mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-14 13:06:45 +07:00
da314c9923
On Mon, Sep 21, 2015 at 02:20:22PM -0400, Tejun Heo wrote: > > store_release and load_acquire are different from the usual memory > barriers and can't be paired this way. You have to pair store_release > and load_acquire. Besides, it isn't a particularly good idea to OK I've decided to drop the acquire/release helpers as they don't help us at all and simply pessimises the code by using full memory barriers (on some architectures) where only a write or read barrier is needed. > depend on memory barriers embedded in other data structures like the > above. Here, especially, rhashtable_insert() would have write barrier > *before* the entry is hashed not necessarily *after*, which means that > in the above case, a socket which appears to have set bound to a > reader might not visible when the reader tries to look up the socket > on the hashtable. But you are right we do need an explicit write barrier here to ensure that the hashing is visible. > There's no reason to be overly smart here. This isn't a crazy hot > path, write barriers tend to be very cheap, store_release more so. > Please just do smp_store_release() and note what it's paired with. It's not about being overly smart. It's about actually understanding what's going on with the code. I've seen too many instances of people simply sprinkling synchronisation primitives around without any knowledge of what is happening underneath, which is just a recipe for creating hard-to-debug races. > > @@ -1539,7 +1546,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, > > } > > } > > > > - if (!nlk->portid) { > > + if (!nlk->bound) { > > I don't think you can skip load_acquire here just because this is the > second deref of the variable. That doesn't change anything. Race > condition could still happen between the first and second tests and > skipping the second would lead to the same kind of bug. The reason this one is OK is because we do not use nlk->portid or try to get nlk from the hash table before we return to user-space. However, there is a real bug here that none of these acquire/release helpers discovered. The two bound tests here used to be a single one. Now that they are separate it is entirely possible for another thread to come in the middle and bind the socket. So we need to repeat the portid check in order to maintain consistency. > > @@ -1587,7 +1594,7 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr, > > !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND)) > > return -EPERM; > > > > - if (!nlk->portid) > > + if (!nlk->bound) > > Don't we need load_acquire here too? Is this path holding a lock > which makes that unnecessary? Ditto. ---8<--- The commit1f770c0a09
("netlink: Fix autobind race condition that leads to zero port ID") created some new races that can occur due to inconcsistencies between the two port IDs. Tejun is right that a barrier is unavoidable. Therefore I am reverting to the original patch that used a boolean to indicate that a user netlink socket has been bound. Barriers have been added where necessary to ensure that a valid portid and the hashed socket is visible. I have also changed netlink_insert to only return EBUSY if the socket is bound to a portid different to the requested one. This combined with only reading nlk->bound once in netlink_bind fixes a race where two threads that bind the socket at the same time with different port IDs may both succeed. Fixes:1f770c0a09
("netlink: Fix autobind race condition that leads to zero port ID") Reported-by: Tejun Heo <tj@kernel.org> Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Nacked-by: Tejun Heo <tj@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
90 lines
2.1 KiB
C
90 lines
2.1 KiB
C
#ifndef _AF_NETLINK_H
|
|
#define _AF_NETLINK_H
|
|
|
|
#include <linux/rhashtable.h>
|
|
#include <linux/atomic.h>
|
|
#include <net/sock.h>
|
|
|
|
#define NLGRPSZ(x) (ALIGN(x, sizeof(unsigned long) * 8) / 8)
|
|
#define NLGRPLONGS(x) (NLGRPSZ(x)/sizeof(unsigned long))
|
|
|
|
struct netlink_ring {
|
|
void **pg_vec;
|
|
unsigned int head;
|
|
unsigned int frames_per_block;
|
|
unsigned int frame_size;
|
|
unsigned int frame_max;
|
|
|
|
unsigned int pg_vec_order;
|
|
unsigned int pg_vec_pages;
|
|
unsigned int pg_vec_len;
|
|
|
|
atomic_t pending;
|
|
};
|
|
|
|
struct netlink_sock {
|
|
/* struct sock has to be the first member of netlink_sock */
|
|
struct sock sk;
|
|
u32 portid;
|
|
u32 dst_portid;
|
|
u32 dst_group;
|
|
u32 flags;
|
|
u32 subscriptions;
|
|
u32 ngroups;
|
|
unsigned long *groups;
|
|
unsigned long state;
|
|
size_t max_recvmsg_len;
|
|
wait_queue_head_t wait;
|
|
bool bound;
|
|
bool cb_running;
|
|
struct netlink_callback cb;
|
|
struct mutex *cb_mutex;
|
|
struct mutex cb_def_mutex;
|
|
void (*netlink_rcv)(struct sk_buff *skb);
|
|
int (*netlink_bind)(struct net *net, int group);
|
|
void (*netlink_unbind)(struct net *net, int group);
|
|
struct module *module;
|
|
#ifdef CONFIG_NETLINK_MMAP
|
|
struct mutex pg_vec_lock;
|
|
struct netlink_ring rx_ring;
|
|
struct netlink_ring tx_ring;
|
|
atomic_t mapped;
|
|
#endif /* CONFIG_NETLINK_MMAP */
|
|
|
|
struct rhash_head node;
|
|
struct rcu_head rcu;
|
|
};
|
|
|
|
static inline struct netlink_sock *nlk_sk(struct sock *sk)
|
|
{
|
|
return container_of(sk, struct netlink_sock, sk);
|
|
}
|
|
|
|
static inline bool netlink_skb_is_mmaped(const struct sk_buff *skb)
|
|
{
|
|
#ifdef CONFIG_NETLINK_MMAP
|
|
return NETLINK_CB(skb).flags & NETLINK_SKB_MMAPED;
|
|
#else
|
|
return false;
|
|
#endif /* CONFIG_NETLINK_MMAP */
|
|
}
|
|
|
|
struct netlink_table {
|
|
struct rhashtable hash;
|
|
struct hlist_head mc_list;
|
|
struct listeners __rcu *listeners;
|
|
unsigned int flags;
|
|
unsigned int groups;
|
|
struct mutex *cb_mutex;
|
|
struct module *module;
|
|
int (*bind)(struct net *net, int group);
|
|
void (*unbind)(struct net *net, int group);
|
|
bool (*compare)(struct net *net, struct sock *sock);
|
|
int registered;
|
|
};
|
|
|
|
extern struct netlink_table *nl_table;
|
|
extern rwlock_t nl_table_lock;
|
|
|
|
#endif
|