net: Namespace-ify sysctl_optmem_max

optmem_max being used in tx zerocopy,
we want to be able to control it on a netns basis.

Following patch changes two tests.

Tested:

oqq130:~# cat /proc/sys/net/core/optmem_max
131072
oqq130:~# echo 1000000 >/proc/sys/net/core/optmem_max
oqq130:~# cat /proc/sys/net/core/optmem_max
1000000
oqq130:~# unshare -n
oqq130:~# cat /proc/sys/net/core/optmem_max
131072
oqq130:~# exit
logout
oqq130:~# cat /proc/sys/net/core/optmem_max
1000000

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 28 insertions, 26 deletions

diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index cca7594be92e..6c4d90b24d46 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -275,9 +275,10 @@ BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk)
 static int bpf_sk_storage_charge(struct bpf_local_storage_map *smap,
 				 void *owner, u32 size)
 {
-	int optmem_max = READ_ONCE(sysctl_optmem_max);
 	struct sock *sk = (struct sock *)owner;
+	int optmem_max;
 
+	optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max);
 	/* same check as in sock_kmalloc() */
 	if (size <= optmem_max &&
 	    atomic_read(&sk->sk_omem_alloc) + size < optmem_max) {
diff --git a/net/core/filter.c b/net/core/filter.c
index eedb33f3e998..6d89a9cf33c9 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1219,8 +1219,8 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
  */
 static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp)
 {
+	int optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max);
 	u32 filter_size = bpf_prog_size(fp->prog->len);
-	int optmem_max = READ_ONCE(sysctl_optmem_max);
 
 	/* same check as in sock_kmalloc() */
 	if (filter_size <= optmem_max &&
@@ -1550,12 +1550,13 @@ EXPORT_SYMBOL_GPL(sk_attach_filter);
 int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 {
 	struct bpf_prog *prog = __get_filter(fprog, sk);
-	int err;
+	int err, optmem_max;
 
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
 
-	if (bpf_prog_size(prog->len) > READ_ONCE(sysctl_optmem_max))
+	optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max);
+	if (bpf_prog_size(prog->len) > optmem_max)
 		err = -ENOMEM;
 	else
 		err = reuseport_attach_prog(sk, prog);
@@ -1594,7 +1595,7 @@ int sk_attach_bpf(u32 ufd, struct sock *sk)
 int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk)
 {
 	struct bpf_prog *prog;
-	int err;
+	int err, optmem_max;
 
 	if (sock_flag(sk, SOCK_FILTER_LOCKED))
 		return -EPERM;
@@ -1622,7 +1623,8 @@ int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk)
 		}
 	} else {
 		/* BPF_PROG_TYPE_SOCKET_FILTER */
-		if (bpf_prog_size(prog->len) > READ_ONCE(sysctl_optmem_max)) {
+		optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max);
+		if (bpf_prog_size(prog->len) > optmem_max) {
 			err = -ENOMEM;
 			goto err_prog_put;
 		}
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index cb8bcbff9e83..72799533426b 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -372,6 +372,10 @@ out_undo:
 static int __net_init net_defaults_init_net(struct net *net)
 {
 	net->core.sysctl_somaxconn = SOMAXCONN;
+	/* Limits per socket sk_omem_alloc usage.
+	 * TCP zerocopy regular usage needs 128 KB.
+	 */
+	net->core.sysctl_optmem_max = 128 * 1024;
 	net->core.sysctl_txrehash = SOCK_TXREHASH_ENABLED;
 
 	return 0;
diff --git a/net/core/sock.c b/net/core/sock.c
index 08ecdc68d2df..446e945f736b 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -283,12 +283,6 @@ EXPORT_SYMBOL(sysctl_rmem_max);
 __u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX;
 __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;
 
-/* Limits per socket sk_omem_alloc usage.
- * TCP zerocopy regular usage needs 128 KB.
- */
-int sysctl_optmem_max __read_mostly = 128 * 1024;
-EXPORT_SYMBOL(sysctl_optmem_max);
-
 int sysctl_tstamp_allow_data __read_mostly = 1;
 
 DEFINE_STATIC_KEY_FALSE(memalloc_socks_key);
@@ -2653,7 +2647,7 @@ struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size,
 
 	/* small safe race: SKB_TRUESIZE may differ from final skb->truesize */
 	if (atomic_read(&sk->sk_omem_alloc) + SKB_TRUESIZE(size) >
-	    READ_ONCE(sysctl_optmem_max))
+	    READ_ONCE(sock_net(sk)->core.sysctl_optmem_max))
 		return NULL;
 
 	skb = alloc_skb(size, priority);
@@ -2671,7 +2665,7 @@ struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size,
  */
 void *sock_kmalloc(struct sock *sk, int size, gfp_t priority)
 {
-	int optmem_max = READ_ONCE(sysctl_optmem_max);
+	int optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max);
 
 	if ((unsigned int)size <= optmem_max &&
 	    atomic_read(&sk->sk_omem_alloc) + size < optmem_max) {
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 03f1edb948d7..0f0cb1465e08 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -509,13 +509,6 @@ static struct ctl_table net_core_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 	{
-		.procname	= "optmem_max",
-		.data		= &sysctl_optmem_max,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
 		.procname	= "tstamp_allow_data",
 		.data		= &sysctl_tstamp_allow_data,
 		.maxlen		= sizeof(int),
@@ -674,6 +667,14 @@ static struct ctl_table netns_core_table[] = {
 		.proc_handler	= proc_dointvec_minmax
 	},
 	{
+		.procname	= "optmem_max",
+		.data		= &init_net.core.sysctl_optmem_max,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.extra1		= SYSCTL_ZERO,
+		.proc_handler	= proc_dointvec_minmax
+	},
+	{
 		.procname	= "txrehash",
 		.data		= &init_net.core.sysctl_txrehash,
 		.maxlen		= sizeof(u8),
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index d7d13940774e..66247e8b429e 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -775,7 +775,7 @@ static int ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen)
 
 	if (optlen < GROUP_FILTER_SIZE(0))
 		return -EINVAL;
-	if (optlen > READ_ONCE(sysctl_optmem_max))
+	if (optlen > READ_ONCE(sock_net(sk)->core.sysctl_optmem_max))
 		return -ENOBUFS;
 
 	gsf = memdup_sockptr(optval, optlen);
@@ -811,7 +811,7 @@ static int compat_ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval,
 
 	if (optlen < size0)
 		return -EINVAL;
-	if (optlen > READ_ONCE(sysctl_optmem_max) - 4)
+	if (optlen > READ_ONCE(sock_net(sk)->core.sysctl_optmem_max) - 4)
 		return -ENOBUFS;
 
 	p = kmalloc(optlen + 4, GFP_KERNEL);
@@ -1254,7 +1254,7 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 
 		if (optlen < IP_MSFILTER_SIZE(0))
 			goto e_inval;
-		if (optlen > READ_ONCE(sysctl_optmem_max)) {
+		if (optlen > READ_ONCE(net->core.sysctl_optmem_max)) {
 			err = -ENOBUFS;
 			break;
 		}
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 9e8ebda170f1..56c3c467f9de 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -210,7 +210,7 @@ static int ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval,
 
 	if (optlen < GROUP_FILTER_SIZE(0))
 		return -EINVAL;
-	if (optlen > READ_ONCE(sysctl_optmem_max))
+	if (optlen > READ_ONCE(sock_net(sk)->core.sysctl_optmem_max))
 		return -ENOBUFS;
 
 	gsf = memdup_sockptr(optval, optlen);
@@ -244,7 +244,7 @@ static int compat_ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval,
 
 	if (optlen < size0)
 		return -EINVAL;
-	if (optlen > READ_ONCE(sysctl_optmem_max) - 4)
+	if (optlen > READ_ONCE(sock_net(sk)->core.sysctl_optmem_max) - 4)
 		return -ENOBUFS;
 
 	p = kmalloc(optlen + 4, GFP_KERNEL);