xen/passthrough: extend hypercall to support rdm reservation policy

This patch extends the existing hypercall to support rdm reservation policy.
We return error or just throw out a warning message depending on whether
the policy is "strict" or "relaxed" when reserving RDM regions in pfn space.
Note in some special cases, e.g. add a device to hwdomain, and remove a
device from user domain, 'relaxed' is fine enough since this is always safe
to hwdomain.

CC: Tim Deegan <tim@xen.org>
CC: Keir Fraser <keir@xen.org>
CC: Jan Beulich <jbeulich@suse.com>
CC: Andrew Cooper <andrew.cooper3@citrix.com>
CC: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
CC: Aravind Gopalakrishnan <Aravind.Gopalakrishnan@amd.com>
CC: Ian Campbell <ian.campbell@citrix.com>
CC: Stefano Stabellini <stefano.stabellini@citrix.com>
CC: Yang Zhang <yang.z.zhang@intel.com>
CC: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Tiejun Chen <tiejun.chen@intel.com>
Reviewed-by: George Dunlap <george.dunlap@eu.citrix.com>
Acked-by: Jan Beulich <jbeulich@suse.com>
--
v13a: Fix build on ARM by passing 0 for flags to arm_smmu_assign_dev.

diff --git a/xen/arch/x86/mm/p2m.c b/xen/arch/x86/mm/p2m.c
index 1e763dcf7a0f3248b586526e5f36c36e7fb3f610..89616b78c37a5db1572b5cbcee2d3e801994ece0 100644 (file)
--- a/xen/arch/x86/mm/p2m.c
+++ b/xen/arch/x86/mm/p2m.c
@@ -901,7 +901,7 @@ int set_mmio_p2m_entry(struct domain *d, unsigned long gfn, mfn_t mfn,
 }
 
 int set_identity_p2m_entry(struct domain *d, unsigned long gfn,
-                           p2m_access_t p2ma)
+                           p2m_access_t p2ma, unsigned int flag)
 {
     p2m_type_t p2mt;
     p2m_access_t a;
@@ -923,7 +923,10 @@ int set_identity_p2m_entry(struct domain *d, unsigned long gfn,
         ret = 0;
     else
     {
-        ret = -EBUSY;
+        if ( flag & XEN_DOMCTL_DEV_RDM_RELAXED )
+            ret = 0;
+        else
+            ret = -EBUSY;
         printk(XENLOG_G_WARNING
                "Cannot setup identity map d%d:%lx,"
                " gfn already mapped to %lx.\n",

diff --git a/xen/drivers/passthrough/amd/pci_amd_iommu.c b/xen/drivers/passthrough/amd/pci_amd_iommu.c
index e83bb35e484c521fc150c9dfbf3f9ed855740317..920b35a38cf95bb81c3475c4124609890f42cd77 100644 (file)
--- a/xen/drivers/passthrough/amd/pci_amd_iommu.c
+++ b/xen/drivers/passthrough/amd/pci_amd_iommu.c
@@ -394,7 +394,8 @@ static int reassign_device(struct domain *source, struct domain *target,
 }
 
 static int amd_iommu_assign_device(struct domain *d, u8 devfn,
-                                   struct pci_dev *pdev)
+                                   struct pci_dev *pdev,
+                                   u32 flag)
 {
     struct ivrs_mappings *ivrs_mappings = get_ivrs_mappings(pdev->seg);
     int bdf = PCI_BDF2(pdev->bus, devfn);

diff --git a/xen/drivers/passthrough/arm/smmu.c b/xen/drivers/passthrough/arm/smmu.c
index 6cc439443bfeb7dd77316e9d19e92508c6254e55..be03dffea7f217841e7573ba064fea70ddd18648 100644 (file)
--- a/xen/drivers/passthrough/arm/smmu.c
+++ b/xen/drivers/passthrough/arm/smmu.c
@@ -2605,7 +2605,7 @@ static void arm_smmu_destroy_iommu_domain(struct iommu_domain *domain)
 }
 
 static int arm_smmu_assign_dev(struct domain *d, u8 devfn,
-                              struct device *dev)
+                              struct device *dev, u32 flag)
 {
        struct iommu_domain *domain;
        struct arm_smmu_xen_domain *xen_domain;
@@ -2709,7 +2709,8 @@ static int arm_smmu_reassign_dev(struct domain *s, struct domain *t,
                return ret;
 
        if (t) {
-               ret = arm_smmu_assign_dev(t, devfn, dev);
+               /* No flags are defined for ARM. */
+               ret = arm_smmu_assign_dev(t, devfn, dev, 0);
                if (ret)
                        return ret;
        }

diff --git a/xen/drivers/passthrough/device_tree.c b/xen/drivers/passthrough/device_tree.c
index 5d3842aeeaa4795e72ccd2d58ab8df5703c67fd8..7ff79f8bc36bd66ff3f3a2091a1484fd3bcd8e24 100644 (file)
--- a/xen/drivers/passthrough/device_tree.c
+++ b/xen/drivers/passthrough/device_tree.c
@@ -52,7 +52,8 @@ int iommu_assign_dt_device(struct domain *d, struct dt_device_node *dev)
             goto fail;
     }
 
-    rc = hd->platform_ops->assign_device(d, 0, dt_to_dev(dev));
+    /* The flag field doesn't matter to DT device. */
+    rc = hd->platform_ops->assign_device(d, 0, dt_to_dev(dev), 0);
 
     if ( rc )
         goto fail;

diff --git a/xen/drivers/passthrough/pci.c b/xen/drivers/passthrough/pci.c
index 863226597287077dcf9024e9e3311543a71e834b..3057b11ca589ddadfa9019f40e2b766baaf95270 100644 (file)
--- a/xen/drivers/passthrough/pci.c
+++ b/xen/drivers/passthrough/pci.c
@@ -1334,7 +1334,7 @@ static int device_assigned(u16 seg, u8 bus, u8 devfn)
     return pdev ? 0 : -EBUSY;
 }
 
-static int assign_device(struct domain *d, u16 seg, u8 bus, u8 devfn)
+static int assign_device(struct domain *d, u16 seg, u8 bus, u8 devfn, u32 flag)
 {
     struct hvm_iommu *hd = domain_hvm_iommu(d);
     struct pci_dev *pdev;
@@ -1370,7 +1370,7 @@ static int assign_device(struct domain *d, u16 seg, u8 bus, u8 devfn)
 
     pdev->fault.count = 0;
 
-    if ( (rc = hd->platform_ops->assign_device(d, devfn, pci_to_dev(pdev))) )
+    if ( (rc = hd->platform_ops->assign_device(d, devfn, pci_to_dev(pdev), flag)) )
         goto done;
 
     for ( ; pdev->phantom_stride; rc = 0 )
@@ -1378,7 +1378,7 @@ static int assign_device(struct domain *d, u16 seg, u8 bus, u8 devfn)
         devfn += pdev->phantom_stride;
         if ( PCI_SLOT(devfn) != PCI_SLOT(pdev->devfn) )
             break;
-        rc = hd->platform_ops->assign_device(d, devfn, pci_to_dev(pdev));
+        rc = hd->platform_ops->assign_device(d, devfn, pci_to_dev(pdev), flag);
         if ( rc )
             printk(XENLOG_G_WARNING "d%d: assign %04x:%02x:%02x.%u failed (%d)\n",
                    d->domain_id, seg, bus, PCI_SLOT(devfn), PCI_FUNC(devfn),
@@ -1495,6 +1495,7 @@ int iommu_do_pci_domctl(
 {
     u16 seg;
     u8 bus, devfn;
+    u32 flag;
     int ret = 0;
     uint32_t machine_sbdf;
 
@@ -1576,9 +1577,15 @@ int iommu_do_pci_domctl(
         seg = machine_sbdf >> 16;
         bus = PCI_BUS(machine_sbdf);
         devfn = PCI_DEVFN2(machine_sbdf);
+        flag = domctl->u.assign_device.flag;
+        if ( flag & ~XEN_DOMCTL_DEV_RDM_RELAXED )
+        {
+            ret = -EINVAL;
+            break;
+        }
 
         ret = device_assigned(seg, bus, devfn) ?:
-              assign_device(d, seg, bus, devfn);
+              assign_device(d, seg, bus, devfn, flag);
         if ( ret == -ERESTART )
             ret = hypercall_create_continuation(__HYPERVISOR_domctl,
                                                 "h", u_domctl);

diff --git a/xen/drivers/passthrough/vtd/iommu.c b/xen/drivers/passthrough/vtd/iommu.c
index 5aa482fe9d329906c5acd2ca9133e5dfef0078aa..a2f3a66ca0a9ea2140b4fa9c0c25f85555d0b2b7 100644 (file)
--- a/xen/drivers/passthrough/vtd/iommu.c
+++ b/xen/drivers/passthrough/vtd/iommu.c
@@ -1807,7 +1807,8 @@ static void iommu_set_pgd(struct domain *d)
 }
 
 static int rmrr_identity_mapping(struct domain *d, bool_t map,
-                                 const struct acpi_rmrr_unit *rmrr)
+                                 const struct acpi_rmrr_unit *rmrr,
+                                 u32 flag)
 {
     unsigned long base_pfn = rmrr->base_address >> PAGE_SHIFT_4K;
     unsigned long end_pfn = PAGE_ALIGN_4K(rmrr->end_address) >> PAGE_SHIFT_4K;
@@ -1855,7 +1856,7 @@ static int rmrr_identity_mapping(struct domain *d, bool_t map,
 
     while ( base_pfn < end_pfn )
     {
-        int err = set_identity_p2m_entry(d, base_pfn, p2m_access_rw);
+        int err = set_identity_p2m_entry(d, base_pfn, p2m_access_rw, flag);
 
         if ( err )
             return err;
@@ -1898,7 +1899,13 @@ static int intel_iommu_add_device(u8 devfn, struct pci_dev *pdev)
              PCI_BUS(bdf) == pdev->bus &&
              PCI_DEVFN2(bdf) == devfn )
         {
-            ret = rmrr_identity_mapping(pdev->domain, 1, rmrr);
+            /*
+             * iommu_add_device() is only called for the hardware
+             * domain (see xen/drivers/passthrough/pci.c:pci_add_device()).
+             * Since RMRRs are always reserved in the e820 map for the hardware
+             * domain, there shouldn't be a conflict.
+             */
+            ret = rmrr_identity_mapping(pdev->domain, 1, rmrr, 0);
             if ( ret )
                 dprintk(XENLOG_ERR VTDPREFIX, "d%d: RMRR mapping failed\n",
                         pdev->domain->domain_id);
@@ -1939,7 +1946,11 @@ static int intel_iommu_remove_device(u8 devfn, struct pci_dev *pdev)
              PCI_DEVFN2(bdf) != devfn )
             continue;
 
-        rmrr_identity_mapping(pdev->domain, 0, rmrr);
+        /*
+         * Any flag is nothing to clear these mappings but here
+         * its always safe and strict to set 0.
+         */
+        rmrr_identity_mapping(pdev->domain, 0, rmrr, 0);
     }
 
     return domain_context_unmap(pdev->domain, devfn, pdev);
@@ -2097,7 +2108,13 @@ static void __hwdom_init setup_hwdom_rmrr(struct domain *d)
     spin_lock(&pcidevs_lock);
     for_each_rmrr_device ( rmrr, bdf, i )
     {
-        ret = rmrr_identity_mapping(d, 1, rmrr);
+        /*
+         * Here means we're add a device to the hardware domain.
+         * Since RMRRs are always reserved in the e820 map for the hardware
+         * domain, there shouldn't be a conflict. So its always safe and
+         * strict to set 0.
+         */
+        ret = rmrr_identity_mapping(d, 1, rmrr, 0);
         if ( ret )
             dprintk(XENLOG_ERR VTDPREFIX,
                      "IOMMU: mapping reserved region failed\n");
@@ -2240,7 +2257,11 @@ static int reassign_device_ownership(
                  PCI_BUS(bdf) == pdev->bus &&
                  PCI_DEVFN2(bdf) == devfn )
             {
-                ret = rmrr_identity_mapping(source, 0, rmrr);
+                /*
+                 * Any RMRR flag is always ignored when remove a device,
+                 * but its always safe and strict to set 0.
+                 */
+                ret = rmrr_identity_mapping(source, 0, rmrr, 0);
                 if ( ret != -ENOENT )
                     return ret;
             }
@@ -2264,7 +2285,7 @@ static int reassign_device_ownership(
 }
 
 static int intel_iommu_assign_device(
-    struct domain *d, u8 devfn, struct pci_dev *pdev)
+    struct domain *d, u8 devfn, struct pci_dev *pdev, u32 flag)
 {
     struct acpi_rmrr_unit *rmrr;
     int ret = 0, i;
@@ -2293,7 +2314,7 @@ static int intel_iommu_assign_device(
              PCI_BUS(bdf) == bus &&
              PCI_DEVFN2(bdf) == devfn )
         {
-            ret = rmrr_identity_mapping(d, 1, rmrr);
+            ret = rmrr_identity_mapping(d, 1, rmrr, flag);
             if ( ret )
             {
                 reassign_device_ownership(d, hardware_domain, devfn, pdev);

diff --git a/xen/include/asm-x86/p2m.h b/xen/include/asm-x86/p2m.h
index 190a2869f1b284e1d5d46d6c820386fecc5c795a..68da0a96fa0678701b68af77584bfaa98c7ddaca 100644 (file)
--- a/xen/include/asm-x86/p2m.h
+++ b/xen/include/asm-x86/p2m.h
@@ -545,7 +545,7 @@ int clear_mmio_p2m_entry(struct domain *d, unsigned long gfn, mfn_t mfn);
 
 /* Set identity addresses in the p2m table (for pass-through) */
 int set_identity_p2m_entry(struct domain *d, unsigned long gfn,
-                           p2m_access_t p2ma);
+                           p2m_access_t p2ma, unsigned int flag);
 
 #define clear_identity_p2m_entry(d, gfn, page_order) \
                         guest_physmap_remove_page(d, gfn, gfn, page_order)

diff --git a/xen/include/public/domctl.h b/xen/include/public/domctl.h
index 631935ac15b2bc9624fcf57d7fc313986c68f4d9..675f021c27a5984a8818e916e5a3fc9c6314d2f6 100644 (file)
--- a/xen/include/public/domctl.h
+++ b/xen/include/public/domctl.h
@@ -471,6 +471,9 @@ struct xen_domctl_assign_device {
             XEN_GUEST_HANDLE_64(char) path; /* path to the device tree node */
         } dt;
     } u;
+    /* IN */
+#define XEN_DOMCTL_DEV_RDM_RELAXED      1
+    uint32_t  flag;   /* flag of assigned device */
 };
 typedef struct xen_domctl_assign_device xen_domctl_assign_device_t;
 DEFINE_XEN_GUEST_HANDLE(xen_domctl_assign_device_t);

diff --git a/xen/include/xen/iommu.h b/xen/include/xen/iommu.h
index 52ed3b70d3a1df88b4d9931f9318e2c79cd61368..1124601d38dd8efe98876eb71d6bdbf40cc8a5ab 100644 (file)
--- a/xen/include/xen/iommu.h
+++ b/xen/include/xen/iommu.h
@@ -139,7 +139,7 @@ struct iommu_ops {
     int (*add_device)(u8 devfn, device_t *dev);
     int (*enable_device)(device_t *dev);
     int (*remove_device)(u8 devfn, device_t *dev);
-    int (*assign_device)(struct domain *, u8 devfn, device_t *dev);
+    int (*assign_device)(struct domain *, u8 devfn, device_t *dev, u32 flag);
     int (*reassign_device)(struct domain *s, struct domain *t,
                            u8 devfn, device_t *dev);
 #ifdef HAS_PCI