From 77b8d7784082889a66d689aac1972154ef46da08 Mon Sep 17 00:00:00 2001
From: Phil Sutter <phil@nwl.cc>
Date: Tue, 2 Jul 2019 20:30:49 +0200
Subject: [PATCH] nft: Set socket receive buffer

When trying to delete user-defined chains in a large ruleset,
iptables-nft aborts with "No buffer space available". This can be
reproduced using the following script:

| #! /bin/bash
| iptables-nft-restore <(
|
| echo "*filter"
| for i in $(seq 0 200000);do
|         printf ":chain_%06x - [0:0]\n" $i
| done
| for i in $(seq 0 200000);do
|         printf -- "-A INPUT -j chain_%06x\n" $i
|         printf -- "-A INPUT -j chain_%06x\n" $i
| done
| echo COMMIT
|
| )
| iptables-nft -X

The problem seems to be the sheer amount of netlink error messages sent
back to user space (one EBUSY for each chain). To solve this, set
receive buffer size depending on number of commands sent to kernel.

Suggested-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
(cherry picked from commit d3e39e9c457f452540359e42fb58d64a28fe3e18)

Conflicts:
	iptables/nft.c
-> Context change due to missing commits 17c282003f463
   ("nft: reset netlink sender buffer size of socket restart") and
   58d7de0181f61 ("xtables: handle concurrent ruleset modifications").

Signed-off-by: Phil Sutter <psutter@redhat.com>
---
 iptables/nft.c | 27 +++++++++++++++++++++++----
 1 file changed, 23 insertions(+), 4 deletions(-)

diff --git a/iptables/nft.c b/iptables/nft.c
index d708fb6176b88..87fdd1e66152d 100644
--- a/iptables/nft.c
+++ b/iptables/nft.c
@@ -170,8 +170,24 @@ static void mnl_set_sndbuffer(const struct mnl_socket *nl,
 	nlbuffsiz = newbuffsiz;
 }
 
+static int nlrcvbuffsiz;
+
+static void mnl_set_rcvbuffer(const struct mnl_socket *nl, int numcmds)
+{
+	int newbuffsiz = getpagesize() * numcmds;
+
+	if (newbuffsiz <= nlrcvbuffsiz)
+		return;
+
+	if (setsockopt(mnl_socket_get_fd(nl), SOL_SOCKET, SO_RCVBUFFORCE,
+		       &newbuffsiz, sizeof(socklen_t)) < 0)
+		return;
+
+	nlrcvbuffsiz = newbuffsiz;
+}
+
 static ssize_t mnl_nft_socket_sendmsg(const struct mnl_socket *nf_sock,
-				      struct nftnl_batch *batch)
+				      struct nftnl_batch *batch, int numcmds)
 {
 	static const struct sockaddr_nl snl = {
 		.nl_family = AF_NETLINK
@@ -186,13 +202,15 @@ static ssize_t mnl_nft_socket_sendmsg(const struct mnl_socket *nf_sock,
 	};
 
 	mnl_set_sndbuffer(nf_sock, batch);
+	mnl_set_rcvbuffer(nf_sock, numcmds);
 	nftnl_batch_iovec(batch, iov, iov_len);
 
 	return sendmsg(mnl_socket_get_fd(nf_sock), &msg, 0);
 }
 
 static int mnl_batch_talk(const struct mnl_socket *nf_sock,
-			  struct nftnl_batch *batch, struct list_head *err_list)
+			  struct nftnl_batch *batch, int numcmds,
+			  struct list_head *err_list)
 {
 	const struct mnl_socket *nl = nf_sock;
 	int ret, fd = mnl_socket_get_fd(nl), portid = mnl_socket_get_portid(nl);
@@ -204,7 +222,7 @@ static int mnl_batch_talk(const struct mnl_socket *nf_sock,
 	};
 	int err = 0;
 
-	ret = mnl_nft_socket_sendmsg(nf_sock, batch);
+	ret = mnl_nft_socket_sendmsg(nf_sock, batch, numcmds);
 	if (ret == -1)
 		return -1;
 
@@ -748,6 +766,7 @@ static int nft_restart(struct nft_handle *h)
 		return -1;
 
 	h->portid = mnl_socket_get_portid(h->nl);
+	nlrcvbuffsiz = 0;
 
 	return 0;
 }
@@ -2728,7 +2747,7 @@ static int nft_action(struct nft_handle *h, int action)
 		break;
 	}
 
-	ret = mnl_batch_talk(h->nl, h->batch, &h->err_list);
+	ret = mnl_batch_talk(h->nl, h->batch, seq, &h->err_list);
 
 	i = 0;
 	buflen = sizeof(errmsg);
-- 
2.22.0