Merge branch 'udpmem'

Paolo Abeni says:

====================
udp: refactor memory accounting

This patch series refactor the udp memory accounting, replacing the
generic implementation with a custom one, in order to remove the needs for
locking the socket on the enqueue and dequeue operations. The socket backlog
usage is dropped, as well.

The first patch factor out pieces of some queue and memory management
socket helpers, so that they can later be used by the udp memory accounting
functions.
The second patch adds the memory account helpers, without using them.
The third patch replacse the old rx memory accounting path for udp over ipv4 and
udp over ipv6. In kernel UDP users are updated, as well.

The memory accounting schema is described in detail in the individual patch
commit message.

The performance gain depends on the specific scenario; with few flows (and
little contention in the original code) the differences are in the noise range,
while with several flows contending the same socket, the measured speed-up
is relevant (e.g. even over 100% in case of extreme contention)

Many thanks to Eric Dumazet for the reiterated reviews and suggestions.

v5 -> v6:
 - do not orphan the skb on enqueue, skb_steal_sock() already did
   the work for us

v4 -> v5:
 - use the receive queue spin lock to protect the memory accounting
 - several minor clean-up

v3 -> v4:
 - simplified the locking schema, always use a plain spinlock

v2 -> v3:
 - do not set the now unsed backlog_rcv callback

v1 -> v2:
 - changed slighly the memory accounting schema, we now perform lazy reclaim
 - fixed forward_alloc updating issue
 - fixed memory counter integer overflows
====================

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

include/net/sock.h

@@ -1274,7 +1274,9 @@ static inline struct inode *SOCK_INODE(struct socket *socket)
 /*
  * Functions for memory accounting
  */
+int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind);
 int __sk_mem_schedule(struct sock *sk, int size, int kind);
+void __sk_mem_reduce_allocated(struct sock *sk, int amount);
 void __sk_mem_reclaim(struct sock *sk, int amount);
 
 #define SK_MEM_QUANTUM ((int)PAGE_SIZE)
@@ -1950,6 +1952,8 @@ void sk_reset_timer(struct sock *sk, struct timer_list *timer,
 
 void sk_stop_timer(struct sock *sk, struct timer_list *timer);
 
+int __sk_queue_drop_skb(struct sock *sk, struct sk_buff *skb,
+			unsigned int flags);
 int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
 int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
 

include/net/udp.h

@@ -246,6 +246,9 @@ static inline __be16 udp_flow_src_port(struct net *net, struct sk_buff *skb,
 }
 
 /* net/ipv4/udp.c */
+void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len);
+int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb);
+
 void udp_v4_early_demux(struct sk_buff *skb);
 int udp_get_port(struct sock *sk, unsigned short snum,
 		 int (*saddr_cmp)(const struct sock *,
@@ -258,6 +261,7 @@ void udp_flush_pending_frames(struct sock *sk);
 void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst);
 int udp_rcv(struct sk_buff *skb);
 int udp_ioctl(struct sock *sk, int cmd, unsigned long arg);
+int udp_init_sock(struct sock *sk);
 int udp_disconnect(struct sock *sk, int flags);
 unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait);
 struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,

net/core/datagram.c

@@ -323,6 +323,27 @@ void __skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb, int len)
 }
 EXPORT_SYMBOL(__skb_free_datagram_locked);
 
+int __sk_queue_drop_skb(struct sock *sk, struct sk_buff *skb,
+			unsigned int flags)
+{
+	int err = 0;
+
+	if (flags & MSG_PEEK) {
+		err = -ENOENT;
+		spin_lock_bh(&sk->sk_receive_queue.lock);
+		if (skb == skb_peek(&sk->sk_receive_queue)) {
+			__skb_unlink(skb, &sk->sk_receive_queue);
+			atomic_dec(&skb->users);
+			err = 0;
+		}
+		spin_unlock_bh(&sk->sk_receive_queue.lock);
+	}
+
+	atomic_inc(&sk->sk_drops);
+	return err;
+}
+EXPORT_SYMBOL(__sk_queue_drop_skb);
+
 /**
  *	skb_kill_datagram - Free a datagram skbuff forcibly
  *	@sk: socket
@@ -346,23 +367,10 @@ EXPORT_SYMBOL(__skb_free_datagram_locked);
 
 int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags)
 {
-	int err = 0;
-
-	if (flags & MSG_PEEK) {
-		err = -ENOENT;
-		spin_lock_bh(&sk->sk_receive_queue.lock);
-		if (skb == skb_peek(&sk->sk_receive_queue)) {
-			__skb_unlink(skb, &sk->sk_receive_queue);
-			atomic_dec(&skb->users);
-			err = 0;
-		}
-		spin_unlock_bh(&sk->sk_receive_queue.lock);
-	}
+	int err = __sk_queue_drop_skb(sk, skb, flags);
 
 	kfree_skb(skb);
-	atomic_inc(&sk->sk_drops);
 	sk_mem_reclaim_partial(sk);
-
 	return err;
 }
 EXPORT_SYMBOL(skb_kill_datagram);

net/core/sock.c

@@ -2091,24 +2091,18 @@ int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb)
 EXPORT_SYMBOL(sk_wait_data);
 
 /**
- *	__sk_mem_schedule - increase sk_forward_alloc and memory_allocated
+ *	__sk_mem_raise_allocated - increase memory_allocated
  *	@sk: socket
  *	@size: memory size to allocate
+ *	@amt: pages to allocate
  *	@kind: allocation type
  *
- *	If kind is SK_MEM_SEND, it means wmem allocation. Otherwise it means
- *	rmem allocation. This function assumes that protocols which have
- *	memory_pressure use sk_wmem_queued as write buffer accounting.
+ *	Similar to __sk_mem_schedule(), but does not update sk_forward_alloc
  */
-int __sk_mem_schedule(struct sock *sk, int size, int kind)
+int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind)
 {
 	struct proto *prot = sk->sk_prot;
-	int amt = sk_mem_pages(size);
-	long allocated;
-
-	sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
-
-	allocated = sk_memory_allocated_add(sk, amt);
+	long allocated = sk_memory_allocated_add(sk, amt);
 
 	if (mem_cgroup_sockets_enabled && sk->sk_memcg &&
 	    !mem_cgroup_charge_skmem(sk->sk_memcg, amt))
@@ -2169,28 +2163,47 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind)
 
 	trace_sock_exceed_buf_limit(sk, prot, allocated);
 
-	/* Alas. Undo changes. */
-	sk->sk_forward_alloc -= amt * SK_MEM_QUANTUM;
-
 	sk_memory_allocated_sub(sk, amt);
 
 	if (mem_cgroup_sockets_enabled && sk->sk_memcg)
 		mem_cgroup_uncharge_skmem(sk->sk_memcg, amt);
 
 	return 0;
 }
+EXPORT_SYMBOL(__sk_mem_raise_allocated);
+
+/**
+ *	__sk_mem_schedule - increase sk_forward_alloc and memory_allocated
+ *	@sk: socket
+ *	@size: memory size to allocate
+ *	@kind: allocation type
+ *
+ *	If kind is SK_MEM_SEND, it means wmem allocation. Otherwise it means
+ *	rmem allocation. This function assumes that protocols which have
+ *	memory_pressure use sk_wmem_queued as write buffer accounting.
+ */
+int __sk_mem_schedule(struct sock *sk, int size, int kind)
+{
+	int ret, amt = sk_mem_pages(size);
+
+	sk->sk_forward_alloc += amt << SK_MEM_QUANTUM_SHIFT;
+	ret = __sk_mem_raise_allocated(sk, size, amt, kind);
+	if (!ret)
+		sk->sk_forward_alloc -= amt << SK_MEM_QUANTUM_SHIFT;
+	return ret;
+}
 EXPORT_SYMBOL(__sk_mem_schedule);
 
 /**
- *	__sk_mem_reclaim - reclaim memory_allocated
+ *	__sk_mem_reduce_allocated - reclaim memory_allocated
  *	@sk: socket
- *	@amount: number of bytes (rounded down to a SK_MEM_QUANTUM multiple)
+ *	@amount: number of quanta
+ *
+ *	Similar to __sk_mem_reclaim(), but does not update sk_forward_alloc
  */
-void __sk_mem_reclaim(struct sock *sk, int amount)
+void __sk_mem_reduce_allocated(struct sock *sk, int amount)
 {
-	amount >>= SK_MEM_QUANTUM_SHIFT;
 	sk_memory_allocated_sub(sk, amount);
-	sk->sk_forward_alloc -= amount << SK_MEM_QUANTUM_SHIFT;
 
 	if (mem_cgroup_sockets_enabled && sk->sk_memcg)
 		mem_cgroup_uncharge_skmem(sk->sk_memcg, amount);
@@ -2199,6 +2212,19 @@ void __sk_mem_reclaim(struct sock *sk, int amount)
 	    (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)))
 		sk_leave_memory_pressure(sk);
 }
+EXPORT_SYMBOL(__sk_mem_reduce_allocated);
+
+/**
+ *	__sk_mem_reclaim - reclaim sk_forward_alloc and memory_allocated
+ *	@sk: socket
+ *	@amount: number of bytes (rounded down to a SK_MEM_QUANTUM multiple)
+ */
+void __sk_mem_reclaim(struct sock *sk, int amount)
+{
+	amount >>= SK_MEM_QUANTUM_SHIFT;
+	sk->sk_forward_alloc -= amount << SK_MEM_QUANTUM_SHIFT;
+	__sk_mem_reduce_allocated(sk, amount);
+}
 EXPORT_SYMBOL(__sk_mem_reclaim);
 
 int sk_set_peek_off(struct sock *sk, int val)