net: sock_def_readable() and friends RCU conversion

sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we
need two atomic operations (and associated dirtying) per incoming
packet.

RCU conversion is pretty much needed :

1) Add a new structure, called "struct socket_wq" to hold all fields
that will need rcu_read_lock() protection (currently: a
wait_queue_head_t and a struct fasync_struct pointer).

[Future patch will add a list anchor for wakeup coalescing]

2) Attach one of such structure to each "struct socket" created in
sock_alloc_inode().

3) Respect RCU grace period when freeing a "struct socket_wq"

4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct
socket_wq"

5) Change sk_sleep() function to use new sk->sk_wq instead of
sk->sk_sleep

6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside
a rcu_read_lock() section.

7) Change all sk_has_sleeper() callers to :
  - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock)
  - Use wq_has_sleeper() to eventually wakeup tasks.
  - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock)

8) sock_wake_async() is modified to use rcu protection as well.

9) Exceptions :
  macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq"
instead of dynamically allocated ones. They dont need rcu freeing.

Some cleanups or followups are probably needed, (possible
sk_callback_lock conversion to a spinlock for example...).

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

1 files changed, 11 insertions, 9 deletions

diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index 1614d78c60ed..20725e213aee 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -30,7 +30,7 @@ struct unix_skb_parms {
 #endif
 };
 
-#define UNIXCB(skb)     (*(struct unix_skb_parms*)&((skb)->cb))
+#define UNIXCB(skb)     (*(struct unix_skb_parms *)&((skb)->cb))
 #define UNIXCREDS(skb)  (&UNIXCB((skb)).creds)
 #define UNIXSID(skb)    (&UNIXCB((skb)).secid)
 
@@ -45,21 +45,23 @@ struct unix_skb_parms {
 struct unix_sock {
         /* WARNING: sk has to be the first member */
         struct sock             sk;
-        struct unix_address     *addr;
-        struct dentry           *dentry;
-        struct vfsmount         *mnt;
+        struct unix_address     *addr;
+        struct dentry           *dentry;
+        struct vfsmount         *mnt;
         struct mutex            readlock;
-        struct sock             *peer;
-        struct sock             *other;
+        struct sock             *peer;
+        struct sock             *other;
         struct list_head        link;
-        atomic_long_t           inflight;
-        spinlock_t              lock;
+        atomic_long_t           inflight;
+        spinlock_t              lock;
         unsigned int            gc_candidate : 1;
         unsigned int            gc_maybe_cycle : 1;
-        wait_queue_head_t       peer_wait;
+        struct socket_wq        peer_wq;
 };
 #define unix_sk(__sk) ((struct unix_sock *)__sk)
 
+#define peer_wait peer_wq.wait
+
 #ifdef CONFIG_SYSCTL
 extern int unix_sysctl_register(struct net *net);
 extern void unix_sysctl_unregister(struct net *net);