From 9d538fa60bad4f7b23193c89e843797a1cf71ef3 Mon Sep 17 00:00:00 2001 From: Christoph Paasch Date: Tue, 26 Sep 2017 17:38:50 -0700 Subject: net: Set sk_prot_creator when cloning sockets to the right proto sk->sk_prot and sk->sk_prot_creator can differ when the app uses IPV6_ADDRFORM (transforming an IPv6-socket to an IPv4-one). Which is why sk_prot_creator is there to make sure that sk_prot_free() does the kmem_cache_free() on the right kmem_cache slab. Now, if such a socket gets transformed back to a listening socket (using connect() with AF_UNSPEC) we will allocate an IPv4 tcp_sock through sk_clone_lock() when a new connection comes in. But sk_prot_creator will still point to the IPv6 kmem_cache (as everything got copied in sk_clone_lock()). When freeing, we will thus put this memory back into the IPv6 kmem_cache although it was allocated in the IPv4 cache. I have seen memory corruption happening because of this. With slub-debugging and MEMCG_KMEM enabled this gives the warning "cache_from_obj: Wrong slab cache. TCPv6 but object is from TCP" A C-program to trigger this: void main(void) { int fd = socket(AF_INET6, SOCK_STREAM, IPPROTO_TCP); int new_fd, newest_fd, client_fd; struct sockaddr_in6 bind_addr; struct sockaddr_in bind_addr4, client_addr1, client_addr2; struct sockaddr unsp; int val; memset(&bind_addr, 0, sizeof(bind_addr)); bind_addr.sin6_family = AF_INET6; bind_addr.sin6_port = ntohs(42424); memset(&client_addr1, 0, sizeof(client_addr1)); client_addr1.sin_family = AF_INET; client_addr1.sin_port = ntohs(42424); client_addr1.sin_addr.s_addr = inet_addr("127.0.0.1"); memset(&client_addr2, 0, sizeof(client_addr2)); client_addr2.sin_family = AF_INET; client_addr2.sin_port = ntohs(42421); client_addr2.sin_addr.s_addr = inet_addr("127.0.0.1"); memset(&unsp, 0, sizeof(unsp)); unsp.sa_family = AF_UNSPEC; bind(fd, (struct sockaddr *)&bind_addr, sizeof(bind_addr)); listen(fd, 5); client_fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP); connect(client_fd, (struct sockaddr *)&client_addr1, sizeof(client_addr1)); new_fd = accept(fd, NULL, NULL); close(fd); val = AF_INET; setsockopt(new_fd, SOL_IPV6, IPV6_ADDRFORM, &val, sizeof(val)); connect(new_fd, &unsp, sizeof(unsp)); memset(&bind_addr4, 0, sizeof(bind_addr4)); bind_addr4.sin_family = AF_INET; bind_addr4.sin_port = ntohs(42421); bind(new_fd, (struct sockaddr *)&bind_addr4, sizeof(bind_addr4)); listen(new_fd, 5); client_fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP); connect(client_fd, (struct sockaddr *)&client_addr2, sizeof(client_addr2)); newest_fd = accept(new_fd, NULL, NULL); close(new_fd); close(client_fd); close(new_fd); } As far as I can see, this bug has been there since the beginning of the git-days. Signed-off-by: Christoph Paasch Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/sock.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/core/sock.c') diff --git a/net/core/sock.c b/net/core/sock.c index 9b7b6bbb2a23..7d55c05f449d 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1654,6 +1654,8 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) sock_copy(newsk, sk); + newsk->sk_prot_creator = sk->sk_prot; + /* SANITY */ if (likely(newsk->sk_net_refcnt)) get_net(sock_net(newsk)); -- cgit v1.2.3 From eefca20eb20c66b06cf5ed09b49b1a7caaa27b7b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 2 Oct 2017 12:20:51 -0700 Subject: socket, bpf: fix possible use after free Starting from linux-4.4, 3WHS no longer takes the listener lock. Since this time, we might hit a use-after-free in sk_filter_charge(), if the filter we got in the memcpy() of the listener content just happened to be replaced by a thread changing listener BPF filter. To fix this, we need to make sure the filter refcount is not already zero before incrementing it again. Fixes: e994b2f0fb92 ("tcp: do not lock listener to process SYN packets") Signed-off-by: Eric Dumazet Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- net/core/filter.c | 12 ++++++++---- net/core/sock.c | 5 ++++- 2 files changed, 12 insertions(+), 5 deletions(-) (limited to 'net/core/sock.c') diff --git a/net/core/filter.c b/net/core/filter.c index 82edad58d066..74b8c91fb5f4 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -989,10 +989,14 @@ static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp) bool sk_filter_charge(struct sock *sk, struct sk_filter *fp) { - bool ret = __sk_filter_charge(sk, fp); - if (ret) - refcount_inc(&fp->refcnt); - return ret; + if (!refcount_inc_not_zero(&fp->refcnt)) + return false; + + if (!__sk_filter_charge(sk, fp)) { + sk_filter_release(fp); + return false; + } + return true; } static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp) diff --git a/net/core/sock.c b/net/core/sock.c index 7d55c05f449d..23953b741a41 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1684,13 +1684,16 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) sock_reset_flag(newsk, SOCK_DONE); - filter = rcu_dereference_protected(newsk->sk_filter, 1); + rcu_read_lock(); + filter = rcu_dereference(sk->sk_filter); if (filter != NULL) /* though it's an empty new sock, the charging may fail * if sysctl_optmem_max was changed between creation of * original socket and cloning */ is_charged = sk_filter_charge(newsk, filter); + RCU_INIT_POINTER(newsk->sk_filter, filter); + rcu_read_unlock(); if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) { /* We need to make sure that we don't uncharge the new -- cgit v1.2.3