Re: [PATCH 18/24] iommu/amd: Introduce helper function for updating device ID mapping table

["guanghuifeng@linux.alibaba.com" <guanghuifeng@linux.alibaba.com>]

在 2026/7/27 21:29, Suravee Suthikulpanit 写道:
> AMD vIOMMU hardware uses the Device ID mapping table to map Guest Device ID
> (GDevID) to Host Device ID when it virtualises guest IOMMU commands.
> It uses GID and GDevID to indexe into the table to look up host device ID.
>
> Linux IOMMU driver programs the table entry using VFCntlMMIO Guest Device
> Map Control Register.
>
> Introduce amd_viommu_set/clear_device_mapping(), which are used to set
> the entry when initialize the IOMMUFD vDevice.  Clearing the entry is
> done during VM destroy.
>
> Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
> ---
>   drivers/iommu/amd/amd_viommu.h | 10 +++++++
>   drivers/iommu/amd/iommufd.c    |  9 ++++++
>   drivers/iommu/amd/viommu.c     | 53 +++++++++++++++++++++++++++++++++-
>   3 files changed, 71 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/iommu/amd/amd_viommu.h b/drivers/iommu/amd/amd_viommu.h
> index b6fd5ffc3b82..ca09a9856938 100644
> --- a/drivers/iommu/amd/amd_viommu.h
> +++ b/drivers/iommu/amd/amd_viommu.h
> @@ -6,6 +6,8 @@
>   #ifndef AMD_VIOMMU_H
>   #define AMD_VIOMMU_H
>   
> +#define VIOMMU_MAX_GDEVID	0xFFFF
> +
>   #if IS_ENABLED(CONFIG_AMD_IOMMU_IOMMUFD)
>   
>   int amd_viommu_init(struct amd_iommu *iommu);
> @@ -20,6 +22,9 @@ void amd_viommu_uninit_one(struct amd_iommu *iommu, struct amd_iommu_viommu *vio
>   
>   int amd_viommu_domain_id_update(struct amd_iommu *iommu, u16 gid,
>   				u16 hdom_id, u16 gdom_id);
> +
> +void amd_viommu_set_device_mapping(struct amd_iommu *iommu, u16 hDevId,
> +				   u16 guestId, u16 gDevId);
>   #else
>   
>   static inline int amd_viommu_init(struct amd_iommu *iommu)
> @@ -45,6 +50,11 @@ static inline void amd_viommu_uninit_one(struct amd_iommu *iommu, struct amd_iom
>   {
>   }
>   
> +static inline void amd_viommu_set_device_mapping(struct amd_iommu *iommu, u16 hDevId,
> +						 u16 guestId, u16 gDevId)
> +{
> +}
> +
>   #endif /* CONFIG_AMD_IOMMU_IOMMUFD */
>   
>   #endif /* AMD_VIOMMU_H */
> diff --git a/drivers/iommu/amd/iommufd.c b/drivers/iommu/amd/iommufd.c
> index 1975b2932107..7e070f72f02e 100644
> --- a/drivers/iommu/amd/iommufd.c
> +++ b/drivers/iommu/amd/iommufd.c
> @@ -136,12 +136,18 @@ static int _amd_viommu_vdevice_init(struct iommufd_vdevice *vdev)
>   	struct pci_dev *pdev = to_pci_dev(vdev->idev->dev);
>   	struct iommufd_viommu *viommu = vdev->viommu;
>   	struct amd_iommu_viommu *aviommu = container_of(viommu, struct amd_iommu_viommu, core);
> +	struct amd_iommu *iommu = container_of(viommu->iommu_dev, struct amd_iommu, iommu);
>   
>   	if (!pdev) {
>   		pr_err("%s: not a PCI device\n", __func__);
>   		return -EINVAL;
>   	}
>   
> +	if (vdev->virt_id > VIOMMU_MAX_GDEVID) {
> +		pr_err("%s: Invalid virtual ID (virt_id=%#llx)\n", __func__, vdev->virt_id);
> +		return -EINVAL;
> +	}
> +
>   	dev_data = dev_iommu_priv_get(&pdev->dev);
>   	if (!dev_data) {
>   		pr_err("%s: Device not found (devid=%#x)\n",
> @@ -152,6 +158,9 @@ static int _amd_viommu_vdevice_init(struct iommufd_vdevice *vdev)
>   	pr_debug("%s: gid=%#x, hdev_id=%#x, gdev_id=%#llx\n", __func__,
>   		 aviommu->gid, pci_dev_id(pdev), vdev->virt_id);
>   
> +	amd_viommu_set_device_mapping(iommu, pci_dev_id(pdev), aviommu->gid,
> +				       (u16)vdev->virt_id);
> +
>   	return 0;
>   }
>   
> diff --git a/drivers/iommu/amd/viommu.c b/drivers/iommu/amd/viommu.c
> index 708f2c7496a4..eb3f5217d856 100644
> --- a/drivers/iommu/amd/viommu.c
> +++ b/drivers/iommu/amd/viommu.c
> @@ -29,7 +29,6 @@
>   /*
>    * Guest Device ID Mapping Table
>    */
> -#define VIOMMU_MAX_GDEVID	0xFFFF
>   #define VIOMMU_DEVID_MAPPING_BASE	0x1000000000ULL
>   #define VIOMMU_DEVID_MAPPING_ENTRY_SIZE	(1 << 20)
>   
> @@ -40,6 +39,7 @@
>   #define VIOMMU_DOMID_MAPPING_BASE	0x2000000000ULL
>   #define VIOMMU_DOMID_MAPPING_ENTRY_SIZE	(1 << 19)
>   
> +#define VIOMMU_VFCTRL_GUEST_DID_MAP_CONTROL0_OFFSET	0x00
>   #define VIOMMU_VFCTRL_GUEST_DID_MAP_CONTROL1_OFFSET	0x08
>   
>   LIST_HEAD(viommu_devid_map);
> @@ -422,6 +422,53 @@ static void __maybe_unused free_private_vm_region(struct amd_iommu *iommu, u64 *
>   	*entry = NULL;
>   }
>   
> +#define DEVID_ENTRY_GDEVID_MASK		GENMASK_ULL(61, 46)
> +#define DEVID_ENTRY_HDEVID_MASK		GENMASK_ULL(29, 14)
> +#define DEVID_ENTRY_WRITE		BIT_ULL(63)
> +#define DEVID_ENTRY_VALID		BIT_ULL(0)
> +
> +/*
> + * Program the DevID via VFCTRL registers
> + * This function will be called during VM init via VFIO.
> + */
> +void amd_viommu_set_device_mapping(struct amd_iommu *iommu, u16 hDevId,
> +				   u16 guestId, u16 gDevId)
> +{
> +	u64 val;
> +	u8 __iomem *vfctrl;
> +
> +	pr_debug("%s: iommu_devid=%#x, gid=%#x, hDevId=%#x, gDevId=%#x\n",
> +		__func__, pci_dev_id(iommu->dev), guestId, hDevId, gDevId);
> +
> +	val = FIELD_PREP(DEVID_ENTRY_GDEVID_MASK, gDevId) |
> +	      FIELD_PREP(DEVID_ENTRY_HDEVID_MASK, hDevId) |
> +	      DEVID_ENTRY_WRITE | DEVID_ENTRY_VALID;
> +
> +	vfctrl = VIOMMU_VFCTRL_MMIO_BASE(iommu, guestId);
> +
> +	writeq(val, vfctrl + VIOMMU_VFCTRL_GUEST_DID_MAP_CONTROL0_OFFSET);
> +}
> +
> +/*
> + * Clear the DevID via VFCTRL registers
> + * This function will be called during VM destroy via VFIO.
> + */
> +static void clear_device_mapping(struct amd_iommu *iommu, u16 guestId, u16 gDevId)
> +{
> +	u64 val;
> +	u8 __iomem *vfctrl;
> +
> +	/*
> +	 * Clear the DevID in VFCTRL registers
> +	 */
> +	val = FIELD_PREP(DEVID_ENTRY_GDEVID_MASK, gDevId) |
> +	      FIELD_PREP(DEVID_ENTRY_HDEVID_MASK, 0) |
> +	      DEVID_ENTRY_WRITE | DEVID_ENTRY_VALID;
> +
> +	vfctrl = VIOMMU_VFCTRL_MMIO_BASE(iommu, guestId);
> +	writeq(val, vfctrl + VIOMMU_VFCTRL_GUEST_DID_MAP_CONTROL0_OFFSET);
> +}


The clear path sets Vld=1 with hDevID=0. This semantics is ambiguous:
Vld=1 marks the entry as a *valid* mapping, and hDevID=0 is a legal PCI
BDF (Bus 0, Dev 0, Func 0), instead of treating the entry as invalid. To 
actually invalidate the mapping,
please use Vld=0

	val = FIELD_PREP(DEVID_ENTRY_GDEVID_MASK, gDevId) |
	      FIELD_PREP(DEVID_ENTRY_HDEVID_MASK, 0) |
	      DEVID_ENTRY_WRITE;

Alternatively, during the clear dev mapping process, you might directly 
specify the original hdevid being used.


> +
>   static void viommu_clear_mapping(struct amd_iommu *iommu,
>   				 struct amd_iommu_viommu *aviommu)
>   {
> @@ -436,6 +483,10 @@ static void viommu_clear_mapping(struct amd_iommu *iommu,
>   	 */
>   	for (i = 0; i <= VIOMMU_MAX_GDOMID; i++)
>   		amd_viommu_domain_id_update(iommu, gid, aviommu->parent->id, i);
> +
> +	for (i = 0; i <= VIOMMU_MAX_GDEVID; i++)
> +		clear_device_mapping(iommu, gid, i);
> +
>   }
>   
>   void amd_viommu_uninit_one(struct amd_iommu *iommu, struct amd_iommu_viommu *aviommu)