1 files changed, 66 insertions, 35 deletions

diff --git a/net/core/sock.c b/net/core/sock.c
index ef30e9d286e7..6e819780c232 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -157,7 +157,7 @@ static const char *const af_family_key_strings[AF_MAX+1] = {
   "sk_lock-27"       , "sk_lock-28"          , "sk_lock-AF_CAN"      ,
   "sk_lock-AF_TIPC"  , "sk_lock-AF_BLUETOOTH", "sk_lock-IUCV"        ,
   "sk_lock-AF_RXRPC" , "sk_lock-AF_ISDN"     , "sk_lock-AF_PHONET"   ,
-  "sk_lock-AF_IEEE802154", "sk_lock-AF_CAIF" ,
+  "sk_lock-AF_IEEE802154", "sk_lock-AF_CAIF" , "sk_lock-AF_ALG"      ,
   "sk_lock-AF_MAX"
 };
 static const char *const af_family_slock_key_strings[AF_MAX+1] = {
@@ -173,7 +173,7 @@ static const char *const af_family_slock_key_strings[AF_MAX+1] = {
   "slock-27"       , "slock-28"          , "slock-AF_CAN"      ,
   "slock-AF_TIPC"  , "slock-AF_BLUETOOTH", "slock-AF_IUCV"     ,
   "slock-AF_RXRPC" , "slock-AF_ISDN"     , "slock-AF_PHONET"   ,
-  "slock-AF_IEEE802154", "slock-AF_CAIF" ,
+  "slock-AF_IEEE802154", "slock-AF_CAIF" , "slock-AF_ALG"      ,
   "slock-AF_MAX"
 };
 static const char *const af_family_clock_key_strings[AF_MAX+1] = {
@@ -189,7 +189,7 @@ static const char *const af_family_clock_key_strings[AF_MAX+1] = {
   "clock-27"       , "clock-28"          , "clock-AF_CAN"      ,
   "clock-AF_TIPC"  , "clock-AF_BLUETOOTH", "clock-AF_IUCV"     ,
   "clock-AF_RXRPC" , "clock-AF_ISDN"     , "clock-AF_PHONET"   ,
-  "clock-AF_IEEE802154", "clock-AF_CAIF" ,
+  "clock-AF_IEEE802154", "clock-AF_CAIF" , "clock-AF_ALG"      ,
   "clock-AF_MAX"
 };
 
@@ -215,7 +215,7 @@ __u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX;
 __u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX;
 __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;
 
-/* Maximal space eaten by iovec or ancilliary data plus some space */
+/* Maximal space eaten by iovec or ancillary data plus some space */
 int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512);
 EXPORT_SYMBOL(sysctl_optmem_max);
 
@@ -992,23 +992,54 @@ static inline void sock_lock_init(struct sock *sk)
 /*
  * 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.
+ * We must not copy fields between sk_dontcopy_begin and sk_dontcopy_end
  */
 static void sock_copy(struct sock *nsk, const struct sock *osk)
 {
 #ifdef CONFIG_SECURITY_NETWORK
         void *sptr = nsk->sk_security;
 #endif
-        BUILD_BUG_ON(offsetof(struct sock, sk_copy_start) !=
-                     sizeof(osk->sk_node) + sizeof(osk->sk_refcnt) +
-                     sizeof(osk->sk_tx_queue_mapping));
-        memcpy(&nsk->sk_copy_start, &osk->sk_copy_start,
-               osk->sk_prot->obj_size - offsetof(struct sock, sk_copy_start));
+        memcpy(nsk, osk, offsetof(struct sock, sk_dontcopy_begin));
+
+        memcpy(&nsk->sk_dontcopy_end, &osk->sk_dontcopy_end,
+               osk->sk_prot->obj_size - offsetof(struct sock, sk_dontcopy_end));
+
 #ifdef CONFIG_SECURITY_NETWORK
         nsk->sk_security = sptr;
         security_sk_clone(osk, nsk);
 #endif
 }
 
+/*
+ * caches using SLAB_DESTROY_BY_RCU should let .next pointer from nulls nodes
+ * un-modified. Special care is taken when initializing object to zero.
+ */
+static inline void sk_prot_clear_nulls(struct sock *sk, int size)
+{
+        if (offsetof(struct sock, sk_node.next) != 0)
+                memset(sk, 0, offsetof(struct sock, sk_node.next));
+        memset(&sk->sk_node.pprev, 0,
+               size - offsetof(struct sock, sk_node.pprev));
+}
+
+void sk_prot_clear_portaddr_nulls(struct sock *sk, int size)
+{
+        unsigned long nulls1, nulls2;
+
+        nulls1 = offsetof(struct sock, __sk_common.skc_node.next);
+        nulls2 = offsetof(struct sock, __sk_common.skc_portaddr_node.next);
+        if (nulls1 > nulls2)
+                swap(nulls1, nulls2);
+
+        if (nulls1 != 0)
+                memset((char *)sk, 0, nulls1);
+        memset((char *)sk + nulls1 + sizeof(void *), 0,
+               nulls2 - nulls1 - sizeof(void *));
+        memset((char *)sk + nulls2 + sizeof(void *), 0,
+               size - nulls2 - sizeof(void *));
+}
+EXPORT_SYMBOL(sk_prot_clear_portaddr_nulls);
+
 static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority,
                 int family)
 {
@@ -1021,19 +1052,12 @@ static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority,
                 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));
+                        if (prot->clear_sk)
+                                prot->clear_sk(sk, prot->obj_size);
+                        else
+                                sk_prot_clear_nulls(sk, prot->obj_size);
                 }
-        }
-        else
+        } else
                 sk = kmalloc(prot->obj_size, priority);
 
         if (sk != NULL) {
@@ -1078,8 +1102,11 @@ static void sk_prot_free(struct proto *prot, struct sock *sk)
 #ifdef CONFIG_CGROUPS
 void sock_update_classid(struct sock *sk)
 {
-        u32 classid = task_cls_classid(current);
+        u32 classid;
 
+        rcu_read_lock();  /* doing current task, which cannot vanish. */
+        classid = task_cls_classid(current);
+        rcu_read_unlock();
         if (classid && classid != sk->sk_classid)
                 sk->sk_classid = classid;
 }
@@ -1148,7 +1175,7 @@ static void __sk_free(struct sock *sk)
 void sk_free(struct sock *sk)
 {
         /*
-         * We substract one from sk_wmem_alloc and can know if
+         * We subtract one from sk_wmem_alloc and can know if
          * some packets are still in some tx queue.
          * If not null, sock_wfree() will call __sk_free(sk) later
          */
@@ -1158,10 +1185,10 @@ void sk_free(struct sock *sk)
 EXPORT_SYMBOL(sk_free);
 
 /*
- * Last sock_put should drop referrence to sk->sk_net. It has already
- * been dropped in sk_change_net. Taking referrence to stopping namespace
+ * Last sock_put should drop reference to sk->sk_net. It has already
+ * been dropped in sk_change_net. Taking reference to stopping namespace
  * is not an option.
- * Take referrence to a socket to remove it from hash _alive_ and after that
+ * Take reference to a socket to remove it from hash _alive_ and after that
  * destroy it in the context of init_net.
  */
 void sk_release_kernel(struct sock *sk)
@@ -1222,7 +1249,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority)
                 sock_reset_flag(newsk, SOCK_DONE);
                 skb_queue_head_init(&newsk->sk_error_queue);
 
-                filter = newsk->sk_filter;
+                filter = rcu_dereference_protected(newsk->sk_filter, 1);
                 if (filter != NULL)
                         sk_filter_charge(newsk, filter);
 
@@ -1557,6 +1584,8 @@ struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size,
 EXPORT_SYMBOL(sock_alloc_send_skb);
 
 static void __lock_sock(struct sock *sk)
+        __releases(&sk->sk_lock.slock)
+        __acquires(&sk->sk_lock.slock)
 {
         DEFINE_WAIT(wait);
 
@@ -1573,6 +1602,8 @@ static void __lock_sock(struct sock *sk)
 }
 
 static void __release_sock(struct sock *sk)
+        __releases(&sk->sk_lock.slock)
+        __acquires(&sk->sk_lock.slock)
 {
         struct sk_buff *skb = sk->sk_backlog.head;
 
@@ -1646,10 +1677,10 @@ 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;
+        long allocated;
 
         sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
-        allocated = atomic_add_return(amt, prot->memory_allocated);
+        allocated = atomic_long_add_return(amt, prot->memory_allocated);
 
         /* Under limit. */
         if (allocated <= prot->sysctl_mem[0]) {
@@ -1707,7 +1738,7 @@ suppress_allocation:
 
         /* Alas. Undo changes. */
         sk->sk_forward_alloc -= amt * SK_MEM_QUANTUM;
-        atomic_sub(amt, prot->memory_allocated);
+        atomic_long_sub(amt, prot->memory_allocated);
         return 0;
 }
 EXPORT_SYMBOL(__sk_mem_schedule);
@@ -1720,12 +1751,12 @@ void __sk_mem_reclaim(struct sock *sk)
 {
         struct proto *prot = sk->sk_prot;
 
-        atomic_sub(sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT,
+        atomic_long_sub(sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT,
                    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]))
+            (atomic_long_read(prot->memory_allocated) < prot->sysctl_mem[0]))
                 *prot->memory_pressure = 0;
 }
 EXPORT_SYMBOL(__sk_mem_reclaim);
@@ -1877,7 +1908,7 @@ static void sock_def_readable(struct sock *sk, int len)
         rcu_read_lock();
         wq = rcu_dereference(sk->sk_wq);
         if (wq_has_sleeper(wq))
-                wake_up_interruptible_sync_poll(&wq->wait, POLLIN |
+                wake_up_interruptible_sync_poll(&wq->wait, POLLIN | POLLPRI |
                                                 POLLRDNORM | POLLRDBAND);
         sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
         rcu_read_unlock();
@@ -2445,12 +2476,12 @@ static char proto_method_implemented(const void *method)
 
 static void proto_seq_printf(struct seq_file *seq, struct proto *proto)
 {
-        seq_printf(seq, "%-9s %4u %6d  %6d   %-3s %6u   %-3s  %-10s "
+        seq_printf(seq, "%-9s %4u %6d  %6ld   %-3s %6u   %-3s  %-10s "
                         "%2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c\n",
                    proto->name,
                    proto->obj_size,
                    sock_prot_inuse_get(seq_file_net(seq), proto),
-                   proto->memory_allocated != NULL ? atomic_read(proto->memory_allocated) : -1,
+                   proto->memory_allocated != NULL ? atomic_long_read(proto->memory_allocated) : -1L,
                    proto->memory_pressure != NULL ? *proto->memory_pressure ? "yes" : "no" : "NI",
                    proto->max_header,
                    proto->slab == NULL ? "no" : "yes",