Merge tag 'for_upstream' of https://git.kernel.org/pub/scm/virt/kvm/mst/qemu into staging

virtio,pci: features, cleanups

vdpa:
      shadow vq vlan support
      net migration with cvq
cxl:
     support emulating 4 HDM decoders
     serial number extended capability
virtio:
      hared dma-buf

Fixes, cleanups all over the place.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

* tag 'for_upstream' of https://git.kernel.org/pub/scm/virt/kvm/mst/qemu: (53 commits)
  libvhost-user: handle shared_object msg
  vhost-user: add shared_object msg
  hw/display: introduce virtio-dmabuf
  util/uuid: add a hash function
  virtio: remove unused next argument from virtqueue_split_read_next_desc()
  virtio: remove unnecessary thread fence while reading next descriptor
  virtio: use shadow_avail_idx while checking number of heads
  libvhost-user.c: add assertion to vu_message_read_default
  pcie_sriov: unregister_vfs(): fix error path
  hw/i386/pc: improve physical address space bound check for 32-bit x86 systems
  amd_iommu: Fix APIC address check
  vdpa net: follow VirtIO initialization properly at cvq isolation probing
  vdpa net: stop probing if cannot set features
  vdpa net: fix error message setting virtio status
  hw/pci-bridge/cxl-upstream: Add serial number extended capability support
  hw/cxl: Support 4 HDM decoders at all levels of topology
  hw/cxl: Fix and use same calculation for HDM decoder block size everywhere
  hw/cxl: Add utility functions decoder interleave ways and target count.
  hw/cxl: Push cxl_decoder_count_enc() and cxl_decode_ig() into .c
  vdpa net: zero vhost_vdpa iova_tree pointer at cleanup
  ...

Conflicts:
  hw/core/machine.c
  Context conflict with commit 314e0a84cd5d ("hw/core: remove needless
  includes") because it removed an adjacent #include.

12 files changed, 48 insertions, 64 deletions

diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c
index 95199c8900..3f2b27cf75 100644
--- a/hw/i386/acpi-build.c
+++ b/hw/i386/acpi-build.c
@@ -1495,14 +1495,14 @@ build_dsdt(GArray *table_data, BIOSLinker *linker,
             aml_append(crs,
                 aml_io(
                        AML_DECODE16,
-                       ACPI_PORT_SMI_CMD,
-                       ACPI_PORT_SMI_CMD,
+                       pm->fadt.smi_cmd,
+                       pm->fadt.smi_cmd,
                        1,
                        2)
             );
             aml_append(dev, aml_name_decl("_CRS", crs));
             aml_append(dev, aml_operation_region("SMIR", AML_SYSTEM_IO,
-                aml_int(ACPI_PORT_SMI_CMD), 2));
+                aml_int(pm->fadt.smi_cmd), 2));
             field = aml_field("SMIR", AML_BYTE_ACC, AML_NOLOCK,
                               AML_WRITE_AS_ZEROS);
             aml_append(field, aml_named_field("SMIC", 8));
@@ -1549,8 +1549,8 @@ build_dsdt(GArray *table_data, BIOSLinker *linker,
             .smi_path = pm->smi_on_cpuhp ? "\\_SB.PCI0.SMI0.SMIC" : NULL,
             .fw_unplugs_cpu = pm->smi_on_cpu_unplug,
         };
-        build_cpus_aml(dsdt, machine, opts, pm->cpu_hp_io_base,
-                       "\\_SB.PCI0", "\\_GPE._E02");
+        build_cpus_aml(dsdt, machine, opts, pc_madt_cpu_entry,
+                       pm->cpu_hp_io_base, "\\_SB.PCI0", "\\_GPE._E02");
     }
 
     if (pcms->memhp_io_base && nr_mem) {
@@ -2547,8 +2547,7 @@ void acpi_build(AcpiBuildTables *tables, MachineState *machine)
 
     acpi_add_table(table_offsets, tables_blob);
     acpi_build_madt(tables_blob, tables->linker, x86ms,
-                    ACPI_DEVICE_IF(x86ms->acpi_dev), x86ms->oem_id,
-                    x86ms->oem_table_id);
+                    x86ms->oem_id, x86ms->oem_table_id);
 
 #ifdef CONFIG_ACPI_ERST
     {
diff --git a/hw/i386/acpi-common.c b/hw/i386/acpi-common.c
index 8a0932fe84..43dc23f7e0 100644
--- a/hw/i386/acpi-common.c
+++ b/hw/i386/acpi-common.c
@@ -94,14 +94,13 @@ build_xrupt_override(GArray *entry, uint8_t src, uint32_t gsi, uint16_t flags)
  * 5.2.8 Multiple APIC Description Table
  */
 void acpi_build_madt(GArray *table_data, BIOSLinker *linker,
-                     X86MachineState *x86ms, AcpiDeviceIf *adev,
+                     X86MachineState *x86ms,
                      const char *oem_id, const char *oem_table_id)
 {
     int i;
     bool x2apic_mode = false;
     MachineClass *mc = MACHINE_GET_CLASS(x86ms);
     const CPUArchIdList *apic_ids = mc->possible_cpu_arch_ids(MACHINE(x86ms));
-    AcpiDeviceIfClass *adevc = ACPI_DEVICE_IF_GET_CLASS(adev);
     AcpiTable table = { .sig = "APIC", .rev = 3, .oem_id = oem_id,
                         .oem_table_id = oem_table_id };
 
@@ -111,7 +110,7 @@ void acpi_build_madt(GArray *table_data, BIOSLinker *linker,
     build_append_int_noprefix(table_data, 1 /* PCAT_COMPAT */, 4); /* Flags */
 
     for (i = 0; i < apic_ids->len; i++) {
-        adevc->madt_cpu(i, apic_ids, table_data, false);
+        pc_madt_cpu_entry(i, apic_ids, table_data, false);
         if (apic_ids->cpus[i].arch_id > 254) {
             x2apic_mode = true;
         }
diff --git a/hw/i386/acpi-common.h b/hw/i386/acpi-common.h
index a68825acf5..b3c56ee014 100644
--- a/hw/i386/acpi-common.h
+++ b/hw/i386/acpi-common.h
@@ -1,7 +1,6 @@
 #ifndef HW_I386_ACPI_COMMON_H
 #define HW_I386_ACPI_COMMON_H
 
-#include "hw/acpi/acpi_dev_interface.h"
 #include "hw/acpi/bios-linker-loader.h"
 #include "hw/i386/x86.h"
 
@@ -9,7 +8,7 @@
 #define ACPI_BUILD_IOAPIC_ID 0x0
 
 void acpi_build_madt(GArray *table_data, BIOSLinker *linker,
-                     X86MachineState *x86ms, AcpiDeviceIf *adev,
+                     X86MachineState *x86ms,
                      const char *oem_id, const char *oem_table_id);
 
 #endif
diff --git a/hw/i386/acpi-microvm.c b/hw/i386/acpi-microvm.c
index a075360d85..fec22d85c1 100644
--- a/hw/i386/acpi-microvm.c
+++ b/hw/i386/acpi-microvm.c
@@ -214,8 +214,7 @@ static void acpi_build_microvm(AcpiBuildTables *tables,
 
     acpi_add_table(table_offsets, tables_blob);
     acpi_build_madt(tables_blob, tables->linker, X86_MACHINE(machine),
-                    ACPI_DEVICE_IF(x86ms->acpi_dev), x86ms->oem_id,
-                    x86ms->oem_table_id);
+                    x86ms->oem_id, x86ms->oem_table_id);
 
 #ifdef CONFIG_ACPI_ERST
     {
diff --git a/hw/i386/amd_iommu.c b/hw/i386/amd_iommu.c
index c98a3c6e11..8d0f2f99dd 100644
--- a/hw/i386/amd_iommu.c
+++ b/hw/i386/amd_iommu.c
@@ -1246,13 +1246,8 @@ static int amdvi_int_remap_msi(AMDVIState *iommu,
         return -AMDVI_IR_ERR;
     }
 
-    if (origin->address & AMDVI_MSI_ADDR_HI_MASK) {
-        trace_amdvi_err("MSI address high 32 bits non-zero when "
-                        "Interrupt Remapping enabled.");
-        return -AMDVI_IR_ERR;
-    }
-
-    if ((origin->address & AMDVI_MSI_ADDR_LO_MASK) != APIC_DEFAULT_ADDRESS) {
+    if (origin->address < AMDVI_INT_ADDR_FIRST ||
+        origin->address + sizeof(origin->data) > AMDVI_INT_ADDR_LAST + 1) {
         trace_amdvi_err("MSI is not from IOAPIC.");
         return -AMDVI_IR_ERR;
     }
diff --git a/hw/i386/amd_iommu.h b/hw/i386/amd_iommu.h
index 6da893ee57..c5065a3e27 100644
--- a/hw/i386/amd_iommu.h
+++ b/hw/i386/amd_iommu.h
@@ -210,8 +210,6 @@
 #define AMDVI_INT_ADDR_FIRST    0xfee00000
 #define AMDVI_INT_ADDR_LAST     0xfeefffff
 #define AMDVI_INT_ADDR_SIZE     (AMDVI_INT_ADDR_LAST - AMDVI_INT_ADDR_FIRST + 1)
-#define AMDVI_MSI_ADDR_HI_MASK  (0xffffffff00000000ULL)
-#define AMDVI_MSI_ADDR_LO_MASK  (0x00000000ffffffffULL)
 
 /* SB IOAPIC is always on this device in AMD systems */
 #define AMDVI_IOAPIC_SB_DEVID   PCI_BUILD_BDF(0, PCI_DEVFN(0x14, 0))
diff --git a/hw/i386/generic_event_device_x86.c b/hw/i386/generic_event_device_x86.c
deleted file mode 100644
index e26fb02a2e..0000000000
--- a/hw/i386/generic_event_device_x86.c
+++ /dev/null
@@ -1,36 +0,0 @@
-/*
- * x86 variant of the generic event device for hw reduced acpi
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2 or later, as published by the Free Software Foundation.
- */
-
-#include "qemu/osdep.h"
-#include "hw/acpi/generic_event_device.h"
-#include "hw/i386/pc.h"
-
-static void acpi_ged_x86_class_init(ObjectClass *class, void *data)
-{
-    AcpiDeviceIfClass *adevc = ACPI_DEVICE_IF_CLASS(class);
-
-    adevc->madt_cpu = pc_madt_cpu_entry;
-}
-
-static const TypeInfo acpi_ged_x86_info = {
-    .name          = TYPE_ACPI_GED_X86,
-    .parent        = TYPE_ACPI_GED,
-    .class_init    = acpi_ged_x86_class_init,
-    .interfaces = (InterfaceInfo[]) {
-        { TYPE_HOTPLUG_HANDLER },
-        { TYPE_ACPI_DEVICE_IF },
-        { }
-    }
-};
-
-static void acpi_ged_x86_register_types(void)
-{
-    type_register_static(&acpi_ged_x86_info);
-}
-
-type_init(acpi_ged_x86_register_types)
diff --git a/hw/i386/meson.build b/hw/i386/meson.build
index cfdbfdcbcb..ff879069c9 100644
--- a/hw/i386/meson.build
+++ b/hw/i386/meson.build
@@ -20,7 +20,6 @@ i386_ss.add(when: 'CONFIG_SGX', if_true: files('sgx-epc.c','sgx.c'),
                                 if_false: files('sgx-stub.c'))
 
 i386_ss.add(when: 'CONFIG_ACPI', if_true: files('acpi-common.c'))
-i386_ss.add(when: 'CONFIG_ACPI_HW_REDUCED', if_true: files('generic_event_device_x86.c'))
 i386_ss.add(when: 'CONFIG_PC', if_true: files(
   'pc.c',
   'pc_sysfw.c',
diff --git a/hw/i386/microvm.c b/hw/i386/microvm.c
index 8deeb62774..b9c93039e2 100644
--- a/hw/i386/microvm.c
+++ b/hw/i386/microvm.c
@@ -204,7 +204,7 @@ static void microvm_devices_init(MicrovmMachineState *mms)
 
     /* Optional and legacy devices */
     if (x86_machine_is_acpi_enabled(x86ms)) {
-        DeviceState *dev = qdev_new(TYPE_ACPI_GED_X86);
+        DeviceState *dev = qdev_new(TYPE_ACPI_GED);
         qdev_prop_set_uint32(dev, "ged-event", ACPI_GED_PWR_DOWN_EVT);
         sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, GED_MMIO_BASE);
         /* sysbus_mmio_map(SYS_BUS_DEVICE(dev), 1, GED_MMIO_BASE_MEMHP); */
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index ec01d74482..aad7e8ccd1 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -814,13 +814,39 @@ static uint64_t pc_get_cxl_range_end(PCMachineState *pcms)
 static hwaddr pc_max_used_gpa(PCMachineState *pcms, uint64_t pci_hole64_size)
 {
     X86CPU *cpu = X86_CPU(first_cpu);
+    PCMachineClass *pcmc = PC_MACHINE_GET_CLASS(pcms);
+    MachineState *ms = MACHINE(pcms);
 
-    /* 32-bit systems don't have hole64 thus return max CPU address */
-    if (cpu->phys_bits <= 32) {
+    if (cpu->env.features[FEAT_8000_0001_EDX] & CPUID_EXT2_LM) {
+        /* 64-bit systems */
+        return pc_pci_hole64_start() + pci_hole64_size - 1;
+    }
+
+    /* 32-bit systems */
+    if (pcmc->broken_32bit_mem_addr_check) {
+        /* old value for compatibility reasons */
         return ((hwaddr)1 << cpu->phys_bits) - 1;
     }
 
-    return pc_pci_hole64_start() + pci_hole64_size - 1;
+    /*
+     * 32-bit systems don't have hole64 but they might have a region for
+     * memory devices. Even if additional hotplugged memory devices might
+     * not be usable by most guest OSes, we need to still consider them for
+     * calculating the highest possible GPA so that we can properly report
+     * if someone configures them on a CPU that cannot possibly address them.
+     */
+    if (pcmc->has_reserved_memory &&
+        (ms->ram_size < ms->maxram_size)) {
+        hwaddr devmem_start;
+        ram_addr_t devmem_size;
+
+        pc_get_device_memory_range(pcms, &devmem_start, &devmem_size);
+        devmem_start += devmem_size;
+        return devmem_start - 1;
+    }
+
+    /* configuration without any memory hotplug */
+    return pc_above_4g_end(pcms) - 1;
 }
 
 /*
diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index ff8654ecda..e36a3262b2 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -496,9 +496,13 @@ DEFINE_I440FX_MACHINE(v8_2, "pc-i440fx-8.2", NULL,
 
 static void pc_i440fx_8_1_machine_options(MachineClass *m)
 {
+    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
+
     pc_i440fx_8_2_machine_options(m);
     m->alias = NULL;
     m->is_default = false;
+    pcmc->broken_32bit_mem_addr_check = true;
+
     compat_props_add(m->compat_props, hw_compat_8_1, hw_compat_8_1_len);
     compat_props_add(m->compat_props, pc_compat_8_1, pc_compat_8_1_len);
 }
diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index 2dd1158b70..a7386f2ca2 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -394,8 +394,10 @@ DEFINE_Q35_MACHINE(v8_2, "pc-q35-8.2", NULL,
 
 static void pc_q35_8_1_machine_options(MachineClass *m)
 {
+    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
     pc_q35_8_2_machine_options(m);
     m->alias = NULL;
+    pcmc->broken_32bit_mem_addr_check = true;
     compat_props_add(m->compat_props, hw_compat_8_1, hw_compat_8_1_len);
     compat_props_add(m->compat_props, pc_compat_8_1, pc_compat_8_1_len);
 }