95d12b..c0e79ea3c502 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -380,6 +380,9 @@ static inline unsigned int ip_skb_dst_mtu(struct sock *sk,
return min(READ_ONCE(skb_dst(skb)->dev->mtu), IP_MAX_MTU);
}
+int ip_metrics_convert(struct net *net, struct nlattr *fc_mx, int fc_mx_len,
+ u32 *metrics);
+
u32 ip_idents_reserve(u32 hash, int segs);
void __ip_select_ident(struct net *net, struct iphdr *iph, int segs);
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index a07b7dd06def..b379520f9133 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -13,7 +13,8 @@ obj-y := route.o inetpeer.o protocol.o \
tcp_offload.o datagram.o raw.o udp.o udplite.o \
udp_offload.o arp.o icmp.o devinet.o af_inet.o igmp.o \
fib_frontend.o fib_semantics.o fib_trie.o fib_notifier.o \
- inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o
+ inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o \
+ metrics.o
obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o
obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index e7c602c600ac..b3ebde36d706 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1019,47 +1019,8 @@ static bool fib_valid_prefsrc(struct fib_config *cfg, __be32 fib_prefsrc)
static int
fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg)
{
- bool ecn_ca = false;
- struct nlattr *nla;
- int remaining;
-
- if (!cfg->fc_mx)
- return 0;
-
- nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
- int type = nla_type(nla);
- u32 val;
-
- if (!type)
- continue;
- if (type > RTAX_MAX)
- return -EINVAL;
-
- if (type == RTAX_CC_ALGO) {
- char tmp[TCP_CA_NAME_MAX];
-
- nla_strlcpy(tmp, nla, sizeof(tmp));
- val = tcp_ca_get_key_by_name(fi->fib_net, tmp, &ecn_ca);
- if (val == TCP_CA_UNSPEC)
- return -EINVAL;
- } else {
- val = nla_get_u32(nla);
- }
- if (type == RTAX_ADVMSS && val > 65535 - 40)
- val = 65535 - 40;
- if (type == RTAX_MTU && val > 65535 - 15)
- val = 65535 - 15;
- if (type == RTAX_HOPLIMIT && val > 255)
- val = 255;
- if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK))
- return -EINVAL;
- fi->fib_metrics->metrics[type - 1] = val;
- }
-
- if (ecn_ca)
- fi->fib_metrics->metrics[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA;
-
- return 0;
+ return ip_metrics_convert(fi->fib_net, cfg->fc_mx, cfg->fc_mx_len,
+ fi->fib_metrics->metrics);
}
struct fib_info *fib_create_info(struct fib_config *cfg,
diff --git a/net/ipv4/metrics.c b/net/ipv4/metrics.c
new file mode 100644
index 000000000000..5121c6475e6b
--- /dev/null
+++ b/net/ipv4/metrics.c
@@ -0,0 +1,53 @@
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+#include <linux/types.h>
+#include <net/ip.h>
+#include <net/net_namespace.h>
+#include <net/tcp.h>
+
+int ip_metrics_convert(struct net *net, struct nlattr *fc_mx, int fc_mx_len,
+ u32 *metrics)
+{
+ bool ecn_ca = false;
+ struct nlattr *nla;
+ int remaining;
+
+ if (!fc_mx)
+ return 0;
+
+ nla_for_each_attr(nla, fc_mx, fc_mx_len, remaining) {
+ int type = nla_type(nla);
+ u32 val;
+
+ if (!type)
+ continue;
+ if (type > RTAX_MAX)
+ return -EINVAL;
+
+ if (type == RTAX_CC_ALGO) {
+ char tmp[TCP_CA_NAME_MAX];
+
+ nla_strlcpy(tmp, nla, sizeof(tmp));
+ val = tcp_ca_get_key_by_name(net, tmp, &ecn_ca);
+ if (val == TCP_CA_UNSPEC)
+ return -EINVAL;
+ } else {
+ val = nla_get_u32(nla);
+ }
+ if (type == RTAX_ADVMSS && val > 65535 - 40)
+ val = 65535 - 40;
+ if (type == RTAX_MTU && val > 65535 - 15)
+ val = 65535 - 15;
+ if (type == RTAX_HOPLIMIT && val > 255)
+ val = 255;
+ if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK))
+ return -EINVAL;
+ metrics[type - 1] = val;
+ }
+
+ if (ecn_ca)
+ metrics[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ip_metrics_convert);
--
2.11.0
^ permalink raw reply related
* [PATCH RFC v2 net-next 00/21] net/ipv6: Separate data structures for FIB and data path
From: David Ahern @ 2018-03-19 3:36 UTC (permalink / raw)
To: netdev
Cc: davem, idosch, roopa, eric.dumazet, weiwan, kafai, yoshfuji,
David Ahern
IPv6 uses the same data struct for both control plane (FIB entries) and
data path (dst entries). This struct has elements needed for both paths
adding memory overhead and complexity (taking a dst hold in most places
but an additional reference on rt6i_ref in a few). Furthermore, because
of the dst_alloc tie, all FIB entries are allocated with GFP_ATOMIC.
This patch set separates FIB entries from dst entries, better aligning
IPv6 code with IPv4, simplifying the reference counting and allowing
FIB entries added by userspace (not autoconf) to use GFP_KERNEL. It is
first step to a number of performance and scalability changes.
The end result of this patch set:
- FIB entries (fib6_info):
/* size: 208, cachelines: 4, members: 25 */
/* sum members: 207, holes: 1, sum holes: 1 */
- dst entries (rt6_info)
/* size: 240, cachelines: 4, members: 11 */
Versus the the single rt6_info struct today for both paths:
/* size: 320, cachelines: 5, members: 28 */
This amounts to a 35% reduction in memory use for FIB entries and a
25% reduction for dst entries.
With respect to locking FIB entries use RCU and a single atomic
counter with fib6_info_hold and fib6_info_release helpers to manage
the reference counting. dst entries use only the traditional dst
refcounts with dst_hold and dst_release.
FIB entries for host routes are referenced by inet6_ifaddr and
ifacaddr6. In both cases, additional holds are taken -- similar to
what is done for devices.
This set is the first of many changes to improve the scalability of the
IPv6 code. Follow on changes include:
- consolidating duplicate fib6_info references like IPv4 does with
duplicate fib_info
- moving fib6_info into a slab cache to avoid allocation roundups to
power of 2 (the 208 size becomes a 256 actual allocation)
- Allow FIB lookups without generating a dst (e.g., most rt6_lookup
users just want to verify the egress device). Means moving dst
allocation to the other side of fib6_rule_lookup which again aligns
with IPv4 behavior
- using separate standalone nexthop objects which have performance
benefits beyond fib_info consolidation
At this point I am not seeing any refcount leaks or underflows, no
oops or bug_ons, or warnings from kasan, so I think it is ready for
others to beat up on it finding errors in code paths I have missed.
RFC v2 changes
- improved commit messages
- move common metrics code from dst.c to net/ipv4/metrics.c (comment
from DaveM)
- address comments from Wei Wang and Martin KaFai Lau (let me know if
I missed something)
- fixes detected by kernel test robots
+ added fib6_metric_set to change metric on a FIB entry which could
be pointing to read-only dst_default_metrics
+ 0day testing found a problem with an intermediate patch; added
dst_hold_safe on rt->from. Code is removed 3 patches later
- allow cacheinfo to handle NULL dst; means only expires is pushed to
userspace
David Ahern (21):
net: Move fib_convert_metrics to metrics file
net: Handle null dst in rtnl_put_cacheinfo
vrf: Move fib6_table into net_vrf
net/ipv6: Pass net to fib6_update_sernum
net/ipv6: Pass net namespace to route functions
net/ipv6: Move support functions up in route.c
net/ipv6: Save route type in rt6_info
net/ipv6: Move nexthop data to fib6_nh
net/ipv6: Defer initialization of dst to data path
net/ipv6: move metrics from dst to rt6_info
net/ipv6: move expires into rt6_info
net/ipv6: Add fib6_null_entry
net/ipv6: Add rt6_info create function for ip6_pol_route_lookup
net/ipv6: Move dst flags to booleans in fib entries
net/ipv6: Create a neigh_lookup for FIB entries
net/ipv6: Add gfp_flags to route add functions
net/ipv6: Cleanup exception and cache route handling
net/ipv6: introduce fib6_info struct and helpers
net/ipv6: separate handling of FIB entries from dst based routes
net/ipv6: Flip FIB entries to fib6_info
net/ipv6: Remove unused code and variables for rt6_info
.../net/ethernet/mellanox/mlxsw/spectrum_router.c | 96 +-
drivers/net/vrf.c | 25 +-
include/net/if_inet6.h | 4 +-
include/net/ip.h | 3 +
include/net/ip6_fib.h | 151 ++-
include/net/ip6_route.h | 45 +-
include/net/netns/ipv6.h | 3 +-
net/core/dst.c | 1 +
net/core/rtnetlink.c | 8 +-
net/ipv4/Makefile | 3 +-
net/ipv4/fib_semantics.c | 43 +-
net/ipv4/metrics.c | 53 +
net/ipv6/addrconf.c | 118 +-
net/ipv6/anycast.c | 21 +-
net/ipv6/ip6_fib.c | 362 +++---
net/ipv6/ip6_output.c | 3 +-
net/ipv6/ndisc.c | 40 +-
net/ipv6/route.c | 1364 ++++++++++----------
net/ipv6/xfrm6_policy.c | 2 -
19 files changed, 1206 insertions(+), 1139 deletions(-)
create mode 100644 net/ipv4/metrics.c
--
2.11.0
^ permalink raw reply
* Re: [PATCH v11 crypto 00/12] Chelsio Inline TLS
From: Atul Gupta @ 2018-03-19 3:26 UTC (permalink / raw)
To: David Miller
Cc: davejwatson, herbert, sd, sbrivio, linux-crypto, netdev, ganeshgr
In-Reply-To: <20180318.103602.252024301365216579.davem@davemloft.net>
On 3/18/2018 8:06 PM, David Miller wrote:
> From: Atul Gupta <atul.gupta@chelsio.com>
> Date: Sun, 18 Mar 2018 14:30:30 +0000
>
>> Hi Dave/Herbert,
>>
>> This series is against crypto tree, should I submit two patch series:
>> 1. netdev specific changes against net-next tree?
>> 2. crypto changes against crypto tree?
> Herbert, is it OK for this entire series to go via net-next?
Once Herbert confirms I will create series against net-next.
> Thanks!
^ permalink raw reply
* Re: [PATCH v11 crypto 06/12] crypto: chtls - structure and macro for Inline TLS
From: Atul Gupta @ 2018-03-19 3:22 UTC (permalink / raw)
To: Sabrina Dubroca
Cc: davejwatson, davem, herbert, sbrivio, linux-crypto, netdev,
ganeshgr
In-Reply-To: <20180318225337.GA19891@bistromath.localdomain>
On 3/19/2018 4:23 AM, Sabrina Dubroca wrote:
> 2018-03-16, 21:07:35 +0530, Atul Gupta wrote:
> [...]
>> +#define SOCK_INLINE (31)
> [...]
>
>> +static inline int csk_flag(const struct sock *sk, enum csk_flags flag)
>> +{
>> + struct chtls_sock *csk = rcu_dereference_sk_user_data(sk);
>> +
>> + if (!sock_flag(sk, SOCK_INLINE))
>> + return 0;
>> + return test_bit(flag, &csk->flags);
>> +}
> Should drivers really start defining their own socket flags?
this is for conn in Inline mode once transitioned to HW, will re-check if can avoid this. Thanks
>
>
>> +static inline void set_queue(struct sk_buff *skb,
>> + unsigned int queue, const struct sock *sk)
>> +{
>> + skb->queue_mapping = queue;
>> +}
> That's skb_set_queue_mapping(), no need to define your own.
Yes, can avoid re-def. Thank you.
>
^ permalink raw reply
* Re: [PATCH v2 13/21] mmc: Remove depends on HAS_DMA in case of platform dependency
From: Ulf Hansson @ 2018-03-19 3:08 UTC (permalink / raw)
To: Geert Uytterhoeven
Cc: alsa-devel-K7yf7f+aM1XWsZ/bQMPhNw, Wolfram Sang,
linux-iio-u79uwXL29TY76Z2rM5mHXA,
linux-fpga-u79uwXL29TY76Z2rM5mHXA,
linux-remoteproc-u79uwXL29TY76Z2rM5mHXA,
Linux Fbdev development list, Bjorn Andersson, Eric Anholt,
netdev-u79uwXL29TY76Z2rM5mHXA,
linux-mtd-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r,
linux-i2c-u79uwXL29TY76Z2rM5mHXA,
linux1394-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f,
Christoph Hellwig, Stefan Wahren, Boris Brezillon,
James E . J . Bottomley, Herbert Xu, linux-scsi,
Richard Weinberger, Jassi Brar, Marek Vasut,
linux-serial-u79uwXL29TY76Z2rM5mHXA, Matias Bjorling,
David Woodhouse
In-Reply-To: <1521208314-4783-14-git-send-email-geert-Td1EMuHUCqxL1ZNQvxDV9g@public.gmane.org>
On 16 March 2018 at 14:51, Geert Uytterhoeven <geert-Td1EMuHUCqxL1ZNQvxDV9g@public.gmane.org> wrote:
> Remove dependencies on HAS_DMA where a Kconfig symbol depends on another
> symbol that implies HAS_DMA, and, optionally, on "|| COMPILE_TEST".
> In most cases this other symbol is an architecture or platform specific
> symbol, or PCI.
>
> Generic symbols and drivers without platform dependencies keep their
> dependencies on HAS_DMA, to prevent compiling subsystems or drivers that
> cannot work anyway.
>
> This simplifies the dependencies, and allows to improve compile-testing.
>
> Signed-off-by: Geert Uytterhoeven <geert-Td1EMuHUCqxL1ZNQvxDV9g@public.gmane.org>
> Reviewed-by: Mark Brown <broonie-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
> Acked-by: Robin Murphy <robin.murphy-5wv7dgnIgG8@public.gmane.org>
Acked-by: Ulf Hansson <ulf.hansson-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org>
> ---
> v2:
> - Add Reviewed-by, Acked-by,
> - Drop RFC state,
> - Split per subsystem.
> ---
> drivers/mmc/host/Kconfig | 10 ++--------
> 1 file changed, 2 insertions(+), 8 deletions(-)
>
> diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
> index 620c2d90a646f387..f6d43348b4a3e5d4 100644
> --- a/drivers/mmc/host/Kconfig
> +++ b/drivers/mmc/host/Kconfig
> @@ -358,7 +358,6 @@ config MMC_MESON_MX_SDIO
> tristate "Amlogic Meson6/Meson8/Meson8b SD/MMC Host Controller support"
> depends on ARCH_MESON || COMPILE_TEST
> depends on COMMON_CLK
> - depends on HAS_DMA
> depends on OF
> help
> This selects support for the SD/MMC Host Controller on
> @@ -401,7 +400,6 @@ config MMC_OMAP
>
> config MMC_OMAP_HS
> tristate "TI OMAP High Speed Multimedia Card Interface support"
> - depends on HAS_DMA
> depends on ARCH_OMAP2PLUS || ARCH_KEYSTONE || COMPILE_TEST
> help
> This selects the TI OMAP High Speed Multimedia card Interface.
> @@ -511,7 +509,6 @@ config MMC_DAVINCI
>
> config MMC_GOLDFISH
> tristate "goldfish qemu Multimedia Card Interface support"
> - depends on HAS_DMA
> depends on GOLDFISH || COMPILE_TEST
> help
> This selects the Goldfish Multimedia card Interface emulation
> @@ -605,7 +602,7 @@ config MMC_SDHI
>
> config MMC_SDHI_SYS_DMAC
> tristate "DMA for SDHI SD/SDIO controllers using SYS-DMAC"
> - depends on MMC_SDHI && HAS_DMA
> + depends on MMC_SDHI
> default MMC_SDHI if (SUPERH || ARM)
> help
> This provides DMA support for SDHI SD/SDIO controllers
> @@ -615,7 +612,7 @@ config MMC_SDHI_SYS_DMAC
> config MMC_SDHI_INTERNAL_DMAC
> tristate "DMA for SDHI SD/SDIO controllers using on-chip bus mastering"
> depends on ARM64 || COMPILE_TEST
> - depends on MMC_SDHI && HAS_DMA
> + depends on MMC_SDHI
> default MMC_SDHI if ARM64
> help
> This provides DMA support for SDHI SD/SDIO controllers
> @@ -688,7 +685,6 @@ config MMC_CAVIUM_THUNDERX
>
> config MMC_DW
> tristate "Synopsys DesignWare Memory Card Interface"
> - depends on HAS_DMA
> depends on ARC || ARM || ARM64 || MIPS || COMPILE_TEST
> help
> This selects support for the Synopsys DesignWare Mobile Storage IP
> @@ -758,7 +754,6 @@ config MMC_DW_ZX
>
> config MMC_SH_MMCIF
> tristate "SuperH Internal MMCIF support"
> - depends on HAS_DMA
> depends on SUPERH || ARCH_RENESAS || COMPILE_TEST
> help
> This selects the MMC Host Interface controller (MMCIF) found in various
> @@ -878,7 +873,6 @@ config MMC_TOSHIBA_PCI
> config MMC_BCM2835
> tristate "Broadcom BCM2835 SDHOST MMC Controller support"
> depends on ARCH_BCM2835 || COMPILE_TEST
> - depends on HAS_DMA
> help
> This selects the BCM2835 SDHOST MMC controller. If you have
> a BCM2835 platform with SD or MMC devices, say Y or M here.
> --
> 2.7.4
>
^ permalink raw reply
* Re: [PATCH v3 18/18] infiniband: cxgb4: Eliminate duplicate barriers on weakly-ordered archs
From: Jason Gunthorpe @ 2018-03-19 1:48 UTC (permalink / raw)
To: Sinan Kaya
Cc: Steve Wise, netdev, timur, sulrich, linux-arm-msm,
linux-arm-kernel, 'Steve Wise', 'Doug Ledford',
linux-rdma, linux-kernel, 'Michael Werner',
'Casey Leedom',
open list:LINUX FOR POWERPC (32-BIT AND 64-BIT)
In-Reply-To: <ac9c34e1-0a81-a494-c7c7-ac9c3922095a@codeaurora.org>
On Sat, Mar 17, 2018 at 02:30:10PM -0400, Sinan Kaya wrote:
> Somebody also has to take a task and work very hard to get rid of __raw_writeX()
> APIs in drivers/net directory. It looked like a very common practice though
> it clearly violates multiarch portability concerns Jason and Deve highlighted.
When you posted your list I thought most of the hits were in what I'd
think of 'one-arch drivers', eg an IRQ controller or clock driver or
something.. Some might have a reason for it (eg avoiding the swap, for
instance), maybe it is a hold over from before writel_relaxed, or
maybe it is just a cargo-cult behavior..
It is the obviously multi-arch drivers that probably need some
attention..
Jason
^ permalink raw reply
* [PATCH net-next v2 2/2] dt: bindings: add new dt entries for brcmfmac
From: Alexey Roslyakov @ 2018-03-19 1:40 UTC (permalink / raw)
To: andrew, kvalo, robh+dt, mark.rutland, arend.vanspriel, franky.lin,
hante.meuleman, chi-hsien.lin, wright.feng, netdev
Cc: linux-wireless, devicetree, linux-kernel, brcm80211-dev-list.pdl,
brcm80211-dev-list, Alexey Roslyakov
In-Reply-To: <20180319014032.9394-1-alexey.roslyakov@gmail.com>
In case if the host has higher align requirements for SG items, allow
setting device-specific aligns for scatterlist items.
Signed-off-by: Alexey Roslyakov <alexey.roslyakov@gmail.com>
---
Documentation/devicetree/bindings/net/wireless/brcm,bcm43xx-fmac.txt | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/Documentation/devicetree/bindings/net/wireless/brcm,bcm43xx-fmac.txt b/Documentation/devicetree/bindings/net/wireless/brcm,bcm43xx-fmac.txt
index 86602f264dce..187b8c1b52a7 100644
--- a/Documentation/devicetree/bindings/net/wireless/brcm,bcm43xx-fmac.txt
+++ b/Documentation/devicetree/bindings/net/wireless/brcm,bcm43xx-fmac.txt
@@ -17,6 +17,11 @@ Optional properties:
When not specified the device will use in-band SDIO interrupts.
- interrupt-names : name of the out-of-band interrupt, which must be set
to "host-wake".
+ - brcm,broken-sg-support : boolean flag to indicate that the SDIO host
+ controller has higher align requirement than 32 bytes for each
+ scatterlist item.
+ - brcm,sd-head-align : alignment requirement for start of data buffer.
+ - brcm,sd-sgentry-align : length alignment requirement for each sg entry.
Example:
--
2.16.1
^ permalink raw reply related
* [PATCH net-next v2 1/2] brcmfmac: add new dt entries for SG SDIO settings
From: Alexey Roslyakov @ 2018-03-19 1:40 UTC (permalink / raw)
To: andrew, kvalo, robh+dt, mark.rutland, arend.vanspriel, franky.lin,
hante.meuleman, chi-hsien.lin, wright.feng, netdev
Cc: linux-wireless, devicetree, linux-kernel, brcm80211-dev-list.pdl,
brcm80211-dev-list, Alexey Roslyakov
In-Reply-To: <20180319014032.9394-1-alexey.roslyakov@gmail.com>
There are 3 fields in SDIO settings (quirks) to workaround some of
the SG SDIO host particularities, i.e higher align requirements for
SG items.
All coding is done the long time ago, but there is no way to change the
driver behavior without patching the kernel.
Add missing devicetree entries.
Signed-off-by: Alexey Roslyakov <alexey.roslyakov@gmail.com>
---
drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c | 12 +++++++++---
1 file changed, 9 insertions(+), 3 deletions(-)
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c
index aee6e5937c41..14135752b659 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c
@@ -30,14 +30,20 @@ void brcmf_of_probe(struct device *dev, enum brcmf_bus_type bus_type,
struct device_node *np = dev->of_node;
int irq;
u32 irqf;
- u32 val;
if (!np || bus_type != BRCMF_BUSTYPE_SDIO ||
!of_device_is_compatible(np, "brcm,bcm4329-fmac"))
return;
- if (of_property_read_u32(np, "brcm,drive-strength", &val) == 0)
- sdio->drive_strength = val;
+ of_property_read_u32(np, "brcm,drive-strength", &sdio->drive_strength);
+
+ sdio->broken_sg_support =
+ of_property_read_bool(np, "brcm,broken-sg-support");
+
+ of_property_read_u16(np, "brcm,sd-head-align", &sdio->sd_head_align);
+
+ of_property_read_u16(np, "brcm,sd-sgentry-align",
+ &sdio->sd_sgentry_align);
/* make sure there are interrupts defined in the node */
if (!of_find_property(np, "interrupts", NULL))
--
2.16.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox