File xsa400-06.patch of Package xen.28173

VT-d: prepare for per-device quarantine page tables (part I)

Arrange for domain ID and page table root to be passed around, the latter in
particular to domain_pgd_maddr() such that taking it from the per-domain
fields can be overridden.

No functional change intended.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Paul Durrant <paul@xen.org>
Reviewed-by: Roger Pau Monné <roger.pau@citrix.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>

--- a/xen/drivers/passthrough/vtd/extern.h
+++ b/xen/drivers/passthrough/vtd/extern.h
@@ -82,9 +82,10 @@ void *map_vtd_domain_page(u64 maddr);
 void unmap_vtd_domain_page(void *va);
 int domain_context_mapping_one(struct domain *domain, struct iommu *iommu,
                                uint8_t bus, uint8_t devfn,
-                               const struct pci_dev *pdev, unsigned int mode);
+                               const struct pci_dev *pdev, domid_t domid,
+                               paddr_t pgd_maddr, unsigned int mode);
 int domain_context_unmap_one(struct domain *domain, struct iommu *iommu,
-                             u8 bus, u8 devfn);
+                             uint8_t bus, uint8_t devfn, domid_t domid);
 int intel_iommu_get_reserved_device_memory(iommu_grdm_t *func, void *ctxt);
 
 unsigned int io_apic_read_remap_rte(unsigned int apic, unsigned int reg);
@@ -103,7 +104,8 @@ void platform_quirks_init(void);
 void vtd_ops_preamble_quirk(struct iommu* iommu);
 void vtd_ops_postamble_quirk(struct iommu* iommu);
 int __must_check me_wifi_quirk(struct domain *domain, uint8_t bus,
-                               uint8_t devfn, unsigned int mode);
+                               uint8_t devfn, domid_t domid, paddr_t pgd_maddr,
+                               unsigned int mode);
 void pci_vtd_quirk(const struct pci_dev *);
 void quirk_iommu_caps(struct iommu *iommu);
 
--- a/xen/drivers/passthrough/vtd/iommu.c
+++ b/xen/drivers/passthrough/vtd/iommu.c
@@ -1415,12 +1415,12 @@ int domain_context_mapping_one(
     struct domain *domain,
     struct iommu *iommu,
     uint8_t bus, uint8_t devfn, const struct pci_dev *pdev,
-    unsigned int mode)
+    domid_t domid, paddr_t pgd_maddr, unsigned int mode)
 {
     struct domain_iommu *hd = dom_iommu(domain);
     struct context_entry *context, *context_entries, lctxt;
     __uint128_t old;
-    u64 maddr, pgd_maddr;
+    uint64_t maddr;
     uint16_t seg = iommu->intel->drhd->segment, prev_did = 0;
     struct domain *prev_dom = NULL;
     int agaw, rc, ret;
@@ -1461,10 +1461,12 @@ int domain_context_mapping_one(
     }
     else
     {
+        paddr_t root = pgd_maddr;
+
         spin_lock(&hd->arch.mapping_lock);
 
         /* Ensure we have pagetables allocated down to leaf PTE. */
-        if ( hd->arch.pgd_maddr == 0 )
+        if ( !root )
         {
             addr_to_dma_page_maddr(domain, 0, 1);
             if ( hd->arch.pgd_maddr == 0 )
@@ -1477,22 +1479,24 @@ int domain_context_mapping_one(
                     rcu_unlock_domain(prev_dom);
                 return -ENOMEM;
             }
+
+            root = hd->arch.pgd_maddr;
         }
 
         /* Skip top levels of page tables for 2- and 3-level DRHDs. */
-        pgd_maddr = hd->arch.pgd_maddr;
         for ( agaw = level_to_agaw(4);
               agaw != level_to_agaw(iommu->nr_pt_levels);
               agaw-- )
         {
-            struct dma_pte *p = map_vtd_domain_page(pgd_maddr);
-            pgd_maddr = dma_pte_addr(*p);
+            struct dma_pte *p = map_vtd_domain_page(root);
+
+            root = dma_pte_addr(*p);
             unmap_vtd_domain_page(p);
-            if ( pgd_maddr == 0 )
+            if ( !root )
                 goto nomem;
         }
 
-        context_set_address_root(lctxt, pgd_maddr);
+        context_set_address_root(lctxt, root);
         if ( ats_enabled && ecap_dev_iotlb(iommu->ecap) )
             context_set_translation_type(lctxt, CONTEXT_TT_DEV_IOTLB);
         else
@@ -1608,15 +1612,21 @@ int domain_context_mapping_one(
     unmap_vtd_domain_page(context_entries);
 
     if ( !seg && !rc )
-        rc = me_wifi_quirk(domain, bus, devfn, mode);
+        rc = me_wifi_quirk(domain, bus, devfn, domid, pgd_maddr, mode);
 
     if ( rc )
     {
         if ( !prev_dom )
-            domain_context_unmap_one(domain, iommu, bus, devfn);
+            domain_context_unmap_one(domain, iommu, bus, devfn,
+                                     domain->domain_id);
         else if ( prev_dom != domain ) /* Avoid infinite recursion. */
+        {
+            hd = dom_iommu(prev_dom);
             domain_context_mapping_one(prev_dom, iommu, bus, devfn, pdev,
+                                       domain->domain_id,
+                                       hd->arch.pgd_maddr,
                                        mode & MAP_WITH_RMRR);
+        }
     }
 
     if ( prev_dom )
@@ -1633,6 +1643,7 @@ static int domain_context_mapping(struct
 {
     struct acpi_drhd_unit *drhd;
     const struct acpi_rmrr_unit *rmrr;
+    paddr_t pgd_maddr = dom_iommu(domain)->arch.pgd_maddr;
     int ret = 0;
     unsigned int i, mode = 0;
     uint16_t seg = pdev->seg, bdf;
@@ -1688,7 +1699,8 @@ static int domain_context_mapping(struct
                    domain->domain_id, seg, bus,
                    PCI_SLOT(devfn), PCI_FUNC(devfn));
         ret = domain_context_mapping_one(domain, drhd->iommu, bus, devfn,
-                                         pdev, mode);
+                                         pdev, domain->domain_id, pgd_maddr,
+                                         mode);
         if ( ret > 0 )
             ret = 0;
         if ( !ret && devfn == pdev->devfn && ats_device(pdev, drhd) > 0 )
@@ -1703,7 +1715,8 @@ static int domain_context_mapping(struct
                    PCI_SLOT(devfn), PCI_FUNC(devfn));
 
         ret = domain_context_mapping_one(domain, drhd->iommu, bus, devfn,
-                                         pdev, mode);
+                                         pdev, domain->domain_id, pgd_maddr,
+                                         mode);
         if ( ret < 0 )
             break;
         prev_present = ret;
@@ -1731,7 +1744,8 @@ static int domain_context_mapping(struct
          */
         if ( ret >= 0 )
             ret = domain_context_mapping_one(domain, drhd->iommu, bus, devfn,
-                                             NULL, mode);
+                                             NULL, domain->domain_id, pgd_maddr,
+                                             mode);
 
         /*
          * Devices behind PCIe-to-PCI/PCIx bridge may generate different
@@ -1746,7 +1760,8 @@ static int domain_context_mapping(struct
         if ( !ret && pdev_type(seg, bus, devfn) == DEV_TYPE_PCIe2PCI_BRIDGE &&
              (secbus != pdev->bus || pdev->devfn != 0) )
             ret = domain_context_mapping_one(domain, drhd->iommu, secbus, 0,
-                                             NULL, mode);
+                                             NULL, domain->domain_id, pgd_maddr,
+                                             mode);
 
         if ( ret )
         {
@@ -1775,7 +1790,7 @@ static int domain_context_mapping(struct
 int domain_context_unmap_one(
     struct domain *domain,
     struct iommu *iommu,
-    u8 bus, u8 devfn)
+    uint8_t bus, uint8_t devfn, domid_t domid)
 {
     struct context_entry *context, *context_entries;
     u64 maddr;
@@ -1833,7 +1848,7 @@ int domain_context_unmap_one(
     unmap_vtd_domain_page(context_entries);
 
     if ( !iommu->intel->drhd->segment && !rc )
-        rc = me_wifi_quirk(domain, bus, devfn, UNMAP_ME_PHANTOM_FUNC);
+        rc = me_wifi_quirk(domain, bus, devfn, domid, 0, UNMAP_ME_PHANTOM_FUNC);
 
     if ( rc && !is_hardware_domain(domain) && domain != dom_io )
     {
@@ -1886,7 +1901,8 @@ static int domain_context_unmap(struct d
             printk(VTDPREFIX "d%d:PCIe: unmap %04x:%02x:%02x.%u\n",
                    domain->domain_id, seg, bus,
                    PCI_SLOT(devfn), PCI_FUNC(devfn));
-        ret = domain_context_unmap_one(domain, iommu, bus, devfn);
+        ret = domain_context_unmap_one(domain, iommu, bus, devfn,
+                                       domain->domain_id);
         if ( !ret && devfn == pdev->devfn && ats_device(pdev, drhd) > 0 )
             disable_ats_device(pdev);
 
@@ -1896,7 +1912,8 @@ static int domain_context_unmap(struct d
         if ( iommu_debug )
             printk(VTDPREFIX "d%d:PCI: unmap %04x:%02x:%02x.%u\n",
                    domain->domain_id, seg, bus, PCI_SLOT(devfn), PCI_FUNC(devfn));
-        ret = domain_context_unmap_one(domain, iommu, bus, devfn);
+        ret = domain_context_unmap_one(domain, iommu, bus, devfn,
+                                       domain->domain_id);
         if ( ret )
             break;
 
@@ -1922,12 +1939,15 @@ static int domain_context_unmap(struct d
         /* PCIe to PCI/PCIx bridge */
         if ( pdev_type(seg, tmp_bus, tmp_devfn) == DEV_TYPE_PCIe2PCI_BRIDGE )
         {
-            ret = domain_context_unmap_one(domain, iommu, tmp_bus, tmp_devfn);
+            ret = domain_context_unmap_one(domain, iommu, tmp_bus, tmp_devfn,
+                                           domain->domain_id);
             if ( !ret )
-                ret = domain_context_unmap_one(domain, iommu, secbus, 0);
+                ret = domain_context_unmap_one(domain, iommu, secbus, 0,
+                                               domain->domain_id);
         }
         else /* Legacy PCI bridge */
-            ret = domain_context_unmap_one(domain, iommu, tmp_bus, tmp_devfn);
+            ret = domain_context_unmap_one(domain, iommu, tmp_bus, tmp_devfn,
+                                           domain->domain_id);
 
         break;
 
--- a/xen/drivers/passthrough/vtd/quirks.c
+++ b/xen/drivers/passthrough/vtd/quirks.c
@@ -347,6 +347,8 @@ void __init platform_quirks_init(void)
 
 static int __must_check map_me_phantom_function(struct domain *domain,
                                                 unsigned int dev,
+                                                domid_t domid,
+                                                paddr_t pgd_maddr,
                                                 unsigned int mode)
 {
     struct acpi_drhd_unit *drhd;
@@ -360,16 +362,17 @@ static int __must_check map_me_phantom_f
     /* map or unmap ME phantom function */
     if ( !(mode & UNMAP_ME_PHANTOM_FUNC) )
         rc = domain_context_mapping_one(domain, drhd->iommu, 0,
-                                        PCI_DEVFN(dev, 7), NULL, mode);
+                                        PCI_DEVFN(dev, 7), NULL,
+                                        domid, pgd_maddr, mode);
     else
         rc = domain_context_unmap_one(domain, drhd->iommu, 0,
-                                      PCI_DEVFN(dev, 7));
+                                      PCI_DEVFN(dev, 7), domid);
 
     return rc;
 }
 
 int me_wifi_quirk(struct domain *domain, uint8_t bus, uint8_t devfn,
-                  unsigned int mode)
+                  domid_t domid, paddr_t pgd_maddr, unsigned int mode)
 {
     u32 id;
     int rc = 0;
@@ -393,7 +396,7 @@ int me_wifi_quirk(struct domain *domain,
             case 0x423b8086:
             case 0x423c8086:
             case 0x423d8086:
-                rc = map_me_phantom_function(domain, 3, mode);
+                rc = map_me_phantom_function(domain, 3, domid, pgd_maddr, mode);
                 break;
             default:
                 break;
@@ -419,7 +422,7 @@ int me_wifi_quirk(struct domain *domain,
             case 0x42388086:        /* Puma Peak */
             case 0x422b8086:
             case 0x422c8086:
-                rc = map_me_phantom_function(domain, 22, mode);
+                rc = map_me_phantom_function(domain, 22, domid, pgd_maddr, mode);
                 break;
             default:
                 break;
openSUSE Build Service is sponsored by