Elena Reshetova
2017-Mar-16 15:28 UTC
[Bridge] [PATCH 07/17] net: convert sock.sk_refcnt from atomic_t to refcount_t
refcount_t type and corresponding API should be
used instead of atomic_t when the variable is used as
a reference counter. This allows to avoid accidental
refcounter overflows that might lead to use-after-free
situations.
Signed-off-by: Elena Reshetova <elena.reshetova at intel.com>
Signed-off-by: Hans Liljestrand <ishkamiel at gmail.com>
Signed-off-by: Kees Cook <keescook at chromium.org>
Signed-off-by: David Windsor <dwindsor at gmail.com>
---
crypto/algif_aead.c | 2 +-
include/net/inet_hashtables.h | 4 ++--
include/net/request_sock.h | 9 +++++----
include/net/sock.h | 17 +++++++++--------
net/atm/proc.c | 2 +-
net/bluetooth/af_bluetooth.c | 2 +-
net/bluetooth/rfcomm/sock.c | 2 +-
net/core/skbuff.c | 6 +++---
net/core/sock.c | 4 ++--
net/ipv4/inet_connection_sock.c | 2 +-
net/ipv4/inet_hashtables.c | 4 ++--
net/ipv4/inet_timewait_sock.c | 8 ++++----
net/ipv4/ping.c | 4 ++--
net/ipv4/raw.c | 2 +-
net/ipv4/syncookies.c | 2 +-
net/ipv4/tcp_fastopen.c | 2 +-
net/ipv4/tcp_ipv4.c | 4 ++--
net/ipv4/udp.c | 6 +++---
net/ipv4/udp_diag.c | 4 ++--
net/ipv6/datagram.c | 2 +-
net/ipv6/inet6_hashtables.c | 4 ++--
net/ipv6/tcp_ipv6.c | 4 ++--
net/ipv6/udp.c | 2 +-
net/key/af_key.c | 2 +-
net/l2tp/l2tp_debugfs.c | 3 +--
net/llc/llc_conn.c | 8 ++++----
net/llc/llc_sap.c | 2 +-
net/netfilter/xt_TPROXY.c | 4 ++--
net/netlink/af_netlink.c | 6 +++---
net/packet/af_packet.c | 2 +-
net/phonet/socket.c | 2 +-
net/rxrpc/af_rxrpc.c | 2 +-
net/sched/em_meta.c | 2 +-
net/tipc/socket.c | 2 +-
net/unix/af_unix.c | 2 +-
35 files changed, 68 insertions(+), 67 deletions(-)
diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c
index 5a80537..607380d 100644
--- a/crypto/algif_aead.c
+++ b/crypto/algif_aead.c
@@ -750,7 +750,7 @@ static void aead_sock_destruct(struct sock *sk)
unsigned int ivlen = crypto_aead_ivsize(
crypto_aead_reqtfm(&ctx->aead_req));
- WARN_ON(atomic_read(&sk->sk_refcnt) != 0);
+ WARN_ON(refcount_read(&sk->sk_refcnt) != 0);
aead_put_sgl(sk);
sock_kzfree_s(sk, ctx->iv, ivlen);
sock_kfree_s(sk, ctx, ctx->len);
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 1178931..b9e6e0e 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -32,7 +32,7 @@
#include <net/tcp_states.h>
#include <net/netns/hash.h>
-#include <linux/atomic.h>
+#include <linux/refcount.h>
#include <asm/byteorder.h>
/* This is for all connections with a full identity, no wildcards.
@@ -334,7 +334,7 @@ static inline struct sock *inet_lookup(struct net *net,
sk = __inet_lookup(net, hashinfo, skb, doff, saddr, sport, daddr,
dport, dif, &refcounted);
- if (sk && !refcounted &&
!atomic_inc_not_zero(&sk->sk_refcnt))
+ if (sk && !refcounted &&
!refcount_inc_not_zero(&sk->sk_refcnt))
sk = NULL;
return sk;
}
diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index a12a5d2..e76e8c2 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -19,6 +19,7 @@
#include <linux/spinlock.h>
#include <linux/types.h>
#include <linux/bug.h>
+#include <linux/refcount.h>
#include <net/sock.h>
@@ -89,7 +90,7 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock
*sk_listener,
return NULL;
req->rsk_listener = NULL;
if (attach_listener) {
- if (unlikely(!atomic_inc_not_zero(&sk_listener->sk_refcnt))) {
+ if (unlikely(!refcount_inc_not_zero(&sk_listener->sk_refcnt))) {
kmem_cache_free(ops->slab, req);
return NULL;
}
@@ -100,7 +101,7 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock
*sk_listener,
sk_node_init(&req_to_sk(req)->sk_node);
sk_tx_queue_clear(req_to_sk(req));
req->saved_syn = NULL;
- atomic_set(&req->rsk_refcnt, 0);
+ refcount_set(&req->rsk_refcnt, 0);
return req;
}
@@ -108,7 +109,7 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock
*sk_listener,
static inline void reqsk_free(struct request_sock *req)
{
/* temporary debugging */
- WARN_ON_ONCE(atomic_read(&req->rsk_refcnt) != 0);
+ WARN_ON_ONCE(refcount_read(&req->rsk_refcnt) != 0);
req->rsk_ops->destructor(req);
if (req->rsk_listener)
@@ -119,7 +120,7 @@ static inline void reqsk_free(struct request_sock *req)
static inline void reqsk_put(struct request_sock *req)
{
- if (atomic_dec_and_test(&req->rsk_refcnt))
+ if (refcount_dec_and_test(&req->rsk_refcnt))
reqsk_free(req);
}
diff --git a/include/net/sock.h b/include/net/sock.h
index 24dcdba..c4f2b6c 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -66,6 +66,7 @@
#include <linux/poll.h>
#include <linux/atomic.h>
+#include <linux/refcount.h>
#include <net/dst.h>
#include <net/checksum.h>
#include <net/tcp_states.h>
@@ -219,7 +220,7 @@ struct sock_common {
u32 skc_tw_rcv_nxt; /* struct tcp_timewait_sock */
};
- atomic_t skc_refcnt;
+ refcount_t skc_refcnt;
/* private: */
int skc_dontcopy_end[0];
union {
@@ -602,7 +603,7 @@ static inline bool __sk_del_node_init(struct sock *sk)
static __always_inline void sock_hold(struct sock *sk)
{
- atomic_inc(&sk->sk_refcnt);
+ refcount_inc(&sk->sk_refcnt);
}
/* Ungrab socket in the context, which assumes that socket refcnt
@@ -610,7 +611,7 @@ static __always_inline void sock_hold(struct sock *sk)
*/
static __always_inline void __sock_put(struct sock *sk)
{
- atomic_dec(&sk->sk_refcnt);
+ refcount_dec(&sk->sk_refcnt);
}
static inline bool sk_del_node_init(struct sock *sk)
@@ -619,7 +620,7 @@ static inline bool sk_del_node_init(struct sock *sk)
if (rc) {
/* paranoid for a while -acme */
- WARN_ON(atomic_read(&sk->sk_refcnt) == 1);
+ WARN_ON(refcount_read(&sk->sk_refcnt) == 1);
__sock_put(sk);
}
return rc;
@@ -641,7 +642,7 @@ static inline bool sk_nulls_del_node_init_rcu(struct sock
*sk)
if (rc) {
/* paranoid for a while -acme */
- WARN_ON(atomic_read(&sk->sk_refcnt) == 1);
+ WARN_ON(refcount_read(&sk->sk_refcnt) == 1);
__sock_put(sk);
}
return rc;
@@ -1130,9 +1131,9 @@ static inline void sk_refcnt_debug_dec(struct sock *sk)
static inline void sk_refcnt_debug_release(const struct sock *sk)
{
- if (atomic_read(&sk->sk_refcnt) != 1)
+ if (refcount_read(&sk->sk_refcnt) != 1)
printk(KERN_DEBUG "Destruction of the %s socket %p delayed,
refcnt=%d\n",
- sk->sk_prot->name, sk, atomic_read(&sk->sk_refcnt));
+ sk->sk_prot->name, sk, refcount_read(&sk->sk_refcnt));
}
#else /* SOCK_REFCNT_DEBUG */
#define sk_refcnt_debug_inc(sk) do { } while (0)
@@ -1641,7 +1642,7 @@ void sock_init_data(struct socket *sock, struct sock *sk);
/* Ungrab socket and destroy it, if it was the last reference. */
static inline void sock_put(struct sock *sk)
{
- if (atomic_dec_and_test(&sk->sk_refcnt))
+ if (refcount_dec_and_test(&sk->sk_refcnt))
sk_free(sk);
}
/* Generic version of sock_put(), dealing with all sockets
diff --git a/net/atm/proc.c b/net/atm/proc.c
index bbb6461..27c9c01 100644
--- a/net/atm/proc.c
+++ b/net/atm/proc.c
@@ -211,7 +211,7 @@ static void vcc_info(struct seq_file *seq, struct atm_vcc
*vcc)
vcc->flags, sk->sk_err,
sk_wmem_alloc_get(sk), sk->sk_sndbuf,
sk_rmem_alloc_get(sk), sk->sk_rcvbuf,
- atomic_read(&sk->sk_refcnt));
+ refcount_read(&sk->sk_refcnt));
}
static void svc_info(struct seq_file *seq, struct atm_vcc *vcc)
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 69e1f7d..dbc00c2 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -631,7 +631,7 @@ static int bt_seq_show(struct seq_file *seq, void *v)
seq_printf(seq,
"%pK %-6d %-6u %-6u %-6u %-6lu %-6lu",
sk,
- atomic_read(&sk->sk_refcnt),
+ refcount_read(&sk->sk_refcnt),
sk_rmem_alloc_get(sk),
sk_wmem_alloc_get(sk),
from_kuid(seq_user_ns(seq), sock_i_uid(sk)),
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index aa1a814..951be13 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -197,7 +197,7 @@ static void rfcomm_sock_kill(struct sock *sk)
if (!sock_flag(sk, SOCK_ZAPPED) || sk->sk_socket)
return;
- BT_DBG("sk %p state %d refcnt %d", sk, sk->sk_state,
atomic_read(&sk->sk_refcnt));
+ BT_DBG("sk %p state %d refcnt %d", sk, sk->sk_state,
refcount_read(&sk->sk_refcnt));
/* Kill poor orphan */
bt_sock_unlink(&rfcomm_sk_list, sk);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index e81a27f..7927fa0 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3763,7 +3763,7 @@ struct sk_buff *skb_clone_sk(struct sk_buff *skb)
struct sock *sk = skb->sk;
struct sk_buff *clone;
- if (!sk || !atomic_inc_not_zero(&sk->sk_refcnt))
+ if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt))
return NULL;
clone = skb_clone(skb, GFP_ATOMIC);
@@ -3829,7 +3829,7 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
/* Take a reference to prevent skb_orphan() from freeing the socket,
* but only if the socket refcount is not zero.
*/
- if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) {
+ if (likely(refcount_inc_not_zero(&sk->sk_refcnt))) {
*skb_hwtstamps(skb) = *hwtstamps;
__skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND);
sock_put(sk);
@@ -3905,7 +3905,7 @@ void skb_complete_wifi_ack(struct sk_buff *skb, bool
acked)
/* Take a reference to prevent skb_orphan() from freeing the socket,
* but only if the socket refcount is not zero.
*/
- if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) {
+ if (likely(refcount_inc_not_zero(&sk->sk_refcnt))) {
err = sock_queue_err_skb(sk, skb);
sock_put(sk);
}
diff --git a/net/core/sock.c b/net/core/sock.c
index e830ddc..e4c52af 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1559,7 +1559,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const
gfp_t priority)
* (Documentation/RCU/rculist_nulls.txt for details)
*/
smp_wmb();
- atomic_set(&newsk->sk_refcnt, 2);
+ refcount_set(&newsk->sk_refcnt, 2);
/*
* Increment the counter in the same struct proto as the master
@@ -2517,7 +2517,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
* (Documentation/RCU/rculist_nulls.txt for details)
*/
smp_wmb();
- atomic_set(&sk->sk_refcnt, 1);
+ refcount_set(&sk->sk_refcnt, 1);
atomic_set(&sk->sk_drops, 0);
}
EXPORT_SYMBOL(sock_init_data);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index b4d5980..f01adaf 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -755,7 +755,7 @@ static void reqsk_queue_hash_req(struct request_sock *req,
* are committed to memory and refcnt initialized.
*/
smp_wmb();
- atomic_set(&req->rsk_refcnt, 2 + 1);
+ refcount_set(&req->rsk_refcnt, 2 + 1);
}
void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index e9a59d2..a4be2c1 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -246,7 +246,7 @@ EXPORT_SYMBOL_GPL(__inet_lookup_listener);
/* All sockets share common refcount, but have different destructors */
void sock_gen_put(struct sock *sk)
{
- if (!atomic_dec_and_test(&sk->sk_refcnt))
+ if (!refcount_dec_and_test(&sk->sk_refcnt))
return;
if (sk->sk_state == TCP_TIME_WAIT)
@@ -287,7 +287,7 @@ struct sock *__inet_lookup_established(struct net *net,
continue;
if (likely(INET_MATCH(sk, net, acookie,
saddr, daddr, ports, dif))) {
- if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt)))
+ if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
goto out;
if (unlikely(!INET_MATCH(sk, net, acookie,
saddr, daddr, ports, dif))) {
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index f8aff2c..5b03915 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -76,7 +76,7 @@ void inet_twsk_free(struct inet_timewait_sock *tw)
void inet_twsk_put(struct inet_timewait_sock *tw)
{
- if (atomic_dec_and_test(&tw->tw_refcnt))
+ if (refcount_dec_and_test(&tw->tw_refcnt))
inet_twsk_free(tw);
}
EXPORT_SYMBOL_GPL(inet_twsk_put);
@@ -131,7 +131,7 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw,
struct sock *sk,
* We can use atomic_set() because prior spin_lock()/spin_unlock()
* committed into memory all tw fields.
*/
- atomic_set(&tw->tw_refcnt, 4);
+ refcount_set(&tw->tw_refcnt, 4);
inet_twsk_add_node_rcu(tw, &ehead->chain);
/* Step 3: Remove SK from hash chain */
@@ -195,7 +195,7 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock
*sk,
* to a non null value before everything is setup for this
* timewait socket.
*/
- atomic_set(&tw->tw_refcnt, 0);
+ refcount_set(&tw->tw_refcnt, 0);
__module_get(tw->tw_prot->owner);
}
@@ -278,7 +278,7 @@ void inet_twsk_purge(struct inet_hashinfo *hashinfo, int
family)
atomic_read(&twsk_net(tw)->count))
continue;
- if (unlikely(!atomic_inc_not_zero(&tw->tw_refcnt)))
+ if (unlikely(!refcount_inc_not_zero(&tw->tw_refcnt)))
continue;
if (unlikely((tw->tw_family != family) ||
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 2af6244..c5434b9 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -289,7 +289,7 @@ void ping_close(struct sock *sk, long timeout)
{
pr_debug("ping_close(sk=%p,sk->num=%u)\n",
inet_sk(sk), inet_sk(sk)->inet_num);
- pr_debug("isk->refcnt = %d\n", sk->sk_refcnt.counter);
+ pr_debug("isk->refcnt = %d\n",
refcount_read(&sk->sk_refcnt));
sk_common_release(sk);
}
@@ -1126,7 +1126,7 @@ static void ping_v4_format_sock(struct sock *sp, struct
seq_file *f,
0, 0L, 0,
from_kuid_munged(seq_user_ns(f), sock_i_uid(sp)),
0, sock_i_ino(sp),
- atomic_read(&sp->sk_refcnt), sp,
+ refcount_read(&sp->sk_refcnt), sp,
atomic_read(&sp->sk_drops));
}
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 8119e1f..7ab99f0 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -1058,7 +1058,7 @@ static void raw_sock_seq_show(struct seq_file *seq, struct
sock *sp, int i)
0, 0L, 0,
from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)),
0, sock_i_ino(sp),
- atomic_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops));
+ refcount_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops));
}
static int raw_seq_show(struct seq_file *seq, void *v)
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 496b97e..42d2426 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -212,7 +212,7 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct
sk_buff *skb,
child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst,
NULL, &own_req);
if (child) {
- atomic_set(&req->rsk_refcnt, 1);
+ refcount_set(&req->rsk_refcnt, 1);
sock_rps_save_rxhash(child, skb);
inet_csk_reqsk_queue_add(sk, req, child);
} else {
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 8ea4e97..d527795 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -214,7 +214,7 @@ static struct sock *tcp_fastopen_create_child(struct sock
*sk,
inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS,
TCP_TIMEOUT_INIT, TCP_RTO_MAX);
- atomic_set(&req->rsk_refcnt, 2);
+ refcount_set(&req->rsk_refcnt, 2);
/* Now finish processing the fastopen child socket. */
inet_csk(child)->icsk_af_ops->rebuild_header(child);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 69f2d20..bb5e4c4 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2269,7 +2269,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file
*f, int i)
from_kuid_munged(seq_user_ns(f), sock_i_uid(sk)),
icsk->icsk_probes_out,
sock_i_ino(sk),
- atomic_read(&sk->sk_refcnt), sk,
+ refcount_read(&sk->sk_refcnt), sk,
jiffies_to_clock_t(icsk->icsk_rto),
jiffies_to_clock_t(icsk->icsk_ack.ato),
(icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong,
@@ -2295,7 +2295,7 @@ static void get_timewait4_sock(const struct
inet_timewait_sock *tw,
" %02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK",
i, src, srcp, dest, destp, tw->tw_substate, 0, 0,
3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0,
- atomic_read(&tw->tw_refcnt), tw);
+ refcount_read(&tw->tw_refcnt), tw);
}
#define TMPSZ 150
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index ea6e4cf..c241d6df 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -577,7 +577,7 @@ struct sock *udp4_lib_lookup(struct net *net, __be32 saddr,
__be16 sport,
sk = __udp4_lib_lookup(net, saddr, sport, daddr, dport,
dif, &udp_table, NULL);
- if (sk && !atomic_inc_not_zero(&sk->sk_refcnt))
+ if (sk && !refcount_inc_not_zero(&sk->sk_refcnt))
sk = NULL;
return sk;
}
@@ -2082,7 +2082,7 @@ void udp_v4_early_demux(struct sk_buff *skb)
uh->source, iph->saddr, dif);
}
- if (!sk || !atomic_inc_not_zero_hint(&sk->sk_refcnt, 2))
+ if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt))
return;
skb->sk = sk;
@@ -2530,7 +2530,7 @@ static void udp4_format_sock(struct sock *sp, struct
seq_file *f,
0, 0L, 0,
from_kuid_munged(seq_user_ns(f), sock_i_uid(sp)),
0, sock_i_ino(sp),
- atomic_read(&sp->sk_refcnt), sp,
+ refcount_read(&sp->sk_refcnt), sp,
atomic_read(&sp->sk_drops));
}
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index 9a89c10..4515836 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -55,7 +55,7 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff
*in_skb,
req->id.idiag_dport,
req->id.idiag_if, tbl, NULL);
#endif
- if (sk && !atomic_inc_not_zero(&sk->sk_refcnt))
+ if (sk && !refcount_inc_not_zero(&sk->sk_refcnt))
sk = NULL;
rcu_read_unlock();
err = -ENOENT;
@@ -206,7 +206,7 @@ static int __udp_diag_destroy(struct sk_buff *in_skb,
return -EINVAL;
}
- if (sk && !atomic_inc_not_zero(&sk->sk_refcnt))
+ if (sk && !refcount_inc_not_zero(&sk->sk_refcnt))
sk = NULL;
rcu_read_unlock();
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index eec27f8..a15c9a6 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -1043,6 +1043,6 @@ void ip6_dgram_sock_seq_show(struct seq_file *seq, struct
sock *sp,
from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)),
0,
sock_i_ino(sp),
- atomic_read(&sp->sk_refcnt), sp,
+ refcount_read(&sp->sk_refcnt), sp,
atomic_read(&sp->sk_drops));
}
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index d090091..b13b8f9 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -75,7 +75,7 @@ struct sock *__inet6_lookup_established(struct net *net,
continue;
if (!INET6_MATCH(sk, net, saddr, daddr, ports, dif))
continue;
- if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt)))
+ if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
goto out;
if (unlikely(!INET6_MATCH(sk, net, saddr, daddr, ports, dif))) {
@@ -172,7 +172,7 @@ struct sock *inet6_lookup(struct net *net, struct
inet_hashinfo *hashinfo,
sk = __inet6_lookup(net, hashinfo, skb, doff, saddr, sport, daddr,
ntohs(dport), dif, &refcounted);
- if (sk && !refcounted &&
!atomic_inc_not_zero(&sk->sk_refcnt))
+ if (sk && !refcounted &&
!refcount_inc_not_zero(&sk->sk_refcnt))
sk = NULL;
return sk;
}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 21bb2fc..1a55d49 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1796,7 +1796,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct
sock *sp, int i)
from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)),
icsk->icsk_probes_out,
sock_i_ino(sp),
- atomic_read(&sp->sk_refcnt), sp,
+ refcount_read(&sp->sk_refcnt), sp,
jiffies_to_clock_t(icsk->icsk_rto),
jiffies_to_clock_t(icsk->icsk_ack.ato),
(icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong,
@@ -1829,7 +1829,7 @@ static void get_timewait6_sock(struct seq_file *seq,
dest->s6_addr32[2], dest->s6_addr32[3], destp,
tw->tw_substate, 0, 0,
3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0,
- atomic_read(&tw->tw_refcnt), tw);
+ refcount_read(&tw->tw_refcnt), tw);
}
static int tcp6_seq_show(struct seq_file *seq, void *v)
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 4e4c401..deff3a6 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -324,7 +324,7 @@ struct sock *udp6_lib_lookup(struct net *net, const struct
in6_addr *saddr, __be
sk = __udp6_lib_lookup(net, saddr, sport, daddr, dport,
dif, &udp_table, NULL);
- if (sk && !atomic_inc_not_zero(&sk->sk_refcnt))
+ if (sk && !refcount_inc_not_zero(&sk->sk_refcnt))
sk = NULL;
return sk;
}
diff --git a/net/key/af_key.c b/net/key/af_key.c
index ba00bd3..30ec662 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -3711,7 +3711,7 @@ static int pfkey_seq_show(struct seq_file *f, void *v)
else
seq_printf(f, "%pK %-6d %-6u %-6u %-6u %-6lu\n",
s,
- atomic_read(&s->sk_refcnt),
+ refcount_read(&s->sk_refcnt),
sk_rmem_alloc_get(s),
sk_wmem_alloc_get(s),
from_kuid_munged(seq_user_ns(f), sock_i_uid(s)),
diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c
index 2d6760a..c87689d 100644
--- a/net/l2tp/l2tp_debugfs.c
+++ b/net/l2tp/l2tp_debugfs.c
@@ -144,9 +144,8 @@ static void l2tp_dfs_seq_tunnel_show(struct seq_file *m,
void *v)
tunnel->encap == L2TP_ENCAPTYPE_IP ? "IP" :
"");
seq_printf(m, " %d sessions, refcnt %d/%d\n", session_count,
- tunnel->sock ? atomic_read(&tunnel->sock->sk_refcnt) : 0,
+ tunnel->sock ? refcount_read(&tunnel->sock->sk_refcnt) : 0,
atomic_read(&tunnel->ref_count));
-
seq_printf(m, " %08x rx %ld/%ld/%ld rx %ld/%ld/%ld\n",
tunnel->debug,
atomic_long_read(&tunnel->stats.tx_packets),
diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index 9b02c13..5e91b47 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -507,7 +507,7 @@ static struct sock *__llc_lookup_established(struct llc_sap
*sap,
sk_nulls_for_each_rcu(rc, node, laddr_hb) {
if (llc_estab_match(sap, daddr, laddr, rc)) {
/* Extra checks required by SLAB_TYPESAFE_BY_RCU */
- if (unlikely(!atomic_inc_not_zero(&rc->sk_refcnt)))
+ if (unlikely(!refcount_inc_not_zero(&rc->sk_refcnt)))
goto again;
if (unlikely(llc_sk(rc)->sap != sap ||
!llc_estab_match(sap, daddr, laddr, rc))) {
@@ -566,7 +566,7 @@ static struct sock *__llc_lookup_listener(struct llc_sap
*sap,
sk_nulls_for_each_rcu(rc, node, laddr_hb) {
if (llc_listener_match(sap, laddr, rc)) {
/* Extra checks required by SLAB_TYPESAFE_BY_RCU */
- if (unlikely(!atomic_inc_not_zero(&rc->sk_refcnt)))
+ if (unlikely(!refcount_inc_not_zero(&rc->sk_refcnt)))
goto again;
if (unlikely(llc_sk(rc)->sap != sap ||
!llc_listener_match(sap, laddr, rc))) {
@@ -973,9 +973,9 @@ void llc_sk_free(struct sock *sk)
skb_queue_purge(&sk->sk_write_queue);
skb_queue_purge(&llc->pdu_unack_q);
#ifdef LLC_REFCNT_DEBUG
- if (atomic_read(&sk->sk_refcnt) != 1) {
+ if (refcount_read(&sk->sk_refcnt) != 1) {
printk(KERN_DEBUG "Destruction of LLC sock %p delayed in %s,
cnt=%d\n",
- sk, __func__, atomic_read(&sk->sk_refcnt));
+ sk, __func__, refcount_read(&sk->sk_refcnt));
printk(KERN_DEBUG "%d LLC sockets are still alive\n",
atomic_read(&llc_sock_nr));
} else {
diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c
index 63b6ab0..d90928f 100644
--- a/net/llc/llc_sap.c
+++ b/net/llc/llc_sap.c
@@ -329,7 +329,7 @@ static struct sock *llc_lookup_dgram(struct llc_sap *sap,
sk_nulls_for_each_rcu(rc, node, laddr_hb) {
if (llc_dgram_match(sap, laddr, rc)) {
/* Extra checks required by SLAB_TYPESAFE_BY_RCU */
- if (unlikely(!atomic_inc_not_zero(&rc->sk_refcnt)))
+ if (unlikely(!refcount_inc_not_zero(&rc->sk_refcnt)))
goto again;
if (unlikely(llc_sk(rc)->sap != sap ||
!llc_dgram_match(sap, laddr, rc))) {
diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c
index 80cb7ba..d51f1e8 100644
--- a/net/netfilter/xt_TPROXY.c
+++ b/net/netfilter/xt_TPROXY.c
@@ -127,7 +127,7 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb,
void *hp,
daddr, dport,
in->ifindex);
- if (sk && !atomic_inc_not_zero(&sk->sk_refcnt))
+ if (sk && !refcount_inc_not_zero(&sk->sk_refcnt))
sk = NULL;
/* NOTE: we return listeners even if bound to
* 0.0.0.0, those are filtered out in
@@ -197,7 +197,7 @@ nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb,
int thoff, void *hp,
daddr, ntohs(dport),
in->ifindex);
- if (sk && !atomic_inc_not_zero(&sk->sk_refcnt))
+ if (sk && !refcount_inc_not_zero(&sk->sk_refcnt))
sk = NULL;
/* NOTE: we return listeners even if bound to
* 0.0.0.0, those are filtered out in
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 9332b24..e3c9a6a 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -544,7 +544,7 @@ static void netlink_remove(struct sock *sk)
table = &nl_table[sk->sk_protocol];
if (!rhashtable_remove_fast(&table->hash, &nlk_sk(sk)->node,
netlink_rhashtable_params)) {
- WARN_ON(atomic_read(&sk->sk_refcnt) == 1);
+ WARN_ON(refcount_read(&sk->sk_refcnt) == 1);
__sock_put(sk);
}
@@ -657,7 +657,7 @@ static void deferred_put_nlk_sk(struct rcu_head *head)
struct netlink_sock *nlk = container_of(head, struct netlink_sock, rcu);
struct sock *sk = &nlk->sk;
- if (!atomic_dec_and_test(&sk->sk_refcnt))
+ if (!refcount_dec_and_test(&sk->sk_refcnt))
return;
if (nlk->cb_running && nlk->cb.done) {
@@ -2469,7 +2469,7 @@ static int netlink_seq_show(struct seq_file *seq, void *v)
sk_rmem_alloc_get(s),
sk_wmem_alloc_get(s),
nlk->cb_running,
- atomic_read(&s->sk_refcnt),
+ refcount_read(&s->sk_refcnt),
atomic_read(&s->sk_drops),
sock_i_ino(s)
);
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 82eb052..ad5e5dc 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -4448,7 +4448,7 @@ static int packet_seq_show(struct seq_file *seq, void *v)
seq_printf(seq,
"%pK %-6d %-4d %04x %-5d %1d %-6u %-6u %-6lu\n",
s,
- atomic_read(&s->sk_refcnt),
+ refcount_read(&s->sk_refcnt),
s->sk_type,
ntohs(po->num),
po->ifindex,
diff --git a/net/phonet/socket.c b/net/phonet/socket.c
index 27b0b13..6b7aa30 100644
--- a/net/phonet/socket.c
+++ b/net/phonet/socket.c
@@ -614,7 +614,7 @@ static int pn_sock_seq_show(struct seq_file *seq, void *v)
sk_wmem_alloc_get(sk), sk_rmem_alloc_get(sk),
from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk)),
sock_i_ino(sk),
- atomic_read(&sk->sk_refcnt), sk,
+ refcount_read(&sk->sk_refcnt), sk,
atomic_read(&sk->sk_drops));
}
seq_pad(seq, '\n');
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index b473ac2..e33e007 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -682,7 +682,7 @@ static int rxrpc_release_sock(struct sock *sk)
{
struct rxrpc_sock *rx = rxrpc_sk(sk);
- _enter("%p{%d,%d}", sk, sk->sk_state,
atomic_read(&sk->sk_refcnt));
+ _enter("%p{%d,%d}", sk, sk->sk_state,
refcount_read(&sk->sk_refcnt));
/* declare the socket closed for business */
sock_orphan(sk);
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index ae7e4f5..b1e7838 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -340,7 +340,7 @@ META_COLLECTOR(int_sk_refcnt)
*err = -1;
return;
}
- dst->value = atomic_read(&skb->sk->sk_refcnt);
+ dst->value = refcount_read(&skb->sk->sk_refcnt);
}
META_COLLECTOR(int_sk_rcvbuf)
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 43e4045..6991dbe 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2307,7 +2307,7 @@ static void tipc_sk_remove(struct tipc_sock *tsk)
struct tipc_net *tn = net_generic(sock_net(sk), tipc_net_id);
if (!rhashtable_remove_fast(&tn->sk_rht, &tsk->node,
tsk_rht_params)) {
- WARN_ON(atomic_read(&sk->sk_refcnt) == 1);
+ WARN_ON(refcount_read(&sk->sk_refcnt) == 1);
__sock_put(sk);
}
}
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index a74339e..e9f8102 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2750,7 +2750,7 @@ static int unix_seq_show(struct seq_file *seq, void *v)
seq_printf(seq, "%pK: %08X %08X %08X %04X %02X %5lu",
s,
- atomic_read(&s->sk_refcnt),
+ refcount_read(&s->sk_refcnt),
0,
s->sk_state == TCP_LISTEN ? __SO_ACCEPTCON : 0,
s->sk_type,
--
2.7.4
Eric Dumazet
2017-Mar-16 16:58 UTC
[Bridge] [PATCH 07/17] net: convert sock.sk_refcnt from atomic_t to refcount_t
On Thu, 2017-03-16 at 17:28 +0200, Elena Reshetova wrote:> refcount_t type and corresponding API should be > used instead of atomic_t when the variable is used as > a reference counter. This allows to avoid accidental > refcounter overflows that might lead to use-after-free > situations....> static __always_inline void sock_hold(struct sock *sk) > { > - atomic_inc(&sk->sk_refcnt); > + refcount_inc(&sk->sk_refcnt); > } >While I certainly see the value of these refcount_t, we have a very different behavior on these atomic_inc() which were doing a single inlined LOCK RMW on x86. We now call an external function performing a atomic_read(), various ops/tests, then atomic_cmpxchg_relaxed(), in a loop, loosing the nice ability for x86 of preventing live locks. Looks a lot of bloat, just to be able to chase hypothetical bugs in the kernel. I would love to have a way to enable extra debugging when I want a debug kernel, like LOCKDEP or KASAN. By adding all this bloat, we assert linux kernel is terminally buggy and every atomic_inc() we did was suspicious, and need to be always instrumented/validated.