Merge git://git.infradead.org/intel-iommu

Pull IOMMU fixes from David Woodhouse:
 "Two minor fixes.

  The first fixes the assignment of SR-IOV virtual functions to the
  correct IOMMU unit, and the second fixes the excessively large (and
  physically contiguous) PASID tables used with SVM"

* git://git.infradead.org/intel-iommu:
  iommu/vt-d: Fix PASID table allocation
  iommu/vt-d: Fix IOMMU lookup for SR-IOV Virtual Functions

diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 58470f5ced04a9547428ec538dbdec3c58f9a1f2..8c53748a769d447fac83622725c305a3ee6bc92f 100644 (file)
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -338,7 +338,9 @@ static int dmar_pci_bus_notifier(struct notifier_block *nb,
        struct pci_dev *pdev = to_pci_dev(data);
        struct dmar_pci_notify_info *info;
 
-       /* Only care about add/remove events for physical functions */
+       /* Only care about add/remove events for physical functions.
+        * For VFs we actually do the lookup based on the corresponding
+        * PF in device_to_iommu() anyway. */
        if (pdev->is_virtfn)
                return NOTIFY_DONE;
        if (action != BUS_NOTIFY_ADD_DEVICE &&

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 3965e73db51cef0f3d3b5593da18c9d9fe25fd9e..d8376c2d18b3bf7491cb80473053b1a34f6cd54f 100644 (file)
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -892,7 +892,13 @@ static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devf
                return NULL;
 
        if (dev_is_pci(dev)) {
+               struct pci_dev *pf_pdev;
+
                pdev = to_pci_dev(dev);
+               /* VFs aren't listed in scope tables; we need to look up
+                * the PF instead to find the IOMMU. */
+               pf_pdev = pci_physfn(pdev);
+               dev = &pf_pdev->dev;
                segment = pci_domain_nr(pdev->bus);
        } else if (has_acpi_companion(dev))
                dev = &ACPI_COMPANION(dev)->dev;
@@ -905,6 +911,13 @@ static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devf
                for_each_active_dev_scope(drhd->devices,
                                          drhd->devices_cnt, i, tmp) {
                        if (tmp == dev) {
+                               /* For a VF use its original BDF# not that of the PF
+                                * which we used for the IOMMU lookup. Strictly speaking
+                                * we could do this for all PCI devices; we only need to
+                                * get the BDF# from the scope table for ACPI matches. */
+                               if (pdev->is_virtfn)
+                                       goto got_pdev;
+
                                *bus = drhd->devices[i].bus;
                                *devfn = drhd->devices[i].devfn;
                                goto out;

diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c
index 8ebb3530afa7574810f849e7a333c19473740304..cb72e0011310d1fbd04cb1560a861c8e5ec2fd55 100644 (file)
--- a/drivers/iommu/intel-svm.c
+++ b/drivers/iommu/intel-svm.c
@@ -39,10 +39,18 @@ int intel_svm_alloc_pasid_tables(struct intel_iommu *iommu)
        struct page *pages;
        int order;
 
-       order = ecap_pss(iommu->ecap) + 7 - PAGE_SHIFT;
-       if (order < 0)
-               order = 0;
-
+       /* Start at 2 because it's defined as 2^(1+PSS) */
+       iommu->pasid_max = 2 << ecap_pss(iommu->ecap);
+
+       /* Eventually I'm promised we will get a multi-level PASID table
+        * and it won't have to be physically contiguous. Until then,
+        * limit the size because 8MiB contiguous allocations can be hard
+        * to come by. The limit of 0x20000, which is 1MiB for each of
+        * the PASID and PASID-state tables, is somewhat arbitrary. */
+       if (iommu->pasid_max > 0x20000)
+               iommu->pasid_max = 0x20000;
+
+       order = get_order(sizeof(struct pasid_entry) * iommu->pasid_max);
        pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
        if (!pages) {
                pr_warn("IOMMU: %s: Failed to allocate PASID table\n",
@@ -53,6 +61,8 @@ int intel_svm_alloc_pasid_tables(struct intel_iommu *iommu)
        pr_info("%s: Allocated order %d PASID table.\n", iommu->name, order);
 
        if (ecap_dis(iommu->ecap)) {
+               /* Just making it explicit... */
+               BUILD_BUG_ON(sizeof(struct pasid_entry) != sizeof(struct pasid_state_entry));
                pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
                if (pages)
                        iommu->pasid_state_table = page_address(pages);
@@ -68,11 +78,7 @@ int intel_svm_alloc_pasid_tables(struct intel_iommu *iommu)
 
 int intel_svm_free_pasid_tables(struct intel_iommu *iommu)
 {
-       int order;
-
-       order = ecap_pss(iommu->ecap) + 7 - PAGE_SHIFT;
-       if (order < 0)
-               order = 0;
+       int order = get_order(sizeof(struct pasid_entry) * iommu->pasid_max);
 
        if (iommu->pasid_table) {
                free_pages((unsigned long)iommu->pasid_table, order);
@@ -371,8 +377,8 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_
                }
                svm->iommu = iommu;
 
-               if (pasid_max > 2 << ecap_pss(iommu->ecap))
-                       pasid_max = 2 << ecap_pss(iommu->ecap);
+               if (pasid_max > iommu->pasid_max)
+                       pasid_max = iommu->pasid_max;
 
                /* Do not use PASID 0 in caching mode (virtualised IOMMU) */
                ret = idr_alloc(&iommu->pasid_idr, svm,

diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 2d9b650047a5b96582f66dff2b2581cce97c2b65..d49e26c6cdc7b5e48e41591f7c73e74d200441a8 100644 (file)
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -429,6 +429,7 @@ struct intel_iommu {
        struct page_req_dsc *prq;
        unsigned char prq_name[16];    /* Name for PRQ interrupt */
        struct idr pasid_idr;
+       u32 pasid_max;
 #endif
        struct q_inval  *qi;            /* Queued invalidation info */
        u32 *iommu_state; /* Store iommu states between suspend and resume.*/