Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1321121 > unrolled thread
| Started by | Alex Williamson <alex.williamson@redhat.com> |
|---|---|
| First post | 2016-01-28 23:50 +0100 |
| Last post | 2016-01-29 11:50 +0100 |
| Articles | 2 — 2 participants |
Back to article view | Back to linux.kernel
This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by
below is the oldest one visible, not the original post.
Re: [RFC PATCH v3 5/5] vfio-pci: Allow to mmap MSI-X table if host bridge supports filtering of MSIs Alex Williamson <alex.williamson@redhat.com> - 2016-01-28 23:50 +0100
Re: [RFC PATCH v3 5/5] vfio-pci: Allow to mmap MSI-X table if host bridge supports filtering of MSIs Yongji Xie <xyjxie@linux.vnet.ibm.com> - 2016-01-29 11:50 +0100
| From | Alex Williamson <alex.williamson@redhat.com> |
|---|---|
| Date | 2016-01-28 23:50 +0100 |
| Subject | Re: [RFC PATCH v3 5/5] vfio-pci: Allow to mmap MSI-X table if host bridge supports filtering of MSIs |
| Message-ID | <qW3y1-1JH-9@gated-at.bofh.it> |
On Fri, 2016-01-15 at 15:06 +0800, Yongji Xie wrote:
> Current vfio-pci implementation disallows to mmap MSI-X
> table in case that user get to touch this directly.
>
> But we should allow to mmap these MSI-X tables if the PCI
> host bridge supports filtering of MSIs.
>
> Signed-off-by: Yongji Xie <xyjxie@linux.vnet.ibm.com>
> ---
> drivers/vfio/pci/vfio_pci.c | 6 ++++--
> 1 file changed, 4 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
> index 11fd0f0..4d68f6a 100644
> --- a/drivers/vfio/pci/vfio_pci.c
> +++ b/drivers/vfio/pci/vfio_pci.c
> @@ -555,7 +555,8 @@ static long vfio_pci_ioctl(void *device_data,
> IORESOURCE_MEM && !pci_resources_share_page(pdev,
> info.index)) {
> info.flags |= VFIO_REGION_INFO_FLAG_MMAP;
> - if (info.index == vdev->msix_bar) {
> + if (!pci_host_bridge_msi_filtered_enabled(pdev) &&
> + info.index == vdev->msix_bar) {
> ret = msix_sparse_mmap_cap(vdev, &caps);
> if (ret)
> return ret;
> @@ -967,7 +968,8 @@ static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma)
> if (phys_len < PAGE_SIZE || req_start + req_len > phys_len)
> return -EINVAL;
>
> - if (index == vdev->msix_bar) {
> + if (!pci_host_bridge_msi_filtered_enabled(pdev) &&
> + index == vdev->msix_bar) {
> /*
> * Disallow mmaps overlapping the MSI-X table; users don't
> * get to touch this directly. We could find somewhere
What about read()/write() access, why would we allow mmap() but not
those?
[toc] | [next] | [standalone]
| From | Yongji Xie <xyjxie@linux.vnet.ibm.com> |
|---|---|
| Date | 2016-01-29 11:50 +0100 |
| Message-ID | <qWeMO-1un-7@gated-at.bofh.it> |
| In reply to | #1321121 |
On 2016/1/29 6:46, Alex Williamson wrote:
> On Fri, 2016-01-15 at 15:06 +0800, Yongji Xie wrote:
>> Current vfio-pci implementation disallows to mmap MSI-X
>> table in case that user get to touch this directly.
>>
>> But we should allow to mmap these MSI-X tables if the PCI
>> host bridge supports filtering of MSIs.
>>
>> Signed-off-by: Yongji Xie <xyjxie@linux.vnet.ibm.com>
>> ---
>> drivers/vfio/pci/vfio_pci.c | 6 ++++--
>> 1 file changed, 4 insertions(+), 2 deletions(-)
>>
>> diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
>> index 11fd0f0..4d68f6a 100644
>> --- a/drivers/vfio/pci/vfio_pci.c
>> +++ b/drivers/vfio/pci/vfio_pci.c
>> @@ -555,7 +555,8 @@ static long vfio_pci_ioctl(void *device_data,
>> IORESOURCE_MEM && !pci_resources_share_page(pdev,
>> info.index)) {
>> info.flags |= VFIO_REGION_INFO_FLAG_MMAP;
>> - if (info.index == vdev->msix_bar) {
>> + if (!pci_host_bridge_msi_filtered_enabled(pdev) &&
>> + info.index == vdev->msix_bar) {
>> ret = msix_sparse_mmap_cap(vdev, &caps);
>> if (ret)
>> return ret;
>> @@ -967,7 +968,8 @@ static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma)
>> if (phys_len < PAGE_SIZE || req_start + req_len > phys_len)
>> return -EINVAL;
>>
>> - if (index == vdev->msix_bar) {
>> + if (!pci_host_bridge_msi_filtered_enabled(pdev) &&
>> + index == vdev->msix_bar) {
>> /*
>> * Disallow mmaps overlapping the MSI-X table; users don't
>> * get to touch this directly. We could find somewhere
> What about read()/write() access, why would we allow mmap() but not
> those?
>
Yes, you are right! I miss the MSI-X table check in vfio_pci_bar_rw().
I will fix it in next version. Thanks.
Regards,
Yongji Xie
[toc] | [prev] | [standalone]
Back to top | Article view | linux.kernel
csiph-web