![Eric Dumazet](/assets/img/avatar_default.png)
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>
74 lines
1.8 KiB
C
74 lines
1.8 KiB
C
#ifndef __LINUX_NET_AFUNIX_H
|
|
#define __LINUX_NET_AFUNIX_H
|
|
|
|
#include <linux/socket.h>
|
|
#include <linux/un.h>
|
|
#include <linux/mutex.h>
|
|
#include <net/sock.h>
|
|
|
|
extern void unix_inflight(struct file *fp);
|
|
extern void unix_notinflight(struct file *fp);
|
|
extern void unix_gc(void);
|
|
extern void wait_for_unix_gc(void);
|
|
|
|
#define UNIX_HASH_SIZE 256
|
|
|
|
extern unsigned int unix_tot_inflight;
|
|
|
|
struct unix_address {
|
|
atomic_t refcnt;
|
|
int len;
|
|
unsigned hash;
|
|
struct sockaddr_un name[0];
|
|
};
|
|
|
|
struct unix_skb_parms {
|
|
struct ucred creds; /* Skb credentials */
|
|
struct scm_fp_list *fp; /* Passed files */
|
|
#ifdef CONFIG_SECURITY_NETWORK
|
|
u32 secid; /* Security ID */
|
|
#endif
|
|
};
|
|
|
|
#define UNIXCB(skb) (*(struct unix_skb_parms *)&((skb)->cb))
|
|
#define UNIXCREDS(skb) (&UNIXCB((skb)).creds)
|
|
#define UNIXSID(skb) (&UNIXCB((skb)).secid)
|
|
|
|
#define unix_state_lock(s) spin_lock(&unix_sk(s)->lock)
|
|
#define unix_state_unlock(s) spin_unlock(&unix_sk(s)->lock)
|
|
#define unix_state_lock_nested(s) \
|
|
spin_lock_nested(&unix_sk(s)->lock, \
|
|
SINGLE_DEPTH_NESTING)
|
|
|
|
#ifdef __KERNEL__
|
|
/* The AF_UNIX socket */
|
|
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 mutex readlock;
|
|
struct sock *peer;
|
|
struct sock *other;
|
|
struct list_head link;
|
|
atomic_long_t inflight;
|
|
spinlock_t lock;
|
|
unsigned int gc_candidate : 1;
|
|
unsigned int gc_maybe_cycle : 1;
|
|
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);
|
|
#else
|
|
static inline int unix_sysctl_register(struct net *net) { return 0; }
|
|
static inline void unix_sysctl_unregister(struct net *net) {}
|
|
#endif
|
|
#endif
|
|
#endif
|