1 files changed, 118 insertions, 151 deletions

diff --git a/include/net/sock.h b/include/net/sock.h
index 67e35c7e230c..8a7889b35810 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -47,6 +47,7 @@
 #include <linux/module.h>
 #include <linux/lockdep.h>
 #include <linux/netdevice.h>
+#include <linux/pcounter.h>
 #include <linux/skbuff.h>       /* struct sk_buff */
 #include <linux/mm.h>
 #include <linux/security.h>
@@ -56,7 +57,6 @@
 #include <asm/atomic.h>
 #include <net/dst.h>
 #include <net/checksum.h>
-#include <net/net_namespace.h>
 
 /*
  * This structure really needs to be cleaned up.
@@ -94,6 +94,7 @@ typedef struct {
 
 struct sock;
 struct proto;
+struct net;
 
 /**
  *      struct sock_common - minimal network layer representation of sockets
@@ -145,7 +146,8 @@ struct sock_common {
   *     @sk_forward_alloc: space allocated forward
   *     @sk_allocation: allocation mode
   *     @sk_sndbuf: size of send buffer in bytes
-  *     @sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE, %SO_OOBINLINE settings
+  *     @sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
+  *                %SO_OOBINLINE settings
   *     @sk_no_check: %SO_NO_CHECK setting, wether or not checkup packets
   *     @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO)
   *     @sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4)
@@ -153,9 +155,12 @@ struct sock_common {
   *     @sk_backlog: always used with the per-socket spinlock held
   *     @sk_callback_lock: used with the callbacks in the end of this struct
   *     @sk_error_queue: rarely used
-  *     @sk_prot_creator: sk_prot of original sock creator (see ipv6_setsockopt, IPV6_ADDRFORM for instance)
+  *     @sk_prot_creator: sk_prot of original sock creator (see ipv6_setsockopt,
+  *                       IPV6_ADDRFORM for instance)
   *     @sk_err: last error
-  *     @sk_err_soft: errors that don't cause failure but are the cause of a persistent failure not just 'timed out'
+  *     @sk_err_soft: errors that don't cause failure but are the cause of a
+  *                   persistent failure not just 'timed out'
+  *     @sk_drops: raw drops counter
   *     @sk_ack_backlog: current listen backlog
   *     @sk_max_ack_backlog: listen backlog set in listen()
   *     @sk_priority: %SO_PRIORITY setting
@@ -239,6 +244,7 @@ struct sock {
         rwlock_t                sk_callback_lock;
         int                     sk_err,
                                 sk_err_soft;
+        atomic_t                sk_drops;
         unsigned short          sk_ack_backlog;
         unsigned short          sk_max_ack_backlog;
         __u32                   sk_priority;
@@ -256,6 +262,8 @@ struct sock {
         __u32                   sk_sndmsg_off;
         int                     sk_write_pending;
         void                    *sk_security;
+        __u32                   sk_mark;
+        /* XXX 4 bytes hole on 64 bit */
         void                    (*sk_state_change)(struct sock *sk);
         void                    (*sk_data_ready)(struct sock *sk, int bytes);
         void                    (*sk_write_space)(struct sock *sk);
@@ -439,7 +447,7 @@ static inline int sk_acceptq_is_full(struct sock *sk)
  */
 static inline int sk_stream_min_wspace(struct sock *sk)
 {
-        return sk->sk_wmem_queued / 2;
+        return sk->sk_wmem_queued >> 1;
 }
 
 static inline int sk_stream_wspace(struct sock *sk)
@@ -454,25 +462,6 @@ static inline int sk_stream_memory_free(struct sock *sk)
         return sk->sk_wmem_queued < sk->sk_sndbuf;
 }
 
-extern void sk_stream_rfree(struct sk_buff *skb);
-
-static inline void sk_stream_set_owner_r(struct sk_buff *skb, struct sock *sk)
-{
-        skb->sk = sk;
-        skb->destructor = sk_stream_rfree;
-        atomic_add(skb->truesize, &sk->sk_rmem_alloc);
-        sk->sk_forward_alloc -= skb->truesize;
-}
-
-static inline void sk_stream_free_skb(struct sock *sk, struct sk_buff *skb)
-{
-        skb_truesize_check(skb);
-        sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
-        sk->sk_wmem_queued   -= skb->truesize;
-        sk->sk_forward_alloc += skb->truesize;
-        __kfree_skb(skb);
-}
-
 /* The per-socket spinlock must be held here. */
 static inline void sk_add_backlog(struct sock *sk, struct sk_buff *skb)
 {
@@ -507,6 +496,7 @@ extern int sk_wait_data(struct sock *sk, long *timeo);
 
 struct request_sock_ops;
 struct timewait_sock_ops;
+struct inet_hashinfo;
 
 /* Networking protocol blocks we attach to sockets.
  * socket layer -> transport layer interface
@@ -560,14 +550,11 @@ struct proto {
         void                    (*unhash)(struct sock *sk);
         int                     (*get_port)(struct sock *sk, unsigned short snum);
 
-#ifdef CONFIG_SMP
         /* Keeping track of sockets in use */
-        void                    (*inuse_add)(struct proto *prot, int inc);
-        int                     (*inuse_getval)(const struct proto *prot);
-        int                     *inuse_ptr;
-#else
-        int                     inuse;
+#ifdef CONFIG_PROC_FS
+        struct pcounter         inuse;
 #endif
+
         /* Memory pressure */
         void                    (*enter_memory_pressure)(void);
         atomic_t                *memory_allocated;      /* Current allocated memory. */
@@ -575,7 +562,7 @@ struct proto {
         /*
          * Pressure flag: try to collapse.
          * Technical note: it is used by multiple contexts non atomically.
-         * All the sk_stream_mem_schedule() is of this nature: accounting
+         * All the __sk_mem_schedule() is of this nature: accounting
          * is strict, actions are advisory and have some latency.
          */
         int                     *memory_pressure;
@@ -592,6 +579,8 @@ struct proto {
         struct request_sock_ops *rsk_prot;
         struct timewait_sock_ops *twsk_prot;
 
+        struct inet_hashinfo    *hashinfo;
+
         struct module           *owner;
 
         char                    name[32];
@@ -602,36 +591,6 @@ struct proto {
 #endif
 };
 
-/*
- * Special macros to let protos use a fast version of inuse{get|add}
- * using a static percpu variable per proto instead of an allocated one,
- * saving one dereference.
- * This might be changed if/when dynamic percpu vars become fast.
- */
-#ifdef CONFIG_SMP
-# define DEFINE_PROTO_INUSE(NAME)                       \
-static DEFINE_PER_CPU(int, NAME##_inuse);               \
-static void NAME##_inuse_add(struct proto *prot, int inc)       \
-{                                                       \
-        __get_cpu_var(NAME##_inuse) += inc;             \
-}                                                       \
-                                                        \
-static int NAME##_inuse_getval(const struct proto *prot)\
-{                                                       \
-        int res = 0, cpu;                               \
-                                                        \
-        for_each_possible_cpu(cpu)                      \
-                res += per_cpu(NAME##_inuse, cpu);      \
-        return res;                                     \
-}
-# define REF_PROTO_INUSE(NAME)                          \
-        .inuse_add = NAME##_inuse_add,                  \
-        .inuse_getval = NAME##_inuse_getval,
-#else
-# define DEFINE_PROTO_INUSE(NAME)
-# define REF_PROTO_INUSE(NAME)
-#endif
-
 extern int proto_register(struct proto *prot, int alloc_slab);
 extern void proto_unregister(struct proto *prot);
 
@@ -660,33 +619,42 @@ static inline void sk_refcnt_debug_release(const struct sock *sk)
 #define sk_refcnt_debug_release(sk) do { } while (0)
 #endif /* SOCK_REFCNT_DEBUG */
 
+
+#ifdef CONFIG_PROC_FS
+# define DEFINE_PROTO_INUSE(NAME) DEFINE_PCOUNTER(NAME)
+# define REF_PROTO_INUSE(NAME) PCOUNTER_MEMBER_INITIALIZER(NAME, .inuse)
 /* Called with local bh disabled */
-static __inline__ void sock_prot_inc_use(struct proto *prot)
+static inline void sock_prot_inuse_add(struct proto *prot, int inc)
 {
-#ifdef CONFIG_SMP
-        prot->inuse_add(prot, 1);
-#else
-        prot->inuse++;
-#endif
+        pcounter_add(&prot->inuse, inc);
 }
-
-static __inline__ void sock_prot_dec_use(struct proto *prot)
+static inline int sock_prot_inuse_init(struct proto *proto)
 {
-#ifdef CONFIG_SMP
-        prot->inuse_add(prot, -1);
-#else
-        prot->inuse--;
-#endif
+        return pcounter_alloc(&proto->inuse);
 }
-
-static __inline__ int sock_prot_inuse(struct proto *proto)
+static inline int sock_prot_inuse_get(struct proto *proto)
+{
+        return pcounter_getval(&proto->inuse);
+}
+static inline void sock_prot_inuse_free(struct proto *proto)
 {
-#ifdef CONFIG_SMP
-        return proto->inuse_getval(proto);
+        pcounter_free(&proto->inuse);
+}
 #else
-        return proto->inuse;
-#endif
+# define DEFINE_PROTO_INUSE(NAME)
+# define REF_PROTO_INUSE(NAME)
+static void inline sock_prot_inuse_add(struct proto *prot, int inc)
+{
+}
+static int inline sock_prot_inuse_init(struct proto *proto)
+{
+        return 0;
 }
+static void inline sock_prot_inuse_free(struct proto *proto)
+{
+}
+#endif
+
 
 /* With per-bucket locks this operation is not-atomic, so that
  * this version is not worse.
@@ -750,32 +718,81 @@ static inline struct inode *SOCK_INODE(struct socket *socket)
         return &container_of(socket, struct socket_alloc, socket)->vfs_inode;
 }
 
-extern void __sk_stream_mem_reclaim(struct sock *sk);
-extern int sk_stream_mem_schedule(struct sock *sk, int size, int kind);
+/*
+ * Functions for memory accounting
+ */
+extern int __sk_mem_schedule(struct sock *sk, int size, int kind);
+extern void __sk_mem_reclaim(struct sock *sk);
 
-#define SK_STREAM_MEM_QUANTUM ((int)PAGE_SIZE)
+#define SK_MEM_QUANTUM ((int)PAGE_SIZE)
+#define SK_MEM_QUANTUM_SHIFT ilog2(SK_MEM_QUANTUM)
+#define SK_MEM_SEND     0
+#define SK_MEM_RECV     1
 
-static inline int sk_stream_pages(int amt)
+static inline int sk_mem_pages(int amt)
 {
-        return DIV_ROUND_UP(amt, SK_STREAM_MEM_QUANTUM);
+        return (amt + SK_MEM_QUANTUM - 1) >> SK_MEM_QUANTUM_SHIFT;
 }
 
-static inline void sk_stream_mem_reclaim(struct sock *sk)
+static inline int sk_has_account(struct sock *sk)
 {
-        if (sk->sk_forward_alloc >= SK_STREAM_MEM_QUANTUM)
-                __sk_stream_mem_reclaim(sk);
+        /* return true if protocol supports memory accounting */
+        return !!sk->sk_prot->memory_allocated;
 }
 
-static inline int sk_stream_rmem_schedule(struct sock *sk, struct sk_buff *skb)
+static inline int sk_wmem_schedule(struct sock *sk, int size)
 {
-        return (int)skb->truesize <= sk->sk_forward_alloc ||
-                sk_stream_mem_schedule(sk, skb->truesize, 1);
+        if (!sk_has_account(sk))
+                return 1;
+        return size <= sk->sk_forward_alloc ||
+                __sk_mem_schedule(sk, size, SK_MEM_SEND);
 }
 
-static inline int sk_stream_wmem_schedule(struct sock *sk, int size)
+static inline int sk_rmem_schedule(struct sock *sk, int size)
 {
+        if (!sk_has_account(sk))
+                return 1;
         return size <= sk->sk_forward_alloc ||
-               sk_stream_mem_schedule(sk, size, 0);
+                __sk_mem_schedule(sk, size, SK_MEM_RECV);
+}
+
+static inline void sk_mem_reclaim(struct sock *sk)
+{
+        if (!sk_has_account(sk))
+                return;
+        if (sk->sk_forward_alloc >= SK_MEM_QUANTUM)
+                __sk_mem_reclaim(sk);
+}
+
+static inline void sk_mem_reclaim_partial(struct sock *sk)
+{
+        if (!sk_has_account(sk))
+                return;
+        if (sk->sk_forward_alloc > SK_MEM_QUANTUM)
+                __sk_mem_reclaim(sk);
+}
+
+static inline void sk_mem_charge(struct sock *sk, int size)
+{
+        if (!sk_has_account(sk))
+                return;
+        sk->sk_forward_alloc -= size;
+}
+
+static inline void sk_mem_uncharge(struct sock *sk, int size)
+{
+        if (!sk_has_account(sk))
+                return;
+        sk->sk_forward_alloc += size;
+}
+
+static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb)
+{
+        skb_truesize_check(skb);
+        sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
+        sk->sk_wmem_queued -= skb->truesize;
+        sk_mem_uncharge(sk, skb->truesize);
+        __kfree_skb(skb);
 }
 
 /* Used by processes to "lock" a socket state, so that
@@ -812,14 +829,14 @@ do {									\
         lockdep_init_map(&(sk)->sk_lock.dep_map, (name), (key), 0);     \
 } while (0)
 
-extern void FASTCALL(lock_sock_nested(struct sock *sk, int subclass));
+extern void lock_sock_nested(struct sock *sk, int subclass);
 
 static inline void lock_sock(struct sock *sk)
 {
         lock_sock_nested(sk, 0);
 }
 
-extern void FASTCALL(release_sock(struct sock *sk));
+extern void release_sock(struct sock *sk);
 
 /* BH context may only use the following locking interface. */
 #define bh_lock_sock(__sk)      spin_lock(&((__sk)->sk_lock.slock))
@@ -944,7 +961,7 @@ static inline int sk_filter(struct sock *sk, struct sk_buff *skb)
                 return err;
         
         rcu_read_lock_bh();
-        filter = sk->sk_filter;
+        filter = rcu_dereference(sk->sk_filter);
         if (filter) {
                 unsigned int pkt_len = sk_run_filter(skb, filter->insns,
                                 filter->len);
@@ -1113,12 +1130,6 @@ static inline int sk_can_gso(const struct sock *sk)
 
 extern void sk_setup_caps(struct sock *sk, struct dst_entry *dst);
 
-static inline void sk_charge_skb(struct sock *sk, struct sk_buff *skb)
-{
-        sk->sk_wmem_queued   += skb->truesize;
-        sk->sk_forward_alloc -= skb->truesize;
-}
-
 static inline int skb_copy_to_page(struct sock *sk, char __user *from,
                                    struct sk_buff *skb, struct page *page,
                                    int off, int copy)
@@ -1138,7 +1149,7 @@ static inline int skb_copy_to_page(struct sock *sk, char __user *from,
         skb->data_len        += copy;
         skb->truesize        += copy;
         sk->sk_wmem_queued   += copy;
-        sk->sk_forward_alloc -= copy;
+        sk_mem_charge(sk, copy);
         return 0;
 }
 
@@ -1164,6 +1175,7 @@ static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
         skb->sk = sk;
         skb->destructor = sock_rfree;
         atomic_add(skb->truesize, &sk->sk_rmem_alloc);
+        sk_mem_charge(sk, skb->truesize);
 }
 
 extern void sk_reset_timer(struct sock *sk, struct timer_list* timer,
@@ -1225,45 +1237,12 @@ static inline void sk_wake_async(struct sock *sk, int how, int band)
 static inline void sk_stream_moderate_sndbuf(struct sock *sk)
 {
         if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK)) {
-                sk->sk_sndbuf = min(sk->sk_sndbuf, sk->sk_wmem_queued / 2);
+                sk->sk_sndbuf = min(sk->sk_sndbuf, sk->sk_wmem_queued >> 1);
                 sk->sk_sndbuf = max(sk->sk_sndbuf, SOCK_MIN_SNDBUF);
         }
 }
 
-static inline struct sk_buff *sk_stream_alloc_pskb(struct sock *sk,
-                                                   int size, int mem,
-                                                   gfp_t gfp)
-{
-        struct sk_buff *skb;
-
-        /* The TCP header must be at least 32-bit aligned.  */
-        size = ALIGN(size, 4);
-
-        skb = alloc_skb_fclone(size + sk->sk_prot->max_header, gfp);
-        if (skb) {
-                skb->truesize += mem;
-                if (sk_stream_wmem_schedule(sk, skb->truesize)) {
-                        /*
-                         * Make sure that we have exactly size bytes
-                         * available to the caller, no more, no less.
-                         */
-                        skb_reserve(skb, skb_tailroom(skb) - size);
-                        return skb;
-                }
-                __kfree_skb(skb);
-        } else {
-                sk->sk_prot->enter_memory_pressure();
-                sk_stream_moderate_sndbuf(sk);
-        }
-        return NULL;
-}
-
-static inline struct sk_buff *sk_stream_alloc_skb(struct sock *sk,
-                                                  int size,
-                                                  gfp_t gfp)
-{
-        return sk_stream_alloc_pskb(sk, size, 0, gfp);
-}
+struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp);
 
 static inline struct page *sk_stream_alloc_page(struct sock *sk)
 {
@@ -1282,7 +1261,7 @@ static inline struct page *sk_stream_alloc_page(struct sock *sk)
  */
 static inline int sock_writeable(const struct sock *sk) 
 {
-        return atomic_read(&sk->sk_wmem_alloc) < (sk->sk_sndbuf / 2);
+        return atomic_read(&sk->sk_wmem_alloc) < (sk->sk_sndbuf >> 1);
 }
 
 static inline gfp_t gfp_any(void)
@@ -1391,23 +1370,11 @@ extern int net_msg_warn;
                                 lock_sock(sk); \
                                 }
 
-static inline void sock_valbool_flag(struct sock *sk, int bit, int valbool)
-{
-        if (valbool)
-                sock_set_flag(sk, bit);
-        else
-                sock_reset_flag(sk, bit);
-}
-
 extern __u32 sysctl_wmem_max;
 extern __u32 sysctl_rmem_max;
 
 extern void sk_init(void);
 
-#ifdef CONFIG_SYSCTL
-extern struct ctl_table core_table[];
-#endif
-
 extern int sysctl_optmem_max;
 
 extern __u32 sysctl_wmem_default;