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

virtio,pc,pci: features, fixes, cleanups

The big thing here are:
stage-1 translation in vtd
internal migration in vhost-user
ghes driver preparation for error injection
new resource uuid feature in virtio gpu
new vmclock device

And as usual, fixes and cleanups.

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

# -----BEGIN PGP SIGNATURE-----
#
# iQFDBAABCAAtFiEEXQn9CHHI+FuUyooNKB8NuNKNVGkFAmeIOiIPHG1zdEByZWRo
# YXQuY29tAAoJECgfDbjSjVRpORgIAL0clwZxQL7PIPJ91FwXc1bo6Do/HYquAzvH
# eA+ryCG5S5ewh/e2R8SdIUG7nYesEMWJGVL1gb3BFu7wgGh1aLaaTxQ1LIo5HpRF
# P0Ak3QO7TKIsSEcZIz9h3eMEpg6X9d8i2h7llp7H3qqXBbduO+cGfeNH/fZD5IEl
# 7DFvXuJUgUtZb38I+qtcO+9EQFKGHjgdQAN5P/I4vawWJdxN9sBfT4YVEgpVhiq/
# ALxdSeaEiXA4EXexdHVZhXiQzEBsCQ78RZIIDiRE8I34cVY7rolTodKRfr4bip3P
# 6Llu11yvzNi1gppOzkny3QFsRza3hV0RisWYjAMTwLhNCdi/mHQ=
# =GjDq
# -----END PGP SIGNATURE-----
# gpg: Signature made Wed 15 Jan 2025 17:43:46 EST
# gpg:                using RSA key 5D09FD0871C8F85B94CA8A0D281F0DB8D28D5469
# gpg:                issuer "mst@redhat.com"
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>" [full]
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>" [full]
# Primary key fingerprint: 0270 606B 6F3C DF3D 0B17  0970 C350 3912 AFBE 8E67
#      Subkey fingerprint: 5D09 FD08 71C8 F85B 94CA  8A0D 281F 0DB8 D28D 5469

* tag 'for_upstream' of https://git.kernel.org/pub/scm/virt/kvm/mst/qemu: (49 commits)
  hw/acpi: Add vmclock device
  virtio-net: vhost-user: Implement internal migration
  vhost: Add stubs for the migration state transfer interface
  hw/cxl: Fix msix_notify: Assertion `vector < dev->msix_entries_nr`
  tests: acpi: update expected blobs
  pci: acpi: Windows 'PCI Label Id' bug workaround
  tests: acpi: whitelist expected blobs
  docs: acpi_hest_ghes: fix documentation for CPER size
  acpi/ghes: Change ghes fill logic to work with only one source
  acpi/ghes: move offset calculus to a separate function
  acpi/ghes: better name the offset of the hardware error firmware
  acpi/ghes: rename etc/hardware_error file macros
  acpi/ghes: don't crash QEMU if ghes GED is not found
  acpi/ghes: better name GHES memory error function
  acpi/ghes: make the GHES record generation more generic
  acpi/ghes: don't check if physical_address is not zero
  acpi/ghes: Change the type for source_id
  acpi/ghes: Remove a duplicated out of bounds check
  acpi/ghes: Fix acpi_ghes_record_errors() argument
  acpi/ghes: better handle source_id and notification
  ...

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

Author: stefanhaRH

MAINTAINERS

@@ -3711,6 +3711,7 @@ F: hw/i386/intel_iommu.c
 F: hw/i386/intel_iommu_internal.h
 F: include/hw/i386/intel_iommu.h
 F: tests/functional/test_intel_iommu.py
+F: tests/qtest/intel-iommu-test.c
 
 AMD-Vi Emulation
 S: Orphan

docs/specs/acpi_hest_ghes.rst

@@ -67,8 +67,10 @@ Design Details
 (3) The address registers table contains N Error Block Address entries
     and N Read Ack Register entries. The size for each entry is 8-byte.
     The Error Status Data Block table contains N Error Status Data Block
-    entries. The size for each entry is 4096(0x1000) bytes. The total size
-    for the "etc/hardware_errors" fw_cfg blob is (N * 8 * 2 + N * 4096) bytes.
+    entries. The size for each entry is defined at the source code as
+    ACPI_GHES_MAX_RAW_DATA_LENGTH (currently 1024 bytes). The total size
+    for the "etc/hardware_errors" fw_cfg blob is
+    (N * 8 * 2 + N * ACPI_GHES_MAX_RAW_DATA_LENGTH) bytes.
     N is the number of the kinds of hardware error sources.
 
 (4) QEMU generates the ACPI linker/loader script for the firmware. The

hw/acpi/Kconfig

@@ -60,6 +60,11 @@ config ACPI_VMGENID
     default y
     depends on PC
 
+config ACPI_VMCLOCK
+    bool
+    default y
+    depends on PC
+
 config ACPI_VIOT
     bool
     depends on ACPI

hw/acpi/cpu.c

@@ -327,6 +327,7 @@ const VMStateDescription vmstate_cpu_hotplug = {
 #define CPU_EJECT_METHOD  "CEJ0"
 #define CPU_OST_METHOD    "COST"
 #define CPU_ADDED_LIST    "CNEW"
+#define CPU_EJ_LIST       "CEJL"
 
 #define CPU_ENABLED       "CPEN"
 #define CPU_SELECTOR      "CSEL"
@@ -488,7 +489,6 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts,
         method = aml_method(CPU_SCAN_METHOD, 0, AML_SERIALIZED);
         {
             const uint8_t max_cpus_per_pass = 255;
-            Aml *else_ctx;
             Aml *while_ctx, *while_ctx2;
             Aml *has_event = aml_local(0);
             Aml *dev_chk = aml_int(1);
@@ -499,6 +499,8 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts,
             Aml *uid = aml_local(3);
             Aml *has_job = aml_local(4);
             Aml *new_cpus = aml_name(CPU_ADDED_LIST);
+            Aml *ej_cpus = aml_name(CPU_EJ_LIST);
+            Aml *num_ej_cpus = aml_local(5);
 
             aml_append(method, aml_acquire(ctrl_lock, 0xFFFF));
 
@@ -513,6 +515,8 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts,
              */
             aml_append(method, aml_name_decl(CPU_ADDED_LIST,
                                              aml_package(max_cpus_per_pass)));
+            aml_append(method, aml_name_decl(CPU_EJ_LIST,
+                                             aml_package(max_cpus_per_pass)));
 
             aml_append(method, aml_store(zero, uid));
             aml_append(method, aml_store(one, has_job));
@@ -527,6 +531,7 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts,
 
                 aml_append(while_ctx2, aml_store(one, has_event));
                 aml_append(while_ctx2, aml_store(zero, num_added_cpus));
+                aml_append(while_ctx2, aml_store(zero, num_ej_cpus));
 
                 /*
                  * Scan CPUs, till there are CPUs with events or
@@ -559,8 +564,10 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts,
                       * if CPU_ADDED_LIST is full, exit inner loop and process
                       * collected CPUs
                       */
-                     ifctx = aml_if(
-                         aml_equal(num_added_cpus, aml_int(max_cpus_per_pass)));
+                     ifctx = aml_if(aml_lor(
+                         aml_equal(num_added_cpus, aml_int(max_cpus_per_pass)),
+                         aml_equal(num_ej_cpus, aml_int(max_cpus_per_pass))
+                         ));
                      {
                          aml_append(ifctx, aml_store(one, has_job));
                          aml_append(ifctx, aml_break());
@@ -577,16 +584,16 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts,
                          aml_append(ifctx, aml_store(one, has_event));
                      }
                      aml_append(while_ctx, ifctx);
-                     else_ctx = aml_else();
+
                      ifctx = aml_if(aml_equal(rm_evt, one));
                      {
-                         aml_append(ifctx,
-                             aml_call2(CPU_NOTIFY_METHOD, uid, eject_req));
-                         aml_append(ifctx, aml_store(one, rm_evt));
+                         /* cache to be removed CPUs to Notify later */
+                         aml_append(ifctx, aml_store(uid,
+                             aml_index(ej_cpus, num_ej_cpus)));
+                         aml_append(ifctx, aml_increment(num_ej_cpus));
                          aml_append(ifctx, aml_store(one, has_event));
                      }
-                     aml_append(else_ctx, ifctx);
-                     aml_append(while_ctx, else_ctx);
+                     aml_append(while_ctx, ifctx);
                      aml_append(while_ctx, aml_increment(uid));
                 }
                 aml_append(while_ctx2, while_ctx);
@@ -620,6 +627,24 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts,
                     aml_append(while_ctx, aml_increment(cpu_idx));
                 }
                 aml_append(while_ctx2, while_ctx);
+
+                /*
+                 * Notify OSPM about to be removed CPUs and clear remove flag
+                 */
+                aml_append(while_ctx2, aml_store(zero, cpu_idx));
+                while_ctx = aml_while(aml_lless(cpu_idx, num_ej_cpus));
+                {
+                    aml_append(while_ctx,
+                        aml_store(aml_derefof(aml_index(ej_cpus, cpu_idx)),
+                                  uid));
+                    aml_append(while_ctx,
+                        aml_call2(CPU_NOTIFY_METHOD, uid, eject_req));
+                    aml_append(while_ctx, aml_store(uid, cpu_selector));
+                    aml_append(while_ctx, aml_store(one, rm_evt));
+                    aml_append(while_ctx, aml_increment(cpu_idx));
+                }
+                aml_append(while_ctx2, while_ctx);
+
                 /*
                  * If another batch is needed, then it will resume scanning
                  * exactly at -- and not after -- the last CPU that's currently

hw/acpi/generic_event_device.c

@@ -363,15 +363,15 @@ static const VMStateDescription vmstate_ghes = {
     .version_id = 1,
     .minimum_version_id = 1,
     .fields = (const VMStateField[]) {
-        VMSTATE_UINT64(ghes_addr_le, AcpiGhesState),
+        VMSTATE_UINT64(hw_error_le, AcpiGhesState),
         VMSTATE_END_OF_LIST()
     },
 };
 
 static bool ghes_needed(void *opaque)
 {
     AcpiGedState *s = opaque;
-    return s->ghes_state.ghes_addr_le;
+    return s->ghes_state.hw_error_le;
 }
 
 static const VMStateDescription vmstate_ghes_state = {

hw/acpi/ghes-stub.c

@@ -11,7 +11,7 @@
 #include "qemu/osdep.h"
 #include "hw/acpi/ghes.h"
 
-int acpi_ghes_record_errors(uint8_t source_id, uint64_t physical_address)
+int acpi_ghes_memory_errors(uint16_t source_id, uint64_t physical_address)
 {
     return -1;
 }