net: sk_prot_alloc() should not blindly overwrite memory

Some sockets use SLAB_DESTROY_BY_RCU, and our RCU code correctness
depends on sk->sk_nulls_node.next being always valid. A NULL
value is not allowed as it might fault a lockless reader.

Current sk_prot_alloc() implementation doesnt respect this hypothesis,
calling kmem_cache_alloc() with __GFP_ZERO. Just call memset() around
the forbidden field.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 17 insertions, 2 deletions

diff --git a/net/core/sock.c b/net/core/sock.c
index 6354863b1c68..ba5d2116aea1 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -939,8 +939,23 @@ 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);