pc & q35: Add new machine opt max-ram-below-4g

This is a pc & q35 only machine opt.

If you add enough PCI devices then all mmio for them will not fit
below 4G which may not be the layout the user wanted. This allows
you to increase the below 4G address space that PCI devices can use
(aka decrease ram below 4G) and therefore in more cases not have any
mmio that is above 4G.

For example using "-machine pc,max-ram-below-4g=2G" on the command
line will limit the amount of ram that is below 4G to 2G.

Note: this machine option cannot be used to increase the amount
of ram below 4G.

Signed-off-by: Don Slutz <dslutz@verizon.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

MST: fix 32 bit

5 files changed, 96 insertions, 2 deletions

diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 67eb45089e..2cf22b1293 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -1643,11 +1643,58 @@ pc_machine_get_hotplug_memory_region_size(Object *obj, Visitor *v, void *opaque,
     visit_type_int(v, &value, name, errp);
 }
 
+static void pc_machine_get_max_ram_below_4g(Object *obj, Visitor *v,
+                                         void *opaque, const char *name,
+                                         Error **errp)
+{
+    PCMachineState *pcms = PC_MACHINE(obj);
+    uint64_t value = pcms->max_ram_below_4g;
+
+    visit_type_size(v, &value, name, errp);
+}
+
+static void pc_machine_set_max_ram_below_4g(Object *obj, Visitor *v,
+                                         void *opaque, const char *name,
+                                         Error **errp)
+{
+    PCMachineState *pcms = PC_MACHINE(obj);
+    Error *error = NULL;
+    uint64_t value;
+
+    visit_type_size(v, &value, name, &error);
+    if (error) {
+        error_propagate(errp, error);
+        return;
+    }
+    if (value > (1ULL << 32)) {
+        error_set(&error, ERROR_CLASS_GENERIC_ERROR,
+                  "Machine option 'max-ram-below-4g=%"PRIu64
+                  "' expects size less than or equal to 4G", value);
+        error_propagate(errp, error);
+        return;
+    }
+
+    if (value < (1ULL << 20)) {
+        error_report("Warning: small max_ram_below_4g(%"PRIu64
+                     ") less than 1M.  BIOS may not work..",
+                     value);
+    }
+
+    pcms->max_ram_below_4g = value;
+}
+
 static void pc_machine_initfn(Object *obj)
 {
+    PCMachineState *pcms = PC_MACHINE(obj);
+
     object_property_add(obj, PC_MACHINE_MEMHP_REGION_SIZE, "int",
                         pc_machine_get_hotplug_memory_region_size,
                         NULL, NULL, NULL, NULL);
+    pcms->max_ram_below_4g = 1ULL << 32; /* 4G */
+    object_property_add(obj, PC_MACHINE_MAX_RAM_BELOW_4G, "size",
+                        pc_machine_get_max_ram_below_4g,
+                        pc_machine_set_max_ram_below_4g,
+                        NULL, NULL, NULL);
 }
 
 static void pc_machine_class_init(ObjectClass *oc, void *data)
diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index 60057f9de4..47546b72ae 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -48,6 +48,7 @@
 #include "exec/address-spaces.h"
 #include "hw/acpi/acpi.h"
 #include "cpu.h"
+#include "qemu/error-report.h"
 #ifdef CONFIG_XEN
 #  include <xen/hvm/hvm_info_table.h>
 #endif
@@ -98,6 +99,7 @@ static void pc_init1(MachineState *machine,
     DeviceState *icc_bridge;
     FWCfgState *fw_cfg = NULL;
     PcGuestInfo *guest_info;
+    ram_addr_t lowmem;
 
     /* Check whether RAM fits below 4G (leaving 1/2 GByte for IO memory).
      * If it doesn't, we need to split it in chunks below and above 4G.
@@ -107,7 +109,25 @@ static void pc_init1(MachineState *machine,
      * breaking migration.
      */
     if (machine->ram_size >= 0xe0000000) {
-        ram_addr_t lowmem = gigabyte_align ? 0xc0000000 : 0xe0000000;
+        lowmem = gigabyte_align ? 0xc0000000 : 0xe0000000;
+    } else {
+        lowmem = 0xe0000000;
+    }
+
+    /* Handle the machine opt max-ram-below-4g.  It is basicly doing
+     * min(qemu limit, user limit).
+     */
+    if (lowmem > pc_machine->max_ram_below_4g) {
+        lowmem = pc_machine->max_ram_below_4g;
+        if (machine->ram_size - lowmem > lowmem &&
+            lowmem & ((1ULL << 30) - 1)) {
+            error_report("Warning: Large machine and max_ram_below_4g(%"PRIu64
+                         ") not a multiple of 1G; possible bad performance.",
+                         pc_machine->max_ram_below_4g);
+        }
+    }
+
+    if (machine->ram_size >= lowmem) {
         above_4g_mem_size = machine->ram_size - lowmem;
         below_4g_mem_size = lowmem;
     } else {
diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index da5fd53304..155db99f63 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -44,6 +44,7 @@
 #include "hw/ide/ahci.h"
 #include "hw/usb.h"
 #include "hw/cpu/icc_bus.h"
+#include "qemu/error-report.h"
 
 /* ICH9 AHCI has 6 ports */
 #define MAX_SATA_PORTS     6
@@ -85,6 +86,7 @@ static void pc_q35_init(MachineState *machine)
     PCIDevice *ahci;
     DeviceState *icc_bridge;
     PcGuestInfo *guest_info;
+    ram_addr_t lowmem;
 
     /* Check whether RAM fits below 4G (leaving 1/2 GByte for IO memory
      * and 256 Mbytes for PCI Express Enhanced Configuration Access Mapping
@@ -96,7 +98,25 @@ static void pc_q35_init(MachineState *machine)
      * breaking migration.
      */
     if (machine->ram_size >= 0xb0000000) {
-        ram_addr_t lowmem = gigabyte_align ? 0x80000000 : 0xb0000000;
+        lowmem = gigabyte_align ? 0x80000000 : 0xb0000000;
+    } else {
+        lowmem = 0xb0000000;
+    }
+
+    /* Handle the machine opt max-ram-below-4g.  It is basicly doing
+     * min(qemu limit, user limit).
+     */
+    if (lowmem > pc_machine->max_ram_below_4g) {
+        lowmem = pc_machine->max_ram_below_4g;
+        if (machine->ram_size - lowmem > lowmem &&
+            lowmem & ((1ULL << 30) - 1)) {
+            error_report("Warning: Large machine and max_ram_below_4g(%"PRIu64
+                         ") not a multiple of 1G; possible bad performance.",
+                         pc_machine->max_ram_below_4g);
+        }
+    }
+
+    if (machine->ram_size >= lowmem) {
         above_4g_mem_size = machine->ram_size - lowmem;
         below_4g_mem_size = lowmem;
     } else {
diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h
index 651971d1cc..486e98feac 100644
--- a/include/hw/i386/pc.h
+++ b/include/hw/i386/pc.h
@@ -33,10 +33,13 @@ struct PCMachineState {
     MemoryRegion hotplug_memory;
 
     HotplugHandler *acpi_dev;
+
+    uint64_t max_ram_below_4g;
 };
 
 #define PC_MACHINE_ACPI_DEVICE_PROP "acpi-device"
 #define PC_MACHINE_MEMHP_REGION_SIZE "hotplug-memory-region-size"
+#define PC_MACHINE_MAX_RAM_BELOW_4G "max-ram-below-4g"
 
 /**
  * PCMachineClass:
diff --git a/vl.c b/vl.c
index ab8f15243b..194c6f79a3 100644
--- a/vl.c
+++ b/vl.c
@@ -381,6 +381,10 @@ static QemuOptsList qemu_machine_opts = {
             .name = "kvm-type",
             .type = QEMU_OPT_STRING,
             .help = "Specifies the KVM virtualization mode (HV, PR)",
+        },{
+            .name = PC_MACHINE_MAX_RAM_BELOW_4G,
+            .type = QEMU_OPT_SIZE,
+            .help = "maximum ram below the 4G boundary (32bit boundary)",
         },
         { /* End of list */ }
     },