1 files changed, 88 insertions, 13 deletions

diff --git a/include/net/sock.h b/include/net/sock.h
index 352f06bbd7a9..950409dcec3d 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -54,6 +54,7 @@
 
 #include <linux/filter.h>
 #include <linux/rculist_nulls.h>
+#include <linux/poll.h>
 
 #include <asm/atomic.h>
 #include <net/dst.h>
@@ -103,15 +104,15 @@ 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 UDP/UDP-Lite protocol
+ *      @skc_refcnt: reference count
+ *      @skc_hash: hash value used with various protocol lookup tables
  *      @skc_family: network address family
  *      @skc_state: Connection state
  *      @skc_reuse: %SO_REUSEADDR setting
  *      @skc_bound_dev_if: bound device index if != 0
- *      @skc_node: main hash linkage for various protocol lookup tables
- *      @skc_nulls_node: main hash linkage for UDP/UDP-Lite protocol
  *      @skc_bind_node: bind hash linkage for various protocol lookup tables
- *      @skc_refcnt: reference count
- *      @skc_hash: hash value used with various protocol lookup tables
  *      @skc_prot: protocol handlers inside a network family
  *      @skc_net: reference to the network namespace of this socket
  *
@@ -119,17 +120,21 @@ struct net;
  *      for struct sock and struct inet_timewait_sock.
  */
 struct sock_common {
-        unsigned short          skc_family;
-        volatile unsigned char  skc_state;
-        unsigned char           skc_reuse;
-        int                     skc_bound_dev_if;
+        /*
+         * first fields are not copied in sock_copy()
+         */
         union {
                 struct hlist_node       skc_node;
                 struct hlist_nulls_node skc_nulls_node;
         };
-        struct hlist_node       skc_bind_node;
         atomic_t                skc_refcnt;
+
         unsigned int            skc_hash;
+        unsigned short          skc_family;
+        volatile unsigned char  skc_state;
+        unsigned char           skc_reuse;
+        int                     skc_bound_dev_if;
+        struct hlist_node       skc_bind_node;
         struct proto            *skc_prot;
 #ifdef CONFIG_NET_NS
         struct net              *skc_net;
@@ -207,15 +212,17 @@ struct sock {
          * don't add nothing before this first member (__sk_common) --acme
          */
         struct sock_common      __sk_common;
+#define sk_node                 __sk_common.skc_node
+#define sk_nulls_node           __sk_common.skc_nulls_node
+#define sk_refcnt               __sk_common.skc_refcnt
+
+#define sk_copy_start           __sk_common.skc_hash
+#define sk_hash                 __sk_common.skc_hash
 #define sk_family               __sk_common.skc_family
 #define sk_state                __sk_common.skc_state
 #define sk_reuse                __sk_common.skc_reuse
 #define sk_bound_dev_if         __sk_common.skc_bound_dev_if
-#define sk_node                 __sk_common.skc_node
-#define sk_nulls_node           __sk_common.skc_nulls_node
 #define sk_bind_node            __sk_common.skc_bind_node
-#define sk_refcnt               __sk_common.skc_refcnt
-#define sk_hash                 __sk_common.skc_hash
 #define sk_prot                 __sk_common.skc_prot
 #define sk_net                  __sk_common.skc_net
         kmemcheck_bitfield_begin(flags);
@@ -1241,6 +1248,74 @@ static inline int sk_has_allocations(const struct sock *sk)
         return sk_wmem_alloc_get(sk) || sk_rmem_alloc_get(sk);
 }
 
+/**
+ * sk_has_sleeper - check if there are any waiting processes
+ * @sk: socket
+ *
+ * Returns true if socket has waiting processes
+ *
+ * The purpose of the sk_has_sleeper and sock_poll_wait is to wrap the memory
+ * barrier call. They were added due to the race found within the tcp code.
+ *
+ * Consider following tcp code paths:
+ *
+ * CPU1                  CPU2
+ *
+ * sys_select            receive packet
+ *   ...                 ...
+ *   __add_wait_queue    update tp->rcv_nxt
+ *   ...                 ...
+ *   tp->rcv_nxt check   sock_def_readable
+ *   ...                 {
+ *   schedule               ...
+ *                          if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+ *                              wake_up_interruptible(sk->sk_sleep)
+ *                          ...
+ *                       }
+ *
+ * The race for tcp fires when the __add_wait_queue changes done by CPU1 stay
+ * in its cache, and so does the tp->rcv_nxt update on CPU2 side.  The CPU1
+ * could then endup calling schedule and sleep forever if there are no more
+ * data on the socket.
+ *
+ * The sk_has_sleeper is always called right after a call to read_lock, so we
+ * can use smp_mb__after_lock barrier.
+ */
+static inline int sk_has_sleeper(struct sock *sk)
+{
+        /*
+         * We need to be sure we are in sync with the
+         * add_wait_queue modifications to the wait queue.
+         *
+         * This memory barrier is paired in the sock_poll_wait.
+         */
+        smp_mb__after_lock();
+        return sk->sk_sleep && waitqueue_active(sk->sk_sleep);
+}
+
+/**
+ * sock_poll_wait - place memory barrier behind the poll_wait call.
+ * @filp:           file
+ * @wait_address:   socket wait queue
+ * @p:              poll_table
+ *
+ * See the comments in the sk_has_sleeper function.
+ */
+static inline void sock_poll_wait(struct file *filp,
+                wait_queue_head_t *wait_address, poll_table *p)
+{
+        if (p && wait_address) {
+                poll_wait(filp, wait_address, p);
+                /*
+                 * We need to be sure we are in sync with the
+                 * socket flags modification.
+                 *
+                 * This memory barrier is paired in the sk_has_sleeper.
+                */
+                smp_mb();
+        }
+}
+
 /*
  *      Queue a received datagram if it will fit. Stream and sequenced
  *      protocols can't normally use this as they need to fit buffers in