Re: [PATCH v3 5/5] iommu/hyperv: Add page-selective IOTLB flush support

[Jacob Pan <jacob.pan@linux.microsoft.com>]

Hi Yu,

On Tue, 11 Aug 2026 23:50:21 +0800
Yu Zhang <zhangyu1@linux.microsoft.com> wrote:

> Add page-selective IOTLB flush using HVCALL_FLUSH_DEVICE_DOMAIN_LIST.
> This hypercall accepts a list of (page_number, page_mask_shift)
> entries, enabling finer-grained IOTLB invalidation compared to the
> domain-wide HVCALL_FLUSH_DEVICE_DOMAIN used by
> hv_iommu_flush_iotlb_all().
> 
> hv_iommu_calc_flush_range() computes the smallest power-of-two aligned
> range that covers the target IOVA region, producing a single flush
> descriptor. This may over-flush when the range is not naturally
> aligned, matching the approach used by Intel VT-d PSI. If the
> page-selective flush fails, the code falls back to a full domain
> flush.
> 
> Signed-off-by: Easwar Hariharan <easwar.hariharan@linux.microsoft.com>
> Signed-off-by: Yu Zhang <zhangyu1@linux.microsoft.com>
> ---
>  drivers/iommu/hyperv/hv-iommu-guest.c | 73
> ++++++++++++++++++++++++++- include/hyperv/hvgdk_mini.h           |
> 1 + include/hyperv/hvhdk_mini.h           | 17 +++++++
>  3 files changed, 90 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/iommu/hyperv/hv-iommu-guest.c
> b/drivers/iommu/hyperv/hv-iommu-guest.c index
> 2a00353ce733..060c2efd6bf0 100644 ---
> a/drivers/iommu/hyperv/hv-iommu-guest.c +++
> b/drivers/iommu/hyperv/hv-iommu-guest.c @@ -9,6 +9,7 @@
>  #define pr_fmt(fmt) "Hyper-V pvIOMMU: " fmt
>  #define dev_fmt(fmt) pr_fmt(fmt)
>  
> +#include <linux/hyperv.h>
why need this?

>  #include <linux/iommu.h>
>  #include <linux/pci.h>
>  #include <linux/dma-map-ops.h>
> @@ -408,10 +409,79 @@ static void hv_iommu_flush_iotlb_all(struct
> iommu_domain *domain)
> hv_flush_device_domain(to_hv_iommu_domain(domain)); }
>  
> +/*
> + * Calculate the minimal power-of-two aligned range that covers
> [start, end]
> + * (end is inclusive). Returns a single (page_number,
> page_mask_shift)
> + * descriptor that may over-flush when the range is not naturally
> aligned.
> + */
> +static void
> +hv_iommu_calc_flush_range(unsigned long start, unsigned long end,
> +			  union hv_iommu_flush_va *va)
> +{
> +	unsigned int sz_lg2;
> +
> +	sz_lg2 = fls_long(start ^ end);
> +	if (sz_lg2 < HV_HYP_PAGE_SHIFT)
> +		sz_lg2 = HV_HYP_PAGE_SHIFT;
> +
> +	/*
> +	 * A valid IOVA range shall not span bit 63. Use the maximum
> mask
> +	 * so the host can safely perform a full flush.
> +	 */
> +	if (WARN_ON_ONCE(sz_lg2 >= BITS_PER_LONG)) {
> +		va->as_uint64 = 0;
> +		va->page_mask_shift =
> +			BITS_PER_LONG - HV_HYP_PAGE_SHIFT;
> +		return;
> +	}
> +
> +	va->page_number =
> +		(start & GENMASK(BITS_PER_LONG - 1, sz_lg2)) >>
> +		HV_HYP_PAGE_SHIFT;
> +	va->page_mask_shift = sz_lg2 - HV_HYP_PAGE_SHIFT;
> +}
> +
> +static void hv_flush_device_domain_list(struct hv_iommu_domain
> *hv_domain,
> +					struct iommu_iotlb_gather
> *iotlb_gather) +{
> +	u64 status;
> +	unsigned long flags;
> +	struct hv_input_flush_device_domain_list *input;
> +
> +	local_irq_save(flags);
> +
> +	input = *this_cpu_ptr(hyperv_pcpu_input_arg);
> +	/* Clear the fixed header and the single range entry. */
> +	memset(input, 0, struct_size(input, iova_list, 1));
> +
> +	input->device_domain = hv_domain->device_domain;
> +	input->flags |= HV_FLUSH_DEVICE_DOMAIN_LIST_IOMMU_FORMAT;
> +	hv_iommu_calc_flush_range(iotlb_gather->start,
> iotlb_gather->end,
> +				  &input->iova_list[0]);
> +
> +	status = hv_do_rep_hypercall(HVCALL_FLUSH_DEVICE_DOMAIN_LIST,
> +				     1, 0, input, NULL);
> +
> +	if (WARN_ON_ONCE(!hv_result_success(status))) {
> +		/* Page-selective flush failed, fall back to full
> flush. */
> +		struct hv_input_flush_device_domain *flush_all =
> (void *)input; +
> +		memset(flush_all, 0, sizeof(*flush_all));
> +		flush_all->device_domain = hv_domain->device_domain;
> +		status = hv_do_hypercall(HVCALL_FLUSH_DEVICE_DOMAIN,
> +					 flush_all, NULL);
> +		WARN(!hv_result_success(status),
> +		     "HVCALL_FLUSH_DEVICE_DOMAIN fallback also
> failed: %lld\n",
> +		     status);
> +	}
> +
> +	local_irq_restore(flags);
> +}
> +
>  static void hv_iommu_iotlb_sync(struct iommu_domain *domain,
>  				struct iommu_iotlb_gather
> *iotlb_gather) {
> -	hv_flush_device_domain(to_hv_iommu_domain(domain));
> +	hv_flush_device_domain_list(to_hv_iommu_domain(domain),
> iotlb_gather); 
>  	iommu_put_pages_list(&iotlb_gather->freelist);
Maybe add a comment explaining that HVCALL_FLUSH_DEVICE_DOMAIN_LIST
covers non-leaf/walk caches, therefore it is safe to put freelist.

>  }
> @@ -464,6 +534,7 @@ static struct iommu_domain
> *hv_iommu_domain_alloc_paging(struct device *dev) 
>  	cfg.common.hw_max_vasz_lg2 = hv_iommu_device->max_iova_width;
>  	cfg.common.hw_max_oasz_lg2 = 52;
> +	cfg.common.features |= BIT(PT_FEAT_FLUSH_RANGE);
>  	/*
>  	 * Hyper-V S1 domains use a 4-level root for IOVA widths up
> to
>  	 * 48 bits. A 5-level root is used only for wider apertures
> when diff --git a/include/hyperv/hvgdk_mini.h
> b/include/hyperv/hvgdk_mini.h index 5bdbb44da112..eaaf87171478 100644
> --- a/include/hyperv/hvgdk_mini.h
> +++ b/include/hyperv/hvgdk_mini.h
> @@ -496,6 +496,7 @@ union hv_vp_assist_msr_contents {	 /*
> HV_REGISTER_VP_ASSIST_PAGE */ #define
> HVCALL_GET_GPA_PAGES_ACCESS_STATES		0x00c9 #define
> HVCALL_CONFIGURE_DEVICE_DOMAIN			0x00ce #define
> HVCALL_FLUSH_DEVICE_DOMAIN			0x00d0 +#define
> HVCALL_FLUSH_DEVICE_DOMAIN_LIST			0x00d1 #define
> HVCALL_ACQUIRE_SPARSE_SPA_PAGE_HOST_ACCESS	0x00d7 #define
> HVCALL_RELEASE_SPARSE_SPA_PAGE_HOST_ACCESS	0x00d8 #define
> HVCALL_MODIFY_SPARSE_GPA_PAGE_HOST_VISIBILITY	0x00db diff
> --git a/include/hyperv/hvhdk_mini.h b/include/hyperv/hvhdk_mini.h
> index 1e3eac99886a..25671ee7056d 100644 ---
> a/include/hyperv/hvhdk_mini.h +++ b/include/hyperv/hvhdk_mini.h
> @@ -674,4 +674,21 @@ struct hv_input_flush_device_domain {
>  	u32 reserved;
>  } __packed;
>  
> +union hv_iommu_flush_va {
> +	u64 as_uint64;
> +	struct {
> +		u64 page_mask_shift : 6;
> +		u64 reserved : 6;
> +		u64 page_number : 52;
> +	};
> +} __packed;
> +
> +struct hv_input_flush_device_domain_list {
> +	struct hv_input_device_domain device_domain;
> +#define HV_FLUSH_DEVICE_DOMAIN_LIST_IOMMU_FORMAT BIT(0)
> +	u32 flags;
> +	u32 reserved;
> +	union hv_iommu_flush_va iova_list[];
> +} __packed;
> +
>  #endif /* _HV_HVHDK_MINI_H */

Reviewed-by: Jacob Pan <jacob.pan@linux.microsoft.com>