On 09/21/2017 02:19 PM, Nikolay Aleksandrov wrote:
> On 21/09/17 09:43, Jiri Pirko wrote:
>> From: Yotam Gigi <yot...@mellanox.com>
>>
>> Make the ipmr module register as a FIB notifier. To do that, implement both
>> the ipmr_seq_read and ipmr_dump ops.
>>
>> The ipmr_seq_read op returns a sequence counter that is incremented on
>> every notification related operation done by the ipmr. To implement that,
>> add a sequence counter in the netns_ipv4 struct and increment it whenever a
>> new MFC route or VIF are added or deleted. The sequence operations are
>> protected by the RTNL lock.
>>
>> The ipmr_dump iterates the list of MFC routes and the list of VIF entries
>> and sends notifications about them. The entries dump is done under RCU.
>>
>> Signed-off-by: Yotam Gigi <yot...@mellanox.com>
>> Reviewed-by: Ido Schimmel <ido...@mellanox.com>
>> Signed-off-by: Jiri Pirko <j...@mellanox.com>
>> ---
>> include/linux/mroute.h | 15 ++++++
>> include/net/netns/ipv4.h | 3 ++
>> net/ipv4/ipmr.c | 135
>> ++++++++++++++++++++++++++++++++++++++++++++++-
>> 3 files changed, 151 insertions(+), 2 deletions(-)
>>
> [snip]
>> +
>> +static int ipmr_dump(struct net *net, struct notifier_block *nb)
>> +{
>> + struct mr_table *mrt;
>> + int err;
>> +
>> + err = ipmr_rules_dump(net, nb);
>> + if (err)
>> + return err;
>> +
>> + ipmr_for_each_table(mrt, net) {
>> + struct vif_device *v = &mrt->vif_table[0];
>> + struct mfc_cache *mfc;
>> + int vifi;
>> +
>> + /* Notifiy on table VIF entries */
>> + for (vifi = 0; vifi < mrt->maxvif; vifi++, v++) {
>> + if (!v->dev)
>> + continue;
>> +
>> + call_ipmr_vif_entry_notifier(nb, net, FIB_EVENT_VIF_ADD,
>> + v, vifi, mrt->id);
>> + }
> The VIF table is protected by mrt_lock (rwlock), here with RCU only
> you're not guaranteed to keep v->dev. It can become NULL after the check
> above.
> For details you can see vif_delete() in net/ipv4/ipmr.c. You need at least
> mrt_lock for reading.
Hmm, that's interesting. That situation would lead the dump to be inconsistent,
thus eventually discarded, right? So I can also just make sure that the driver
ignores dev=NULL notifications and that would be enough to solve it.
I have to think about it a bit more, but anyway, maybe taking the mrt_lock for
the VIF dump is the right solution here.
Anyway, thanks for the review!
>> +
>> + /* Notify on table MFC entries */
>> + list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list)
>> + call_ipmr_mfc_entry_notifier(nb, net,
>> + FIB_EVENT_ENTRY_ADD, mfc,
>> + mrt->id);
>> + }
>> +
>> + return 0;
>> +}
>> +
>> +static const struct fib_notifier_ops ipmr_notifier_ops_template = {
>> + .family = RTNL_FAMILY_IPMR,
>> + .fib_seq_read = ipmr_seq_read,
>> + .fib_dump = ipmr_dump,
>> + .owner = THIS_MODULE,
>> +};
>> +
>> +int __net_init ipmr_notifier_init(struct net *net)
>> +{
>> + struct fib_notifier_ops *ops;
>> +
>> + net->ipv4.ipmr_seq = 0;
>> +
>> + ops = fib_notifier_ops_register(&ipmr_notifier_ops_template, net);
>> + if (IS_ERR(ops))
>> + return PTR_ERR(ops);
>> + net->ipv4.ipmr_notifier_ops = ops;
>> +
>> + return 0;
>> +}
>> +
>> +static void __net_exit ipmr_notifier_exit(struct net *net)
>> +{
>> + fib_notifier_ops_unregister(net->ipv4.ipmr_notifier_ops);
>> + net->ipv4.ipmr_notifier_ops = NULL;
>> +}
>> +
>> /* Setup for IP multicast routing */
>> static int __net_init ipmr_net_init(struct net *net)
>> {
>> int err;
>>
>> + err = ipmr_notifier_init(net);
>> + if (err)
>> + goto ipmr_notifier_fail;
>> +
>> err = ipmr_rules_init(net);
>> if (err < 0)
>> - goto fail;
>> + goto ipmr_rules_fail;
>>
>> #ifdef CONFIG_PROC_FS
>> err = -ENOMEM;
>> @@ -3074,7 +3202,9 @@ static int __net_init ipmr_net_init(struct net *net)
>> proc_vif_fail:
>> ipmr_rules_exit(net);
>> #endif
>> -fail:
>> +ipmr_rules_fail:
>> + ipmr_notifier_exit(net);
>> +ipmr_notifier_fail:
>> return err;
>> }
>>
>> @@ -3084,6 +3214,7 @@ static void __net_exit ipmr_net_exit(struct net *net)
>> remove_proc_entry("ip_mr_cache", net->proc_net);
>> remove_proc_entry("ip_mr_vif", net->proc_net);
>> #endif
>> + ipmr_notifier_exit(net);
>> ipmr_rules_exit(net);
>> }
>>
>>
