RE: [PATCH V10 11/11] iommu/vt-d: Add custom allocator for IOASID

[Tian, Kevin]

> From: Jacob Pan <jacob.jun.pan@xxxxxxxxxxxxxxx>
> Sent: Saturday, March 21, 2020 7:28 AM
> 
> When VT-d driver runs in the guest, PASID allocation must be
> performed via virtual command interface. This patch registers a
> custom IOASID allocator which takes precedence over the default
> XArray based allocator. The resulting IOASID allocation will always
> come from the host. This ensures that PASID namespace is system-
> wide.
> 
> Signed-off-by: Lu Baolu <baolu.lu@xxxxxxxxxxxxxxx>
> Signed-off-by: Liu, Yi L <yi.l.liu@xxxxxxxxx>
> Signed-off-by: Jacob Pan <jacob.jun.pan@xxxxxxxxxxxxxxx>
> ---
>  drivers/iommu/intel-iommu.c | 84
> +++++++++++++++++++++++++++++++++++++++++++++
>  include/linux/intel-iommu.h |  2 ++
>  2 files changed, 86 insertions(+)
> 
> diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
> index a76afb0fd51a..c1c0b0fb93c3 100644
> --- a/drivers/iommu/intel-iommu.c
> +++ b/drivers/iommu/intel-iommu.c
> @@ -1757,6 +1757,9 @@ static void free_dmar_iommu(struct intel_iommu
> *iommu)
>  		if (ecap_prs(iommu->ecap))
>  			intel_svm_finish_prq(iommu);
>  	}
> +	if (ecap_vcs(iommu->ecap) && vccap_pasid(iommu->vccap))
> +		ioasid_unregister_allocator(&iommu->pasid_allocator);
> +
>  #endif
>  }
> 
> @@ -3291,6 +3294,84 @@ static int copy_translation_tables(struct
> intel_iommu *iommu)
>  	return ret;
>  }
> 
> +#ifdef CONFIG_INTEL_IOMMU_SVM
> +static ioasid_t intel_ioasid_alloc(ioasid_t min, ioasid_t max, void *data)

the name is too generic... can we add vcmd in the name to clarify
its purpose, e.g. intel_vcmd_ioasid_alloc?

> +{
> +	struct intel_iommu *iommu = data;
> +	ioasid_t ioasid;
> +
> +	if (!iommu)
> +		return INVALID_IOASID;
> +	/*
> +	 * VT-d virtual command interface always uses the full 20 bit
> +	 * PASID range. Host can partition guest PASID range based on
> +	 * policies but it is out of guest's control.
> +	 */
> +	if (min < PASID_MIN || max > intel_pasid_max_id)
> +		return INVALID_IOASID;
> +
> +	if (vcmd_alloc_pasid(iommu, &ioasid))
> +		return INVALID_IOASID;
> +
> +	return ioasid;
> +}
> +
> +static void intel_ioasid_free(ioasid_t ioasid, void *data)
> +{
> +	struct intel_iommu *iommu = data;
> +
> +	if (!iommu)
> +		return;
> +	/*
> +	 * Sanity check the ioasid owner is done at upper layer, e.g. VFIO
> +	 * We can only free the PASID when all the devices are unbound.
> +	 */
> +	if (ioasid_find(NULL, ioasid, NULL)) {
> +		pr_alert("Cannot free active IOASID %d\n", ioasid);
> +		return;
> +	}

However the sanity check is not done in default_free. Is there a reason
why using vcmd adds such  new requirement?

> +	vcmd_free_pasid(iommu, ioasid);
> +}
> +
> +static void register_pasid_allocator(struct intel_iommu *iommu)
> +{
> +	/*
> +	 * If we are running in the host, no need for custom allocator
> +	 * in that PASIDs are allocated from the host system-wide.
> +	 */
> +	if (!cap_caching_mode(iommu->cap))
> +		return;

is it more accurate to check against vcmd capability?

> +
> +	if (!sm_supported(iommu)) {
> +		pr_warn("VT-d Scalable Mode not enabled, no PASID
> allocation\n");
> +		return;
> +	}
> +
> +	/*
> +	 * Register a custom PASID allocator if we are running in a guest,
> +	 * guest PASID must be obtained via virtual command interface.
> +	 * There can be multiple vIOMMUs in each guest but only one
> allocator
> +	 * is active. All vIOMMU allocators will eventually be calling the same

which one? the first or last?

> +	 * host allocator.
> +	 */
> +	if (ecap_vcs(iommu->ecap) && vccap_pasid(iommu->vccap)) {
> +		pr_info("Register custom PASID allocator\n");
> +		iommu->pasid_allocator.alloc = intel_ioasid_alloc;
> +		iommu->pasid_allocator.free = intel_ioasid_free;
> +		iommu->pasid_allocator.pdata = (void *)iommu;
> +		if (ioasid_register_allocator(&iommu->pasid_allocator)) {
> +			pr_warn("Custom PASID allocator failed, scalable
> mode disabled\n");
> +			/*
> +			 * Disable scalable mode on this IOMMU if there
> +			 * is no custom allocator. Mixing SM capable
> vIOMMU
> +			 * and non-SM vIOMMU are not supported.
> +			 */
> +			intel_iommu_sm = 0;

since you register an allocator for every vIOMMU, means previously
registered allocators should also be unregistered here?

> +		}
> +	}
> +}
> +#endif
> +
>  static int __init init_dmars(void)
>  {
>  	struct dmar_drhd_unit *drhd;
> @@ -3408,6 +3489,9 @@ static int __init init_dmars(void)
>  	 */
>  	for_each_active_iommu(iommu, drhd) {
>  		iommu_flush_write_buffer(iommu);
> +#ifdef CONFIG_INTEL_IOMMU_SVM
> +		register_pasid_allocator(iommu);
> +#endif
>  		iommu_set_root_entry(iommu);
>  		iommu->flush.flush_context(iommu, 0, 0, 0,
> DMA_CCMD_GLOBAL_INVL);
>  		iommu->flush.flush_iotlb(iommu, 0, 0, 0,
> DMA_TLB_GLOBAL_FLUSH);
> diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
> index 9cbf5357138b..9c357a325c72 100644
> --- a/include/linux/intel-iommu.h
> +++ b/include/linux/intel-iommu.h
> @@ -19,6 +19,7 @@
>  #include <linux/iommu.h>
>  #include <linux/io-64-nonatomic-lo-hi.h>
>  #include <linux/dmar.h>
> +#include <linux/ioasid.h>
> 
>  #include <asm/cacheflush.h>
>  #include <asm/iommu.h>
> @@ -563,6 +564,7 @@ struct intel_iommu {
>  #ifdef CONFIG_INTEL_IOMMU_SVM
>  	struct page_req_dsc *prq;
>  	unsigned char prq_name[16];    /* Name for PRQ interrupt */
> +	struct ioasid_allocator_ops pasid_allocator; /* Custom allocator for
> PASIDs */
>  #endif
>  	struct q_inval  *qi;            /* Queued invalidation info */
>  	u32 *iommu_state; /* Store iommu states between suspend and
> resume.*/
> --
> 2.7.4