[lkml]   [2022]   [Jan]   [24]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
    Patch in this message
    Subject[PATCH 5.4 300/320] netns: add schedule point in ops_exit_list()
    From: Eric Dumazet <>

    commit 2836615aa22de55b8fca5e32fe1b27a67cda625e upstream.

    When under stress, cleanup_net() can have to dismantle
    netns in big numbers. ops_exit_list() currently calls
    many helpers [1] that have no schedule point, and we can
    end up with soft lockups, particularly on hosts
    with many cpus.

    Even for moderate amount of netns processed by cleanup_net()
    this patch avoids latency spikes.

    [1] Some of these helpers like fib_sync_up() and fib_sync_down_dev()
    are very slow because net/ipv4/fib_semantics.c uses host-wide hash tables,
    and ifindex is used as the only input of two hash functions.
    ifindexes tend to be the same for all netns (lo.ifindex==1 per instance)
    This will be fixed in a separate patch.

    Fixes: 72ad937abd0a ("net: Add support for batching network namespace cleanups")
    Signed-off-by: Eric Dumazet <>
    Cc: Eric W. Biederman <>
    Signed-off-by: David S. Miller <>
    Signed-off-by: Greg Kroah-Hartman <>
    net/core/net_namespace.c | 4 +++-
    1 file changed, 3 insertions(+), 1 deletion(-)

    --- a/net/core/net_namespace.c
    +++ b/net/core/net_namespace.c
    @@ -168,8 +168,10 @@ static void ops_exit_list(const struct p
    struct net *net;
    if (ops->exit) {
    - list_for_each_entry(net, net_exit_list, exit_list)
    + list_for_each_entry(net, net_exit_list, exit_list) {
    + cond_resched();
    + }
    if (ops->exit_batch)

     \ /
      Last update: 2022-01-24 21:11    [W:4.043 / U:0.424 seconds]
    ©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site