Re: [RFC][PATCH 02/13] introduce XENMEM_reserved_device_memory_map

["Jan Beulich" <JBeulich@suse.com>]

>>> On 23.04.15 at 14:32, <tiejun.chen@intel.com> wrote:
> But if you already have one just please ignore this and tell me

Here's what I currently have:

introduce XENMEM_reserved_device_memory_map

This is a prerequisite for punching holes into HVM and PVH guests' P2M
to allow passing through devices that are associated with (on VT-d)
RMRRs.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Kevin Tian <kevin.tian@intel.com>
---
v??: Comment iommu_grdm_t typedef. Comment on the purpose of the new
     hypercall in the public header. (Both requested by Tim.)

--- unstable.orig/xen/common/compat/memory.c
+++ unstable/xen/common/compat/memory.c
@@ -17,6 +17,37 @@ CHECK_TYPE(domid);
 CHECK_mem_access_op;
 CHECK_vmemrange;
 
+#ifdef HAS_PASSTHROUGH
+struct get_reserved_device_memory {
+    struct compat_reserved_device_memory_map map;
+    unsigned int used_entries;
+};
+
+static int get_reserved_device_memory(xen_pfn_t start,
+                                      xen_ulong_t nr, void *ctxt)
+{
+    struct get_reserved_device_memory *grdm = ctxt;
+
+    if ( grdm->used_entries < grdm->map.nr_entries )
+    {
+        struct compat_reserved_device_memory rdm = {
+            .start_pfn = start, .nr_pages = nr
+        };
+
+        if ( rdm.start_pfn != start || rdm.nr_pages != nr )
+            return -ERANGE;
+
+        if ( __copy_to_compat_offset(grdm->map.buffer, grdm->used_entries,
+                                     &rdm, 1) )
+            return -EFAULT;
+    }
+
+    ++grdm->used_entries;
+
+    return 0;
+}
+#endif
+
 int compat_memory_op(unsigned int cmd, XEN_GUEST_HANDLE_PARAM(void) compat)
 {
     int split, op = cmd & MEMOP_CMD_MASK;
@@ -303,6 +334,29 @@ int compat_memory_op(unsigned int cmd, X
             break;
         }
 
+#ifdef HAS_PASSTHROUGH
+        case XENMEM_reserved_device_memory_map:
+        {
+            struct get_reserved_device_memory grdm;
+
+            if ( copy_from_guest(&grdm.map, compat, 1) ||
+                 !compat_handle_okay(grdm.map.buffer, grdm.map.nr_entries) )
+                return -EFAULT;
+
+            grdm.used_entries = 0;
+            rc = iommu_get_reserved_device_memory(get_reserved_device_memory,
+                                                  &grdm);
+
+            if ( !rc && grdm.map.nr_entries < grdm.used_entries )
+                rc = -ENOBUFS;
+            grdm.map.nr_entries = grdm.used_entries;
+            if ( __copy_to_guest(compat, &grdm.map, 1) )
+                rc = -EFAULT;
+
+            return rc;
+        }
+#endif
+
         default:
             return compat_arch_memory_op(cmd, compat);
         }
--- unstable.orig/xen/common/memory.c
+++ unstable/xen/common/memory.c
@@ -748,6 +748,34 @@ static int construct_memop_from_reservat
     return 0;
 }
 
+#ifdef HAS_PASSTHROUGH
+struct get_reserved_device_memory {
+    struct xen_reserved_device_memory_map map;
+    unsigned int used_entries;
+};
+
+static int get_reserved_device_memory(xen_pfn_t start,
+                                      xen_ulong_t nr, void *ctxt)
+{
+    struct get_reserved_device_memory *grdm = ctxt;
+
+    if ( grdm->used_entries < grdm->map.nr_entries )
+    {
+        struct xen_reserved_device_memory rdm = {
+            .start_pfn = start, .nr_pages = nr
+        };
+
+        if ( __copy_to_guest_offset(grdm->map.buffer, grdm->used_entries,
+                                    &rdm, 1) )
+            return -EFAULT;
+    }
+
+    ++grdm->used_entries;
+
+    return 0;
+}
+#endif
+
 long do_memory_op(unsigned long cmd, XEN_GUEST_HANDLE_PARAM(void) arg)
 {
     struct domain *d;
@@ -1162,6 +1190,32 @@ long do_memory_op(unsigned long cmd, XEN
         break;
     }
 
+#ifdef HAS_PASSTHROUGH
+    case XENMEM_reserved_device_memory_map:
+    {
+        struct get_reserved_device_memory grdm;
+
+        if ( unlikely(start_extent) )
+            return -ENOSYS;
+
+        if ( copy_from_guest(&grdm.map, arg, 1) ||
+             !guest_handle_okay(grdm.map.buffer, grdm.map.nr_entries) )
+            return -EFAULT;
+
+        grdm.used_entries = 0;
+        rc = iommu_get_reserved_device_memory(get_reserved_device_memory,
+                                              &grdm);
+
+        if ( !rc && grdm.map.nr_entries < grdm.used_entries )
+            rc = -ENOBUFS;
+        grdm.map.nr_entries = grdm.used_entries;
+        if ( __copy_to_guest(arg, &grdm.map, 1) )
+            rc = -EFAULT;
+
+        break;
+    }
+#endif
+
     default:
         rc = arch_memory_op(cmd, arg);
         break;
--- unstable.orig/xen/drivers/passthrough/iommu.c
+++ unstable/xen/drivers/passthrough/iommu.c
@@ -344,6 +344,16 @@ void iommu_crash_shutdown(void)
     iommu_enabled = iommu_intremap = 0;
 }
 
+int iommu_get_reserved_device_memory(iommu_grdm_t *func, void *ctxt)
+{
+    const struct iommu_ops *ops = iommu_get_ops();
+
+    if ( !iommu_enabled || !ops->get_reserved_device_memory )
+        return 0;
+
+    return ops->get_reserved_device_memory(func, ctxt);
+}
+
 bool_t iommu_has_feature(struct domain *d, enum iommu_feature feature)
 {
     const struct hvm_iommu *hd = domain_hvm_iommu(d);
--- unstable.orig/xen/drivers/passthrough/vtd/dmar.c
+++ unstable/xen/drivers/passthrough/vtd/dmar.c
@@ -893,3 +893,20 @@ int platform_supports_x2apic(void)
     unsigned int mask = ACPI_DMAR_INTR_REMAP | ACPI_DMAR_X2APIC_OPT_OUT;
     return cpu_has_x2apic && ((dmar_flags & mask) == ACPI_DMAR_INTR_REMAP);
 }
+
+int intel_iommu_get_reserved_device_memory(iommu_grdm_t *func, void *ctxt)
+{
+    struct acpi_rmrr_unit *rmrr;
+    int rc = 0;
+
+    list_for_each_entry(rmrr, &acpi_rmrr_units, list)
+    {
+        rc = func(PFN_DOWN(rmrr->base_address),
+                  PFN_UP(rmrr->end_address) - PFN_DOWN(rmrr->base_address),
+                  ctxt);
+        if ( rc )
+            break;
+    }
+
+    return rc;
+}
--- unstable.orig/xen/drivers/passthrough/vtd/extern.h
+++ unstable/xen/drivers/passthrough/vtd/extern.h
@@ -75,6 +75,7 @@ int domain_context_mapping_one(struct do
                                u8 bus, u8 devfn, const struct pci_dev *);
 int domain_context_unmap_one(struct domain *domain, struct iommu *iommu,
                              u8 bus, u8 devfn);
+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);
 void io_apic_write_remap_rte(unsigned int apic,
--- unstable.orig/xen/drivers/passthrough/vtd/iommu.c
+++ unstable/xen/drivers/passthrough/vtd/iommu.c
@@ -2491,6 +2491,7 @@ const struct iommu_ops intel_iommu_ops =
     .crash_shutdown = vtd_crash_shutdown,
     .iotlb_flush = intel_iommu_iotlb_flush,
     .iotlb_flush_all = intel_iommu_iotlb_flush_all,
+    .get_reserved_device_memory = intel_iommu_get_reserved_device_memory,
     .dump_p2m_table = vtd_dump_p2m_table,
 };
 
--- unstable.orig/xen/include/public/memory.h
+++ unstable/xen/include/public/memory.h
@@ -573,7 +573,29 @@ struct xen_vnuma_topology_info {
 typedef struct xen_vnuma_topology_info xen_vnuma_topology_info_t;
 DEFINE_XEN_GUEST_HANDLE(xen_vnuma_topology_info_t);
 
-/* Next available subop number is 27 */
+/*
+ * With some legacy devices, certain guest-physical addresses cannot safely
+ * be used for other purposes, e.g. to map guest RAM.  This hypercall
+ * enumerates those regions so the toolstack can avoid using them.
+ */
+#define XENMEM_reserved_device_memory_map   27
+struct xen_reserved_device_memory {
+    xen_pfn_t start_pfn;
+    xen_ulong_t nr_pages;
+};
+typedef struct xen_reserved_device_memory xen_reserved_device_memory_t;
+DEFINE_XEN_GUEST_HANDLE(xen_reserved_device_memory_t);
+
+struct xen_reserved_device_memory_map {
+    /* IN/OUT */
+    unsigned int nr_entries;
+    /* OUT */
+    XEN_GUEST_HANDLE(xen_reserved_device_memory_t) buffer;
+};
+typedef struct xen_reserved_device_memory_map xen_reserved_device_memory_map_t;
+DEFINE_XEN_GUEST_HANDLE(xen_reserved_device_memory_map_t);
+
+/* Next available subop number is 28 */
 
 #endif /* __XEN_PUBLIC_MEMORY_H__ */
 
--- unstable.orig/xen/include/xen/iommu.h
+++ unstable/xen/include/xen/iommu.h
@@ -121,6 +121,14 @@ void iommu_dt_domain_destroy(struct doma
 
 struct page_info;
 
+/*
+ * Any non-zero value returned from callbacks of this type will cause the
+ * function the callback was handed to terminate its iteration. Assigning
+ * meaning of these non-zero values is left to the top level caller /
+ * callback pair.
+ */
+typedef int iommu_grdm_t(xen_pfn_t start, xen_ulong_t nr, void *ctxt);
+
 struct iommu_ops {
     int (*init)(struct domain *d);
     void (*hwdom_init)(struct domain *d);
@@ -152,12 +160,14 @@ struct iommu_ops {
     void (*crash_shutdown)(void);
     void (*iotlb_flush)(struct domain *d, unsigned long gfn, unsigned int page_count);
     void (*iotlb_flush_all)(struct domain *d);
+    int (*get_reserved_device_memory)(iommu_grdm_t *, void *);
     void (*dump_p2m_table)(struct domain *d);
 };
 
 void iommu_suspend(void);
 void iommu_resume(void);
 void iommu_crash_shutdown(void);
+int iommu_get_reserved_device_memory(iommu_grdm_t *, void *);
 
 void iommu_share_p2m_table(struct domain *d);
 
--- unstable.orig/xen/include/xlat.lst
+++ unstable/xen/include/xlat.lst
@@ -61,9 +61,10 @@
 !	memory_exchange			memory.h
 !	memory_map			memory.h
 !	memory_reservation		memory.h
-?	mem_access_op		memory.h
+?	mem_access_op			memory.h
 !	pod_target			memory.h
 !	remove_from_physmap		memory.h
+!	reserved_device_memory_map	memory.h
 ?	vmemrange			memory.h
 !	vnuma_topology_info		memory.h
 ?	physdev_eoi			physdev.h