IOMMU/x86: maintain a per-device pseudo domain ID

In order to subsequently enable per-device quarantine page tables, we'll
need domain-ID-like identifiers to be inserted in the respective device
(AMD) or context (Intel) table entries alongside the per-device page
table root addresses.

Make use of "real" domain IDs occupying only half of the value range
coverable by domid_t.

Note that in VT-d's iommu_alloc() I didn't want to introduce new memory
leaks in case of error, but existing ones don't get plugged - that'll be
the subject of a later change.

The VT-d changes are slightly asymmetric, but this way we can avoid
assigning pseudo domain IDs to devices which would never be mapped while
still avoiding to add a new parameter to domain_context_unmap().

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Paul Durrant <paul@xen.org>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Roger Pau Monné <roger.pau@citrix.com>
master commit: 97af062b89
master date: 2022-04-05 14:19:10 +0200

xen/drivers/passthrough/amd/iommu.h

@@ -96,6 +96,7 @@ struct amd_iommu {
     struct ring_buffer cmd_buffer;
     struct ring_buffer event_log;
     struct ring_buffer ppr_log;
+    unsigned long *domid_map;
 
     int exclusion_enable;
     int exclusion_allow_all;

xen/drivers/passthrough/amd/iommu_detect.c

@@ -180,6 +180,11 @@ int __init amd_iommu_detect_one_acpi(
     if ( rt )
         goto out;
 
+    iommu->domid_map = iommu_init_domid();
+    rt = -ENOMEM;
+    if ( !iommu->domid_map )
+        goto out;
+
     rt = pci_ro_device(iommu->seg, bus, PCI_DEVFN(dev, func));
     if ( rt )
         printk(XENLOG_ERR "Could not mark config space of %pp read-only (%d)\n",
@@ -190,7 +195,10 @@ int __init amd_iommu_detect_one_acpi(
 
  out:
     if ( rt )
+    {
+        xfree(iommu->domid_map);
         xfree(iommu);
+    }
 
     return rt;
 }

xen/drivers/passthrough/amd/pci_amd_iommu.c

@@ -508,6 +508,8 @@ static int amd_iommu_add_device(u8 devfn, struct pci_dev *pdev)
     struct amd_iommu *iommu;
     u16 bdf;
     struct ivrs_mappings *ivrs_mappings;
+    bool fresh_domid = false;
+    int ret;
 
     if ( !pdev->domain )
         return -EINVAL;
@@ -568,7 +570,22 @@ static int amd_iommu_add_device(u8 devfn, struct pci_dev *pdev)
         spin_unlock_irqrestore(&iommu->lock, flags);
     }
 
-    return amd_iommu_setup_domain_device(pdev->domain, iommu, devfn, pdev);
+    if ( iommu_quarantine && pdev->arch.pseudo_domid == DOMID_INVALID )
+    {
+        pdev->arch.pseudo_domid = iommu_alloc_domid(iommu->domid_map);
+        if ( pdev->arch.pseudo_domid == DOMID_INVALID )
+            return -ENOSPC;
+        fresh_domid = true;
+    }
+
+    ret = amd_iommu_setup_domain_device(pdev->domain, iommu, devfn, pdev);
+    if ( ret && fresh_domid )
+    {
+        iommu_free_domid(pdev->arch.pseudo_domid, iommu->domid_map);
+        pdev->arch.pseudo_domid = DOMID_INVALID;
+    }
+
+    return ret;
 }
 
 static int amd_iommu_remove_device(u8 devfn, struct pci_dev *pdev)
@@ -591,6 +608,9 @@ static int amd_iommu_remove_device(u8 devfn, struct pci_dev *pdev)
 
     amd_iommu_disable_domain_device(pdev->domain, iommu, devfn, pdev);
 
+    iommu_free_domid(pdev->arch.pseudo_domid, iommu->domid_map);
+    pdev->arch.pseudo_domid = DOMID_INVALID;
+
     ivrs_mappings = get_ivrs_mappings(pdev->seg);
     bdf = PCI_BDF2(pdev->bus, devfn);
     if ( amd_iommu_perdev_intremap &&

xen/drivers/passthrough/pci.c

@@ -327,6 +327,7 @@ static struct pci_dev *alloc_pdev(struct pci_seg *pseg, u8 bus, u8 devfn)
     *((u8*) &pdev->bus) = bus;
     *((u8*) &pdev->devfn) = devfn;
     pdev->domain = NULL;
+    pdev->arch.pseudo_domid = DOMID_INVALID;
     INIT_LIST_HEAD(&pdev->msi_list);
 
     pos = pci_find_cap_offset(pseg->nr, bus, PCI_SLOT(devfn), PCI_FUNC(devfn),
@@ -1276,8 +1277,12 @@ static int _dump_pci_devices(struct pci_seg *pseg, void *arg)
 
     list_for_each_entry ( pdev, &pseg->alldevs_list, alldevs_list )
     {
-        printk("%pp - %pd - node %-3d - MSIs < ",
-               &pdev->sbdf, pdev->domain,
+        printk("%pp - ", &pdev->sbdf);
+        if ( pdev->domain == dom_io )
+            printk("DomIO:%x", pdev->arch.pseudo_domid);
+        else
+            printk("%pd", pdev->domain);
+        printk(" - node %-3d - MSIs < ",
                (pdev->node != NUMA_NO_NODE) ? pdev->node : -1);
         list_for_each_entry ( msi, &pdev->msi_list, list )
                printk("%d ", msi->irq);

xen/drivers/passthrough/vtd/iommu.c

@@ -22,6 +22,7 @@
 #include <xen/sched.h>
 #include <xen/xmalloc.h>
 #include <xen/domain_page.h>
+#include <xen/err.h>
 #include <xen/iocap.h>
 #include <xen/iommu.h>
 #include <xen/numa.h>
@@ -1204,7 +1205,7 @@ int __init iommu_alloc(struct acpi_drhd_unit *drhd)
 {
     struct vtd_iommu *iommu;
     unsigned long sagaw, nr_dom;
-    int agaw;
+    int agaw, rc;
 
     if ( nr_iommus >= MAX_IOMMUS )
     {
@@ -1297,7 +1298,16 @@ int __init iommu_alloc(struct acpi_drhd_unit *drhd)
     if ( !iommu->domid_map )
         return -ENOMEM;
 
+    iommu->pseudo_domid_map = iommu_init_domid();
+    rc = -ENOMEM;
+    if ( !iommu->pseudo_domid_map )
+        goto free;
+
     return 0;
+
+ free:
+    iommu_free(drhd);
+    return rc;
 }
 
 void __init iommu_free(struct acpi_drhd_unit *drhd)
@@ -1320,6 +1330,7 @@ void __init iommu_free(struct acpi_drhd_unit *drhd)
 
     xfree(iommu->domid_bitmap);
     xfree(iommu->domid_map);
+    xfree(iommu->pseudo_domid_map);
 
     if ( iommu->msi.irq >= 0 )
         destroy_irq(iommu->msi.irq);
@@ -1581,8 +1592,8 @@ int domain_context_mapping_one(
     return rc ?: pdev && prev_dom;
 }
 
-static int domain_context_unmap(struct domain *d, uint8_t devfn,
-                                struct pci_dev *pdev);
+static const struct acpi_drhd_unit *domain_context_unmap(
+    struct domain *d, uint8_t devfn, struct pci_dev *pdev);
 
 static int domain_context_mapping(struct domain *domain, u8 devfn,
                                   struct pci_dev *pdev)
@@ -1590,6 +1601,7 @@ static int domain_context_mapping(struct domain *domain, u8 devfn,
     struct acpi_drhd_unit *drhd;
     const struct acpi_rmrr_unit *rmrr;
     paddr_t pgd_maddr = dom_iommu(domain)->arch.vtd.pgd_maddr;
+    domid_t orig_domid = pdev->arch.pseudo_domid;
     int ret = 0;
     unsigned int i, mode = 0;
     uint16_t seg = pdev->seg, bdf;
@@ -1649,6 +1661,14 @@ static int domain_context_mapping(struct domain *domain, u8 devfn,
         break;
 
     case DEV_TYPE_PCIe_ENDPOINT:
+        if ( iommu_quarantine && orig_domid == DOMID_INVALID )
+        {
+            pdev->arch.pseudo_domid =
+                iommu_alloc_domid(drhd->iommu->pseudo_domid_map);
+            if ( pdev->arch.pseudo_domid == DOMID_INVALID )
+                return -ENOSPC;
+        }
+
         if ( iommu_debug )
             printk(VTDPREFIX "%pd:PCIe: map %pp\n",
                    domain, &PCI_SBDF3(seg, bus, devfn));
@@ -1663,6 +1683,14 @@ static int domain_context_mapping(struct domain *domain, u8 devfn,
         break;
 
     case DEV_TYPE_PCI:
+        if ( iommu_quarantine && orig_domid == DOMID_INVALID )
+        {
+            pdev->arch.pseudo_domid =
+                iommu_alloc_domid(drhd->iommu->pseudo_domid_map);
+            if ( pdev->arch.pseudo_domid == DOMID_INVALID )
+                return -ENOSPC;
+        }
+
         if ( iommu_debug )
             printk(VTDPREFIX "%pd:PCI: map %pp\n",
                    domain, &PCI_SBDF3(seg, bus, devfn));
@@ -1736,6 +1764,13 @@ static int domain_context_mapping(struct domain *domain, u8 devfn,
     if ( !ret && devfn == pdev->devfn )
         pci_vtd_quirk(pdev);
 
+    if ( ret && drhd && orig_domid == DOMID_INVALID )
+    {
+        iommu_free_domid(pdev->arch.pseudo_domid,
+                         drhd->iommu->pseudo_domid_map);
+        pdev->arch.pseudo_domid = DOMID_INVALID;
+    }
+
     return ret;
 }
 
@@ -1818,8 +1853,10 @@ int domain_context_unmap_one(
     return rc;
 }
 
-static int domain_context_unmap(struct domain *domain, u8 devfn,
-                                struct pci_dev *pdev)
+static const struct acpi_drhd_unit *domain_context_unmap(
+    struct domain *domain,
+    uint8_t devfn,
+    struct pci_dev *pdev)
 {
     struct acpi_drhd_unit *drhd;
     struct vtd_iommu *iommu;
@@ -1829,7 +1866,7 @@ static int domain_context_unmap(struct domain *domain, u8 devfn,
 
     drhd = acpi_find_matched_drhd_unit(pdev);
     if ( !drhd )
-        return -ENODEV;
+        return ERR_PTR(-ENODEV);
     iommu = drhd->iommu;
 
     switch ( pdev->type )
@@ -1839,7 +1876,7 @@ static int domain_context_unmap(struct domain *domain, u8 devfn,
             printk(VTDPREFIX "%pd:Hostbridge: skip %pp unmap\n",
                    domain, &PCI_SBDF3(seg, bus, devfn));
         if ( !is_hardware_domain(domain) )
-            return -EPERM;
+            return ERR_PTR(-EPERM);
         goto out;
 
     case DEV_TYPE_PCIe_BRIDGE:
@@ -1912,7 +1949,7 @@ static int domain_context_unmap(struct domain *domain, u8 devfn,
         check_cleanup_domid_map(domain, pdev, iommu);
 
 out:
-    return ret;
+    return ret ? ERR_PTR(ret) : drhd;
 }
 
 static void iommu_clear_root_pgtable(struct domain *d)
@@ -2137,16 +2174,17 @@ static int intel_iommu_enable_device(struct pci_dev *pdev)
 
 static int intel_iommu_remove_device(u8 devfn, struct pci_dev *pdev)
 {
+    const struct acpi_drhd_unit *drhd;
     struct acpi_rmrr_unit *rmrr;
     u16 bdf;
-    int ret, i;
+    unsigned int i;
 
     if ( !pdev->domain )
         return -EINVAL;
 
-    ret = domain_context_unmap(pdev->domain, devfn, pdev);
-    if ( ret )
-        return ret;
+    drhd = domain_context_unmap(pdev->domain, devfn, pdev);
+    if ( IS_ERR(drhd) )
+        return PTR_ERR(drhd);
 
     for_each_rmrr_device ( rmrr, bdf, i )
     {
@@ -2163,6 +2201,13 @@ static int intel_iommu_remove_device(u8 devfn, struct pci_dev *pdev)
                                rmrr->end_address, 0);
     }
 
+    if ( drhd )
+    {
+        iommu_free_domid(pdev->arch.pseudo_domid,
+                         drhd->iommu->pseudo_domid_map);
+        pdev->arch.pseudo_domid = DOMID_INVALID;
+    }
+
     return 0;
 }
 

xen/drivers/passthrough/vtd/iommu.h

@@ -535,6 +535,7 @@ struct vtd_iommu {
     } flush;
 
     struct list_head ats_devices;
+    unsigned long *pseudo_domid_map; /* "pseudo" domain id bitmap */
     unsigned long *domid_bitmap;  /* domain id bitmap */
     u16 *domid_map;               /* domain id mapping array */
     uint32_t version;

xen/drivers/passthrough/x86/iommu.c

@@ -386,6 +386,53 @@ void __hwdom_init arch_iommu_hwdom_init(struct domain *d)
         return;
 }
 
+unsigned long *__init iommu_init_domid(void)
+{
+    if ( !iommu_quarantine )
+        return ZERO_BLOCK_PTR;
+
+    BUILD_BUG_ON(DOMID_MASK * 2U >= UINT16_MAX);
+
+    return xzalloc_array(unsigned long,
+                         BITS_TO_LONGS(UINT16_MAX - DOMID_MASK));
+}
+
+domid_t iommu_alloc_domid(unsigned long *map)
+{
+    /*
+     * This is used uniformly across all IOMMUs, such that on typical
+     * systems we wouldn't re-use the same ID very quickly (perhaps never).
+     */
+    static unsigned int start;
+    unsigned int idx = find_next_zero_bit(map, UINT16_MAX - DOMID_MASK, start);
+
+    ASSERT(pcidevs_locked());
+
+    if ( idx >= UINT16_MAX - DOMID_MASK )
+        idx = find_first_zero_bit(map, UINT16_MAX - DOMID_MASK);
+    if ( idx >= UINT16_MAX - DOMID_MASK )
+        return DOMID_INVALID;
+
+    __set_bit(idx, map);
+
+    start = idx + 1;
+
+    return idx | (DOMID_MASK + 1);
+}
+
+void iommu_free_domid(domid_t domid, unsigned long *map)
+{
+    ASSERT(pcidevs_locked());
+
+    if ( domid == DOMID_INVALID )
+        return;
+
+    ASSERT(domid > DOMID_MASK);
+
+    if ( !__test_and_clear_bit(domid & DOMID_MASK, map) )
+        BUG();
+}
+
 int iommu_free_pgtables(struct domain *d)
 {
     struct domain_iommu *hd = dom_iommu(d);

xen/include/asm-x86/iommu.h

@@ -142,6 +142,10 @@ int pi_update_irte(const struct pi_desc *pi_desc, const struct pirq *pirq,
         iommu_vcall(ops, sync_cache, addr, size);       \
 })
 
+unsigned long *iommu_init_domid(void);
+domid_t iommu_alloc_domid(unsigned long *map);
+void iommu_free_domid(domid_t domid, unsigned long *map);
+
 int __must_check iommu_free_pgtables(struct domain *d);
 struct domain_iommu;
 struct page_info *__must_check iommu_alloc_pgtable(struct domain_iommu *hd);

xen/include/asm-x86/pci.h

@@ -15,6 +15,12 @@
 
 struct arch_pci_dev {
     vmask_t used_vectors;
+    /*
+     * These fields are (de)initialized under pcidevs-lock. Other uses of
+     * them don't race (de)initialization and hence don't strictly need any
+     * locking.
+     */
+    domid_t pseudo_domid;
 };
 
 int pci_conf_write_intercept(unsigned int seg, unsigned int bdf,