Re: [PATCH 09/14] iommu/vt-d: preserve PASID table of preserved device

[Pranjal Shrivastava]

On Tue, Feb 03, 2026 at 10:09:43PM +0000, Samiullah Khawaja wrote:
> In scalable mode the PASID table is used to fetch the io page tables.
> Preserve and restore the PASID table of the preserved devices.
> 
> Signed-off-by: Samiullah Khawaja <skhawaja@xxxxxxxxxx>
> ---
>  drivers/iommu/intel/iommu.c      |   4 +-
>  drivers/iommu/intel/iommu.h      |   5 ++
>  drivers/iommu/intel/liveupdate.c | 130 +++++++++++++++++++++++++++++++
>  drivers/iommu/intel/pasid.c      |   7 +-
>  drivers/iommu/intel/pasid.h      |   9 +++
>  include/linux/kho/abi/iommu.h    |   8 ++
>  6 files changed, 160 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
> index 83faad53f247..2d0dae57f5a2 100644
> --- a/drivers/iommu/intel/iommu.c
> +++ b/drivers/iommu/intel/iommu.c
> @@ -2944,8 +2944,10 @@ static bool __maybe_clean_unpreserved_context_entries(struct intel_iommu *iommu)
>  		if (info->iommu != iommu)
>  			continue;
>  
> -		if (dev_iommu_preserved_state(&pdev->dev))
> +		if (dev_iommu_preserved_state(&pdev->dev)) {
> +			pasid_cleanup_preserved_table(&pdev->dev);
>  			continue;
> +		}
>  
>  		domain_context_clear(info);
>  	}
> diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h
> index 057bd6035d85..d24d6aeaacc0 100644
> --- a/drivers/iommu/intel/iommu.h
> +++ b/drivers/iommu/intel/iommu.h
> @@ -1286,6 +1286,7 @@ int intel_iommu_preserve(struct iommu_device *iommu, struct iommu_ser *iommu_ser
>  void intel_iommu_unpreserve(struct iommu_device *iommu, struct iommu_ser *iommu_ser);
>  void intel_iommu_liveupdate_restore_root_table(struct intel_iommu *iommu,
>  					       struct iommu_ser *iommu_ser);
> +void pasid_cleanup_preserved_table(struct device *dev);
>  #else
>  static inline int intel_iommu_preserve_device(struct device *dev, struct device_ser *device_ser)
>  {
> @@ -1309,6 +1310,10 @@ static inline void intel_iommu_liveupdate_restore_root_table(struct intel_iommu
>  							     struct iommu_ser *iommu_ser)
>  {
>  }
> +
> +static inline void pasid_cleanup_preserved_table(struct device *dev)
> +{
> +}
>  #endif
>  
>  #ifdef CONFIG_INTEL_IOMMU_SVM
> diff --git a/drivers/iommu/intel/liveupdate.c b/drivers/iommu/intel/liveupdate.c
> index 6dcb5783d1db..53bb5fe3a764 100644
> --- a/drivers/iommu/intel/liveupdate.c
> +++ b/drivers/iommu/intel/liveupdate.c
> @@ -14,6 +14,7 @@
>  #include <linux/pci.h>
>  
>  #include "iommu.h"
> +#include "pasid.h"
>  #include "../iommu-pages.h"
>  
>  static void unpreserve_iommu_context(struct intel_iommu *iommu, int end)
> @@ -113,9 +114,89 @@ void intel_iommu_liveupdate_restore_root_table(struct intel_iommu *iommu,
>  		iommu->reg_phys, iommu_ser->intel.root_table);
>  }
>  
> +enum pasid_lu_op {
> +	PASID_LU_OP_PRESERVE = 1,
> +	PASID_LU_OP_UNPRESERVE,
> +	PASID_LU_OP_RESTORE,
> +	PASID_LU_OP_FREE,
> +};
> +
> +static int pasid_lu_do_op(void *table, enum pasid_lu_op op)
> +{
> +	int ret = 0;
> +
> +	switch (op) {
> +	case PASID_LU_OP_PRESERVE:
> +		ret = iommu_preserve_page(table);
> +		break;
> +	case PASID_LU_OP_UNPRESERVE:
> +		iommu_unpreserve_page(table);
> +		break;
> +	case PASID_LU_OP_RESTORE:
> +		iommu_restore_page(virt_to_phys(table));
> +		break;
> +	case PASID_LU_OP_FREE:
> +		iommu_free_pages(table);
> +		break;
> +	}
> +
> +	return ret;
> +}
> +
> +static int pasid_lu_handle_pd(struct pasid_dir_entry *dir, enum pasid_lu_op op)
> +{
> +	struct pasid_entry *table;
> +	int ret;
> +
> +	/* Only preserve first table for NO_PASID. */
> +	table = get_pasid_table_from_pde(&dir[0]);
> +	if (!table)
> +		return -EINVAL;
> +
> +	ret = pasid_lu_do_op(table, op);
> +	if (ret)
> +		return ret;
> +
> +	ret = pasid_lu_do_op(dir, op);
> +	if (ret)
> +		goto err;
> +
> +	return 0;
> +err:
> +	if (op == PASID_LU_OP_PRESERVE)
> +		pasid_lu_do_op(table, PASID_LU_OP_UNPRESERVE);
> +
> +	return ret;
> +}
> +
> +void pasid_cleanup_preserved_table(struct device *dev)
> +{
> +	struct pasid_table *pasid_table;
> +	struct pasid_dir_entry *dir;
> +	struct pasid_entry *table;
> +
> +	pasid_table = intel_pasid_get_table(dev);
> +	if (!pasid_table)
> +		return;
> +
> +	dir = pasid_table->table;
> +	table = get_pasid_table_from_pde(&dir[0]);
> +	if (!table)
> +		return;
> +
> +	/* Cleanup everything except the first entry. */
> +	memset(&table[1], 0, SZ_4K - sizeof(*table));
> +	memset(&dir[1], 0, SZ_4K - sizeof(struct pasid_dir_entry));

(Not too familiar with Intel IOMMU / VT-d)
We seem to hardcode SZ_4K when clearing the directory entries. But in
intel_pasid_alloc_table(), the allocation size seems to depend on
max_pasid which could be larger than one page (order > 0)?

If the directory is multi-page, won't we leave the trailing pages
and full of stale PDE pointers that the HW could still walk?

> +
> +	clflush_cache_range(&table[0], SZ_4K);
> +	clflush_cache_range(&dir[0], SZ_4K);
> +}
> +

[ ------ >8 ------ ]

Thanks,
Praan