nexthop: Restart nexthop dump based on last dumped nexthop identifier

Currently, a multi-part nexthop dump is restarted based on the number of
nexthops that have been dumped so far. This can result in a lot of
nexthops not being dumped when nexthops are simultaneously deleted:

 # ip nexthop | wc -l
 65536
 # ip nexthop flush
 Dump was interrupted and may be inconsistent.
 Flushed 36040 nexthops
 # ip nexthop | wc -l
 29496

Instead, restart the dump based on the nexthop identifier (fixed number)
of the last successfully dumped nexthop:

 # ip nexthop | wc -l
 65536
 # ip nexthop flush
 Dump was interrupted and may be inconsistent.
 Flushed 65536 nexthops
 # ip nexthop | wc -l
 0

Reported-by: Maksym Yaremchuk <maksymy@nvidia.com>
Tested-by: Maksym Yaremchuk <maksymy@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 6 insertions, 8 deletions

diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 5a2fc8798d20..4075230b14c6 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -3140,26 +3140,24 @@ static int rtm_dump_walk_nexthops(struct sk_buff *skb,
 				  void *data)
 {
 	struct rb_node *node;
-	int idx = 0, s_idx;
+	int s_idx;
 	int err;
 
 	s_idx = ctx->idx;
 	for (node = rb_first(root); node; node = rb_next(node)) {
 		struct nexthop *nh;
 
-		if (idx < s_idx)
-			goto cont;
-
 		nh = rb_entry(node, struct nexthop, rb_node);
-		ctx->idx = idx;
+		if (nh->id < s_idx)
+			continue;
+
+		ctx->idx = nh->id;
 		err = nh_cb(skb, cb, nh, data);
 		if (err)
 			return err;
-cont:
-		idx++;
 	}
 
-	ctx->idx = idx;
+	ctx->idx++;
 	return 0;
 }