1 files changed, 136 insertions, 56 deletions

diff --git a/include/net/sock.h b/include/net/sock.h
index adab9dc58183..c0b938cb4b1a 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -52,12 +52,13 @@
 #include <linux/mm.h>
 #include <linux/security.h>
 #include <linux/slab.h>
+#include <linux/uaccess.h>
 
 #include <linux/filter.h>
 #include <linux/rculist_nulls.h>
 #include <linux/poll.h>
 
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 #include <net/dst.h>
 #include <net/checksum.h>
 
@@ -105,10 +106,8 @@ struct net;
 
 /**
  *      struct sock_common - minimal network layer representation of sockets
- *      @skc_node: main hash linkage for various protocol lookup tables
- *      @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol
- *      @skc_refcnt: reference count
- *      @skc_tx_queue_mapping: tx queue number for this connection
+ *      @skc_daddr: Foreign IPv4 addr
+ *      @skc_rcv_saddr: Bound local IPv4 addr
  *      @skc_hash: hash value used with various protocol lookup tables
  *      @skc_u16hashes: two u16 hash values used by UDP lookup tables
  *      @skc_family: network address family
@@ -119,20 +118,20 @@ struct net;
  *      @skc_portaddr_node: second hash linkage for UDP/UDP-Lite protocol
  *      @skc_prot: protocol handlers inside a network family
  *      @skc_net: reference to the network namespace of this socket
+ *      @skc_node: main hash linkage for various protocol lookup tables
+ *      @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol
+ *      @skc_tx_queue_mapping: tx queue number for this connection
+ *      @skc_refcnt: reference count
  *
  *      This is the minimal network layer representation of sockets, the header
  *      for struct sock and struct inet_timewait_sock.
  */
 struct sock_common {
-        /*
-         * first fields are not copied in sock_copy()
+        /* skc_daddr and skc_rcv_saddr must be grouped :
+         * cf INET_MATCH() and INET_TW_MATCH()
          */
-        union {
-                struct hlist_node       skc_node;
-                struct hlist_nulls_node skc_nulls_node;
-        };
-        atomic_t                skc_refcnt;
-        int                     skc_tx_queue_mapping;
+        __be32                  skc_daddr;
+        __be32                  skc_rcv_saddr;
 
         union  {
                 unsigned int    skc_hash;
@@ -150,6 +149,22 @@ struct sock_common {
 #ifdef CONFIG_NET_NS
         struct net              *skc_net;
 #endif
+        /*
+         * fields between dontcopy_begin/dontcopy_end
+         * are not copied in sock_copy()
+         */
+        /* private: */
+        int                     skc_dontcopy_begin[0];
+        /* public: */
+        union {
+                struct hlist_node       skc_node;
+                struct hlist_nulls_node skc_nulls_node;
+        };
+        int                     skc_tx_queue_mapping;
+        atomic_t                skc_refcnt;
+        /* private: */
+        int                     skc_dontcopy_end[0];
+        /* public: */
 };
 
 /**
@@ -163,7 +178,6 @@ struct sock_common {
   *     @sk_dst_cache: destination cache
   *     @sk_dst_lock: destination cache lock
   *     @sk_policy: flow policy
-  *     @sk_rmem_alloc: receive queue bytes committed
   *     @sk_receive_queue: incoming packets
   *     @sk_wmem_alloc: transmit queue bytes committed
   *     @sk_write_queue: Packet sending queue
@@ -232,7 +246,8 @@ struct sock {
 #define sk_refcnt               __sk_common.skc_refcnt
 #define sk_tx_queue_mapping     __sk_common.skc_tx_queue_mapping
 
-#define sk_copy_start           __sk_common.skc_hash
+#define sk_dontcopy_begin       __sk_common.skc_dontcopy_begin
+#define sk_dontcopy_end         __sk_common.skc_dontcopy_end
 #define sk_hash                 __sk_common.skc_hash
 #define sk_family               __sk_common.skc_family
 #define sk_state                __sk_common.skc_state
@@ -241,59 +256,67 @@ struct sock {
 #define sk_bind_node            __sk_common.skc_bind_node
 #define sk_prot                 __sk_common.skc_prot
 #define sk_net                  __sk_common.skc_net
-        kmemcheck_bitfield_begin(flags);
-        unsigned int            sk_shutdown  : 2,
-                                sk_no_check  : 2,
-                                sk_userlocks : 4,
-                                sk_protocol  : 8,
-                                sk_type      : 16;
-        kmemcheck_bitfield_end(flags);
-        int                     sk_rcvbuf;
         socket_lock_t           sk_lock;
+        struct sk_buff_head     sk_receive_queue;
         /*
          * The backlog queue is special, it is always used with
          * the per-socket spinlock held and requires low latency
          * access. Therefore we special case it's implementation.
+         * Note : rmem_alloc is in this structure to fill a hole
+         * on 64bit arches, not because its logically part of
+         * backlog.
          */
         struct {
-                struct sk_buff *head;
-                struct sk_buff *tail;
-                int len;
+                atomic_t        rmem_alloc;
+                int             len;
+                struct sk_buff  *head;
+                struct sk_buff  *tail;
         } sk_backlog;
-        struct socket_wq        *sk_wq;
-        struct dst_entry        *sk_dst_cache;
+#define sk_rmem_alloc sk_backlog.rmem_alloc
+        int                     sk_forward_alloc;
+#ifdef CONFIG_RPS
+        __u32                   sk_rxhash;
+#endif
+        atomic_t                sk_drops;
+        int                     sk_rcvbuf;
+
+        struct sk_filter __rcu  *sk_filter;
+        struct socket_wq __rcu  *sk_wq;
+
+#ifdef CONFIG_NET_DMA
+        struct sk_buff_head     sk_async_wait_queue;
+#endif
+
 #ifdef CONFIG_XFRM
         struct xfrm_policy      *sk_policy[2];
 #endif
+        unsigned long           sk_flags;
+        struct dst_entry        *sk_dst_cache;
         spinlock_t              sk_dst_lock;
-        atomic_t                sk_rmem_alloc;
         atomic_t                sk_wmem_alloc;
         atomic_t                sk_omem_alloc;
         int                     sk_sndbuf;
-        struct sk_buff_head     sk_receive_queue;
         struct sk_buff_head     sk_write_queue;
-#ifdef CONFIG_NET_DMA
-        struct sk_buff_head     sk_async_wait_queue;
-#endif
+        kmemcheck_bitfield_begin(flags);
+        unsigned int            sk_shutdown  : 2,
+                                sk_no_check  : 2,
+                                sk_userlocks : 4,
+                                sk_protocol  : 8,
+                                sk_type      : 16;
+        kmemcheck_bitfield_end(flags);
         int                     sk_wmem_queued;
-        int                     sk_forward_alloc;
         gfp_t                   sk_allocation;
         int                     sk_route_caps;
         int                     sk_route_nocaps;
         int                     sk_gso_type;
         unsigned int            sk_gso_max_size;
         int                     sk_rcvlowat;
-#ifdef CONFIG_RPS
-        __u32                   sk_rxhash;
-#endif
-        unsigned long           sk_flags;
         unsigned long           sk_lingertime;
         struct sk_buff_head     sk_error_queue;
         struct proto            *sk_prot_creator;
         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;
@@ -301,7 +324,6 @@ struct sock {
         const struct cred       *sk_peer_cred;
         long                    sk_rcvtimeo;
         long                    sk_sndtimeo;
-        struct sk_filter        *sk_filter;
         void                    *sk_protinfo;
         struct timer_list       sk_timer;
         ktime_t                 sk_stamp;
@@ -509,9 +531,6 @@ static __inline__ void sk_add_bind_node(struct sock *sk,
 #define sk_nulls_for_each_from(__sk, node) \
         if (__sk && ({ node = &(__sk)->sk_nulls_node; 1; })) \
                 hlist_nulls_for_each_entry_from(__sk, node, sk_nulls_node)
-#define sk_for_each_continue(__sk, node) \
-        if (__sk && ({ node = &(__sk)->sk_node; 1; })) \
-                hlist_for_each_entry_continue(__sk, node, sk_node)
 #define sk_for_each_safe(__sk, node, tmp, list) \
         hlist_for_each_entry_safe(__sk, node, tmp, list, sk_node)
 #define sk_for_each_bound(__sk, node, list) \
@@ -734,6 +753,8 @@ struct proto {
                                         int level,
                                         int optname, char __user *optval,
                                         int __user *option);
+        int                     (*compat_ioctl)(struct sock *sk,
+                                        unsigned int cmd, unsigned long arg);
 #endif
         int                     (*sendmsg)(struct kiocb *iocb, struct sock *sk,
                                            struct msghdr *msg, size_t len);
@@ -754,6 +775,7 @@ struct proto {
         void                    (*unhash)(struct sock *sk);
         void                    (*rehash)(struct sock *sk);
         int                     (*get_port)(struct sock *sk, unsigned short snum);
+        void                    (*clear_sk)(struct sock *sk, int size);
 
         /* Keeping track of sockets in use */
 #ifdef CONFIG_PROC_FS
@@ -762,7 +784,7 @@ struct proto {
 
         /* Memory pressure */
         void                    (*enter_memory_pressure)(struct sock *sk);
-        atomic_t                *memory_allocated;      /* Current allocated memory. */
+        atomic_long_t           *memory_allocated;      /* Current allocated memory. */
         struct percpu_counter   *sockets_allocated;     /* Current number of sockets. */
         /*
          * Pressure flag: try to collapse.
@@ -771,7 +793,7 @@ struct proto {
          * is strict, actions are advisory and have some latency.
          */
         int                     *memory_pressure;
-        int                     *sysctl_mem;
+        long                    *sysctl_mem;
         int                     *sysctl_wmem;
         int                     *sysctl_rmem;
         int                     max_header;
@@ -852,6 +874,8 @@ static inline void __sk_prot_rehash(struct sock *sk)
         sk->sk_prot->hash(sk);
 }
 
+void sk_prot_clear_portaddr_nulls(struct sock *sk, int size);
+
 /* About 10 seconds */
 #define SOCK_DESTROY_TIME (10*HZ)
 
@@ -1155,6 +1179,8 @@ extern void sk_common_release(struct sock *sk);
 /* Initialise core socket variables */
 extern void sock_init_data(struct socket *sock, struct sock *sk);
 
+extern void sk_filter_release_rcu(struct rcu_head *rcu);
+
 /**
  *      sk_filter_release - release a socket filter
  *      @fp: filter to remove
@@ -1165,7 +1191,7 @@ extern void sock_init_data(struct socket *sock, struct sock *sk);
 static inline void sk_filter_release(struct sk_filter *fp)
 {
         if (atomic_dec_and_test(&fp->refcnt))
-                kfree(fp);
+                call_rcu(&fp->rcu, sk_filter_release_rcu);
 }
 
 static inline void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
@@ -1240,7 +1266,8 @@ static inline void sk_set_socket(struct sock *sk, struct socket *sock)
 
 static inline wait_queue_head_t *sk_sleep(struct sock *sk)
 {
-        return &sk->sk_wq->wait;
+        BUILD_BUG_ON(offsetof(struct socket_wq, wait) != 0);
+        return &rcu_dereference_raw(sk->sk_wq)->wait;
 }
 /* Detach socket from process context.
  * Announce socket dead, detach it from wait queue and inode.
@@ -1261,7 +1288,7 @@ static inline void sock_orphan(struct sock *sk)
 static inline void sock_graft(struct sock *sk, struct socket *parent)
 {
         write_lock_bh(&sk->sk_callback_lock);
-        rcu_assign_pointer(sk->sk_wq, parent->wq);
+        sk->sk_wq = parent->wq;
         parent->sk = sk;
         sk_set_socket(sk, parent);
         security_sock_graft(sk, parent);
@@ -1362,6 +1389,59 @@ static inline void sk_nocaps_add(struct sock *sk, int flags)
         sk->sk_route_caps &= ~flags;
 }
 
+static inline int skb_do_copy_data_nocache(struct sock *sk, struct sk_buff *skb,
+                                           char __user *from, char *to,
+                                           int copy, int offset)
+{
+        if (skb->ip_summed == CHECKSUM_NONE) {
+                int err = 0;
+                __wsum csum = csum_and_copy_from_user(from, to, copy, 0, &err);
+                if (err)
+                        return err;
+                skb->csum = csum_block_add(skb->csum, csum, offset);
+        } else if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) {
+                if (!access_ok(VERIFY_READ, from, copy) ||
+                    __copy_from_user_nocache(to, from, copy))
+                        return -EFAULT;
+        } else if (copy_from_user(to, from, copy))
+                return -EFAULT;
+
+        return 0;
+}
+
+static inline int skb_add_data_nocache(struct sock *sk, struct sk_buff *skb,
+                                       char __user *from, int copy)
+{
+        int err, offset = skb->len;
+
+        err = skb_do_copy_data_nocache(sk, skb, from, skb_put(skb, copy),
+                                       copy, offset);
+        if (err)
+                __skb_trim(skb, offset);
+
+        return err;
+}
+
+static inline int skb_copy_to_page_nocache(struct sock *sk, char __user *from,
+                                           struct sk_buff *skb,
+                                           struct page *page,
+                                           int off, int copy)
+{
+        int err;
+
+        err = skb_do_copy_data_nocache(sk, skb, from, page_address(page) + off,
+                                       copy, skb->len);
+        if (err)
+                return err;
+
+        skb->len             += copy;
+        skb->data_len        += copy;
+        skb->truesize        += copy;
+        sk->sk_wmem_queued   += copy;
+        sk_mem_charge(sk, copy);
+        return 0;
+}
+
 static inline int skb_copy_to_page(struct sock *sk, char __user *from,
                                    struct sk_buff *skb, struct page *page,
                                    int off, int copy)
@@ -1558,7 +1638,11 @@ static inline void sk_wake_async(struct sock *sk, int how, int band)
 }
 
 #define SOCK_MIN_SNDBUF 2048
-#define SOCK_MIN_RCVBUF 256
+/*
+ * Since sk_rmem_alloc sums skb->truesize, even a small frame might need
+ * sizeof(sk_buff) + MTU + padding, unless net driver perform copybreak
+ */
+#define SOCK_MIN_RCVBUF (2048 + sizeof(struct sk_buff))
 
 static inline void sk_stream_moderate_sndbuf(struct sock *sk)
 {
@@ -1670,17 +1754,13 @@ static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
 
 /**
  * sock_tx_timestamp - checks whether the outgoing packet is to be time stamped
- * @msg:        outgoing packet
  * @sk:         socket sending this packet
- * @shtx:       filled with instructions for time stamping
+ * @tx_flags:   filled with instructions for time stamping
  *
  * Currently only depends on SOCK_TIMESTAMPING* flags. Returns error code if
  * parameters are invalid.
  */
-extern int sock_tx_timestamp(struct msghdr *msg,
-                             struct sock *sk,
-                             union skb_shared_tx *shtx);
-
+extern int sock_tx_timestamp(struct sock *sk, __u8 *tx_flags);
 
 /**
  * sk_eat_skb - Release a skb if it is no longer needed
@@ -1722,7 +1802,7 @@ void sock_net_set(struct sock *sk, struct net *net)
 
 /*
  * Kernel sockets, f.e. rtnl or icmp_socket, are a part of a namespace.
- * They should not hold a referrence to a namespace in order to allow
+ * They should not hold a reference to a namespace in order to allow
  * to stop it.
  * Sockets after sk_change_net should be released using sk_release_kernel
  */