1 files changed, 91 insertions, 10 deletions

diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c
index ebc5f034e3..10b84d039b 100644
--- a/hw/i386/acpi-build.c
+++ b/hw/i386/acpi-build.c
@@ -25,7 +25,9 @@
 #include <glib.h>
 #include "qemu-common.h"
 #include "qemu/bitmap.h"
+#include "qemu/osdep.h"
 #include "qemu/range.h"
+#include "qemu/error-report.h"
 #include "hw/pci/pci.h"
 #include "qom/cpu.h"
 #include "hw/i386/pc.h"
@@ -52,6 +54,16 @@
 #include "qapi/qmp/qint.h"
 #include "qom/qom-qobject.h"
 
+/* These are used to size the ACPI tables for -M pc-i440fx-1.7 and
+ * -M pc-i440fx-2.0.  Even if the actual amount of AML generated grows
+ * a little bit, there should be plenty of free space since the DSDT
+ * shrunk by ~1.5k between QEMU 2.0 and QEMU 2.1.
+ */
+#define ACPI_BUILD_LEGACY_CPU_AML_SIZE    97
+#define ACPI_BUILD_ALIGN_SIZE             0x1000
+
+#define ACPI_BUILD_TABLE_SIZE             0x20000
+
 typedef struct AcpiCpuInfo {
     DECLARE_BITMAP(found_cpus, ACPI_CPU_HOTPLUG_ID_LIMIT);
 } AcpiCpuInfo;
@@ -64,6 +76,7 @@ typedef struct AcpiMcfgInfo {
 typedef struct AcpiPmInfo {
     bool s3_disabled;
     bool s4_disabled;
+    bool pcihp_bridge_en;
     uint8_t s4_val;
     uint16_t sci_int;
     uint8_t acpi_enable_cmd;
@@ -85,6 +98,7 @@ typedef struct AcpiBuildPciBusHotplugState {
     GArray *device_table;
     GArray *notify_table;
     struct AcpiBuildPciBusHotplugState *parent;
+    bool pcihp_bridge_en;
 } AcpiBuildPciBusHotplugState;
 
 static void acpi_get_dsdt(AcpiMiscInfo *info)
@@ -188,6 +202,9 @@ static void acpi_get_pm_info(AcpiPmInfo *pm)
                                            NULL);
     pm->gpe0_blk_len = object_property_get_int(obj, ACPI_PM_PROP_GPE0_BLK_LEN,
                                                NULL);
+    pm->pcihp_bridge_en =
+        object_property_get_bool(obj, "acpi-pci-hotplug-with-bridge-support",
+                                 NULL);
 }
 
 static void acpi_get_misc_info(AcpiMiscInfo *info)
@@ -768,11 +785,13 @@ static void acpi_set_pci_info(void)
 }
 
 static void build_pci_bus_state_init(AcpiBuildPciBusHotplugState *state,
-                                     AcpiBuildPciBusHotplugState *parent)
+                                     AcpiBuildPciBusHotplugState *parent,
+                                     bool pcihp_bridge_en)
 {
     state->parent = parent;
     state->device_table = build_alloc_array();
     state->notify_table = build_alloc_array();
+    state->pcihp_bridge_en = pcihp_bridge_en;
 }
 
 static void build_pci_bus_state_cleanup(AcpiBuildPciBusHotplugState *state)
@@ -786,7 +805,7 @@ static void *build_pci_bus_begin(PCIBus *bus, void *parent_state)
     AcpiBuildPciBusHotplugState *parent = parent_state;
     AcpiBuildPciBusHotplugState *child = g_malloc(sizeof *child);
 
-    build_pci_bus_state_init(child, parent);
+    build_pci_bus_state_init(child, parent, parent->pcihp_bridge_en);
 
     return child;
 }
@@ -807,6 +826,14 @@ static void build_pci_bus_end(PCIBus *bus, void *bus_state)
     GArray *method;
     bool bus_hotplug_support = false;
 
+    /*
+     * Skip bridge subtree creation if bridge hotplug is disabled
+     * to make acpi tables compatible with legacy machine types.
+     */
+    if (!child->pcihp_bridge_en && bus->parent_dev) {
+        return;
+    }
+
     if (bus->parent_dev) {
         op = 0x82; /* DeviceOp */
         build_append_nameseg(bus_table, "S%.02X_",
@@ -844,6 +871,7 @@ static void build_pci_bus_end(PCIBus *bus, void *bus_state)
         PCIDeviceClass *pc;
         PCIDevice *pdev = bus->devices[i];
         int slot = PCI_SLOT(i);
+        bool bridge_in_acpi;
 
         if (!pdev) {
             continue;
@@ -853,7 +881,13 @@ static void build_pci_bus_end(PCIBus *bus, void *bus_state)
         pc = PCI_DEVICE_GET_CLASS(pdev);
         dc = DEVICE_GET_CLASS(pdev);
 
-        if (pc->class_id == PCI_CLASS_BRIDGE_ISA || pc->is_bridge) {
+        /* When hotplug for bridges is enabled, bridges are
+         * described in ACPI separately (see build_pci_bus_end).
+         * In this case they aren't themselves hot-pluggable.
+         */
+        bridge_in_acpi = pc->is_bridge && child->pcihp_bridge_en;
+
+        if (pc->class_id == PCI_CLASS_BRIDGE_ISA || bridge_in_acpi) {
             set_bit(slot, slot_device_system);
         }
 
@@ -865,7 +899,7 @@ static void build_pci_bus_end(PCIBus *bus, void *bus_state)
             }
         }
 
-        if (!dc->hotpluggable || pc->is_bridge) {
+        if (!dc->hotpluggable || bridge_in_acpi) {
             clear_bit(slot, slot_hotplug_enable);
         }
     }
@@ -1130,7 +1164,7 @@ build_ssdt(GArray *table_data, GArray *linker,
                 bus = PCI_HOST_BRIDGE(pci_host)->bus;
             }
 
-            build_pci_bus_state_init(&hotplug_state, NULL);
+            build_pci_bus_state_init(&hotplug_state, NULL, pm->pcihp_bridge_en);
 
             if (bus) {
                 /* Scan all PCI buses. Generate tables to support hotplug. */
@@ -1359,7 +1393,7 @@ build_rsdp(GArray *rsdp_table, GArray *linker, unsigned rsdt)
 {
     AcpiRsdpDescriptor *rsdp = acpi_data_push(rsdp_table, sizeof *rsdp);
 
-    bios_linker_loader_alloc(linker, ACPI_BUILD_RSDP_FILE, 1,
+    bios_linker_loader_alloc(linker, ACPI_BUILD_RSDP_FILE, 16,
                              true /* fseg memory */);
 
     memcpy(&rsdp->signature, "RSD PTR ", 8);
@@ -1440,13 +1474,14 @@ static
 void acpi_build(PcGuestInfo *guest_info, AcpiBuildTables *tables)
 {
     GArray *table_offsets;
-    unsigned facs, dsdt, rsdt;
+    unsigned facs, ssdt, dsdt, rsdt;
     AcpiCpuInfo cpu;
     AcpiPmInfo pm;
     AcpiMiscInfo misc;
     AcpiMcfgInfo mcfg;
     PcPciInfo pci;
     uint8_t *u;
+    size_t aml_len = 0;
 
     acpi_get_cpu_info(&cpu);
     acpi_get_pm_info(&pm);
@@ -1474,13 +1509,20 @@ void acpi_build(PcGuestInfo *guest_info, AcpiBuildTables *tables)
     dsdt = tables->table_data->len;
     build_dsdt(tables->table_data, tables->linker, &misc);
 
+    /* Count the size of the DSDT and SSDT, we will need it for legacy
+     * sizing of ACPI tables.
+     */
+    aml_len += tables->table_data->len - dsdt;
+
     /* ACPI tables pointed to by RSDT */
     acpi_add_table(table_offsets, tables->table_data);
     build_fadt(tables->table_data, tables->linker, &pm, facs, dsdt);
 
+    ssdt = tables->table_data->len;
     acpi_add_table(table_offsets, tables->table_data);
     build_ssdt(tables->table_data, tables->linker, &cpu, &pm, &misc, &pci,
                guest_info);
+    aml_len += tables->table_data->len - ssdt;
 
     acpi_add_table(table_offsets, tables->table_data);
     build_madt(tables->table_data, tables->linker, &cpu, guest_info);
@@ -1513,14 +1555,53 @@ void acpi_build(PcGuestInfo *guest_info, AcpiBuildTables *tables)
     /* RSDP is in FSEG memory, so allocate it separately */
     build_rsdp(tables->rsdp, tables->linker, rsdt);
 
-    /* We'll expose it all to Guest so align size to reduce
+    /* We'll expose it all to Guest so we want to reduce
      * chance of size changes.
      * RSDP is small so it's easy to keep it immutable, no need to
      * bother with alignment.
+     *
+     * We used to align the tables to 4k, but of course this would
+     * too simple to be enough.  4k turned out to be too small an
+     * alignment very soon, and in fact it is almost impossible to
+     * keep the table size stable for all (max_cpus, max_memory_slots)
+     * combinations.  So the table size is always 64k for pc-i440fx-2.1
+     * and we give an error if the table grows beyond that limit.
+     *
+     * We still have the problem of migrating from "-M pc-i440fx-2.0".  For
+     * that, we exploit the fact that QEMU 2.1 generates _smaller_ tables
+     * than 2.0 and we can always pad the smaller tables with zeros.  We can
+     * then use the exact size of the 2.0 tables.
+     *
+     * All this is for PIIX4, since QEMU 2.0 didn't support Q35 migration.
      */
-    acpi_align_size(tables->table_data, 0x1000);
+    if (guest_info->legacy_acpi_table_size) {
+        /* Subtracting aml_len gives the size of fixed tables.  Then add the
+         * size of the PIIX4 DSDT/SSDT in QEMU 2.0.
+         */
+        int legacy_aml_len =
+            guest_info->legacy_acpi_table_size +
+            ACPI_BUILD_LEGACY_CPU_AML_SIZE * max_cpus;
+        int legacy_table_size =
+            ROUND_UP(tables->table_data->len - aml_len + legacy_aml_len,
+                     ACPI_BUILD_ALIGN_SIZE);
+        if (tables->table_data->len > legacy_table_size) {
+            /* Should happen only with PCI bridges and -M pc-i440fx-2.0.  */
+            error_report("Warning: migration may not work.");
+        }
+        g_array_set_size(tables->table_data, legacy_table_size);
+    } else {
+        /* Make sure we have a buffer in case we need to resize the tables. */
+        if (tables->table_data->len > ACPI_BUILD_TABLE_SIZE / 2) {
+            /* As of QEMU 2.1, this fires with 160 VCPUs and 255 memory slots.  */
+            error_report("Warning: ACPI tables are larger than 64k.");
+            error_report("Warning: migration may not work.");
+            error_report("Warning: please remove CPUs, NUMA nodes, "
+                         "memory slots or PCI bridges.");
+        }
+        acpi_align_size(tables->table_data, ACPI_BUILD_TABLE_SIZE);
+    }
 
-    acpi_align_size(tables->linker, 0x1000);
+    acpi_align_size(tables->linker, ACPI_BUILD_ALIGN_SIZE);
 
     /* Cleanup memory that's no longer used. */
     g_array_free(table_offsets, true);