linux-kernel - Re: [PATCH v8 26/29] vfio-pci: Register an iommu fault handler

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: <20190603163139.70fe8839@x1.home>
Date:   Mon, 3 Jun 2019 16:31:39 -0600
From:   Alex Williamson <alex.williamson@...hat.com>
To:     Eric Auger <eric.auger@...hat.com>
Cc:     eric.auger.pro@...il.com, iommu@...ts.linux-foundation.org,
        linux-kernel@...r.kernel.org, kvm@...r.kernel.org,
        kvmarm@...ts.cs.columbia.edu, joro@...tes.org,
        jacob.jun.pan@...ux.intel.com, yi.l.liu@...el.com,
        jean-philippe.brucker@....com, will.deacon@....com,
        robin.murphy@....com, kevin.tian@...el.com, ashok.raj@...el.com,
        marc.zyngier@....com, peter.maydell@...aro.org,
        vincent.stehle@....com
Subject: Re: [PATCH v8 26/29] vfio-pci: Register an iommu fault handler

On Sun, 26 May 2019 18:10:01 +0200
Eric Auger <eric.auger@...hat.com> wrote:

> This patch registers a fault handler which records faults in
> a circular buffer and then signals an eventfd. This buffer is
> exposed within the fault region.
> 
> Signed-off-by: Eric Auger <eric.auger@...hat.com>
> 
> ---
> 
> v3 -> v4:
> - move iommu_unregister_device_fault_handler to vfio_pci_release
> ---
>  drivers/vfio/pci/vfio_pci.c         | 49 +++++++++++++++++++++++++++++
>  drivers/vfio/pci/vfio_pci_private.h |  1 +
>  2 files changed, 50 insertions(+)
> 
> diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
> index f75f61127277..520999994ba8 100644
> --- a/drivers/vfio/pci/vfio_pci.c
> +++ b/drivers/vfio/pci/vfio_pci.c
> @@ -30,6 +30,7 @@
>  #include <linux/vfio.h>
>  #include <linux/vgaarb.h>
>  #include <linux/nospec.h>
> +#include <linux/circ_buf.h>
>  
>  #include "vfio_pci_private.h"
>  
> @@ -296,6 +297,46 @@ static const struct vfio_pci_regops vfio_pci_fault_prod_regops = {
>  	.add_capability = vfio_pci_fault_prod_add_capability,
>  };
>  
> +int vfio_pci_iommu_dev_fault_handler(struct iommu_fault_event *evt, void *data)
> +{
> +	struct vfio_pci_device *vdev = (struct vfio_pci_device *) data;
> +	struct vfio_region_fault_prod *prod_region =
> +		(struct vfio_region_fault_prod *)vdev->fault_pages;
> +	struct vfio_region_fault_cons *cons_region =
> +		(struct vfio_region_fault_cons *)(vdev->fault_pages + 2 * PAGE_SIZE);
> +	struct iommu_fault *new =
> +		(struct iommu_fault *)(vdev->fault_pages + prod_region->offset +
> +			prod_region->prod * prod_region->entry_size);
> +	int prod, cons, size;
> +
> +	mutex_lock(&vdev->fault_queue_lock);
> +
> +	if (!vdev->fault_abi)
> +		goto unlock;
> +
> +	prod = prod_region->prod;
> +	cons = cons_region->cons;
> +	size = prod_region->nb_entries;
> +
> +	if (CIRC_SPACE(prod, cons, size) < 1)
> +		goto unlock;
> +
> +	*new = evt->fault;
> +	prod = (prod + 1) % size;
> +	prod_region->prod = prod;
> +	mutex_unlock(&vdev->fault_queue_lock);
> +
> +	mutex_lock(&vdev->igate);
> +	if (vdev->dma_fault_trigger)
> +		eventfd_signal(vdev->dma_fault_trigger, 1);
> +	mutex_unlock(&vdev->igate);
> +	return 0;
> +
> +unlock:
> +	mutex_unlock(&vdev->fault_queue_lock);
> +	return -EINVAL;
> +}
> +
>  static int vfio_pci_init_fault_region(struct vfio_pci_device *vdev)
>  {
>  	struct vfio_region_fault_prod *header;
> @@ -328,6 +369,13 @@ static int vfio_pci_init_fault_region(struct vfio_pci_device *vdev)
>  	header = (struct vfio_region_fault_prod *)vdev->fault_pages;
>  	header->version = -1;
>  	header->offset = PAGE_SIZE;
> +
> +	ret = iommu_register_device_fault_handler(&vdev->pdev->dev,
> +					vfio_pci_iommu_dev_fault_handler,
> +					vdev);
> +	if (ret)
> +		goto out;
> +
>  	return 0;
>  out:
>  	kfree(vdev->fault_pages);
> @@ -570,6 +618,7 @@ static void vfio_pci_release(void *device_data)
>  	if (!(--vdev->refcnt)) {
>  		vfio_spapr_pci_eeh_release(vdev->pdev);
>  		vfio_pci_disable(vdev);
> +		iommu_unregister_device_fault_handler(&vdev->pdev->dev);


But this can fail if there are pending faults which leaves a device
reference and then the system is broken :(

>  	}
>  
>  	mutex_unlock(&vdev->reflck->lock);
> diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h
> index 8e0a55682d3f..a9276926f008 100644
> --- a/drivers/vfio/pci/vfio_pci_private.h
> +++ b/drivers/vfio/pci/vfio_pci_private.h
> @@ -122,6 +122,7 @@ struct vfio_pci_device {
>  	int			ioeventfds_nr;
>  	struct eventfd_ctx	*err_trigger;
>  	struct eventfd_ctx	*req_trigger;
> +	struct eventfd_ctx	*dma_fault_trigger;
>  	struct mutex		fault_queue_lock;
>  	int			fault_abi;
>  	struct list_head	dummy_resources_list;