[NET] CORE: Introducing new memory accounting interface.

This patch introduces new memory accounting functions for each network
protocol. Most of them are renamed from memory accounting functions
for stream protocols. At the same time, some stream memory accounting
functions are removed since other functions do same thing.

Renaming:
	sk_stream_free_skb()		->	sk_wmem_free_skb()
	__sk_stream_mem_reclaim()	->	__sk_mem_reclaim()
	sk_stream_mem_reclaim()		->	sk_mem_reclaim()
	sk_stream_mem_schedule 		->    	__sk_mem_schedule()
	sk_stream_pages()      		->	sk_mem_pages()
	sk_stream_rmem_schedule()	->	sk_rmem_schedule()
	sk_stream_wmem_schedule()	->	sk_wmem_schedule()
	sk_charge_skb()			->	sk_mem_charge()

Removeing
	sk_stream_rfree():	consolidates into sock_rfree()
	sk_stream_set_owner_r(): consolidates into skb_set_owner_r()
	sk_stream_mem_schedule()

The following functions are added.
    	sk_has_account(): check if the protocol supports accounting
	sk_mem_uncharge(): do the opposite of sk_mem_charge()

In addition, to achieve consolidation, updating sk_wmem_queued is
removed from sk_mem_charge().

Next, to consolidate memory accounting functions, this patch adds
memory accounting calls to network core functions. Moreover, present
memory accounting call is renamed to new accounting call.

Finally we replace present memory accounting calls with new interface
in TCP and SCTP.

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>

1 files changed, 104 insertions, 0 deletions

diff --git a/net/core/sock.c b/net/core/sock.c
index 118214047ed..8c184c4a381 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -282,6 +282,11 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
         if (err)
                 goto out;
 
+        if (!sk_rmem_schedule(sk, skb->truesize)) {
+                err = -ENOBUFS;
+                goto out;
+        }
+
         skb->dev = NULL;
         skb_set_owner_r(skb, sk);
 
@@ -1107,7 +1112,9 @@ void sock_rfree(struct sk_buff *skb)
 {
         struct sock *sk = skb->sk;
 
+        skb_truesize_check(skb);
         atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
+        sk_mem_uncharge(skb->sk, skb->truesize);
 }
 
 
@@ -1384,6 +1391,103 @@ int sk_wait_data(struct sock *sk, long *timeo)
 
 EXPORT_SYMBOL(sk_wait_data);
 
+/**
+ *      __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)
+{
+        struct proto *prot = sk->sk_prot;
+        int amt = sk_mem_pages(size);
+        int allocated;
+
+        sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
+        allocated = atomic_add_return(amt, prot->memory_allocated);
+
+        /* Under limit. */
+        if (allocated <= prot->sysctl_mem[0]) {
+                if (prot->memory_pressure && *prot->memory_pressure)
+                        *prot->memory_pressure = 0;
+                return 1;
+        }
+
+        /* Under pressure. */
+        if (allocated > prot->sysctl_mem[1])
+                if (prot->enter_memory_pressure)
+                        prot->enter_memory_pressure();
+
+        /* Over hard limit. */
+        if (allocated > prot->sysctl_mem[2])
+                goto suppress_allocation;
+
+        /* guarantee minimum buffer size under pressure */
+        if (kind == SK_MEM_RECV) {
+                if (atomic_read(&sk->sk_rmem_alloc) < prot->sysctl_rmem[0])
+                        return 1;
+        } else { /* SK_MEM_SEND */
+                if (sk->sk_type == SOCK_STREAM) {
+                        if (sk->sk_wmem_queued < prot->sysctl_wmem[0])
+                                return 1;
+                } else if (atomic_read(&sk->sk_wmem_alloc) <
+                           prot->sysctl_wmem[0])
+                                return 1;
+        }
+
+        if (prot->memory_pressure) {
+                if (!*prot->memory_pressure ||
+                    prot->sysctl_mem[2] > atomic_read(prot->sockets_allocated) *
+                    sk_mem_pages(sk->sk_wmem_queued +
+                                 atomic_read(&sk->sk_rmem_alloc) +
+                                 sk->sk_forward_alloc))
+                        return 1;
+        }
+
+suppress_allocation:
+
+        if (kind == SK_MEM_SEND && sk->sk_type == SOCK_STREAM) {
+                sk_stream_moderate_sndbuf(sk);
+
+                /* Fail only if socket is _under_ its sndbuf.
+                 * In this case we cannot block, so that we have to fail.
+                 */
+                if (sk->sk_wmem_queued + size >= sk->sk_sndbuf)
+                        return 1;
+        }
+
+        /* Alas. Undo changes. */
+        sk->sk_forward_alloc -= amt * SK_MEM_QUANTUM;
+        atomic_sub(amt, prot->memory_allocated);
+        return 0;
+}
+
+EXPORT_SYMBOL(__sk_mem_schedule);
+
+/**
+ *      __sk_reclaim - reclaim memory_allocated
+ *      @sk: socket
+ */
+void __sk_mem_reclaim(struct sock *sk)
+{
+        struct proto *prot = sk->sk_prot;
+
+        atomic_sub(sk->sk_forward_alloc / SK_MEM_QUANTUM,
+                   prot->memory_allocated);
+        sk->sk_forward_alloc &= SK_MEM_QUANTUM - 1;
+
+        if (prot->memory_pressure && *prot->memory_pressure &&
+            (atomic_read(prot->memory_allocated) < prot->sysctl_mem[0]))
+                *prot->memory_pressure = 0;
+}
+
+EXPORT_SYMBOL(__sk_mem_reclaim);
+
+
 /*
  * Set of default routines for initialising struct proto_ops when
  * the protocol does not support a particular function. In certain