search for: tun_sock_destruct

On Thu, Apr 16, 2009 at 01:08:18AM -0000, Herbert Xu wrote: > On Wed, Apr 15, 2009 at 10:38:34PM +0800, Herbert Xu wrote: > > > > So how about this? We replace the dev destructor with our own that > > doesn't immediately call free_netdev. We only call free_netdev once > > all tun fd's attached to the device have been closed. > > Here's the patch.

On Thu, Apr 16, 2009 at 01:08:18AM -0000, Herbert Xu wrote: > On Wed, Apr 15, 2009 at 10:38:34PM +0800, Herbert Xu wrote: > > > > So how about this? We replace the dev destructor with our own that > > doesn't immediately call free_netdev. We only call free_netdev once > > all tun fd's attached to the device have been closed. > > Here's the patch.

...gt;sk_sleep)) - wake_up_interruptible_sync(sk->sk_sleep); + wake_up_interruptible_sync_poll(sk->sk_sleep, POLLOUT | + POLLWRNORM | POLLWRBAND); tun = container_of(sk, struct tun_sock, sk)->tun; kill_fasync(&tun->fasync, SIGIO, POLL_OUT); @@ -858,6 +872,37 @@ static void tun_sock_destruct(struct sock *sk) free_netdev(container_of(sk, struct tun_sock, sk)->tun->dev); } +static int tun_sendmsg(struct kiocb *iocb, struct socket *sock, + struct msghdr *m, size_t total_len) +{ + struct tun_struct *tun = container_of(sock, struct tun_struct, socket); + return tun_get_us...

...gt;sk_sleep)) - wake_up_interruptible_sync(sk->sk_sleep); + wake_up_interruptible_sync_poll(sk->sk_sleep, POLLOUT | + POLLWRNORM | POLLWRBAND); tun = container_of(sk, struct tun_sock, sk)->tun; kill_fasync(&tun->fasync, SIGIO, POLL_OUT); @@ -858,6 +872,37 @@ static void tun_sock_destruct(struct sock *sk) free_netdev(container_of(sk, struct tun_sock, sk)->tun->dev); } +static int tun_sendmsg(struct kiocb *iocb, struct socket *sock, + struct msghdr *m, size_t total_len) +{ + struct tun_struct *tun = container_of(sock, struct tun_struct, socket); + return tun_get_us...

...gt;sk_sleep)) - wake_up_interruptible_sync(sk->sk_sleep); + wake_up_interruptible_sync_poll(sk->sk_sleep, POLLOUT | + POLLWRNORM | POLLWRBAND); tun = container_of(sk, struct tun_sock, sk)->tun; kill_fasync(&tun->fasync, SIGIO, POLL_OUT); @@ -858,6 +872,37 @@ static void tun_sock_destruct(struct sock *sk) free_netdev(container_of(sk, struct tun_sock, sk)->tun->dev); } +static int tun_sendmsg(struct kiocb *iocb, struct socket *sock, + struct msghdr *m, size_t total_len) +{ + struct tun_struct *tun = container_of(sock, struct tun_struct, socket); + return tun_get_us...

...gt;sk_sleep)) - wake_up_interruptible_sync(sk->sk_sleep); + wake_up_interruptible_sync_poll(sk->sk_sleep, POLLOUT | + POLLWRNORM | POLLWRBAND); tun = container_of(sk, struct tun_sock, sk)->tun; kill_fasync(&tun->fasync, SIGIO, POLL_OUT); @@ -858,6 +872,37 @@ static void tun_sock_destruct(struct sock *sk) free_netdev(container_of(sk, struct tun_sock, sk)->tun->dev); } +static int tun_sendmsg(struct kiocb *iocb, struct socket *sock, + struct msghdr *m, size_t total_len) +{ + struct tun_struct *tun = container_of(sock, struct tun_struct, socket); + return tun_get_us...

...gt;sk_sleep)) - wake_up_interruptible_sync(sk->sk_sleep); + wake_up_interruptible_sync_poll(sk->sk_sleep, POLLOUT | + POLLWRNORM | POLLWRBAND); tun = container_of(sk, struct tun_sock, sk)->tun; kill_fasync(&tun->fasync, SIGIO, POLL_OUT); @@ -858,6 +872,37 @@ static void tun_sock_destruct(struct sock *sk) free_netdev(container_of(sk, struct tun_sock, sk)->tun->dev); } +static int tun_sendmsg(struct kiocb *iocb, struct socket *sock, + struct msghdr *m, size_t total_len) +{ + struct tun_struct *tun = container_of(sock, struct tun_struct, socket); + return tun_get_us...

...gt;sk_sleep)) - wake_up_interruptible_sync(sk->sk_sleep); + wake_up_interruptible_sync_poll(sk->sk_sleep, POLLOUT | + POLLWRNORM | POLLWRBAND); tun = container_of(sk, struct tun_sock, sk)->tun; kill_fasync(&tun->fasync, SIGIO, POLL_OUT); @@ -858,6 +872,37 @@ static void tun_sock_destruct(struct sock *sk) free_netdev(container_of(sk, struct tun_sock, sk)->tun->dev); } +static int tun_sendmsg(struct kiocb *iocb, struct socket *sock, + struct msghdr *m, size_t total_len) +{ + struct tun_struct *tun = container_of(sock, struct tun_struct, socket); + return tun_get_us...

fre, 27 03 2009 kl. 10:22 +1030, skrev Rusty Russell: > From: Matias Zabaljauregui <zabaljauregui at gmail.com> > > Impact: cleanup > > This patch allow us to use KVM hypercalls Something has broken in relation to this change. I'm not sure it is this change itself or one following, but I get the following error when using lguest: lguest: unhandled trap 6 at 0x418726

fre, 27 03 2009 kl. 10:22 +1030, skrev Rusty Russell: > From: Matias Zabaljauregui <zabaljauregui at gmail.com> > > Impact: cleanup > > This patch allow us to use KVM hypercalls Something has broken in relation to this change. I'm not sure it is this change itself or one following, but I get the following error when using lguest: lguest: unhandled trap 6 at 0x418726

As multi-queue nics were commonly used for high-end servers, current single queue based tap can not satisfy the requirement of scaling guest network performance as the numbers of vcpus increase. So the following series implements multiple queue support in tun/tap. In order to take advantages of this, a multi-queue capable driver and qemu were also needed. I just rebase the latest version of

As multi-queue nics were commonly used for high-end servers, current single queue based tap can not satisfy the requirement of scaling guest network performance as the numbers of vcpus increase. So the following series implements multiple queue support in tun/tap. In order to take advantages of this, a multi-queue capable driver and qemu were also needed. I just rebase the latest version of