iommu: Allow ATS to work on VFs when the PF uses IDENTITY

PCI ATS has a global Smallest Translation Unit field that is located in
the PF but shared by all of the VFs.

The expectation is that the STU will be set to the root port's global STU
capability which is driven by the IO page table configuration of the iommu
HW. Today it becomes set when the iommu driver first enables ATS.

Thus, to enable ATS on the VF, the PF must have already had the correct
STU programmed, even if ATS is off on the PF.

Unfortunately the PF only programs the STU when the PF enables ATS. The
iommu drivers tend to leave ATS disabled when IDENTITY translation is
being used.

Thus we can get into a state where the PF is setup to use IDENTITY with
the DMA API while the VF would like to use VFIO with a PAGING domain and
have ATS turned on. This fails because the PF never loaded a PAGING domain
and so it never setup the STU, and the VF can't do it.

The simplest solution is to have the iommu driver set the ATS STU when it
probes the device. This way the ATS STU is loaded immediately at boot time
to all PFs and there is no issue when a VF comes to use it.

Add a new call pci_prepare_ats() which should be called by iommu drivers
in their probe_device() op for every PCI device if the iommu driver
supports ATS. This will setup the STU based on whatever page size
capability the iommu HW has.

Signed-off-by: Jason Gunthorpe <[email protected]>
Acked-by: Bjorn Helgaas <[email protected]>
Reviewed-by: Kevin Tian <[email protected]>
Reviewed-by: Lu Baolu <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Joerg Roedel <[email protected]>

Author: jgunthorpe

drivers/iommu/amd/iommu.c

@@ -2203,6 +2203,9 @@ static struct iommu_device *amd_iommu_probe_device(struct device *dev)
 
 	iommu_completion_wait(iommu);
 
+	if (dev_is_pci(dev))
+		pci_prepare_ats(to_pci_dev(dev), PAGE_SHIFT);
+
 	return iommu_dev;
 }
 

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c

@@ -3295,6 +3295,12 @@ static struct iommu_device *arm_smmu_probe_device(struct device *dev)
 	    smmu->features & ARM_SMMU_FEAT_STALL_FORCE)
 		master->stall_enabled = true;
 
+	if (dev_is_pci(dev)) {
+		unsigned int stu = __ffs(smmu->pgsize_bitmap);
+
+		pci_prepare_ats(to_pci_dev(dev), stu);
+	}
+
 	return &smmu->iommu;
 
 err_free_master:

drivers/iommu/intel/iommu.c

@@ -4091,6 +4091,7 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev)
 
 	dev_iommu_priv_set(dev, info);
 	if (pdev && pci_ats_supported(pdev)) {
+		pci_prepare_ats(pdev, VTD_PAGE_SHIFT);
 		ret = device_rbtree_insert(iommu, info);
 		if (ret)
 			goto free;

drivers/pci/ats.c

@@ -47,6 +47,39 @@ bool pci_ats_supported(struct pci_dev *dev)
 }
 EXPORT_SYMBOL_GPL(pci_ats_supported);
 
+/**
+ * pci_prepare_ats - Setup the PS for ATS
+ * @dev: the PCI device
+ * @ps: the IOMMU page shift
+ *
+ * This must be done by the IOMMU driver on the PF before any VFs are created to
+ * ensure that the VF can have ATS enabled.
+ *
+ * Returns 0 on success, or negative on failure.
+ */
+int pci_prepare_ats(struct pci_dev *dev, int ps)
+{
+	u16 ctrl;
+
+	if (!pci_ats_supported(dev))
+		return -EINVAL;
+
+	if (WARN_ON(dev->ats_enabled))
+		return -EBUSY;
+
+	if (ps < PCI_ATS_MIN_STU)
+		return -EINVAL;
+
+	if (dev->is_virtfn)
+		return 0;
+
+	dev->ats_stu = ps;
+	ctrl = PCI_ATS_CTRL_STU(dev->ats_stu - PCI_ATS_MIN_STU);
+	pci_write_config_word(dev, dev->ats_cap + PCI_ATS_CTRL, ctrl);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pci_prepare_ats);
+
 /**
  * pci_enable_ats - enable the ATS capability
  * @dev: the PCI device

include/linux/pci-ats.h

@@ -8,6 +8,7 @@
 /* Address Translation Service */
 bool pci_ats_supported(struct pci_dev *dev);
 int pci_enable_ats(struct pci_dev *dev, int ps);
+int pci_prepare_ats(struct pci_dev *dev, int ps);
 void pci_disable_ats(struct pci_dev *dev);
 int pci_ats_queue_depth(struct pci_dev *dev);
 int pci_ats_page_aligned(struct pci_dev *dev);
@@ -16,6 +17,8 @@ static inline bool pci_ats_supported(struct pci_dev *d)
 { return false; }
 static inline int pci_enable_ats(struct pci_dev *d, int ps)
 { return -ENODEV; }
+static inline int pci_prepare_ats(struct pci_dev *dev, int ps)
+{ return -ENODEV; }
 static inline void pci_disable_ats(struct pci_dev *d) { }
 static inline int pci_ats_queue_depth(struct pci_dev *d)
 { return -ENODEV; }