From 0e4be9e57e8cb8f2130280c26a2d6de9c06a8500 Mon Sep 17 00:00:00 2001 From: Francesco Ruggeri Date: Fri, 18 Sep 2020 13:19:01 -0700 Subject: [PATCH] net: use exponential backoff in netdev_wait_allrefs The combination of aca_free_rcu, introduced in commit 2384d02520ff ("net/ipv6: Add anycast addresses to a global hashtable"), and fib6_info_destroy_rcu, introduced in commit 9b0a8da8c4c6 ("net/ipv6: respect rcu grace period before freeing fib6_info"), can result in an extra rcu grace period being needed when deleting an interface, with the result that netdev_wait_allrefs ends up hitting the msleep(250), which is considerably longer than the required grace period. This can result in long delays when deleting a large number of interfaces, and it can be observed with this script: ns=dummy-ns NIFS=100 ip netns add $ns ip netns exec $ns ip link set lo up ip netns exec $ns sysctl net.ipv6.conf.default.disable_ipv6=0 ip netns exec $ns sysctl net.ipv6.conf.default.forwarding=1 for ((i=0; i<$NIFS; i++)) do if=eth$i ip netns exec $ns ip link add $if type dummy ip netns exec $ns ip link set $if up ip netns exec $ns ip -6 addr add 2021:$i::1/120 dev $if done for ((i=0; i<$NIFS; i++)) do if=eth$i ip netns exec $ns ip link del $if done ip netns del $ns Instead of using a fixed msleep(250), this patch tries an extra rcu_barrier() followed by an exponential backoff. Time with this patch on a 5.4 kernel: real 0m7.704s user 0m0.385s sys 0m1.230s Time without this patch: real 0m31.522s user 0m0.438s sys 0m1.156s v2: use exponential backoff instead of trying to wake up netdev_wait_allrefs. v3: preserve reverse christmas tree ordering of local variables v4: try an extra rcu_barrier before the backoff, plus some cosmetic changes. Signed-off-by: Francesco Ruggeri Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/dev.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/net/core/dev.c b/net/core/dev.c index 10767ce2bf69..bd32ba6202d1 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -10028,10 +10028,12 @@ EXPORT_SYMBOL(netdev_refcnt_read); * We can get stuck here if buggy protocols don't correctly * call dev_put. */ +#define WAIT_REFS_MIN_MSECS 1 +#define WAIT_REFS_MAX_MSECS 250 static void netdev_wait_allrefs(struct net_device *dev) { unsigned long rebroadcast_time, warning_time; - int refcnt; + int wait = 0, refcnt; linkwatch_forget_dev(dev); @@ -10065,7 +10067,13 @@ static void netdev_wait_allrefs(struct net_device *dev) rebroadcast_time = jiffies; } - msleep(250); + if (!wait) { + rcu_barrier(); + wait = WAIT_REFS_MIN_MSECS; + } else { + msleep(wait); + wait = min(wait << 1, WAIT_REFS_MAX_MSECS); + } refcnt = netdev_refcnt_read(dev); -- GitLab