[UDP]: Add memory accounting.

Signed-off-by: Takahiro Yasui <tyasui@redhat.com>
Signed-off-by: Hideo Aoki <haoki@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 157 insertions, 7 deletions

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 6f7872b..17a6e46 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -446,6 +446,33 @@ tcp_dma_copybreak - INTEGER
 	and CONFIG_NET_DMA is enabled.
 	Default: 4096
 
+UDP variables:
+
+udp_mem - vector of 3 INTEGERs: min, pressure, max
+	Number of pages allowed for queueing by all UDP sockets.
+
+	min: Below this number of pages UDP is not bothered about its
+	memory appetite. When amount of memory allocated by UDP exceeds
+	this number, UDP starts to moderate memory usage.
+
+	pressure: This value was introduced to follow format of tcp_mem.
+
+	max: Number of pages allowed for queueing by all UDP sockets.
+
+	Default is calculated at boot time from amount of available memory.
+
+udp_rmem_min - INTEGER
+	Minimal size of receive buffer used by UDP sockets in moderation.
+	Each UDP socket is able to use the size for receiving data, even if
+	total pages of UDP sockets exceed udp_mem pressure. The unit is byte.
+	Default: 4096
+
+udp_wmem_min - INTEGER
+	Minimal size of send buffer used by UDP sockets in moderation.
+	Each UDP socket is able to use the size for sending data, even if
+	total pages of UDP sockets exceed udp_mem pressure. The unit is byte.
+	Default: 4096
+
 CIPSOv4 Variables:
 
 cipso_cache_enable - BOOLEAN
diff --git a/include/net/udp.h b/include/net/udp.h
index 98cb09c..93796be 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -65,6 +65,13 @@ extern rwlock_t udp_hash_lock;
 
 extern struct proto udp_prot;
 
+extern atomic_t udp_memory_allocated;
+
+/* sysctl variables for udp */
+extern int sysctl_udp_mem[3];
+extern int sysctl_udp_rmem_min;
+extern int sysctl_udp_wmem_min;
+
 struct sk_buff;
 
 /*
@@ -198,4 +205,6 @@ extern void udp_proc_unregister(struct udp_seq_afinfo *afinfo);
 extern int  udp4_proc_init(void);
 extern void udp4_proc_exit(void);
 #endif
+
+extern void udp_init(void);
 #endif	/* _UDP_H */
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 03633b7..0e12cf6 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -139,6 +139,8 @@ void inet_sock_destruct(struct sock *sk)
 	__skb_queue_purge(&sk->sk_receive_queue);
 	__skb_queue_purge(&sk->sk_error_queue);
 
+	sk_mem_reclaim(sk);
+
 	if (sk->sk_type == SOCK_STREAM && sk->sk_state != TCP_CLOSE) {
 		printk("Attempt to release TCP socket in state %d %p\n",
 		       sk->sk_state, sk);
@@ -1417,6 +1419,9 @@ static int __init inet_init(void)
 	/* Setup TCP slab cache for open requests. */
 	tcp_init();
 
+	/* Setup UDP memory threshold */
+	udp_init();
+
 	/* Add UDP-Lite (RFC 3828) */
 	udplite4_register();
 
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 41734db..53bc010 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -56,7 +56,8 @@ static int sockstat_seq_show(struct seq_file *seq, void *v)
 		   sock_prot_inuse(&tcp_prot), atomic_read(&tcp_orphan_count),
 		   tcp_death_row.tw_count, atomic_read(&tcp_sockets_allocated),
 		   atomic_read(&tcp_memory_allocated));
-	seq_printf(seq, "UDP: inuse %d\n", sock_prot_inuse(&udp_prot));
+	seq_printf(seq, "UDP: inuse %d mem %d\n", sock_prot_inuse(&udp_prot),
+		   atomic_read(&udp_memory_allocated));
 	seq_printf(seq, "UDPLITE: inuse %d\n", sock_prot_inuse(&udplite_prot));
 	seq_printf(seq, "RAW: inuse %d\n", sock_prot_inuse(&raw_prot));
 	seq_printf(seq,  "FRAG: inuse %d memory %d\n",
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 844f26f..a5a9f8e3 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -19,6 +19,7 @@
 #include <net/ip.h>
 #include <net/route.h>
 #include <net/tcp.h>
+#include <net/udp.h>
 #include <net/cipso_ipv4.h>
 #include <net/inet_frag.h>
 
@@ -812,6 +813,36 @@ static struct ctl_table ipv4_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec,
 	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "udp_mem",
+		.data		= &sysctl_udp_mem,
+		.maxlen		= sizeof(sysctl_udp_mem),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "udp_rmem_min",
+		.data		= &sysctl_udp_rmem_min,
+		.maxlen		= sizeof(sysctl_udp_rmem_min),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "udp_wmem_min",
+		.data		= &sysctl_udp_wmem_min,
+		.maxlen		= sizeof(sysctl_udp_wmem_min),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero
+	},
 	{ .ctl_name = 0 }
 };
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 1ce6b60..3532843 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -82,6 +82,7 @@
 #include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/ioctls.h>
+#include <linux/bootmem.h>
 #include <linux/types.h>
 #include <linux/fcntl.h>
 #include <linux/module.h>
@@ -118,6 +119,17 @@ EXPORT_SYMBOL(udp_stats_in6);
 struct hlist_head udp_hash[UDP_HTABLE_SIZE];
 DEFINE_RWLOCK(udp_hash_lock);
 
+int sysctl_udp_mem[3] __read_mostly;
+int sysctl_udp_rmem_min __read_mostly;
+int sysctl_udp_wmem_min __read_mostly;
+
+EXPORT_SYMBOL(sysctl_udp_mem);
+EXPORT_SYMBOL(sysctl_udp_rmem_min);
+EXPORT_SYMBOL(sysctl_udp_wmem_min);
+
+atomic_t udp_memory_allocated;
+EXPORT_SYMBOL(udp_memory_allocated);
+
 static inline int __udp_lib_lport_inuse(__u16 num,
 					const struct hlist_head udptable[])
 {
@@ -901,13 +913,17 @@ try_again:
 		err = ulen;
 
 out_free:
+	lock_sock(sk);
 	skb_free_datagram(sk, skb);
+	release_sock(sk);
 out:
 	return err;
 
 csum_copy_err:
+	lock_sock(sk);
 	if (!skb_kill_datagram(sk, skb, flags))
 		UDP_INC_STATS_USER(UDP_MIB_INERRORS, is_udplite);
+	release_sock(sk);
 
 	if (noblock)
 		return -EAGAIN;
@@ -1072,7 +1088,15 @@ static int __udp4_lib_mcast_deliver(struct sk_buff *skb,
 				skb1 = skb_clone(skb, GFP_ATOMIC);
 
 			if (skb1) {
-				int ret = udp_queue_rcv_skb(sk, skb1);
+				int ret = 0;
+
+				bh_lock_sock_nested(sk);
+				if (!sock_owned_by_user(sk))
+					ret = udp_queue_rcv_skb(sk, skb1);
+				else
+					sk_add_backlog(sk, skb1);
+				bh_unlock_sock(sk);
+
 				if (ret > 0)
 					/* we should probably re-process instead
 					 * of dropping packets here. */
@@ -1165,7 +1189,13 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[],
 			       inet_iif(skb), udptable);
 
 	if (sk != NULL) {
-		int ret = udp_queue_rcv_skb(sk, skb);
+		int ret = 0;
+		bh_lock_sock_nested(sk);
+		if (!sock_owned_by_user(sk))
+			ret = udp_queue_rcv_skb(sk, skb);
+		else
+			sk_add_backlog(sk, skb);
+		bh_unlock_sock(sk);
 		sock_put(sk);
 
 		/* a return value > 0 means to resubmit the input, but
@@ -1460,6 +1490,10 @@ struct proto udp_prot = {
 	.hash		   = udp_lib_hash,
 	.unhash		   = udp_lib_unhash,
 	.get_port	   = udp_v4_get_port,
+	.memory_allocated  = &udp_memory_allocated,
+	.sysctl_mem	   = sysctl_udp_mem,
+	.sysctl_wmem	   = &sysctl_udp_wmem_min,
+	.sysctl_rmem	   = &sysctl_udp_rmem_min,
 	.obj_size	   = sizeof(struct udp_sock),
 #ifdef CONFIG_COMPAT
 	.compat_setsockopt = compat_udp_setsockopt,
@@ -1655,6 +1689,25 @@ void udp4_proc_exit(void)
 }
 #endif /* CONFIG_PROC_FS */
 
+void __init udp_init(void)
+{
+	unsigned long limit;
+
+	/* Set the pressure threshold up by the same strategy of TCP. It is a
+	 * fraction of global memory that is up to 1/2 at 256 MB, decreasing
+	 * toward zero with the amount of memory, with a floor of 128 pages.
+	 */
+	limit = min(nr_all_pages, 1UL<<(28-PAGE_SHIFT)) >> (20-PAGE_SHIFT);
+	limit = (limit * (nr_all_pages >> (20-PAGE_SHIFT))) >> (PAGE_SHIFT-11);
+	limit = max(limit, 128UL);
+	sysctl_udp_mem[0] = limit / 4 * 3;
+	sysctl_udp_mem[1] = limit;
+	sysctl_udp_mem[2] = sysctl_udp_mem[0] * 2;
+
+	sysctl_udp_rmem_min = SK_MEM_QUANTUM;
+	sysctl_udp_wmem_min = SK_MEM_QUANTUM;
+}
+
 EXPORT_SYMBOL(udp_disconnect);
 EXPORT_SYMBOL(udp_hash);
 EXPORT_SYMBOL(udp_hash_lock);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index c9a97b4..bf58aca 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -204,13 +204,17 @@ try_again:
 		err = ulen;
 
 out_free:
+	lock_sock(sk);
 	skb_free_datagram(sk, skb);
+	release_sock(sk);
 out:
 	return err;
 
 csum_copy_err:
+	lock_sock(sk);
 	if (!skb_kill_datagram(sk, skb, flags))
 		UDP6_INC_STATS_USER(UDP_MIB_INERRORS, is_udplite);
+	release_sock(sk);
 
 	if (flags & MSG_DONTWAIT)
 		return -EAGAIN;
@@ -366,10 +370,21 @@ static int __udp6_lib_mcast_deliver(struct sk_buff *skb, struct in6_addr *saddr,
 	while ((sk2 = udp_v6_mcast_next(sk_next(sk2), uh->dest, daddr,
 					uh->source, saddr, dif))) {
 		struct sk_buff *buff = skb_clone(skb, GFP_ATOMIC);
-		if (buff)
-			udpv6_queue_rcv_skb(sk2, buff);
+		if (buff) {
+			bh_lock_sock_nested(sk2);
+			if (!sock_owned_by_user(sk2))
+				udpv6_queue_rcv_skb(sk2, buff);
+			else
+				sk_add_backlog(sk2, buff);
+			bh_unlock_sock(sk2);
+		}
 	}
-	udpv6_queue_rcv_skb(sk, skb);
+	bh_lock_sock_nested(sk);
+	if (!sock_owned_by_user(sk))
+		udpv6_queue_rcv_skb(sk, skb);
+	else
+		sk_add_backlog(sk, skb);
+	bh_unlock_sock(sk);
 out:
 	read_unlock(&udp_hash_lock);
 	return 0;
@@ -482,7 +497,12 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[],
 
 	/* deliver */
 
-	udpv6_queue_rcv_skb(sk, skb);
+	bh_lock_sock_nested(sk);
+	if (!sock_owned_by_user(sk))
+		udpv6_queue_rcv_skb(sk, skb);
+	else
+		sk_add_backlog(sk, skb);
+	bh_unlock_sock(sk);
 	sock_put(sk);
 	return 0;
 
@@ -994,6 +1014,10 @@ struct proto udpv6_prot = {
 	.hash		   = udp_lib_hash,
 	.unhash		   = udp_lib_unhash,
 	.get_port	   = udp_v6_get_port,
+	.memory_allocated  = &udp_memory_allocated,
+	.sysctl_mem	   = sysctl_udp_mem,
+	.sysctl_wmem	   = &sysctl_udp_wmem_min,
+	.sysctl_rmem	   = &sysctl_udp_rmem_min,
 	.obj_size	   = sizeof(struct udp6_sock),
 #ifdef CONFIG_COMPAT
 	.compat_setsockopt = compat_udpv6_setsockopt,