From: "Matthew R. Ochs" <mochs@nvidia.com>

The MMIO region size required to support virtualized environments with
large PCI BAR regions can exceed the hardcoded limit configured in QEMU.
For example, a VM with multiple NVIDIA Grace-Hopper GPUs passed through
requires more MMIO memory than the amount provided by VIRT_HIGH_PCIE_MMIO
(currently 512GB). Instead of updating VIRT_HIGH_PCIE_MMIO, introduce a
new parameter, highmem-mmio-size, that specifies the MMIO size required
to support the VM configuration.

Example usage with 1TB MMIO region size:
	-machine virt,gic-version=3,highmem-mmio-size=1T

Signed-off-by: Matthew R. Ochs <mochs@nvidia.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Nicolin Chen <nicolinc@nvidia.com>
Message-id: 20250221145419.1281890-1-mochs@nvidia.com
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 docs/system/arm/virt.rst |  4 ++++
 hw/arm/virt.c            | 52 +++++++++++++++++++++++++++++++++++++++-
 2 files changed, 55 insertions(+), 1 deletion(-)

diff --git a/docs/system/arm/virt.rst b/docs/system/arm/virt.rst
index 0c9c2ce0351..adf446c0a29 100644
--- a/docs/system/arm/virt.rst
+++ b/docs/system/arm/virt.rst
@@ -144,6 +144,10 @@ highmem-mmio
   Set ``on``/``off`` to enable/disable the high memory region for PCI MMIO.
   The default is ``on``.
 
+highmem-mmio-size
+  Set the high memory region size for PCI MMIO. Must be a power of 2 and
+  greater than or equal to the default size (512G).
+
 gic-version
   Specify the version of the Generic Interrupt Controller (GIC) to provide.
   Valid values are:
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 4a5a9666e91..ee69081ef42 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -53,6 +53,7 @@
 #include "hw/loader.h"
 #include "qapi/error.h"
 #include "qemu/bitops.h"
+#include "qemu/cutils.h"
 #include "qemu/error-report.h"
 #include "qemu/module.h"
 #include "hw/pci-host/gpex.h"
@@ -192,6 +193,10 @@ static const MemMapEntry base_memmap[] = {
     [VIRT_MEM] =                { GiB, LEGACY_RAMLIMIT_BYTES },
 };
 
+/* Update the docs for highmem-mmio-size when changing this default */
+#define DEFAULT_HIGH_PCIE_MMIO_SIZE_GB 512
+#define DEFAULT_HIGH_PCIE_MMIO_SIZE (DEFAULT_HIGH_PCIE_MMIO_SIZE_GB * GiB)
+
 /*
  * Highmem IO Regions: This memory map is floating, located after the RAM.
  * Each MemMapEntry base (GPA) will be dynamically computed, depending on the
@@ -207,13 +212,16 @@ static const MemMapEntry base_memmap[] = {
  * PA space for one specific region is always reserved, even if the region
  * has been disabled or doesn't fit into the PA space. However, the PA space
  * for the region won't be reserved in these circumstances with compact layout.
+ *
+ * Note that the highmem-mmio-size property will update the high PCIE MMIO size
+ * field in this array.
  */
 static MemMapEntry extended_memmap[] = {
     /* Additional 64 MB redist region (can contain up to 512 redistributors) */
     [VIRT_HIGH_GIC_REDIST2] =   { 0x0, 64 * MiB },
     [VIRT_HIGH_PCIE_ECAM] =     { 0x0, 256 * MiB },
     /* Second PCIe window */
-    [VIRT_HIGH_PCIE_MMIO] =     { 0x0, 512 * GiB },
+    [VIRT_HIGH_PCIE_MMIO] =     { 0x0, DEFAULT_HIGH_PCIE_MMIO_SIZE },
 };
 
 static const int a15irqmap[] = {
@@ -2550,6 +2558,40 @@ static void virt_set_highmem_mmio(Object *obj, bool value, Error **errp)
     vms->highmem_mmio = value;
 }
 
+static void virt_get_highmem_mmio_size(Object *obj, Visitor *v,
+                                       const char *name, void *opaque,
+                                       Error **errp)
+{
+    uint64_t size = extended_memmap[VIRT_HIGH_PCIE_MMIO].size;
+
+    visit_type_size(v, name, &size, errp);
+}
+
+static void virt_set_highmem_mmio_size(Object *obj, Visitor *v,
+                                       const char *name, void *opaque,
+                                       Error **errp)
+{
+    uint64_t size;
+
+    if (!visit_type_size(v, name, &size, errp)) {
+        return;
+    }
+
+    if (!is_power_of_2(size)) {
+        error_setg(errp, "highmem-mmio-size is not a power of 2");
+        return;
+    }
+
+    if (size < DEFAULT_HIGH_PCIE_MMIO_SIZE) {
+        char *sz = size_to_str(DEFAULT_HIGH_PCIE_MMIO_SIZE);
+        error_setg(errp, "highmem-mmio-size cannot be set to a lower value "
+                         "than the default (%s)", sz);
+        g_free(sz);
+        return;
+    }
+
+    extended_memmap[VIRT_HIGH_PCIE_MMIO].size = size;
+}
 
 static bool virt_get_its(Object *obj, Error **errp)
 {
@@ -3207,6 +3249,14 @@ static void virt_machine_class_init(ObjectClass *oc, void *data)
                                           "Set on/off to enable/disable high "
                                           "memory region for PCI MMIO");
 
+    object_class_property_add(oc, "highmem-mmio-size", "size",
+                                   virt_get_highmem_mmio_size,
+                                   virt_set_highmem_mmio_size,
+                                   NULL, NULL);
+    object_class_property_set_description(oc, "highmem-mmio-size",
+                                          "Set the high memory region size "
+                                          "for PCI MMIO");
+
     object_class_property_add_str(oc, "gic-version", virt_get_gic_version,
                                   virt_set_gic_version);
     object_class_property_set_description(oc, "gic-version",
-- 
2.43.0