github-mirror/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-07-28 18:21:24 +02:00
Code Issues Actions Packages Projects Releases Wiki Activity Graph

Merge branch 'ipv4-flush-the-fib-once-on-multiple-nexthop-removal'

Browse Source 
Cosmin Ratiu says:

====================
ipv4: Flush the FIB once on multiple nexthop removal

This series optimizes multiple nexthop removal performance from having
to do a FIB flush for each nexthop being removed to only doing a single
FIB flush after all nexthops are removed.

This dramatically improves performance in scenarios where there are
many nexthops and many ipv4 routes. Please see individual patches for
more details and for a test scenario.
====================

Link: https://patch.msgid.link/20260507075606.322405-1-cratiu@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This commit is contained in:
Jakub Kicinski 2026-05-10 10:16:02 -07:00
commit bb3402f3df
1 changed files with 56 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

88
net/ipv4/nexthop.c
View File

@ -20,8 +20,8 @@
#define NH_RES_DEFAULT_IDLE_TIMER (120 * HZ)
#define NH_RES_DEFAULT_UNBALANCED_TIMER 0 /* No forced rebalancing. */
static void remove_nexthop(struct net *net, struct nexthop *nh,
struct nl_info *nlinfo);
static bool __must_check remove_nexthop(struct net *net, struct nexthop *nh,
struct nl_info *nlinfo);
#define NH_DEV_HASHBITS 8
#define NH_DEV_HASHSIZE (1U << NH_DEV_HASHBITS)
@ -2016,9 +2016,9 @@ static void nh_hthr_group_rebalance(struct nh_group *nhg)
}
}
static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge,
struct nl_info *nlinfo,
struct list_head *deferred_free)
static bool __must_check
remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge,
struct nl_info *nlinfo, struct list_head *deferred_free)
{
struct nh_grp_entry *nhges, *new_nhges;
struct nexthop *nhp = nhge->nh_parent;
@ -2033,10 +2033,8 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge,
newg = nhg->spare;
/* last entry, keep it visible and remove the parent */
if (nhg->num_nh == 1) {
remove_nexthop(net, nhp, nlinfo);
return;
}
if (nhg->num_nh == 1)
return remove_nexthop(net, nhp, nlinfo);
newg->has_v4 = false;
newg->is_multipath = nhg->is_multipath;
@ -2093,22 +2091,27 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge,
if (nlinfo)
nexthop_notify(RTM_NEWNEXTHOP, nhp, nlinfo);
return false;
}
static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh,
struct nl_info *nlinfo)
static bool __must_check
remove_nexthop_from_groups(struct net *net, struct nexthop *nh,
struct nl_info *nlinfo)
{
struct nh_grp_entry *nhge, *tmp;
LIST_HEAD(deferred_free);
bool need_flush = false;
/* If there is nothing to do, let's avoid the costly call to
* synchronize_net()
*/
if (list_empty(&nh->grp_list))
return;
return false;
list_for_each_entry_safe(nhge, tmp, &nh->grp_list, nh_list)
remove_nh_grp_entry(net, nhge, nlinfo, &deferred_free);
need_flush |= remove_nh_grp_entry(net, nhge, nlinfo,
&deferred_free);
/* make sure all see the newly published array before releasing rtnl */
synchronize_net();
@ -2118,6 +2121,8 @@ static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh,
list_del(&nhge->nh_list);
free_percpu(nhge->stats);
}
return need_flush;
}
static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo)
@ -2142,18 +2147,15 @@ static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo)
}
/* not called for nexthop replace */
static void __remove_nexthop_fib(struct net *net, struct nexthop *nh)
static bool __must_check __remove_nexthop_fib(struct net *net,
struct nexthop *nh)
{
bool need_flush = !list_empty(&nh->fi_list);
struct fib6_info *f6i;
bool do_flush = false;
struct fib_info *fi;
list_for_each_entry(fi, &nh->fi_list, nh_list) {
list_for_each_entry(fi, &nh->fi_list, nh_list)
fi->fib_flags |= RTNH_F_DEAD;
do_flush = true;
}
if (do_flush)
fib_flush(net);
spin_lock_bh(&nh->lock);
@ -2173,12 +2175,14 @@ static void __remove_nexthop_fib(struct net *net, struct nexthop *nh)
}
spin_unlock_bh(&nh->lock);
return need_flush;
}
static void __remove_nexthop(struct net *net, struct nexthop *nh,
struct nl_info *nlinfo)
static bool __must_check __remove_nexthop(struct net *net, struct nexthop *nh,
struct nl_info *nlinfo)
{
__remove_nexthop_fib(net, nh);
bool need_flush = __remove_nexthop_fib(net, nh);
if (nh->is_group) {
remove_nexthop_group(nh, nlinfo);
@ -2189,13 +2193,17 @@ static void __remove_nexthop(struct net *net, struct nexthop *nh,
if (nhi->fib_nhc.nhc_dev)
hlist_del(&nhi->dev_hash);
remove_nexthop_from_groups(net, nh, nlinfo);
need_flush |= remove_nexthop_from_groups(net, nh, nlinfo);
}
return need_flush;
}
static void remove_nexthop(struct net *net, struct nexthop *nh,
struct nl_info *nlinfo)
static bool __must_check remove_nexthop(struct net *net, struct nexthop *nh,
struct nl_info *nlinfo)
{
bool need_flush;
call_nexthop_notifiers(net, NEXTHOP_EVENT_DEL, nh, NULL);
/* remove from the tree */
@ -2204,10 +2212,19 @@ static void remove_nexthop(struct net *net, struct nexthop *nh,
if (nlinfo)
nexthop_notify(RTM_DELNEXTHOP, nh, nlinfo);
__remove_nexthop(net, nh, nlinfo);
need_flush = __remove_nexthop(net, nh, nlinfo);
nh_base_seq_inc(net);
nexthop_put(nh);
return need_flush;
}
static void remove_one_nexthop(struct net *net, struct nexthop *nh,
struct nl_info *nlinfo)
{
if (remove_nexthop(net, nh, nlinfo))
fib_flush(net);
}
/* if any FIB entries reference this nexthop, any dst entries
@ -2592,7 +2609,7 @@ static int replace_nexthop(struct net *net, struct nexthop *old,
if (!err) {
nh_rt_cache_flush(net, old, new);
__remove_nexthop(net, new, NULL);
WARN_ON_ONCE(__remove_nexthop(net, new, NULL));
nexthop_put(new);
}
@ -2699,6 +2716,7 @@ static void nexthop_flush_dev(struct net_device *dev, unsigned long event)
unsigned int hash = nh_dev_hashfn(dev->ifindex);
struct net *net = dev_net(dev);
struct hlist_head *head = &net->nexthop.devhash[hash];
bool need_flush = false;
struct hlist_node *n;
struct nh_info *nhi;
@ -2710,22 +2728,28 @@ static void nexthop_flush_dev(struct net_device *dev, unsigned long event)
(event == NETDEV_DOWN || event == NETDEV_CHANGE))
continue;
remove_nexthop(net, nhi->nh_parent, NULL);
need_flush |= remove_nexthop(net, nhi->nh_parent, NULL);
}
if (need_flush)
fib_flush(net);
}
/* rtnl; called when net namespace is deleted */
static void flush_all_nexthops(struct net *net)
{
struct rb_root *root = &net->nexthop.rb_root;
bool need_flush = false;
struct rb_node *node;
struct nexthop *nh;
while ((node = rb_first(root))) {
nh = rb_entry(node, struct nexthop, rb_node);
remove_nexthop(net, nh, NULL);
need_flush |= remove_nexthop(net, nh, NULL);
cond_resched();
}
if (need_flush)
fib_flush(net);
}
static struct nexthop *nexthop_create_group(struct net *net,
@ -2994,7 +3018,7 @@ static struct nexthop *nexthop_add(struct net *net, struct nh_config *cfg,
err = insert_nexthop(net, nh, cfg, extack);
if (err) {
__remove_nexthop(net, nh, NULL);
WARN_ON_ONCE(__remove_nexthop(net, nh, NULL));
nexthop_put(nh);
nh = ERR_PTR(err);
}
@ -3363,7 +3387,7 @@ static int rtm_del_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh,
nh = nexthop_find_by_id(net, id);
if (nh)
remove_nexthop(net, nh, &nlinfo);
remove_one_nexthop(net, nh, &nlinfo);
else
err = -ENOENT;