Message-ID: <27e4db66-7df2-16b4-c3d9-982d6ea845b0@redhat.com>
Date:   Fri, 7 Oct 2016 19:11:43 +0200
From:   Auger Eric <eric.auger@...hat.com>
To:     Alex Williamson <alex.williamson@...hat.com>
Cc:     yehuday@...vell.com, drjones@...hat.com, jason@...edaemon.net,
        kvm@...r.kernel.org, marc.zyngier@....com, p.fedin@...sung.com,
        joro@...tes.org, will.deacon@....com, linux-kernel@...r.kernel.org,
        Bharat.Bhushan@...escale.com, Jean-Philippe.Brucker@....com,
        iommu@...ts.linux-foundation.org, pranav.sawargaonkar@...il.com,
        linux-arm-kernel@...ts.infradead.org, tglx@...utronix.de,
        robin.murphy@....com, Manish.Jaggi@...iumnetworks.com,
        christoffer.dall@...aro.org, eric.auger.pro@...il.com
Subject: Re: [PATCH v13 12/15] vfio: Allow reserved msi iova registration

Hi Alex,

On 06/10/2016 22:19, Alex Williamson wrote:
> On Thu,  6 Oct 2016 08:45:28 +0000
> Eric Auger <eric.auger@...hat.com> wrote:
> 
>> The user is allowed to register a reserved MSI IOVA range by using the
>> DMA MAP API and setting the new flag: VFIO_DMA_MAP_FLAG_MSI_RESERVED_IOVA.
>> This region is stored in the vfio_dma rb tree. At that point the iova
>> range is not mapped to any target address yet. The host kernel will use
>> those iova when needed, typically when MSIs are allocated.
>>
>> Signed-off-by: Eric Auger <eric.auger@...hat.com>
>> Signed-off-by: Bharat Bhushan <Bharat.Bhushan@...escale.com>
>>
>> ---
>> v12 -> v13:
>> - use iommu_get_dma_msi_region_cookie
>>
>> v9 -> v10
>> - use VFIO_IOVA_RESERVED_MSI enum value
>>
>> v7 -> v8:
>> - use iommu_msi_set_aperture function. There is no notion of
>>   unregistration anymore since the reserved msi slot remains
>>   until the container gets closed.
>>
>> v6 -> v7:
>> - use iommu_free_reserved_iova_domain
>> - convey prot attributes downto dma-reserved-iommu iova domain creation
>> - reserved bindings teardown now performed on iommu domain destruction
>> - rename VFIO_DMA_MAP_FLAG_MSI_RESERVED_IOVA into
>>          VFIO_DMA_MAP_FLAG_RESERVED_MSI_IOVA
>> - change title
>> - pass the protection attribute to dma-reserved-iommu API
>>
>> v3 -> v4:
>> - use iommu_alloc/free_reserved_iova_domain exported by dma-reserved-iommu
>> - protect vfio_register_reserved_iova_range implementation with
>>   CONFIG_IOMMU_DMA_RESERVED
>> - handle unregistration by user-space and on vfio_iommu_type1 release
>>
>> v1 -> v2:
>> - set returned value according to alloc_reserved_iova_domain result
>> - free the iova domains in case any error occurs
>>
>> RFC v1 -> v1:
>> - takes into account Alex comments, based on
>>   [RFC PATCH 1/6] vfio: Add interface for add/del reserved iova region:
>> - use the existing dma map/unmap ioctl interface with a flag to register
>>   a reserved IOVA range. A single reserved iova region is allowed.
>> ---
>>  drivers/vfio/vfio_iommu_type1.c | 77 ++++++++++++++++++++++++++++++++++++++++-
>>  include/uapi/linux/vfio.h       | 10 +++++-
>>  2 files changed, 85 insertions(+), 2 deletions(-)
>>
>> diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
>> index 5bc5fc9..c2f8bd9 100644
>> --- a/drivers/vfio/vfio_iommu_type1.c
>> +++ b/drivers/vfio/vfio_iommu_type1.c
>> @@ -442,6 +442,20 @@ static void vfio_unmap_unpin(struct vfio_iommu *iommu, struct vfio_dma *dma)
>>  	vfio_lock_acct(-unlocked);
>>  }
>>  
>> +static int vfio_set_msi_aperture(struct vfio_iommu *iommu,
>> +				dma_addr_t iova, size_t size)
>> +{
>> +	struct vfio_domain *d;
>> +	int ret = 0;
>> +
>> +	list_for_each_entry(d, &iommu->domain_list, next) {
>> +		ret = iommu_get_dma_msi_region_cookie(d->domain, iova, size);
>> +		if (ret)
>> +			break;
>> +	}
>> +	return ret;
> 
> Doesn't this need an unwind on failure loop?
At the moment the de-allocation is done by the smmu driver, on
domain_free ops, which calls iommu_put_dma_cookie. In case,
iommu_get_dma_msi_region_cookie fails on a given VFIO domain currently
there is no other way but destroying all VFIO domains and redo everything.

So yes I plan to unfold everything, ie call iommu_put_dma_cookie for
each domain.
> 
>> +}
>> +
>>  static void vfio_remove_dma(struct vfio_iommu *iommu, struct vfio_dma *dma)
>>  {
>>  	vfio_unmap_unpin(iommu, dma);
>> @@ -691,6 +705,63 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,
>>  	return ret;
>>  }
>>  
>> +static int vfio_register_msi_range(struct vfio_iommu *iommu,
>> +				   struct vfio_iommu_type1_dma_map *map)
>> +{
>> +	dma_addr_t iova = map->iova;
>> +	size_t size = map->size;
>> +	int ret = 0;
>> +	struct vfio_dma *dma;
>> +	unsigned long order;
>> +	uint64_t mask;
>> +
>> +	/* Verify that none of our __u64 fields overflow */
>> +	if (map->size != size || map->iova != iova)
>> +		return -EINVAL;
>> +
>> +	order =  __ffs(vfio_pgsize_bitmap(iommu));
>> +	mask = ((uint64_t)1 << order) - 1;
>> +
>> +	WARN_ON(mask & PAGE_MASK);
>> +
>> +	if (!size || (size | iova) & mask)
>> +		return -EINVAL;
>> +
>> +	/* Don't allow IOVA address wrap */
>> +	if (iova + size - 1 < iova)
>> +		return -EINVAL;
>> +
>> +	mutex_lock(&iommu->lock);
>> +
>> +	if (vfio_find_dma(iommu, iova, size, VFIO_IOVA_ANY)) {
>> +		ret =  -EEXIST;
>> +		goto unlock;
>> +	}
>> +
>> +	dma = kzalloc(sizeof(*dma), GFP_KERNEL);
>> +	if (!dma) {
>> +		ret = -ENOMEM;
>> +		goto unlock;
>> +	}
>> +
>> +	dma->iova = iova;
>> +	dma->size = size;
>> +	dma->type = VFIO_IOVA_RESERVED_MSI;
>> +
>> +	ret = vfio_set_msi_aperture(iommu, iova, size);
>> +	if (ret)
>> +		goto free_unlock;
>> +
>> +	vfio_link_dma(iommu, dma);
>> +	goto unlock;
>> +
>> +free_unlock:
>> +	kfree(dma);
>> +unlock:
>> +	mutex_unlock(&iommu->lock);
>> +	return ret;
>> +}
>> +
>>  static int vfio_bus_type(struct device *dev, void *data)
>>  {
>>  	struct bus_type **bus = data;
>> @@ -1064,7 +1135,8 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
>>  	} else if (cmd == VFIO_IOMMU_MAP_DMA) {
>>  		struct vfio_iommu_type1_dma_map map;
>>  		uint32_t mask = VFIO_DMA_MAP_FLAG_READ |
>> -				VFIO_DMA_MAP_FLAG_WRITE;
>> +				VFIO_DMA_MAP_FLAG_WRITE |
>> +				VFIO_DMA_MAP_FLAG_RESERVED_MSI_IOVA;
>>  
>>  		minsz = offsetofend(struct vfio_iommu_type1_dma_map, size);
>>  
>> @@ -1074,6 +1146,9 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
>>  		if (map.argsz < minsz || map.flags & ~mask)
>>  			return -EINVAL;
>>  
>> +		if (map.flags & VFIO_DMA_MAP_FLAG_RESERVED_MSI_IOVA)
>> +			return vfio_register_msi_range(iommu, &map);
>> +
>>  		return vfio_dma_do_map(iommu, &map);
>>  
>>  	} else if (cmd == VFIO_IOMMU_UNMAP_DMA) {
>> diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
>> index 255a211..4a9dbc2 100644
>> --- a/include/uapi/linux/vfio.h
>> +++ b/include/uapi/linux/vfio.h
>> @@ -498,12 +498,19 @@ struct vfio_iommu_type1_info {
>>   *
>>   * Map process virtual addresses to IO virtual addresses using the
>>   * provided struct vfio_dma_map. Caller sets argsz. READ &/ WRITE required.
>> + *
>> + * In case RESERVED_MSI_IOVA flag is set, the API only aims at registering an
>> + * IOVA region that will be used on some platforms to map the host MSI frames.
>> + * In that specific case, vaddr is ignored. Once registered, an MSI reserved
>> + * IOVA region stays until the container is closed.
>>   */
>>  struct vfio_iommu_type1_dma_map {
>>  	__u32	argsz;
>>  	__u32	flags;
>>  #define VFIO_DMA_MAP_FLAG_READ (1 << 0)		/* readable from device */
>>  #define VFIO_DMA_MAP_FLAG_WRITE (1 << 1)	/* writable from device */
>> +/* reserved iova for MSI vectors*/
>> +#define VFIO_DMA_MAP_FLAG_RESERVED_MSI_IOVA (1 << 2)
>>  	__u64	vaddr;				/* Process virtual address */
>>  	__u64	iova;				/* IO virtual address */
>>  	__u64	size;				/* Size of mapping (bytes) */
>> @@ -519,7 +526,8 @@ struct vfio_iommu_type1_dma_map {
>>   * Caller sets argsz.  The actual unmapped size is returned in the size
>>   * field.  No guarantee is made to the user that arbitrary unmaps of iova
>>   * or size different from those used in the original mapping call will
>> - * succeed.
>> + * succeed. Once registered, an MSI region cannot be unmapped and stays
>> + * until the container is closed.
>>   */
>>  struct vfio_iommu_type1_dma_unmap {
>>  	__u32	argsz;
> 
> What happens when an x86 user does a mapping with this new flag set?
> It seems like we end up configuring everything just as we would on a
> platform requiring MSI mapping, including setting the domain MSI
> geometry.  Should we be testing the MSI geometry flag on the iommu to
> see if this is supported?  Surprisingly few things seem to check that
> flag.

Yes I need to test the capability first and return -EINVAL in case the
capability is not supported..

Thanks

Eric
> 
> _______________________________________________
> linux-arm-kernel mailing list
> linux-arm-kernel@...ts.infradead.org
> http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
> 

Powered by blists - more mailing lists