net: ipv4: Emit notification when fib hardware flags are changed

After installing a route to the kernel, user space receives an
acknowledgment, which means the route was installed in the kernel,
but not necessarily in hardware.

The asynchronous nature of route installation in hardware can lead to a
routing daemon advertising a route before it was actually installed in
hardware. This can result in packet loss or mis-routed packets until the
route is installed in hardware.

It is also possible for a route already installed in hardware to change
its action and therefore its flags. For example, a host route that is
trapping packets can be "promoted" to perform decapsulation following
the installation of an IPinIP/VXLAN tunnel.

Emit RTM_NEWROUTE notifications whenever RTM_F_OFFLOAD/RTM_F_TRAP flags
are changed. The aim is to provide an indication to user-space
(e.g., routing daemons) about the state of the route in hardware.

Introduce a sysctl that controls this behavior.

Keep the default value at 0 (i.e., do not emit notifications) for several
reasons:
- Multiple RTM_NEWROUTE notification per-route might confuse existing
  routing daemons.
- Convergence reasons in routing daemons.
- The extra notifications will negatively impact the insertion rate.
- Not all users are interested in these notifications.

Signed-off-by: Amit Cohen <amcohen@nvidia.com>
Acked-by: Roopa Prabhu <roopa@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index 2685ec161060b75791949eb1c008c2458c90ac37..b0e800e68366fa42109b03354aeac449461f9cdc 100644 (file)
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -178,6 +178,26 @@ min_adv_mss - INTEGER
        The advertised MSS depends on the first hop route MTU, but will
        never be lower than this setting.
 
+fib_notify_on_flag_change - INTEGER
+        Whether to emit RTM_NEWROUTE notifications whenever RTM_F_OFFLOAD/
+        RTM_F_TRAP flags are changed.
+
+        After installing a route to the kernel, user space receives an
+        acknowledgment, which means the route was installed in the kernel,
+        but not necessarily in hardware.
+        It is also possible for a route already installed in hardware to change
+        its action and therefore its flags. For example, a host route that is
+        trapping packets can be "promoted" to perform decapsulation following
+        the installation of an IPinIP/VXLAN tunnel.
+        The notifications will indicate to user-space the state of the route.
+
+        Default: 0 (Do not emit notifications.)
+
+        Possible values:
+
+        - 0 - Do not emit notifications.
+        - 1 - Emit notifications.
+
 IP Fragmentation:
 
 ipfrag_high_thresh - LONG INTEGER

diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 8e4fcac4df72f7f4188df410e90e3706998dc738..70a2a085dd1aecc0b4cbbe9d2f678bb53bd84051 100644 (file)
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -188,6 +188,8 @@ struct netns_ipv4 {
        int sysctl_udp_wmem_min;
        int sysctl_udp_rmem_min;
 
+       int sysctl_fib_notify_on_flag_change;
+
 #ifdef CONFIG_NET_L3_MASTER_DEV
        int sysctl_udp_l3mdev_accept;
 #endif

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index b94fa8eb831bf3b18917529ef6a9263edb968592..ab42f6404fc62064719d11730d03f113890b8abd 100644 (file)
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1871,6 +1871,8 @@ static __net_init int inet_init_net(struct net *net)
        net->ipv4.sysctl_igmp_llm_reports = 1;
        net->ipv4.sysctl_igmp_qrv = 2;
 
+       net->ipv4.sysctl_fib_notify_on_flag_change = 0;
+
        return 0;
 }
 

diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 28117c05dc353eaccd3e0e18cae02e807427e3b6..60559b7081589c0c14802daa56b7216e0bc1912d 100644 (file)
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1038,6 +1038,8 @@ fib_find_matching_alias(struct net *net, const struct fib_rt_info *fri)
 void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri)
 {
        struct fib_alias *fa_match;
+       struct sk_buff *skb;
+       int err;
 
        rcu_read_lock();
 
@@ -1045,9 +1047,34 @@ void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri)
        if (!fa_match)
                goto out;
 
+       if (fa_match->offload == fri->offload && fa_match->trap == fri->trap)
+               goto out;
+
        fa_match->offload = fri->offload;
        fa_match->trap = fri->trap;
 
+       if (!net->ipv4.sysctl_fib_notify_on_flag_change)
+               goto out;
+
+       skb = nlmsg_new(fib_nlmsg_size(fa_match->fa_info), GFP_ATOMIC);
+       if (!skb) {
+               err = -ENOBUFS;
+               goto errout;
+       }
+
+       err = fib_dump_info(skb, 0, 0, RTM_NEWROUTE, fri, 0);
+       if (err < 0) {
+               /* -EMSGSIZE implies BUG in fib_nlmsg_size() */
+               WARN_ON(err == -EMSGSIZE);
+               kfree_skb(skb);
+               goto errout;
+       }
+
+       rtnl_notify(skb, net, 0, RTNLGRP_IPV4_ROUTE, NULL, GFP_ATOMIC);
+       goto out;
+
+errout:
+       rtnl_set_sk_err(net, RTNLGRP_IPV4_ROUTE, err);
 out:
        rcu_read_unlock();
 }

diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 3e5f4f2e705e84937112aed32df60b6a9d7e8127..e5798b3b59d23207a470900deea63065c9445586 100644 (file)
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -1354,6 +1354,15 @@ static struct ctl_table ipv4_net_table[] = {
                .proc_handler   = proc_dointvec_minmax,
                .extra1         = SYSCTL_ONE
        },
+       {
+               .procname       = "fib_notify_on_flag_change",
+               .data           = &init_net.ipv4.sysctl_fib_notify_on_flag_change,
+               .maxlen         = sizeof(int),
+               .mode           = 0644,
+               .proc_handler   = proc_dointvec_minmax,
+               .extra1         = SYSCTL_ZERO,
+               .extra2         = SYSCTL_ONE,
+       },
        { }
 };