From 43815482370c510c569fd18edb57afcb0fa8cab6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 29 Apr 2010 11:01:49 +0000 Subject: 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 Signed-off-by: David S. Miller --- include/linux/net.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux/net.h') diff --git a/include/linux/net.h b/include/linux/net.h index 4157b5d42bd6..2b4deeeb8646 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -59,6 +59,7 @@ typedef enum { #include #include /* For O_CLOEXEC and O_NONBLOCK */ #include +#include struct poll_table_struct; struct pipe_inode_info; @@ -116,6 +117,12 @@ enum sock_shutdown_cmd { SHUT_RDWR = 2, }; +struct socket_wq { + wait_queue_head_t wait; + struct fasync_struct *fasync_list; + struct rcu_head rcu; +} ____cacheline_aligned_in_smp; + /** * struct socket - general BSD socket * @state: socket state (%SS_CONNECTED, etc) @@ -135,11 +142,8 @@ struct socket { kmemcheck_bitfield_end(type); unsigned long flags; - /* - * Please keep fasync_list & wait fields in the same cache line - */ - struct fasync_struct *fasync_list; - wait_queue_head_t wait; + + struct socket_wq *wq; struct file *file; struct sock *sk; -- cgit v1.2.3