1 files changed, 40 insertions, 9 deletions

diff --git a/net/core/sock.c b/net/core/sock.c
index b0ba569bc973..bbb25be7ddfe 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -631,7 +631,7 @@ set_rcvbuf:
 
         case SO_TIMESTAMPING:
                 if (val & ~SOF_TIMESTAMPING_MASK) {
-                        ret = EINVAL;
+                        ret = -EINVAL;
                         break;
                 }
                 sock_valbool_flag(sk, SOCK_TIMESTAMPING_TX_HARDWARE,
@@ -919,13 +919,19 @@ static inline void sock_lock_init(struct sock *sk)
                         af_family_keys + sk->sk_family);
 }
 
+/*
+ * Copy all fields from osk to nsk but nsk->sk_refcnt must not change yet,
+ * even temporarly, because of RCU lookups. sk_node should also be left as is.
+ */
 static void sock_copy(struct sock *nsk, const struct sock *osk)
 {
 #ifdef CONFIG_SECURITY_NETWORK
         void *sptr = nsk->sk_security;
 #endif
-
-        memcpy(nsk, osk, osk->sk_prot->obj_size);
+        BUILD_BUG_ON(offsetof(struct sock, sk_copy_start) !=
+                     sizeof(osk->sk_node) + sizeof(osk->sk_refcnt));
+        memcpy(&nsk->sk_copy_start, &osk->sk_copy_start,
+               osk->sk_prot->obj_size - offsetof(struct sock, sk_copy_start));
 #ifdef CONFIG_SECURITY_NETWORK
         nsk->sk_security = sptr;
         security_sk_clone(osk, nsk);
@@ -939,8 +945,23 @@ static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority,
         struct kmem_cache *slab;
 
         slab = prot->slab;
-        if (slab != NULL)
-                sk = kmem_cache_alloc(slab, priority);
+        if (slab != NULL) {
+                sk = kmem_cache_alloc(slab, priority & ~__GFP_ZERO);
+                if (!sk)
+                        return sk;
+                if (priority & __GFP_ZERO) {
+                        /*
+                         * caches using SLAB_DESTROY_BY_RCU should let
+                         * sk_node.next un-modified. Special care is taken
+                         * when initializing object to zero.
+                         */
+                        if (offsetof(struct sock, sk_node.next) != 0)
+                                memset(sk, 0, offsetof(struct sock, sk_node.next));
+                        memset(&sk->sk_node.pprev, 0,
+                               prot->obj_size - offsetof(struct sock,
+                                                         sk_node.pprev));
+                }
+        }
         else
                 sk = kmalloc(prot->obj_size, priority);
 
@@ -1125,6 +1146,11 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority)
 
                 newsk->sk_err      = 0;
                 newsk->sk_priority = 0;
+                /*
+                 * Before updating sk_refcnt, we must commit prior changes to memory
+                 * (Documentation/RCU/rculist_nulls.txt for details)
+                 */
+                smp_wmb();
                 atomic_set(&newsk->sk_refcnt, 2);
 
                 /*
@@ -1715,7 +1741,7 @@ EXPORT_SYMBOL(sock_no_sendpage);
 static void sock_def_wakeup(struct sock *sk)
 {
         read_lock(&sk->sk_callback_lock);
-        if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+        if (sk_has_sleeper(sk))
                 wake_up_interruptible_all(sk->sk_sleep);
         read_unlock(&sk->sk_callback_lock);
 }
@@ -1723,7 +1749,7 @@ static void sock_def_wakeup(struct sock *sk)
 static void sock_def_error_report(struct sock *sk)
 {
         read_lock(&sk->sk_callback_lock);
-        if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+        if (sk_has_sleeper(sk))
                 wake_up_interruptible_poll(sk->sk_sleep, POLLERR);
         sk_wake_async(sk, SOCK_WAKE_IO, POLL_ERR);
         read_unlock(&sk->sk_callback_lock);
@@ -1732,7 +1758,7 @@ static void sock_def_error_report(struct sock *sk)
 static void sock_def_readable(struct sock *sk, int len)
 {
         read_lock(&sk->sk_callback_lock);
-        if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+        if (sk_has_sleeper(sk))
                 wake_up_interruptible_sync_poll(sk->sk_sleep, POLLIN |
                                                 POLLRDNORM | POLLRDBAND);
         sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
@@ -1747,7 +1773,7 @@ static void sock_def_write_space(struct sock *sk)
          * progress.  --DaveM
          */
         if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) {
-                if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+                if (sk_has_sleeper(sk))
                         wake_up_interruptible_sync_poll(sk->sk_sleep, POLLOUT |
                                                 POLLWRNORM | POLLWRBAND);
 
@@ -1840,6 +1866,11 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 
         sk->sk_stamp = ktime_set(-1L, 0);
 
+        /*
+         * Before updating sk_refcnt, we must commit prior changes to memory
+         * (Documentation/RCU/rculist_nulls.txt for details)
+         */
+        smp_wmb();
         atomic_set(&sk->sk_refcnt, 1);
         atomic_set(&sk->sk_wmem_alloc, 1);
         atomic_set(&sk->sk_drops, 0);