linux-kernel - Re: vhost changes (batched) in linux-next after 12/13 trigger random crashes in KVM guests after reboot

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <2dc1df65-1431-3917-40e5-c2b12096e2a7@de.ibm.com>
Date:   Thu, 13 Feb 2020 17:32:59 +0100
From:   Christian Borntraeger <borntraeger@...ibm.com>
To:     Eugenio Pérez <eperezma@...hat.com>
Cc:     "Michael S. Tsirkin" <mst@...hat.com>,
        "virtualization@...ts.linux-foundation.org" 
        <virtualization@...ts.linux-foundation.org>,
        Stephen Rothwell <sfr@...b.auug.org.au>,
        Linux Next Mailing List <linux-next@...r.kernel.org>,
        "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
        kvm list <kvm@...r.kernel.org>,
        Halil Pasic <pasic@...ux.ibm.com>,
        Cornelia Huck <cohuck@...hat.com>
Subject: Re: vhost changes (batched) in linux-next after 12/13 trigger random
 crashes in KVM guests after reboot



On 13.02.20 17:29, Eugenio Pérez wrote:
> Can we try with this traces?

Does not apply on eccb852f1fe6bede630e2e4f1a121a81e34354ab, can you double check?

> 
> From b793b4106085ab1970bdedb340e49f37843ed585 Mon Sep 17 00:00:00 2001
> From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= <eperezma@...hat.com>
> Date: Thu, 13 Feb 2020 17:27:05 +0100
> Subject: [PATCH] vhost: Add debug in ioctl calls
> 
> ---
>  drivers/vhost/net.c   | 20 +++++++++++++++++---
>  drivers/vhost/vhost.c | 16 ++++++++++++++--
>  2 files changed, 31 insertions(+), 5 deletions(-)
> 
> diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
> index e158159671fa..e4d5f843f9c0 100644
> --- a/drivers/vhost/net.c
> +++ b/drivers/vhost/net.c
> @@ -1505,10 +1505,13 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
>  
>  	mutex_lock(&n->dev.mutex);
>  	r = vhost_dev_check_owner(&n->dev);
> -	if (r)
> +	if (r) {
> +		pr_debug("vhost_dev_check_owner index=%u fd=%d rc r=%d", index, fd, r);
>  		goto err;
> +	}
>  
>  	if (index >= VHOST_NET_VQ_MAX) {
> +		pr_debug("vhost_dev_check_owner index=%u fd=%d MAX=%d", index, fd, VHOST_NET_VQ_MAX);
>  		r = -ENOBUFS;
>  		goto err;
>  	}
> @@ -1518,22 +1521,26 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
>  
>  	/* Verify that ring has been setup correctly. */
>  	if (!vhost_vq_access_ok(vq)) {
> +		pr_debug("vhost_net_set_backend index=%u fd=%d !vhost_vq_access_ok", index, fd);
>  		r = -EFAULT;
>  		goto err_vq;
>  	}
>  	sock = get_socket(fd);
>  	if (IS_ERR(sock)) {
>  		r = PTR_ERR(sock);
> +		pr_debug("vhost_net_set_backend index=%u fd=%d get_socket err r=%d", index, fd, r);
>  		goto err_vq;
>  	}
>  
>  	/* start polling new socket */
>  	oldsock = vq->private_data;
>  	if (sock != oldsock) {
> +		pr_debug("sock=%p != oldsock=%p index=%u fd=%d vq=%p", sock, oldsock, index, fd, vq);
>  		ubufs = vhost_net_ubuf_alloc(vq,
>  					     sock && vhost_sock_zcopy(sock));
>  		if (IS_ERR(ubufs)) {
>  			r = PTR_ERR(ubufs);
> +			pr_debug("ubufs index=%u fd=%d err r=%d vq=%p", index, fd, r, vq);
>  			goto err_ubufs;
>  		}
>  
> @@ -1541,11 +1548,15 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
>  		vq->private_data = sock;
>  		vhost_net_buf_unproduce(nvq);
>  		r = vhost_vq_init_access(vq);
> -		if (r)
> +		if (r) {
> +			pr_debug("init_access index=%u fd=%d r=%d vq=%p", index, fd, r, vq);
>  			goto err_used;
> +		}
>  		r = vhost_net_enable_vq(n, vq);
> -		if (r)
> +		if (r) {
> +			pr_debug("enable_vq index=%u fd=%d r=%d vq=%p", index, fd, r, vq);
>  			goto err_used;
> +		}
>  		if (index == VHOST_NET_VQ_RX)
>  			nvq->rx_ring = get_tap_ptr_ring(fd);
>  
> @@ -1559,6 +1570,8 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
>  
>  	mutex_unlock(&vq->mutex);
>  
> +	pr_debug("sock=%p", sock);
> +
>  	if (oldubufs) {
>  		vhost_net_ubuf_put_wait_and_free(oldubufs);
>  		mutex_lock(&vq->mutex);
> @@ -1710,6 +1723,7 @@ static long vhost_net_ioctl(struct file *f, unsigned int ioctl,
>  
>  	switch (ioctl) {
>  	case VHOST_NET_SET_BACKEND:
> +		pr_debug("VHOST_NET_SET_BACKEND");
>  		if (copy_from_user(&backend, argp, sizeof backend))
>  			return -EFAULT;
>  		return vhost_net_set_backend(n, backend.index, backend.fd);
> diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
> index 021d70bed015..7f4848f9cec3 100644
> --- a/drivers/vhost/vhost.c
> +++ b/drivers/vhost/vhost.c
> @@ -1642,18 +1642,30 @@ long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *arg
>  			r = -EINVAL;
>  			break;
>  		}
> +
> +		if (vq->last_avail_idx || vq->avail_idx) {
> +			pr_debug(
> +				"strange VHOST_SET_VRING_BASE [vq=%p][s.index=%u][s.num=%u]",
> +				vq, s.index, s.num);
> +			dump_stack();
> +			r = 0;
> +			break;
> +		}
>  		vq->last_avail_idx = s.num;
>  		/* Forget the cached index value. */
>  		vq->avail_idx = vq->last_avail_idx;
>  		pr_debug(
> -			"VHOST_SET_VRING_BASE [vq=%p][vq->last_avail_idx=%u][vq->avail_idx=%u]",
> -			vq, vq->last_avail_idx, vq->avail_idx);
> +			"VHOST_SET_VRING_BASE [vq=%p][vq->last_avail_idx=%u][vq->avail_idx=%u][s.index=%u][s.num=%u]",
> +			vq, vq->last_avail_idx, vq->avail_idx, s.index, s.num);
>  		break;
>  	case VHOST_GET_VRING_BASE:
>  		s.index = idx;
>  		s.num = vq->last_avail_idx;
>  		if (copy_to_user(argp, &s, sizeof s))
>  			r = -EFAULT;
> +		pr_debug(
> +			"VHOST_GET_VRING_BASE [vq=%p][vq->last_avail_idx=%u][vq->avail_idx=%u][s.index=%u][s.num=%u]",
> +			vq, vq->last_avail_idx, vq->avail_idx, s.index, s.num);
>  		break;
>  	case VHOST_SET_VRING_KICK:
>  		if (copy_from_user(&f, argp, sizeof f)) {
>