rpms
/
qemu-kvm
7
0
Fork 0
Code Issues Pull Requests Releases Activity

* Wed Apr 24 2024 Miroslav Rezanina <mrezanin@redhat.com> - 9.0.0-1 

- Rebase to QEMU 9.0.0 [RHEL-28073]
- Resolves: RHEL-28073
  (Rebase qemu-kvm to QEMU 9.0.0 for RHEL 9.5)
This commit is contained in:
Miroslav Rezanina 2024-04-24 05:32:21 -04:00
parent 942f1fed56
commit 209f2f84bf
179 changed files with 614 additions and 31744 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
.gitignore vendored
View File

@ -28,3 +28,4 @@
/qemu-8.0.0.tar.xz
/qemu-8.1.0.tar.xz
/qemu-8.2.0.tar.xz
/qemu-9.0.0.tar.xz

19
0004-Initial-redhat-build.patch
View File

@ -1,4 +1,4 @@
From faae70a870156f86a5cf55ca967b15d7612941ff Mon Sep 17 00:00:00 2001
From ea7dff3dbf979d7d8a85a16cf5187235143e1048 Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Wed, 26 May 2021 10:56:02 +0200
Subject: Initial redhat build
@ -13,7 +13,7 @@ several issues are fixed in QEMU tree:
We disable make check due to issues with some of the tests.
This rebase is based on qemu-kvm-8.1.0-5.el9
This rebase is based on qemu-kvm-8.2.0-11.el9
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
--
@ -83,6 +83,12 @@ Rebase changes (8.2.0):
- Added --disable-plugins configure option
- Fixing frh.py strings
Rebase notes (9.0.0):
- Fixed qemu-kvm binary location change
- Remove hppa-firmware64.img
- Package stp files for utilities
- Download subprojects on local build
Merged patches (6.0.0):
- 605758c902 Limit build on Power to qemu-img and qemu-ga only
@ -193,14 +199,17 @@ Merged patches (8.1.0):
Merged patches (8.2.0):
- cd9efa221d Enable qemu-kvm-device-usb-redirec for aarch64
Merged patches (9.0.0 rc0):
- 25de053dbf spec: Enable zstd
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
---
.distro/Makefile | 100 +
.distro/Makefile | 101 +
.distro/Makefile.common | 42 +
.distro/README.tests | 39 +
.distro/modules-load.conf | 4 +
.distro/qemu-guest-agent.service | 1 -
.distro/qemu-kvm.spec.template | 4909 +++++++++++++++++++++++
.distro/qemu-kvm.spec.template | 5170 +++++++++++++++++++++++
.distro/rpminspect.yaml | 6 +-
.distro/scripts/extract_build_cmd.py | 12 +
.distro/scripts/frh.py | 4 +-
@ -211,7 +220,7 @@ Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
scripts/systemtap/conf.d/qemu_kvm.conf | 4 +
scripts/systemtap/script.d/qemu_kvm.stp | 1 +
ui/vnc-auth-sasl.c | 2 +-
16 files changed, 5168 insertions(+), 6 deletions(-)
16 files changed, 5430 insertions(+), 6 deletions(-)
create mode 100644 .distro/Makefile
create mode 100644 .distro/Makefile.common
create mode 100644 .distro/README.tests

266
0005-Enable-disable-devices-for-RHEL.patch
View File

@ -1,4 +1,4 @@
From 048067b4618ba1fa7c8c517185d4cd3a675eba72 Mon Sep 17 00:00:00 2001
From 780c39975b059deaee106775b6e3a240155acea3 Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Wed, 7 Dec 2022 03:05:48 -0500
Subject: Enable/disable devices for RHEL
@ -47,6 +47,12 @@ Rebase notes (8.2.0):
- Disable new neoverse-v2
- Removed CONFIG_OPENGL from x86_64 config file
Rebase notes (9.0.0 rc0):
- Split CONFIG_IDE_QDEV to CONFIG_IDE_DEV and CONFIG_IDE_BUS (upstream change)
Rebase notes (9.0.0 rc1):
- Do not compile armv7 cpu types
Merged patches (6.1.0):
- c51bf45304 Remove SPICE and QXL from x86_64-rh-devices.mak
- 02fc745601 aarch64-rh-devices: add CONFIG_PVPANIC_PCI
@ -74,36 +80,41 @@ Merged patches (8.1.0):
Merged patches (8.2.0):
- b29f66431f Enable igb on x86_64
Merged patches (9.0.0 rc0):
- 3889ede5d9 Compile IOMMUFD on x86_64
- 0beb18451f Compile IOMMUFD on s390x
- 2b4b13f70d Compile IOMMUFD object on aarch64
---
.distro/qemu-kvm.spec.template | 18 +--
.../aarch64-softmmu/aarch64-rh-devices.mak | 41 +++++++
.../aarch64-softmmu/aarch64-rh-devices.mak | 42 +++++++
.../ppc64-softmmu/ppc64-rh-devices.mak | 37 ++++++
configs/devices/rh-virtio.mak | 10 ++
.../s390x-softmmu/s390x-rh-devices.mak | 18 +++
.../x86_64-softmmu/x86_64-rh-devices.mak | 110 ++++++++++++++++++
.../s390x-softmmu/s390x-rh-devices.mak | 19 +++
.../x86_64-softmmu/x86_64-rh-devices.mak | 112 ++++++++++++++++++
hw/arm/virt.c | 2 +
hw/block/fdc.c | 10 ++
hw/cpu/meson.build | 3 +-
hw/cxl/meson.build | 3 +-
hw/display/cirrus_vga.c | 4 +
hw/ide/piix.c | 5 +-
hw/ide/qdev.c | 9 ++
hw/input/pckbd.c | 2 +
hw/net/e1000.c | 2 +
hw/ppc/spapr_cpu_core.c | 2 +
hw/usb/meson.build | 2 +-
hw/virtio/meson.build | 5 +-
hw/virtio/meson.build | 6 +-
target/arm/arm-qmp-cmds.c | 2 +
target/arm/cpu.c | 4 +
target/arm/cpu.h | 3 +
target/arm/cpu64.c | 12 +-
target/arm/tcg/cpu32.c | 2 +
target/arm/tcg/cpu64.c | 8 ++
target/arm/tcg/meson.build | 4 +-
target/ppc/cpu-models.c | 9 ++
target/s390x/cpu_models_sysemu.c | 3 +
target/s390x/kvm/kvm.c | 8 ++
tests/qtest/arm-cpu-features.c | 4 +
28 files changed, 323 insertions(+), 15 deletions(-)
28 files changed, 321 insertions(+), 17 deletions(-)
create mode 100644 configs/devices/aarch64-softmmu/aarch64-rh-devices.mak
create mode 100644 configs/devices/ppc64-softmmu/ppc64-rh-devices.mak
create mode 100644 configs/devices/rh-virtio.mak
@ -112,10 +123,10 @@ Merged patches (8.2.0):
diff --git a/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak b/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak
new file mode 100644
index 0000000000..aec1831199
index 0000000000..b0191d3c69
--- /dev/null
+++ b/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak
@@ -0,0 +1,41 @@
@@ -0,0 +1,42 @@
+include ../rh-virtio.mak
+
+CONFIG_ARM_GIC_KVM=y
@ -157,6 +168,7 @@ index 0000000000..aec1831199
+CONFIG_VHOST_VSOCK=y
+CONFIG_VHOST_USER_VSOCK=y
+CONFIG_VHOST_USER_FS=y
+CONFIG_IOMMUFD=y
diff --git a/configs/devices/ppc64-softmmu/ppc64-rh-devices.mak b/configs/devices/ppc64-softmmu/ppc64-rh-devices.mak
new file mode 100644
index 0000000000..dbb7d30829
@ -218,10 +230,10 @@ index 0000000000..94ede1b5f6
+CONFIG_VIRTIO_SERIAL=y
diff --git a/configs/devices/s390x-softmmu/s390x-rh-devices.mak b/configs/devices/s390x-softmmu/s390x-rh-devices.mak
new file mode 100644
index 0000000000..69a799adbd
index 0000000000..24cf6dbd03
--- /dev/null
+++ b/configs/devices/s390x-softmmu/s390x-rh-devices.mak
@@ -0,0 +1,18 @@
@@ -0,0 +1,19 @@
+include ../rh-virtio.mak
+
+CONFIG_PCI=y
@ -240,12 +252,13 @@ index 0000000000..69a799adbd
+CONFIG_VHOST_VSOCK=y
+CONFIG_VHOST_USER_VSOCK=y
+CONFIG_VHOST_USER_FS=y
+CONFIG_IOMMUFD=y
diff --git a/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak b/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak
new file mode 100644
index 0000000000..ce5be73633
index 0000000000..d60ff1bcfc
--- /dev/null
+++ b/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak
@@ -0,0 +1,110 @@
@@ -0,0 +1,112 @@
+include ../rh-virtio.mak
+
+CONFIG_ACPI=y
@ -283,7 +296,8 @@ index 0000000000..ce5be73633
+CONFIG_IDE_CORE=y
+CONFIG_IDE_PCI=y
+CONFIG_IDE_PIIX=y
+CONFIG_IDE_QDEV=y
+CONFIG_IDE_DEV=y
+CONFIG_IDE_BUS=y
+CONFIG_IGB_PCI_EXPRESS=y
+CONFIG_IOAPIC=y
+CONFIG_IOH3420=y
@ -356,28 +370,29 @@ index 0000000000..ce5be73633
+CONFIG_VHOST_VSOCK=y
+CONFIG_VHOST_USER_VSOCK=y
+CONFIG_VHOST_USER_FS=y
+CONFIG_IOMMUFD=y
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index be2856c018..af9ea4dd1c 100644
index a9a913aead..6c6d155002 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -205,6 +205,7 @@ static const int a15irqmap[] = {
};
static const char *valid_cpus[] = {
@@ -2954,6 +2954,7 @@ static void virt_machine_class_init(ObjectClass *oc, void *data)
MachineClass *mc = MACHINE_CLASS(oc);
HotplugHandlerClass *hc = HOTPLUG_HANDLER_CLASS(oc);
static const char * const valid_cpu_types[] = {
+#if 0 /* Disabled for Red Hat Enterprise Linux */
#ifdef CONFIG_TCG
ARM_CPU_TYPE_NAME("cortex-a7"),
ARM_CPU_TYPE_NAME("cortex-a15"),
@@ -219,6 +220,7 @@ static const char *valid_cpus[] = {
ARM_CPU_TYPE_NAME("neoverse-n2"),
#endif
ARM_CPU_TYPE_NAME("cortex-a53"),
ARM_CPU_TYPE_NAME("cortex-a7"),
ARM_CPU_TYPE_NAME("cortex-a15"),
@@ -2971,6 +2972,7 @@ static void virt_machine_class_init(ObjectClass *oc, void *data)
#endif /* CONFIG_TCG */
#ifdef TARGET_AARCH64
ARM_CPU_TYPE_NAME("cortex-a53"),
+#endif /* disabled for RHEL */
ARM_CPU_TYPE_NAME("cortex-a57"),
ARM_CPU_TYPE_NAME("host"),
ARM_CPU_TYPE_NAME("max"),
ARM_CPU_TYPE_NAME("cortex-a57"),
#if defined(CONFIG_KVM) || defined(CONFIG_HVF)
ARM_CPU_TYPE_NAME("host"),
diff --git a/hw/block/fdc.c b/hw/block/fdc.c
index d7cc4d3ec1..12d0a60905 100644
index 6dd94e98bc..a05757fc9a 100644
--- a/hw/block/fdc.c
+++ b/hw/block/fdc.c
@@ -49,6 +49,8 @@
@ -405,7 +420,7 @@ index d7cc4d3ec1..12d0a60905 100644
error_setg(errp, "Cannot choose a fallback FDrive type of 'auto'");
return;
diff --git a/hw/cpu/meson.build b/hw/cpu/meson.build
index 6d319947ca..91962fd863 100644
index 38cdcfbe57..e588ecfd42 100644
--- a/hw/cpu/meson.build
+++ b/hw/cpu/meson.build
@@ -1,4 +1,5 @@
@ -416,7 +431,7 @@ index 6d319947ca..91962fd863 100644
system_ss.add(when: 'CONFIG_ARM11MPCORE', if_true: files('arm11mpcore.c'))
system_ss.add(when: 'CONFIG_REALVIEW', if_true: files('realview_mpcore.c'))
diff --git a/hw/cxl/meson.build b/hw/cxl/meson.build
index ea0aebf6e3..6878f06974 100644
index 3e375f61a9..613adb3ebb 100644
--- a/hw/cxl/meson.build
+++ b/hw/cxl/meson.build
@@ -6,7 +6,8 @@ system_ss.add(when: 'CONFIG_CXL',
@ -430,7 +445,7 @@ index ea0aebf6e3..6878f06974 100644
if_false: files(
'cxl-host-stubs.c',
diff --git a/hw/display/cirrus_vga.c b/hw/display/cirrus_vga.c
index b80f98b6c4..0370cf8a64 100644
index 150883a971..497365bd80 100644
--- a/hw/display/cirrus_vga.c
+++ b/hw/display/cirrus_vga.c
@@ -36,6 +36,7 @@
@ -452,10 +467,10 @@ index b80f98b6c4..0370cf8a64 100644
* Follow real hardware, cirrus card emulated has 4 MB video memory.
* Also accept 8 MB/16 MB for backward compatibility.
diff --git a/hw/ide/piix.c b/hw/ide/piix.c
index 4e5e12935f..03ca06bb17 100644
index 80efc633d3..9cb82b8eea 100644
--- a/hw/ide/piix.c
+++ b/hw/ide/piix.c
@@ -190,7 +190,8 @@ static void piix3_ide_class_init(ObjectClass *klass, void *data)
@@ -191,7 +191,8 @@ static void piix3_ide_class_init(ObjectClass *klass, void *data)
k->device_id = PCI_DEVICE_ID_INTEL_82371SB_1;
k->class_id = PCI_CLASS_STORAGE_IDE;
set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
@ -465,7 +480,7 @@ index 4e5e12935f..03ca06bb17 100644
}
static const TypeInfo piix3_ide_info = {
@@ -214,6 +215,8 @@ static void piix4_ide_class_init(ObjectClass *klass, void *data)
@@ -215,6 +216,8 @@ static void piix4_ide_class_init(ObjectClass *klass, void *data)
k->class_id = PCI_CLASS_STORAGE_IDE;
set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
dc->hotpluggable = false;
@ -474,57 +489,11 @@ index 4e5e12935f..03ca06bb17 100644
}
static const TypeInfo piix4_ide_info = {
diff --git a/hw/ide/qdev.c b/hw/ide/qdev.c
index 1b3b4da01d..454bfa5783 100644
--- a/hw/ide/qdev.c
+++ b/hw/ide/qdev.c
@@ -283,10 +283,13 @@ static void ide_cd_realize(IDEDevice *dev, Error **errp)
ide_dev_initfn(dev, IDE_CD, errp);
}
+/* Disabled for Red Hat Enterprise Linux */
+#if 0
static void ide_cf_realize(IDEDevice *dev, Error **errp)
{
ide_dev_initfn(dev, IDE_CFATA, errp);
}
+#endif
#define DEFINE_IDE_DEV_PROPERTIES() \
DEFINE_BLOCK_PROPERTIES(IDEDrive, dev.conf), \
@@ -346,6 +349,8 @@ static const TypeInfo ide_cd_info = {
.class_init = ide_cd_class_init,
};
+/* Disabled for Red Hat Enterprise Linux */
+#if 0
static Property ide_cf_properties[] = {
DEFINE_IDE_DEV_PROPERTIES(),
DEFINE_BLOCK_CHS_PROPERTIES(IDEDrive, dev.conf),
@@ -371,6 +376,7 @@ static const TypeInfo ide_cf_info = {
.instance_size = sizeof(IDEDrive),
.class_init = ide_cf_class_init,
};
+#endif
static void ide_device_class_init(ObjectClass *klass, void *data)
{
@@ -396,7 +402,10 @@ static void ide_register_types(void)
type_register_static(&ide_bus_info);
type_register_static(&ide_hd_info);
type_register_static(&ide_cd_info);
+/* Disabled for Red Hat Enterprise Linux */
+#if 0
type_register_static(&ide_cf_info);
+#endif
type_register_static(&ide_device_type_info);
}
diff --git a/hw/input/pckbd.c b/hw/input/pckbd.c
index b92b63bedc..3b6235dde6 100644
index 74f10b640f..2e85ecf476 100644
--- a/hw/input/pckbd.c
+++ b/hw/input/pckbd.c
@@ -957,6 +957,8 @@ static void i8042_class_initfn(ObjectClass *klass, void *data)
@@ -952,6 +952,8 @@ static void i8042_class_initfn(ObjectClass *klass, void *data)
dc->vmsd = &vmstate_kbd_isa;
adevc->build_dev_aml = i8042_build_aml;
set_bit(DEVICE_CATEGORY_INPUT, dc->categories);
@ -534,7 +503,7 @@ index b92b63bedc..3b6235dde6 100644
static const TypeInfo i8042_info = {
diff --git a/hw/net/e1000.c b/hw/net/e1000.c
index 8ffe1077f1..b3dfeeca4f 100644
index 43f3a4a701..267f182883 100644
--- a/hw/net/e1000.c
+++ b/hw/net/e1000.c
@@ -1746,6 +1746,7 @@ static const E1000Info e1000_devices[] = {
@ -554,10 +523,10 @@ index 8ffe1077f1..b3dfeeca4f 100644
static void e1000_register_types(void)
diff --git a/hw/ppc/spapr_cpu_core.c b/hw/ppc/spapr_cpu_core.c
index 91fae56573..33e0c8724c 100644
index e7c9edd033..3b0a47a28c 100644
--- a/hw/ppc/spapr_cpu_core.c
+++ b/hw/ppc/spapr_cpu_core.c
@@ -386,10 +386,12 @@ static const TypeInfo spapr_cpu_core_type_infos[] = {
@@ -389,10 +389,12 @@ static const TypeInfo spapr_cpu_core_type_infos[] = {
.instance_size = sizeof(SpaprCpuCore),
.class_size = sizeof(SpaprCpuCoreClass),
},
@ -565,16 +534,16 @@ index 91fae56573..33e0c8724c 100644
DEFINE_SPAPR_CPU_CORE_TYPE("970_v2.2"),
DEFINE_SPAPR_CPU_CORE_TYPE("970mp_v1.0"),
DEFINE_SPAPR_CPU_CORE_TYPE("970mp_v1.1"),
DEFINE_SPAPR_CPU_CORE_TYPE("power5+_v2.1"),
DEFINE_SPAPR_CPU_CORE_TYPE("power5p_v2.1"),
+#endif
DEFINE_SPAPR_CPU_CORE_TYPE("power7_v2.3"),
DEFINE_SPAPR_CPU_CORE_TYPE("power7+_v2.1"),
DEFINE_SPAPR_CPU_CORE_TYPE("power7p_v2.1"),
DEFINE_SPAPR_CPU_CORE_TYPE("power8_v2.0"),
diff --git a/hw/usb/meson.build b/hw/usb/meson.build
index e94149ebde..4a8adbf3dc 100644
index aac3bb35f2..5411ff35df 100644
--- a/hw/usb/meson.build
+++ b/hw/usb/meson.build
@@ -52,7 +52,7 @@ system_ss.add(when: 'CONFIG_USB_SMARTCARD', if_true: files('dev-smartcard-reader
@@ -55,7 +55,7 @@ system_ss.add(when: 'CONFIG_USB_SMARTCARD', if_true: files('dev-smartcard-reader
if cacard.found()
usbsmartcard_ss = ss.source_set()
usbsmartcard_ss.add(when: 'CONFIG_USB_SMARTCARD',
@ -584,26 +553,34 @@ index e94149ebde..4a8adbf3dc 100644
endif
diff --git a/hw/virtio/meson.build b/hw/virtio/meson.build
index c0055a7832..12e1d6c67e 100644
index d7f18c96e6..aaabbb8b0b 100644
--- a/hw/virtio/meson.build
+++ b/hw/virtio/meson.build
@@ -17,8 +17,9 @@ if have_vhost
if have_vhost_user
# fixme - this really should be generic
specific_virtio_ss.add(files('vhost-user.c'))
@@ -20,7 +20,8 @@ if have_vhost
system_virtio_ss.add(files('vhost-user-base.c'))
# MMIO Stubs
- system_virtio_ss.add(files('vhost-user-device.c'))
- system_virtio_ss.add(when: 'CONFIG_VIRTIO_PCI', if_true: files('vhost-user-device-pci.c'))
+# Disabled for 8.2.0 rebase for RHEL 9.4.0
+# system_virtio_ss.add(files('vhost-user-device.c'))
system_virtio_ss.add(when: 'CONFIG_VHOST_USER_GPIO', if_true: files('vhost-user-gpio.c'))
system_virtio_ss.add(when: 'CONFIG_VHOST_USER_I2C', if_true: files('vhost-user-i2c.c'))
system_virtio_ss.add(when: 'CONFIG_VHOST_USER_RNG', if_true: files('vhost-user-rng.c'))
@@ -28,7 +29,8 @@ if have_vhost
system_virtio_ss.add(when: 'CONFIG_VHOST_USER_INPUT', if_true: files('vhost-user-input.c'))
# PCI Stubs
- system_virtio_ss.add(when: 'CONFIG_VIRTIO_PCI', if_true: files('vhost-user-device-pci.c'))
+# Disabled for 8.2.0 rebase for RHEL 9.4.0
+# system_virtio_ss.add(when: 'CONFIG_VIRTIO_PCI', if_true: files('vhost-user-device-pci.c'))
endif
if have_vhost_vdpa
system_virtio_ss.add(files('vhost-vdpa.c'))
system_virtio_ss.add(when: ['CONFIG_VIRTIO_PCI', 'CONFIG_VHOST_USER_GPIO'],
if_true: files('vhost-user-gpio-pci.c'))
system_virtio_ss.add(when: ['CONFIG_VIRTIO_PCI', 'CONFIG_VHOST_USER_I2C'],
diff --git a/target/arm/arm-qmp-cmds.c b/target/arm/arm-qmp-cmds.c
index b53d5efe13..64989a02d1 100644
index 3cc8cc738b..6f21fea1f5 100644
--- a/target/arm/arm-qmp-cmds.c
+++ b/target/arm/arm-qmp-cmds.c
@@ -231,6 +231,7 @@ CpuModelExpansionInfo *qmp_query_cpu_model_expansion(CpuModelExpansionType type,
@@ -223,6 +223,7 @@ CpuModelExpansionInfo *qmp_query_cpu_model_expansion(CpuModelExpansionType type,
static void arm_cpu_add_definition(gpointer data, gpointer user_data)
{
ObjectClass *oc = data;
@ -611,23 +588,23 @@ index b53d5efe13..64989a02d1 100644
CpuDefinitionInfoList **cpu_list = user_data;
CpuDefinitionInfo *info;
const char *typename;
@@ -240,6 +241,7 @@ static void arm_cpu_add_definition(gpointer data, gpointer user_data)
info->name = g_strndup(typename,
strlen(typename) - strlen("-" TYPE_ARM_CPU));
@@ -231,6 +232,7 @@ static void arm_cpu_add_definition(gpointer data, gpointer user_data)
info = g_malloc0(sizeof(*info));
info->name = cpu_model_from_type(typename);
info->q_typename = g_strdup(typename);
+ info->deprecated = !!cc->deprecation_note;
QAPI_LIST_PREPEND(*cpu_list, info);
}
diff --git a/target/arm/cpu.c b/target/arm/cpu.c
index efb22a87f9..a32521ada9 100644
index ab8d007a86..e5dce20f19 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -2524,6 +2524,10 @@ static void cpu_register_class_init(ObjectClass *oc, void *data)
@@ -2546,6 +2546,10 @@ static void cpu_register_class_init(ObjectClass *oc, void *data)
acc->info = data;
cc->gdb_core_xml_file = "arm-core.xml";
+
+
+ if (acc->info->deprecation_note) {
+ cc->deprecation_note = acc->info->deprecation_note;
+ }
@ -635,10 +612,10 @@ index efb22a87f9..a32521ada9 100644
void arm_cpu_register(const ARMCPUInfo *info)
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index a0282e0d28..7e0f0dfea7 100644
index bc0c84873f..e9472c8bb8 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -34,6 +34,8 @@
@@ -37,6 +37,8 @@
#define KVM_HAVE_MCE_INJECTION 1
#endif
@ -647,7 +624,7 @@ index a0282e0d28..7e0f0dfea7 100644
#define EXCP_UDEF 1 /* undefined instruction */
#define EXCP_SWI 2 /* software interrupt */
#define EXCP_PREFETCH_ABORT 3
@@ -1120,6 +1122,7 @@ typedef struct ARMCPUInfo {
@@ -1092,6 +1094,7 @@ typedef struct ARMCPUInfo {
const char *name;
void (*initfn)(Object *obj);
void (*class_init)(ObjectClass *oc, void *data);
@ -656,7 +633,7 @@ index a0282e0d28..7e0f0dfea7 100644
/**
diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c
index 1e9c6c85ae..10be900803 100644
index 985b1efe16..46a4e80171 100644
--- a/target/arm/cpu64.c
+++ b/target/arm/cpu64.c
@@ -648,6 +648,7 @@ static void aarch64_a57_initfn(Object *obj)
@ -688,7 +665,7 @@ index 1e9c6c85ae..10be900803 100644
{ .name = "max", .initfn = aarch64_max_initfn },
#if defined(CONFIG_KVM) || defined(CONFIG_HVF)
{ .name = "host", .initfn = aarch64_host_initfn },
@@ -815,8 +820,13 @@ static void aarch64_cpu_instance_init(Object *obj)
@@ -814,8 +819,13 @@ static void aarch64_cpu_instance_init(Object *obj)
static void cpu_register_class_init(ObjectClass *oc, void *data)
{
ARMCPUClass *acc = ARM_CPU_CLASS(oc);
@ -703,24 +680,24 @@ index 1e9c6c85ae..10be900803 100644
void aarch64_cpu_register(const ARMCPUInfo *info)
diff --git a/target/arm/tcg/cpu32.c b/target/arm/tcg/cpu32.c
index d9e0e2a4dd..c5c639a6ea 100644
index de8f2be941..8896295ae3 100644
--- a/target/arm/tcg/cpu32.c
+++ b/target/arm/tcg/cpu32.c
@@ -98,6 +98,7 @@ void aa32_max_features(ARMCPU *cpu)
@@ -92,6 +92,7 @@ void aa32_max_features(ARMCPU *cpu)
cpu->isar.id_dfr1 = t;
}
+#if 0 /* Disabled for Red Hat Enterprise Linux */
/* CPU models. These are not needed for the AArch64 linux-user build. */
#if !defined(CONFIG_USER_ONLY) || !defined(TARGET_AARCH64)
+#if 0 /* Disabled for Red Hat Enterprise Linux */
#if !defined(CONFIG_USER_ONLY)
static bool arm_v7m_cpu_exec_interrupt(CPUState *cs, int interrupt_request)
{
@@ -1189,3 +1190,4 @@ static void arm_tcg_cpu_register_types(void)
@@ -1037,3 +1038,4 @@ static void arm_tcg_cpu_register_types(void)
type_init(arm_tcg_cpu_register_types)
#endif /* !CONFIG_USER_ONLY || !TARGET_AARCH64 */
+#endif /* disabled for RHEL */
diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c
index fcda99e158..bd5a993ff8 100644
index 9f7a9f3d2c..7ec6851c9c 100644
--- a/target/arm/tcg/cpu64.c
+++ b/target/arm/tcg/cpu64.c
@@ -29,6 +29,7 @@
@ -755,7 +732,7 @@ index fcda99e158..bd5a993ff8 100644
/*
* -cpu max: a CPU with as many features enabled as our emulation supports.
@@ -1259,6 +1263,7 @@ void aarch64_max_tcg_initfn(Object *obj)
@@ -1271,6 +1275,7 @@ void aarch64_max_tcg_initfn(Object *obj)
qdev_property_add_static(DEVICE(obj), &arm_cpu_lpa2_property);
}
@ -763,7 +740,7 @@ index fcda99e158..bd5a993ff8 100644
static const ARMCPUInfo aarch64_cpus[] = {
{ .name = "cortex-a35", .initfn = aarch64_a35_initfn },
{ .name = "cortex-a55", .initfn = aarch64_a55_initfn },
@@ -1270,14 +1275,17 @@ static const ARMCPUInfo aarch64_cpus[] = {
@@ -1282,14 +1287,17 @@ static const ARMCPUInfo aarch64_cpus[] = {
{ .name = "neoverse-v1", .initfn = aarch64_neoverse_v1_initfn },
{ .name = "neoverse-n2", .initfn = aarch64_neoverse_n2_initfn },
};
@ -781,8 +758,20 @@ index fcda99e158..bd5a993ff8 100644
}
type_init(aarch64_cpu_register_types)
diff --git a/target/arm/tcg/meson.build b/target/arm/tcg/meson.build
index 3b1a9f0fc5..6898b4de6f 100644
--- a/target/arm/tcg/meson.build
+++ b/target/arm/tcg/meson.build
@@ -56,5 +56,5 @@ arm_system_ss.add(files(
'psci.c',
))
-arm_system_ss.add(when: 'CONFIG_ARM_V7M', if_true: files('cpu-v7m.c'))
-arm_user_ss.add(when: 'TARGET_AARCH64', if_false: files('cpu-v7m.c'))
+#arm_system_ss.add(when: 'CONFIG_ARM_V7M', if_true: files('cpu-v7m.c'))
+#arm_user_ss.add(when: 'TARGET_AARCH64', if_false: files('cpu-v7m.c'))
diff --git a/target/ppc/cpu-models.c b/target/ppc/cpu-models.c
index 7dbb47de64..69fddb05bc 100644
index f2301b43f7..f77ebfcc81 100644
--- a/target/ppc/cpu-models.c
+++ b/target/ppc/cpu-models.c
@@ -66,6 +66,7 @@
@ -806,13 +795,13 @@ index 7dbb47de64..69fddb05bc 100644
POWERPC_DEF("970fx_v1.0", CPU_POWERPC_970FX_v10, 970,
@@ -718,6 +721,7 @@
"PowerPC 970MP v1.1")
POWERPC_DEF("power5+_v2.1", CPU_POWERPC_POWER5P_v21, POWER5P,
POWERPC_DEF("power5p_v2.1", CPU_POWERPC_POWER5P_v21, POWER5P,
"POWER5+ v2.1")
+#endif
POWERPC_DEF("power7_v2.3", CPU_POWERPC_POWER7_v23, POWER7,
"POWER7 v2.3")
POWERPC_DEF("power7+_v2.1", CPU_POWERPC_POWER7P_v21, POWER7,
@@ -898,12 +902,15 @@ PowerPCCPUAlias ppc_cpu_aliases[] = {
POWERPC_DEF("power7p_v2.1", CPU_POWERPC_POWER7P_v21, POWER7,
@@ -894,13 +898,16 @@ PowerPCCPUAlias ppc_cpu_aliases[] = {
{ "7447a", "7447a_v1.2" },
{ "7457a", "7457a_v1.2" },
{ "apollo7pm", "7457a_v1.0" },
@ -822,13 +811,14 @@ index 7dbb47de64..69fddb05bc 100644
{ "970", "970_v2.2" },
{ "970fx", "970fx_v3.1" },
{ "970mp", "970mp_v1.1" },
{ "power5+", "power5+_v2.1" },
{ "power5+", "power5p_v2.1" },
{ "power5+_v2.1", "power5p_v2.1" },
{ "power5gs", "power5+_v2.1" },
+#endif
{ "power7", "power7_v2.3" },
{ "power7+", "power7+_v2.1" },
{ "power8e", "power8e_v2.1" },
@@ -913,12 +920,14 @@ PowerPCCPUAlias ppc_cpu_aliases[] = {
{ "power7+", "power7p_v2.1" },
{ "power7+_v2.1", "power7p_v2.1" },
@@ -911,12 +918,14 @@ PowerPCCPUAlias ppc_cpu_aliases[] = {
{ "power10", "power10_v2.0" },
#endif
@ -844,10 +834,10 @@ index 7dbb47de64..69fddb05bc 100644
{ NULL, NULL }
};
diff --git a/target/s390x/cpu_models_sysemu.c b/target/s390x/cpu_models_sysemu.c
index 63981bf36b..87a4480c05 100644
index 2d99218069..0728bfcc20 100644
--- a/target/s390x/cpu_models_sysemu.c
+++ b/target/s390x/cpu_models_sysemu.c
@@ -35,6 +35,9 @@ static void check_unavailable_features(const S390CPUModel *max_model,
@@ -34,6 +34,9 @@ static void check_unavailable_features(const S390CPUModel *max_model,
(max_model->def->gen == model->def->gen &&
max_model->def->ec_ga < model->def->ec_ga)) {
list_add_feat("type", unavailable);
@ -858,10 +848,10 @@ index 63981bf36b..87a4480c05 100644
/* detect missing features if any to properly report them */
diff --git a/target/s390x/kvm/kvm.c b/target/s390x/kvm/kvm.c
index 33ab3551f4..912e493951 100644
index 4ce809c5d4..55fb4855b1 100644
--- a/target/s390x/kvm/kvm.c
+++ b/target/s390x/kvm/kvm.c
@@ -2567,6 +2567,14 @@ void kvm_s390_apply_cpu_model(const S390CPUModel *model, Error **errp)
@@ -2565,6 +2565,14 @@ void kvm_s390_apply_cpu_model(const S390CPUModel *model, Error **errp)
error_setg(errp, "KVM doesn't support CPU models");
return;
}
@ -877,10 +867,10 @@ index 33ab3551f4..912e493951 100644
prop.ibc = s390_ibc_from_cpu_model(model);
/* configure cpu features indicated via STFL(e) */
diff --git a/tests/qtest/arm-cpu-features.c b/tests/qtest/arm-cpu-features.c
index a8a4c668ad..2458cc527c 100644
index 9d6e6190d5..f822526acb 100644
--- a/tests/qtest/arm-cpu-features.c
+++ b/tests/qtest/arm-cpu-features.c
@@ -451,8 +451,10 @@ static void test_query_cpu_model_expansion(const void *data)
@@ -452,8 +452,10 @@ static void test_query_cpu_model_expansion(const void *data)
assert_error(qts, "host", "The CPU type 'host' requires KVM", NULL);
/* Test expected feature presence/absence for some cpu types */
@ -891,7 +881,7 @@ index a8a4c668ad..2458cc527c 100644
/* Enabling and disabling pmu should always work. */
assert_has_feature_enabled(qts, "max", "pmu");
@@ -469,6 +471,7 @@ static void test_query_cpu_model_expansion(const void *data)
@@ -470,6 +472,7 @@ static void test_query_cpu_model_expansion(const void *data)
assert_has_feature_enabled(qts, "cortex-a57", "pmu");
assert_has_feature_enabled(qts, "cortex-a57", "aarch64");
@ -899,7 +889,7 @@ index a8a4c668ad..2458cc527c 100644
assert_has_feature_enabled(qts, "a64fx", "pmu");
assert_has_feature_enabled(qts, "a64fx", "aarch64");
/*
@@ -481,6 +484,7 @@ static void test_query_cpu_model_expansion(const void *data)
@@ -482,6 +485,7 @@ static void test_query_cpu_model_expansion(const void *data)
"{ 'sve384': true }");
assert_error(qts, "a64fx", "cannot enable sve640",
"{ 'sve640': true }");

168
0006-Machine-type-related-general-changes.patch
View File

@ -1,4 +1,4 @@
From d9ff466c980d219ebf230ea24becce294c196f1f Mon Sep 17 00:00:00 2001
From 8e6a30073f9c1a5d6294b2d16556522453e227e7 Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Fri, 11 Jan 2019 09:54:45 +0100
Subject: Machine type related general changes
@ -26,6 +26,12 @@ Rebase notes (7.1.0):
Rebase notes (8.1.0):
- Do not modify unused vga-isa.c
Rebase notes (9.0.0 rc0):
- Updated smsbios handling
Rebase notes (9.0.0 rc4):
- Moving downstream compat changes
Merged patches (6.1.0):
- f2fb42a3c6 redhat: add missing entries in hw_compat_rhel_8_4
- 1949ec258e hw/arm/virt: Disable PL011 clock migration through hw_compat_rhel_8_3
@ -61,24 +67,27 @@ Merged patches (8.1.0):
Merged patches (8.2.0):
- 4ee284aca9 Add machine types compat bits. (partial)
Merged patches (9.0.0 rc0):
- 4b8fe42abc virtio-mem: default-enable "dynamic-memslots"
---
hw/acpi/piix4.c | 2 +-
hw/arm/virt.c | 2 +-
hw/core/machine.c | 267 +++++++++++++++++++++++++++++++++++
hw/i386/pc_piix.c | 2 +
hw/i386/pc_q35.c | 2 +
hw/core/machine.c | 269 +++++++++++++++++++++++++++++++++++
hw/i386/fw_cfg.c | 3 +-
hw/net/rtl8139.c | 4 +-
hw/smbios/smbios.c | 46 +++++-
hw/timer/i8254_common.c | 2 +-
hw/usb/hcd-xhci-pci.c | 59 ++++++--
hw/usb/hcd-xhci-pci.h | 1 +
hw/virtio/virtio-mem.c | 3 +-
include/hw/boards.h | 40 ++++++
include/hw/firmware/smbios.h | 5 +-
include/hw/firmware/smbios.h | 4 +-
include/hw/i386/pc.h | 3 +
13 files changed, 413 insertions(+), 22 deletions(-)
13 files changed, 414 insertions(+), 24 deletions(-)
diff --git a/hw/acpi/piix4.c b/hw/acpi/piix4.c
index dd523d2e4c..5050c0ba97 100644
index debe1adb84..e8ddcd716e 100644
--- a/hw/acpi/piix4.c
+++ b/hw/acpi/piix4.c
@@ -245,7 +245,7 @@ static bool vmstate_test_migrate_acpi_index(void *opaque, int version_id)
@ -88,28 +97,28 @@ index dd523d2e4c..5050c0ba97 100644
- .minimum_version_id = 3,
+ .minimum_version_id = 2,
.post_load = vmstate_acpi_post_load,
.fields = (VMStateField[]) {
.fields = (const VMStateField[]) {
VMSTATE_PCI_DEVICE(parent_obj, PIIX4PMState),
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index af9ea4dd1c..62f0f7d4d6 100644
index 6c6d155002..36e9b4b4e9 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -1638,7 +1638,7 @@ static void virt_build_smbios(VirtMachineState *vms)
@@ -1651,7 +1651,7 @@ static void virt_build_smbios(VirtMachineState *vms)
smbios_set_defaults("QEMU", product,
vmc->smbios_old_sys_ver ? "1.0" : mc->name, false,
- true, SMBIOS_ENTRY_POINT_TYPE_64);
+ true, NULL, NULL, SMBIOS_ENTRY_POINT_TYPE_64);
vmc->smbios_old_sys_ver ? "1.0" : mc->name,
- true);
+ true, NULL, NULL);
/* build the array of physical mem area from base_memmap */
mem_array.address = vms->memmap[VIRT_MEM].base;
diff --git a/hw/core/machine.c b/hw/core/machine.c
index 0c17398141..446601ee30 100644
index 37ede0e7d4..695cb89a46 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -57,6 +57,273 @@ GlobalProperty hw_compat_7_2[] = {
@@ -296,6 +296,275 @@ GlobalProperty hw_compat_2_1[] = {
};
const size_t hw_compat_7_2_len = G_N_ELEMENTS(hw_compat_7_2);
const size_t hw_compat_2_1_len = G_N_ELEMENTS(hw_compat_2_1);
+/*
+ * RHEL only: machine types for previous major releases are deprecated
@ -132,6 +141,8 @@ index 0c17398141..446601ee30 100644
+ { "vfio-pci-nohotplug", "x-ramfb-migrate", "off" },
+ /* hw_compat_rhel_9_4 from hw_compat_8_1 */
+ { "igb", "x-pcie-flr-init", "off" },
+ /* hw_compat_rhel_9_4 jira RHEL-24045 */
+ { "virtio-mem", "dynamic-memslots", "off" },
+};
+const size_t hw_compat_rhel_9_4_len = G_N_ELEMENTS(hw_compat_rhel_9_4);
+
@ -378,37 +389,25 @@ index 0c17398141..446601ee30 100644
+};
+const size_t hw_compat_rhel_7_6_len = G_N_ELEMENTS(hw_compat_rhel_7_6);
+
GlobalProperty hw_compat_7_1[] = {
{ "virtio-device", "queue_reset", "false" },
{ "virtio-rng-pci", "vectors", "0" },
diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index eace854335..2a9f465619 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -238,6 +238,8 @@ static void pc_init1(MachineState *machine,
smbios_set_defaults("QEMU", mc->desc,
mc->name, pcmc->smbios_legacy_mode,
pcmc->smbios_uuid_encoded,
+ pcmc->smbios_stream_product,
+ pcmc->smbios_stream_version,
pcms->smbios_entry_point_type);
}
diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index 4f3e5412f6..912cb0c0dc 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -206,6 +206,8 @@ static void pc_q35_init(MachineState *machine)
smbios_set_defaults("QEMU", mc->desc,
mc->name, pcmc->smbios_legacy_mode,
pcmc->smbios_uuid_encoded,
+ pcmc->smbios_stream_product,
+ pcmc->smbios_stream_version,
pcms->smbios_entry_point_type);
MachineState *current_machine;
static char *machine_get_kernel(Object *obj, Error **errp)
diff --git a/hw/i386/fw_cfg.c b/hw/i386/fw_cfg.c
index d802d2787f..c7aa39a13e 100644
--- a/hw/i386/fw_cfg.c
+++ b/hw/i386/fw_cfg.c
@@ -64,7 +64,8 @@ void fw_cfg_build_smbios(PCMachineState *pcms, FWCfgState *fw_cfg,
if (pcmc->smbios_defaults) {
/* These values are guest ABI, do not change */
smbios_set_defaults("QEMU", mc->desc, mc->name,
- pcmc->smbios_uuid_encoded);
+ pcmc->smbios_uuid_encoded,
+ pcmc->smbios_stream_product, pcmc->smbios_stream_version);
}
/* tell smbios about cpuid version and features */
diff --git a/hw/net/rtl8139.c b/hw/net/rtl8139.c
index 4af8c66266..7dc12907ab 100644
index 897c86ec41..2d0db43f49 100644
--- a/hw/net/rtl8139.c
+++ b/hw/net/rtl8139.c
@@ -3169,7 +3169,7 @@ static int rtl8139_pre_save(void *opaque)
@ -431,20 +430,21 @@ index 4af8c66266..7dc12907ab 100644
VMSTATE_UINT16(tally_counters.TxUndrn, RTL8139State),
diff --git a/hw/smbios/smbios.c b/hw/smbios/smbios.c
index 2a90601ac5..7bde23e59d 100644
index eed5787b15..68608a3403 100644
--- a/hw/smbios/smbios.c
+++ b/hw/smbios/smbios.c
@@ -58,6 +58,9 @@ static bool smbios_legacy = true;
static bool smbios_uuid_encoded = true;
/* end: legacy structures & constants for <= 2.0 machines */
@@ -39,6 +39,10 @@ size_t usr_blobs_len;
static unsigned usr_table_max;
static unsigned usr_table_cnt;
+/* Set to true for modern Windows 10 HardwareID-6 compat */
+static bool smbios_type2_required;
+
+
uint8_t *smbios_tables;
size_t smbios_tables_len;
@@ -670,7 +673,7 @@ static void smbios_build_type_1_table(void)
unsigned smbios_table_max;
@@ -629,7 +633,7 @@ static void smbios_build_type_1_table(void)
static void smbios_build_type_2_table(void)
{
@ -453,21 +453,17 @@ index 2a90601ac5..7bde23e59d 100644
SMBIOS_TABLE_SET_STR(2, manufacturer_str, type2.manufacturer);
SMBIOS_TABLE_SET_STR(2, product_str, type2.product);
@@ -985,7 +988,10 @@ void smbios_set_cpuid(uint32_t version, uint32_t features)
@@ -1018,16 +1022,52 @@ void smbios_set_default_processor_family(uint16_t processor_family)
void smbios_set_defaults(const char *manufacturer, const char *product,
const char *version, bool legacy_mode,
- bool uuid_encoded, SmbiosEntryPointType ep_type)
const char *version,
- bool uuid_encoded)
+ bool uuid_encoded,
+ const char *stream_product,
+ const char *stream_version,
+ SmbiosEntryPointType ep_type)
+ const char *stream_version)
{
smbios_have_defaults = true;
smbios_legacy = legacy_mode;
@@ -1006,11 +1012,45 @@ void smbios_set_defaults(const char *manufacturer, const char *product,
g_free(smbios_entries);
}
smbios_uuid_encoded = uuid_encoded;
+ /*
+ * If @stream_product & @stream_version are non-NULL, then
@ -494,12 +490,12 @@ index 2a90601ac5..7bde23e59d 100644
+ *
+ * We get 'System Manufacturer' and 'Baseboard Manufacturer'
+ */
SMBIOS_SET_DEFAULT(type1.manufacturer, manufacturer);
SMBIOS_SET_DEFAULT(type1.product, product);
SMBIOS_SET_DEFAULT(type1.version, version);
+ SMBIOS_SET_DEFAULT(type1.family, "Red Hat Enterprise Linux");
SMBIOS_SET_DEFAULT(smbios_type1.manufacturer, manufacturer);
SMBIOS_SET_DEFAULT(smbios_type1.product, product);
SMBIOS_SET_DEFAULT(smbios_type1.version, version);
+ SMBIOS_SET_DEFAULT(smbios_type1.family, "Red Hat Enterprise Linux");
+ if (stream_version != NULL) {
+ SMBIOS_SET_DEFAULT(type1.sku, stream_version);
+ SMBIOS_SET_DEFAULT(smbios_type1.sku, stream_version);
+ }
SMBIOS_SET_DEFAULT(type2.manufacturer, manufacturer);
- SMBIOS_SET_DEFAULT(type2.product, product);
@ -513,20 +509,20 @@ index 2a90601ac5..7bde23e59d 100644
SMBIOS_SET_DEFAULT(type3.manufacturer, manufacturer);
SMBIOS_SET_DEFAULT(type3.version, version);
diff --git a/hw/timer/i8254_common.c b/hw/timer/i8254_common.c
index b25da448c8..0331e84398 100644
index 28fdabc321..bad13ec224 100644
--- a/hw/timer/i8254_common.c
+++ b/hw/timer/i8254_common.c
@@ -229,7 +229,7 @@ static const VMStateDescription vmstate_pit_common = {
.pre_save = pit_dispatch_pre_save,
.post_load = pit_dispatch_post_load,
.fields = (VMStateField[]) {
.fields = (const VMStateField[]) {
- VMSTATE_UINT32_V(channels[0].irq_disabled, PITCommonState, 3),
+ VMSTATE_UINT32(channels[0].irq_disabled, PITCommonState), /* qemu-kvm's v2 had 'flags' here */
VMSTATE_STRUCT_ARRAY(channels, PITCommonState, 3, 2,
vmstate_pit_channel, PITChannelState),
VMSTATE_INT64(channels[0].next_transition_time,
diff --git a/hw/usb/hcd-xhci-pci.c b/hw/usb/hcd-xhci-pci.c
index 643d4643e4..529bad9366 100644
index 4423983308..43b4b71fdf 100644
--- a/hw/usb/hcd-xhci-pci.c
+++ b/hw/usb/hcd-xhci-pci.c
@@ -104,6 +104,33 @@ static int xhci_pci_vmstate_post_load(void *opaque, int version_id)
@ -636,11 +632,26 @@ index 08f70ce97c..1be7527c1b 100644
} XHCIPciState;
#endif
diff --git a/hw/virtio/virtio-mem.c b/hw/virtio/virtio-mem.c
index ffd119ebac..0e2be2219c 100644
--- a/hw/virtio/virtio-mem.c
+++ b/hw/virtio/virtio-mem.c
@@ -1694,8 +1694,9 @@ static Property virtio_mem_properties[] = {
#endif
DEFINE_PROP_BOOL(VIRTIO_MEM_EARLY_MIGRATION_PROP, VirtIOMEM,
early_migration, true),
+ /* RHEL: default-enable "dynamic-memslots" (jira RHEL-24045) */
DEFINE_PROP_BOOL(VIRTIO_MEM_DYNAMIC_MEMSLOTS_PROP, VirtIOMEM,
- dynamic_memslots, false),
+ dynamic_memslots, true),
DEFINE_PROP_END_OF_LIST(),
};
diff --git a/include/hw/boards.h b/include/hw/boards.h
index da85f86efb..4a21eddbf9 100644
index 8b8f6d5c00..0466f9d0f3 100644
--- a/include/hw/boards.h
+++ b/include/hw/boards.h
@@ -503,4 +503,44 @@ extern const size_t hw_compat_2_2_len;
@@ -512,4 +512,44 @@ extern const size_t hw_compat_2_2_len;
extern GlobalProperty hw_compat_2_1[];
extern const size_t hw_compat_2_1_len;
@ -686,26 +697,25 @@ index da85f86efb..4a21eddbf9 100644
+extern const char *rhel_old_machine_deprecation;
#endif
diff --git a/include/hw/firmware/smbios.h b/include/hw/firmware/smbios.h
index 7f3259a630..d24b3ccd32 100644
index 8d3fb2fb3b..d9d6d7a169 100644
--- a/include/hw/firmware/smbios.h
+++ b/include/hw/firmware/smbios.h
@@ -294,7 +294,10 @@ void smbios_entry_add(QemuOpts *opts, Error **errp);
@@ -332,7 +332,9 @@ void smbios_entry_add(QemuOpts *opts, Error **errp);
void smbios_set_cpuid(uint32_t version, uint32_t features);
void smbios_set_defaults(const char *manufacturer, const char *product,
const char *version, bool legacy_mode,
- bool uuid_encoded, SmbiosEntryPointType ep_type);
const char *version,
- bool uuid_encoded);
+ bool uuid_encoded,
+ const char *stream_product,
+ const char *stream_version,
+ SmbiosEntryPointType ep_type);
uint8_t *smbios_get_table_legacy(MachineState *ms, size_t *length);
+ const char *stream_version);
void smbios_set_default_processor_family(uint16_t processor_family);
uint8_t *smbios_get_table_legacy(size_t *length, Error **errp);
void smbios_get_tables(MachineState *ms,
const struct smbios_phys_mem_area *mem_array,
diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h
index a10ceeabbf..037942d233 100644
index 27a68071d7..ebd8f973f2 100644
--- a/include/hw/i386/pc.h
+++ b/include/hw/i386/pc.h
@@ -113,6 +113,9 @@ struct PCMachineClass {
@@ -112,6 +112,9 @@ struct PCMachineClass {
bool smbios_legacy_mode;
bool smbios_uuid_encoded;
SmbiosEntryPointType default_smbios_ep_type;

138
0007-Add-aarch64-machine-types.patch
View File

@ -1,4 +1,4 @@
From 23f614ab0b79ec1c6f65a7f0d6993bfdfc53fd23 Mon Sep 17 00:00:00 2001
From cf398296f3fcee185a00f23de5deae57c97d648e Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Fri, 19 Oct 2018 12:53:31 +0200
Subject: Add aarch64 machine types
@ -30,6 +30,9 @@ Rebase notes (8.0.0):
Rebase notes (8.1.0):
- Added setting default_nic
Rebase notes (9.0.0 rc0):
- call arm_virt_compat_set on rhel type class_init
Merged patches (6.2.0):
- 9a3d4fde0e hw/arm/virt: Remove 9.0 machine type
- f7d04d6695 hw: arm: virt: Add hw_compat_rhel_8_5 to 8.5 machine type
@ -64,34 +67,67 @@ Merged patches (8.1.0):
Merged patches (8.2.0):
- 4ee284aca9 Add machine types compat bits. (partial)
Merged patches (9.0.0 rc0):
- 117068376a hw/arm/virt: Fix compats
- 8bcccfabc4 hw/arm/virt: Add properties to disable high memory regions
- 0005a8b93a hw/arm/virt: deprecate virt-rhel9.{0,2}.0 machine types
---
hw/arm/virt.c | 250 +++++++++++++++++++++++++++++++++++++++++-
hw/arm/virt.c | 299 +++++++++++++++++++++++++++++++++++++++++-
include/hw/arm/virt.h | 8 ++
2 files changed, 257 insertions(+), 1 deletion(-)
2 files changed, 306 insertions(+), 1 deletion(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 62f0f7d4d6..c541efee5e 100644
index 36e9b4b4e9..22bc345137 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -82,6 +82,7 @@
#include "hw/char/pl011.h"
#include "qemu/guest-random.h"
@@ -101,6 +101,7 @@ static void arm_virt_compat_set(MachineClass *mc)
arm_virt_compat_len);
}
+#if 0 /* Disabled for Red Hat Enterprise Linux */
#define DEFINE_VIRT_MACHINE_LATEST(major, minor, latest) \
static void virt_##major##_##minor##_class_init(ObjectClass *oc, \
void *data) \
@@ -108,7 +109,48 @@
@@ -128,7 +129,63 @@ static void arm_virt_compat_set(MachineClass *mc)
DEFINE_VIRT_MACHINE_LATEST(major, minor, true)
#define DEFINE_VIRT_MACHINE(major, minor) \
DEFINE_VIRT_MACHINE_LATEST(major, minor, false)
+#endif /* disabled for RHEL */
+
+/*
+ * This variable is for changes to properties that are RHEL specific,
+ * different to the current upstream and to be applied to the latest
+ * machine type. They may be overriden by older machine compats.
+ *
+ * virtio-net-pci variant romfiles are not needed because edk2 does
+ * fully support the pxe boot. Besides virtio romfiles are not shipped
+ * on rhel/aarch64.
+ */
+GlobalProperty arm_rhel_compat[] = {
+ {"virtio-net-pci", "romfile", "" },
+ {"virtio-net-pci-transitional", "romfile", "" },
+ {"virtio-net-pci-non-transitional", "romfile", "" },
+};
+const size_t arm_rhel_compat_len = G_N_ELEMENTS(arm_rhel_compat);
+/*
+ * This cannot be called from the rhel_virt_class_init() because
+ * TYPE_RHEL_MACHINE is abstract and mc->compat_props g_ptr_array_new()
+ * only is called on virt-rhelm.n.s non abstract class init.
+ */
+static void arm_rhel_compat_set(MachineClass *mc)
+{
+ compat_props_add(mc->compat_props, arm_rhel_compat,
+ arm_rhel_compat_len);
+}
+
+#define DEFINE_RHEL_MACHINE_LATEST(m, n, s, latest) \
+ static void rhel##m##n##s##_virt_class_init(ObjectClass *oc, \
+ void *data) \
+ { \
+ MachineClass *mc = MACHINE_CLASS(oc); \
+ arm_rhel_compat_set(mc); \
+ rhel##m##n##s##_virt_options(mc); \
+ mc->desc = "RHEL " # m "." # n "." # s " ARM Virtual Machine"; \
+ if (latest) { \
@ -114,23 +150,10 @@ index 62f0f7d4d6..c541efee5e 100644
+ DEFINE_RHEL_MACHINE_LATEST(major, minor, subminor, true)
+#define DEFINE_RHEL_MACHINE(major, minor, subminor) \
+ DEFINE_RHEL_MACHINE_LATEST(major, minor, subminor, false)
+
+/* This variable is for changes to properties that are RHEL specific,
+ * different to the current upstream and to be applied to the latest
+ * machine type.
+ */
+GlobalProperty arm_rhel_compat[] = {
+ {
+ .driver = "virtio-net-pci",
+ .property = "romfile",
+ .value = "",
+ },
+};
+const size_t arm_rhel_compat_len = G_N_ELEMENTS(arm_rhel_compat);
/* Number of external interrupt lines to configure the GIC with */
#define NUM_IRQS 256
@@ -2341,6 +2383,7 @@ static void machvirt_init(MachineState *machine)
@@ -2355,6 +2412,7 @@ static void machvirt_init(MachineState *machine)
qemu_add_machine_init_done_notifier(&vms->machine_done);
}
@ -138,7 +161,7 @@ index 62f0f7d4d6..c541efee5e 100644
static bool virt_get_secure(Object *obj, Error **errp)
{
VirtMachineState *vms = VIRT_MACHINE(obj);
@@ -2368,6 +2411,7 @@ static void virt_set_virt(Object *obj, bool value, Error **errp)
@@ -2382,6 +2440,7 @@ static void virt_set_virt(Object *obj, bool value, Error **errp)
vms->virt = value;
}
@ -146,7 +169,7 @@ index 62f0f7d4d6..c541efee5e 100644
static bool virt_get_highmem(Object *obj, Error **errp)
{
@@ -2383,6 +2427,7 @@ static void virt_set_highmem(Object *obj, bool value, Error **errp)
@@ -2397,6 +2456,7 @@ static void virt_set_highmem(Object *obj, bool value, Error **errp)
vms->highmem = value;
}
@ -154,16 +177,23 @@ index 62f0f7d4d6..c541efee5e 100644
static bool virt_get_compact_highmem(Object *obj, Error **errp)
{
VirtMachineState *vms = VIRT_MACHINE(obj);
@@ -2438,7 +2483,7 @@ static void virt_set_highmem_mmio(Object *obj, bool value, Error **errp)
@@ -2410,6 +2470,7 @@ static void virt_set_compact_highmem(Object *obj, bool value, Error **errp)
vms->highmem_mmio = value;
vms->highmem_compact = value;
}
-
+#endif /* disabled for RHEL */
static bool virt_get_highmem_redists(Object *obj, Error **errp)
{
@@ -2453,7 +2514,6 @@ static void virt_set_highmem_mmio(Object *obj, bool value, Error **errp)
vms->highmem_mmio = value;
}
-
static bool virt_get_its(Object *obj, Error **errp)
{
@@ -2454,6 +2499,7 @@ static void virt_set_its(Object *obj, bool value, Error **errp)
VirtMachineState *vms = VIRT_MACHINE(obj);
@@ -2468,6 +2528,7 @@ static void virt_set_its(Object *obj, bool value, Error **errp)
vms->its = value;
}
@ -171,7 +201,7 @@ index 62f0f7d4d6..c541efee5e 100644
static bool virt_get_dtb_randomness(Object *obj, Error **errp)
{
VirtMachineState *vms = VIRT_MACHINE(obj);
@@ -2467,6 +2513,7 @@ static void virt_set_dtb_randomness(Object *obj, bool value, Error **errp)
@@ -2481,6 +2542,7 @@ static void virt_set_dtb_randomness(Object *obj, bool value, Error **errp)
vms->dtb_randomness = value;
}
@ -179,7 +209,7 @@ index 62f0f7d4d6..c541efee5e 100644
static char *virt_get_oem_id(Object *obj, Error **errp)
{
@@ -2550,6 +2597,7 @@ static void virt_set_ras(Object *obj, bool value, Error **errp)
@@ -2564,6 +2626,7 @@ static void virt_set_ras(Object *obj, bool value, Error **errp)
vms->ras = value;
}
@ -187,7 +217,7 @@ index 62f0f7d4d6..c541efee5e 100644
static bool virt_get_mte(Object *obj, Error **errp)
{
VirtMachineState *vms = VIRT_MACHINE(obj);
@@ -2563,6 +2611,7 @@ static void virt_set_mte(Object *obj, bool value, Error **errp)
@@ -2577,6 +2640,7 @@ static void virt_set_mte(Object *obj, bool value, Error **errp)
vms->mte = value;
}
@ -195,7 +225,7 @@ index 62f0f7d4d6..c541efee5e 100644
static char *virt_get_gic_version(Object *obj, Error **errp)
{
@@ -2935,6 +2984,7 @@ static int virt_kvm_type(MachineState *ms, const char *type_str)
@@ -2949,6 +3013,7 @@ static int virt_kvm_type(MachineState *ms, const char *type_str)
return fixed_ipa ? 0 : requested_pa_size;
}
@ -203,7 +233,7 @@ index 62f0f7d4d6..c541efee5e 100644
static void virt_machine_class_init(ObjectClass *oc, void *data)
{
MachineClass *mc = MACHINE_CLASS(oc);
@@ -3405,3 +3455,201 @@ static void virt_machine_2_6_options(MachineClass *mc)
@@ -3463,3 +3528,235 @@ static void virt_machine_2_6_options(MachineClass *mc)
vmc->no_pmu = true;
}
DEFINE_VIRT_MACHINE(2, 6)
@ -213,6 +243,7 @@ index 62f0f7d4d6..c541efee5e 100644
+{
+ MachineClass *mc = MACHINE_CLASS(oc);
+ HotplugHandlerClass *hc = HOTPLUG_HANDLER_CLASS(oc);
+ arm_virt_compat_set(mc);
+
+ mc->family = "virt-rhel-Z";
+ mc->init = machvirt_init;
@ -258,6 +289,28 @@ index 62f0f7d4d6..c541efee5e 100644
+ "Set on/off to enable/disable using "
+ "physical address space above 32 bits");
+
+ object_class_property_add_bool(oc, "highmem-redists",
+ virt_get_highmem_redists,
+ virt_set_highmem_redists);
+ object_class_property_set_description(oc, "highmem-redists",
+ "Set on/off to enable/disable high "
+ "memory region for GICv3 or GICv4 "
+ "redistributor");
+
+ object_class_property_add_bool(oc, "highmem-ecam",
+ virt_get_highmem_ecam,
+ virt_set_highmem_ecam);
+ object_class_property_set_description(oc, "highmem-ecam",
+ "Set on/off to enable/disable high "
+ "memory region for PCI ECAM");
+
+ object_class_property_add_bool(oc, "highmem-mmio",
+ virt_get_highmem_mmio,
+ virt_set_highmem_mmio);
+ object_class_property_set_description(oc, "highmem-mmio",
+ "Set on/off to enable/disable high "
+ "memory region 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",
@ -382,14 +435,24 @@ index 62f0f7d4d6..c541efee5e 100644
+}
+type_init(rhel_machine_init);
+
+static void rhel940_virt_options(MachineClass *mc)
+{
+}
+DEFINE_RHEL_MACHINE_AS_LATEST(9, 4, 0)
+
+static void rhel920_virt_options(MachineClass *mc)
+{
+ compat_props_add(mc->compat_props, arm_rhel_compat, arm_rhel_compat_len);
+ rhel940_virt_options(mc);
+
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_4, hw_compat_rhel_9_4_len);
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_3, hw_compat_rhel_9_3_len);
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_2, hw_compat_rhel_9_2_len);
+
+ /* RHEL 9.4 is the first supported release */
+ mc->deprecation_reason =
+ "machine types for versions prior to 9.4 are deprecated";
+}
+DEFINE_RHEL_MACHINE_AS_LATEST(9, 2, 0)
+DEFINE_RHEL_MACHINE(9, 2, 0)
+
+static void rhel900_virt_options(MachineClass *mc)
+{
@ -398,6 +461,7 @@ index 62f0f7d4d6..c541efee5e 100644
+ rhel920_virt_options(mc);
+
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_1, hw_compat_rhel_9_1_len);
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_0, hw_compat_rhel_9_0_len);
+
+ /* Disable FEAT_LPA2 since old kernels (<= v5.12) don't boot with that feature */
+ vmc->no_tcg_lpa2 = true;
@ -406,10 +470,10 @@ index 62f0f7d4d6..c541efee5e 100644
+}
+DEFINE_RHEL_MACHINE(9, 0, 0)
diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h
index f69239850e..7b8abe5645 100644
index bb486d36b1..237fc77bda 100644
--- a/include/hw/arm/virt.h
+++ b/include/hw/arm/virt.h
@@ -177,9 +177,17 @@ struct VirtMachineState {
@@ -179,9 +179,17 @@ struct VirtMachineState {
#define VIRT_ECAM_ID(high) (high ? VIRT_HIGH_PCIE_ECAM : VIRT_PCIE_ECAM)

50
0008-Add-ppc64-machine-types.patch
View File

@ -1,4 +1,4 @@
From d03cff85f5f1b69b1a66011ebaa974ece81d31bc Mon Sep 17 00:00:00 2001
From fb905dbe5b51ed899062ef99a2dd7f238d3e3384 Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Fri, 19 Oct 2018 13:27:13 +0200
Subject: Add ppc64 machine types
@ -34,20 +34,20 @@ Merged patches (7.1.0):
8 files changed, 314 insertions(+), 1 deletion(-)
diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index df09aa9d6a..ff459e1a46 100644
index e9bc97fee0..a258d81846 100644
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -1689,6 +1689,9 @@ static void spapr_machine_reset(MachineState *machine, ShutdownCause reason)
@@ -1718,6 +1718,9 @@ static void spapr_machine_reset(MachineState *machine, ShutdownCause reason)
pef_kvm_reset(machine->cgs, &error_fatal);
spapr_caps_apply(spapr);
spapr_nested_reset(spapr);
+ if (spapr->svm_allowed) {
+ kvmppc_svm_allow(&error_fatal);
+ }
first_ppc_cpu = POWERPC_CPU(first_cpu);
if (kvm_enabled() && kvmppc_has_cap_mmu_radix() &&
@@ -3397,6 +3400,20 @@ static void spapr_set_host_serial(Object *obj, const char *value, Error **errp)
@@ -3421,6 +3424,20 @@ static void spapr_set_host_serial(Object *obj, const char *value, Error **errp)
spapr->host_serial = g_strdup(value);
}
@ -68,7 +68,7 @@ index df09aa9d6a..ff459e1a46 100644
static void spapr_instance_init(Object *obj)
{
SpaprMachineState *spapr = SPAPR_MACHINE(obj);
@@ -3475,6 +3492,12 @@ static void spapr_instance_init(Object *obj)
@@ -3499,6 +3516,12 @@ static void spapr_instance_init(Object *obj)
spapr_get_host_serial, spapr_set_host_serial);
object_property_set_description(obj, "host-serial",
"Host serial number to advertise in guest device tree");
@ -81,7 +81,7 @@ index df09aa9d6a..ff459e1a46 100644
}
static void spapr_machine_finalizefn(Object *obj)
@@ -4734,6 +4757,7 @@ static void spapr_machine_class_init(ObjectClass *oc, void *data)
@@ -4754,6 +4777,7 @@ static void spapr_machine_class_init(ObjectClass *oc, void *data)
vmc->client_architecture_support = spapr_vof_client_architecture_support;
vmc->quiesce = spapr_vof_quiesce;
vmc->setprop = spapr_vof_setprop;
@ -89,15 +89,15 @@ index df09aa9d6a..ff459e1a46 100644
}
static const TypeInfo spapr_machine_info = {
@@ -4785,6 +4809,7 @@ static void spapr_machine_latest_class_options(MachineClass *mc)
@@ -4805,6 +4829,7 @@ static void spapr_machine_latest_class_options(MachineClass *mc)
} \
type_init(spapr_machine_register_##suffix)
+#if 0 /* Disabled for Red Hat Enterprise Linux */
/*
* pseries-8.2
* pseries-9.0
*/
@@ -4967,6 +4992,7 @@ static void spapr_machine_4_1_class_options(MachineClass *mc)
@@ -4998,6 +5023,7 @@ static void spapr_machine_4_1_class_options(MachineClass *mc)
}
DEFINE_SPAPR_MACHINE(4_1, "4.1", false);
@ -105,7 +105,7 @@ index df09aa9d6a..ff459e1a46 100644
/*
* pseries-4.0
@@ -4982,6 +5008,8 @@ static bool phb_placement_4_0(SpaprMachineState *spapr, uint32_t index,
@@ -5013,6 +5039,8 @@ static bool phb_placement_4_0(SpaprMachineState *spapr, uint32_t index,
}
return true;
}
@ -114,7 +114,7 @@ index df09aa9d6a..ff459e1a46 100644
static void spapr_machine_4_0_class_options(MachineClass *mc)
{
SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc);
@@ -5306,6 +5334,221 @@ static void spapr_machine_2_1_class_options(MachineClass *mc)
@@ -5338,6 +5366,221 @@ static void spapr_machine_2_1_class_options(MachineClass *mc)
compat_props_add(mc->compat_props, hw_compat_2_1, hw_compat_2_1_len);
}
DEFINE_SPAPR_MACHINE(2_1, "2.1", false);
@ -337,7 +337,7 @@ index df09aa9d6a..ff459e1a46 100644
static void spapr_machine_register_types(void)
{
diff --git a/hw/ppc/spapr_cpu_core.c b/hw/ppc/spapr_cpu_core.c
index 33e0c8724c..9d01663f43 100644
index 3b0a47a28c..375e0c8e45 100644
--- a/hw/ppc/spapr_cpu_core.c
+++ b/hw/ppc/spapr_cpu_core.c
@@ -25,6 +25,7 @@
@ -348,7 +348,7 @@ index 33e0c8724c..9d01663f43 100644
static void spapr_reset_vcpu(PowerPCCPU *cpu)
{
@@ -261,6 +262,7 @@ static bool spapr_realize_vcpu(PowerPCCPU *cpu, SpaprMachineState *spapr,
@@ -264,6 +265,7 @@ static bool spapr_realize_vcpu(PowerPCCPU *cpu, SpaprMachineState *spapr,
{
CPUPPCState *env = &cpu->env;
CPUState *cs = CPU(cpu);
@ -356,7 +356,7 @@ index 33e0c8724c..9d01663f43 100644
if (!qdev_realize(DEVICE(cpu), NULL, errp)) {
return false;
@@ -277,6 +279,17 @@ static bool spapr_realize_vcpu(PowerPCCPU *cpu, SpaprMachineState *spapr,
@@ -280,6 +282,17 @@ static bool spapr_realize_vcpu(PowerPCCPU *cpu, SpaprMachineState *spapr,
/* Set time-base frequency to 512 MHz. vhyp must be set first. */
cpu_ppc_tb_init(env, SPAPR_TIMEBASE_FREQ);
@ -375,10 +375,10 @@ index 33e0c8724c..9d01663f43 100644
qdev_unrealize(DEVICE(cpu));
return false;
diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h
index e91791a1a9..1951d8a2a0 100644
index 4aaf23d28f..3233c54d11 100644
--- a/include/hw/ppc/spapr.h
+++ b/include/hw/ppc/spapr.h
@@ -154,6 +154,7 @@ struct SpaprMachineClass {
@@ -157,6 +157,7 @@ struct SpaprMachineClass {
bool pre_5_2_numa_associativity;
bool pre_6_2_numa_affinity;
@ -386,7 +386,7 @@ index e91791a1a9..1951d8a2a0 100644
bool (*phb_placement)(SpaprMachineState *spapr, uint32_t index,
uint64_t *buid, hwaddr *pio,
hwaddr *mmio32, hwaddr *mmio64,
@@ -256,6 +257,9 @@ struct SpaprMachineState {
@@ -259,6 +260,9 @@ struct SpaprMachineState {
/* Set by -boot */
char *boot_device;
@ -422,10 +422,10 @@ index ebef2cccec..ff2c00c60e 100644
const CompatInfo *compat = compat_by_pvr(compat_pvr);
const CompatInfo *min = compat_by_pvr(min_compat_pvr);
diff --git a/target/ppc/cpu-models.c b/target/ppc/cpu-models.c
index 69fddb05bc..64a05aaef3 100644
index f77ebfcc81..18e9422006 100644
--- a/target/ppc/cpu-models.c
+++ b/target/ppc/cpu-models.c
@@ -748,6 +748,7 @@
@@ -744,6 +744,7 @@
/* PowerPC CPU aliases */
PowerPCCPUAlias ppc_cpu_aliases[] = {
@ -434,10 +434,10 @@ index 69fddb05bc..64a05aaef3 100644
{ "405cr", "405crc" },
{ "405gp", "405gpd" },
diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h
index f8101ffa29..e799a2bee6 100644
index 67e6b2effd..11187aeb93 100644
--- a/target/ppc/cpu.h
+++ b/target/ppc/cpu.h
@@ -1635,6 +1635,7 @@ static inline int cpu_mmu_index(CPUPPCState *env, bool ifetch)
@@ -1655,6 +1655,7 @@ static inline int ppc_env_mmu_index(CPUPPCState *env, bool ifetch)
/* Compatibility modes */
#if defined(TARGET_PPC64)
@ -446,7 +446,7 @@ index f8101ffa29..e799a2bee6 100644
uint32_t min_compat_pvr, uint32_t max_compat_pvr);
bool ppc_type_check_compat(const char *cputype, uint32_t compat_pvr,
diff --git a/target/ppc/kvm.c b/target/ppc/kvm.c
index 9b1abe2fc4..56f1c46e8e 100644
index 8231feb2d4..59f640cf7b 100644
--- a/target/ppc/kvm.c
+++ b/target/ppc/kvm.c
@@ -89,6 +89,7 @@ static int cap_large_decr;
@ -465,7 +465,7 @@ index 9b1abe2fc4..56f1c46e8e 100644
cap_large_decr = kvmppc_get_dec_bits();
cap_fwnmi = kvm_vm_check_extension(s, KVM_CAP_PPC_FWNMI);
/*
@@ -2579,6 +2581,16 @@ bool kvmppc_supports_ail_3(void)
@@ -2564,6 +2566,16 @@ bool kvmppc_supports_ail_3(void)
return cap_ail_mode_3;
}
@ -482,7 +482,7 @@ index 9b1abe2fc4..56f1c46e8e 100644
PowerPCCPUClass *kvm_ppc_get_host_cpu_class(void)
{
uint32_t host_pvr = mfpvr();
@@ -2979,3 +2991,18 @@ bool kvm_arch_cpu_check_are_resettable(void)
@@ -2964,3 +2976,18 @@ bool kvm_arch_cpu_check_are_resettable(void)
void kvm_arch_accel_class_init(ObjectClass *oc)
{
}

20
0009-Add-s390x-machine-types.patch
View File

@ -1,4 +1,4 @@
From 3623043d4a923bf9f541d439c76e7874cf0fa81d Mon Sep 17 00:00:00 2001
From 04178c77cfe188b4eed9c08a0bf66842e61fe5dc Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Fri, 19 Oct 2018 13:47:32 +0200
Subject: Add s390x machine types
@ -49,18 +49,18 @@ Merged patches (8.2.0):
4 files changed, 174 insertions(+)
diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
index 7262725d2e..984891b82a 100644
index b1dcb3857f..ff753a29e0 100644
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -855,6 +855,7 @@ bool css_migration_enabled(void)
@@ -859,6 +859,7 @@ bool css_migration_enabled(void)
} \
type_init(ccw_machine_register_##suffix)
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void ccw_machine_8_2_instance_options(MachineState *machine)
static void ccw_machine_9_0_instance_options(MachineState *machine)
{
}
@@ -1256,6 +1257,164 @@ static void ccw_machine_2_4_class_options(MachineClass *mc)
@@ -1272,6 +1273,164 @@ static void ccw_machine_2_4_class_options(MachineClass *mc)
compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat));
}
DEFINE_CCW_MACHINE(2_4, "2.4", false);
@ -226,7 +226,7 @@ index 7262725d2e..984891b82a 100644
static void ccw_machine_register_types(void)
{
diff --git a/target/s390x/cpu_models.c b/target/s390x/cpu_models.c
index a63d990e4e..198b81f2c0 100644
index 8ed3bb6a27..370b3b3065 100644
--- a/target/s390x/cpu_models.c
+++ b/target/s390x/cpu_models.c
@@ -46,6 +46,9 @@
@ -239,7 +239,7 @@ index a63d990e4e..198b81f2c0 100644
static S390CPUDef s390_cpu_defs[] = {
CPUDEF_INIT(0x2064, 7, 1, 38, 0x00000000U, "z900", "IBM zSeries 900 GA1"),
CPUDEF_INIT(0x2064, 7, 2, 38, 0x00000000U, "z900.2", "IBM zSeries 900 GA2"),
@@ -856,22 +859,30 @@ static void s390_host_cpu_model_class_init(ObjectClass *oc, void *data)
@@ -866,22 +869,30 @@ static void s390_host_cpu_model_class_init(ObjectClass *oc, void *data)
static void s390_base_cpu_model_class_init(ObjectClass *oc, void *data)
{
S390CPUClass *xcc = S390_CPU_CLASS(oc);
@ -284,10 +284,10 @@ index d7b8912989..1a806a97c4 100644
/* CPU model based on a CPU definition */
diff --git a/target/s390x/cpu_models_sysemu.c b/target/s390x/cpu_models_sysemu.c
index 87a4480c05..28c1b0486c 100644
index 0728bfcc20..ca2e5d91e2 100644
--- a/target/s390x/cpu_models_sysemu.c
+++ b/target/s390x/cpu_models_sysemu.c
@@ -60,6 +60,7 @@ static void create_cpu_model_list(ObjectClass *klass, void *opaque)
@@ -59,6 +59,7 @@ static void create_cpu_model_list(ObjectClass *klass, void *opaque)
CpuDefinitionInfo *info;
char *name = g_strdup(object_class_get_name(klass));
S390CPUClass *scc = S390_CPU_CLASS(klass);
@ -295,7 +295,7 @@ index 87a4480c05..28c1b0486c 100644
/* strip off the -s390x-cpu */
g_strrstr(name, "-" TYPE_S390_CPU)[0] = 0;
@@ -69,6 +70,7 @@ static void create_cpu_model_list(ObjectClass *klass, void *opaque)
@@ -68,6 +69,7 @@ static void create_cpu_model_list(ObjectClass *klass, void *opaque)
info->migration_safe = scc->is_migration_safe;
info->q_static = scc->is_static;
info->q_typename = g_strdup(object_class_get_name(klass));

100
0010-Add-x86_64-machine-types.patch
View File

@ -1,4 +1,4 @@
From b432505cb28bc3b9b0c1849210ac6c63bca3fe37 Mon Sep 17 00:00:00 2001
From 3c88acb005806ad2386ab6c94a8831151f624738 Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Fri, 19 Oct 2018 13:10:31 +0200
Subject: Add x86_64 machine types
@ -57,23 +57,40 @@ Merged patches (8.1.0):
Merged patches (8.2.0):
- 4ee284aca9 Add machine types compat bits. (partial)
- 719e2ac147 Fix x86 machine type compatibility for qemu-kvm 8.1.0
Merged patches (9.0.0 rc0):
- 9149e2bc8f x86: rhel 9.2.0 machine type compat fix
---
hw/i386/fw_cfg.c | 2 +-
hw/i386/pc.c | 159 ++++++++++++++++++++-
hw/i386/pc_piix.c | 112 ++++++++++++++-
hw/i386/pc_q35.c | 285 ++++++++++++++++++++++++++++++++++++-
hw/i386/pc_piix.c | 109 ++++++++++++++
hw/i386/pc_q35.c | 285 +++++++++++++++++++++++++++++++++++++
include/hw/boards.h | 2 +
include/hw/i386/pc.h | 33 +++++
target/i386/cpu.c | 21 +++
target/i386/kvm/kvm-cpu.c | 1 +
target/i386/kvm/kvm.c | 4 +
tests/qtest/pvpanic-test.c | 5 +-
9 files changed, 615 insertions(+), 7 deletions(-)
10 files changed, 617 insertions(+), 4 deletions(-)
diff --git a/hw/i386/fw_cfg.c b/hw/i386/fw_cfg.c
index c7aa39a13e..283c3f4c16 100644
--- a/hw/i386/fw_cfg.c
+++ b/hw/i386/fw_cfg.c
@@ -63,7 +63,7 @@ void fw_cfg_build_smbios(PCMachineState *pcms, FWCfgState *fw_cfg,
if (pcmc->smbios_defaults) {
/* These values are guest ABI, do not change */
- smbios_set_defaults("QEMU", mc->desc, mc->name,
+ smbios_set_defaults("Red Hat", "KVM", mc->desc,
pcmc->smbios_uuid_encoded,
pcmc->smbios_stream_product, pcmc->smbios_stream_version);
}
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 29b9964733..a1faa9e92c 100644
index 5c21b0c4db..4a154c1a9a 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -323,6 +323,161 @@ GlobalProperty pc_compat_2_0[] = {
@@ -326,6 +326,161 @@ GlobalProperty pc_compat_2_0[] = {
};
const size_t pc_compat_2_0_len = G_N_ELEMENTS(pc_compat_2_0);
@ -235,15 +252,15 @@ index 29b9964733..a1faa9e92c 100644
GSIState *pc_gsi_create(qemu_irq **irqs, bool pci_enabled)
{
GSIState *s;
@@ -1826,6 +1981,7 @@ static void pc_machine_class_init(ObjectClass *oc, void *data)
pcmc->kvmclock_create_always = true;
@@ -1813,6 +1968,7 @@ static void pc_machine_class_init(ObjectClass *oc, void *data)
pcmc->resizable_acpi_blob = true;
x86mc->apic_xrupt_override = true;
assert(!mc->get_hotplug_handler);
+ mc->async_pf_vmexit_disable = false;
mc->get_hotplug_handler = pc_get_hotplug_handler;
mc->hotplug_allowed = pc_hotplug_allowed;
mc->cpu_index_to_instance_props = x86_cpu_index_to_props;
@@ -1836,7 +1992,8 @@ static void pc_machine_class_init(ObjectClass *oc, void *data)
@@ -1823,7 +1979,8 @@ static void pc_machine_class_init(ObjectClass *oc, void *data)
mc->has_hotpluggable_cpus = true;
mc->default_boot_order = "cad";
mc->block_default_type = IF_IDE;
@ -254,10 +271,10 @@ index 29b9964733..a1faa9e92c 100644
mc->wakeup = pc_machine_wakeup;
hc->pre_plug = pc_machine_device_pre_plug_cb;
diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index 2a9f465619..44038391fb 100644
index 18ba076609..a647262d63 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -53,6 +53,7 @@
@@ -52,6 +52,7 @@
#include "qapi/error.h"
#include "qemu/error-report.h"
#include "sysemu/xen.h"
@ -265,18 +282,7 @@ index 2a9f465619..44038391fb 100644
#ifdef CONFIG_XEN
#include <xen/hvm/hvm_info_table.h>
#include "hw/xen/xen_pt.h"
@@ -235,8 +236,8 @@ static void pc_init1(MachineState *machine,
if (pcmc->smbios_defaults) {
MachineClass *mc = MACHINE_GET_CLASS(machine);
/* These values are guest ABI, do not change */
- smbios_set_defaults("QEMU", mc->desc,
- mc->name, pcmc->smbios_legacy_mode,
+ smbios_set_defaults("Red Hat", "KVM",
+ mc->desc, pcmc->smbios_legacy_mode,
pcmc->smbios_uuid_encoded,
pcmc->smbios_stream_product,
pcmc->smbios_stream_version,
@@ -453,6 +454,7 @@ static void pc_set_south_bridge(Object *obj, int value, Error **errp)
@@ -422,6 +423,7 @@ static void pc_set_south_bridge(Object *obj, int value, Error **errp)
* hw_compat_*, pc_compat_*, or * pc_*_machine_options().
*/
@ -284,7 +290,7 @@ index 2a9f465619..44038391fb 100644
static void pc_compat_2_3_fn(MachineState *machine)
{
X86MachineState *x86ms = X86_MACHINE(machine);
@@ -970,3 +972,109 @@ static void xenfv_3_1_machine_options(MachineClass *m)
@@ -951,3 +953,110 @@ static void xenfv_3_1_machine_options(MachineClass *m)
DEFINE_PC_MACHINE(xenfv, "xenfv-3.1", pc_xen_hvm_init,
xenfv_3_1_machine_options);
#endif
@ -314,8 +320,7 @@ index 2a9f465619..44038391fb 100644
+
+static void pc_init_rhel760(MachineState *machine)
+{
+ pc_init1(machine, TYPE_I440FX_PCI_HOST_BRIDGE, \
+ TYPE_I440FX_PCI_DEVICE);
+ pc_init1(machine, TYPE_I440FX_PCI_DEVICE);
+}
+
+static void pc_machine_rhel760_options(MachineClass *m)
@ -339,6 +344,8 @@ index 2a9f465619..44038391fb 100644
+ pcmc->enforce_amd_1tb_hole = false;
+ /* From pc_i440fx_8_0_machine_options() */
+ pcmc->default_smbios_ep_type = SMBIOS_ENTRY_POINT_TYPE_32;
+ /* From pc_i440fx_8_1_machine_options() */
+ pcmc->broken_32bit_mem_addr_check = true;
+ /* Introduced in QEMU 8.2 */
+ pcmc->default_south_bridge = TYPE_PIIX3_DEVICE;
+
@ -395,21 +402,10 @@ index 2a9f465619..44038391fb 100644
+DEFINE_PC_MACHINE(rhel760, "pc-i440fx-rhel7.6.0", pc_init_rhel760,
+ pc_machine_rhel760_options);
diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index 912cb0c0dc..6387df97c8 100644
index c7bc8a2041..e872dc7e46 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -203,8 +203,8 @@ static void pc_q35_init(MachineState *machine)
if (pcmc->smbios_defaults) {
/* These values are guest ABI, do not change */
- smbios_set_defaults("QEMU", mc->desc,
- mc->name, pcmc->smbios_legacy_mode,
+ smbios_set_defaults("Red Hat", "KVM",
+ mc->desc, pcmc->smbios_legacy_mode,
pcmc->smbios_uuid_encoded,
pcmc->smbios_stream_product,
pcmc->smbios_stream_version,
@@ -363,6 +363,7 @@ static void pc_q35_init(MachineState *machine)
@@ -341,6 +341,7 @@ static void pc_q35_init(MachineState *machine)
DEFINE_PC_MACHINE(suffix, name, pc_init_##suffix, optionfn)
@ -417,7 +413,7 @@ index 912cb0c0dc..6387df97c8 100644
static void pc_q35_machine_options(MachineClass *m)
{
PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
@@ -699,3 +700,283 @@ static void pc_q35_2_4_machine_options(MachineClass *m)
@@ -693,3 +694,287 @@ static void pc_q35_2_4_machine_options(MachineClass *m)
DEFINE_Q35_MACHINE(v2_4, "pc-q35-2.4", NULL,
pc_q35_2_4_machine_options);
@ -444,6 +440,8 @@ index 912cb0c0dc..6387df97c8 100644
+ m->alias = "q35";
+ m->max_cpus = 710;
+ compat_props_add(m->compat_props, pc_rhel_compat, pc_rhel_compat_len);
+ compat_props_add(m->compat_props,
+ pc_q35_compat_defaults, pc_q35_compat_defaults_len);
+}
+
+static void pc_q35_init_rhel940(MachineState *machine)
@ -480,6 +478,8 @@ index 912cb0c0dc..6387df97c8 100644
+
+ /* From pc_q35_8_0_machine_options() */
+ pcmc->default_smbios_ep_type = SMBIOS_ENTRY_POINT_TYPE_32;
+ /* From pc_q35_8_1_machine_options() */
+ pcmc->broken_32bit_mem_addr_check = true;
+
+ compat_props_add(m->compat_props, hw_compat_rhel_9_4,
+ hw_compat_rhel_9_4_len);
@ -702,10 +702,10 @@ index 912cb0c0dc..6387df97c8 100644
+DEFINE_PC_MACHINE(q35_rhel760, "pc-q35-rhel7.6.0", pc_q35_init_rhel760,
+ pc_q35_machine_rhel760_options);
diff --git a/include/hw/boards.h b/include/hw/boards.h
index 4a21eddbf9..4edfdb0ddb 100644
index 0466f9d0f3..46b8725c41 100644
--- a/include/hw/boards.h
+++ b/include/hw/boards.h
@@ -277,6 +277,8 @@ struct MachineClass {
@@ -283,6 +283,8 @@ struct MachineClass {
strList *allowed_dynamic_sysbus_devices;
bool auto_enable_numa_with_memhp;
bool auto_enable_numa_with_memdev;
@ -715,12 +715,12 @@ index 4a21eddbf9..4edfdb0ddb 100644
bool smbus_no_migration_support;
bool nvdimm_supported;
diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h
index 037942d233..37644ede7e 100644
index ebd8f973f2..a984c951ad 100644
--- a/include/hw/i386/pc.h
+++ b/include/hw/i386/pc.h
@@ -314,6 +314,39 @@ extern const size_t pc_compat_1_4_len;
int pc_machine_kvm_type(MachineState *machine, const char *vm_type);
@@ -291,6 +291,39 @@ extern const size_t pc_compat_2_1_len;
extern GlobalProperty pc_compat_2_0[];
extern const size_t pc_compat_2_0_len;
+extern GlobalProperty pc_rhel_compat[];
+extern const size_t pc_rhel_compat_len;
@ -759,7 +759,7 @@ index 037942d233..37644ede7e 100644
static void pc_machine_##suffix##_class_init(ObjectClass *oc, void *data) \
{ \
diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index cd16cb893d..93203d9b91 100644
index 33760a2ee1..be7b0663cd 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -2190,9 +2190,13 @@ static const CPUCaches epyc_genoa_cache_info = {
@ -925,10 +925,10 @@ index 9c791b7b05..b91af5051f 100644
};
diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
index 4ce80555b4..9d41edf01e 100644
index e68cbe9293..739f33db47 100644
--- a/target/i386/kvm/kvm.c
+++ b/target/i386/kvm/kvm.c
@@ -3711,6 +3711,7 @@ static int kvm_get_msrs(X86CPU *cpu)
@@ -3715,6 +3715,7 @@ static int kvm_get_msrs(X86CPU *cpu)
struct kvm_msr_entry *msrs = cpu->kvm_msr_buf->entries;
int ret, i;
uint64_t mtrr_top_bits;
@ -936,7 +936,7 @@ index 4ce80555b4..9d41edf01e 100644
kvm_msr_buf_reset(cpu);
@@ -4065,6 +4066,9 @@ static int kvm_get_msrs(X86CPU *cpu)
@@ -4069,6 +4070,9 @@ static int kvm_get_msrs(X86CPU *cpu)
break;
case MSR_KVM_ASYNC_PF_EN:
env->async_pf_en_msr = msrs[i].data;

20
0011-Enable-make-check.patch
View File

@ -1,4 +1,4 @@
From 66a0510405e5142a1f9e38e0770aa0f10aed3e03 Mon Sep 17 00:00:00 2001
From 5768cf6811842e5c59da3b752f60659a9d6b5ba1 Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Wed, 2 Sep 2020 09:39:41 +0200
Subject: Enable make check
@ -63,10 +63,10 @@ Merged patches (8.1.0):
13 files changed, 33 insertions(+), 30 deletions(-)
diff --git a/tests/avocado/replay_kernel.py b/tests/avocado/replay_kernel.py
index c37afa662c..61c95a2198 100644
index 10d99403a4..c3422ea1e4 100644
--- a/tests/avocado/replay_kernel.py
+++ b/tests/avocado/replay_kernel.py
@@ -153,7 +153,7 @@ def test_aarch64_virt(self):
@@ -166,7 +166,7 @@ def test_aarch64_virt(self):
"""
:avocado: tags=arch:aarch64
:avocado: tags=machine:virt
@ -76,7 +76,7 @@ index c37afa662c..61c95a2198 100644
kernel_url = ('https://archives.fedoraproject.org/pub/archive/fedora'
'/linux/releases/29/Everything/aarch64/os/images/pxeboot'
diff --git a/tests/avocado/reverse_debugging.py b/tests/avocado/reverse_debugging.py
index 4cce5a5598..e9248a04a2 100644
index 92855a02a5..87822074b6 100644
--- a/tests/avocado/reverse_debugging.py
+++ b/tests/avocado/reverse_debugging.py
@@ -230,7 +230,7 @@ def test_aarch64_virt(self):
@ -120,7 +120,7 @@ index 15fd87b2c1..f0d9d89c93 100644
kernel_path = self._grab_aarch64_kernel()
kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE +
diff --git a/tests/qemu-iotests/meson.build b/tests/qemu-iotests/meson.build
index 53847cb98f..a2abdb650e 100644
index fad340ad59..3c0d5241f6 100644
--- a/tests/qemu-iotests/meson.build
+++ b/tests/qemu-iotests/meson.build
@@ -51,21 +51,21 @@ foreach format, speed: qemu_iotests_formats
@ -163,7 +163,7 @@ index 53847cb98f..a2abdb650e 100644
+# endforeach
endforeach
diff --git a/tests/qemu-iotests/testenv.py b/tests/qemu-iotests/testenv.py
index 3ff38f2661..cab9a2bd6c 100644
index 588f30a4f1..3929a3634f 100644
--- a/tests/qemu-iotests/testenv.py
+++ b/tests/qemu-iotests/testenv.py
@@ -244,6 +244,9 @@ def __init__(self, source_dir: str, build_dir: str,
@ -216,7 +216,7 @@ index 663bb6c485..2efc43e3f7 100644
"-device intel-hda,id=" HDA_ID CODEC_DEVICES);
diff --git a/tests/qtest/libqos/meson.build b/tests/qtest/libqos/meson.build
index 90aae42a22..9bc4e41af0 100644
index 3aed6efcb8..119613237e 100644
--- a/tests/qtest/libqos/meson.build
+++ b/tests/qtest/libqos/meson.build
@@ -44,7 +44,7 @@ libqos_srcs = files(
@ -242,10 +242,10 @@ index 8ac95b89f7..cd2102555c 100644
qtest_outl(s, 0xcf8, 0x8000f840); /* PMBASE */
diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build
index 47dabf91d0..0bdfa3a821 100644
index 36c5c13a7b..a2887d6057 100644
--- a/tests/qtest/meson.build
+++ b/tests/qtest/meson.build
@@ -97,7 +97,6 @@ qtests_i386 = \
@@ -101,7 +101,6 @@ qtests_i386 = \
'drive_del-test',
'tco-test',
'cpu-plug-test',
@ -254,7 +254,7 @@ index 47dabf91d0..0bdfa3a821 100644
'migration-test',
'test-x86-cpuid-compat',
diff --git a/tests/qtest/virtio-net-failover.c b/tests/qtest/virtio-net-failover.c
index 0d40bc1f2d..4c633c1584 100644
index 73dfabc272..a9dd304781 100644
--- a/tests/qtest/virtio-net-failover.c
+++ b/tests/qtest/virtio-net-failover.c
@@ -26,6 +26,7 @@

19
0012-vfio-cap-number-of-devices-that-can-be-assigned.patch
View File

@ -1,4 +1,4 @@
From a27cfa0b407bd806ce389a7c69d0130bcfd35244 Mon Sep 17 00:00:00 2001
From e06a905d726fc20ea6bd95dff1bd0ffe97ebb202 Mon Sep 17 00:00:00 2001
From: Bandan Das <bsd@redhat.com>
Date: Tue, 3 Dec 2013 20:05:13 +0100
Subject: vfio: cap number of devices that can be assigned
@ -27,7 +27,7 @@ to 64 as some usecases require more than 32 devices.
Signed-off-by: Bandan Das <bsd@redhat.com>
Rebase changes (231025):
Rebase changes (8.2.0):
- Update to upstream changes
---
hw/vfio/pci.c | 31 ++++++++++++++++++++++++++++++-
@ -35,10 +35,10 @@ Rebase changes (231025):
2 files changed, 31 insertions(+), 1 deletion(-)
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index c62c02f7b6..ec98080f28 100644
index 64780d1b79..57ac63c10c 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -48,6 +48,9 @@
@@ -50,6 +50,9 @@
/* Protected by BQL */
static KVMRouteChange vfio_route_change;
@ -48,15 +48,14 @@ index c62c02f7b6..ec98080f28 100644
static void vfio_disable_interrupts(VFIOPCIDevice *vdev);
static void vfio_mmap_set_enabled(VFIOPCIDevice *vdev, bool enabled);
static void vfio_msi_disable_common(VFIOPCIDevice *vdev);
@@ -3076,14 +3079,37 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
{
@@ -2946,13 +2949,36 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
ERRP_GUARD();
VFIOPCIDevice *vdev = VFIO_PCI(pdev);
VFIODevice *vbasedev = &vdev->vbasedev;
+ VFIODevice *vbasedev_iter;
+ VFIOGroup *group;
char *tmp, *subsys;
Error *err = NULL;
struct stat st;
- int i, ret;
+ int ret, i = 0;
bool is_mdev;
@ -84,10 +83,10 @@ index c62c02f7b6..ec98080f28 100644
+ return;
+ }
+
if (!vbasedev->sysfsdev) {
if (vbasedev->fd < 0 && !vbasedev->sysfsdev) {
if (!(~vdev->host.domain || ~vdev->host.bus ||
~vdev->host.slot || ~vdev->host.function)) {
@@ -3501,6 +3527,9 @@ static Property vfio_pci_dev_properties[] = {
@@ -3370,6 +3396,9 @@ static Property vfio_pci_dev_properties[] = {
DEFINE_PROP_BOOL("x-no-kvm-msix", VFIOPCIDevice, no_kvm_msix, false),
DEFINE_PROP_BOOL("x-no-geforce-quirks", VFIOPCIDevice,
no_geforce_quirks, false),
@ -98,7 +97,7 @@ index c62c02f7b6..ec98080f28 100644
false),
DEFINE_PROP_BOOL("x-no-vfio-ioeventfd", VFIOPCIDevice, no_vfio_ioeventfd,
diff --git a/hw/vfio/pci.h b/hw/vfio/pci.h
index fba8737ab2..eb74d9de2d 100644
index 6e64a2654e..b7de39c010 100644
--- a/hw/vfio/pci.h
+++ b/hw/vfio/pci.h
@@ -142,6 +142,7 @@ struct VFIOPCIDevice {

8
0013-Add-support-statement-to-help-output.patch
View File

@ -1,4 +1,4 @@
From 424f14d123fe1043518758605d94ed5ba50e52ad Mon Sep 17 00:00:00 2001
From b467dc6a24ef41fa574260429807711f6802a54d Mon Sep 17 00:00:00 2001
From: Eduardo Habkost <ehabkost@redhat.com>
Date: Wed, 4 Dec 2013 18:53:17 +0100
Subject: Add support statement to -help output
@ -21,10 +21,10 @@ Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
1 file changed, 9 insertions(+)
diff --git a/system/vl.c b/system/vl.c
index 2bcd9efb9a..93635ffc5b 100644
index c644222982..03c3b0aa94 100644
--- a/system/vl.c
+++ b/system/vl.c
@@ -870,9 +870,17 @@ static void version(void)
@@ -869,9 +869,17 @@ static void version(void)
QEMU_COPYRIGHT "\n");
}
@ -42,7 +42,7 @@ index 2bcd9efb9a..93635ffc5b 100644
printf("usage: %s [options] [disk_image]\n\n"
"'disk_image' is a raw hard disk image for IDE hard disk 0\n\n",
g_get_prgname());
@@ -898,6 +906,7 @@ static void help(int exitcode)
@@ -897,6 +905,7 @@ static void help(int exitcode)
"\n"
QEMU_HELP_BOTTOM "\n");

6
0014-Use-qemu-kvm-in-documentation-instead-of-qemu-system.patch
View File

@ -1,4 +1,4 @@
From c683ff4a770b77dbe707413840918a46f67fa825 Mon Sep 17 00:00:00 2001
From 20cc3a6d9bce3e40d165f865b5e398c300cae7bf Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Wed, 8 Jul 2020 08:35:50 +0200
Subject: Use qemu-kvm in documentation instead of qemu-system-<arch>
@ -36,10 +36,10 @@ index 52d6454b93..d74dbdeca9 100644
.. |I2C| replace:: I\ :sup:`2`\ C
.. |I2S| replace:: I\ :sup:`2`\ S
diff --git a/qemu-options.hx b/qemu-options.hx
index 42fd09e4de..557118cb1f 100644
index 8ce85d4559..4fc27ee2e2 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -3469,11 +3469,11 @@ SRST
@@ -3493,11 +3493,11 @@ SRST
::

4
0015-qcow2-Deprecation-warning-when-opening-v2-images-rw.patch
View File

@ -1,4 +1,4 @@
From 776bff1be5e98982a9bbc8345ff27274ff5b8c0f Mon Sep 17 00:00:00 2001
From 2f9fdd21ecf2810d0d83a8125ce0cc1e75dbb13a Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Fri, 20 Aug 2021 18:25:12 +0200
Subject: qcow2: Deprecation warning when opening v2 images rw
@ -44,7 +44,7 @@ Rebase notes (6.1.0):
2 files changed, 7 insertions(+)
diff --git a/block/qcow2.c b/block/qcow2.c
index 13e032bd5e..7968735346 100644
index 956128b409..0e8b2f7518 100644
--- a/block/qcow2.c
+++ b/block/qcow2.c
@@ -1358,6 +1358,12 @@ qcow2_do_open(BlockDriverState *bs, QDict *options, int flags,

121
0016-Add-upstream-compatibility-bits.patch Normal file
View File

@ -0,0 +1,121 @@
From 59470e8ab849f22b407f55292e540e16a8cad01a Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Wed, 20 Mar 2024 05:34:32 -0400
Subject: Add upstream compatibility bits
Adding new compats structure for changes introduced during rebase to QEMU 9.0.0.
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
---
Rebase notes (9.0.0 rc2):
- Add aw-bits setting for aarch compat record (overwritten for 9.4 and older)
---
hw/arm/virt.c | 3 +++
hw/core/machine.c | 10 ++++++++++
hw/i386/pc_piix.c | 3 ++-
hw/i386/pc_q35.c | 3 +++
hw/s390x/s390-virtio-ccw.c | 1 +
include/hw/boards.h | 3 +++
6 files changed, 22 insertions(+), 1 deletion(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 22bc345137..f1af9495c6 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -144,6 +144,8 @@ GlobalProperty arm_rhel_compat[] = {
{"virtio-net-pci", "romfile", "" },
{"virtio-net-pci-transitional", "romfile", "" },
{"virtio-net-pci-non-transitional", "romfile", "" },
+ /* arm_rhel_compat from arm_virt_compat, added for 9.0.0 rebase */
+ { TYPE_VIRTIO_IOMMU_PCI, "aw-bits", "48" },
};
const size_t arm_rhel_compat_len = G_N_ELEMENTS(arm_rhel_compat);
@@ -3728,6 +3730,7 @@ type_init(rhel_machine_init);
static void rhel940_virt_options(MachineClass *mc)
{
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_5, hw_compat_rhel_9_5_len);
}
DEFINE_RHEL_MACHINE_AS_LATEST(9, 4, 0)
diff --git a/hw/core/machine.c b/hw/core/machine.c
index 695cb89a46..0f256d9633 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -302,6 +302,16 @@ const size_t hw_compat_2_1_len = G_N_ELEMENTS(hw_compat_2_1);
const char *rhel_old_machine_deprecation =
"machine types for previous major releases are deprecated";
+GlobalProperty hw_compat_rhel_9_5[] = {
+ /* hw_compat_rhel_9_5 from hw_compat_8_2 */
+ { "migration", "zero-page-detection", "legacy"},
+ /* hw_compat_rhel_9_5 from hw_compat_8_2 */
+ { TYPE_VIRTIO_IOMMU_PCI, "granule", "4k" },
+ /* hw_compat_rhel_9_5 from hw_compat_8_2 */
+ { TYPE_VIRTIO_IOMMU_PCI, "aw-bits", "64" },
+};
+const size_t hw_compat_rhel_9_5_len = G_N_ELEMENTS(hw_compat_rhel_9_5);
+
GlobalProperty hw_compat_rhel_9_4[] = {
/* hw_compat_rhel_9_4 from hw_compat_8_0 */
{ TYPE_VIRTIO_NET, "host_uso", "off"},
diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index a647262d63..6b260682eb 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -1015,7 +1015,8 @@ static void pc_machine_rhel760_options(MachineClass *m)
object_class_property_set_description(oc, "x-south-bridge",
"Use a different south bridge than PIIX3");
-
+ compat_props_add(m->compat_props, hw_compat_rhel_9_5,
+ hw_compat_rhel_9_5_len);
compat_props_add(m->compat_props, hw_compat_rhel_9_4,
hw_compat_rhel_9_4_len);
compat_props_add(m->compat_props, hw_compat_rhel_9_3,
diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index e872dc7e46..2b54944c0f 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -733,6 +733,9 @@ static void pc_q35_machine_rhel940_options(MachineClass *m)
m->desc = "RHEL-9.4.0 PC (Q35 + ICH9, 2009)";
pcmc->smbios_stream_product = "RHEL";
pcmc->smbios_stream_version = "9.4.0";
+
+ compat_props_add(m->compat_props, hw_compat_rhel_9_5,
+ hw_compat_rhel_9_5_len);
}
DEFINE_PC_MACHINE(q35_rhel940, "pc-q35-rhel9.4.0", pc_q35_init_rhel940,
diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
index ff753a29e0..9ad54682c6 100644
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -1282,6 +1282,7 @@ static void ccw_machine_rhel940_instance_options(MachineState *machine)
static void ccw_machine_rhel940_class_options(MachineClass *mc)
{
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_5, hw_compat_rhel_9_5_len);
}
DEFINE_CCW_MACHINE(rhel940, "rhel9.4.0", true);
diff --git a/include/hw/boards.h b/include/hw/boards.h
index 46b8725c41..cca62f906b 100644
--- a/include/hw/boards.h
+++ b/include/hw/boards.h
@@ -514,6 +514,9 @@ extern const size_t hw_compat_2_2_len;
extern GlobalProperty hw_compat_2_1[];
extern const size_t hw_compat_2_1_len;
+extern GlobalProperty hw_compat_rhel_9_5[];
+extern const size_t hw_compat_rhel_9_5_len;
+
extern GlobalProperty hw_compat_rhel_9_4[];
extern const size_t hw_compat_rhel_9_4_len;
--
2.39.3

44
0016-Introduce-RHEL-9.4.0-qemu-kvm-machine-type-for-aarch.patch
View File

@ -1,44 +0,0 @@
From 3b9b38339346ebfaf3e8ddf0822eba1cc9e78408 Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Thu, 14 Dec 2023 04:42:01 -0500
Subject: Introduce RHEL 9.4.0 qemu-kvm machine type for aarch64
Jira: https://issues.redhat.com/browse/RHEL-17168
Adding new machine type to support enabling new features.
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
---
hw/arm/virt.c | 9 ++++++++-
1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index c541efee5e..0b17c94ad7 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -3630,14 +3630,21 @@ static void rhel_machine_init(void)
}
type_init(rhel_machine_init);
+static void rhel940_virt_options(MachineClass *mc)
+{
+}
+DEFINE_RHEL_MACHINE_AS_LATEST(9, 4, 0)
+
static void rhel920_virt_options(MachineClass *mc)
{
+ rhel940_virt_options(mc);
+
compat_props_add(mc->compat_props, arm_rhel_compat, arm_rhel_compat_len);
compat_props_add(mc->compat_props, hw_compat_rhel_9_4, hw_compat_rhel_9_4_len);
compat_props_add(mc->compat_props, hw_compat_rhel_9_3, hw_compat_rhel_9_3_len);
compat_props_add(mc->compat_props, hw_compat_rhel_9_2, hw_compat_rhel_9_2_len);
}
-DEFINE_RHEL_MACHINE_AS_LATEST(9, 2, 0)
+DEFINE_RHEL_MACHINE(9, 2, 0)
static void rhel900_virt_options(MachineClass *mc)
{
--
2.39.3

30
0017-x86-rhel-9.4.0-machine-type-compat-fix.patch Normal file
View File

@ -0,0 +1,30 @@
From ba574acacf679850e337ec2d5e7836b8277cf393 Mon Sep 17 00:00:00 2001
From: Sebastian Ott <sebott@redhat.com>
Date: Thu, 18 Apr 2024 15:04:28 +0200
Subject: x86: rhel 9.4.0 machine type compat fix
Fix up the compatibility for 9.4.0. Ensure that pc-q35-rhel9.4.0
still uses SMBIOS 3.X by default.
Signed-off-by: Sebastian Ott <sebott@redhat.com>
---
hw/i386/pc_q35.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index 2b54944c0f..2f11f9af7d 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -734,6 +734,9 @@ static void pc_q35_machine_rhel940_options(MachineClass *m)
pcmc->smbios_stream_product = "RHEL";
pcmc->smbios_stream_version = "9.4.0";
+ /* From pc_q35_8_2_machine_options() - use SMBIOS 3.X by default */
+ pcmc->default_smbios_ep_type = SMBIOS_ENTRY_POINT_TYPE_64;
+
compat_props_add(m->compat_props, hw_compat_rhel_9_5,
hw_compat_rhel_9_5_len);
}
--
2.39.3

37
kvm-Compile-IOMMUFD-object-on-aarch64.patch
View File

@ -1,37 +0,0 @@
From 363d6aedc82314a70bdfbe9fa23b7e8fdda50138 Mon Sep 17 00:00:00 2001
From: Eric Auger <eric.auger@redhat.com>
Date: Thu, 11 Jan 2024 12:26:19 -0500
Subject: [PATCH 066/101] Compile IOMMUFD object on aarch64
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 211: IOMMUFD backend backport
RH-Jira: RHEL-19302 RHEL-21057
RH-Acked-by: Cédric Le Goater <clg@redhat.com>
RH-Acked-by: Sebastian Ott <sebott@redhat.com>
RH-Commit: [65/67] 9358030fdd499c5fe122dee3bb4f114966fac9c2 (eauger1/centos-qemu-kvm)
Upstream: RHEL only
Compiles the IOMMUFD object on aarch64 to be able to use
the IOMMUFD VFIO backend.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
configs/devices/aarch64-softmmu/aarch64-rh-devices.mak | 1 +
1 file changed, 1 insertion(+)
diff --git a/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak b/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak
index aec1831199..b0191d3c69 100644
--- a/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak
+++ b/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak
@@ -39,3 +39,4 @@ CONFIG_PXB=y
CONFIG_VHOST_VSOCK=y
CONFIG_VHOST_USER_VSOCK=y
CONFIG_VHOST_USER_FS=y
+CONFIG_IOMMUFD=y
--
2.39.3

37
kvm-Compile-IOMMUFD-on-s390x.patch
View File

@ -1,37 +0,0 @@
From c1e9ddf8d0ea6d358fcaa5cacd3a91920f36e73b Mon Sep 17 00:00:00 2001
From: Eric Auger <eric.auger@redhat.com>
Date: Thu, 11 Jan 2024 12:33:17 -0500
Subject: [PATCH 067/101] Compile IOMMUFD on s390x
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 211: IOMMUFD backend backport
RH-Jira: RHEL-19302 RHEL-21057
RH-Acked-by: Cédric Le Goater <clg@redhat.com>
RH-Acked-by: Sebastian Ott <sebott@redhat.com>
RH-Commit: [66/67] d3004aafca2bb76d817ac99c3d65973b8fbd4557 (eauger1/centos-qemu-kvm)
Upstream: RHEL only
Compiles the IOMMUFD object on s390x to be able to use
the IOMMUFD VFIO backend.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
configs/devices/s390x-softmmu/s390x-rh-devices.mak | 1 +
1 file changed, 1 insertion(+)
diff --git a/configs/devices/s390x-softmmu/s390x-rh-devices.mak b/configs/devices/s390x-softmmu/s390x-rh-devices.mak
index 69a799adbd..24cf6dbd03 100644
--- a/configs/devices/s390x-softmmu/s390x-rh-devices.mak
+++ b/configs/devices/s390x-softmmu/s390x-rh-devices.mak
@@ -16,3 +16,4 @@ CONFIG_WDT_DIAG288=y
CONFIG_VHOST_VSOCK=y
CONFIG_VHOST_USER_VSOCK=y
CONFIG_VHOST_USER_FS=y
+CONFIG_IOMMUFD=y
--
2.39.3

37
kvm-Compile-IOMMUFD-on-x86_64.patch
View File

@ -1,37 +0,0 @@
From be2c3d9bbee1bdec061c901f507bc999fa40a53e Mon Sep 17 00:00:00 2001
From: Eric Auger <eric.auger@redhat.com>
Date: Thu, 11 Jan 2024 12:34:44 -0500
Subject: [PATCH 068/101] Compile IOMMUFD on x86_64
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 211: IOMMUFD backend backport
RH-Jira: RHEL-19302 RHEL-21057
RH-Acked-by: Cédric Le Goater <clg@redhat.com>
RH-Acked-by: Sebastian Ott <sebott@redhat.com>
RH-Commit: [67/67] 411d48a5cc7ce1f05be793fd9a89c143ce34c91a (eauger1/centos-qemu-kvm)
Upstream: RHEL only
Compiles the IOMMUFD object on s390x to be able to use
the IOMMUFD VFIO backend.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
configs/devices/x86_64-softmmu/x86_64-rh-devices.mak | 1 +
1 file changed, 1 insertion(+)
diff --git a/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak b/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak
index ce5be73633..ba41108e0c 100644
--- a/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak
+++ b/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak
@@ -108,3 +108,4 @@ CONFIG_SGX=y
CONFIG_VHOST_VSOCK=y
CONFIG_VHOST_USER_VSOCK=y
CONFIG_VHOST_USER_FS=y
+CONFIG_IOMMUFD=y
--
2.39.3

155
kvm-Implement-SMBIOS-type-9-v2.6.patch
View File

@ -1,155 +0,0 @@
From 5c639f8ce65183ce8e44ee8e0230e9d627a440d7 Mon Sep 17 00:00:00 2001
From: Igor Mammedov <imammedo@redhat.com>
Date: Wed, 21 Feb 2024 17:00:27 +0000
Subject: [PATCH 05/20] Implement SMBIOS type 9 v2.6
RH-Author: Igor Mammedov <imammedo@redhat.com>
RH-MergeRequest: 230: Workaround Windows failing to find 64bit SMBIOS entry point with SeaBIOS
RH-Jira: RHEL-21705
RH-Acked-by: MST <mst@redhat.com>
RH-Acked-by: Ani Sinha <None>
RH-Commit: [3/18] ead230527d93938907a561cf5b985ee4f54d82b1
JIRA: https://issues.redhat.com/browse/RHEL-21705
Author: Felix Wu <flwu@google.com>
Signed-off-by: Felix Wu <flwu@google.com>
Signed-off-by: Nabih Estefan <nabihestefan@google.com>
Message-Id: <20240221170027.1027325-3-nabihestefan@google.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
(cherry picked from commit 04f143d828845d0fd52dd4a52664d81a4f5431f7)
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
---
hw/smbios/smbios.c | 49 +++++++++++++++++++++++++++++++++---
include/hw/firmware/smbios.h | 4 +++
qemu-options.hx | 2 +-
3 files changed, 51 insertions(+), 4 deletions(-)
diff --git a/hw/smbios/smbios.c b/hw/smbios/smbios.c
index 4f5637d445..074705fa4c 100644
--- a/hw/smbios/smbios.c
+++ b/hw/smbios/smbios.c
@@ -124,7 +124,7 @@ static QTAILQ_HEAD(, type8_instance) type8 = QTAILQ_HEAD_INITIALIZER(type8);
/* type 9 instance for parsing */
struct type9_instance {
- const char *slot_designation;
+ const char *slot_designation, *pcidev;
uint8_t slot_type, slot_data_bus_width, current_usage, slot_length,
slot_characteristics1, slot_characteristics2;
uint16_t slot_id;
@@ -427,6 +427,11 @@ static const QemuOptDesc qemu_smbios_type9_opts[] = {
.type = QEMU_OPT_NUMBER,
.help = "slot characteristics2, see the spec",
},
+ {
+ .name = "pci_device",
+ .type = QEMU_OPT_STRING,
+ .help = "PCI device, if provided."
+ }
};
static const QemuOptDesc qemu_smbios_type11_opts[] = {
@@ -851,7 +856,7 @@ static void smbios_build_type_8_table(void)
}
}
-static void smbios_build_type_9_table(void)
+static void smbios_build_type_9_table(Error **errp)
{
unsigned instance = 0;
struct type9_instance *t9;
@@ -868,6 +873,43 @@ static void smbios_build_type_9_table(void)
t->slot_characteristics1 = t9->slot_characteristics1;
t->slot_characteristics2 = t9->slot_characteristics2;
+ if (t9->pcidev) {
+ PCIDevice *pdev = NULL;
+ int rc = pci_qdev_find_device(t9->pcidev, &pdev);
+ if (rc != 0) {
+ error_setg(errp,
+ "No PCI device %s for SMBIOS type 9 entry %s",
+ t9->pcidev, t9->slot_designation);
+ return;
+ }
+ /*
+ * We only handle the case were the device is attached to
+ * the PCI root bus. The general case is more complex as
+ * bridges are enumerated later and the table would need
+ * to be updated at this moment.
+ */
+ if (!pci_bus_is_root(pci_get_bus(pdev))) {
+ error_setg(errp,
+ "Cannot create type 9 entry for PCI device %s: "
+ "not attached to the root bus",
+ t9->pcidev);
+ return;
+ }
+ t->segment_group_number = cpu_to_le16(0);
+ t->bus_number = pci_dev_bus_num(pdev);
+ t->device_number = pdev->devfn;
+ } else {
+ /*
+ * Per SMBIOS spec, For slots that are not of the PCI, AGP, PCI-X,
+ * or PCI-Express type that do not have bus/device/function
+ * information, 0FFh should be populated in the fields of Segment
+ * Group Number, Bus Number, Device/Function Number.
+ */
+ t->segment_group_number = 0xff;
+ t->bus_number = 0xff;
+ t->device_number = 0xff;
+ }
+
SMBIOS_BUILD_TABLE_POST;
instance++;
}
@@ -1222,7 +1264,7 @@ void smbios_get_tables(MachineState *ms,
}
smbios_build_type_8_table();
- smbios_build_type_9_table();
+ smbios_build_type_9_table(errp);
smbios_build_type_11_table();
#define MAX_DIMM_SZ (16 * GiB)
@@ -1568,6 +1610,7 @@ void smbios_entry_add(QemuOpts *opts, Error **errp)
t->slot_id = qemu_opt_get_number(opts, "slot_id", 0);
t->slot_characteristics1 = qemu_opt_get_number(opts, "slot_characteristics1", 0);
t->slot_characteristics2 = qemu_opt_get_number(opts, "slot_characteristics2", 0);
+ save_opt(&t->pcidev, opts, "pcidev");
QTAILQ_INSERT_TAIL(&type9, t, next);
return;
}
diff --git a/include/hw/firmware/smbios.h b/include/hw/firmware/smbios.h
index 6bbd5a4c20..f8dd07fe4c 100644
--- a/include/hw/firmware/smbios.h
+++ b/include/hw/firmware/smbios.h
@@ -222,6 +222,10 @@ struct smbios_type_9 {
uint16_t slot_id;
uint8_t slot_characteristics1;
uint8_t slot_characteristics2;
+ /* SMBIOS spec v2.6+ */
+ uint16_t segment_group_number;
+ uint8_t bus_number;
+ uint8_t device_number;
} QEMU_PACKED;
/* SMBIOS type 11 - OEM strings */
diff --git a/qemu-options.hx b/qemu-options.hx
index 94cacc2c63..93364e1765 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -2710,7 +2710,7 @@ SRST
``-smbios type=4[,sock_pfx=str][,manufacturer=str][,version=str][,serial=str][,asset=str][,part=str][,processor-id=%d]``
Specify SMBIOS type 4 fields
-``-smbios type=9[,slot_designation=str][,slot_type=%d][,slot_data_bus_width=%d][,current_usage=%d][,slot_length=%d][,slot_id=%d][,slot_characteristics1=%d][,slot_characteristics12=%d]``
+``-smbios type=9[,slot_designation=str][,slot_type=%d][,slot_data_bus_width=%d][,current_usage=%d][,slot_length=%d][,slot_id=%d][,slot_characteristics1=%d][,slot_characteristics12=%d][,pci_device=str]``
Specify SMBIOS type 9 fields
``-smbios type=11[,value=str][,path=filename]``
--
2.39.3

218
kvm-Implement-base-of-SMBIOS-type-9-descriptor.patch
View File

@ -1,218 +0,0 @@
From 84fc607d678bd72397a41d706e91fa241fd97266 Mon Sep 17 00:00:00 2001
From: Igor Mammedov <imammedo@redhat.com>
Date: Wed, 21 Feb 2024 17:00:26 +0000
Subject: [PATCH 04/20] Implement base of SMBIOS type 9 descriptor.
RH-Author: Igor Mammedov <imammedo@redhat.com>
RH-MergeRequest: 230: Workaround Windows failing to find 64bit SMBIOS entry point with SeaBIOS
RH-Jira: RHEL-21705
RH-Acked-by: MST <mst@redhat.com>
RH-Acked-by: Ani Sinha <None>
RH-Commit: [2/18] 2678cc080bfbf3357fa2f94ceaf42fc61b690d32
JIRA: https://issues.redhat.com/browse/RHEL-21705
commit: 735eee07d1f963635d3c3bf9f5e4bf1bc000870e
Author: Felix Wu <flwu@google.com>
Version 2.1+.
Signed-off-by: Felix Wu <flwu@google.com>
Signed-off-by: Nabih Estefan <nabihestefan@google.com>
Message-Id: <20240221170027.1027325-2-nabihestefan@google.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
---
hw/smbios/smbios.c | 99 ++++++++++++++++++++++++++++++++++++
include/hw/firmware/smbios.h | 13 +++++
qemu-options.hx | 3 ++
3 files changed, 115 insertions(+)
diff --git a/hw/smbios/smbios.c b/hw/smbios/smbios.c
index 7bde23e59d..4f5637d445 100644
--- a/hw/smbios/smbios.c
+++ b/hw/smbios/smbios.c
@@ -122,6 +122,16 @@ struct type8_instance {
};
static QTAILQ_HEAD(, type8_instance) type8 = QTAILQ_HEAD_INITIALIZER(type8);
+/* type 9 instance for parsing */
+struct type9_instance {
+ const char *slot_designation;
+ uint8_t slot_type, slot_data_bus_width, current_usage, slot_length,
+ slot_characteristics1, slot_characteristics2;
+ uint16_t slot_id;
+ QTAILQ_ENTRY(type9_instance) next;
+};
+static QTAILQ_HEAD(, type9_instance) type9 = QTAILQ_HEAD_INITIALIZER(type9);
+
static struct {
size_t nvalues;
char **values;
@@ -371,6 +381,54 @@ static const QemuOptDesc qemu_smbios_type8_opts[] = {
},
};
+static const QemuOptDesc qemu_smbios_type9_opts[] = {
+ {
+ .name = "type",
+ .type = QEMU_OPT_NUMBER,
+ .help = "SMBIOS element type",
+ },
+ {
+ .name = "slot_designation",
+ .type = QEMU_OPT_STRING,
+ .help = "string number for reference designation",
+ },
+ {
+ .name = "slot_type",
+ .type = QEMU_OPT_NUMBER,
+ .help = "connector type",
+ },
+ {
+ .name = "slot_data_bus_width",
+ .type = QEMU_OPT_NUMBER,
+ .help = "port type",
+ },
+ {
+ .name = "current_usage",
+ .type = QEMU_OPT_NUMBER,
+ .help = "current usage",
+ },
+ {
+ .name = "slot_length",
+ .type = QEMU_OPT_NUMBER,
+ .help = "system slot length",
+ },
+ {
+ .name = "slot_id",
+ .type = QEMU_OPT_NUMBER,
+ .help = "system slot id",
+ },
+ {
+ .name = "slot_characteristics1",
+ .type = QEMU_OPT_NUMBER,
+ .help = "slot characteristics1, see the spec",
+ },
+ {
+ .name = "slot_characteristics2",
+ .type = QEMU_OPT_NUMBER,
+ .help = "slot characteristics2, see the spec",
+ },
+};
+
static const QemuOptDesc qemu_smbios_type11_opts[] = {
{
.name = "value",
@@ -594,6 +652,7 @@ bool smbios_skip_table(uint8_t type, bool required_table)
#define T2_BASE 0x200
#define T3_BASE 0x300
#define T4_BASE 0x400
+#define T9_BASE 0x900
#define T11_BASE 0xe00
#define T16_BASE 0x1000
@@ -792,6 +851,28 @@ static void smbios_build_type_8_table(void)
}
}
+static void smbios_build_type_9_table(void)
+{
+ unsigned instance = 0;
+ struct type9_instance *t9;
+
+ QTAILQ_FOREACH(t9, &type9, next) {
+ SMBIOS_BUILD_TABLE_PRE(9, T9_BASE + instance, true);
+
+ SMBIOS_TABLE_SET_STR(9, slot_designation, t9->slot_designation);
+ t->slot_type = t9->slot_type;
+ t->slot_data_bus_width = t9->slot_data_bus_width;
+ t->current_usage = t9->current_usage;
+ t->slot_length = t9->slot_length;
+ t->slot_id = t9->slot_id;
+ t->slot_characteristics1 = t9->slot_characteristics1;
+ t->slot_characteristics2 = t9->slot_characteristics2;
+
+ SMBIOS_BUILD_TABLE_POST;
+ instance++;
+ }
+}
+
static void smbios_build_type_11_table(void)
{
char count_str[128];
@@ -1141,6 +1222,7 @@ void smbios_get_tables(MachineState *ms,
}
smbios_build_type_8_table();
+ smbios_build_type_9_table();
smbios_build_type_11_table();
#define MAX_DIMM_SZ (16 * GiB)
@@ -1472,6 +1554,23 @@ void smbios_entry_add(QemuOpts *opts, Error **errp)
t8_i->port_type = qemu_opt_get_number(opts, "port_type", 0);
QTAILQ_INSERT_TAIL(&type8, t8_i, next);
return;
+ case 9: {
+ if (!qemu_opts_validate(opts, qemu_smbios_type9_opts, errp)) {
+ return;
+ }
+ struct type9_instance *t;
+ t = g_new0(struct type9_instance, 1);
+ save_opt(&t->slot_designation, opts, "slot_designation");
+ t->slot_type = qemu_opt_get_number(opts, "slot_type", 0);
+ t->slot_data_bus_width = qemu_opt_get_number(opts, "slot_data_bus_width", 0);
+ t->current_usage = qemu_opt_get_number(opts, "current_usage", 0);
+ t->slot_length = qemu_opt_get_number(opts, "slot_length", 0);
+ t->slot_id = qemu_opt_get_number(opts, "slot_id", 0);
+ t->slot_characteristics1 = qemu_opt_get_number(opts, "slot_characteristics1", 0);
+ t->slot_characteristics2 = qemu_opt_get_number(opts, "slot_characteristics2", 0);
+ QTAILQ_INSERT_TAIL(&type9, t, next);
+ return;
+ }
case 11:
if (!qemu_opts_validate(opts, qemu_smbios_type11_opts, errp)) {
return;
diff --git a/include/hw/firmware/smbios.h b/include/hw/firmware/smbios.h
index d24b3ccd32..6bbd5a4c20 100644
--- a/include/hw/firmware/smbios.h
+++ b/include/hw/firmware/smbios.h
@@ -211,6 +211,19 @@ struct smbios_type_8 {
uint8_t port_type;
} QEMU_PACKED;
+/* SMBIOS type 9 - System Slots (v2.1+) */
+struct smbios_type_9 {
+ struct smbios_structure_header header;
+ uint8_t slot_designation;
+ uint8_t slot_type;
+ uint8_t slot_data_bus_width;
+ uint8_t current_usage;
+ uint8_t slot_length;
+ uint16_t slot_id;
+ uint8_t slot_characteristics1;
+ uint8_t slot_characteristics2;
+} QEMU_PACKED;
+
/* SMBIOS type 11 - OEM strings */
struct smbios_type_11 {
struct smbios_structure_header header;
diff --git a/qemu-options.hx b/qemu-options.hx
index 0814f43066..94cacc2c63 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -2710,6 +2710,9 @@ SRST
``-smbios type=4[,sock_pfx=str][,manufacturer=str][,version=str][,serial=str][,asset=str][,part=str][,processor-id=%d]``
Specify SMBIOS type 4 fields
+``-smbios type=9[,slot_designation=str][,slot_type=%d][,slot_data_bus_width=%d][,current_usage=%d][,slot_length=%d][,slot_id=%d][,slot_characteristics1=%d][,slot_characteristics12=%d]``
+ Specify SMBIOS type 9 fields
+
``-smbios type=11[,value=str][,path=filename]``
Specify SMBIOS type 11 fields
--
2.39.3

60
kvm-Revert-chardev-char-socket-Fix-TLS-io-channels-sendi.patch
View File

@ -1,60 +0,0 @@
From 2e0e4355b2d4edb66b7d8c198339e17940abd682 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Daniel=20P=2E=20Berrang=C3=A9?= <berrange@redhat.com>
Date: Mon, 18 Mar 2024 13:03:19 +0000
Subject: [PATCH 2/3] Revert "chardev/char-socket: Fix TLS io channels sending
too much data to the backend"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Daniel P. Berrangé <berrange@redhat.com>
RH-MergeRequest: 233: Fix handling of TLS sessions in chardevs
RH-Jira: RHEL-24614
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Marc-André Lureau <marcandre.lureau@redhat.com>
RH-Commit: [2/3] 1cb3d72b86ced0f70a09dfa0d325ae8a85db1b2b (berrange/centos-src-qemu)
This commit results in unexpected termination of the TLS connection.
When 'fd_can_read' returns 0, the code goes on to pass a zero length
buffer to qio_channel_read. The TLS impl calls into gnutls_recv()
with this zero length buffer, at which point GNUTLS returns an error
GNUTLS_E_INVALID_REQUEST. This is treated as fatal by QEMU's TLS code
resulting in the connection being torn down by the chardev.
Simply skipping the qio_channel_read when the buffer length is zero
is also not satisfactory, as it results in a high CPU burn busy loop
massively slowing QEMU's functionality.
The proper solution is to avoid tcp_chr_read being called at all
unless the frontend is able to accept more data. This will be done
in a followup commit.
This reverts commit 462945cd22d2bcd233401ed3aa167d83a8e35b05
Reviewed-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
(cherry picked from commit e8ee827ffdb86ebbd5f5213a1f78123c25a90864)
---
chardev/char-socket.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/chardev/char-socket.c b/chardev/char-socket.c
index f48d341ebc..51d0943fce 100644
--- a/chardev/char-socket.c
+++ b/chardev/char-socket.c
@@ -492,9 +492,9 @@ static gboolean tcp_chr_read(QIOChannel *chan, GIOCondition cond, void *opaque)
s->max_size <= 0) {
return TRUE;
}
- len = tcp_chr_read_poll(opaque);
- if (len > sizeof(buf)) {
- len = sizeof(buf);
+ len = sizeof(buf);
+ if (len > s->max_size) {
+ len = s->max_size;
}
size = tcp_chr_recv(chr, (void *)buf, len);
if (size == 0 || (size == -1 && errno != EAGAIN)) {
--
2.39.3

216
kvm-Revert-chardev-use-a-child-source-for-qio-input-sour.patch
View File

@ -1,216 +0,0 @@
From ab5a33d57b48e35388928e388bb6e6479bc77651 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Daniel=20P=2E=20Berrang=C3=A9?= <berrange@redhat.com>
Date: Mon, 18 Mar 2024 17:08:30 +0000
Subject: [PATCH 3/3] Revert "chardev: use a child source for qio input source"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Daniel P. Berrangé <berrange@redhat.com>
RH-MergeRequest: 233: Fix handling of TLS sessions in chardevs
RH-Jira: RHEL-24614
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Marc-André Lureau <marcandre.lureau@redhat.com>
RH-Commit: [3/3] b58e6c19c2b11d5d28db31cf1386226fb01d195e (berrange/centos-src-qemu)
This reverts commit a7077b8e354d90fec26c2921aa2dea85b90dff90,
and add comments to explain why child sources cannot be used.
When a GSource is added as a child of another GSource, if its
'prepare' function indicates readiness, then the parent's
'prepare' function will never be run. The io_watch_poll_prepare
absolutely *must* be run on every iteration of the main loop,
to ensure that the chardev backend doesn't feed data to the
frontend that it is unable to consume.
At the time a7077b8e354d90fec26c2921aa2dea85b90dff90 was made,
all the child GSource impls were relying on poll'ing an FD,
so their 'prepare' functions would never indicate readiness
ahead of poll() being invoked. So the buggy behaviour was
not noticed and lay dormant.
Relatively recently the QIOChannelTLS impl introduced a
level 2 child GSource, which checks with GNUTLS whether it
has cached any data that was decoded but not yet consumed:
commit ffda5db65aef42266a5053a4be34515106c4c7ee
Author: Antoine Damhet <antoine.damhet@shadow.tech>
Date: Tue Nov 15 15:23:29 2022 +0100
io/channel-tls: fix handling of bigger read buffers
Since the TLS backend can read more data from the underlying QIOChannel
we introduce a minimal child GSource to notify if we still have more
data available to be read.
Signed-off-by: Antoine Damhet <antoine.damhet@shadow.tech>
Signed-off-by: Charles Frey <charles.frey@shadow.tech>
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
With this, it is now quite common for the 'prepare' function
on a QIOChannelTLS GSource to indicate immediate readiness,
bypassing the parent GSource 'prepare' function. IOW, the
critical 'io_watch_poll_prepare' is being skipped on some
iterations of the main loop. As a result chardev frontend
asserts are now being triggered as they are fed data they
are not ready to consume.
A reproducer is as follows:
* In terminal 1 run a GNUTLS *echo* server
$ gnutls-serv --echo \
--x509cafile ca-cert.pem \
--x509keyfile server-key.pem \
--x509certfile server-cert.pem \
-p 9000
* In terminal 2 run a QEMU guest
$ qemu-system-s390x \
-nodefaults \
-display none \
-object tls-creds-x509,id=tls0,dir=$PWD,endpoint=client \
-chardev socket,id=con0,host=localhost,port=9000,tls-creds=tls0 \
-device sclpconsole,chardev=con0 \
-hda Fedora-Cloud-Base-39-1.5.s390x.qcow2
After the previous patch revert, but before this patch revert,
this scenario will crash:
qemu-system-s390x: ../hw/char/sclpconsole.c:73: chr_read: Assertion
`size <= SIZE_BUFFER_VT220 - scon->iov_data_len' failed.
This assert indicates that 'tcp_chr_read' was called without
'tcp_chr_read_poll' having first been checked for ability to
receive more data
QEMU's use of a 'prepare' function to create/delete another
GSource is rather a hack and not normally the kind of thing that
is expected to be done by a GSource. There is no mechanism to
force GLib to always run the 'prepare' function of a parent
GSource. The best option is to simply not use the child source
concept, and go back to the functional approach previously
relied on.
Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Tested-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
(cherry picked from commit 038b4217884c6f297278bb1ec6f0463c6c8221de)
---
chardev/char-io.c | 56 ++++++++++++++++++++++++++++++++++++++++++-----
1 file changed, 51 insertions(+), 5 deletions(-)
diff --git a/chardev/char-io.c b/chardev/char-io.c
index 4451128cba..dab77b112e 100644
--- a/chardev/char-io.c
+++ b/chardev/char-io.c
@@ -33,6 +33,7 @@ typedef struct IOWatchPoll {
IOCanReadHandler *fd_can_read;
GSourceFunc fd_read;
void *opaque;
+ GMainContext *context;
} IOWatchPoll;
static IOWatchPoll *io_watch_poll_from_source(GSource *source)
@@ -50,28 +51,59 @@ static gboolean io_watch_poll_prepare(GSource *source,
return FALSE;
}
+ /*
+ * We do not register the QIOChannel watch as a child GSource.
+ * The 'prepare' function on the parent GSource will be
+ * skipped if a child GSource's 'prepare' function indicates
+ * readiness. We need this prepare function be guaranteed
+ * to run on *every* iteration of the main loop, because
+ * it is critical to ensure we remove the QIOChannel watch
+ * if 'fd_can_read' indicates the frontend cannot receive
+ * more data.
+ */
if (now_active) {
iwp->src = qio_channel_create_watch(
iwp->ioc, G_IO_IN | G_IO_ERR | G_IO_HUP | G_IO_NVAL);
g_source_set_callback(iwp->src, iwp->fd_read, iwp->opaque, NULL);
- g_source_add_child_source(source, iwp->src);
- g_source_unref(iwp->src);
+ g_source_attach(iwp->src, iwp->context);
} else {
- g_source_remove_child_source(source, iwp->src);
+ g_source_destroy(iwp->src);
+ g_source_unref(iwp->src);
iwp->src = NULL;
}
return FALSE;
}
+static gboolean io_watch_poll_check(GSource *source)
+{
+ return FALSE;
+}
+
static gboolean io_watch_poll_dispatch(GSource *source, GSourceFunc callback,
gpointer user_data)
{
- return G_SOURCE_CONTINUE;
+ abort();
+}
+
+static void io_watch_poll_finalize(GSource *source)
+{
+ /*
+ * Due to a glib bug, removing the last reference to a source
+ * inside a finalize callback causes recursive locking (and a
+ * deadlock). This is not a problem inside other callbacks,
+ * including dispatch callbacks, so we call io_remove_watch_poll
+ * to remove this source. At this point, iwp->src must
+ * be NULL, or we would leak it.
+ */
+ IOWatchPoll *iwp = io_watch_poll_from_source(source);
+ assert(iwp->src == NULL);
}
static GSourceFuncs io_watch_poll_funcs = {
.prepare = io_watch_poll_prepare,
+ .check = io_watch_poll_check,
.dispatch = io_watch_poll_dispatch,
+ .finalize = io_watch_poll_finalize,
};
GSource *io_add_watch_poll(Chardev *chr,
@@ -91,6 +123,7 @@ GSource *io_add_watch_poll(Chardev *chr,
iwp->ioc = ioc;
iwp->fd_read = (GSourceFunc) fd_read;
iwp->src = NULL;
+ iwp->context = context;
name = g_strdup_printf("chardev-iowatch-%s", chr->label);
g_source_set_name((GSource *)iwp, name);
@@ -101,10 +134,23 @@ GSource *io_add_watch_poll(Chardev *chr,
return (GSource *)iwp;
}
+static void io_remove_watch_poll(GSource *source)
+{
+ IOWatchPoll *iwp;
+
+ iwp = io_watch_poll_from_source(source);
+ if (iwp->src) {
+ g_source_destroy(iwp->src);
+ g_source_unref(iwp->src);
+ iwp->src = NULL;
+ }
+ g_source_destroy(&iwp->parent);
+}
+
void remove_fd_in_watch(Chardev *chr)
{
if (chr->gsource) {
- g_source_destroy(chr->gsource);
+ io_remove_watch_poll(chr->gsource);
chr->gsource = NULL;
}
}
--
2.39.3

60
kvm-aio-make-aio_context_acquire-aio_context_release-a-n.patch
View File

@ -1,60 +0,0 @@
From 6b5cfed21e20b372090046a934387255ff4bda58 Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Tue, 5 Dec 2023 13:20:01 -0500
Subject: [PATCH 084/101] aio: make aio_context_acquire()/aio_context_release()
a no-op
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 214: Remove AioContext lock
RH-Jira: RHEL-15965
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Commit: [15/26] 723dcada900aaf08862e8221921be22506b561a8 (kmwolf/centos-qemu-kvm)
aio_context_acquire()/aio_context_release() has been replaced by
fine-grained locking to protect state shared by multiple threads. The
AioContext lock still plays the role of balancing locking in
AIO_WAIT_WHILE() and many functions in QEMU either require that the
AioContext lock is held or not held for this reason. In other words, the
AioContext lock is purely there for consistency with itself and serves
no real purpose anymore.
Stop actually acquiring/releasing the lock in
aio_context_acquire()/aio_context_release() so that subsequent patches
can remove callers across the codebase incrementally.
I have performed "make check" and qemu-iotests stress tests across
x86-64, ppc64le, and aarch64 to confirm that there are no failures as a
result of eliminating the lock.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Acked-by: Kevin Wolf <kwolf@redhat.com>
Message-ID: <20231205182011.1976568-5-stefanha@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
util/async.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/util/async.c b/util/async.c
index 8f90ddc304..04ee83d220 100644
--- a/util/async.c
+++ b/util/async.c
@@ -725,12 +725,12 @@ void aio_context_unref(AioContext *ctx)
void aio_context_acquire(AioContext *ctx)
{
- qemu_rec_mutex_lock(&ctx->lock);
+ /* TODO remove this function */
}
void aio_context_release(AioContext *ctx)
{
- qemu_rec_mutex_unlock(&ctx->lock);
+ /* TODO remove this function */
}
QEMU_DEFINE_STATIC_CO_TLS(AioContext *, my_aiocontext)
--
2.39.3

102
kvm-aio-remove-aio_context_acquire-aio_context_release-A.patch
View File

@ -1,102 +0,0 @@
From 14913d8970090c8914dc19dad14f3b9f91985ec3 Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Tue, 5 Dec 2023 13:20:07 -0500
Subject: [PATCH 090/101] aio: remove
aio_context_acquire()/aio_context_release() API
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 214: Remove AioContext lock
RH-Jira: RHEL-15965
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Commit: [21/26] 4b6d4afcac79d3248a6722b063b5fc777dc418df (kmwolf/centos-qemu-kvm)
Delete these functions because nothing calls these functions anymore.
I introduced these APIs in commit 98563fc3ec44 ("aio: add
aio_context_acquire() and aio_context_release()") in 2014. It's with a
sigh of relief that I delete these APIs almost 10 years later.
Thanks to Paolo Bonzini's vision for multi-queue QEMU, we got an
understanding of where the code needed to go in order to remove the
limitations that the original dataplane and the IOThread/AioContext
approach that followed it.
Emanuele Giuseppe Esposito had the splendid determination to convert
large parts of the codebase so that they no longer needed the AioContext
lock. This was a painstaking process, both in the actual code changes
required and the iterations of code review that Emanuele eked out of
Kevin and me over many months.
Kevin Wolf tackled multitudes of graph locking conversions to protect
in-flight I/O from run-time changes to the block graph as well as the
clang Thread Safety Analysis annotations that allow the compiler to
check whether the graph lock is being used correctly.
And me, well, I'm just here to add some pizzazz to the QEMU multi-queue
block layer :). Thank you to everyone who helped with this effort,
including Eric Blake, code reviewer extraordinaire, and others who I've
forgotten to mention.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-ID: <20231205182011.1976568-11-stefanha@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
include/block/aio.h | 17 -----------------
util/async.c | 10 ----------
2 files changed, 27 deletions(-)
diff --git a/include/block/aio.h b/include/block/aio.h
index f08b358077..af05512a7d 100644
--- a/include/block/aio.h
+++ b/include/block/aio.h
@@ -278,23 +278,6 @@ void aio_context_ref(AioContext *ctx);
*/
void aio_context_unref(AioContext *ctx);
-/* Take ownership of the AioContext. If the AioContext will be shared between
- * threads, and a thread does not want to be interrupted, it will have to
- * take ownership around calls to aio_poll(). Otherwise, aio_poll()
- * automatically takes care of calling aio_context_acquire and
- * aio_context_release.
- *
- * Note that this is separate from bdrv_drained_begin/bdrv_drained_end. A
- * thread still has to call those to avoid being interrupted by the guest.
- *
- * Bottom halves, timers and callbacks can be created or removed without
- * acquiring the AioContext.
- */
-void aio_context_acquire(AioContext *ctx);
-
-/* Relinquish ownership of the AioContext. */
-void aio_context_release(AioContext *ctx);
-
/**
* aio_bh_schedule_oneshot_full: Allocate a new bottom half structure that will
* run only once and as soon as possible.
diff --git a/util/async.c b/util/async.c
index dfd44ef612..460529057c 100644
--- a/util/async.c
+++ b/util/async.c
@@ -719,16 +719,6 @@ void aio_context_unref(AioContext *ctx)
g_source_unref(&ctx->source);
}
-void aio_context_acquire(AioContext *ctx)
-{
- /* TODO remove this function */
-}
-
-void aio_context_release(AioContext *ctx)
-{
- /* TODO remove this function */
-}
-
QEMU_DEFINE_STATIC_CO_TLS(AioContext *, my_aiocontext)
AioContext *qemu_get_current_aio_context(void)
--
2.39.3

81
kvm-aio-wait-draw-equivalence-between-AIO_WAIT_WHILE-and.patch
View File

@ -1,81 +0,0 @@
From e1e2f3972065c4b5d6fcf37e0e1c4fb92a0d5260 Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Tue, 5 Dec 2023 13:20:06 -0500
Subject: [PATCH 089/101] aio-wait: draw equivalence between AIO_WAIT_WHILE()
and AIO_WAIT_WHILE_UNLOCKED()
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 214: Remove AioContext lock
RH-Jira: RHEL-15965
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Commit: [20/26] 20e49777869714c99769263103f1b0c2c370cfcd (kmwolf/centos-qemu-kvm)
Now that the AioContext lock no longer exists, AIO_WAIT_WHILE() and
AIO_WAIT_WHILE_UNLOCKED() are equivalent.
A future patch will get rid of AIO_WAIT_WHILE_UNLOCKED().
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-ID: <20231205182011.1976568-10-stefanha@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
include/block/aio-wait.h | 16 ++++------------
1 file changed, 4 insertions(+), 12 deletions(-)
diff --git a/include/block/aio-wait.h b/include/block/aio-wait.h
index 5449b6d742..157f105916 100644
--- a/include/block/aio-wait.h
+++ b/include/block/aio-wait.h
@@ -63,9 +63,6 @@ extern AioWait global_aio_wait;
* @ctx: the aio context, or NULL if multiple aio contexts (for which the
* caller does not hold a lock) are involved in the polling condition.
* @cond: wait while this conditional expression is true
- * @unlock: whether to unlock and then lock again @ctx. This applies
- * only when waiting for another AioContext from the main loop.
- * Otherwise it's ignored.
*
* Wait while a condition is true. Use this to implement synchronous
* operations that require event loop activity.
@@ -78,7 +75,7 @@ extern AioWait global_aio_wait;
* wait on conditions between two IOThreads since that could lead to deadlock,
* go via the main loop instead.
*/
-#define AIO_WAIT_WHILE_INTERNAL(ctx, cond, unlock) ({ \
+#define AIO_WAIT_WHILE_INTERNAL(ctx, cond) ({ \
bool waited_ = false; \
AioWait *wait_ = &global_aio_wait; \
AioContext *ctx_ = (ctx); \
@@ -95,13 +92,7 @@ extern AioWait global_aio_wait;
assert(qemu_get_current_aio_context() == \
qemu_get_aio_context()); \
while ((cond)) { \
- if (unlock && ctx_) { \
- aio_context_release(ctx_); \
- } \
aio_poll(qemu_get_aio_context(), true); \
- if (unlock && ctx_) { \
- aio_context_acquire(ctx_); \
- } \
waited_ = true; \
} \
} \
@@ -109,10 +100,11 @@ extern AioWait global_aio_wait;
waited_; })
#define AIO_WAIT_WHILE(ctx, cond) \
- AIO_WAIT_WHILE_INTERNAL(ctx, cond, true)
+ AIO_WAIT_WHILE_INTERNAL(ctx, cond)
+/* TODO replace this with AIO_WAIT_WHILE() in a future patch */
#define AIO_WAIT_WHILE_UNLOCKED(ctx, cond) \
- AIO_WAIT_WHILE_INTERNAL(ctx, cond, false)
+ AIO_WAIT_WHILE_INTERNAL(ctx, cond)
/**
* aio_wait_kick:
--
2.39.3

476
kvm-backends-iommufd-Introduce-the-iommufd-object.patch
View File

@ -1,476 +0,0 @@
From 0d8255c98b3ef6f603ff0279592d3e91de26de0e Mon Sep 17 00:00:00 2001
From: Eric Auger <eric.auger@redhat.com>
Date: Tue, 21 Nov 2023 16:44:00 +0800
Subject: [PATCH 021/101] backends/iommufd: Introduce the iommufd object
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 211: IOMMUFD backend backport
RH-Jira: RHEL-19302 RHEL-21057
RH-Acked-by: Cédric Le Goater <clg@redhat.com>
RH-Acked-by: Sebastian Ott <sebott@redhat.com>
RH-Commit: [20/67] 8a56344ab4a2126f248bfa492ccddd19265f39be (eauger1/centos-qemu-kvm)
Introduce an iommufd object which allows the interaction
with the host /dev/iommu device.
The /dev/iommu can have been already pre-opened outside of qemu,
in which case the fd can be passed directly along with the
iommufd object:
This allows the iommufd object to be shared accross several
subsystems (VFIO, VDPA, ...). For example, libvirt would open
the /dev/iommu once.
If no fd is passed along with the iommufd object, the /dev/iommu
is opened by the qemu code.
Suggested-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Yi Liu <yi.l.liu@intel.com>
Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Tested-by: Eric Auger <eric.auger@redhat.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Cédric Le Goater <clg@redhat.com>
(cherry picked from commit 6e6d8ac62b5b38dc9d4b69ffdf073f0a0b43b7be)
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
MAINTAINERS | 8 ++
backends/Kconfig | 4 +
backends/iommufd.c | 245 +++++++++++++++++++++++++++++++++++++++
backends/meson.build | 1 +
backends/trace-events | 10 ++
include/sysemu/iommufd.h | 38 ++++++
qapi/qom.json | 19 +++
qemu-options.hx | 12 ++
8 files changed, 337 insertions(+)
create mode 100644 backends/iommufd.c
create mode 100644 include/sysemu/iommufd.h
diff --git a/MAINTAINERS b/MAINTAINERS
index 695e0bd34f..a5a446914a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2167,6 +2167,14 @@ F: hw/vfio/ap.c
F: docs/system/s390x/vfio-ap.rst
L: qemu-s390x@nongnu.org
+iommufd
+M: Yi Liu <yi.l.liu@intel.com>
+M: Eric Auger <eric.auger@redhat.com>
+M: Zhenzhong Duan <zhenzhong.duan@intel.com>
+S: Supported
+F: backends/iommufd.c
+F: include/sysemu/iommufd.h
+
vhost
M: Michael S. Tsirkin <mst@redhat.com>
S: Supported
diff --git a/backends/Kconfig b/backends/Kconfig
index f35abc1609..2cb23f62fa 100644
--- a/backends/Kconfig
+++ b/backends/Kconfig
@@ -1 +1,5 @@
source tpm/Kconfig
+
+config IOMMUFD
+ bool
+ depends on VFIO
diff --git a/backends/iommufd.c b/backends/iommufd.c
new file mode 100644
index 0000000000..ba58a0eb0d
--- /dev/null
+++ b/backends/iommufd.c
@@ -0,0 +1,245 @@
+/*
+ * iommufd container backend
+ *
+ * Copyright (C) 2023 Intel Corporation.
+ * Copyright Red Hat, Inc. 2023
+ *
+ * Authors: Yi Liu <yi.l.liu@intel.com>
+ * Eric Auger <eric.auger@redhat.com>
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#include "qemu/osdep.h"
+#include "sysemu/iommufd.h"
+#include "qapi/error.h"
+#include "qapi/qmp/qerror.h"
+#include "qemu/module.h"
+#include "qom/object_interfaces.h"
+#include "qemu/error-report.h"
+#include "monitor/monitor.h"
+#include "trace.h"
+#include <sys/ioctl.h>
+#include <linux/iommufd.h>
+
+static void iommufd_backend_init(Object *obj)
+{
+ IOMMUFDBackend *be = IOMMUFD_BACKEND(obj);
+
+ be->fd = -1;
+ be->users = 0;
+ be->owned = true;
+ qemu_mutex_init(&be->lock);
+}
+
+static void iommufd_backend_finalize(Object *obj)
+{
+ IOMMUFDBackend *be = IOMMUFD_BACKEND(obj);
+
+ if (be->owned) {
+ close(be->fd);
+ be->fd = -1;
+ }
+}
+
+static void iommufd_backend_set_fd(Object *obj, const char *str, Error **errp)
+{
+ IOMMUFDBackend *be = IOMMUFD_BACKEND(obj);
+ int fd = -1;
+
+ fd = monitor_fd_param(monitor_cur(), str, errp);
+ if (fd == -1) {
+ error_prepend(errp, "Could not parse remote object fd %s:", str);
+ return;
+ }
+ qemu_mutex_lock(&be->lock);
+ be->fd = fd;
+ be->owned = false;
+ qemu_mutex_unlock(&be->lock);
+ trace_iommu_backend_set_fd(be->fd);
+}
+
+static bool iommufd_backend_can_be_deleted(UserCreatable *uc)
+{
+ IOMMUFDBackend *be = IOMMUFD_BACKEND(uc);
+
+ return !be->users;
+}
+
+static void iommufd_backend_class_init(ObjectClass *oc, void *data)
+{
+ UserCreatableClass *ucc = USER_CREATABLE_CLASS(oc);
+
+ ucc->can_be_deleted = iommufd_backend_can_be_deleted;
+
+ object_class_property_add_str(oc, "fd", NULL, iommufd_backend_set_fd);
+}
+
+int iommufd_backend_connect(IOMMUFDBackend *be, Error **errp)
+{
+ int fd, ret = 0;
+
+ qemu_mutex_lock(&be->lock);
+ if (be->users == UINT32_MAX) {
+ error_setg(errp, "too many connections");
+ ret = -E2BIG;
+ goto out;
+ }
+ if (be->owned && !be->users) {
+ fd = qemu_open_old("/dev/iommu", O_RDWR);
+ if (fd < 0) {
+ error_setg_errno(errp, errno, "/dev/iommu opening failed");
+ ret = fd;
+ goto out;
+ }
+ be->fd = fd;
+ }
+ be->users++;
+out:
+ trace_iommufd_backend_connect(be->fd, be->owned,
+ be->users, ret);
+ qemu_mutex_unlock(&be->lock);
+ return ret;
+}
+
+void iommufd_backend_disconnect(IOMMUFDBackend *be)
+{
+ qemu_mutex_lock(&be->lock);
+ if (!be->users) {
+ goto out;
+ }
+ be->users--;
+ if (!be->users && be->owned) {
+ close(be->fd);
+ be->fd = -1;
+ }
+out:
+ trace_iommufd_backend_disconnect(be->fd, be->users);
+ qemu_mutex_unlock(&be->lock);
+}
+
+int iommufd_backend_alloc_ioas(IOMMUFDBackend *be, uint32_t *ioas_id,
+ Error **errp)
+{
+ int ret, fd = be->fd;
+ struct iommu_ioas_alloc alloc_data = {
+ .size = sizeof(alloc_data),
+ .flags = 0,
+ };
+
+ ret = ioctl(fd, IOMMU_IOAS_ALLOC, &alloc_data);
+ if (ret) {
+ error_setg_errno(errp, errno, "Failed to allocate ioas");
+ return ret;
+ }
+
+ *ioas_id = alloc_data.out_ioas_id;
+ trace_iommufd_backend_alloc_ioas(fd, *ioas_id, ret);
+
+ return ret;
+}
+
+void iommufd_backend_free_id(IOMMUFDBackend *be, uint32_t id)
+{
+ int ret, fd = be->fd;
+ struct iommu_destroy des = {
+ .size = sizeof(des),
+ .id = id,
+ };
+
+ ret = ioctl(fd, IOMMU_DESTROY, &des);
+ trace_iommufd_backend_free_id(fd, id, ret);
+ if (ret) {
+ error_report("Failed to free id: %u %m", id);
+ }
+}
+
+int iommufd_backend_map_dma(IOMMUFDBackend *be, uint32_t ioas_id, hwaddr iova,
+ ram_addr_t size, void *vaddr, bool readonly)
+{
+ int ret, fd = be->fd;
+ struct iommu_ioas_map map = {
+ .size = sizeof(map),
+ .flags = IOMMU_IOAS_MAP_READABLE |
+ IOMMU_IOAS_MAP_FIXED_IOVA,
+ .ioas_id = ioas_id,
+ .__reserved = 0,
+ .user_va = (uintptr_t)vaddr,
+ .iova = iova,
+ .length = size,
+ };
+
+ if (!readonly) {
+ map.flags |= IOMMU_IOAS_MAP_WRITEABLE;
+ }
+
+ ret = ioctl(fd, IOMMU_IOAS_MAP, &map);
+ trace_iommufd_backend_map_dma(fd, ioas_id, iova, size,
+ vaddr, readonly, ret);
+ if (ret) {
+ ret = -errno;
+
+ /* TODO: Not support mapping hardware PCI BAR region for now. */
+ if (errno == EFAULT) {
+ warn_report("IOMMU_IOAS_MAP failed: %m, PCI BAR?");
+ } else {
+ error_report("IOMMU_IOAS_MAP failed: %m");
+ }
+ }
+ return ret;
+}
+
+int iommufd_backend_unmap_dma(IOMMUFDBackend *be, uint32_t ioas_id,
+ hwaddr iova, ram_addr_t size)
+{
+ int ret, fd = be->fd;
+ struct iommu_ioas_unmap unmap = {
+ .size = sizeof(unmap),
+ .ioas_id = ioas_id,
+ .iova = iova,
+ .length = size,
+ };
+
+ ret = ioctl(fd, IOMMU_IOAS_UNMAP, &unmap);
+ /*
+ * IOMMUFD takes mapping as some kind of object, unmapping
+ * nonexistent mapping is treated as deleting a nonexistent
+ * object and return ENOENT. This is different from legacy
+ * backend which allows it. vIOMMU may trigger a lot of
+ * redundant unmapping, to avoid flush the log, treat them
+ * as succeess for IOMMUFD just like legacy backend.
+ */
+ if (ret && errno == ENOENT) {
+ trace_iommufd_backend_unmap_dma_non_exist(fd, ioas_id, iova, size, ret);
+ ret = 0;
+ } else {
+ trace_iommufd_backend_unmap_dma(fd, ioas_id, iova, size, ret);
+ }
+
+ if (ret) {
+ ret = -errno;
+ error_report("IOMMU_IOAS_UNMAP failed: %m");
+ }
+ return ret;
+}
+
+static const TypeInfo iommufd_backend_info = {
+ .name = TYPE_IOMMUFD_BACKEND,
+ .parent = TYPE_OBJECT,
+ .instance_size = sizeof(IOMMUFDBackend),
+ .instance_init = iommufd_backend_init,
+ .instance_finalize = iommufd_backend_finalize,
+ .class_size = sizeof(IOMMUFDBackendClass),
+ .class_init = iommufd_backend_class_init,
+ .interfaces = (InterfaceInfo[]) {
+ { TYPE_USER_CREATABLE },
+ { }
+ }
+};
+
+static void register_types(void)
+{
+ type_register_static(&iommufd_backend_info);
+}
+
+type_init(register_types);
diff --git a/backends/meson.build b/backends/meson.build
index 914c7c4afb..9a5cea480d 100644
--- a/backends/meson.build
+++ b/backends/meson.build
@@ -20,6 +20,7 @@ if have_vhost_user
system_ss.add(when: 'CONFIG_VIRTIO', if_true: files('vhost-user.c'))
endif
system_ss.add(when: 'CONFIG_VIRTIO_CRYPTO', if_true: files('cryptodev-vhost.c'))
+system_ss.add(when: 'CONFIG_IOMMUFD', if_true: files('iommufd.c'))
if have_vhost_user_crypto
system_ss.add(when: 'CONFIG_VIRTIO_CRYPTO', if_true: files('cryptodev-vhost-user.c'))
endif
diff --git a/backends/trace-events b/backends/trace-events
index 652eb76a57..d45c6e31a6 100644
--- a/backends/trace-events
+++ b/backends/trace-events
@@ -5,3 +5,13 @@ dbus_vmstate_pre_save(void)
dbus_vmstate_post_load(int version_id) "version_id: %d"
dbus_vmstate_loading(const char *id) "id: %s"
dbus_vmstate_saving(const char *id) "id: %s"
+
+# iommufd.c
+iommufd_backend_connect(int fd, bool owned, uint32_t users, int ret) "fd=%d owned=%d users=%d (%d)"
+iommufd_backend_disconnect(int fd, uint32_t users) "fd=%d users=%d"
+iommu_backend_set_fd(int fd) "pre-opened /dev/iommu fd=%d"
+iommufd_backend_map_dma(int iommufd, uint32_t ioas, uint64_t iova, uint64_t size, void *vaddr, bool readonly, int ret) " iommufd=%d ioas=%d iova=0x%"PRIx64" size=0x%"PRIx64" addr=%p readonly=%d (%d)"
+iommufd_backend_unmap_dma_non_exist(int iommufd, uint32_t ioas, uint64_t iova, uint64_t size, int ret) " Unmap nonexistent mapping: iommufd=%d ioas=%d iova=0x%"PRIx64" size=0x%"PRIx64" (%d)"
+iommufd_backend_unmap_dma(int iommufd, uint32_t ioas, uint64_t iova, uint64_t size, int ret) " iommufd=%d ioas=%d iova=0x%"PRIx64" size=0x%"PRIx64" (%d)"
+iommufd_backend_alloc_ioas(int iommufd, uint32_t ioas, int ret) " iommufd=%d ioas=%d (%d)"
+iommufd_backend_free_id(int iommufd, uint32_t id, int ret) " iommufd=%d id=%d (%d)"
diff --git a/include/sysemu/iommufd.h b/include/sysemu/iommufd.h
new file mode 100644
index 0000000000..9c5524b0ed
--- /dev/null
+++ b/include/sysemu/iommufd.h
@@ -0,0 +1,38 @@
+#ifndef SYSEMU_IOMMUFD_H
+#define SYSEMU_IOMMUFD_H
+
+#include "qom/object.h"
+#include "qemu/thread.h"
+#include "exec/hwaddr.h"
+#include "exec/cpu-common.h"
+
+#define TYPE_IOMMUFD_BACKEND "iommufd"
+OBJECT_DECLARE_TYPE(IOMMUFDBackend, IOMMUFDBackendClass, IOMMUFD_BACKEND)
+
+struct IOMMUFDBackendClass {
+ ObjectClass parent_class;
+};
+
+struct IOMMUFDBackend {
+ Object parent;
+
+ /*< protected >*/
+ int fd; /* /dev/iommu file descriptor */
+ bool owned; /* is the /dev/iommu opened internally */
+ QemuMutex lock;
+ uint32_t users;
+
+ /*< public >*/
+};
+
+int iommufd_backend_connect(IOMMUFDBackend *be, Error **errp);
+void iommufd_backend_disconnect(IOMMUFDBackend *be);
+
+int iommufd_backend_alloc_ioas(IOMMUFDBackend *be, uint32_t *ioas_id,
+ Error **errp);
+void iommufd_backend_free_id(IOMMUFDBackend *be, uint32_t id);
+int iommufd_backend_map_dma(IOMMUFDBackend *be, uint32_t ioas_id, hwaddr iova,
+ ram_addr_t size, void *vaddr, bool readonly);
+int iommufd_backend_unmap_dma(IOMMUFDBackend *be, uint32_t ioas_id,
+ hwaddr iova, ram_addr_t size);
+#endif
diff --git a/qapi/qom.json b/qapi/qom.json
index c53ef978ff..95516ba325 100644
--- a/qapi/qom.json
+++ b/qapi/qom.json
@@ -794,6 +794,23 @@
{ 'struct': 'VfioUserServerProperties',
'data': { 'socket': 'SocketAddress', 'device': 'str' } }
+##
+# @IOMMUFDProperties:
+#
+# Properties for iommufd objects.
+#
+# @fd: file descriptor name previously passed via 'getfd' command,
+# which represents a pre-opened /dev/iommu. This allows the
+# iommufd object to be shared accross several subsystems
+# (VFIO, VDPA, ...), and the file descriptor to be shared
+# with other process, e.g. DPDK. (default: QEMU opens
+# /dev/iommu by itself)
+#
+# Since: 9.0
+##
+{ 'struct': 'IOMMUFDProperties',
+ 'data': { '*fd': 'str' } }
+
##
# @RngProperties:
#
@@ -934,6 +951,7 @@
'input-barrier',
{ 'name': 'input-linux',
'if': 'CONFIG_LINUX' },
+ 'iommufd',
'iothread',
'main-loop',
{ 'name': 'memory-backend-epc',
@@ -1003,6 +1021,7 @@
'input-barrier': 'InputBarrierProperties',
'input-linux': { 'type': 'InputLinuxProperties',
'if': 'CONFIG_LINUX' },
+ 'iommufd': 'IOMMUFDProperties',
'iothread': 'IothreadProperties',
'main-loop': 'MainLoopProperties',
'memory-backend-epc': { 'type': 'MemoryBackendEpcProperties',
diff --git a/qemu-options.hx b/qemu-options.hx
index 557118cb1f..0814f43066 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -5224,6 +5224,18 @@ SRST
The ``share`` boolean option is on by default with memfd.
+ ``-object iommufd,id=id[,fd=fd]``
+ Creates an iommufd backend which allows control of DMA mapping
+ through the ``/dev/iommu`` device.
+
+ The ``id`` parameter is a unique ID which frontends (such as
+ vfio-pci of vdpa) will use to connect with the iommufd backend.
+
+ The ``fd`` parameter is an optional pre-opened file descriptor
+ resulting from ``/dev/iommu`` opening. Usually the iommufd is shared
+ across all subsystems, bringing the benefit of centralized
+ reference counting.
+
``-object rng-builtin,id=id``
Creates a random number generator backend which obtains entropy
from QEMU builtin functions. The ``id`` parameter is a unique ID
--
2.39.3

47
kvm-backends-iommufd-Remove-check-on-number-of-backend-u.patch
View File

@ -1,47 +0,0 @@
From da9a24793e876f6f2727d57f939d882be26a47b8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= <clg@redhat.com>
Date: Fri, 22 Dec 2023 08:55:23 +0100
Subject: [PATCH 064/101] backends/iommufd: Remove check on number of backend
users
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 211: IOMMUFD backend backport
RH-Jira: RHEL-19302 RHEL-21057
RH-Acked-by: Cédric Le Goater <clg@redhat.com>
RH-Acked-by: Sebastian Ott <sebott@redhat.com>
RH-Commit: [63/67] ac4d4589d1f2de5ac3f0adfd8d1f27dbf6bbfdee (eauger1/centos-qemu-kvm)
QOM already has a ref count on objects and it will assert much
earlier, when INT_MAX is reached.
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Signed-off-by: Cédric Le Goater <clg@redhat.com>
(cherry picked from commit c2ab3a6f7411c895e538e8350fee8948ac07c1a0)
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
backends/iommufd.c | 5 -----
1 file changed, 5 deletions(-)
diff --git a/backends/iommufd.c b/backends/iommufd.c
index ba58a0eb0d..393c0d9a37 100644
--- a/backends/iommufd.c
+++ b/backends/iommufd.c
@@ -80,11 +80,6 @@ int iommufd_backend_connect(IOMMUFDBackend *be, Error **errp)
int fd, ret = 0;
qemu_mutex_lock(&be->lock);
- if (be->users == UINT32_MAX) {
- error_setg(errp, "too many connections");
- ret = -E2BIG;
- goto out;
- }
if (be->owned && !be->users) {
fd = qemu_open_old("/dev/iommu", O_RDWR);
if (fd < 0) {
--
2.39.3

112
kvm-backends-iommufd-Remove-mutex.patch
View File

@ -1,112 +0,0 @@
From 92aff3cc1a412de01e9563802fa48848eae5283f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= <clg@redhat.com>
Date: Thu, 21 Dec 2023 16:58:41 +0100
Subject: [PATCH 065/101] backends/iommufd: Remove mutex
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 211: IOMMUFD backend backport
RH-Jira: RHEL-19302 RHEL-21057
RH-Acked-by: Cédric Le Goater <clg@redhat.com>
RH-Acked-by: Sebastian Ott <sebott@redhat.com>
RH-Commit: [64/67] 65518432b18f18ceadafe1b0698cdaa962e84f61 (eauger1/centos-qemu-kvm)
Coverity reports a concurrent data access violation because be->users
is being accessed in iommufd_backend_can_be_deleted() without holding
the mutex.
However, these routines are called from the QEMU main thread when a
device is created. In this case, the code paths should be protected by
the BQL lock and it should be safe to drop the IOMMUFD backend mutex.
Simply remove it.
Fixes: CID 1531550
Fixes: CID 1531549
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Signed-off-by: Cédric Le Goater <clg@redhat.com>
(cherry picked from commit 19368b1905b4b917e915526fcbd5bfa3f7439451)
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
backends/iommufd.c | 7 -------
include/sysemu/iommufd.h | 2 --
2 files changed, 9 deletions(-)
diff --git a/backends/iommufd.c b/backends/iommufd.c
index 393c0d9a37..1ef683c7b0 100644
--- a/backends/iommufd.c
+++ b/backends/iommufd.c
@@ -29,7 +29,6 @@ static void iommufd_backend_init(Object *obj)
be->fd = -1;
be->users = 0;
be->owned = true;
- qemu_mutex_init(&be->lock);
}
static void iommufd_backend_finalize(Object *obj)
@@ -52,10 +51,8 @@ static void iommufd_backend_set_fd(Object *obj, const char *str, Error **errp)
error_prepend(errp, "Could not parse remote object fd %s:", str);
return;
}
- qemu_mutex_lock(&be->lock);
be->fd = fd;
be->owned = false;
- qemu_mutex_unlock(&be->lock);
trace_iommu_backend_set_fd(be->fd);
}
@@ -79,7 +76,6 @@ int iommufd_backend_connect(IOMMUFDBackend *be, Error **errp)
{
int fd, ret = 0;
- qemu_mutex_lock(&be->lock);
if (be->owned && !be->users) {
fd = qemu_open_old("/dev/iommu", O_RDWR);
if (fd < 0) {
@@ -93,13 +89,11 @@ int iommufd_backend_connect(IOMMUFDBackend *be, Error **errp)
out:
trace_iommufd_backend_connect(be->fd, be->owned,
be->users, ret);
- qemu_mutex_unlock(&be->lock);
return ret;
}
void iommufd_backend_disconnect(IOMMUFDBackend *be)
{
- qemu_mutex_lock(&be->lock);
if (!be->users) {
goto out;
}
@@ -110,7 +104,6 @@ void iommufd_backend_disconnect(IOMMUFDBackend *be)
}
out:
trace_iommufd_backend_disconnect(be->fd, be->users);
- qemu_mutex_unlock(&be->lock);
}
int iommufd_backend_alloc_ioas(IOMMUFDBackend *be, uint32_t *ioas_id,
diff --git a/include/sysemu/iommufd.h b/include/sysemu/iommufd.h
index 9c5524b0ed..9af27ebd6c 100644
--- a/include/sysemu/iommufd.h
+++ b/include/sysemu/iommufd.h
@@ -2,7 +2,6 @@
#define SYSEMU_IOMMUFD_H
#include "qom/object.h"
-#include "qemu/thread.h"
#include "exec/hwaddr.h"
#include "exec/cpu-common.h"
@@ -19,7 +18,6 @@ struct IOMMUFDBackend {
/*< protected >*/
int fd; /* /dev/iommu file descriptor */
bool owned; /* is the /dev/iommu opened internally */
- QemuMutex lock;
uint32_t users;
/*< public >*/
--
2.39.3

104
kvm-block-backend-Allow-concurrent-context-changes.patch
View File

@ -1,104 +0,0 @@
From afa842e9fdf6e1d6e5d5785679a22779632142bd Mon Sep 17 00:00:00 2001
From: Hanna Czenczek <hreitz@redhat.com>
Date: Fri, 2 Feb 2024 15:47:54 +0100
Subject: [PATCH 03/22] block-backend: Allow concurrent context changes
RH-Author: Hanna Czenczek <hreitz@redhat.com>
RH-MergeRequest: 222: Allow concurrent BlockBackend context changes
RH-Jira: RHEL-24593
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [1/2] 9e1b535f60f7afa94a0817dc3e71136e41631c71 (hreitz/qemu-kvm-c-9-s)
Since AioContext locks have been removed, a BlockBackend's AioContext
may really change at any time (only exception is that it is often
confined to a drained section, as noted in this patch). Therefore,
blk_get_aio_context() cannot rely on its root node's context always
matching that of the BlockBackend.
In practice, whether they match does not matter anymore anyway: Requests
can be sent to BDSs from any context, so anyone who requests the BB's
context should have no reason to require the root node to have the same
context. Therefore, we can and should remove the assertion to that
effect.
In addition, because the context can be set and queried from different
threads concurrently, it has to be accessed with atomic operations.
Buglink: https://issues.redhat.com/browse/RHEL-19381
Suggested-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
Message-ID: <20240202144755.671354-2-hreitz@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit ad893672027ffe26db498947d70cde6d4f58a111)
---
block/block-backend.c | 22 +++++++++++-----------
1 file changed, 11 insertions(+), 11 deletions(-)
diff --git a/block/block-backend.c b/block/block-backend.c
index 209eb07528..9c4de79e6b 100644
--- a/block/block-backend.c
+++ b/block/block-backend.c
@@ -44,7 +44,7 @@ struct BlockBackend {
char *name;
int refcnt;
BdrvChild *root;
- AioContext *ctx;
+ AioContext *ctx; /* access with atomic operations only */
DriveInfo *legacy_dinfo; /* null unless created by drive_new() */
QTAILQ_ENTRY(BlockBackend) link; /* for block_backends */
QTAILQ_ENTRY(BlockBackend) monitor_link; /* for monitor_block_backends */
@@ -2414,22 +2414,22 @@ void blk_op_unblock_all(BlockBackend *blk, Error *reason)
}
}
+/**
+ * Return BB's current AioContext. Note that this context may change
+ * concurrently at any time, with one exception: If the BB has a root node
+ * attached, its context will only change through bdrv_try_change_aio_context(),
+ * which creates a drained section. Therefore, incrementing such a BB's
+ * in-flight counter will prevent its context from changing.
+ */
AioContext *blk_get_aio_context(BlockBackend *blk)
{
- BlockDriverState *bs;
IO_CODE();
if (!blk) {
return qemu_get_aio_context();
}
- bs = blk_bs(blk);
- if (bs) {
- AioContext *ctx = bdrv_get_aio_context(blk_bs(blk));
- assert(ctx == blk->ctx);
- }
-
- return blk->ctx;
+ return qatomic_read(&blk->ctx);
}
int blk_set_aio_context(BlockBackend *blk, AioContext *new_context,
@@ -2442,7 +2442,7 @@ int blk_set_aio_context(BlockBackend *blk, AioContext *new_context,
GLOBAL_STATE_CODE();
if (!bs) {
- blk->ctx = new_context;
+ qatomic_set(&blk->ctx, new_context);
return 0;
}
@@ -2471,7 +2471,7 @@ static void blk_root_set_aio_ctx_commit(void *opaque)
AioContext *new_context = s->new_ctx;
ThrottleGroupMember *tgm = &blk->public.throttle_group_member;
- blk->ctx = new_context;
+ qatomic_set(&blk->ctx, new_context);
if (tgm->throttle_state) {
throttle_group_detach_aio_context(tgm);
throttle_group_attach_aio_context(tgm, new_context);
--
2.39.3

69
kvm-block-coroutine-wrapper-use-qemu_get_current_aio_con.patch
View File

@ -1,69 +0,0 @@
From b1a68aebadecd7d339cf5eaffeda15099c998528 Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Tue, 12 Sep 2023 19:10:37 -0400
Subject: [PATCH 095/101] block-coroutine-wrapper: use
qemu_get_current_aio_context()
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 214: Remove AioContext lock
RH-Jira: RHEL-15965
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Commit: [26/26] cde767bcdc626e90721792e3889952057a548ac5 (kmwolf/centos-qemu-kvm)
Use qemu_get_current_aio_context() in mixed wrappers and coroutine
wrappers so that code runs in the caller's AioContext instead of moving
to the BlockDriverState's AioContext. This change is necessary for the
multi-queue block layer where any thread can call into the block layer.
Most wrappers are IO_CODE where it's safe to use the current AioContext
nowadays. BlockDrivers and the core block layer use their own locks and
no longer depend on the AioContext lock for thread-safety.
The bdrv_create() wrapper invokes GLOBAL_STATE code. Using the current
AioContext is safe because this code is only called with the BQL held
from the main loop thread.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-ID: <20230912231037.826804-6-stefanha@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
scripts/block-coroutine-wrapper.py | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/scripts/block-coroutine-wrapper.py b/scripts/block-coroutine-wrapper.py
index c9c09fcacd..dbbde99e39 100644
--- a/scripts/block-coroutine-wrapper.py
+++ b/scripts/block-coroutine-wrapper.py
@@ -92,8 +92,6 @@ def __init__(self, wrapper_type: str, return_type: str, name: str,
f"{self.name}")
self.target_name = f'{subsystem}_{subname}'
- self.ctx = self.gen_ctx()
-
self.get_result = 's->ret = '
self.ret = 'return s.ret;'
self.co_ret = 'return '
@@ -167,7 +165,7 @@ def create_mixed_wrapper(func: FuncDecl) -> str:
{func.co_ret}{name}({ func.gen_list('{name}') });
}} else {{
{struct_name} s = {{
- .poll_state.ctx = {func.ctx},
+ .poll_state.ctx = qemu_get_current_aio_context(),
.poll_state.in_progress = true,
{ func.gen_block(' .{name} = {name},') }
@@ -191,7 +189,7 @@ def create_co_wrapper(func: FuncDecl) -> str:
{func.return_type} {func.name}({ func.gen_list('{decl}') })
{{
{struct_name} s = {{
- .poll_state.ctx = {func.ctx},
+ .poll_state.ctx = qemu_get_current_aio_context(),
.poll_state.in_progress = true,
{ func.gen_block(' .{name} = {name},') }
--
2.39.3

217
kvm-block-file-posix-set-up-Linux-AIO-and-io_uring-in-th.patch
View File

@ -1,217 +0,0 @@
From 25cce5df341861e8ba8ec57722558e2dee3ce56a Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Thu, 14 Sep 2023 10:00:58 -0400
Subject: [PATCH 073/101] block/file-posix: set up Linux AIO and io_uring in
the current thread
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 214: Remove AioContext lock
RH-Jira: RHEL-15965
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Commit: [4/26] 74c7daf805daefe706378308c3afeb28d861164b (kmwolf/centos-qemu-kvm)
The file-posix block driver currently only sets up Linux AIO and
io_uring in the BDS's AioContext. In the multi-queue block layer we must
be able to submit I/O requests in AioContexts that do not have Linux AIO
and io_uring set up yet since any thread can call into the block driver.
Set up Linux AIO and io_uring for the current AioContext during request
submission. We lose the ability to return an error from
.bdrv_file_open() when Linux AIO and io_uring setup fails (e.g. due to
resource limits). Instead the user only gets warnings and we fall back
to aio=threads. This is still better than a fatal error after startup.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-ID: <20230914140101.1065008-2-stefanha@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
block/file-posix.c | 103 ++++++++++++++++++++++-----------------------
1 file changed, 51 insertions(+), 52 deletions(-)
diff --git a/block/file-posix.c b/block/file-posix.c
index b862406c71..35684f7e21 100644
--- a/block/file-posix.c
+++ b/block/file-posix.c
@@ -712,17 +712,11 @@ static int raw_open_common(BlockDriverState *bs, QDict *options,
#ifdef CONFIG_LINUX_AIO
/* Currently Linux does AIO only for files opened with O_DIRECT */
- if (s->use_linux_aio) {
- if (!(s->open_flags & O_DIRECT)) {
- error_setg(errp, "aio=native was specified, but it requires "
- "cache.direct=on, which was not specified.");
- ret = -EINVAL;
- goto fail;
- }
- if (!aio_setup_linux_aio(bdrv_get_aio_context(bs), errp)) {
- error_prepend(errp, "Unable to use native AIO: ");
- goto fail;
- }
+ if (s->use_linux_aio && !(s->open_flags & O_DIRECT)) {
+ error_setg(errp, "aio=native was specified, but it requires "
+ "cache.direct=on, which was not specified.");
+ ret = -EINVAL;
+ goto fail;
}
#else
if (s->use_linux_aio) {
@@ -733,14 +727,7 @@ static int raw_open_common(BlockDriverState *bs, QDict *options,
}
#endif /* !defined(CONFIG_LINUX_AIO) */
-#ifdef CONFIG_LINUX_IO_URING
- if (s->use_linux_io_uring) {
- if (!aio_setup_linux_io_uring(bdrv_get_aio_context(bs), errp)) {
- error_prepend(errp, "Unable to use io_uring: ");
- goto fail;
- }
- }
-#else
+#ifndef CONFIG_LINUX_IO_URING
if (s->use_linux_io_uring) {
error_setg(errp, "aio=io_uring was specified, but is not supported "
"in this build.");
@@ -2444,6 +2431,48 @@ static bool bdrv_qiov_is_aligned(BlockDriverState *bs, QEMUIOVector *qiov)
return true;
}
+#ifdef CONFIG_LINUX_IO_URING
+static inline bool raw_check_linux_io_uring(BDRVRawState *s)
+{
+ Error *local_err = NULL;
+ AioContext *ctx;
+
+ if (!s->use_linux_io_uring) {
+ return false;
+ }
+
+ ctx = qemu_get_current_aio_context();
+ if (unlikely(!aio_setup_linux_io_uring(ctx, &local_err))) {
+ error_reportf_err(local_err, "Unable to use linux io_uring, "
+ "falling back to thread pool: ");
+ s->use_linux_io_uring = false;
+ return false;
+ }
+ return true;
+}
+#endif
+
+#ifdef CONFIG_LINUX_AIO
+static inline bool raw_check_linux_aio(BDRVRawState *s)
+{
+ Error *local_err = NULL;
+ AioContext *ctx;
+
+ if (!s->use_linux_aio) {
+ return false;
+ }
+
+ ctx = qemu_get_current_aio_context();
+ if (unlikely(!aio_setup_linux_aio(ctx, &local_err))) {
+ error_reportf_err(local_err, "Unable to use Linux AIO, "
+ "falling back to thread pool: ");
+ s->use_linux_aio = false;
+ return false;
+ }
+ return true;
+}
+#endif
+
static int coroutine_fn raw_co_prw(BlockDriverState *bs, int64_t *offset_ptr,
uint64_t bytes, QEMUIOVector *qiov, int type)
{
@@ -2474,13 +2503,13 @@ static int coroutine_fn raw_co_prw(BlockDriverState *bs, int64_t *offset_ptr,
if (s->needs_alignment && !bdrv_qiov_is_aligned(bs, qiov)) {
type |= QEMU_AIO_MISALIGNED;
#ifdef CONFIG_LINUX_IO_URING
- } else if (s->use_linux_io_uring) {
+ } else if (raw_check_linux_io_uring(s)) {
assert(qiov->size == bytes);
ret = luring_co_submit(bs, s->fd, offset, qiov, type);
goto out;
#endif
#ifdef CONFIG_LINUX_AIO
- } else if (s->use_linux_aio) {
+ } else if (raw_check_linux_aio(s)) {
assert(qiov->size == bytes);
ret = laio_co_submit(s->fd, offset, qiov, type,
s->aio_max_batch);
@@ -2567,39 +2596,13 @@ static int coroutine_fn raw_co_flush_to_disk(BlockDriverState *bs)
};
#ifdef CONFIG_LINUX_IO_URING
- if (s->use_linux_io_uring) {
+ if (raw_check_linux_io_uring(s)) {
return luring_co_submit(bs, s->fd, 0, NULL, QEMU_AIO_FLUSH);
}
#endif
return raw_thread_pool_submit(handle_aiocb_flush, &acb);
}
-static void raw_aio_attach_aio_context(BlockDriverState *bs,
- AioContext *new_context)
-{
- BDRVRawState __attribute__((unused)) *s = bs->opaque;
-#ifdef CONFIG_LINUX_AIO
- if (s->use_linux_aio) {
- Error *local_err = NULL;
- if (!aio_setup_linux_aio(new_context, &local_err)) {
- error_reportf_err(local_err, "Unable to use native AIO, "
- "falling back to thread pool: ");
- s->use_linux_aio = false;
- }
- }
-#endif
-#ifdef CONFIG_LINUX_IO_URING
- if (s->use_linux_io_uring) {
- Error *local_err = NULL;
- if (!aio_setup_linux_io_uring(new_context, &local_err)) {
- error_reportf_err(local_err, "Unable to use linux io_uring, "
- "falling back to thread pool: ");
- s->use_linux_io_uring = false;
- }
- }
-#endif
-}
-
static void raw_close(BlockDriverState *bs)
{
BDRVRawState *s = bs->opaque;
@@ -3896,7 +3899,6 @@ BlockDriver bdrv_file = {
.bdrv_co_copy_range_from = raw_co_copy_range_from,
.bdrv_co_copy_range_to = raw_co_copy_range_to,
.bdrv_refresh_limits = raw_refresh_limits,
- .bdrv_attach_aio_context = raw_aio_attach_aio_context,
.bdrv_co_truncate = raw_co_truncate,
.bdrv_co_getlength = raw_co_getlength,
@@ -4266,7 +4268,6 @@ static BlockDriver bdrv_host_device = {
.bdrv_co_copy_range_from = raw_co_copy_range_from,
.bdrv_co_copy_range_to = raw_co_copy_range_to,
.bdrv_refresh_limits = raw_refresh_limits,
- .bdrv_attach_aio_context = raw_aio_attach_aio_context,
.bdrv_co_truncate = raw_co_truncate,
.bdrv_co_getlength = raw_co_getlength,
@@ -4402,7 +4403,6 @@ static BlockDriver bdrv_host_cdrom = {
.bdrv_co_pwritev = raw_co_pwritev,
.bdrv_co_flush_to_disk = raw_co_flush_to_disk,
.bdrv_refresh_limits = cdrom_refresh_limits,
- .bdrv_attach_aio_context = raw_aio_attach_aio_context,
.bdrv_co_truncate = raw_co_truncate,
.bdrv_co_getlength = raw_co_getlength,
@@ -4528,7 +4528,6 @@ static BlockDriver bdrv_host_cdrom = {
.bdrv_co_pwritev = raw_co_pwritev,
.bdrv_co_flush_to_disk = raw_co_flush_to_disk,
.bdrv_refresh_limits = cdrom_refresh_limits,
- .bdrv_attach_aio_context = raw_aio_attach_aio_context,
.bdrv_co_truncate = raw_co_truncate,
.bdrv_co_getlength = raw_co_getlength,
--
2.39.3

4438
kvm-block-remove-AioContext-locking.patch
View File

File diff suppressed because it is too large Load Diff

97
kvm-block-remove-bdrv_co_lock.patch
View File

@ -1,97 +0,0 @@
From d0514c7d5d6cc1aa140119c95d5ea2c1591b01e9 Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Tue, 5 Dec 2023 13:20:04 -0500
Subject: [PATCH 087/101] block: remove bdrv_co_lock()
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 214: Remove AioContext lock
RH-Jira: RHEL-15965
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Commit: [18/26] a303f861ea5e84d8e89fd51e530fd0cb2da17b89 (kmwolf/centos-qemu-kvm)
The bdrv_co_lock() and bdrv_co_unlock() functions are already no-ops.
Remove them.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-ID: <20231205182011.1976568-8-stefanha@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
block.c | 10 ----------
blockdev.c | 5 -----
include/block/block-global-state.h | 14 --------------
3 files changed, 29 deletions(-)
diff --git a/block.c b/block.c
index 91ace5d2d5..434b7f4d72 100644
--- a/block.c
+++ b/block.c
@@ -7431,16 +7431,6 @@ void coroutine_fn bdrv_co_leave(BlockDriverState *bs, AioContext *old_ctx)
bdrv_dec_in_flight(bs);
}
-void coroutine_fn bdrv_co_lock(BlockDriverState *bs)
-{
- /* TODO removed in next patch */
-}
-
-void coroutine_fn bdrv_co_unlock(BlockDriverState *bs)
-{
- /* TODO removed in next patch */
-}
-
static void bdrv_do_remove_aio_context_notifier(BdrvAioNotifier *ban)
{
GLOBAL_STATE_CODE();
diff --git a/blockdev.c b/blockdev.c
index 5d8b3a23eb..3a5e7222ec 100644
--- a/blockdev.c
+++ b/blockdev.c
@@ -2264,18 +2264,13 @@ void coroutine_fn qmp_block_resize(const char *device, const char *node_name,
return;
}
- bdrv_co_lock(bs);
bdrv_drained_begin(bs);
- bdrv_co_unlock(bs);
old_ctx = bdrv_co_enter(bs);
blk_co_truncate(blk, size, false, PREALLOC_MODE_OFF, 0, errp);
bdrv_co_leave(bs, old_ctx);
- bdrv_co_lock(bs);
bdrv_drained_end(bs);
- bdrv_co_unlock(bs);
-
blk_co_unref(blk);
}
diff --git a/include/block/block-global-state.h b/include/block/block-global-state.h
index 0327f1c605..4ec0b217f0 100644
--- a/include/block/block-global-state.h
+++ b/include/block/block-global-state.h
@@ -267,20 +267,6 @@ int bdrv_debug_remove_breakpoint(BlockDriverState *bs, const char *tag);
int bdrv_debug_resume(BlockDriverState *bs, const char *tag);
bool bdrv_debug_is_suspended(BlockDriverState *bs, const char *tag);
-/**
- * Locks the AioContext of @bs if it's not the current AioContext. This avoids
- * double locking which could lead to deadlocks: This is a coroutine_fn, so we
- * know we already own the lock of the current AioContext.
- *
- * May only be called in the main thread.
- */
-void coroutine_fn bdrv_co_lock(BlockDriverState *bs);
-
-/**
- * Unlocks the AioContext of @bs if it's not the current AioContext.
- */
-void coroutine_fn bdrv_co_unlock(BlockDriverState *bs);
-
bool bdrv_child_change_aio_context(BdrvChild *c, AioContext *ctx,
GHashTable *visited, Transaction *tran,
Error **errp);
--
2.39.3

411
kvm-block-remove-outdated-AioContext-locking-comments.patch
View File

@ -1,411 +0,0 @@
From dc4eb64185957a01948217814478abc450ce5f26 Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Tue, 5 Dec 2023 13:20:11 -0500
Subject: [PATCH 094/101] block: remove outdated AioContext locking comments
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 214: Remove AioContext lock
RH-Jira: RHEL-15965
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Commit: [25/26] 395e18fb40d28d4bc961acee1a00da7f60748076 (kmwolf/centos-qemu-kvm)
The AioContext lock no longer exists.
There is one noteworthy change:
- * More specifically, these functions use BDRV_POLL_WHILE(bs), which
- * requires the caller to be either in the main thread and hold
- * the BlockdriverState (bs) AioContext lock, or directly in the
- * home thread that runs the bs AioContext. Calling them from
- * another thread in another AioContext would cause deadlocks.
+ * More specifically, these functions use BDRV_POLL_WHILE(bs), which requires
+ * the caller to be either in the main thread or directly in the home thread
+ * that runs the bs AioContext. Calling them from another thread in another
+ * AioContext would cause deadlocks.
I am not sure whether deadlocks are still possible. Maybe they have just
moved to the fine-grained locks that have replaced the AioContext. Since
I am not sure if the deadlocks are gone, I have kept the substance
unchanged and just removed mention of the AioContext.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-ID: <20231205182011.1976568-15-stefanha@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
block.c | 73 ++++++----------------------
block/block-backend.c | 8 ---
block/export/vhost-user-blk-server.c | 4 --
include/block/block-common.h | 3 --
include/block/block-io.h | 9 ++--
include/block/block_int-common.h | 2 -
tests/qemu-iotests/202 | 2 +-
tests/qemu-iotests/203 | 3 +-
8 files changed, 22 insertions(+), 82 deletions(-)
diff --git a/block.c b/block.c
index 434b7f4d72..a097772238 100644
--- a/block.c
+++ b/block.c
@@ -1616,11 +1616,6 @@ out:
g_free(gen_node_name);
}
-/*
- * The caller must always hold @bs AioContext lock, because this function calls
- * bdrv_refresh_total_sectors() which polls when called from non-coroutine
- * context.
- */
static int no_coroutine_fn GRAPH_UNLOCKED
bdrv_open_driver(BlockDriverState *bs, BlockDriver *drv, const char *node_name,
QDict *options, int open_flags, Error **errp)
@@ -2901,7 +2896,7 @@ uint64_t bdrv_qapi_perm_to_blk_perm(BlockPermission qapi_perm)
* Replaces the node that a BdrvChild points to without updating permissions.
*
* If @new_bs is non-NULL, the parent of @child must already be drained through
- * @child and the caller must hold the AioContext lock for @new_bs.
+ * @child.
*/
static void GRAPH_WRLOCK
bdrv_replace_child_noperm(BdrvChild *child, BlockDriverState *new_bs)
@@ -3041,9 +3036,8 @@ static TransactionActionDrv bdrv_attach_child_common_drv = {
*
* Returns new created child.
*
- * The caller must hold the AioContext lock for @child_bs. Both @parent_bs and
- * @child_bs can move to a different AioContext in this function. Callers must
- * make sure that their AioContext locking is still correct after this.
+ * Both @parent_bs and @child_bs can move to a different AioContext in this
+ * function.
*/
static BdrvChild * GRAPH_WRLOCK
bdrv_attach_child_common(BlockDriverState *child_bs,
@@ -3142,9 +3136,8 @@ bdrv_attach_child_common(BlockDriverState *child_bs,
/*
* Function doesn't update permissions, caller is responsible for this.
*
- * The caller must hold the AioContext lock for @child_bs. Both @parent_bs and
- * @child_bs can move to a different AioContext in this function. Callers must
- * make sure that their AioContext locking is still correct after this.
+ * Both @parent_bs and @child_bs can move to a different AioContext in this
+ * function.
*
* After calling this function, the transaction @tran may only be completed
* while holding a writer lock for the graph.
@@ -3184,9 +3177,6 @@ bdrv_attach_child_noperm(BlockDriverState *parent_bs,
*
* On failure NULL is returned, errp is set and the reference to
* child_bs is also dropped.
- *
- * The caller must hold the AioContext lock @child_bs, but not that of @ctx
- * (unless @child_bs is already in @ctx).
*/
BdrvChild *bdrv_root_attach_child(BlockDriverState *child_bs,
const char *child_name,
@@ -3226,9 +3216,6 @@ out:
*
* On failure NULL is returned, errp is set and the reference to
* child_bs is also dropped.
- *
- * If @parent_bs and @child_bs are in different AioContexts, the caller must
- * hold the AioContext lock for @child_bs, but not for @parent_bs.
*/
BdrvChild *bdrv_attach_child(BlockDriverState *parent_bs,
BlockDriverState *child_bs,
@@ -3418,9 +3405,8 @@ static BdrvChildRole bdrv_backing_role(BlockDriverState *bs)
*
* Function doesn't update permissions, caller is responsible for this.
*
- * The caller must hold the AioContext lock for @child_bs. Both @parent_bs and
- * @child_bs can move to a different AioContext in this function. Callers must
- * make sure that their AioContext locking is still correct after this.
+ * Both @parent_bs and @child_bs can move to a different AioContext in this
+ * function.
*
* After calling this function, the transaction @tran may only be completed
* while holding a writer lock for the graph.
@@ -3513,9 +3499,8 @@ out:
}
/*
- * The caller must hold the AioContext lock for @backing_hd. Both @bs and
- * @backing_hd can move to a different AioContext in this function. Callers must
- * make sure that their AioContext locking is still correct after this.
+ * Both @bs and @backing_hd can move to a different AioContext in this
+ * function.
*
* If a backing child is already present (i.e. we're detaching a node), that
* child node must be drained.
@@ -3574,8 +3559,6 @@ int bdrv_set_backing_hd(BlockDriverState *bs, BlockDriverState *backing_hd,
* itself, all options starting with "${bdref_key}." are considered part of the
* BlockdevRef.
*
- * The caller must hold the main AioContext lock.
- *
* TODO Can this be unified with bdrv_open_image()?
*/
int bdrv_open_backing_file(BlockDriverState *bs, QDict *parent_options,
@@ -3745,9 +3728,7 @@ done:
*
* The BlockdevRef will be removed from the options QDict.
*
- * The caller must hold the lock of the main AioContext and no other AioContext.
- * @parent can move to a different AioContext in this function. Callers must
- * make sure that their AioContext locking is still correct after this.
+ * @parent can move to a different AioContext in this function.
*/
BdrvChild *bdrv_open_child(const char *filename,
QDict *options, const char *bdref_key,
@@ -3778,9 +3759,7 @@ BdrvChild *bdrv_open_child(const char *filename,
/*
* Wrapper on bdrv_open_child() for most popular case: open primary child of bs.
*
- * The caller must hold the lock of the main AioContext and no other AioContext.
- * @parent can move to a different AioContext in this function. Callers must
- * make sure that their AioContext locking is still correct after this.
+ * @parent can move to a different AioContext in this function.
*/
int bdrv_open_file_child(const char *filename,
QDict *options, const char *bdref_key,
@@ -3923,8 +3902,6 @@ out:
* The reference parameter may be used to specify an existing block device which
* should be opened. If specified, neither options nor a filename may be given,
* nor can an existing BDS be reused (that is, *pbs has to be NULL).
- *
- * The caller must always hold the main AioContext lock.
*/
static BlockDriverState * no_coroutine_fn
bdrv_open_inherit(const char *filename, const char *reference, QDict *options,
@@ -4217,7 +4194,6 @@ close_and_fail:
return NULL;
}
-/* The caller must always hold the main AioContext lock. */
BlockDriverState *bdrv_open(const char *filename, const char *reference,
QDict *options, int flags, Error **errp)
{
@@ -4665,10 +4641,7 @@ int bdrv_reopen_set_read_only(BlockDriverState *bs, bool read_only,
*
* Return 0 on success, otherwise return < 0 and set @errp.
*
- * The caller must hold the AioContext lock of @reopen_state->bs.
* @reopen_state->bs can move to a different AioContext in this function.
- * Callers must make sure that their AioContext locking is still correct after
- * this.
*/
static int GRAPH_UNLOCKED
bdrv_reopen_parse_file_or_backing(BDRVReopenState *reopen_state,
@@ -4801,8 +4774,6 @@ out_rdlock:
* It is the responsibility of the caller to then call the abort() or
* commit() for any other BDS that have been left in a prepare() state
*
- * The caller must hold the AioContext lock of @reopen_state->bs.
- *
* After calling this function, the transaction @change_child_tran may only be
* completed while holding a writer lock for the graph.
*/
@@ -5437,8 +5408,6 @@ int bdrv_drop_filter(BlockDriverState *bs, Error **errp)
* child.
*
* This function does not create any image files.
- *
- * The caller must hold the AioContext lock for @bs_top.
*/
int bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top,
Error **errp)
@@ -5545,9 +5514,8 @@ static void bdrv_delete(BlockDriverState *bs)
* after the call (even on failure), so if the caller intends to reuse the
* dictionary, it needs to use qobject_ref() before calling bdrv_open.
*
- * The caller holds the AioContext lock for @bs. It must make sure that @bs
- * stays in the same AioContext, i.e. @options must not refer to nodes in a
- * different AioContext.
+ * The caller must make sure that @bs stays in the same AioContext, i.e.
+ * @options must not refer to nodes in a different AioContext.
*/
BlockDriverState *bdrv_insert_node(BlockDriverState *bs, QDict *options,
int flags, Error **errp)
@@ -7565,10 +7533,6 @@ static TransactionActionDrv set_aio_context = {
*
* Must be called from the main AioContext.
*
- * The caller must own the AioContext lock for the old AioContext of bs, but it
- * must not own the AioContext lock for new_context (unless new_context is the
- * same as the current context of bs).
- *
* @visited will accumulate all visited BdrvChild objects. The caller is
* responsible for freeing the list afterwards.
*/
@@ -7621,13 +7585,6 @@ static bool bdrv_change_aio_context(BlockDriverState *bs, AioContext *ctx,
*
* If ignore_child is not NULL, that child (and its subgraph) will not
* be touched.
- *
- * This function still requires the caller to take the bs current
- * AioContext lock, otherwise draining will fail since AIO_WAIT_WHILE
- * assumes the lock is always held if bs is in another AioContext.
- * For the same reason, it temporarily also holds the new AioContext, since
- * bdrv_drained_end calls BDRV_POLL_WHILE that assumes the lock is taken too.
- * Therefore the new AioContext lock must not be taken by the caller.
*/
int bdrv_try_change_aio_context(BlockDriverState *bs, AioContext *ctx,
BdrvChild *ignore_child, Error **errp)
@@ -7653,8 +7610,8 @@ int bdrv_try_change_aio_context(BlockDriverState *bs, AioContext *ctx,
/*
* Linear phase: go through all callbacks collected in the transaction.
- * Run all callbacks collected in the recursion to switch all nodes
- * AioContext lock (transaction commit), or undo all changes done in the
+ * Run all callbacks collected in the recursion to switch every node's
+ * AioContext (transaction commit), or undo all changes done in the
* recursion (transaction abort).
*/
diff --git a/block/block-backend.c b/block/block-backend.c
index f412bed274..209eb07528 100644
--- a/block/block-backend.c
+++ b/block/block-backend.c
@@ -390,8 +390,6 @@ BlockBackend *blk_new(AioContext *ctx, uint64_t perm, uint64_t shared_perm)
* Both sets of permissions can be changed later using blk_set_perm().
*
* Return the new BlockBackend on success, null on failure.
- *
- * Callers must hold the AioContext lock of @bs.
*/
BlockBackend *blk_new_with_bs(BlockDriverState *bs, uint64_t perm,
uint64_t shared_perm, Error **errp)
@@ -416,8 +414,6 @@ BlockBackend *blk_new_with_bs(BlockDriverState *bs, uint64_t perm,
* Just as with bdrv_open(), after having called this function the reference to
* @options belongs to the block layer (even on failure).
*
- * Called without holding an AioContext lock.
- *
* TODO: Remove @filename and @flags; it should be possible to specify a whole
* BDS tree just by specifying the @options QDict (or @reference,
* alternatively). At the time of adding this function, this is not possible,
@@ -872,8 +868,6 @@ BlockBackend *blk_by_public(BlockBackendPublic *public)
/*
* Disassociates the currently associated BlockDriverState from @blk.
- *
- * The caller must hold the AioContext lock for the BlockBackend.
*/
void blk_remove_bs(BlockBackend *blk)
{
@@ -915,8 +909,6 @@ void blk_remove_bs(BlockBackend *blk)
/*
* Associates a new BlockDriverState with @blk.
- *
- * Callers must hold the AioContext lock of @bs.
*/
int blk_insert_bs(BlockBackend *blk, BlockDriverState *bs, Error **errp)
{
diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c
index 16f48388d3..50c358e8cd 100644
--- a/block/export/vhost-user-blk-server.c
+++ b/block/export/vhost-user-blk-server.c
@@ -278,7 +278,6 @@ static void vu_blk_exp_resize(void *opaque)
vu_config_change_msg(&vexp->vu_server.vu_dev);
}
-/* Called with vexp->export.ctx acquired */
static void vu_blk_drained_begin(void *opaque)
{
VuBlkExport *vexp = opaque;
@@ -287,7 +286,6 @@ static void vu_blk_drained_begin(void *opaque)
vhost_user_server_detach_aio_context(&vexp->vu_server);
}
-/* Called with vexp->export.blk AioContext acquired */
static void vu_blk_drained_end(void *opaque)
{
VuBlkExport *vexp = opaque;
@@ -300,8 +298,6 @@ static void vu_blk_drained_end(void *opaque)
* Ensures that bdrv_drained_begin() waits until in-flight requests complete
* and the server->co_trip coroutine has terminated. It will be restarted in
* vhost_user_server_attach_aio_context().
- *
- * Called with vexp->export.ctx acquired.
*/
static bool vu_blk_drained_poll(void *opaque)
{
diff --git a/include/block/block-common.h b/include/block/block-common.h
index d7599564db..a846023a09 100644
--- a/include/block/block-common.h
+++ b/include/block/block-common.h
@@ -70,9 +70,6 @@
* automatically takes the graph rdlock when calling the wrapped function. In
* the same way, no_co_wrapper_bdrv_wrlock functions automatically take the
* graph wrlock.
- *
- * If the first parameter of the function is a BlockDriverState, BdrvChild or
- * BlockBackend pointer, the AioContext lock for it is taken in the wrapper.
*/
#define no_co_wrapper
#define no_co_wrapper_bdrv_rdlock
diff --git a/include/block/block-io.h b/include/block/block-io.h
index 8eb39a858b..b49e0537dd 100644
--- a/include/block/block-io.h
+++ b/include/block/block-io.h
@@ -332,11 +332,10 @@ bdrv_co_copy_range(BdrvChild *src, int64_t src_offset,
* "I/O or GS" API functions. These functions can run without
* the BQL, but only in one specific iothread/main loop.
*
- * More specifically, these functions use BDRV_POLL_WHILE(bs), which
- * requires the caller to be either in the main thread and hold
- * the BlockdriverState (bs) AioContext lock, or directly in the
- * home thread that runs the bs AioContext. Calling them from
- * another thread in another AioContext would cause deadlocks.
+ * More specifically, these functions use BDRV_POLL_WHILE(bs), which requires
+ * the caller to be either in the main thread or directly in the home thread
+ * that runs the bs AioContext. Calling them from another thread in another
+ * AioContext would cause deadlocks.
*
* Therefore, these functions are not proper I/O, because they
* can't run in *any* iothreads, but only in a specific one.
diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h
index 4e31d161c5..151279d481 100644
--- a/include/block/block_int-common.h
+++ b/include/block/block_int-common.h
@@ -1192,8 +1192,6 @@ struct BlockDriverState {
/* The error object in use for blocking operations on backing_hd */
Error *backing_blocker;
- /* Protected by AioContext lock */
-
/*
* If we are reading a disk image, give its size in sectors.
* Generally read-only; it is written to by load_snapshot and
diff --git a/tests/qemu-iotests/202 b/tests/qemu-iotests/202
index b784dcd791..13304242e5 100755
--- a/tests/qemu-iotests/202
+++ b/tests/qemu-iotests/202
@@ -21,7 +21,7 @@
# Check that QMP 'transaction' blockdev-snapshot-sync with multiple drives on a
# single IOThread completes successfully. This particular command triggered a
# hang due to recursive AioContext locking and BDRV_POLL_WHILE(). Protect
-# against regressions.
+# against regressions even though the AioContext lock no longer exists.
import iotests
diff --git a/tests/qemu-iotests/203 b/tests/qemu-iotests/203
index ab80fd0e44..1ba878522b 100755
--- a/tests/qemu-iotests/203
+++ b/tests/qemu-iotests/203
@@ -21,7 +21,8 @@
# Check that QMP 'migrate' with multiple drives on a single IOThread completes
# successfully. This particular command triggered a hang in the source QEMU
# process due to recursive AioContext locking in bdrv_invalidate_all() and
-# BDRV_POLL_WHILE().
+# BDRV_POLL_WHILE(). Protect against regressions even though the AioContext
+# lock no longer exists.
import iotests
--
2.39.3

105
kvm-chardev-char-socket-Fix-TLS-io-channels-sending-too-.patch
View File

@ -1,105 +0,0 @@
From 95b2ffc5f01dc4309c2e747ed883d22cd1d26347 Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Sat, 2 Mar 2024 17:00:23 +0100
Subject: [PATCH 2/2] chardev/char-socket: Fix TLS io channels sending too much
data to the backend
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Thomas Huth <thuth@redhat.com>
RH-MergeRequest: 227: Fix TLS io channels sending too much data to the backend
RH-Jira: RHEL-24614
RH-Acked-by: Cédric Le Goater <clg@redhat.com>
RH-Acked-by: Daniel P. Berrangé <berrange@redhat.com>
RH-Commit: [1/1] fce871914e0ce52e16a6edae0e007513f9fec1ae (thuth/qemu-kvm-cs9)
JIRA: https://issues.redhat.com/browse/RHEL-24614
commit 462945cd22d2bcd233401ed3aa167d83a8e35b05
Author: Thomas Huth <thuth@redhat.com>
Date: Thu Feb 29 11:43:37 2024 +0100
chardev/char-socket: Fix TLS io channels sending too much data to the backend
Commit ffda5db65a ("io/channel-tls: fix handling of bigger read buffers")
changed the behavior of the TLS io channels to schedule a second reading
attempt if there is still incoming data pending. This caused a regression
with backends like the sclpconsole that check in their read function that
the sender does not try to write more bytes to it than the device can
currently handle.
The problem can be reproduced like this:
1) In one terminal, do this:
mkdir qemu-pki
cd qemu-pki
openssl genrsa 2048 > ca-key.pem
openssl req -new -x509 -nodes -days 365000 -key ca-key.pem -out ca-cert.pem
# enter some dummy value for the cert
openssl genrsa 2048 > server-key.pem
openssl req -new -x509 -nodes -days 365000 -key server-key.pem \
-out server-cert.pem
# enter some other dummy values for the cert
gnutls-serv --echo --x509cafile ca-cert.pem --x509keyfile server-key.pem \
--x509certfile server-cert.pem -p 8338
2) In another terminal, do this:
wget https://download.fedoraproject.org/pub/fedora-secondary/releases/39/Cloud/s390x/images/Fedora-Cloud-Base-39-1.5.s390x.qcow2
qemu-system-s390x -nographic -nodefaults \
-hda Fedora-Cloud-Base-39-1.5.s390x.qcow2 \
-object tls-creds-x509,id=tls0,endpoint=client,verify-peer=false,dir=$PWD/qemu-pki \
-chardev socket,id=tls_chardev,host=localhost,port=8338,tls-creds=tls0 \
-device sclpconsole,chardev=tls_chardev,id=tls_serial
QEMU then aborts after a second or two with:
qemu-system-s390x: ../hw/char/sclpconsole.c:73: chr_read: Assertion
`size <= SIZE_BUFFER_VT220 - scon->iov_data_len' failed.
Aborted (core dumped)
It looks like the second read does not trigger the chr_can_read() function
to be called before the second read, which should normally always be done
before sending bytes to a character device to see how much it can handle,
so the s->max_size in tcp_chr_read() still contains the old value from the
previous read. Let's make sure that we use the up-to-date value by calling
tcp_chr_read_poll() again here.
Fixes: ffda5db65a ("io/channel-tls: fix handling of bigger read buffers")
Buglink: https://issues.redhat.com/browse/RHEL-24614
Reviewed-by: "Daniel P. Berrangé" <berrange@redhat.com>
Message-ID: <20240229104339.42574-1-thuth@redhat.com>
Reviewed-by: Antoine Damhet <antoine.damhet@blade-group.com>
Tested-by: Antoine Damhet <antoine.damhet@blade-group.com>
Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
---
chardev/char-socket.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/chardev/char-socket.c b/chardev/char-socket.c
index 73947da188..034840593d 100644
--- a/chardev/char-socket.c
+++ b/chardev/char-socket.c
@@ -492,9 +492,9 @@ static gboolean tcp_chr_read(QIOChannel *chan, GIOCondition cond, void *opaque)
s->max_size <= 0) {
return TRUE;
}
- len = sizeof(buf);
- if (len > s->max_size) {
- len = s->max_size;
+ len = tcp_chr_read_poll(opaque);
+ if (len > sizeof(buf)) {
+ len = sizeof(buf);
}
size = tcp_chr_recv(chr, (void *)buf, len);
if (size == 0 || (size == -1 && errno != EAGAIN)) {
--
2.39.3

78
kvm-chardev-lower-priority-of-the-HUP-GSource-in-socket-.patch
View File

@ -1,78 +0,0 @@
From 4d4102f6e2f9afd6182888787ae8b570347df87d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Daniel=20P=2E=20Berrang=C3=A9?= <berrange@redhat.com>
Date: Mon, 18 Mar 2024 18:06:59 +0000
Subject: [PATCH 1/3] chardev: lower priority of the HUP GSource in socket
chardev
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Daniel P. Berrangé <berrange@redhat.com>
RH-MergeRequest: 233: Fix handling of TLS sessions in chardevs
RH-Jira: RHEL-24614
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Marc-André Lureau <marcandre.lureau@redhat.com>
RH-Commit: [1/3] 842f54349191b0206e68f35a7a80155f5a584942 (berrange/centos-src-qemu)
The socket chardev often has 2 GSource object registered against the
same FD. One is registered all the time and is just intended to handle
POLLHUP events, while the other gets registered & unregistered on the
fly as the frontend is ready to receive more data or not.
It is very common for poll() to signal a POLLHUP event at the same time
as there is pending incoming data from the disconnected client. It is
therefore essential to process incoming data prior to processing HUP.
The problem with having 2 GSource on the same FD is that there is no
guaranteed ordering of execution between them, so the chardev code may
process HUP first and thus discard data.
This failure scenario is non-deterministic but can be seen fairly
reliably by reverting a7077b8e354d90fec26c2921aa2dea85b90dff90, and
then running 'tests/unit/test-char', which will sometimes fail with
missing data.
Ideally QEMU would only have 1 GSource, but that's a complex code
refactoring job. The next best solution is to try to ensure ordering
between the 2 GSource objects. This can be achieved by lowering the
priority of the HUP GSource, so that it is never dispatched if the
main GSource is also ready to dispatch. Counter-intuitively, lowering
the priority of a GSource is done by raising its priority number.
Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
(cherry picked from commit 8bd8b04adc9f18904f323dff085f8b4ec77915c6)
---
chardev/char-socket.c | 16 ++++++++++++++++
1 file changed, 16 insertions(+)
diff --git a/chardev/char-socket.c b/chardev/char-socket.c
index 034840593d..f48d341ebc 100644
--- a/chardev/char-socket.c
+++ b/chardev/char-socket.c
@@ -597,6 +597,22 @@ static void update_ioc_handlers(SocketChardev *s)
remove_hup_source(s);
s->hup_source = qio_channel_create_watch(s->ioc, G_IO_HUP);
+ /*
+ * poll() is liable to return POLLHUP even when there is
+ * still incoming data available to read on the FD. If
+ * we have the hup_source at the same priority as the
+ * main io_add_watch_poll GSource, then we might end up
+ * processing the POLLHUP event first, closing the FD,
+ * and as a result silently discard data we should have
+ * read.
+ *
+ * By setting the hup_source to G_PRIORITY_DEFAULT + 1,
+ * we ensure that io_add_watch_poll GSource will always
+ * be dispatched first, thus guaranteeing we will be
+ * able to process all incoming data before closing the
+ * FD
+ */
+ g_source_set_priority(s->hup_source, G_PRIORITY_DEFAULT + 1);
g_source_set_callback(s->hup_source, (GSourceFunc)tcp_chr_hup,
chr, NULL);
g_source_attach(s->hup_source, chr->gcontext);
--
2.39.3

412
kvm-coroutine-cap-per-thread-local-pool-size.patch
View File

@ -1,412 +0,0 @@
From e99c56752a1c4021a93c92b7be78856ebefaa1b3 Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Mon, 18 Mar 2024 14:34:29 -0400
Subject: [PATCH 1/2] coroutine: cap per-thread local pool size
RH-Author: Stefan Hajnoczi <stefanha@redhat.com>
RH-MergeRequest: 234: coroutine: cap per-thread local pool size
RH-Jira: RHEL-28947
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Commit: [1/2] 5971de1c1e238457925bfb9c4bfc932de857b28d (stefanha/centos-stream-qemu-kvm)
The coroutine pool implementation can hit the Linux vm.max_map_count
limit, causing QEMU to abort with "failed to allocate memory for stack"
or "failed to set up stack guard page" during coroutine creation.
This happens because per-thread pools can grow to tens of thousands of
coroutines. Each coroutine causes 2 virtual memory areas to be created.
Eventually vm.max_map_count is reached and memory-related syscalls fail.
The per-thread pool sizes are non-uniform and depend on past coroutine
usage in each thread, so it's possible for one thread to have a large
pool while another thread's pool is empty.
Switch to a new coroutine pool implementation with a global pool that
grows to a maximum number of coroutines and per-thread local pools that
are capped at hardcoded small number of coroutines.
This approach does not leave large numbers of coroutines pooled in a
thread that may not use them again. In order to perform well it
amortizes the cost of global pool accesses by working in batches of
coroutines instead of individual coroutines.
The global pool is a list. Threads donate batches of coroutines to when
they have too many and take batches from when they have too few:
.-----------------------------------.
| Batch 1 | Batch 2 | Batch 3 | ... | global_pool
`-----------------------------------'
Each thread has up to 2 batches of coroutines:
.-------------------.
| Batch 1 | Batch 2 | per-thread local_pool (maximum 2 batches)
`-------------------'
The goal of this change is to reduce the excessive number of pooled
coroutines that cause QEMU to abort when vm.max_map_count is reached
without losing the performance of an adequately sized coroutine pool.
Here are virtio-blk disk I/O benchmark results:
RW BLKSIZE IODEPTH OLD NEW CHANGE
randread 4k 1 113725 117451 +3.3%
randread 4k 8 192968 198510 +2.9%
randread 4k 16 207138 209429 +1.1%
randread 4k 32 212399 215145 +1.3%
randread 4k 64 218319 221277 +1.4%
randread 128k 1 17587 17535 -0.3%
randread 128k 8 17614 17616 +0.0%
randread 128k 16 17608 17609 +0.0%
randread 128k 32 17552 17553 +0.0%
randread 128k 64 17484 17484 +0.0%
See files/{fio.sh,test.xml.j2} for the benchmark configuration:
https://gitlab.com/stefanha/virt-playbooks/-/tree/coroutine-pool-fix-sizing
Buglink: https://issues.redhat.com/browse/RHEL-28947
Reported-by: Sanjay Rao <srao@redhat.com>
Reported-by: Boaz Ben Shabat <bbenshab@redhat.com>
Reported-by: Joe Mario <jmario@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-ID: <20240318183429.1039340-1-stefanha@redhat.com>
(cherry picked from commit 86a637e48104ae74d8be53bed6441ce32be33433)
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
util/qemu-coroutine.c | 282 +++++++++++++++++++++++++++++++++---------
1 file changed, 223 insertions(+), 59 deletions(-)
diff --git a/util/qemu-coroutine.c b/util/qemu-coroutine.c
index 5fd2dbaf8b..2790959eaf 100644
--- a/util/qemu-coroutine.c
+++ b/util/qemu-coroutine.c
@@ -18,39 +18,200 @@
#include "qemu/atomic.h"
#include "qemu/coroutine_int.h"
#include "qemu/coroutine-tls.h"
+#include "qemu/cutils.h"
#include "block/aio.h"
-/**
- * The minimal batch size is always 64, coroutines from the release_pool are
- * reused as soon as there are 64 coroutines in it. The maximum pool size starts
- * with 64 and is increased on demand so that coroutines are not deleted even if
- * they are not immediately reused.
- */
enum {
- POOL_MIN_BATCH_SIZE = 64,
- POOL_INITIAL_MAX_SIZE = 64,
+ COROUTINE_POOL_BATCH_MAX_SIZE = 128,
};
-/** Free list to speed up creation */
-static QSLIST_HEAD(, Coroutine) release_pool = QSLIST_HEAD_INITIALIZER(pool);
-static unsigned int pool_max_size = POOL_INITIAL_MAX_SIZE;
-static unsigned int release_pool_size;
+/*
+ * Coroutine creation and deletion is expensive so a pool of unused coroutines
+ * is kept as a cache. When the pool has coroutines available, they are
+ * recycled instead of creating new ones from scratch. Coroutines are added to
+ * the pool upon termination.
+ *
+ * The pool is global but each thread maintains a small local pool to avoid
+ * global pool contention. Threads fetch and return batches of coroutines from
+ * the global pool to maintain their local pool. The local pool holds up to two
+ * batches whereas the maximum size of the global pool is controlled by the
+ * qemu_coroutine_inc_pool_size() API.
+ *
+ * .-----------------------------------.
+ * | Batch 1 | Batch 2 | Batch 3 | ... | global_pool
+ * `-----------------------------------'
+ *
+ * .-------------------.
+ * | Batch 1 | Batch 2 | per-thread local_pool (maximum 2 batches)
+ * `-------------------'
+ */
+typedef struct CoroutinePoolBatch {
+ /* Batches are kept in a list */
+ QSLIST_ENTRY(CoroutinePoolBatch) next;
+
+ /* This batch holds up to @COROUTINE_POOL_BATCH_MAX_SIZE coroutines */
+ QSLIST_HEAD(, Coroutine) list;
+ unsigned int size;
+} CoroutinePoolBatch;
+
+typedef QSLIST_HEAD(, CoroutinePoolBatch) CoroutinePool;
+
+/* Host operating system limit on number of pooled coroutines */
+static unsigned int global_pool_hard_max_size;
+
+static QemuMutex global_pool_lock; /* protects the following variables */
+static CoroutinePool global_pool = QSLIST_HEAD_INITIALIZER(global_pool);
+static unsigned int global_pool_size;
+static unsigned int global_pool_max_size = COROUTINE_POOL_BATCH_MAX_SIZE;
+
+QEMU_DEFINE_STATIC_CO_TLS(CoroutinePool, local_pool);
+QEMU_DEFINE_STATIC_CO_TLS(Notifier, local_pool_cleanup_notifier);
-typedef QSLIST_HEAD(, Coroutine) CoroutineQSList;
-QEMU_DEFINE_STATIC_CO_TLS(CoroutineQSList, alloc_pool);
-QEMU_DEFINE_STATIC_CO_TLS(unsigned int, alloc_pool_size);
-QEMU_DEFINE_STATIC_CO_TLS(Notifier, coroutine_pool_cleanup_notifier);
+static CoroutinePoolBatch *coroutine_pool_batch_new(void)
+{
+ CoroutinePoolBatch *batch = g_new(CoroutinePoolBatch, 1);
+
+ QSLIST_INIT(&batch->list);
+ batch->size = 0;
+ return batch;
+}
-static void coroutine_pool_cleanup(Notifier *n, void *value)
+static void coroutine_pool_batch_delete(CoroutinePoolBatch *batch)
{
Coroutine *co;
Coroutine *tmp;
- CoroutineQSList *alloc_pool = get_ptr_alloc_pool();
- QSLIST_FOREACH_SAFE(co, alloc_pool, pool_next, tmp) {
- QSLIST_REMOVE_HEAD(alloc_pool, pool_next);
+ QSLIST_FOREACH_SAFE(co, &batch->list, pool_next, tmp) {
+ QSLIST_REMOVE_HEAD(&batch->list, pool_next);
qemu_coroutine_delete(co);
}
+ g_free(batch);
+}
+
+static void local_pool_cleanup(Notifier *n, void *value)
+{
+ CoroutinePool *local_pool = get_ptr_local_pool();
+ CoroutinePoolBatch *batch;
+ CoroutinePoolBatch *tmp;
+
+ QSLIST_FOREACH_SAFE(batch, local_pool, next, tmp) {
+ QSLIST_REMOVE_HEAD(local_pool, next);
+ coroutine_pool_batch_delete(batch);
+ }
+}
+
+/* Ensure the atexit notifier is registered */
+static void local_pool_cleanup_init_once(void)
+{
+ Notifier *notifier = get_ptr_local_pool_cleanup_notifier();
+ if (!notifier->notify) {
+ notifier->notify = local_pool_cleanup;
+ qemu_thread_atexit_add(notifier);
+ }
+}
+
+/* Helper to get the next unused coroutine from the local pool */
+static Coroutine *coroutine_pool_get_local(void)
+{
+ CoroutinePool *local_pool = get_ptr_local_pool();
+ CoroutinePoolBatch *batch = QSLIST_FIRST(local_pool);
+ Coroutine *co;
+
+ if (unlikely(!batch)) {
+ return NULL;
+ }
+
+ co = QSLIST_FIRST(&batch->list);
+ QSLIST_REMOVE_HEAD(&batch->list, pool_next);
+ batch->size--;
+
+ if (batch->size == 0) {
+ QSLIST_REMOVE_HEAD(local_pool, next);
+ coroutine_pool_batch_delete(batch);
+ }
+ return co;
+}
+
+/* Get the next batch from the global pool */
+static void coroutine_pool_refill_local(void)
+{
+ CoroutinePool *local_pool = get_ptr_local_pool();
+ CoroutinePoolBatch *batch;
+
+ WITH_QEMU_LOCK_GUARD(&global_pool_lock) {
+ batch = QSLIST_FIRST(&global_pool);
+
+ if (batch) {
+ QSLIST_REMOVE_HEAD(&global_pool, next);
+ global_pool_size -= batch->size;
+ }
+ }
+
+ if (batch) {
+ QSLIST_INSERT_HEAD(local_pool, batch, next);
+ local_pool_cleanup_init_once();
+ }
+}
+
+/* Add a batch of coroutines to the global pool */
+static void coroutine_pool_put_global(CoroutinePoolBatch *batch)
+{
+ WITH_QEMU_LOCK_GUARD(&global_pool_lock) {
+ unsigned int max = MIN(global_pool_max_size,
+ global_pool_hard_max_size);
+
+ if (global_pool_size < max) {
+ QSLIST_INSERT_HEAD(&global_pool, batch, next);
+
+ /* Overshooting the max pool size is allowed */
+ global_pool_size += batch->size;
+ return;
+ }
+ }
+
+ /* The global pool was full, so throw away this batch */
+ coroutine_pool_batch_delete(batch);
+}
+
+/* Get the next unused coroutine from the pool or return NULL */
+static Coroutine *coroutine_pool_get(void)
+{
+ Coroutine *co;
+
+ co = coroutine_pool_get_local();
+ if (!co) {
+ coroutine_pool_refill_local();
+ co = coroutine_pool_get_local();
+ }
+ return co;
+}
+
+static void coroutine_pool_put(Coroutine *co)
+{
+ CoroutinePool *local_pool = get_ptr_local_pool();
+ CoroutinePoolBatch *batch = QSLIST_FIRST(local_pool);
+
+ if (unlikely(!batch)) {
+ batch = coroutine_pool_batch_new();
+ QSLIST_INSERT_HEAD(local_pool, batch, next);
+ local_pool_cleanup_init_once();
+ }
+
+ if (unlikely(batch->size >= COROUTINE_POOL_BATCH_MAX_SIZE)) {
+ CoroutinePoolBatch *next = QSLIST_NEXT(batch, next);
+
+ /* Is the local pool full? */
+ if (next) {
+ QSLIST_REMOVE_HEAD(local_pool, next);
+ coroutine_pool_put_global(batch);
+ }
+
+ batch = coroutine_pool_batch_new();
+ QSLIST_INSERT_HEAD(local_pool, batch, next);
+ }
+
+ QSLIST_INSERT_HEAD(&batch->list, co, pool_next);
+ batch->size++;
}
Coroutine *qemu_coroutine_create(CoroutineEntry *entry, void *opaque)
@@ -58,31 +219,7 @@ Coroutine *qemu_coroutine_create(CoroutineEntry *entry, void *opaque)
Coroutine *co = NULL;
if (IS_ENABLED(CONFIG_COROUTINE_POOL)) {
- CoroutineQSList *alloc_pool = get_ptr_alloc_pool();
-
- co = QSLIST_FIRST(alloc_pool);
- if (!co) {
- if (release_pool_size > POOL_MIN_BATCH_SIZE) {
- /* Slow path; a good place to register the destructor, too. */
- Notifier *notifier = get_ptr_coroutine_pool_cleanup_notifier();
- if (!notifier->notify) {
- notifier->notify = coroutine_pool_cleanup;
- qemu_thread_atexit_add(notifier);
- }
-
- /* This is not exact; there could be a little skew between
- * release_pool_size and the actual size of release_pool. But
- * it is just a heuristic, it does not need to be perfect.
- */
- set_alloc_pool_size(qatomic_xchg(&release_pool_size, 0));
- QSLIST_MOVE_ATOMIC(alloc_pool, &release_pool);
- co = QSLIST_FIRST(alloc_pool);
- }
- }
- if (co) {
- QSLIST_REMOVE_HEAD(alloc_pool, pool_next);
- set_alloc_pool_size(get_alloc_pool_size() - 1);
- }
+ co = coroutine_pool_get();
}
if (!co) {
@@ -100,19 +237,10 @@ static void coroutine_delete(Coroutine *co)
co->caller = NULL;
if (IS_ENABLED(CONFIG_COROUTINE_POOL)) {
- if (release_pool_size < qatomic_read(&pool_max_size) * 2) {
- QSLIST_INSERT_HEAD_ATOMIC(&release_pool, co, pool_next);
- qatomic_inc(&release_pool_size);
- return;
- }
- if (get_alloc_pool_size() < qatomic_read(&pool_max_size)) {
- QSLIST_INSERT_HEAD(get_ptr_alloc_pool(), co, pool_next);
- set_alloc_pool_size(get_alloc_pool_size() + 1);
- return;
- }
+ coroutine_pool_put(co);
+ } else {
+ qemu_coroutine_delete(co);
}
-
- qemu_coroutine_delete(co);
}
void qemu_aio_coroutine_enter(AioContext *ctx, Coroutine *co)
@@ -223,10 +351,46 @@ AioContext *qemu_coroutine_get_aio_context(Coroutine *co)
void qemu_coroutine_inc_pool_size(unsigned int additional_pool_size)
{
- qatomic_add(&pool_max_size, additional_pool_size);
+ QEMU_LOCK_GUARD(&global_pool_lock);
+ global_pool_max_size += additional_pool_size;
}
void qemu_coroutine_dec_pool_size(unsigned int removing_pool_size)
{
- qatomic_sub(&pool_max_size, removing_pool_size);
+ QEMU_LOCK_GUARD(&global_pool_lock);
+ global_pool_max_size -= removing_pool_size;
+}
+
+static unsigned int get_global_pool_hard_max_size(void)
+{
+#ifdef __linux__
+ g_autofree char *contents = NULL;
+ int max_map_count;
+
+ /*
+ * Linux processes can have up to max_map_count virtual memory areas
+ * (VMAs). mmap(2), mprotect(2), etc fail with ENOMEM beyond this limit. We
+ * must limit the coroutine pool to a safe size to avoid running out of
+ * VMAs.
+ */
+ if (g_file_get_contents("/proc/sys/vm/max_map_count", &contents, NULL,
+ NULL) &&
+ qemu_strtoi(contents, NULL, 10, &max_map_count) == 0) {
+ /*
+ * This is a conservative upper bound that avoids exceeding
+ * max_map_count. Leave half for non-coroutine users like library
+ * dependencies, vhost-user, etc. Each coroutine takes up 2 VMAs so
+ * halve the amount again.
+ */
+ return max_map_count / 4;
+ }
+#endif
+
+ return UINT_MAX;
+}
+
+static void __attribute__((constructor)) qemu_coroutine_init(void)
+{
+ qemu_mutex_init(&global_pool_lock);
+ global_pool_hard_max_size = get_global_pool_hard_max_size();
}
--
2.39.3

61
kvm-coroutine-reserve-5-000-mappings.patch
View File

@ -1,61 +0,0 @@
From 0aa65dc3acba481f7064df936ab49e3bceb1d5bd Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Wed, 20 Mar 2024 14:12:32 -0400
Subject: [PATCH 2/2] coroutine: reserve 5,000 mappings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Stefan Hajnoczi <stefanha@redhat.com>
RH-MergeRequest: 234: coroutine: cap per-thread local pool size
RH-Jira: RHEL-28947
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Commit: [2/2] 78560c2b947471111cc16c313d6f38db42860a1c (stefanha/centos-stream-qemu-kvm)
Daniel P. Berrangé <berrange@redhat.com> pointed out that the coroutine
pool size heuristic is very conservative. Instead of halving
max_map_count, he suggested reserving 5,000 mappings for non-coroutine
users based on observations of guests he has access to.
Fixes: 86a637e48104 ("coroutine: cap per-thread local pool size")
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Message-id: 20240320181232.1464819-1-stefanha@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit 9352f80cd926fe2dde7c89b93ee33bb0356ff40e)
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
util/qemu-coroutine.c | 15 ++++++++++-----
1 file changed, 10 insertions(+), 5 deletions(-)
diff --git a/util/qemu-coroutine.c b/util/qemu-coroutine.c
index 2790959eaf..eb4eebefdf 100644
--- a/util/qemu-coroutine.c
+++ b/util/qemu-coroutine.c
@@ -377,12 +377,17 @@ static unsigned int get_global_pool_hard_max_size(void)
NULL) &&
qemu_strtoi(contents, NULL, 10, &max_map_count) == 0) {
/*
- * This is a conservative upper bound that avoids exceeding
- * max_map_count. Leave half for non-coroutine users like library
- * dependencies, vhost-user, etc. Each coroutine takes up 2 VMAs so
- * halve the amount again.
+ * This is an upper bound that avoids exceeding max_map_count. Leave a
+ * fixed amount for non-coroutine users like library dependencies,
+ * vhost-user, etc. Each coroutine takes up 2 VMAs so halve the
+ * remaining amount.
*/
- return max_map_count / 4;
+ if (max_map_count > 5000) {
+ return (max_map_count - 5000) / 2;
+ } else {
+ /* Disable the global pool but threads still have local pools */
+ return 0;
+ }
}
#endif
--
2.39.3

75
kvm-dma-helpers-don-t-lock-AioContext-in-dma_blk_cb.patch
View File

@ -1,75 +0,0 @@
From ac9dc8ea241ef6d3a0447d696620d4d4053b71bf Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Mon, 4 Dec 2023 11:42:59 -0500
Subject: [PATCH 080/101] dma-helpers: don't lock AioContext in dma_blk_cb()
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 214: Remove AioContext lock
RH-Jira: RHEL-15965
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Commit: [11/26] a8580463ba6aee4ca248c0b947b9e72bd9e87aab (kmwolf/centos-qemu-kvm)
Commit abfcd2760b3e ("dma-helpers: prevent dma_blk_cb() vs
dma_aio_cancel() race") acquired the AioContext lock inside dma_blk_cb()
to avoid a race with scsi_device_purge_requests() running in the main
loop thread.
The SCSI code no longer calls dma_aio_cancel() from the main loop thread
while I/O is running in the IOThread AioContext. Therefore it is no
longer necessary to take this lock to protect DMAAIOCB fields. The
->cb() function also does not require the lock because blk_aio_*() and
friends do not need the AioContext lock.
Both hw/ide/core.c and hw/ide/macio.c also call dma_blk_io() but don't
rely on it taking the AioContext lock, so this change is safe.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Message-ID: <20231204164259.1515217-5-stefanha@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
system/dma-helpers.c | 7 ++-----
1 file changed, 2 insertions(+), 5 deletions(-)
diff --git a/system/dma-helpers.c b/system/dma-helpers.c
index 36211acc7e..528117f256 100644
--- a/system/dma-helpers.c
+++ b/system/dma-helpers.c
@@ -119,13 +119,12 @@ static void dma_blk_cb(void *opaque, int ret)
trace_dma_blk_cb(dbs, ret);
- aio_context_acquire(ctx);
dbs->acb = NULL;
dbs->offset += dbs->iov.size;
if (dbs->sg_cur_index == dbs->sg->nsg || ret < 0) {
dma_complete(dbs, ret);
- goto out;
+ return;
}
dma_blk_unmap(dbs);
@@ -168,7 +167,7 @@ static void dma_blk_cb(void *opaque, int ret)
trace_dma_map_wait(dbs);
dbs->bh = aio_bh_new(ctx, reschedule_dma, dbs);
cpu_register_map_client(dbs->bh);
- goto out;
+ return;
}
if (!QEMU_IS_ALIGNED(dbs->iov.size, dbs->align)) {
@@ -179,8 +178,6 @@ static void dma_blk_cb(void *opaque, int ret)
dbs->acb = dbs->io_func(dbs->offset, &dbs->iov,
dma_blk_cb, dbs, dbs->io_func_opaque);
assert(dbs->acb);
-out:
- aio_context_release(ctx);
}
static void dma_aio_cancel(BlockAIOCB *acb)
--
2.39.3

228
kvm-docs-devel-Add-VFIO-iommufd-backend-documentation.patch
View File

@ -1,228 +0,0 @@
From 71aa0219f7c84cbf175eb2a091d48d5fd5daa40b Mon Sep 17 00:00:00 2001
From: Zhenzhong Duan <zhenzhong.duan@intel.com>
Date: Tue, 21 Nov 2023 16:44:26 +0800
Subject: [PATCH 047/101] docs/devel: Add VFIO iommufd backend documentation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 211: IOMMUFD backend backport
RH-Jira: RHEL-19302 RHEL-21057
RH-Acked-by: Cédric Le Goater <clg@redhat.com>
RH-Acked-by: Sebastian Ott <sebott@redhat.com>
RH-Commit: [46/67] 6cf49d00e87788f894d690a985bb6798eae24505 (eauger1/centos-qemu-kvm)
Suggested-by: Cédric Le Goater <clg@redhat.com>
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Yi Liu <yi.l.liu@intel.com>
Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Cédric Le Goater <clg@redhat.com>
(cherry picked from commit 98dad2b01931f6064c6c4b48ca3c2a1d9f542cd8)
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
MAINTAINERS | 1 +
docs/devel/index-internals.rst | 1 +
docs/devel/vfio-iommufd.rst | 166 +++++++++++++++++++++++++++++++++
3 files changed, 168 insertions(+)
create mode 100644 docs/devel/vfio-iommufd.rst
diff --git a/MAINTAINERS b/MAINTAINERS
index ca70bb4e64..0ddb20a35f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2176,6 +2176,7 @@ F: backends/iommufd.c
F: include/sysemu/iommufd.h
F: include/qemu/chardev_open.h
F: util/chardev_open.c
+F: docs/devel/vfio-iommufd.rst
vhost
M: Michael S. Tsirkin <mst@redhat.com>
diff --git a/docs/devel/index-internals.rst b/docs/devel/index-internals.rst
index 6f81df92bc..3def4a138b 100644
--- a/docs/devel/index-internals.rst
+++ b/docs/devel/index-internals.rst
@@ -18,5 +18,6 @@ Details about QEMU's various subsystems including how to add features to them.
s390-dasd-ipl
tracing
vfio-migration
+ vfio-iommufd
writing-monitor-commands
virtio-backends
diff --git a/docs/devel/vfio-iommufd.rst b/docs/devel/vfio-iommufd.rst
new file mode 100644
index 0000000000..3d1c11f175
--- /dev/null
+++ b/docs/devel/vfio-iommufd.rst
@@ -0,0 +1,166 @@
+===============================
+IOMMUFD BACKEND usage with VFIO
+===============================
+
+(Same meaning for backend/container/BE)
+
+With the introduction of iommufd, the Linux kernel provides a generic
+interface for user space drivers to propagate their DMA mappings to kernel
+for assigned devices. While the legacy kernel interface is group-centric,
+the new iommufd interface is device-centric, relying on device fd and iommufd.
+
+To support both interfaces in the QEMU VFIO device, introduce a base container
+to abstract the common part of VFIO legacy and iommufd container. So that the
+generic VFIO code can use either container.
+
+The base container implements generic functions such as memory_listener and
+address space management whereas the derived container implements callbacks
+specific to either legacy or iommufd. Each container has its own way to setup
+secure context and dma management interface. The below diagram shows how it
+looks like with both containers.
+
+::
+
+ VFIO AddressSpace/Memory
+ +-------+ +----------+ +-----+ +-----+
+ | pci | | platform | | ap | | ccw |
+ +---+---+ +----+-----+ +--+--+ +--+--+ +----------------------+
+ | | | | | AddressSpace |
+ | | | | +------------+---------+
+ +---V-----------V-----------V--------V----+ /
+ | VFIOAddressSpace | <------------+
+ | | | MemoryListener
+ | VFIOContainerBase list |
+ +-------+----------------------------+----+
+ | |
+ | |
+ +-------V------+ +--------V----------+
+ | iommufd | | vfio legacy |
+ | container | | container |
+ +-------+------+ +--------+----------+
+ | |
+ | /dev/iommu | /dev/vfio/vfio
+ | /dev/vfio/devices/vfioX | /dev/vfio/$group_id
+ Userspace | |
+ ============+============================+===========================
+ Kernel | device fd |
+ +---------------+ | group/container fd
+ | (BIND_IOMMUFD | | (SET_CONTAINER/SET_IOMMU)
+ | ATTACH_IOAS) | | device fd
+ | | |
+ | +-------V------------V-----------------+
+ iommufd | | vfio |
+ (map/unmap | +---------+--------------------+-------+
+ ioas_copy) | | | map/unmap
+ | | |
+ +------V------+ +-----V------+ +------V--------+
+ | iommfd core | | device | | vfio iommu |
+ +-------------+ +------------+ +---------------+
+
+* Secure Context setup
+
+ - iommufd BE: uses device fd and iommufd to setup secure context
+ (bind_iommufd, attach_ioas)
+ - vfio legacy BE: uses group fd and container fd to setup secure context
+ (set_container, set_iommu)
+
+* Device access
+
+ - iommufd BE: device fd is opened through ``/dev/vfio/devices/vfioX``
+ - vfio legacy BE: device fd is retrieved from group fd ioctl
+
+* DMA Mapping flow
+
+ 1. VFIOAddressSpace receives MemoryRegion add/del via MemoryListener
+ 2. VFIO populates DMA map/unmap via the container BEs
+ * iommufd BE: uses iommufd
+ * vfio legacy BE: uses container fd
+
+Example configuration
+=====================
+
+Step 1: configure the host device
+---------------------------------
+
+It's exactly same as the VFIO device with legacy VFIO container.
+
+Step 2: configure QEMU
+----------------------
+
+Interactions with the ``/dev/iommu`` are abstracted by a new iommufd
+object (compiled in with the ``CONFIG_IOMMUFD`` option).
+
+Any QEMU device (e.g. VFIO device) wishing to use ``/dev/iommu`` must
+be linked with an iommufd object. It gets a new optional property
+named iommufd which allows to pass an iommufd object. Take ``vfio-pci``
+device for example:
+
+.. code-block:: bash
+
+ -object iommufd,id=iommufd0
+ -device vfio-pci,host=0000:02:00.0,iommufd=iommufd0
+
+Note the ``/dev/iommu`` and VFIO cdev can be externally opened by a
+management layer. In such a case the fd is passed, the fd supports a
+string naming the fd or a number, for example:
+
+.. code-block:: bash
+
+ -object iommufd,id=iommufd0,fd=22
+ -device vfio-pci,iommufd=iommufd0,fd=23
+
+If the ``fd`` property is not passed, the fd is opened by QEMU.
+
+If no ``iommufd`` object is passed to the ``vfio-pci`` device, iommufd
+is not used and the user gets the behavior based on the legacy VFIO
+container:
+
+.. code-block:: bash
+
+ -device vfio-pci,host=0000:02:00.0
+
+Supported platform
+==================
+
+Supports x86, ARM and s390x currently.
+
+Caveats
+=======
+
+Dirty page sync
+---------------
+
+Dirty page sync with iommufd backend is unsupported yet, live migration is
+disabled by default. But it can be force enabled like below, low efficient
+though.
+
+.. code-block:: bash
+
+ -object iommufd,id=iommufd0
+ -device vfio-pci,host=0000:02:00.0,iommufd=iommufd0,enable-migration=on
+
+P2P DMA
+-------
+
+PCI p2p DMA is unsupported as IOMMUFD doesn't support mapping hardware PCI
+BAR region yet. Below warning shows for assigned PCI device, it's not a bug.
+
+.. code-block:: none
+
+ qemu-system-x86_64: warning: IOMMU_IOAS_MAP failed: Bad address, PCI BAR?
+ qemu-system-x86_64: vfio_container_dma_map(0x560cb6cb1620, 0xe000000021000, 0x3000, 0x7f32ed55c000) = -14 (Bad address)
+
+FD passing with mdev
+--------------------
+
+``vfio-pci`` device checks sysfsdev property to decide if backend is a mdev.
+If FD passing is used, there is no way to know that and the mdev is treated
+like a real PCI device. There is an error as below if user wants to enable
+RAM discarding for mdev.
+
+.. code-block:: none
+
+ qemu-system-x86_64: -device vfio-pci,iommufd=iommufd0,x-balloon-allowed=on,fd=9: vfio VFIO_FD9: x-balloon-allowed only potentially compatible with mdev devices
+
+``vfio-ap`` and ``vfio-ccw`` devices don't have same issue as their backend
+devices are always mdev and RAM discarding is force enabled.
--
2.39.3

98
kvm-docs-remove-AioContext-lock-from-IOThread-docs.patch
View File

@ -1,98 +0,0 @@
From fc69df3a70bed5722643cc16828ca20beae3a20d Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Tue, 5 Dec 2023 13:20:08 -0500
Subject: [PATCH 091/101] docs: remove AioContext lock from IOThread docs
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 214: Remove AioContext lock
RH-Jira: RHEL-15965
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Commit: [22/26] ab89cda483e74ded983d26e1c6e50217405e0a55 (kmwolf/centos-qemu-kvm)
Encourage the use of locking primitives and stop mentioning the
AioContext lock since it is being removed.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-ID: <20231205182011.1976568-12-stefanha@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
docs/devel/multiple-iothreads.txt | 47 +++++++++++--------------------
1 file changed, 16 insertions(+), 31 deletions(-)
diff --git a/docs/devel/multiple-iothreads.txt b/docs/devel/multiple-iothreads.txt
index a3e949f6b3..4865196bde 100644
--- a/docs/devel/multiple-iothreads.txt
+++ b/docs/devel/multiple-iothreads.txt
@@ -88,27 +88,18 @@ loop, depending on which AioContext instance the caller passes in.
How to synchronize with an IOThread
-----------------------------------
-AioContext is not thread-safe so some rules must be followed when using file
-descriptors, event notifiers, timers, or BHs across threads:
+Variables that can be accessed by multiple threads require some form of
+synchronization such as qemu_mutex_lock(), rcu_read_lock(), etc.
-1. AioContext functions can always be called safely. They handle their
-own locking internally.
-
-2. Other threads wishing to access the AioContext must use
-aio_context_acquire()/aio_context_release() for mutual exclusion. Once the
-context is acquired no other thread can access it or run event loop iterations
-in this AioContext.
-
-Legacy code sometimes nests aio_context_acquire()/aio_context_release() calls.
-Do not use nesting anymore, it is incompatible with the BDRV_POLL_WHILE() macro
-used in the block layer and can lead to hangs.
-
-There is currently no lock ordering rule if a thread needs to acquire multiple
-AioContexts simultaneously. Therefore, it is only safe for code holding the
-QEMU global mutex to acquire other AioContexts.
+AioContext functions like aio_set_fd_handler(), aio_set_event_notifier(),
+aio_bh_new(), and aio_timer_new() are thread-safe. They can be used to trigger
+activity in an IOThread.
Side note: the best way to schedule a function call across threads is to call
-aio_bh_schedule_oneshot(). No acquire/release or locking is needed.
+aio_bh_schedule_oneshot().
+
+The main loop thread can wait synchronously for a condition using
+AIO_WAIT_WHILE().
AioContext and the block layer
------------------------------
@@ -124,22 +115,16 @@ Block layer code must therefore expect to run in an IOThread and avoid using
old APIs that implicitly use the main loop. See the "How to program for
IOThreads" above for information on how to do that.
-If main loop code such as a QMP function wishes to access a BlockDriverState
-it must first call aio_context_acquire(bdrv_get_aio_context(bs)) to ensure
-that callbacks in the IOThread do not run in parallel.
-
Code running in the monitor typically needs to ensure that past
requests from the guest are completed. When a block device is running
in an IOThread, the IOThread can also process requests from the guest
(via ioeventfd). To achieve both objects, wrap the code between
bdrv_drained_begin() and bdrv_drained_end(), thus creating a "drained
-section". The functions must be called between aio_context_acquire()
-and aio_context_release(). You can freely release and re-acquire the
-AioContext within a drained section.
-
-Long-running jobs (usually in the form of coroutines) are best scheduled in
-the BlockDriverState's AioContext to avoid the need to acquire/release around
-each bdrv_*() call. The functions bdrv_add/remove_aio_context_notifier,
-or alternatively blk_add/remove_aio_context_notifier if you use BlockBackends,
-can be used to get a notification whenever bdrv_try_change_aio_context() moves a
+section".
+
+Long-running jobs (usually in the form of coroutines) are often scheduled in
+the BlockDriverState's AioContext. The functions
+bdrv_add/remove_aio_context_notifier, or alternatively
+blk_add/remove_aio_context_notifier if you use BlockBackends, can be used to
+get a notification whenever bdrv_try_change_aio_context() moves a
BlockDriverState to a different AioContext.
--
2.39.3

1190
kvm-graph-lock-remove-AioContext-locking.patch
View File

File diff suppressed because it is too large Load Diff

94
kvm-hv-balloon-use-get_min_alignment-to-express-32-GiB-a.patch
View File

@ -1,94 +0,0 @@
From a5b4eec5f456b1ca3fe753e1d76f96cf3f8914ef Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Wed, 17 Jan 2024 14:55:53 +0100
Subject: [PATCH 01/22] hv-balloon: use get_min_alignment() to express 32 GiB
alignment
RH-Author: David Hildenbrand <david@redhat.com>
RH-MergeRequest: 221: memory-device: reintroduce memory region size check
RH-Jira: RHEL-20341
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Igor Mammedov <imammedo@redhat.com>
RH-Commit: [1/2] cbe092fe549552928270892253b31cd8fe199825
https://issues.redhat.com/browse/RHEL-20341
Let's implement the get_min_alignment() callback for memory devices, and
copy for the device memory region the alignment of the host memory
region. This mimics what virtio-mem does, and allows for re-introducing
proper alignment checks for the memory region size (where we don't care
about additional device requirements) in memory device core.
Message-ID: <20240117135554.787344-2-david@redhat.com>
Reviewed-by: Maciej S. Szmigiero <maciej.szmigiero@oracle.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
(cherry picked from commit f77c5f38f49c71bc14cf1019ac92b0b95f572414)
Signed-off-by: David Hildenbrand <david@redhat.com>
---
hw/hyperv/hv-balloon.c | 37 +++++++++++++++++++++----------------
1 file changed, 21 insertions(+), 16 deletions(-)
diff --git a/hw/hyperv/hv-balloon.c b/hw/hyperv/hv-balloon.c
index 66f297c1d7..0829c495b0 100644
--- a/hw/hyperv/hv-balloon.c
+++ b/hw/hyperv/hv-balloon.c
@@ -1476,22 +1476,7 @@ static void hv_balloon_ensure_mr(HvBalloon *balloon)
balloon->mr = g_new0(MemoryRegion, 1);
memory_region_init(balloon->mr, OBJECT(balloon), TYPE_HV_BALLOON,
memory_region_size(hostmem_mr));
-
- /*
- * The VM can indicate an alignment up to 32 GiB. Memory device core can
- * usually only handle/guarantee 1 GiB alignment. The user will have to
- * specify a larger maxmem eventually.
- *
- * The memory device core will warn the user in case maxmem might have to be
- * increased and will fail plugging the device if there is not sufficient
- * space after alignment.
- *
- * TODO: we could do the alignment ourselves in a slightly bigger region.
- * But this feels better, although the warning might be annoying. Maybe
- * we can optimize that in the future (e.g., with such a device on the
- * cmdline place/size the device memory region differently.
- */
- balloon->mr->align = MAX(32 * GiB, memory_region_get_alignment(hostmem_mr));
+ balloon->mr->align = memory_region_get_alignment(hostmem_mr);
}
static void hv_balloon_free_mr(HvBalloon *balloon)
@@ -1653,6 +1638,25 @@ static MemoryRegion *hv_balloon_md_get_memory_region(MemoryDeviceState *md,
return balloon->mr;
}
+static uint64_t hv_balloon_md_get_min_alignment(const MemoryDeviceState *md)
+{
+ /*
+ * The VM can indicate an alignment up to 32 GiB. Memory device core can
+ * usually only handle/guarantee 1 GiB alignment. The user will have to
+ * specify a larger maxmem eventually.
+ *
+ * The memory device core will warn the user in case maxmem might have to be
+ * increased and will fail plugging the device if there is not sufficient
+ * space after alignment.
+ *
+ * TODO: we could do the alignment ourselves in a slightly bigger region.
+ * But this feels better, although the warning might be annoying. Maybe
+ * we can optimize that in the future (e.g., with such a device on the
+ * cmdline place/size the device memory region differently.
+ */
+ return 32 * GiB;
+}
+
static void hv_balloon_md_fill_device_info(const MemoryDeviceState *md,
MemoryDeviceInfo *info)
{
@@ -1765,5 +1769,6 @@ static void hv_balloon_class_init(ObjectClass *klass, void *data)
mdc->get_memory_region = hv_balloon_md_get_memory_region;
mdc->decide_memslots = hv_balloon_decide_memslots;
mdc->get_memslots = hv_balloon_get_memslots;
+ mdc->get_min_alignment = hv_balloon_md_get_min_alignment;
mdc->fill_device_info = hv_balloon_md_fill_device_info;
}
--
2.39.3

42
kvm-hw-arm-Activate-IOMMUFD-for-virt-machines.patch
View File

@ -1,42 +0,0 @@
From ceaee9c4372bbdc4196cb6808515047388f7aa26 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= <clg@redhat.com>
Date: Tue, 21 Nov 2023 16:44:18 +0800
Subject: [PATCH 039/101] hw/arm: Activate IOMMUFD for virt machines
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 211: IOMMUFD backend backport
RH-Jira: RHEL-19302 RHEL-21057
RH-Acked-by: Cédric Le Goater <clg@redhat.com>
RH-Acked-by: Sebastian Ott <sebott@redhat.com>
RH-Commit: [38/67] 0a059ae661616e95eb8455e17f35774495cae8e7 (eauger1/centos-qemu-kvm)
Signed-off-by: Cédric Le Goater <clg@redhat.com>
Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Tested-by: Eric Auger <eric.auger@redhat.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Cédric Le Goater <clg@redhat.com>
(cherry picked from commit 0970238343af45a8b547695bfc22f18d4eb7da7e)
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
hw/arm/Kconfig | 1 +
1 file changed, 1 insertion(+)
diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig
index 3ada335a24..660f49db49 100644
--- a/hw/arm/Kconfig
+++ b/hw/arm/Kconfig
@@ -8,6 +8,7 @@ config ARM_VIRT
imply TPM_TIS_SYSBUS
imply TPM_TIS_I2C
imply NVDIMM
+ imply IOMMUFD
select ARM_GIC
select ACPI
select ARM_SMMUV3
--
2.39.3

88
kvm-hw-arm-virt-Add-properties-to-disable-high-memory-re.patch
View File

@ -1,88 +0,0 @@
From e670722b9a6460d41497688d820d5a9a9b51d8e9 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Tue, 9 Jan 2024 11:36:42 +1000
Subject: [PATCH 001/101] hw/arm/virt: Add properties to disable high memory
regions
RH-Author: Gavin Shan <gshan@redhat.com>
RH-MergeRequest: 210: hw/arm/virt: Add properties to disable high memory regions
RH-Jira: RHEL-19738
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Commit: [1/1] 4097ba5133a67126e30b84202cb40df4e019c5f4
Upstream: RHEL-only
Brew: https://brewweb.engineering.redhat.com/brew/taskinfo?taskID=57927352
There are 3 high memory regions for GICv3 or GICv4 redistributor, PCI
ECAM and PCI MMIO. Each of them has a property introduced by upstream
commit 6a48c64eec ("hw/arm/virt: Add properties to disable high memory
regions") so that the corresponding high memory region can be disabled.
It's notable that another property ("compact-highmem") introduced by
upstream commit f40408a9fe ("hw/arm/virt: Add 'compact-highmem' property")
so that the compact high memory region layout during assignment can be
disabled, compatible to the old machine types. However, we don't have
the compatible issue since the compact high memory region layout is
always kept as disabled until RHEL9.2.0 machine type and onwards.
Expose those 3 properties: "highmem-redists", "highmem-ecam" and
"highmem-mmio". The property "compact-highmem" is kept as hidden.
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
hw/arm/virt.c | 24 +++++++++++++++++++++++-
1 file changed, 23 insertions(+), 1 deletion(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 5cab00b4cd..60f117f0d2 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -2456,6 +2456,7 @@ static void virt_set_compact_highmem(Object *obj, bool value, Error **errp)
vms->highmem_compact = value;
}
+#endif /* disabled for RHEL */
static bool virt_get_highmem_redists(Object *obj, Error **errp)
{
@@ -2498,7 +2499,6 @@ static void virt_set_highmem_mmio(Object *obj, bool value, Error **errp)
vms->highmem_mmio = value;
}
-#endif /* disabled for RHEL */
static bool virt_get_its(Object *obj, Error **errp)
{
@@ -3521,6 +3521,28 @@ static void rhel_machine_class_init(ObjectClass *oc, void *data)
"Set on/off to enable/disable using "
"physical address space above 32 bits");
+ object_class_property_add_bool(oc, "highmem-redists",
+ virt_get_highmem_redists,
+ virt_set_highmem_redists);
+ object_class_property_set_description(oc, "highmem-redists",
+ "Set on/off to enable/disable high "
+ "memory region for GICv3 or GICv4 "
+ "redistributor");
+
+ object_class_property_add_bool(oc, "highmem-ecam",
+ virt_get_highmem_ecam,
+ virt_set_highmem_ecam);
+ object_class_property_set_description(oc, "highmem-ecam",
+ "Set on/off to enable/disable high "
+ "memory region for PCI ECAM");
+
+ object_class_property_add_bool(oc, "highmem-mmio",
+ virt_get_highmem_mmio,
+ virt_set_highmem_mmio);
+ object_class_property_set_description(oc, "highmem-mmio",
+ "Set on/off to enable/disable high "
+ "memory region 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",
--
2.39.3

132
kvm-hw-arm-virt-Fix-compats.patch
View File

@ -1,132 +0,0 @@
From 3f58194f8642a71c47d91d3c00a34faf44ea2c11 Mon Sep 17 00:00:00 2001
From: Eric Auger <eric.auger@redhat.com>
Date: Wed, 3 Jan 2024 05:57:38 -0500
Subject: [PATCH] hw/arm/virt: Fix compats
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 209: hw/arm/virt: Fix compats
RH-Jira: RHEL-17168
RH-Acked-by: Gavin Shan <gshan@redhat.com>
RH-Acked-by: Sebastian Ott <sebott@redhat.com>
RH-Commit: [1/1] bcdf6493bbd6d7b52b0b88ff44441d22aeddfde2 (eauger1/centos-qemu-kvm)
arm_rhel_compat is not added for virt-rhel9.4.0 machine causing
the efi-virtio.rom to be looked for when instantiating a virtio-net-pci
device and it won't be found since not shipped on ARM. This is a
regression compared to 9.2.
Actually we do not need any rom file for any virtio-net-pci variant
because edk2 already brings the functionality. So for 9.4 onwards, we
want to set romfiles to "" for all of them.
However at the moment we apply arm_rhel_compat from the latest
rhel*_virt_options(). This is not aligned with the generic compat
usage which sets compats for a given machine type to accomodate for
changes that occured after its advent. Here we are somehow abusing
the compat infra to set general driver options that should apply for
all machines. On top of that this is really error prone and we have
forgotten to add arm_rhel_compat several times in the past.
So let's introduce set_arm_rhel_compat() being called before any
*virt_options in the non abstract machine class. That way the setting
will apply to any machine type without any need to add it in any
future machine types.
For < 9.4 machines we don't really care keeping non void romfiles
for transitional and non transitional devices because anyway this was
not working. So let's keep things simple and apply the new defaults for
all RHEL9 machine types.
Finally, to follow the generic pattern we should set hw_compat_rhel_9_0
in 9.0 machine as it is done on x86 or ccw. This has no consequence on
aarch64 because it only contains x86 stuff but that helps understanding
the consistency.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
hw/arm/virt.c | 43 +++++++++++++++++++++++++++++--------------
1 file changed, 29 insertions(+), 14 deletions(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 0b17c94ad7..5cab00b4cd 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -111,11 +111,39 @@
DEFINE_VIRT_MACHINE_LATEST(major, minor, false)
#endif /* disabled for RHEL */
+/*
+ * This variable is for changes to properties that are RHEL specific,
+ * different to the current upstream and to be applied to the latest
+ * machine type. They may be overriden by older machine compats.
+ *
+ * virtio-net-pci variant romfiles are not needed because edk2 does
+ * fully support the pxe boot. Besides virtio romfiles are not shipped
+ * on rhel/aarch64.
+ */
+GlobalProperty arm_rhel_compat[] = {
+ {"virtio-net-pci", "romfile", "" },
+ {"virtio-net-pci-transitional", "romfile", "" },
+ {"virtio-net-pci-non-transitional", "romfile", "" },
+};
+const size_t arm_rhel_compat_len = G_N_ELEMENTS(arm_rhel_compat);
+
+/*
+ * This cannot be called from the rhel_virt_class_init() because
+ * TYPE_RHEL_MACHINE is abstract and mc->compat_props g_ptr_array_new()
+ * only is called on virt-rhelm.n.s non abstract class init.
+ */
+static void arm_rhel_compat_set(MachineClass *mc)
+{
+ compat_props_add(mc->compat_props, arm_rhel_compat,
+ arm_rhel_compat_len);
+}
+
#define DEFINE_RHEL_MACHINE_LATEST(m, n, s, latest) \
static void rhel##m##n##s##_virt_class_init(ObjectClass *oc, \
void *data) \
{ \
MachineClass *mc = MACHINE_CLASS(oc); \
+ arm_rhel_compat_set(mc); \
rhel##m##n##s##_virt_options(mc); \
mc->desc = "RHEL " # m "." # n "." # s " ARM Virtual Machine"; \
if (latest) { \
@@ -139,19 +167,6 @@
#define DEFINE_RHEL_MACHINE(major, minor, subminor) \
DEFINE_RHEL_MACHINE_LATEST(major, minor, subminor, false)
-/* This variable is for changes to properties that are RHEL specific,
- * different to the current upstream and to be applied to the latest
- * machine type.
- */
-GlobalProperty arm_rhel_compat[] = {
- {
- .driver = "virtio-net-pci",
- .property = "romfile",
- .value = "",
- },
-};
-const size_t arm_rhel_compat_len = G_N_ELEMENTS(arm_rhel_compat);
-
/* Number of external interrupt lines to configure the GIC with */
#define NUM_IRQS 256
@@ -3639,7 +3654,6 @@ static void rhel920_virt_options(MachineClass *mc)
{
rhel940_virt_options(mc);
- compat_props_add(mc->compat_props, arm_rhel_compat, arm_rhel_compat_len);
compat_props_add(mc->compat_props, hw_compat_rhel_9_4, hw_compat_rhel_9_4_len);
compat_props_add(mc->compat_props, hw_compat_rhel_9_3, hw_compat_rhel_9_3_len);
compat_props_add(mc->compat_props, hw_compat_rhel_9_2, hw_compat_rhel_9_2_len);
@@ -3653,6 +3667,7 @@ static void rhel900_virt_options(MachineClass *mc)
rhel920_virt_options(mc);
compat_props_add(mc->compat_props, hw_compat_rhel_9_1, hw_compat_rhel_9_1_len);
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_0, hw_compat_rhel_9_0_len);
/* Disable FEAT_LPA2 since old kernels (<= v5.12) don't boot with that feature */
vmc->no_tcg_lpa2 = true;
--
2.39.3

41
kvm-hw-arm-virt-deprecate-virt-rhel9.-0-2-.0-machine-typ.patch
View File

@ -1,41 +0,0 @@
From 4c1d07995a7afb6fae68a7e7a8b6b6c94fa0a7bb Mon Sep 17 00:00:00 2001
From: Cornelia Huck <cohuck@redhat.com>
Date: Mon, 12 Feb 2024 10:37:54 +0100
Subject: [PATCH 5/6] hw/arm/virt: deprecate virt-rhel9.{0,2}.0 machine types
RH-Author: Cornelia Huck <cohuck@redhat.com>
RH-MergeRequest: 225: hw/arm/virt: deprecate virt-rhel9.{0,2}.0 machine types
RH-Jira: RHEL-24988
RH-Acked-by: Sebastian Ott <sebott@redhat.com>
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Commit: [1/1] f15579db44808fa8a2d7bc01b3915aa59c064411 (cohuck/qemu-kvm-c9s)
Jira: https://issues.redhat.com/browse/RHEL-24988
Upstream: RHEL only
We do not plan to support any machine types prior to 9.4.0; leave them
in, but mark as deprecated.
Signed-off-by: Cornelia Huck <cohuck@redhat.com>
---
hw/arm/virt.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 60f117f0d2..943c563391 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -3679,6 +3679,10 @@ static void rhel920_virt_options(MachineClass *mc)
compat_props_add(mc->compat_props, hw_compat_rhel_9_4, hw_compat_rhel_9_4_len);
compat_props_add(mc->compat_props, hw_compat_rhel_9_3, hw_compat_rhel_9_3_len);
compat_props_add(mc->compat_props, hw_compat_rhel_9_2, hw_compat_rhel_9_2_len);
+
+ /* RHEL 9.4 is the first supported release */
+ mc->deprecation_reason =
+ "machine types for versions prior to 9.4 are deprecated";
}
DEFINE_RHEL_MACHINE(9, 2, 0)
--
2.39.3

41
kvm-hw-i386-Activate-IOMMUFD-for-q35-machines.patch
View File

@ -1,41 +0,0 @@
From 7a6be312c11911bdd2ce82566be22a3e014947c2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= <clg@redhat.com>
Date: Tue, 21 Nov 2023 16:44:20 +0800
Subject: [PATCH 041/101] hw/i386: Activate IOMMUFD for q35 machines
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 211: IOMMUFD backend backport
RH-Jira: RHEL-19302 RHEL-21057
RH-Acked-by: Cédric Le Goater <clg@redhat.com>
RH-Acked-by: Sebastian Ott <sebott@redhat.com>
RH-Commit: [40/67] b15764ab24fd57389a8d219736613484acd7d29e (eauger1/centos-qemu-kvm)
Signed-off-by: Cédric Le Goater <clg@redhat.com>
Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Cédric Le Goater <clg@redhat.com>
(cherry picked from commit 64ad06f6eba66c514477f490bcba409439a480d8)
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
hw/i386/Kconfig | 1 +
1 file changed, 1 insertion(+)
diff --git a/hw/i386/Kconfig b/hw/i386/Kconfig
index 55850791df..a1846be6f7 100644
--- a/hw/i386/Kconfig
+++ b/hw/i386/Kconfig
@@ -95,6 +95,7 @@ config Q35
imply E1000E_PCI_EXPRESS
imply VMPORT
imply VMMOUSE
+ imply IOMMUFD
select PC_PCI
select PC_ACPI
select PCI_EXPRESS_Q35
--
2.39.3

186
kvm-hw-i386-pc-Defer-smbios_set_defaults-to-machine_done.patch
View File

@ -1,186 +0,0 @@
From ea2e2368dcf4140be47288472f2c2a094358e0c7 Mon Sep 17 00:00:00 2001
From: Igor Mammedov <imammedo@redhat.com>
Date: Thu, 8 Feb 2024 23:03:45 +0100
Subject: [PATCH 03/20] hw/i386/pc: Defer smbios_set_defaults() to machine_done
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Igor Mammedov <imammedo@redhat.com>
RH-MergeRequest: 230: Workaround Windows failing to find 64bit SMBIOS entry point with SeaBIOS
RH-Jira: RHEL-21705
RH-Acked-by: MST <mst@redhat.com>
RH-Acked-by: Ani Sinha <None>
RH-Commit: [1/18] 9d4c1d1a910fec7d310429d6fc0b10c798932db7
JIRA: https://issues.redhat.com/browse/RHEL-21705
commit: a0204a5ed091dfe79aced7ec8f3ce1931fd25816
Author: Bernhard Beschow <shentey@gmail.com>
Handling most of smbios data generation in the machine_done notifier is similar
to how the ARM virt machine handles it which also calls smbios_set_defaults()
there. The result is that all pc machines are freed from explicitly worrying
about smbios setup.
Signed-off-by: Bernhard Beschow <shentey@gmail.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-ID: <20240208220349.4948-6-shentey@gmail.com>
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Conflicts: hw/i386/pc_q35.c, hw/i386/pc_piix.c
due to missing 4d3457fef9 (w/i386/pc: Merge pc_guest_info_init() into pc_machine_initfn())
and different signature of smbios_set_defaults() downstream
Fixup: hw/i386/fw_cfg.c to account for downstream changes smbios_set_defaults()
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
---
hw/i386/fw_cfg.c | 14 +++++++++++++-
hw/i386/fw_cfg.h | 3 ++-
hw/i386/pc.c | 2 +-
hw/i386/pc_piix.c | 12 ------------
hw/i386/pc_q35.c | 11 -----------
include/hw/i386/pc.h | 1 -
6 files changed, 16 insertions(+), 27 deletions(-)
diff --git a/hw/i386/fw_cfg.c b/hw/i386/fw_cfg.c
index 7362daa45a..6a5466faf0 100644
--- a/hw/i386/fw_cfg.c
+++ b/hw/i386/fw_cfg.c
@@ -48,15 +48,27 @@ const char *fw_cfg_arch_key_name(uint16_t key)
return NULL;
}
-void fw_cfg_build_smbios(MachineState *ms, FWCfgState *fw_cfg)
+void fw_cfg_build_smbios(PCMachineState *pcms, FWCfgState *fw_cfg)
{
#ifdef CONFIG_SMBIOS
uint8_t *smbios_tables, *smbios_anchor;
size_t smbios_tables_len, smbios_anchor_len;
struct smbios_phys_mem_area *mem_array;
unsigned i, array_count;
+ MachineState *ms = MACHINE(pcms);
+ PCMachineClass *pcmc = PC_MACHINE_GET_CLASS(pcms);
+ MachineClass *mc = MACHINE_GET_CLASS(pcms);
X86CPU *cpu = X86_CPU(ms->possible_cpus->cpus[0].cpu);
+ if (pcmc->smbios_defaults) {
+ /* These values are guest ABI, do not change */
+ smbios_set_defaults("QEMU", mc->desc, mc->name,
+ pcmc->smbios_legacy_mode, pcmc->smbios_uuid_encoded,
+ pcmc->smbios_stream_product,
+ pcmc->smbios_stream_version,
+ pcms->smbios_entry_point_type);
+ }
+
/* tell smbios about cpuid version and features */
smbios_set_cpuid(cpu->env.cpuid_version, cpu->env.features[FEAT_1_EDX]);
diff --git a/hw/i386/fw_cfg.h b/hw/i386/fw_cfg.h
index 86ca7c1c0c..1e1de6b4a3 100644
--- a/hw/i386/fw_cfg.h
+++ b/hw/i386/fw_cfg.h
@@ -10,6 +10,7 @@
#define HW_I386_FW_CFG_H
#include "hw/boards.h"
+#include "hw/i386/pc.h"
#include "hw/nvram/fw_cfg.h"
#define FW_CFG_IO_BASE 0x510
@@ -22,7 +23,7 @@
FWCfgState *fw_cfg_arch_create(MachineState *ms,
uint16_t boot_cpus,
uint16_t apic_id_limit);
-void fw_cfg_build_smbios(MachineState *ms, FWCfgState *fw_cfg);
+void fw_cfg_build_smbios(PCMachineState *ms, FWCfgState *fw_cfg);
void fw_cfg_build_feature_control(MachineState *ms, FWCfgState *fw_cfg);
void fw_cfg_add_acpi_dsdt(Aml *scope, FWCfgState *fw_cfg);
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index a1faa9e92c..16de2a59e8 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -847,7 +847,7 @@ void pc_machine_done(Notifier *notifier, void *data)
acpi_setup();
if (x86ms->fw_cfg) {
- fw_cfg_build_smbios(MACHINE(pcms), x86ms->fw_cfg);
+ fw_cfg_build_smbios(pcms, x86ms->fw_cfg);
fw_cfg_build_feature_control(MACHINE(pcms), x86ms->fw_cfg);
/* update FW_CFG_NB_CPUS to account for -device added CPUs */
fw_cfg_modify_i16(x86ms->fw_cfg, FW_CFG_NB_CPUS, x86ms->boot_cpus);
diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index 09d02cc91f..7344b35cf1 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -36,7 +36,6 @@
#include "hw/rtc/mc146818rtc.h"
#include "hw/southbridge/piix.h"
#include "hw/display/ramfb.h"
-#include "hw/firmware/smbios.h"
#include "hw/pci/pci.h"
#include "hw/pci/pci_ids.h"
#include "hw/usb.h"
@@ -233,17 +232,6 @@ static void pc_init1(MachineState *machine,
pc_guest_info_init(pcms);
- if (pcmc->smbios_defaults) {
- MachineClass *mc = MACHINE_GET_CLASS(machine);
- /* These values are guest ABI, do not change */
- smbios_set_defaults("Red Hat", "KVM",
- mc->desc, pcmc->smbios_legacy_mode,
- pcmc->smbios_uuid_encoded,
- pcmc->smbios_stream_product,
- pcmc->smbios_stream_version,
- pcms->smbios_entry_point_type);
- }
-
/* allocate ram and load rom/bios */
if (!xen_enabled()) {
pc_memory_init(pcms, system_memory, rom_memory, hole64_size);
diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index c6967e1846..9a22ff5dd6 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -45,7 +45,6 @@
#include "hw/i386/amd_iommu.h"
#include "hw/i386/intel_iommu.h"
#include "hw/display/ramfb.h"
-#include "hw/firmware/smbios.h"
#include "hw/ide/pci.h"
#include "hw/ide/ahci.h"
#include "hw/intc/ioapic.h"
@@ -201,16 +200,6 @@ static void pc_q35_init(MachineState *machine)
pc_guest_info_init(pcms);
- if (pcmc->smbios_defaults) {
- /* These values are guest ABI, do not change */
- smbios_set_defaults("Red Hat", "KVM",
- mc->desc, pcmc->smbios_legacy_mode,
- pcmc->smbios_uuid_encoded,
- pcmc->smbios_stream_product,
- pcmc->smbios_stream_version,
- pcms->smbios_entry_point_type);
- }
-
/* create pci host bus */
phb = OBJECT(qdev_new(TYPE_Q35_HOST_DEVICE));
diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h
index 37644ede7e..c286c10bc3 100644
--- a/include/hw/i386/pc.h
+++ b/include/hw/i386/pc.h
@@ -12,7 +12,6 @@
#include "hw/hotplug.h"
#include "qom/object.h"
#include "hw/i386/sgx-epc.h"
-#include "hw/firmware/smbios.h"
#include "hw/cxl/cxl.h"
#define HPET_INTCAP "hpet-intcap"
--
2.39.3

116
kvm-hw-ppc-Kconfig-Imply-VFIO_PCI.patch
View File

@ -1,116 +0,0 @@
From 84f378c41832602dcf9bad6167b1f532c7c53e37 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= <clg@redhat.com>
Date: Tue, 21 Nov 2023 15:03:55 +0100
Subject: [PATCH 048/101] hw/ppc/Kconfig: Imply VFIO_PCI
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 211: IOMMUFD backend backport
RH-Jira: RHEL-19302 RHEL-21057
RH-Acked-by: Cédric Le Goater <clg@redhat.com>
RH-Acked-by: Sebastian Ott <sebott@redhat.com>
RH-Commit: [47/67] c1a40cdab9bf62b16cb428d57a20b3e0eaa6de38 (eauger1/centos-qemu-kvm)
When the legacy and iommufd backends were introduced, a set of common
vfio-pci routines were exported in pci.c for both backends to use :
vfio_pci_pre_reset
vfio_pci_get_pci_hot_reset_info
vfio_pci_host_match
vfio_pci_post_reset
This introduced a build failure on PPC when --without-default-devices
is use because VFIO is always selected in ppc/Kconfig but VFIO_PCI is
not.
Use an 'imply VFIO_PCI' in ppc/Kconfig and bypass compilation of the
VFIO EEH hooks routines defined in hw/ppc/spapr_pci_vfio.c with
CONFIG_VFIO_PCI.
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Signed-off-by: Cédric Le Goater <clg@redhat.com>
(cherry picked from commit 4278df9d1d2383b738338c857406357660f11e42)
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
hw/ppc/Kconfig | 2 +-
hw/ppc/spapr_pci_vfio.c | 36 ++++++++++++++++++++++++++++++++++++
2 files changed, 37 insertions(+), 1 deletion(-)
diff --git a/hw/ppc/Kconfig b/hw/ppc/Kconfig
index 56f0475a8e..44263a58c4 100644
--- a/hw/ppc/Kconfig
+++ b/hw/ppc/Kconfig
@@ -3,11 +3,11 @@ config PSERIES
imply PCI_DEVICES
imply TEST_DEVICES
imply VIRTIO_VGA
+ imply VFIO_PCI if LINUX # needed by spapr_pci_vfio.c
select NVDIMM
select DIMM
select PCI
select SPAPR_VSCSI
- select VFIO if LINUX # needed by spapr_pci_vfio.c
select XICS
select XIVE
select MSI_NONBROKEN
diff --git a/hw/ppc/spapr_pci_vfio.c b/hw/ppc/spapr_pci_vfio.c
index d1d07bec46..76b2a3487b 100644
--- a/hw/ppc/spapr_pci_vfio.c
+++ b/hw/ppc/spapr_pci_vfio.c
@@ -26,10 +26,12 @@
#include "hw/pci/pci_device.h"
#include "hw/vfio/vfio-common.h"
#include "qemu/error-report.h"
+#include CONFIG_DEVICES /* CONFIG_VFIO_PCI */
/*
* Interfaces for IBM EEH (Enhanced Error Handling)
*/
+#ifdef CONFIG_VFIO_PCI
static bool vfio_eeh_container_ok(VFIOContainer *container)
{
/*
@@ -314,3 +316,37 @@ int spapr_phb_vfio_eeh_configure(SpaprPhbState *sphb)
return RTAS_OUT_SUCCESS;
}
+
+#else
+
+bool spapr_phb_eeh_available(SpaprPhbState *sphb)
+{
+ return false;
+}
+
+void spapr_phb_vfio_reset(DeviceState *qdev)
+{
+}
+
+int spapr_phb_vfio_eeh_set_option(SpaprPhbState *sphb,
+ unsigned int addr, int option)
+{
+ return RTAS_OUT_NOT_SUPPORTED;
+}
+
+int spapr_phb_vfio_eeh_get_state(SpaprPhbState *sphb, int *state)
+{
+ return RTAS_OUT_NOT_SUPPORTED;
+}
+
+int spapr_phb_vfio_eeh_reset(SpaprPhbState *sphb, int option)
+{
+ return RTAS_OUT_NOT_SUPPORTED;
+}
+
+int spapr_phb_vfio_eeh_configure(SpaprPhbState *sphb)
+{
+ return RTAS_OUT_NOT_SUPPORTED;
+}
+
+#endif /* CONFIG_VFIO_PCI */
--
2.39.3

73
kvm-hw-vfio-fix-iteration-over-global-VFIODevice-list.patch
View File

@ -1,73 +0,0 @@
From 8f27893a37e55a31180bb66cd9eae7199911881b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Volker=20R=C3=BCmelin?= <vr_qemu@t-online.de>
Date: Fri, 29 Dec 2023 21:38:54 +0100
Subject: [PATCH 060/101] hw/vfio: fix iteration over global VFIODevice list
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 211: IOMMUFD backend backport
RH-Jira: RHEL-19302 RHEL-21057
RH-Acked-by: Cédric Le Goater <clg@redhat.com>
RH-Acked-by: Sebastian Ott <sebott@redhat.com>
RH-Commit: [59/67] f926e1233c8c5ad418e8794b1a103371c9dc5eb0 (eauger1/centos-qemu-kvm)
Commit 3d779abafe ("vfio/common: Introduce a global VFIODevice list")
introduced a global VFIODevice list, but forgot to update the list
element field name when iterating over the new list. Change the code
to use the correct list element field.
Fixes: 3d779abafe ("vfio/common: Introduce a global VFIODevice list")
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/2061
Signed-off-by: Volker Rümelin <vr_qemu@t-online.de>
Reviewed-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
(cherry picked from commit 9353b6da430f90e47f352dbf6dc31120c8914da6)
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
hw/vfio/common.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index 0d4d8b8416..0b3352f2a9 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -73,7 +73,7 @@ bool vfio_mig_active(void)
return false;
}
- QLIST_FOREACH(vbasedev, &vfio_device_list, next) {
+ QLIST_FOREACH(vbasedev, &vfio_device_list, global_next) {
if (vbasedev->migration_blocker) {
return false;
}
@@ -94,7 +94,7 @@ static bool vfio_multiple_devices_migration_is_supported(void)
unsigned int device_num = 0;
bool all_support_p2p = true;
- QLIST_FOREACH(vbasedev, &vfio_device_list, next) {
+ QLIST_FOREACH(vbasedev, &vfio_device_list, global_next) {
if (vbasedev->migration) {
device_num++;
@@ -1366,13 +1366,13 @@ void vfio_reset_handler(void *opaque)
{
VFIODevice *vbasedev;
- QLIST_FOREACH(vbasedev, &vfio_device_list, next) {
+ QLIST_FOREACH(vbasedev, &vfio_device_list, global_next) {
if (vbasedev->dev->realized) {
vbasedev->ops->vfio_compute_needs_reset(vbasedev);
}
}
- QLIST_FOREACH(vbasedev, &vfio_device_list, next) {
+ QLIST_FOREACH(vbasedev, &vfio_device_list, global_next) {
if (vbasedev->dev->realized && vbasedev->needs_reset) {
vbasedev->ops->vfio_hot_reset_multi(vbasedev);
}
--
2.39.3

54
kvm-include-ui-rect.h-fix-qemu_rect_init-mis-assignment.patch
View File

@ -1,54 +0,0 @@
From 51b8f29cddb73eb02f91af5f52a205fdd3af6583 Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Wed, 17 Jan 2024 21:08:59 +0100
Subject: [PATCH 099/101] include/ui/rect.h: fix qemu_rect_init()
mis-assignment
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Thomas Huth <thuth@redhat.com>
RH-MergeRequest: 216: Fix regression in QEMU's virtio-gpu VNC sessions
RH-Jira: RHEL-21570
RH-Acked-by: Marc-André Lureau <marcandre.lureau@redhat.com>
RH-Acked-by: Cédric Le Goater <clg@redhat.com>
RH-Commit: [1/1] a9d487be04e2c1847b80c479b5cc790af81e3428 (thuth/qemu-kvm-cs9)
JIRA: https://issues.redhat.com/browse/RHEL-21570
commit 9d5b42beb6978dc6219d5dc029c9d453c6b8d503
Author: Elen Avan <elen.avan@bk.ru>
Date: Fri Dec 22 22:17:21 2023 +0300
include/ui/rect.h: fix qemu_rect_init() mis-assignment
Signed-off-by: Elen Avan <elen.avan@bk.ru>
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/2051
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/2050
Fixes: a200d53b1fde "virtio-gpu: replace PIXMAN for region/rect test"
Cc: qemu-stable@nongnu.org
Reviewed-by: Michael Tokarev <mjt@tls.msk.ru>
Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>
Signed-off-by: Thomas Huth <thuth@redhat.com>
---
include/ui/rect.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/include/ui/rect.h b/include/ui/rect.h
index 94898f92d0..68f05d78a8 100644
--- a/include/ui/rect.h
+++ b/include/ui/rect.h
@@ -19,7 +19,7 @@ static inline void qemu_rect_init(QemuRect *rect,
uint16_t width, uint16_t height)
{
rect->x = x;
- rect->y = x;
+ rect->y = y;
rect->width = width;
rect->height = height;
}
--
2.39.3

133
kvm-iotests-Add-test-for-reset-AioContext-switches-with-.patch
View File

@ -1,133 +0,0 @@
From 65d58819ff7b012e43b5f1da1356b559d3f5a962 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Thu, 14 Mar 2024 17:58:25 +0100
Subject: [PATCH 3/4] iotests: Add test for reset/AioContext switches with NBD
exports
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 231: Fix deadlock and crash during storage migration
RH-Jira: RHEL-28125
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Eric Blake <eblake@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Commit: [3/3] 7266acdf85271d157497bfe452aa6eeb58fbe7c6 (kmwolf/centos-qemu-kvm)
This replicates the scenario in which the bug was reported.
Unfortunately this relies on actually executing a guest (so that the
firmware initialises the virtio-blk device and moves it to its
configured iothread), so this can't make use of the qtest accelerator
like most other test cases. I tried to find a different easy way to
trigger the bug, but couldn't find one.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-ID: <20240314165825.40261-3-kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit e8fce34eccf68a32f4ecf2c6f121ff2ac383d6bf)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
tests/qemu-iotests/tests/iothreads-nbd-export | 66 +++++++++++++++++++
.../tests/iothreads-nbd-export.out | 19 ++++++
2 files changed, 85 insertions(+)
create mode 100755 tests/qemu-iotests/tests/iothreads-nbd-export
create mode 100644 tests/qemu-iotests/tests/iothreads-nbd-export.out
diff --git a/tests/qemu-iotests/tests/iothreads-nbd-export b/tests/qemu-iotests/tests/iothreads-nbd-export
new file mode 100755
index 0000000000..037260729c
--- /dev/null
+++ b/tests/qemu-iotests/tests/iothreads-nbd-export
@@ -0,0 +1,66 @@
+#!/usr/bin/env python3
+# group: rw quick
+#
+# Copyright (C) 2024 Red Hat, Inc.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program. If not, see <http://www.gnu.org/licenses/>.
+#
+# Creator/Owner: Kevin Wolf <kwolf@redhat.com>
+
+import time
+import qemu
+import iotests
+
+iotests.script_initialize(supported_fmts=['qcow2'],
+ supported_platforms=['linux'])
+
+with iotests.FilePath('disk1.img') as path, \
+ iotests.FilePath('nbd.sock', base_dir=iotests.sock_dir) as nbd_sock, \
+ qemu.machine.QEMUMachine(iotests.qemu_prog) as vm:
+
+ img_size = '10M'
+
+ iotests.log('Preparing disk...')
+ iotests.qemu_img_create('-f', iotests.imgfmt, path, img_size)
+ vm.add_args('-blockdev', f'file,node-name=disk-file,filename={path}')
+ vm.add_args('-blockdev', 'qcow2,node-name=disk,file=disk-file')
+ vm.add_args('-object', 'iothread,id=iothread0')
+ vm.add_args('-device',
+ 'virtio-blk,drive=disk,iothread=iothread0,share-rw=on')
+
+ iotests.log('Launching VM...')
+ vm.add_args('-accel', 'kvm', '-accel', 'tcg')
+ #vm.add_args('-accel', 'qtest')
+ vm.launch()
+
+ iotests.log('Exporting to NBD...')
+ iotests.log(vm.qmp('nbd-server-start',
+ addr={'type': 'unix', 'data': {'path': nbd_sock}}))
+ iotests.log(vm.qmp('block-export-add', type='nbd', id='exp0',
+ node_name='disk', writable=True))
+
+ iotests.log('Connecting qemu-img...')
+ qemu_io = iotests.QemuIoInteractive('-f', 'raw',
+ f'nbd+unix:///disk?socket={nbd_sock}')
+
+ iotests.log('Moving the NBD export to a different iothread...')
+ for i in range(0, 10):
+ iotests.log(vm.qmp('system_reset'))
+ time.sleep(0.1)
+
+ iotests.log('Checking that it is still alive...')
+ iotests.log(vm.qmp('query-status'))
+
+ qemu_io.close()
+ vm.shutdown()
diff --git a/tests/qemu-iotests/tests/iothreads-nbd-export.out b/tests/qemu-iotests/tests/iothreads-nbd-export.out
new file mode 100644
index 0000000000..bc514e35e5
--- /dev/null
+++ b/tests/qemu-iotests/tests/iothreads-nbd-export.out
@@ -0,0 +1,19 @@
+Preparing disk...
+Launching VM...
+Exporting to NBD...
+{"return": {}}
+{"return": {}}
+Connecting qemu-img...
+Moving the NBD export to a different iothread...
+{"return": {}}
+{"return": {}}
+{"return": {}}
+{"return": {}}
+{"return": {}}
+{"return": {}}
+{"return": {}}
+{"return": {}}
+{"return": {}}
+{"return": {}}
+Checking that it is still alive...
+{"return": {"running": true, "status": "running"}}
--
2.39.3

49
kvm-iotests-add-filter_qmp_generated_node_ids.patch
View File

@ -1,49 +0,0 @@
From a9be663beaace1c31d75ca353e5d3bb0657a4f6c Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Thu, 18 Jan 2024 09:48:21 -0500
Subject: [PATCH 11/22] iotests: add filter_qmp_generated_node_ids()
RH-Author: Stefan Hajnoczi <stefanha@redhat.com>
RH-MergeRequest: 219: virtio-blk: add iothread-vq-mapping parameter
RH-Jira: RHEL-17369 RHEL-20764 RHEL-7356
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Commit: [7/17] 8dd20acc5b1e992294ed422e80897a9c221940dd (stefanha/centos-stream-qemu-kvm)
Add a filter function for QMP responses that contain QEMU's
automatically generated node ids. The ids change between runs and must
be masked in the reference output.
The next commit will use this new function.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-ID: <20240118144823.1497953-2-stefanha@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit da62b507a20510d819bcfbe8f5e573409b954006)
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
tests/qemu-iotests/iotests.py | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py
index e5c5798c71..ea48af4a7b 100644
--- a/tests/qemu-iotests/iotests.py
+++ b/tests/qemu-iotests/iotests.py
@@ -651,6 +651,13 @@ def _filter(_key, value):
def filter_generated_node_ids(msg):
return re.sub("#block[0-9]+", "NODE_NAME", msg)
+def filter_qmp_generated_node_ids(qmsg):
+ def _filter(_key, value):
+ if is_str(value):
+ return filter_generated_node_ids(value)
+ return value
+ return filter_qmp(qmsg, _filter)
+
def filter_img_info(output: str, filename: str,
drop_child_info: bool = True) -> str:
lines = []
--
2.39.3

49
kvm-iotests-iothreads-stream-Use-the-right-TimeoutError.patch
View File

@ -1,49 +0,0 @@
From 453da839a7d81896d03b827a95c1991a60740dc5 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Thu, 25 Jan 2024 16:21:50 +0100
Subject: [PATCH 21/22] iotests/iothreads-stream: Use the right TimeoutError
RH-Author: Stefan Hajnoczi <stefanha@redhat.com>
RH-MergeRequest: 219: virtio-blk: add iothread-vq-mapping parameter
RH-Jira: RHEL-17369 RHEL-20764 RHEL-7356
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Commit: [17/17] ca5a512ccccb668089b726d7499562d1e294c828 (stefanha/centos-stream-qemu-kvm)
Since Python 3.11 asyncio.TimeoutError is an alias for TimeoutError, but
in older versions it's not. We really have to catch asyncio.TimeoutError
here, otherwise a slow test run will fail (as has happened multiple
times on CI recently).
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-ID: <20240125152150.42389-1-kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit c9c0b37ff4c11b712b21efabe8e5381d223d0295)
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
tests/qemu-iotests/tests/iothreads-stream | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/tests/qemu-iotests/tests/iothreads-stream b/tests/qemu-iotests/tests/iothreads-stream
index 503f221f16..231195b5e8 100755
--- a/tests/qemu-iotests/tests/iothreads-stream
+++ b/tests/qemu-iotests/tests/iothreads-stream
@@ -18,6 +18,7 @@
#
# Creator/Owner: Kevin Wolf <kwolf@redhat.com>
+import asyncio
import iotests
iotests.script_initialize(supported_fmts=['qcow2'],
@@ -69,6 +70,6 @@ with iotests.FilePath('disk1.img') as base1_path, \
# The test is done once both jobs are gone
if finished == 2:
break
- except TimeoutError:
+ except asyncio.TimeoutError:
pass
vm.cmd('query-jobs')
--
2.39.3

592
kvm-iotests-port-141-to-Python-for-reliable-QMP-testing.patch
View File

@ -1,592 +0,0 @@
From 70efc3bbf1f7d7b1b0c2475d9ce3bb70cc9d1cc7 Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Thu, 18 Jan 2024 09:48:22 -0500
Subject: [PATCH 12/22] iotests: port 141 to Python for reliable QMP testing
RH-Author: Stefan Hajnoczi <stefanha@redhat.com>
RH-MergeRequest: 219: virtio-blk: add iothread-vq-mapping parameter
RH-Jira: RHEL-17369 RHEL-20764 RHEL-7356
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Commit: [8/17] 0783f536508916feac4b4c39e41c22c24a2e52e7 (stefanha/centos-stream-qemu-kvm)
The common.qemu bash functions allow tests to interact with the QMP
monitor of a QEMU process. I spent two days trying to update 141 when
the order of the test output changed, but found it would still fail
occassionally because printf() and QMP events race with synchronous QMP
communication.
I gave up and ported 141 to the existing Python API for QMP tests. The
Python API is less affected by the order in which QEMU prints output
because it does not print all QMP traffic by default.
The next commit changes the order in which QMP messages are received.
Make 141 reliable first.
Cc: Hanna Czenczek <hreitz@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-ID: <20240118144823.1497953-3-stefanha@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 9ee2dd4c22a3639c5462b3fc20df60c005c3de64)
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
tests/qemu-iotests/141 | 307 ++++++++++++++++---------------------
tests/qemu-iotests/141.out | 200 ++++++------------------
2 files changed, 176 insertions(+), 331 deletions(-)
diff --git a/tests/qemu-iotests/141 b/tests/qemu-iotests/141
index a37030ee17..a7d3985a02 100755
--- a/tests/qemu-iotests/141
+++ b/tests/qemu-iotests/141
@@ -1,9 +1,12 @@
-#!/usr/bin/env bash
+#!/usr/bin/env python3
# group: rw auto quick
#
# Test case for ejecting BDSs with block jobs still running on them
#
-# Copyright (C) 2016 Red Hat, Inc.
+# Originally written in bash by Hanna Czenczek, ported to Python by Stefan
+# Hajnoczi.
+#
+# Copyright Red Hat
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
@@ -19,177 +22,129 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
-# creator
-owner=hreitz@redhat.com
-
-seq="$(basename $0)"
-echo "QA output created by $seq"
-
-status=1 # failure is the default!
-
-_cleanup()
-{
- _cleanup_qemu
- _cleanup_test_img
- for img in "$TEST_DIR"/{b,m,o}.$IMGFMT; do
- _rm_test_img "$img"
- done
-}
-trap "_cleanup; exit \$status" 0 1 2 3 15
-
-# get standard environment, filters and checks
-. ./common.rc
-. ./common.filter
-. ./common.qemu
-
-# Needs backing file and backing format support
-_supported_fmt qcow2 qed
-_supported_proto file
-_supported_os Linux
-
-
-test_blockjob()
-{
- _send_qemu_cmd $QEMU_HANDLE \
- "{'execute': 'blockdev-add',
- 'arguments': {
- 'node-name': 'drv0',
- 'driver': '$IMGFMT',
- 'file': {
- 'driver': 'file',
- 'filename': '$TEST_IMG'
- }}}" \
- 'return'
-
- # If "$2" is an event, we may or may not see it before the
- # {"return": {}}. Therefore, filter the {"return": {}} out both
- # here and in the next command. (Naturally, if we do not see it
- # here, we will see it before the next command can be executed,
- # so it will appear in the next _send_qemu_cmd's output.)
- _send_qemu_cmd $QEMU_HANDLE \
- "$1" \
- "$2" \
- | _filter_img_create | _filter_qmp_empty_return
-
- # We want this to return an error because the block job is still running
- _send_qemu_cmd $QEMU_HANDLE \
- "{'execute': 'blockdev-del',
- 'arguments': {'node-name': 'drv0'}}" \
- 'error' | _filter_generated_node_ids | _filter_qmp_empty_return
-
- _send_qemu_cmd $QEMU_HANDLE \
- "{'execute': 'block-job-cancel',
- 'arguments': {'device': 'job0'}}" \
- "$3"
-
- _send_qemu_cmd $QEMU_HANDLE \
- "{'execute': 'blockdev-del',
- 'arguments': {'node-name': 'drv0'}}" \
- 'return'
-}
-
-
-TEST_IMG="$TEST_DIR/b.$IMGFMT" _make_test_img 1M
-TEST_IMG="$TEST_DIR/m.$IMGFMT" _make_test_img -b "$TEST_DIR/b.$IMGFMT" -F $IMGFMT 1M
-_make_test_img -b "$TEST_DIR/m.$IMGFMT" 1M -F $IMGFMT
-
-_launch_qemu -nodefaults
-
-_send_qemu_cmd $QEMU_HANDLE \
- "{'execute': 'qmp_capabilities'}" \
- 'return'
-
-echo
-echo '=== Testing drive-backup ==='
-echo
-
-# drive-backup will not send BLOCK_JOB_READY by itself, and cancelling the job
-# will consequently result in BLOCK_JOB_CANCELLED being emitted.
-
-test_blockjob \
- "{'execute': 'drive-backup',
- 'arguments': {'job-id': 'job0',
- 'device': 'drv0',
- 'target': '$TEST_DIR/o.$IMGFMT',
- 'format': '$IMGFMT',
- 'sync': 'none'}}" \
- 'return' \
- '"status": "null"'
-
-echo
-echo '=== Testing drive-mirror ==='
-echo
-
-# drive-mirror will send BLOCK_JOB_READY basically immediately, and cancelling
-# the job will consequently result in BLOCK_JOB_COMPLETED being emitted.
-
-test_blockjob \
- "{'execute': 'drive-mirror',
- 'arguments': {'job-id': 'job0',
- 'device': 'drv0',
- 'target': '$TEST_DIR/o.$IMGFMT',
- 'format': '$IMGFMT',
- 'sync': 'none'}}" \
- 'BLOCK_JOB_READY' \
- '"status": "null"'
-
-echo
-echo '=== Testing active block-commit ==='
-echo
-
-# An active block-commit will send BLOCK_JOB_READY basically immediately, and
-# cancelling the job will consequently result in BLOCK_JOB_COMPLETED being
-# emitted.
-
-test_blockjob \
- "{'execute': 'block-commit',
- 'arguments': {'job-id': 'job0', 'device': 'drv0'}}" \
- 'BLOCK_JOB_READY' \
- '"status": "null"'
-
-echo
-echo '=== Testing non-active block-commit ==='
-echo
-
-# Give block-commit something to work on, otherwise it would be done
-# immediately, send a BLOCK_JOB_COMPLETED and ejecting the BDS would work just
-# fine without the block job still running.
-
-$QEMU_IO -c 'write 0 1M' "$TEST_DIR/m.$IMGFMT" | _filter_qemu_io
-
-test_blockjob \
- "{'execute': 'block-commit',
- 'arguments': {'job-id': 'job0',
- 'device': 'drv0',
- 'top': '$TEST_DIR/m.$IMGFMT',
- 'speed': 1}}" \
- 'return' \
- '"status": "null"'
-
-echo
-echo '=== Testing block-stream ==='
-echo
-
-# Give block-stream something to work on, otherwise it would be done
-# immediately, send a BLOCK_JOB_COMPLETED and ejecting the BDS would work just
-# fine without the block job still running.
-
-$QEMU_IO -c 'write 0 1M' "$TEST_DIR/b.$IMGFMT" | _filter_qemu_io
-
-# With some data to stream (and @speed set to 1), block-stream will not complete
-# until we send the block-job-cancel command.
-
-test_blockjob \
- "{'execute': 'block-stream',
- 'arguments': {'job-id': 'job0',
- 'device': 'drv0',
- 'speed': 1}}" \
- 'return' \
- '"status": "null"'
-
-_cleanup_qemu
-
-# success, all done
-echo "*** done"
-rm -f $seq.full
-status=0
+import iotests
+
+# Common filters to mask values that vary in the test output
+QMP_FILTERS = [iotests.filter_qmp_testfiles, \
+ iotests.filter_qmp_imgfmt]
+
+
+class TestCase:
+ def __init__(self, name, vm, image_path, cancel_event):
+ self.name = name
+ self.vm = vm
+ self.image_path = image_path
+ self.cancel_event = cancel_event
+
+ def __enter__(self):
+ iotests.log(f'=== Testing {self.name} ===')
+ self.vm.qmp_log('blockdev-add', \
+ node_name='drv0', \
+ driver=iotests.imgfmt, \
+ file={'driver': 'file', 'filename': self.image_path}, \
+ filters=QMP_FILTERS)
+
+ def __exit__(self, *exc_details):
+ # This is expected to fail because the job still exists
+ self.vm.qmp_log('blockdev-del', node_name='drv0', \
+ filters=[iotests.filter_qmp_generated_node_ids])
+
+ self.vm.qmp_log('block-job-cancel', device='job0')
+ event = self.vm.event_wait(self.cancel_event)
+ iotests.log(event, filters=[iotests.filter_qmp_event])
+
+ # This time it succeeds
+ self.vm.qmp_log('blockdev-del', node_name='drv0')
+
+ # Separate test cases in output
+ iotests.log('')
+
+
+def main() -> None:
+ with iotests.FilePath('bottom', 'middle', 'top', 'target') as \
+ (bottom_path, middle_path, top_path, target_path), \
+ iotests.VM() as vm:
+
+ iotests.log('Creating bottom <- middle <- top backing file chain...')
+ IMAGE_SIZE='1M'
+ iotests.qemu_img_create('-f', iotests.imgfmt, bottom_path, IMAGE_SIZE)
+ iotests.qemu_img_create('-f', iotests.imgfmt, \
+ '-F', iotests.imgfmt, \
+ '-b', bottom_path, \
+ middle_path, \
+ IMAGE_SIZE)
+ iotests.qemu_img_create('-f', iotests.imgfmt, \
+ '-F', iotests.imgfmt, \
+ '-b', middle_path, \
+ top_path, \
+ IMAGE_SIZE)
+
+ iotests.log('Starting VM...')
+ vm.add_args('-nodefaults')
+ vm.launch()
+
+ # drive-backup will not send BLOCK_JOB_READY by itself, and cancelling
+ # the job will consequently result in BLOCK_JOB_CANCELLED being
+ # emitted.
+ with TestCase('drive-backup', vm, top_path, 'BLOCK_JOB_CANCELLED'):
+ vm.qmp_log('drive-backup', \
+ job_id='job0', \
+ device='drv0', \
+ target=target_path, \
+ format=iotests.imgfmt, \
+ sync='none', \
+ filters=QMP_FILTERS)
+
+ # drive-mirror will send BLOCK_JOB_READY basically immediately, and
+ # cancelling the job will consequently result in BLOCK_JOB_COMPLETED
+ # being emitted.
+ with TestCase('drive-mirror', vm, top_path, 'BLOCK_JOB_COMPLETED'):
+ vm.qmp_log('drive-mirror', \
+ job_id='job0', \
+ device='drv0', \
+ target=target_path, \
+ format=iotests.imgfmt, \
+ sync='none', \
+ filters=QMP_FILTERS)
+ event = vm.event_wait('BLOCK_JOB_READY')
+ assert event is not None # silence mypy
+ iotests.log(event, filters=[iotests.filter_qmp_event])
+
+ # An active block-commit will send BLOCK_JOB_READY basically
+ # immediately, and cancelling the job will consequently result in
+ # BLOCK_JOB_COMPLETED being emitted.
+ with TestCase('active block-commit', vm, top_path, \
+ 'BLOCK_JOB_COMPLETED'):
+ vm.qmp_log('block-commit', \
+ job_id='job0', \
+ device='drv0')
+ event = vm.event_wait('BLOCK_JOB_READY')
+ assert event is not None # silence mypy
+ iotests.log(event, filters=[iotests.filter_qmp_event])
+
+ # Give block-commit something to work on, otherwise it would be done
+ # immediately, send a BLOCK_JOB_COMPLETED and ejecting the BDS would
+ # work just fine without the block job still running.
+ iotests.qemu_io(middle_path, '-c', f'write 0 {IMAGE_SIZE}')
+ with TestCase('non-active block-commit', vm, top_path, \
+ 'BLOCK_JOB_CANCELLED'):
+ vm.qmp_log('block-commit', \
+ job_id='job0', \
+ device='drv0', \
+ top=middle_path, \
+ speed=1, \
+ filters=[iotests.filter_qmp_testfiles])
+
+ # Give block-stream something to work on, otherwise it would be done
+ # immediately, send a BLOCK_JOB_COMPLETED and ejecting the BDS would
+ # work just fine without the block job still running.
+ iotests.qemu_io(bottom_path, '-c', f'write 0 {IMAGE_SIZE}')
+ with TestCase('block-stream', vm, top_path, 'BLOCK_JOB_CANCELLED'):
+ vm.qmp_log('block-stream', \
+ job_id='job0', \
+ device='drv0', \
+ speed=1)
+
+if __name__ == '__main__':
+ iotests.script_main(main, supported_fmts=['qcow2', 'qed'],
+ supported_protocols=['file'])
diff --git a/tests/qemu-iotests/141.out b/tests/qemu-iotests/141.out
index 63203d9944..91b7ba50af 100644
--- a/tests/qemu-iotests/141.out
+++ b/tests/qemu-iotests/141.out
@@ -1,179 +1,69 @@
-QA output created by 141
-Formatting 'TEST_DIR/b.IMGFMT', fmt=IMGFMT size=1048576
-Formatting 'TEST_DIR/m.IMGFMT', fmt=IMGFMT size=1048576 backing_file=TEST_DIR/b.IMGFMT backing_fmt=IMGFMT
-Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 backing_file=TEST_DIR/m.IMGFMT backing_fmt=IMGFMT
-{'execute': 'qmp_capabilities'}
-{"return": {}}
-
+Creating bottom <- middle <- top backing file chain...
+Starting VM...
=== Testing drive-backup ===
-
-{'execute': 'blockdev-add',
- 'arguments': {
- 'node-name': 'drv0',
- 'driver': 'IMGFMT',
- 'file': {
- 'driver': 'file',
- 'filename': 'TEST_DIR/t.IMGFMT'
- }}}
-{"return": {}}
-{'execute': 'drive-backup',
-'arguments': {'job-id': 'job0',
-'device': 'drv0',
-'target': 'TEST_DIR/o.IMGFMT',
-'format': 'IMGFMT',
-'sync': 'none'}}
-Formatting 'TEST_DIR/o.IMGFMT', fmt=IMGFMT size=1048576 backing_file=TEST_DIR/t.IMGFMT backing_fmt=IMGFMT
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "job0"}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "job0"}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "paused", "id": "job0"}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "job0"}}
-{'execute': 'blockdev-del',
- 'arguments': {'node-name': 'drv0'}}
+{"execute": "blockdev-add", "arguments": {"driver": "IMGFMT", "file": {"driver": "file", "filename": "TEST_DIR/PID-top"}, "node-name": "drv0"}}
+{"return": {}}
+{"execute": "drive-backup", "arguments": {"device": "drv0", "format": "IMGFMT", "job-id": "job0", "sync": "none", "target": "TEST_DIR/PID-target"}}
+{"return": {}}
+{"execute": "blockdev-del", "arguments": {"node-name": "drv0"}}
{"error": {"class": "GenericError", "desc": "Node 'drv0' is busy: node is used as backing hd of 'NODE_NAME'"}}
-{'execute': 'block-job-cancel',
- 'arguments': {'device': 'job0'}}
+{"execute": "block-job-cancel", "arguments": {"device": "job0"}}
{"return": {}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "aborting", "id": "job0"}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_CANCELLED", "data": {"device": "job0", "len": 1048576, "offset": 0, "speed": 0, "type": "backup"}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "concluded", "id": "job0"}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "null", "id": "job0"}}
-{'execute': 'blockdev-del',
- 'arguments': {'node-name': 'drv0'}}
+{"data": {"device": "job0", "len": 1048576, "offset": 0, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_CANCELLED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}}
+{"execute": "blockdev-del", "arguments": {"node-name": "drv0"}}
{"return": {}}
=== Testing drive-mirror ===
-
-{'execute': 'blockdev-add',
- 'arguments': {
- 'node-name': 'drv0',
- 'driver': 'IMGFMT',
- 'file': {
- 'driver': 'file',
- 'filename': 'TEST_DIR/t.IMGFMT'
- }}}
-{"return": {}}
-{'execute': 'drive-mirror',
-'arguments': {'job-id': 'job0',
-'device': 'drv0',
-'target': 'TEST_DIR/o.IMGFMT',
-'format': 'IMGFMT',
-'sync': 'none'}}
-Formatting 'TEST_DIR/o.IMGFMT', fmt=IMGFMT size=1048576 backing_file=TEST_DIR/t.IMGFMT backing_fmt=IMGFMT
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "job0"}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "job0"}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "job0"}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "mirror"}}
-{'execute': 'blockdev-del',
- 'arguments': {'node-name': 'drv0'}}
+{"execute": "blockdev-add", "arguments": {"driver": "IMGFMT", "file": {"driver": "file", "filename": "TEST_DIR/PID-top"}, "node-name": "drv0"}}
+{"return": {}}
+{"execute": "drive-mirror", "arguments": {"device": "drv0", "format": "IMGFMT", "job-id": "job0", "sync": "none", "target": "TEST_DIR/PID-target"}}
+{"return": {}}
+{"data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "mirror"}, "event": "BLOCK_JOB_READY", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}}
+{"execute": "blockdev-del", "arguments": {"node-name": "drv0"}}
{"error": {"class": "GenericError", "desc": "Node 'drv0' is busy: block device is in use by block job: mirror"}}
-{'execute': 'block-job-cancel',
- 'arguments': {'device': 'job0'}}
+{"execute": "block-job-cancel", "arguments": {"device": "job0"}}
{"return": {}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "job0"}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "job0"}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "mirror"}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "concluded", "id": "job0"}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "null", "id": "job0"}}
-{'execute': 'blockdev-del',
- 'arguments': {'node-name': 'drv0'}}
+{"data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "mirror"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}}
+{"execute": "blockdev-del", "arguments": {"node-name": "drv0"}}
{"return": {}}
=== Testing active block-commit ===
-
-{'execute': 'blockdev-add',
- 'arguments': {
- 'node-name': 'drv0',
- 'driver': 'IMGFMT',
- 'file': {
- 'driver': 'file',
- 'filename': 'TEST_DIR/t.IMGFMT'
- }}}
-{"return": {}}
-{'execute': 'block-commit',
-'arguments': {'job-id': 'job0', 'device': 'drv0'}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "job0"}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "job0"}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "job0"}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "commit"}}
-{'execute': 'blockdev-del',
- 'arguments': {'node-name': 'drv0'}}
+{"execute": "blockdev-add", "arguments": {"driver": "IMGFMT", "file": {"driver": "file", "filename": "TEST_DIR/PID-top"}, "node-name": "drv0"}}
+{"return": {}}
+{"execute": "block-commit", "arguments": {"device": "drv0", "job-id": "job0"}}
+{"return": {}}
+{"data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "commit"}, "event": "BLOCK_JOB_READY", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}}
+{"execute": "blockdev-del", "arguments": {"node-name": "drv0"}}
{"error": {"class": "GenericError", "desc": "Node 'drv0' is busy: block device is in use by block job: commit"}}
-{'execute': 'block-job-cancel',
- 'arguments': {'device': 'job0'}}
+{"execute": "block-job-cancel", "arguments": {"device": "job0"}}
{"return": {}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "job0"}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "job0"}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "commit"}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "concluded", "id": "job0"}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "null", "id": "job0"}}
-{'execute': 'blockdev-del',
- 'arguments': {'node-name': 'drv0'}}
+{"data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "commit"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}}
+{"execute": "blockdev-del", "arguments": {"node-name": "drv0"}}
{"return": {}}
=== Testing non-active block-commit ===
-
-wrote 1048576/1048576 bytes at offset 0
-1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-{'execute': 'blockdev-add',
- 'arguments': {
- 'node-name': 'drv0',
- 'driver': 'IMGFMT',
- 'file': {
- 'driver': 'file',
- 'filename': 'TEST_DIR/t.IMGFMT'
- }}}
-{"return": {}}
-{'execute': 'block-commit',
-'arguments': {'job-id': 'job0',
-'device': 'drv0',
-'top': 'TEST_DIR/m.IMGFMT',
-'speed': 1}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "job0"}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "job0"}}
-{'execute': 'blockdev-del',
- 'arguments': {'node-name': 'drv0'}}
+{"execute": "blockdev-add", "arguments": {"driver": "IMGFMT", "file": {"driver": "file", "filename": "TEST_DIR/PID-top"}, "node-name": "drv0"}}
+{"return": {}}
+{"execute": "block-commit", "arguments": {"device": "drv0", "job-id": "job0", "speed": 1, "top": "TEST_DIR/PID-middle"}}
+{"return": {}}
+{"execute": "blockdev-del", "arguments": {"node-name": "drv0"}}
{"error": {"class": "GenericError", "desc": "Node 'drv0' is busy: block device is in use by block job: commit"}}
-{'execute': 'block-job-cancel',
- 'arguments': {'device': 'job0'}}
+{"execute": "block-job-cancel", "arguments": {"device": "job0"}}
{"return": {}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "aborting", "id": "job0"}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_CANCELLED", "data": {"device": "job0", "len": 1048576, "offset": 524288, "speed": 1, "type": "commit"}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "concluded", "id": "job0"}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "null", "id": "job0"}}
-{'execute': 'blockdev-del',
- 'arguments': {'node-name': 'drv0'}}
+{"data": {"device": "job0", "len": 1048576, "offset": 524288, "speed": 1, "type": "commit"}, "event": "BLOCK_JOB_CANCELLED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}}
+{"execute": "blockdev-del", "arguments": {"node-name": "drv0"}}
{"return": {}}
=== Testing block-stream ===
-
-wrote 1048576/1048576 bytes at offset 0
-1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-{'execute': 'blockdev-add',
- 'arguments': {
- 'node-name': 'drv0',
- 'driver': 'IMGFMT',
- 'file': {
- 'driver': 'file',
- 'filename': 'TEST_DIR/t.IMGFMT'
- }}}
-{"return": {}}
-{'execute': 'block-stream',
-'arguments': {'job-id': 'job0',
-'device': 'drv0',
-'speed': 1}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "job0"}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "job0"}}
-{'execute': 'blockdev-del',
- 'arguments': {'node-name': 'drv0'}}
+{"execute": "blockdev-add", "arguments": {"driver": "IMGFMT", "file": {"driver": "file", "filename": "TEST_DIR/PID-top"}, "node-name": "drv0"}}
+{"return": {}}
+{"execute": "block-stream", "arguments": {"device": "drv0", "job-id": "job0", "speed": 1}}
+{"return": {}}
+{"execute": "blockdev-del", "arguments": {"node-name": "drv0"}}
{"error": {"class": "GenericError", "desc": "Node 'drv0' is busy: block device is in use by block job: stream"}}
-{'execute': 'block-job-cancel',
- 'arguments': {'device': 'job0'}}
+{"execute": "block-job-cancel", "arguments": {"device": "job0"}}
{"return": {}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "aborting", "id": "job0"}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_CANCELLED", "data": {"device": "job0", "len": 1048576, "offset": 524288, "speed": 1, "type": "stream"}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "concluded", "id": "job0"}}
-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "null", "id": "job0"}}
-{'execute': 'blockdev-del',
- 'arguments': {'node-name': 'drv0'}}
+{"data": {"device": "job0", "len": 1048576, "offset": 524288, "speed": 1, "type": "stream"}, "event": "BLOCK_JOB_CANCELLED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}}
+{"execute": "blockdev-del", "arguments": {"node-name": "drv0"}}
{"return": {}}
-*** done
+
--
2.39.3

105
kvm-job-remove-outdated-AioContext-locking-comments.patch
View File

@ -1,105 +0,0 @@
From 4ab25b33831fa207500179bd30f29388d81e4cce Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Tue, 5 Dec 2023 13:20:10 -0500
Subject: [PATCH 093/101] job: remove outdated AioContext locking comments
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 214: Remove AioContext lock
RH-Jira: RHEL-15965
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Commit: [24/26] 15ff2928be82d6905c22619458487fbb72d6044a (kmwolf/centos-qemu-kvm)
The AioContext lock no longer exists.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-ID: <20231205182011.1976568-14-stefanha@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
include/qemu/job.h | 20 --------------------
1 file changed, 20 deletions(-)
diff --git a/include/qemu/job.h b/include/qemu/job.h
index e502787dd8..9ea98b5927 100644
--- a/include/qemu/job.h
+++ b/include/qemu/job.h
@@ -67,8 +67,6 @@ typedef struct Job {
/**
* The completion function that will be called when the job completes.
- * Called with AioContext lock held, since many callback implementations
- * use bdrv_* functions that require to hold the lock.
*/
BlockCompletionFunc *cb;
@@ -264,9 +262,6 @@ struct JobDriver {
*
* This callback will not be invoked if the job has already failed.
* If it fails, abort and then clean will be called.
- *
- * Called with AioContext lock held, since many callbacs implementations
- * use bdrv_* functions that require to hold the lock.
*/
int (*prepare)(Job *job);
@@ -277,9 +272,6 @@ struct JobDriver {
*
* All jobs will complete with a call to either .commit() or .abort() but
* never both.
- *
- * Called with AioContext lock held, since many callback implementations
- * use bdrv_* functions that require to hold the lock.
*/
void (*commit)(Job *job);
@@ -290,9 +282,6 @@ struct JobDriver {
*
* All jobs will complete with a call to either .commit() or .abort() but
* never both.
- *
- * Called with AioContext lock held, since many callback implementations
- * use bdrv_* functions that require to hold the lock.
*/
void (*abort)(Job *job);
@@ -301,9 +290,6 @@ struct JobDriver {
* .commit() or .abort(). Regardless of which callback is invoked after
* completion, .clean() will always be called, even if the job does not
* belong to a transaction group.
- *
- * Called with AioContext lock held, since many callbacs implementations
- * use bdrv_* functions that require to hold the lock.
*/
void (*clean)(Job *job);
@@ -318,17 +304,12 @@ struct JobDriver {
* READY).
* (If the callback is NULL, the job is assumed to terminate
* without I/O.)
- *
- * Called with AioContext lock held, since many callback implementations
- * use bdrv_* functions that require to hold the lock.
*/
bool (*cancel)(Job *job, bool force);
/**
* Called when the job is freed.
- * Called with AioContext lock held, since many callback implementations
- * use bdrv_* functions that require to hold the lock.
*/
void (*free)(Job *job);
};
@@ -424,7 +405,6 @@ void job_ref_locked(Job *job);
* Release a reference that was previously acquired with job_ref_locked() or
* job_create(). If it's the last reference to the object, it will be freed.
*
- * Takes AioContext lock internally to invoke a job->driver callback.
* Called with job lock held.
*/
void job_unref_locked(Job *job);
--
2.39.3

42
kvm-kconfig-Activate-IOMMUFD-for-s390x-machines.patch
View File

@ -1,42 +0,0 @@
From 9c2eb4ab03903bc084c53ac29b60b8d2121c9fed Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= <clg@redhat.com>
Date: Tue, 21 Nov 2023 16:44:19 +0800
Subject: [PATCH 040/101] kconfig: Activate IOMMUFD for s390x machines
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 211: IOMMUFD backend backport
RH-Jira: RHEL-19302 RHEL-21057
RH-Acked-by: Cédric Le Goater <clg@redhat.com>
RH-Acked-by: Sebastian Ott <sebott@redhat.com>
RH-Commit: [39/67] cf0ebe770b8db5916dd35247618c0a325dc1eaab (eauger1/centos-qemu-kvm)
Signed-off-by: Cédric Le Goater <clg@redhat.com>
Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>
Reviewed-by: Eric Farman <farman@linux.ibm.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Cédric Le Goater <clg@redhat.com>
(cherry picked from commit 73e2df669335047b542b67d37ade060a6ae40dd8)
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
hw/s390x/Kconfig | 1 +
1 file changed, 1 insertion(+)
diff --git a/hw/s390x/Kconfig b/hw/s390x/Kconfig
index 4c068d7960..26ad104485 100644
--- a/hw/s390x/Kconfig
+++ b/hw/s390x/Kconfig
@@ -6,6 +6,7 @@ config S390_CCW_VIRTIO
imply VFIO_CCW
imply WDT_DIAG288
imply PCIE_DEVICES
+ imply IOMMUFD
select PCI_EXPRESS
select S390_FLIC
select S390_FLIC_KVM if KVM
--
2.39.3

112
kvm-memory-device-reintroduce-memory-region-size-check.patch
View File

@ -1,112 +0,0 @@
From 633c6a52ac88526534466ae311522fe5447bcf91 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Wed, 17 Jan 2024 14:55:54 +0100
Subject: [PATCH 02/22] memory-device: reintroduce memory region size check
RH-Author: David Hildenbrand <david@redhat.com>
RH-MergeRequest: 221: memory-device: reintroduce memory region size check
RH-Jira: RHEL-20341
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Igor Mammedov <imammedo@redhat.com>
RH-Commit: [2/2] e9ff2339b0c07c3f48f5834c9c80cd6d4cbc8f71
JIRA: https://issues.redhat.com/browse/RHEL-20341
We used to check that the memory region size is multiples of the overall
requested address alignment for the device memory address.
We removed that check, because there are cases (i.e., hv-balloon) where
devices unconditionally request an address alignment that has a very large
alignment (i.e., 32 GiB), but the actual memory device size might not be
multiples of that alignment.
However, this change:
(a) allows for some practically impossible DIMM sizes, like "1GB+1 byte".
(b) allows for DIMMs that partially cover hugetlb pages, previously
reported in [1].
Both scenarios don't make any sense: we might even waste memory.
So let's reintroduce that check, but only check that the
memory region size is multiples of the memory region alignment (i.e.,
page size, huge page size), but not any additional memory device
requirements communicated using md->get_min_alignment().
The following examples now fail again as expected:
(a) 1M with 2M THP
qemu-system-x86_64 -m 4g,maxmem=16g,slots=1 -S -nodefaults -nographic \
-object memory-backend-ram,id=mem1,size=1M \
-device pc-dimm,id=dimm1,memdev=mem1
-> backend memory size must be multiple of 0x200000
(b) 1G+1byte
qemu-system-x86_64 -m 4g,maxmem=16g,slots=1 -S -nodefaults -nographic \
-object memory-backend-ram,id=mem1,size=1073741825B \
-device pc-dimm,id=dimm1,memdev=mem1
-> backend memory size must be multiple of 0x200000
(c) Unliagned hugetlb size (2M)
qemu-system-x86_64 -m 4g,maxmem=16g,slots=1 -S -nodefaults -nographic \
-object memory-backend-file,id=mem1,mem-path=/dev/hugepages/tmp,size=511M \
-device pc-dimm,id=dimm1,memdev=mem1
backend memory size must be multiple of 0x200000
(d) Unliagned hugetlb size (1G)
qemu-system-x86_64 -m 4g,maxmem=16g,slots=1 -S -nodefaults -nographic \
-object memory-backend-file,id=mem1,mem-path=/dev/hugepages1G/tmp,size=2047M \
-device pc-dimm,id=dimm1,memdev=mem1
-> backend memory size must be multiple of 0x40000000
Note that this fix depends on a hv-balloon change to communicate its
additional alignment requirements using get_min_alignment() instead of
through the memory region.
[1] https://lkml.kernel.org/r/f77d641d500324525ac036fe1827b3070de75fc1.1701088320.git.mprivozn@redhat.com
Message-ID: <20240117135554.787344-3-david@redhat.com>
Reported-by: Zhenyu Zhang <zhenyzha@redhat.com>
Reported-by: Michal Privoznik <mprivozn@redhat.com>
Fixes: eb1b7c4bd413 ("memory-device: Drop size alignment check")
Tested-by: Zhenyu Zhang <zhenyzha@redhat.com>
Tested-by: Mario Casquero <mcasquer@redhat.com>
Reviewed-by: Maciej S. Szmigiero <maciej.szmigiero@oracle.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
(cherry picked from commit 540a1abbf0b243e4cfb4333c5d30a041f7080ba4)
Signed-off-by: David Hildenbrand <david@redhat.com>
---
hw/mem/memory-device.c | 14 ++++++++++++++
1 file changed, 14 insertions(+)
diff --git a/hw/mem/memory-device.c b/hw/mem/memory-device.c
index a1b1af26bc..e098585cda 100644
--- a/hw/mem/memory-device.c
+++ b/hw/mem/memory-device.c
@@ -374,6 +374,20 @@ void memory_device_pre_plug(MemoryDeviceState *md, MachineState *ms,
goto out;
}
+ /*
+ * We always want the memory region size to be multiples of the memory
+ * region alignment: for example, DIMMs with 1G+1byte size don't make
+ * any sense. Note that we don't check that the size is multiples
+ * of any additional alignment requirements the memory device might
+ * have when it comes to the address in physical address space.
+ */
+ if (!QEMU_IS_ALIGNED(memory_region_size(mr),
+ memory_region_get_alignment(mr))) {
+ error_setg(errp, "backend memory size must be multiple of 0x%"
+ PRIx64, memory_region_get_alignment(mr));
+ return;
+ }
+
if (legacy_align) {
align = *legacy_align;
} else {
--
2.39.3

90
kvm-mirror-Don-t-call-job_pause_point-under-graph-lock.patch
View File

@ -1,90 +0,0 @@
From 21cadc8ed200ad9af13b217b441b9f12cd2163ee Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Wed, 13 Mar 2024 16:30:00 +0100
Subject: [PATCH 1/4] mirror: Don't call job_pause_point() under graph lock
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 231: Fix deadlock and crash during storage migration
RH-Jira: RHEL-28125
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Eric Blake <eblake@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Commit: [1/3] 093910fcd5ea1516d0ed48a9cd73dad6170590f3 (kmwolf/centos-qemu-kvm)
Calling job_pause_point() while holding the graph reader lock
potentially results in a deadlock: bdrv_graph_wrlock() first drains
everything, including the mirror job, which pauses it. The job is only
unpaused at the end of the drain section, which is when the graph writer
lock has been successfully taken. However, if the job happens to be
paused at a pause point where it still holds the reader lock, the writer
lock can't be taken as long as the job is still paused.
Mark job_pause_point() as GRAPH_UNLOCKED and fix mirror accordingly.
Cc: qemu-stable@nongnu.org
Buglink: https://issues.redhat.com/browse/RHEL-28125
Fixes: 004915a96a7a ("block: Protect bs->backing with graph_lock")
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-ID: <20240313153000.33121-1-kwolf@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit ae5a40e8581185654a667fbbf7e4adbc2a2a3e45)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
block/mirror.c | 10 ++++++----
include/qemu/job.h | 2 +-
2 files changed, 7 insertions(+), 5 deletions(-)
diff --git a/block/mirror.c b/block/mirror.c
index 5145eb53e1..1bdce3b657 100644
--- a/block/mirror.c
+++ b/block/mirror.c
@@ -479,9 +479,9 @@ static unsigned mirror_perform(MirrorBlockJob *s, int64_t offset,
return bytes_handled;
}
-static void coroutine_fn GRAPH_RDLOCK mirror_iteration(MirrorBlockJob *s)
+static void coroutine_fn GRAPH_UNLOCKED mirror_iteration(MirrorBlockJob *s)
{
- BlockDriverState *source = s->mirror_top_bs->backing->bs;
+ BlockDriverState *source;
MirrorOp *pseudo_op;
int64_t offset;
/* At least the first dirty chunk is mirrored in one iteration. */
@@ -489,6 +489,10 @@ static void coroutine_fn GRAPH_RDLOCK mirror_iteration(MirrorBlockJob *s)
bool write_zeroes_ok = bdrv_can_write_zeroes_with_unmap(blk_bs(s->target));
int max_io_bytes = MAX(s->buf_size / MAX_IN_FLIGHT, MAX_IO_BYTES);
+ bdrv_graph_co_rdlock();
+ source = s->mirror_top_bs->backing->bs;
+ bdrv_graph_co_rdunlock();
+
bdrv_dirty_bitmap_lock(s->dirty_bitmap);
offset = bdrv_dirty_iter_next(s->dbi);
if (offset < 0) {
@@ -1066,9 +1070,7 @@ static int coroutine_fn mirror_run(Job *job, Error **errp)
mirror_wait_for_free_in_flight_slot(s);
continue;
} else if (cnt != 0) {
- bdrv_graph_co_rdlock();
mirror_iteration(s);
- bdrv_graph_co_rdunlock();
}
}
diff --git a/include/qemu/job.h b/include/qemu/job.h
index 9ea98b5927..2b873f2576 100644
--- a/include/qemu/job.h
+++ b/include/qemu/job.h
@@ -483,7 +483,7 @@ void job_enter(Job *job);
*
* Called with job_mutex *not* held.
*/
-void coroutine_fn job_pause_point(Job *job);
+void coroutine_fn GRAPH_UNLOCKED job_pause_point(Job *job);
/**
* @job: The job that calls the function.
--
2.39.3

1630
kvm-monitor-only-run-coroutine-commands-in-qemu_aio_cont.patch
View File

File diff suppressed because it is too large Load Diff

95
kvm-nbd-server-Fix-race-in-draining-the-export.patch
View File

@ -1,95 +0,0 @@
From dc4dd11233522d8195782a2196aaae44bd924575 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Thu, 14 Mar 2024 17:58:24 +0100
Subject: [PATCH 2/4] nbd/server: Fix race in draining the export
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 231: Fix deadlock and crash during storage migration
RH-Jira: RHEL-28125
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Eric Blake <eblake@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Commit: [2/3] 036e1b171986099904dee468c59d77437e3d3d61 (kmwolf/centos-qemu-kvm)
When draining an NBD export, nbd_drained_begin() first sets
client->quiescing so that nbd_client_receive_next_request() won't start
any new request coroutines. Then nbd_drained_poll() tries to makes sure
that we wait for any existing request coroutines by checking that
client->nb_requests has become 0.
However, there is a small window between creating a new request
coroutine and increasing client->nb_requests. If a coroutine is in this
state, it won't be waited for and drain returns too early.
In the context of switching to a different AioContext, this means that
blk_aio_attached() will see client->recv_coroutine != NULL and fail its
assertion.
Fix this by increasing client->nb_requests immediately when starting the
coroutine. Doing this after the checks if we should create a new
coroutine is okay because client->lock is held.
Cc: qemu-stable@nongnu.org
Fixes: fd6afc501a01 ("nbd/server: Use drained block ops to quiesce the server")
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-ID: <20240314165825.40261-2-kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 9c707525cbb1dd1e56876e45c70c0c08f2876d41)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
nbd/server.c | 15 +++++++--------
1 file changed, 7 insertions(+), 8 deletions(-)
diff --git a/nbd/server.c b/nbd/server.c
index 941832f178..c3484cc1eb 100644
--- a/nbd/server.c
+++ b/nbd/server.c
@@ -3007,8 +3007,8 @@ static coroutine_fn int nbd_handle_request(NBDClient *client,
/* Owns a reference to the NBDClient passed as opaque. */
static coroutine_fn void nbd_trip(void *opaque)
{
- NBDClient *client = opaque;
- NBDRequestData *req = NULL;
+ NBDRequestData *req = opaque;
+ NBDClient *client = req->client;
NBDRequest request = { 0 }; /* GCC thinks it can be used uninitialized */
int ret;
Error *local_err = NULL;
@@ -3037,8 +3037,6 @@ static coroutine_fn void nbd_trip(void *opaque)
goto done;
}
- req = nbd_request_get(client);
-
/*
* nbd_co_receive_request() returns -EAGAIN when nbd_drained_begin() has
* set client->quiescing but by the time we get back nbd_drained_end() may
@@ -3112,9 +3110,7 @@ static coroutine_fn void nbd_trip(void *opaque)
}
done:
- if (req) {
- nbd_request_put(req);
- }
+ nbd_request_put(req);
qemu_mutex_unlock(&client->lock);
@@ -3143,10 +3139,13 @@ disconnect:
*/
static void nbd_client_receive_next_request(NBDClient *client)
{
+ NBDRequestData *req;
+
if (!client->recv_coroutine && client->nb_requests < MAX_NBD_REQUESTS &&
!client->quiescing) {
nbd_client_get(client);
- client->recv_coroutine = qemu_coroutine_create(nbd_trip, client);
+ req = nbd_request_get(client);
+ client->recv_coroutine = qemu_coroutine_create(nbd_trip, req);
aio_co_schedule(client->exp->common.ctx, client->recv_coroutine);
}
}
--
2.39.3

53
kvm-nbd-server-avoid-per-NBDRequest-nbd_client_get-put.patch
View File

@ -1,53 +0,0 @@
From cd7788a857a6099206c4063e3ef69cb9e4aebcbc Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Thu, 21 Dec 2023 14:24:50 -0500
Subject: [PATCH 070/101] nbd/server: avoid per-NBDRequest nbd_client_get/put()
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 214: Remove AioContext lock
RH-Jira: RHEL-15965
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Commit: [1/26] 5acb090ac4adf4260cd9e9c5605a27012b2a33aa (kmwolf/centos-qemu-kvm)
nbd_trip() processes a single NBD request from start to finish and holds
an NBDClient reference throughout. NBDRequest does not outlive the scope
of nbd_trip(). Therefore it is unnecessary to ref/unref NBDClient for
each NBDRequest.
Removing these nbd_client_get()/nbd_client_put() calls will make
thread-safety easier in the commits that follow.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Message-ID: <20231221192452.1785567-5-stefanha@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
nbd/server.c | 3 ---
1 file changed, 3 deletions(-)
diff --git a/nbd/server.c b/nbd/server.c
index 895cf0a752..0b09ccc8dc 100644
--- a/nbd/server.c
+++ b/nbd/server.c
@@ -1557,7 +1557,6 @@ static NBDRequestData *nbd_request_get(NBDClient *client)
client->nb_requests++;
req = g_new0(NBDRequestData, 1);
- nbd_client_get(client);
req->client = client;
return req;
}
@@ -1578,8 +1577,6 @@ static void nbd_request_put(NBDRequestData *req)
}
nbd_client_receive_next_request(client);
-
- nbd_client_put(client);
}
static void blk_aio_attached(AioContext *ctx, void *opaque)
--
2.39.3

373
kvm-nbd-server-introduce-NBDClient-lock-to-protect-field.patch
View File

@ -1,373 +0,0 @@
From bb0a6afff7f23a3ddb460dc1b2e70c06565f8a3f Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Thu, 21 Dec 2023 14:24:52 -0500
Subject: [PATCH 072/101] nbd/server: introduce NBDClient->lock to protect
fields
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 214: Remove AioContext lock
RH-Jira: RHEL-15965
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Commit: [3/26] 49b64adaaf8b1c30f339d1ecc8ea89fb9db63f1c (kmwolf/centos-qemu-kvm)
NBDClient has a number of fields that are accessed by both the export
AioContext and the main loop thread. When the AioContext lock is removed
these fields will need another form of protection.
Add NBDClient->lock and protect fields that are accessed by both
threads. Also add assertions where possible and otherwise add doc
comments stating assumptions about which thread and lock holding.
Note this patch moves the client->recv_coroutine assertion from
nbd_co_receive_request() to nbd_trip() where client->lock is held.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-ID: <20231221192452.1785567-7-stefanha@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
nbd/server.c | 144 +++++++++++++++++++++++++++++++++++++++------------
1 file changed, 111 insertions(+), 33 deletions(-)
diff --git a/nbd/server.c b/nbd/server.c
index e91e2e0903..941832f178 100644
--- a/nbd/server.c
+++ b/nbd/server.c
@@ -125,23 +125,25 @@ struct NBDClient {
int refcount; /* atomic */
void (*close_fn)(NBDClient *client, bool negotiated);
+ QemuMutex lock;
+
NBDExport *exp;
QCryptoTLSCreds *tlscreds;
char *tlsauthz;
QIOChannelSocket *sioc; /* The underlying data channel */
QIOChannel *ioc; /* The current I/O channel which may differ (eg TLS) */
- Coroutine *recv_coroutine;
+ Coroutine *recv_coroutine; /* protected by lock */
CoMutex send_lock;
Coroutine *send_coroutine;
- bool read_yielding;
- bool quiescing;
+ bool read_yielding; /* protected by lock */
+ bool quiescing; /* protected by lock */
QTAILQ_ENTRY(NBDClient) next;
- int nb_requests;
- bool closing;
+ int nb_requests; /* protected by lock */
+ bool closing; /* protected by lock */
uint32_t check_align; /* If non-zero, check for aligned client requests */
@@ -1415,11 +1417,18 @@ nbd_read_eof(NBDClient *client, void *buffer, size_t size, Error **errp)
len = qio_channel_readv(client->ioc, &iov, 1, errp);
if (len == QIO_CHANNEL_ERR_BLOCK) {
- client->read_yielding = true;
+ WITH_QEMU_LOCK_GUARD(&client->lock) {
+ client->read_yielding = true;
+
+ /* Prompt main loop thread to re-run nbd_drained_poll() */
+ aio_wait_kick();
+ }
qio_channel_yield(client->ioc, G_IO_IN);
- client->read_yielding = false;
- if (client->quiescing) {
- return -EAGAIN;
+ WITH_QEMU_LOCK_GUARD(&client->lock) {
+ client->read_yielding = false;
+ if (client->quiescing) {
+ return -EAGAIN;
+ }
}
continue;
} else if (len < 0) {
@@ -1528,6 +1537,7 @@ void nbd_client_put(NBDClient *client)
blk_exp_unref(&client->exp->common);
}
g_free(client->contexts.bitmaps);
+ qemu_mutex_destroy(&client->lock);
g_free(client);
}
}
@@ -1561,11 +1571,13 @@ static void client_close(NBDClient *client, bool negotiated)
{
assert(qemu_in_main_thread());
- if (client->closing) {
- return;
- }
+ WITH_QEMU_LOCK_GUARD(&client->lock) {
+ if (client->closing) {
+ return;
+ }
- client->closing = true;
+ client->closing = true;
+ }
/* Force requests to finish. They will drop their own references,
* then we'll close the socket and free the NBDClient.
@@ -1579,6 +1591,7 @@ static void client_close(NBDClient *client, bool negotiated)
}
}
+/* Runs in export AioContext with client->lock held */
static NBDRequestData *nbd_request_get(NBDClient *client)
{
NBDRequestData *req;
@@ -1591,6 +1604,7 @@ static NBDRequestData *nbd_request_get(NBDClient *client)
return req;
}
+/* Runs in export AioContext with client->lock held */
static void nbd_request_put(NBDRequestData *req)
{
NBDClient *client = req->client;
@@ -1614,14 +1628,18 @@ static void blk_aio_attached(AioContext *ctx, void *opaque)
NBDExport *exp = opaque;
NBDClient *client;
+ assert(qemu_in_main_thread());
+
trace_nbd_blk_aio_attached(exp->name, ctx);
exp->common.ctx = ctx;
QTAILQ_FOREACH(client, &exp->clients, next) {
- assert(client->nb_requests == 0);
- assert(client->recv_coroutine == NULL);
- assert(client->send_coroutine == NULL);
+ WITH_QEMU_LOCK_GUARD(&client->lock) {
+ assert(client->nb_requests == 0);
+ assert(client->recv_coroutine == NULL);
+ assert(client->send_coroutine == NULL);
+ }
}
}
@@ -1629,6 +1647,8 @@ static void blk_aio_detach(void *opaque)
{
NBDExport *exp = opaque;
+ assert(qemu_in_main_thread());
+
trace_nbd_blk_aio_detach(exp->name, exp->common.ctx);
exp->common.ctx = NULL;
@@ -1639,8 +1659,12 @@ static void nbd_drained_begin(void *opaque)
NBDExport *exp = opaque;
NBDClient *client;
+ assert(qemu_in_main_thread());
+
QTAILQ_FOREACH(client, &exp->clients, next) {
- client->quiescing = true;
+ WITH_QEMU_LOCK_GUARD(&client->lock) {
+ client->quiescing = true;
+ }
}
}
@@ -1649,28 +1673,48 @@ static void nbd_drained_end(void *opaque)
NBDExport *exp = opaque;
NBDClient *client;
+ assert(qemu_in_main_thread());
+
QTAILQ_FOREACH(client, &exp->clients, next) {
- client->quiescing = false;
- nbd_client_receive_next_request(client);
+ WITH_QEMU_LOCK_GUARD(&client->lock) {
+ client->quiescing = false;
+ nbd_client_receive_next_request(client);
+ }
}
}
+/* Runs in export AioContext */
+static void nbd_wake_read_bh(void *opaque)
+{
+ NBDClient *client = opaque;
+ qio_channel_wake_read(client->ioc);
+}
+
static bool nbd_drained_poll(void *opaque)
{
NBDExport *exp = opaque;
NBDClient *client;
+ assert(qemu_in_main_thread());
+
QTAILQ_FOREACH(client, &exp->clients, next) {
- if (client->nb_requests != 0) {
- /*
- * If there's a coroutine waiting for a request on nbd_read_eof()
- * enter it here so we don't depend on the client to wake it up.
- */
- if (client->recv_coroutine != NULL && client->read_yielding) {
- qio_channel_wake_read(client->ioc);
- }
+ WITH_QEMU_LOCK_GUARD(&client->lock) {
+ if (client->nb_requests != 0) {
+ /*
+ * If there's a coroutine waiting for a request on nbd_read_eof()
+ * enter it here so we don't depend on the client to wake it up.
+ *
+ * Schedule a BH in the export AioContext to avoid missing the
+ * wake up due to the race between qio_channel_wake_read() and
+ * qio_channel_yield().
+ */
+ if (client->recv_coroutine != NULL && client->read_yielding) {
+ aio_bh_schedule_oneshot(nbd_export_aio_context(client->exp),
+ nbd_wake_read_bh, client);
+ }
- return true;
+ return true;
+ }
}
}
@@ -1681,6 +1725,8 @@ static void nbd_eject_notifier(Notifier *n, void *data)
{
NBDExport *exp = container_of(n, NBDExport, eject_notifier);
+ assert(qemu_in_main_thread());
+
blk_exp_request_shutdown(&exp->common);
}
@@ -2566,7 +2612,6 @@ static int coroutine_fn nbd_co_receive_request(NBDRequestData *req,
int ret;
g_assert(qemu_in_coroutine());
- assert(client->recv_coroutine == qemu_coroutine_self());
ret = nbd_receive_request(client, request, errp);
if (ret < 0) {
return ret;
@@ -2975,6 +3020,9 @@ static coroutine_fn void nbd_trip(void *opaque)
*/
trace_nbd_trip();
+
+ qemu_mutex_lock(&client->lock);
+
if (client->closing) {
goto done;
}
@@ -2990,7 +3038,21 @@ static coroutine_fn void nbd_trip(void *opaque)
}
req = nbd_request_get(client);
- ret = nbd_co_receive_request(req, &request, &local_err);
+
+ /*
+ * nbd_co_receive_request() returns -EAGAIN when nbd_drained_begin() has
+ * set client->quiescing but by the time we get back nbd_drained_end() may
+ * have already cleared client->quiescing. In that case we try again
+ * because nothing else will spawn an nbd_trip() coroutine until we set
+ * client->recv_coroutine = NULL further down.
+ */
+ do {
+ assert(client->recv_coroutine == qemu_coroutine_self());
+ qemu_mutex_unlock(&client->lock);
+ ret = nbd_co_receive_request(req, &request, &local_err);
+ qemu_mutex_lock(&client->lock);
+ } while (ret == -EAGAIN && !client->quiescing);
+
client->recv_coroutine = NULL;
if (client->closing) {
@@ -3002,15 +3064,16 @@ static coroutine_fn void nbd_trip(void *opaque)
}
if (ret == -EAGAIN) {
- assert(client->quiescing);
goto done;
}
nbd_client_receive_next_request(client);
+
if (ret == -EIO) {
goto disconnect;
}
+ qemu_mutex_unlock(&client->lock);
qio_channel_set_cork(client->ioc, true);
if (ret < 0) {
@@ -3030,6 +3093,10 @@ static coroutine_fn void nbd_trip(void *opaque)
g_free(request.contexts->bitmaps);
g_free(request.contexts);
}
+
+ qio_channel_set_cork(client->ioc, false);
+ qemu_mutex_lock(&client->lock);
+
if (ret < 0) {
error_prepend(&local_err, "Failed to send reply: ");
goto disconnect;
@@ -3044,11 +3111,13 @@ static coroutine_fn void nbd_trip(void *opaque)
goto disconnect;
}
- qio_channel_set_cork(client->ioc, false);
done:
if (req) {
nbd_request_put(req);
}
+
+ qemu_mutex_unlock(&client->lock);
+
if (!nbd_client_put_nonzero(client)) {
aio_co_reschedule_self(qemu_get_aio_context());
nbd_client_put(client);
@@ -3059,13 +3128,19 @@ disconnect:
if (local_err) {
error_reportf_err(local_err, "Disconnect client, due to: ");
}
+
nbd_request_put(req);
+ qemu_mutex_unlock(&client->lock);
aio_co_reschedule_self(qemu_get_aio_context());
client_close(client, true);
nbd_client_put(client);
}
+/*
+ * Runs in export AioContext and main loop thread. Caller must hold
+ * client->lock.
+ */
static void nbd_client_receive_next_request(NBDClient *client)
{
if (!client->recv_coroutine && client->nb_requests < MAX_NBD_REQUESTS &&
@@ -3091,7 +3166,9 @@ static coroutine_fn void nbd_co_client_start(void *opaque)
return;
}
- nbd_client_receive_next_request(client);
+ WITH_QEMU_LOCK_GUARD(&client->lock) {
+ nbd_client_receive_next_request(client);
+ }
}
/*
@@ -3108,6 +3185,7 @@ void nbd_client_new(QIOChannelSocket *sioc,
Coroutine *co;
client = g_new0(NBDClient, 1);
+ qemu_mutex_init(&client->lock);
client->refcount = 1;
client->tlscreds = tlscreds;
if (tlscreds) {
--
2.39.3

176
kvm-nbd-server-only-traverse-NBDExport-clients-from-main.patch
View File

@ -1,176 +0,0 @@
From 8b60d72532b6511b41d82d591fb4f509314ef15f Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Thu, 21 Dec 2023 14:24:51 -0500
Subject: [PATCH 071/101] nbd/server: only traverse NBDExport->clients from
main loop thread
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 214: Remove AioContext lock
RH-Jira: RHEL-15965
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Commit: [2/26] e7794a3a5c363c7508ee505c4ba03d9ef8862ca9 (kmwolf/centos-qemu-kvm)
The NBD clients list is currently accessed from both the export
AioContext and the main loop thread. When the AioContext lock is removed
there will be nothing protecting the clients list.
Adding a lock around the clients list is tricky because NBDClient
structs are refcounted and may be freed from the export AioContext or
the main loop thread. nbd_export_request_shutdown() -> client_close() ->
nbd_client_put() is also tricky because the list lock would be held
while indirectly dropping references to NDBClients.
A simpler approach is to only allow nbd_client_put() and client_close()
calls from the main loop thread. Then the NBD clients list is only
accessed from the main loop thread and no fancy locking is needed.
nbd_trip() just needs to reschedule itself in the main loop AioContext
before calling nbd_client_put() and client_close(). This costs more CPU
cycles per NBD request so add nbd_client_put_nonzero() to optimize the
common case where more references to NBDClient remain.
Note that nbd_client_get() can still be called from either thread, so
make NBDClient->refcount atomic.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-ID: <20231221192452.1785567-6-stefanha@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
nbd/server.c | 61 +++++++++++++++++++++++++++++++++++++++++++---------
1 file changed, 51 insertions(+), 10 deletions(-)
diff --git a/nbd/server.c b/nbd/server.c
index 0b09ccc8dc..e91e2e0903 100644
--- a/nbd/server.c
+++ b/nbd/server.c
@@ -122,7 +122,7 @@ struct NBDMetaContexts {
};
struct NBDClient {
- int refcount;
+ int refcount; /* atomic */
void (*close_fn)(NBDClient *client, bool negotiated);
NBDExport *exp;
@@ -1501,14 +1501,17 @@ static int coroutine_fn nbd_receive_request(NBDClient *client, NBDRequest *reque
#define MAX_NBD_REQUESTS 16
+/* Runs in export AioContext and main loop thread */
void nbd_client_get(NBDClient *client)
{
- client->refcount++;
+ qatomic_inc(&client->refcount);
}
void nbd_client_put(NBDClient *client)
{
- if (--client->refcount == 0) {
+ assert(qemu_in_main_thread());
+
+ if (qatomic_fetch_dec(&client->refcount) == 1) {
/* The last reference should be dropped by client->close,
* which is called by client_close.
*/
@@ -1529,8 +1532,35 @@ void nbd_client_put(NBDClient *client)
}
}
+/*
+ * Tries to release the reference to @client, but only if other references
+ * remain. This is an optimization for the common case where we want to avoid
+ * the expense of scheduling nbd_client_put() in the main loop thread.
+ *
+ * Returns true upon success or false if the reference was not released because
+ * it is the last reference.
+ */
+static bool nbd_client_put_nonzero(NBDClient *client)
+{
+ int old = qatomic_read(&client->refcount);
+ int expected;
+
+ do {
+ if (old == 1) {
+ return false;
+ }
+
+ expected = old;
+ old = qatomic_cmpxchg(&client->refcount, expected, expected - 1);
+ } while (old != expected);
+
+ return true;
+}
+
static void client_close(NBDClient *client, bool negotiated)
{
+ assert(qemu_in_main_thread());
+
if (client->closing) {
return;
}
@@ -2933,15 +2963,20 @@ static coroutine_fn int nbd_handle_request(NBDClient *client,
static coroutine_fn void nbd_trip(void *opaque)
{
NBDClient *client = opaque;
- NBDRequestData *req;
+ NBDRequestData *req = NULL;
NBDRequest request = { 0 }; /* GCC thinks it can be used uninitialized */
int ret;
Error *local_err = NULL;
+ /*
+ * Note that nbd_client_put() and client_close() must be called from the
+ * main loop thread. Use aio_co_reschedule_self() to switch AioContext
+ * before calling these functions.
+ */
+
trace_nbd_trip();
if (client->closing) {
- nbd_client_put(client);
- return;
+ goto done;
}
if (client->quiescing) {
@@ -2949,10 +2984,9 @@ static coroutine_fn void nbd_trip(void *opaque)
* We're switching between AIO contexts. Don't attempt to receive a new
* request and kick the main context which may be waiting for us.
*/
- nbd_client_put(client);
client->recv_coroutine = NULL;
aio_wait_kick();
- return;
+ goto done;
}
req = nbd_request_get(client);
@@ -3012,8 +3046,13 @@ static coroutine_fn void nbd_trip(void *opaque)
qio_channel_set_cork(client->ioc, false);
done:
- nbd_request_put(req);
- nbd_client_put(client);
+ if (req) {
+ nbd_request_put(req);
+ }
+ if (!nbd_client_put_nonzero(client)) {
+ aio_co_reschedule_self(qemu_get_aio_context());
+ nbd_client_put(client);
+ }
return;
disconnect:
@@ -3021,6 +3060,8 @@ disconnect:
error_reportf_err(local_err, "Disconnect client, due to: ");
}
nbd_request_put(req);
+
+ aio_co_reschedule_self(qemu_get_aio_context());
client_close(client, true);
nbd_client_put(client);
}
--
2.39.3

115
kvm-pc-q35-set-SMBIOS-entry-point-type-to-auto-by-defaul.patch
View File

@ -1,115 +0,0 @@
From 9ca64f73238d9f1b9f13d8e941ba42771a992afb Mon Sep 17 00:00:00 2001
From: Igor Mammedov <imammedo@redhat.com>
Date: Fri, 29 Dec 2023 14:06:05 +0100
Subject: [PATCH 20/20] pc/q35: set SMBIOS entry point type to 'auto' by
default
RH-Author: Igor Mammedov <imammedo@redhat.com>
RH-MergeRequest: 230: Workaround Windows failing to find 64bit SMBIOS entry point with SeaBIOS
RH-Jira: RHEL-21705
RH-Acked-by: MST <mst@redhat.com>
RH-Acked-by: Ani Sinha <None>
RH-Commit: [18/18] c7fc6ac7350bca3ff99e58620710a86218385781
JIRA: https://issues.redhat.com/browse/RHEL-21705
Use smbios-entry-point-type='auto' for newer machine types as a workaround
for Windows not detecting SMBIOS tables. Which makes QEMU pick SMBIOS tables
based on configuration (with 2.x preferred and fallback to 3.x if the former
isn't compatible with configuration)
Default compat setting of smbios-entry-point-type after series
for pc/q35 machines:
* 9.0-newer: 'auto'
* 8.1-8.2: '64'
* 8.0-older: '32'
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/2008
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Ani Sinha <anisinha@redhat.com>
Tested-by: Fiona Ebner <f.ebner@proxmox.com>
Conflicts: hw/i386/pc_piix.c hw/i386/pc_q35.c
due to RHEL machine types
REHL only parts:
Fix RHEL 'pc' machine types at SMBIOS 2.X
for the latest RHEL 'q35' machine type use version autoselect
which propagates to RHEL 9.4 q35 macine type while RHEL 9.2 q35 and older
are kept at SMBIOS_ENTRY_POINT_TYPE_32 (see: pc_q35_machine_rhel920_options)
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
---
hw/i386/pc.c | 2 +-
hw/i386/pc_piix.c | 7 +++++++
hw/i386/pc_q35.c | 5 +++++
3 files changed, 13 insertions(+), 1 deletion(-)
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index ae6777fc1a..d6f267b220 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -2004,7 +2004,7 @@ static void pc_machine_class_init(ObjectClass *oc, void *data)
mc->nvdimm_supported = true;
mc->smp_props.dies_supported = true;
mc->default_ram_id = "pc.ram";
- pcmc->default_smbios_ep_type = SMBIOS_ENTRY_POINT_TYPE_64;
+ pcmc->default_smbios_ep_type = SMBIOS_ENTRY_POINT_TYPE_AUTO;
object_class_property_add(oc, PC_MACHINE_MAX_RAM_BELOW_4G, "size",
pc_machine_get_max_ram_below_4g, pc_machine_set_max_ram_below_4g,
diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index 7344b35cf1..54d1c58bce 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -539,9 +539,14 @@ static void pc_i440fx_machine_options(MachineClass *m)
static void pc_i440fx_8_2_machine_options(MachineClass *m)
{
+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
+
pc_i440fx_machine_options(m);
m->alias = "pc";
m->is_default = true;
+
+ /* For pc-i44fx-8.2 and 8.1, use SMBIOS 3.X by default */
+ pcmc->default_smbios_ep_type = SMBIOS_ENTRY_POINT_TYPE_64;
}
DEFINE_I440FX_MACHINE(v8_2, "pc-i440fx-8.2", NULL,
@@ -982,6 +987,8 @@ static void pc_machine_rhel7_options(MachineClass *m)
m->alias = "pc";
m->is_default = 1;
m->smp_props.prefer_sockets = true;
+ /* there aren't ne PC macine types in RHEL9, keep it at SMBIOS 2.X */
+ pcmc->default_smbios_ep_type = SMBIOS_ENTRY_POINT_TYPE_32;
}
static void pc_init_rhel760(MachineState *machine)
diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index 9a22ff5dd6..cd5fb7380e 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -377,8 +377,11 @@ static void pc_q35_machine_options(MachineClass *m)
static void pc_q35_8_2_machine_options(MachineClass *m)
{
+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
pc_q35_machine_options(m);
m->alias = "q35";
+ /* For pc-q35-8.2 and 8.1, use SMBIOS 3.X by default */
+ pcmc->default_smbios_ep_type = SMBIOS_ENTRY_POINT_TYPE_64;
}
DEFINE_Q35_MACHINE(v8_2, "pc-q35-8.2", NULL,
@@ -712,6 +715,8 @@ static void pc_q35_machine_rhel_options(MachineClass *m)
m->alias = "q35";
m->max_cpus = 710;
compat_props_add(m->compat_props, pc_rhel_compat, pc_rhel_compat_len);
+ /* use SMBIOS version autoselect by default for the latest RHEL machine */
+ pcmc->default_smbios_ep_type = SMBIOS_ENTRY_POINT_TYPE_AUTO;
}
static void pc_q35_init_rhel940(MachineState *machine)
--
2.39.3

44
kvm-pc-smbios-fixup-manufacturer-product-version-to-matc.patch
View File

@ -1,44 +0,0 @@
From 03cad16743d9a4d377af66611d030eca9eda326d Mon Sep 17 00:00:00 2001
From: Igor Mammedov <imammedo@redhat.com>
Date: Tue, 19 Mar 2024 11:42:04 +0100
Subject: [PATCH 4/4] pc: smbios: fixup manufacturer/product/version to match
downstream
RH-Author: Igor Mammedov <imammedo@redhat.com>
RH-MergeRequest: 232: pc: smbios: fixup manufacturer/product/version to match downstream
RH-Jira: RHEL-21705
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Ani Sinha <anisinha@redhat.com>
RH-Commit: [1/1] 9235f64acb5ff46360282e889d0aedcb13374ac1
JIRA: https://issues.redhat.com/browse/RHEL-21705
commit [1] discarded RHEL only change that customizes
SMBIOS values for manufacturer/product/version for pc/q35
machine types.
Fix it up by reverting back to ("Red Hat", "KVM", mc->desc)
tuple.
1)
Fixes: 208239eb2 (hw/i386/pc: Defer smbios_set_defaults() to machine_done)
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
---
hw/i386/fw_cfg.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/hw/i386/fw_cfg.c b/hw/i386/fw_cfg.c
index 58429bb78d..d6a24177e2 100644
--- a/hw/i386/fw_cfg.c
+++ b/hw/i386/fw_cfg.c
@@ -63,7 +63,7 @@ void fw_cfg_build_smbios(PCMachineState *pcms, FWCfgState *fw_cfg,
if (pcmc->smbios_defaults) {
/* These values are guest ABI, do not change */
- smbios_set_defaults("QEMU", mc->desc, mc->name,
+ smbios_set_defaults("Red Hat", "KVM", mc->desc,
pcmc->smbios_uuid_encoded,
pcmc->smbios_stream_product,
pcmc->smbios_stream_version);
--
2.39.3

167
kvm-qdev-add-IOThreadVirtQueueMappingList-property-type.patch
View File

@ -1,167 +0,0 @@
From f1e82fe5076b4030d385dfa49b8284899386114d Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Wed, 20 Dec 2023 08:47:54 -0500
Subject: [PATCH 08/22] qdev: add IOThreadVirtQueueMappingList property type
RH-Author: Stefan Hajnoczi <stefanha@redhat.com>
RH-MergeRequest: 219: virtio-blk: add iothread-vq-mapping parameter
RH-Jira: RHEL-17369 RHEL-20764 RHEL-7356
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Commit: [4/17] 817aa1339da8ed3814730473342ba045e66d5b51 (stefanha/centos-stream-qemu-kvm)
virtio-blk and virtio-scsi devices will need a way to specify the
mapping between IOThreads and virtqueues. At the moment all virtqueues
are assigned to a single IOThread or the main loop. This single thread
can be a CPU bottleneck, so it is necessary to allow finer-grained
assignment to spread the load.
Introduce DEFINE_PROP_IOTHREAD_VQ_MAPPING_LIST() so devices can take a
parameter that maps virtqueues to IOThreads. The command-line syntax for
this new property is as follows:
--device '{"driver":"foo","iothread-vq-mapping":[{"iothread":"iothread0","vqs":[0,1,2]},...]}'
IOThreads are specified by name and virtqueues are specified by 0-based
index.
It will be common to simply assign virtqueues round-robin across a set
of IOThreads. A convenient syntax that does not require specifying
individual virtqueue indices is available:
--device '{"driver":"foo","iothread-vq-mapping":[{"iothread":"iothread0"},{"iothread":"iothread1"},...]}'
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-ID: <20231220134755.814917-4-stefanha@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit cf03a152c5d749fd0083bfe540df9524f1d2ff1d)
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
hw/core/qdev-properties-system.c | 46 +++++++++++++++++++++++++++++
include/hw/qdev-properties-system.h | 5 ++++
qapi/virtio.json | 29 ++++++++++++++++++
3 files changed, 80 insertions(+)
diff --git a/hw/core/qdev-properties-system.c b/hw/core/qdev-properties-system.c
index 73cced4626..1a396521d5 100644
--- a/hw/core/qdev-properties-system.c
+++ b/hw/core/qdev-properties-system.c
@@ -18,6 +18,7 @@
#include "qapi/qapi-types-block.h"
#include "qapi/qapi-types-machine.h"
#include "qapi/qapi-types-migration.h"
+#include "qapi/qapi-visit-virtio.h"
#include "qapi/qmp/qerror.h"
#include "qemu/ctype.h"
#include "qemu/cutils.h"
@@ -1160,3 +1161,48 @@ const PropertyInfo qdev_prop_cpus390entitlement = {
.set = qdev_propinfo_set_enum,
.set_default_value = qdev_propinfo_set_default_value_enum,
};
+
+/* --- IOThreadVirtQueueMappingList --- */
+
+static void get_iothread_vq_mapping_list(Object *obj, Visitor *v,
+ const char *name, void *opaque, Error **errp)
+{
+ IOThreadVirtQueueMappingList **prop_ptr =
+ object_field_prop_ptr(obj, opaque);
+
+ visit_type_IOThreadVirtQueueMappingList(v, name, prop_ptr, errp);
+}
+
+static void set_iothread_vq_mapping_list(Object *obj, Visitor *v,
+ const char *name, void *opaque, Error **errp)
+{
+ IOThreadVirtQueueMappingList **prop_ptr =
+ object_field_prop_ptr(obj, opaque);
+ IOThreadVirtQueueMappingList *list;
+
+ if (!visit_type_IOThreadVirtQueueMappingList(v, name, &list, errp)) {
+ return;
+ }
+
+ qapi_free_IOThreadVirtQueueMappingList(*prop_ptr);
+ *prop_ptr = list;
+}
+
+static void release_iothread_vq_mapping_list(Object *obj,
+ const char *name, void *opaque)
+{
+ IOThreadVirtQueueMappingList **prop_ptr =
+ object_field_prop_ptr(obj, opaque);
+
+ qapi_free_IOThreadVirtQueueMappingList(*prop_ptr);
+ *prop_ptr = NULL;
+}
+
+const PropertyInfo qdev_prop_iothread_vq_mapping_list = {
+ .name = "IOThreadVirtQueueMappingList",
+ .description = "IOThread virtqueue mapping list [{\"iothread\":\"<id>\", "
+ "\"vqs\":[1,2,3,...]},...]",
+ .get = get_iothread_vq_mapping_list,
+ .set = set_iothread_vq_mapping_list,
+ .release = release_iothread_vq_mapping_list,
+};
diff --git a/include/hw/qdev-properties-system.h b/include/hw/qdev-properties-system.h
index 91f7a2452d..06c359c190 100644
--- a/include/hw/qdev-properties-system.h
+++ b/include/hw/qdev-properties-system.h
@@ -24,6 +24,7 @@ extern const PropertyInfo qdev_prop_off_auto_pcibar;
extern const PropertyInfo qdev_prop_pcie_link_speed;
extern const PropertyInfo qdev_prop_pcie_link_width;
extern const PropertyInfo qdev_prop_cpus390entitlement;
+extern const PropertyInfo qdev_prop_iothread_vq_mapping_list;
#define DEFINE_PROP_PCI_DEVFN(_n, _s, _f, _d) \
DEFINE_PROP_SIGNED(_n, _s, _f, _d, qdev_prop_pci_devfn, int32_t)
@@ -82,4 +83,8 @@ extern const PropertyInfo qdev_prop_cpus390entitlement;
DEFINE_PROP_SIGNED(_n, _s, _f, _d, qdev_prop_cpus390entitlement, \
CpuS390Entitlement)
+#define DEFINE_PROP_IOTHREAD_VQ_MAPPING_LIST(_name, _state, _field) \
+ DEFINE_PROP(_name, _state, _field, qdev_prop_iothread_vq_mapping_list, \
+ IOThreadVirtQueueMappingList *)
+
#endif
diff --git a/qapi/virtio.json b/qapi/virtio.json
index e6dcee7b83..19c7c36e36 100644
--- a/qapi/virtio.json
+++ b/qapi/virtio.json
@@ -928,3 +928,32 @@
'data': { 'path': 'str', 'queue': 'uint16', '*index': 'uint16' },
'returns': 'VirtioQueueElement',
'features': [ 'unstable' ] }
+
+##
+# @IOThreadVirtQueueMapping:
+#
+# Describes the subset of virtqueues assigned to an IOThread.
+#
+# @iothread: the id of IOThread object
+#
+# @vqs: an optional array of virtqueue indices that will be handled by this
+# IOThread. When absent, virtqueues are assigned round-robin across all
+# IOThreadVirtQueueMappings provided. Either all IOThreadVirtQueueMappings
+# must have @vqs or none of them must have it.
+#
+# Since: 9.0
+##
+
+{ 'struct': 'IOThreadVirtQueueMapping',
+ 'data': { 'iothread': 'str', '*vqs': ['uint16'] } }
+
+##
+# @DummyVirtioForceArrays:
+#
+# Not used by QMP; hack to let us use IOThreadVirtQueueMappingList internally
+#
+# Since: 9.0
+##
+
+{ 'struct': 'DummyVirtioForceArrays',
+ 'data': { 'unused-iothread-vq-mapping': ['IOThreadVirtQueueMapping'] } }
--
2.39.3

85
kvm-qdev-properties-alias-all-object-class-properties.patch
View File

@ -1,85 +0,0 @@
From 4251aab5b2beb68d1800cd4a329361ff6f57c430 Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Wed, 20 Dec 2023 08:47:52 -0500
Subject: [PATCH 07/22] qdev-properties: alias all object class properties
RH-Author: Stefan Hajnoczi <stefanha@redhat.com>
RH-MergeRequest: 219: virtio-blk: add iothread-vq-mapping parameter
RH-Jira: RHEL-17369 RHEL-20764 RHEL-7356
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Commit: [3/17] bc5d0aafe4645dacf9277904a2b20760d6e676e1 (stefanha/centos-stream-qemu-kvm)
qdev_alias_all_properties() aliases a DeviceState's qdev properties onto
an Object. This is used for VirtioPCIProxy types so that --device
virtio-blk-pci has properties of its embedded --device virtio-blk-device
object.
Currently this function is implemented using qdev properties. Change the
function to use QOM object class properties instead. This works because
qdev properties create QOM object class properties, but it also catches
any QOM object class-only properties that have no qdev properties.
This change ensures that properties of devices are shown with --device
foo,\? even if they are QOM object class properties.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-ID: <20231220134755.814917-2-stefanha@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 350147a871a545ab56b4a1062c8485635d9ffc24)
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
hw/core/qdev-properties.c | 18 ++++++++++--------
include/hw/qdev-properties.h | 4 ++--
2 files changed, 12 insertions(+), 10 deletions(-)
diff --git a/hw/core/qdev-properties.c b/hw/core/qdev-properties.c
index 840006e953..7d6fa726fd 100644
--- a/hw/core/qdev-properties.c
+++ b/hw/core/qdev-properties.c
@@ -1076,16 +1076,18 @@ void device_class_set_props(DeviceClass *dc, Property *props)
void qdev_alias_all_properties(DeviceState *target, Object *source)
{
ObjectClass *class;
- Property *prop;
+ ObjectPropertyIterator iter;
+ ObjectProperty *prop;
class = object_get_class(OBJECT(target));
- do {
- DeviceClass *dc = DEVICE_CLASS(class);
- for (prop = dc->props_; prop && prop->name; prop++) {
- object_property_add_alias(source, prop->name,
- OBJECT(target), prop->name);
+ object_class_property_iter_init(&iter, class);
+ while ((prop = object_property_iter_next(&iter))) {
+ if (object_property_find(source, prop->name)) {
+ continue; /* skip duplicate properties */
}
- class = object_class_get_parent(class);
- } while (class != object_class_by_name(TYPE_DEVICE));
+
+ object_property_add_alias(source, prop->name,
+ OBJECT(target), prop->name);
+ }
}
diff --git a/include/hw/qdev-properties.h b/include/hw/qdev-properties.h
index 25743a29a0..09aa04ca1e 100644
--- a/include/hw/qdev-properties.h
+++ b/include/hw/qdev-properties.h
@@ -230,8 +230,8 @@ void qdev_property_add_static(DeviceState *dev, Property *prop);
* @target: Device which has properties to be aliased
* @source: Object to add alias properties to
*
- * Add alias properties to the @source object for all qdev properties on
- * the @target DeviceState.
+ * Add alias properties to the @source object for all properties on the @target
+ * DeviceState.
*
* This is useful when @target is an internal implementation object
* owned by @source, and you want to expose all the properties of that
--
2.39.3

135
kvm-qemu_init-increase-NOFILE-soft-limit-on-POSIX.patch
View File

@ -1,135 +0,0 @@
From f2fe6c7a2def488633cbb67e28ac00279d6e8de4 Mon Sep 17 00:00:00 2001
From: Cornelia Huck <cohuck@redhat.com>
Date: Tue, 27 Feb 2024 11:17:39 +0100
Subject: [PATCH 1/2] qemu_init: increase NOFILE soft limit on POSIX
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Cornelia Huck <cohuck@redhat.com>
RH-MergeRequest: 226: qemu_init: increase NOFILE soft limit on POSIX
RH-Jira: RHEL-26049
RH-Acked-by: Gavin Shan <gshan@redhat.com>
RH-Acked-by: Ani Sinha <None>
RH-Acked-by: Shaoqin Huang <None>
RH-Commit: [1/1] cee5404aef3f6437d45a1c43bdee73a57a528bee (cohuck/qemu-kvm-c9s)
Jira: https://issues.redhat.com/browse/RHEL-26049
In many configurations, e.g. multiple vNICs with multiple queues or
with many Ceph OSDs, the default soft limit of 1024 is not enough.
QEMU is supposed to work fine with file descriptors >= 1024 and does
not use select() on POSIX. Bump the soft limit to the allowed hard
limit to avoid issues with the aforementioned configurations.
Of course the limit could be raised from the outside, but the man page
of systemd.exec states about 'LimitNOFILE=':
> Don't use.
> [...]
> Typically applications should increase their soft limit to the hard
> limit on their own, if they are OK with working with file
> descriptors above 1023,
If the soft limit is already the same as the hard limit, avoid the
superfluous setrlimit call. This can avoid a warning with a strict
seccomp filter blocking setrlimit if NOFILE was already raised before
executing QEMU.
Buglink: https://bugzilla.proxmox.com/show_bug.cgi?id=4507
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
(cherry picked from commit 03e471c41d8b1b6eb16c9714f387449f52fe5c1d)
Signed-off-by: Cornelia Huck <cohuck@redhat.com>
---
include/sysemu/os-posix.h | 1 +
include/sysemu/os-win32.h | 5 +++++
os-posix.c | 22 ++++++++++++++++++++++
system/vl.c | 2 ++
4 files changed, 30 insertions(+)
diff --git a/include/sysemu/os-posix.h b/include/sysemu/os-posix.h
index dff32ae185..b881ac6c6f 100644
--- a/include/sysemu/os-posix.h
+++ b/include/sysemu/os-posix.h
@@ -51,6 +51,7 @@ bool is_daemonized(void);
void os_daemonize(void);
bool os_set_runas(const char *user_id);
void os_set_chroot(const char *path);
+void os_setup_limits(void);
void os_setup_post(void);
int os_mlock(void);
diff --git a/include/sysemu/os-win32.h b/include/sysemu/os-win32.h
index 1047d260cb..b82a5d3ad9 100644
--- a/include/sysemu/os-win32.h
+++ b/include/sysemu/os-win32.h
@@ -128,6 +128,11 @@ static inline int os_mlock(void)
return -ENOSYS;
}
+static inline void os_setup_limits(void)
+{
+ return;
+}
+
#define fsync _commit
#if !defined(lseek)
diff --git a/os-posix.c b/os-posix.c
index 52ef6990ff..a4284e2c07 100644
--- a/os-posix.c
+++ b/os-posix.c
@@ -24,6 +24,7 @@
*/
#include "qemu/osdep.h"
+#include <sys/resource.h>
#include <sys/wait.h>
#include <pwd.h>
#include <grp.h>
@@ -256,6 +257,27 @@ void os_daemonize(void)
}
}
+void os_setup_limits(void)
+{
+ struct rlimit nofile;
+
+ if (getrlimit(RLIMIT_NOFILE, &nofile) < 0) {
+ warn_report("unable to query NOFILE limit: %s", strerror(errno));
+ return;
+ }
+
+ if (nofile.rlim_cur == nofile.rlim_max) {
+ return;
+ }
+
+ nofile.rlim_cur = nofile.rlim_max;
+
+ if (setrlimit(RLIMIT_NOFILE, &nofile) < 0) {
+ warn_report("unable to set NOFILE limit: %s", strerror(errno));
+ return;
+ }
+}
+
void os_setup_post(void)
{
int fd = 0;
diff --git a/system/vl.c b/system/vl.c
index 93635ffc5b..6443b6e469 100644
--- a/system/vl.c
+++ b/system/vl.c
@@ -2783,6 +2783,8 @@ void qemu_init(int argc, char **argv)
error_init(argv[0]);
qemu_init_exec_dir(argv[0]);
+ os_setup_limits();
+
qemu_init_arch_modules();
qemu_init_subsystems();
--
2.39.3

106
kvm-s390x-pci-avoid-double-enable-disable-of-aif.patch
View File

@ -1,106 +0,0 @@
From 64b0180f5a52668f8ac4c444ba369231dbc4d5b9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= <clg@redhat.com>
Date: Mon, 22 Jan 2024 09:25:53 +0100
Subject: [PATCH 096/101] s390x/pci: avoid double enable/disable of aif
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Cédric Le Goater <clg@redhat.com>
RH-MergeRequest: 215: s390x: Fix reset ordering of passthrough ISM devices
RH-Jira: RHEL-21169
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Commit: [1/3] ebdf8a474ea21486f5ec051683f17bae6d20f675 (clegoate/qemu-kvm-c9s)
JIRA: https://issues.redhat.com/browse/RHEL-21169
commit 07b2c8e034d80ff92e202405c494d2ff80fcf848
Author: Matthew Rosato <mjrosato@linux.ibm.com>
Date: Thu Jan 18 13:51:49 2024 -0500
s390x/pci: avoid double enable/disable of aif
Use a flag to keep track of whether AIF is currently enabled. This can be
used to avoid enabling/disabling AIF multiple times as well as to determine
whether or not it should be disabled during reset processing.
Fixes: d0bc7091c2 ("s390x/pci: enable adapter event notification for interpreted devices")
Reported-by: Cédric Le Goater <clg@redhat.com>
Reviewed-by: Eric Farman <farman@linux.ibm.com>
Signed-off-by: Matthew Rosato <mjrosato@linux.ibm.com>
Message-ID: <20240118185151.265329-2-mjrosato@linux.ibm.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
hw/s390x/s390-pci-kvm.c | 25 +++++++++++++++++++++++--
include/hw/s390x/s390-pci-bus.h | 1 +
2 files changed, 24 insertions(+), 2 deletions(-)
diff --git a/hw/s390x/s390-pci-kvm.c b/hw/s390x/s390-pci-kvm.c
index ff41e4106d..1ee510436c 100644
--- a/hw/s390x/s390-pci-kvm.c
+++ b/hw/s390x/s390-pci-kvm.c
@@ -27,6 +27,7 @@ bool s390_pci_kvm_interp_allowed(void)
int s390_pci_kvm_aif_enable(S390PCIBusDevice *pbdev, ZpciFib *fib, bool assist)
{
+ int rc;
struct kvm_s390_zpci_op args = {
.fh = pbdev->fh,
.op = KVM_S390_ZPCIOP_REG_AEN,
@@ -38,15 +39,35 @@ int s390_pci_kvm_aif_enable(S390PCIBusDevice *pbdev, ZpciFib *fib, bool assist)
.u.reg_aen.flags = (assist) ? 0 : KVM_S390_ZPCIOP_REGAEN_HOST
};
- return kvm_vm_ioctl(kvm_state, KVM_S390_ZPCI_OP, &args);
+ if (pbdev->aif) {
+ return -EINVAL;
+ }
+
+ rc = kvm_vm_ioctl(kvm_state, KVM_S390_ZPCI_OP, &args);
+ if (rc == 0) {
+ pbdev->aif = true;
+ }
+
+ return rc;
}
int s390_pci_kvm_aif_disable(S390PCIBusDevice *pbdev)
{
+ int rc;
+
struct kvm_s390_zpci_op args = {
.fh = pbdev->fh,
.op = KVM_S390_ZPCIOP_DEREG_AEN
};
- return kvm_vm_ioctl(kvm_state, KVM_S390_ZPCI_OP, &args);
+ if (!pbdev->aif) {
+ return -EINVAL;
+ }
+
+ rc = kvm_vm_ioctl(kvm_state, KVM_S390_ZPCI_OP, &args);
+ if (rc == 0) {
+ pbdev->aif = false;
+ }
+
+ return rc;
}
diff --git a/include/hw/s390x/s390-pci-bus.h b/include/hw/s390x/s390-pci-bus.h
index b1bdbeaeb5..435e788867 100644
--- a/include/hw/s390x/s390-pci-bus.h
+++ b/include/hw/s390x/s390-pci-bus.h
@@ -361,6 +361,7 @@ struct S390PCIBusDevice {
bool unplug_requested;
bool interp;
bool forwarding_assist;
+ bool aif;
QTAILQ_ENTRY(S390PCIBusDevice) link;
};
--
2.39.3

137
kvm-s390x-pci-drive-ISM-reset-from-subsystem-reset.patch
View File

@ -1,137 +0,0 @@
From c885b17e09ab19a3e8d3b2e1765963811af6f764 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= <clg@redhat.com>
Date: Mon, 22 Jan 2024 09:25:53 +0100
Subject: [PATCH 098/101] s390x/pci: drive ISM reset from subsystem reset
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Cédric Le Goater <clg@redhat.com>
RH-MergeRequest: 215: s390x: Fix reset ordering of passthrough ISM devices
RH-Jira: RHEL-21169
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Commit: [3/3] 426cf156a2c67e6dcd7483a769fa3741e2700504 (clegoate/qemu-kvm-c9s)
JIRA: https://issues.redhat.com/browse/RHEL-21169
commit 68c691ca99a2538d6a53a70ce8a9ce06ee307ff1
Author: Matthew Rosato <mjrosato@linux.ibm.com>
Date: Thu Jan 18 13:51:51 2024 -0500
s390x/pci: drive ISM reset from subsystem reset
ISM devices are sensitive to manipulation of the IOMMU, so the ISM device
needs to be reset before the vfio-pci device is reset (triggering a full
UNMAP). In order to ensure this occurs, trigger ISM device resets from
subsystem_reset before triggering the PCI bus reset (which will also
trigger vfio-pci reset). This only needs to be done for ISM devices
which were enabled for use by the guest.
Further, ensure that AIF is disabled as part of the reset event.
Fixes: ef1535901a ("s390x: do a subsystem reset before the unprotect on reboot")
Fixes: 03451953c7 ("s390x/pci: reset ISM passthrough devices on shutdown and system reset")
Reported-by: Cédric Le Goater <clg@redhat.com>
Signed-off-by: Matthew Rosato <mjrosato@linux.ibm.com>
Message-ID: <20240118185151.265329-4-mjrosato@linux.ibm.com>
Reviewed-by: Eric Farman <farman@linux.ibm.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
hw/s390x/s390-pci-bus.c | 26 +++++++++++++++++---------
hw/s390x/s390-virtio-ccw.c | 8 ++++++++
include/hw/s390x/s390-pci-bus.h | 1 +
3 files changed, 26 insertions(+), 9 deletions(-)
diff --git a/hw/s390x/s390-pci-bus.c b/hw/s390x/s390-pci-bus.c
index 347580ebac..3e57d5faca 100644
--- a/hw/s390x/s390-pci-bus.c
+++ b/hw/s390x/s390-pci-bus.c
@@ -151,20 +151,12 @@ static void s390_pci_shutdown_notifier(Notifier *n, void *opaque)
pci_device_reset(pbdev->pdev);
}
-static void s390_pci_reset_cb(void *opaque)
-{
- S390PCIBusDevice *pbdev = opaque;
-
- pci_device_reset(pbdev->pdev);
-}
-
static void s390_pci_perform_unplug(S390PCIBusDevice *pbdev)
{
HotplugHandler *hotplug_ctrl;
if (pbdev->pft == ZPCI_PFT_ISM) {
notifier_remove(&pbdev->shutdown_notifier);
- qemu_unregister_reset(s390_pci_reset_cb, pbdev);
}
/* Unplug the PCI device */
@@ -1132,7 +1124,6 @@ static void s390_pcihost_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
if (pbdev->pft == ZPCI_PFT_ISM) {
pbdev->shutdown_notifier.notify = s390_pci_shutdown_notifier;
qemu_register_shutdown_notifier(&pbdev->shutdown_notifier);
- qemu_register_reset(s390_pci_reset_cb, pbdev);
}
} else {
pbdev->fh |= FH_SHM_EMUL;
@@ -1279,6 +1270,23 @@ static void s390_pci_enumerate_bridge(PCIBus *bus, PCIDevice *pdev,
pci_default_write_config(pdev, PCI_SUBORDINATE_BUS, s->bus_no, 1);
}
+void s390_pci_ism_reset(void)
+{
+ S390pciState *s = s390_get_phb();
+
+ S390PCIBusDevice *pbdev, *next;
+
+ /* Trigger reset event for each passthrough ISM device currently in-use */
+ QTAILQ_FOREACH_SAFE(pbdev, &s->zpci_devs, link, next) {
+ if (pbdev->interp && pbdev->pft == ZPCI_PFT_ISM &&
+ pbdev->fh & FH_MASK_ENABLE) {
+ s390_pci_kvm_aif_disable(pbdev);
+
+ pci_device_reset(pbdev->pdev);
+ }
+ }
+}
+
static void s390_pcihost_reset(DeviceState *dev)
{
S390pciState *s = S390_PCI_HOST_BRIDGE(dev);
diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
index e26ce26f5a..24f4773179 100644
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -118,6 +118,14 @@ static void subsystem_reset(void)
DeviceState *dev;
int i;
+ /*
+ * ISM firmware is sensitive to unexpected changes to the IOMMU, which can
+ * occur during reset of the vfio-pci device (unmap of entire aperture).
+ * Ensure any passthrough ISM devices are reset now, while CPUs are paused
+ * but before vfio-pci cleanup occurs.
+ */
+ s390_pci_ism_reset();
+
for (i = 0; i < ARRAY_SIZE(reset_dev_types); i++) {
dev = DEVICE(object_resolve_path_type("", reset_dev_types[i], NULL));
if (dev) {
diff --git a/include/hw/s390x/s390-pci-bus.h b/include/hw/s390x/s390-pci-bus.h
index 435e788867..2c43ea123f 100644
--- a/include/hw/s390x/s390-pci-bus.h
+++ b/include/hw/s390x/s390-pci-bus.h
@@ -401,5 +401,6 @@ S390PCIBusDevice *s390_pci_find_dev_by_target(S390pciState *s,
const char *target);
S390PCIBusDevice *s390_pci_find_next_avail_dev(S390pciState *s,
S390PCIBusDevice *pbdev);
+void s390_pci_ism_reset(void);
#endif
--
2.39.3

71
kvm-s390x-pci-refresh-fh-before-disabling-aif.patch
View File

@ -1,71 +0,0 @@
From 49078bdfd4c116da3e920632ec6f7041f1b38015 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= <clg@redhat.com>
Date: Mon, 22 Jan 2024 09:25:53 +0100
Subject: [PATCH 097/101] s390x/pci: refresh fh before disabling aif
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Cédric Le Goater <clg@redhat.com>
RH-MergeRequest: 215: s390x: Fix reset ordering of passthrough ISM devices
RH-Jira: RHEL-21169
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Commit: [2/3] 3523067909c41818dfc769abdb93930833416c11 (clegoate/qemu-kvm-c9s)
JIRA: https://issues.redhat.com/browse/RHEL-21169
commit 30e35258e25c75c9d799c34fd89afcafffb37084
Author: Matthew Rosato <mjrosato@linux.ibm.com>
Date: Thu Jan 18 13:51:50 2024 -0500
s390x/pci: refresh fh before disabling aif
Typically we refresh the host fh during CLP enable, however it's possible
that the device goes through multiple reset events before the guest
performs another CLP enable. Let's handle this for now by refreshing the
host handle from vfio before disabling aif.
Fixes: 03451953c7 ("s390x/pci: reset ISM passthrough devices on shutdown and system reset")
Reported-by: Cédric Le Goater <clg@redhat.com>
Reviewed-by: Eric Farman <farman@linux.ibm.com>
Signed-off-by: Matthew Rosato <mjrosato@linux.ibm.com>
Message-ID: <20240118185151.265329-3-mjrosato@linux.ibm.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
hw/s390x/s390-pci-kvm.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/hw/s390x/s390-pci-kvm.c b/hw/s390x/s390-pci-kvm.c
index 1ee510436c..9eef4fc3ec 100644
--- a/hw/s390x/s390-pci-kvm.c
+++ b/hw/s390x/s390-pci-kvm.c
@@ -18,6 +18,7 @@
#include "hw/s390x/s390-pci-bus.h"
#include "hw/s390x/s390-pci-kvm.h"
#include "hw/s390x/s390-pci-inst.h"
+#include "hw/s390x/s390-pci-vfio.h"
#include "cpu_models.h"
bool s390_pci_kvm_interp_allowed(void)
@@ -64,6 +65,14 @@ int s390_pci_kvm_aif_disable(S390PCIBusDevice *pbdev)
return -EINVAL;
}
+ /*
+ * The device may have already been reset but we still want to relinquish
+ * the guest ISC, so always be sure to use an up-to-date host fh.
+ */
+ if (!s390_pci_get_host_fh(pbdev, &args.fh)) {
+ return -EPERM;
+ }
+
rc = kvm_vm_ioctl(kvm_state, KVM_S390_ZPCI_OP, &args);
if (rc == 0) {
pbdev->aif = false;
--
2.39.3

124
kvm-scsi-Await-request-purging.patch
View File

@ -1,124 +0,0 @@
From 94d6458a58239b52394d58b6880509041186d5a8 Mon Sep 17 00:00:00 2001
From: Hanna Czenczek <hreitz@redhat.com>
Date: Fri, 2 Feb 2024 15:47:55 +0100
Subject: [PATCH 04/22] scsi: Await request purging
RH-Author: Hanna Czenczek <hreitz@redhat.com>
RH-MergeRequest: 222: Allow concurrent BlockBackend context changes
RH-Jira: RHEL-24593
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [2/2] 35a89273cab0af8f999881e67d359fe1328363a0 (hreitz/qemu-kvm-c-9-s)
scsi_device_for_each_req_async() currently does not provide any way to
be awaited. One of its callers is scsi_device_purge_requests(), which
therefore currently does not guarantee that all requests are fully
settled when it returns.
We want all requests to be settled, because scsi_device_purge_requests()
is called through the unrealize path, including the one invoked by
virtio_scsi_hotunplug() through qdev_simple_device_unplug_cb(), which
most likely assumes that all SCSI requests are done then.
In fact, scsi_device_purge_requests() already contains a blk_drain(),
but this will not fully await scsi_device_for_each_req_async(), only the
I/O requests it potentially cancels (not the non-I/O requests).
However, we can have scsi_device_for_each_req_async() increment the BB
in-flight counter, and have scsi_device_for_each_req_async_bh()
decrement it when it is done. This way, the blk_drain() will fully
await all SCSI requests to be purged.
This also removes the need for scsi_device_for_each_req_async_bh() to
double-check the current context and potentially re-schedule itself,
should it now differ from the BB's context: Changing a BB's AioContext
with a root node is done through bdrv_try_change_aio_context(), which
creates a drained section. With this patch, we keep the BB in-flight
counter elevated throughout, so we know the BB's context cannot change.
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
Message-ID: <20240202144755.671354-3-hreitz@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 1604c0493193273e4eac547f86fbd2845e7f9af4)
---
hw/scsi/scsi-bus.c | 30 +++++++++++++++++++++---------
1 file changed, 21 insertions(+), 9 deletions(-)
diff --git a/hw/scsi/scsi-bus.c b/hw/scsi/scsi-bus.c
index 5b08cbf60a..b1bf8e6433 100644
--- a/hw/scsi/scsi-bus.c
+++ b/hw/scsi/scsi-bus.c
@@ -120,17 +120,13 @@ static void scsi_device_for_each_req_async_bh(void *opaque)
SCSIRequest *next;
/*
- * If the AioContext changed before this BH was called then reschedule into
- * the new AioContext before accessing ->requests. This can happen when
- * scsi_device_for_each_req_async() is called and then the AioContext is
- * changed before BHs are run.
+ * The BB cannot have changed contexts between this BH being scheduled and
+ * now: BBs' AioContexts, when they have a node attached, can only be
+ * changed via bdrv_try_change_aio_context(), in a drained section. While
+ * we have the in-flight counter incremented, that drain must block.
*/
ctx = blk_get_aio_context(s->conf.blk);
- if (ctx != qemu_get_current_aio_context()) {
- aio_bh_schedule_oneshot(ctx, scsi_device_for_each_req_async_bh,
- g_steal_pointer(&data));
- return;
- }
+ assert(ctx == qemu_get_current_aio_context());
QTAILQ_FOREACH_SAFE(req, &s->requests, next, next) {
data->fn(req, data->fn_opaque);
@@ -138,11 +134,16 @@ static void scsi_device_for_each_req_async_bh(void *opaque)
/* Drop the reference taken by scsi_device_for_each_req_async() */
object_unref(OBJECT(s));
+
+ /* Paired with blk_inc_in_flight() in scsi_device_for_each_req_async() */
+ blk_dec_in_flight(s->conf.blk);
}
/*
* Schedule @fn() to be invoked for each enqueued request in device @s. @fn()
* runs in the AioContext that is executing the request.
+ * Keeps the BlockBackend's in-flight counter incremented until everything is
+ * done, so draining it will settle all scheduled @fn() calls.
*/
static void scsi_device_for_each_req_async(SCSIDevice *s,
void (*fn)(SCSIRequest *, void *),
@@ -163,6 +164,8 @@ static void scsi_device_for_each_req_async(SCSIDevice *s,
*/
object_ref(OBJECT(s));
+ /* Paired with blk_dec_in_flight() in scsi_device_for_each_req_async_bh() */
+ blk_inc_in_flight(s->conf.blk);
aio_bh_schedule_oneshot(blk_get_aio_context(s->conf.blk),
scsi_device_for_each_req_async_bh,
data);
@@ -1728,11 +1731,20 @@ static void scsi_device_purge_one_req(SCSIRequest *req, void *opaque)
scsi_req_cancel_async(req, NULL);
}
+/**
+ * Cancel all requests, and block until they are deleted.
+ */
void scsi_device_purge_requests(SCSIDevice *sdev, SCSISense sense)
{
scsi_device_for_each_req_async(sdev, scsi_device_purge_one_req, NULL);
+ /*
+ * Await all the scsi_device_purge_one_req() calls scheduled by
+ * scsi_device_for_each_req_async(), and all I/O requests that were
+ * cancelled this way, but may still take a bit of time to settle.
+ */
blk_drain(sdev->conf.blk);
+
scsi_device_set_ua(sdev, sense);
}
--
2.39.3

88
kvm-scsi-assert-that-callbacks-run-in-the-correct-AioCon.patch
View File

@ -1,88 +0,0 @@
From cd08d22a0da022d99fe6cfddb7de680abf66c8be Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Tue, 5 Dec 2023 13:19:59 -0500
Subject: [PATCH 082/101] scsi: assert that callbacks run in the correct
AioContext
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 214: Remove AioContext lock
RH-Jira: RHEL-15965
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Commit: [13/26] d2fd5065c3b72d9d2f4e37efee39fe12eba0f0a9 (kmwolf/centos-qemu-kvm)
Since the removal of AioContext locking, the correctness of the code
relies on running requests from a single AioContext at any given time.
Add assertions that verify that callbacks are invoked in the correct
AioContext.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-ID: <20231205182011.1976568-3-stefanha@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
hw/scsi/scsi-disk.c | 14 ++++++++++++++
system/dma-helpers.c | 3 +++
2 files changed, 17 insertions(+)
diff --git a/hw/scsi/scsi-disk.c b/hw/scsi/scsi-disk.c
index 2c1bbb3530..a5048e0aaf 100644
--- a/hw/scsi/scsi-disk.c
+++ b/hw/scsi/scsi-disk.c
@@ -273,6 +273,10 @@ static void scsi_aio_complete(void *opaque, int ret)
SCSIDiskReq *r = (SCSIDiskReq *)opaque;
SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, r->req.dev);
+ /* The request must only run in the BlockBackend's AioContext */
+ assert(blk_get_aio_context(s->qdev.conf.blk) ==
+ qemu_get_current_aio_context());
+
assert(r->req.aiocb != NULL);
r->req.aiocb = NULL;
@@ -370,8 +374,13 @@ static void scsi_dma_complete(void *opaque, int ret)
static void scsi_read_complete_noio(SCSIDiskReq *r, int ret)
{
+ SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, r->req.dev);
uint32_t n;
+ /* The request must only run in the BlockBackend's AioContext */
+ assert(blk_get_aio_context(s->qdev.conf.blk) ==
+ qemu_get_current_aio_context());
+
assert(r->req.aiocb == NULL);
if (scsi_disk_req_check_error(r, ret, false)) {
goto done;
@@ -496,8 +505,13 @@ static void scsi_read_data(SCSIRequest *req)
static void scsi_write_complete_noio(SCSIDiskReq *r, int ret)
{
+ SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, r->req.dev);
uint32_t n;
+ /* The request must only run in the BlockBackend's AioContext */
+ assert(blk_get_aio_context(s->qdev.conf.blk) ==
+ qemu_get_current_aio_context());
+
assert (r->req.aiocb == NULL);
if (scsi_disk_req_check_error(r, ret, false)) {
goto done;
diff --git a/system/dma-helpers.c b/system/dma-helpers.c
index 528117f256..9b221cf94e 100644
--- a/system/dma-helpers.c
+++ b/system/dma-helpers.c
@@ -119,6 +119,9 @@ static void dma_blk_cb(void *opaque, int ret)
trace_dma_blk_cb(dbs, ret);
+ /* DMAAIOCB is not thread-safe and must be accessed only from dbs->ctx */
+ assert(ctx == qemu_get_current_aio_context());
+
dbs->acb = NULL;
dbs->offset += dbs->iov.size;
--
2.39.3

245
kvm-scsi-don-t-lock-AioContext-in-I-O-code-path.patch
View File

@ -1,245 +0,0 @@
From d1d384bd24a7aeb527f4abd8a0958146544ef9bb Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Mon, 4 Dec 2023 11:42:58 -0500
Subject: [PATCH 079/101] scsi: don't lock AioContext in I/O code path
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 214: Remove AioContext lock
RH-Jira: RHEL-15965
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Commit: [10/26] b5814cec94af5c254e300646d8783672b085bac3 (kmwolf/centos-qemu-kvm)
blk_aio_*() doesn't require the AioContext lock and the SCSI subsystem's
internal state also does not anymore.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Acked-by: Kevin Wolf <kwolf@redhat.com>
Message-ID: <20231204164259.1515217-4-stefanha@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
hw/scsi/scsi-disk.c | 23 -----------------------
hw/scsi/scsi-generic.c | 20 +++-----------------
2 files changed, 3 insertions(+), 40 deletions(-)
diff --git a/hw/scsi/scsi-disk.c b/hw/scsi/scsi-disk.c
index 6691f5edb8..2c1bbb3530 100644
--- a/hw/scsi/scsi-disk.c
+++ b/hw/scsi/scsi-disk.c
@@ -273,8 +273,6 @@ static void scsi_aio_complete(void *opaque, int ret)
SCSIDiskReq *r = (SCSIDiskReq *)opaque;
SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, r->req.dev);
- aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk));
-
assert(r->req.aiocb != NULL);
r->req.aiocb = NULL;
@@ -286,7 +284,6 @@ static void scsi_aio_complete(void *opaque, int ret)
scsi_req_complete(&r->req, GOOD);
done:
- aio_context_release(blk_get_aio_context(s->qdev.conf.blk));
scsi_req_unref(&r->req);
}
@@ -394,8 +391,6 @@ static void scsi_read_complete(void *opaque, int ret)
SCSIDiskReq *r = (SCSIDiskReq *)opaque;
SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, r->req.dev);
- aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk));
-
assert(r->req.aiocb != NULL);
r->req.aiocb = NULL;
@@ -406,7 +401,6 @@ static void scsi_read_complete(void *opaque, int ret)
trace_scsi_disk_read_complete(r->req.tag, r->qiov.size);
}
scsi_read_complete_noio(r, ret);
- aio_context_release(blk_get_aio_context(s->qdev.conf.blk));
}
/* Actually issue a read to the block device. */
@@ -448,8 +442,6 @@ static void scsi_do_read_cb(void *opaque, int ret)
SCSIDiskReq *r = (SCSIDiskReq *)opaque;
SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, r->req.dev);
- aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk));
-
assert (r->req.aiocb != NULL);
r->req.aiocb = NULL;
@@ -459,7 +451,6 @@ static void scsi_do_read_cb(void *opaque, int ret)
block_acct_done(blk_get_stats(s->qdev.conf.blk), &r->acct);
}
scsi_do_read(opaque, ret);
- aio_context_release(blk_get_aio_context(s->qdev.conf.blk));
}
/* Read more data from scsi device into buffer. */
@@ -533,8 +524,6 @@ static void scsi_write_complete(void * opaque, int ret)
SCSIDiskReq *r = (SCSIDiskReq *)opaque;
SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, r->req.dev);
- aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk));
-
assert (r->req.aiocb != NULL);
r->req.aiocb = NULL;
@@ -544,7 +533,6 @@ static void scsi_write_complete(void * opaque, int ret)
block_acct_done(blk_get_stats(s->qdev.conf.blk), &r->acct);
}
scsi_write_complete_noio(r, ret);
- aio_context_release(blk_get_aio_context(s->qdev.conf.blk));
}
static void scsi_write_data(SCSIRequest *req)
@@ -1742,8 +1730,6 @@ static void scsi_unmap_complete(void *opaque, int ret)
SCSIDiskReq *r = data->r;
SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, r->req.dev);
- aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk));
-
assert(r->req.aiocb != NULL);
r->req.aiocb = NULL;
@@ -1754,7 +1740,6 @@ static void scsi_unmap_complete(void *opaque, int ret)
block_acct_done(blk_get_stats(s->qdev.conf.blk), &r->acct);
scsi_unmap_complete_noio(data, ret);
}
- aio_context_release(blk_get_aio_context(s->qdev.conf.blk));
}
static void scsi_disk_emulate_unmap(SCSIDiskReq *r, uint8_t *inbuf)
@@ -1822,8 +1807,6 @@ static void scsi_write_same_complete(void *opaque, int ret)
SCSIDiskReq *r = data->r;
SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, r->req.dev);
- aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk));
-
assert(r->req.aiocb != NULL);
r->req.aiocb = NULL;
@@ -1847,7 +1830,6 @@ static void scsi_write_same_complete(void *opaque, int ret)
data->sector << BDRV_SECTOR_BITS,
&data->qiov, 0,
scsi_write_same_complete, data);
- aio_context_release(blk_get_aio_context(s->qdev.conf.blk));
return;
}
@@ -1857,7 +1839,6 @@ done:
scsi_req_unref(&r->req);
qemu_vfree(data->iov.iov_base);
g_free(data);
- aio_context_release(blk_get_aio_context(s->qdev.conf.blk));
}
static void scsi_disk_emulate_write_same(SCSIDiskReq *r, uint8_t *inbuf)
@@ -2810,7 +2791,6 @@ static void scsi_block_sgio_complete(void *opaque, int ret)
{
SCSIBlockReq *req = (SCSIBlockReq *)opaque;
SCSIDiskReq *r = &req->req;
- SCSIDevice *s = r->req.dev;
sg_io_hdr_t *io_hdr = &req->io_header;
if (ret == 0) {
@@ -2827,13 +2807,10 @@ static void scsi_block_sgio_complete(void *opaque, int ret)
}
if (ret > 0) {
- aio_context_acquire(blk_get_aio_context(s->conf.blk));
if (scsi_handle_rw_error(r, ret, true)) {
- aio_context_release(blk_get_aio_context(s->conf.blk));
scsi_req_unref(&r->req);
return;
}
- aio_context_release(blk_get_aio_context(s->conf.blk));
/* Ignore error. */
ret = 0;
diff --git a/hw/scsi/scsi-generic.c b/hw/scsi/scsi-generic.c
index 2417f0ad84..b7b04e1d63 100644
--- a/hw/scsi/scsi-generic.c
+++ b/hw/scsi/scsi-generic.c
@@ -109,15 +109,11 @@ done:
static void scsi_command_complete(void *opaque, int ret)
{
SCSIGenericReq *r = (SCSIGenericReq *)opaque;
- SCSIDevice *s = r->req.dev;
-
- aio_context_acquire(blk_get_aio_context(s->conf.blk));
assert(r->req.aiocb != NULL);
r->req.aiocb = NULL;
scsi_command_complete_noio(r, ret);
- aio_context_release(blk_get_aio_context(s->conf.blk));
}
static int execute_command(BlockBackend *blk,
@@ -274,14 +270,12 @@ static void scsi_read_complete(void * opaque, int ret)
SCSIDevice *s = r->req.dev;
int len;
- aio_context_acquire(blk_get_aio_context(s->conf.blk));
-
assert(r->req.aiocb != NULL);
r->req.aiocb = NULL;
if (ret || r->req.io_canceled) {
scsi_command_complete_noio(r, ret);
- goto done;
+ return;
}
len = r->io_header.dxfer_len - r->io_header.resid;
@@ -320,7 +314,7 @@ static void scsi_read_complete(void * opaque, int ret)
r->io_header.status != GOOD ||
len == 0) {
scsi_command_complete_noio(r, 0);
- goto done;
+ return;
}
/* Snoop READ CAPACITY output to set the blocksize. */
@@ -356,9 +350,6 @@ static void scsi_read_complete(void * opaque, int ret)
req_complete:
scsi_req_data(&r->req, len);
scsi_req_unref(&r->req);
-
-done:
- aio_context_release(blk_get_aio_context(s->conf.blk));
}
/* Read more data from scsi device into buffer. */
@@ -391,14 +382,12 @@ static void scsi_write_complete(void * opaque, int ret)
trace_scsi_generic_write_complete(ret);
- aio_context_acquire(blk_get_aio_context(s->conf.blk));
-
assert(r->req.aiocb != NULL);
r->req.aiocb = NULL;
if (ret || r->req.io_canceled) {
scsi_command_complete_noio(r, ret);
- goto done;
+ return;
}
if (r->req.cmd.buf[0] == MODE_SELECT && r->req.cmd.buf[4] == 12 &&
@@ -408,9 +397,6 @@ static void scsi_write_complete(void * opaque, int ret)
}
scsi_command_complete_noio(r, ret);
-
-done:
- aio_context_release(blk_get_aio_context(s->conf.blk));
}
/* Write data to a scsi device. Returns nonzero on failure.
--
2.39.3

307
kvm-scsi-only-access-SCSIDevice-requests-from-one-thread.patch
View File

@ -1,307 +0,0 @@
From 42dd1357310bd1a68d6cacaa53cd5b1d1b02880d Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Mon, 4 Dec 2023 11:42:56 -0500
Subject: [PATCH 077/101] scsi: only access SCSIDevice->requests from one
thread
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 214: Remove AioContext lock
RH-Jira: RHEL-15965
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Commit: [8/26] 9df662e82a63e93d184b5763bebbe7e43bc9dabe (kmwolf/centos-qemu-kvm)
Stop depending on the AioContext lock and instead access
SCSIDevice->requests from only one thread at a time:
- When the VM is running only the BlockBackend's AioContext may access
the requests list.
- When the VM is stopped only the main loop may access the requests
list.
These constraints protect the requests list without the need for locking
in the I/O code path.
Note that multiple IOThreads are not supported yet because the code
assumes all SCSIRequests are executed from a single AioContext. Leave
that as future work.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-ID: <20231204164259.1515217-2-stefanha@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
hw/scsi/scsi-bus.c | 181 ++++++++++++++++++++++++++++-------------
include/hw/scsi/scsi.h | 7 +-
2 files changed, 131 insertions(+), 57 deletions(-)
diff --git a/hw/scsi/scsi-bus.c b/hw/scsi/scsi-bus.c
index fc4b77fdb0..b649cdf555 100644
--- a/hw/scsi/scsi-bus.c
+++ b/hw/scsi/scsi-bus.c
@@ -85,6 +85,89 @@ SCSIDevice *scsi_device_get(SCSIBus *bus, int channel, int id, int lun)
return d;
}
+/*
+ * Invoke @fn() for each enqueued request in device @s. Must be called from the
+ * main loop thread while the guest is stopped. This is only suitable for
+ * vmstate ->put(), use scsi_device_for_each_req_async() for other cases.
+ */
+static void scsi_device_for_each_req_sync(SCSIDevice *s,
+ void (*fn)(SCSIRequest *, void *),
+ void *opaque)
+{
+ SCSIRequest *req;
+ SCSIRequest *next_req;
+
+ assert(!runstate_is_running());
+ assert(qemu_in_main_thread());
+
+ QTAILQ_FOREACH_SAFE(req, &s->requests, next, next_req) {
+ fn(req, opaque);
+ }
+}
+
+typedef struct {
+ SCSIDevice *s;
+ void (*fn)(SCSIRequest *, void *);
+ void *fn_opaque;
+} SCSIDeviceForEachReqAsyncData;
+
+static void scsi_device_for_each_req_async_bh(void *opaque)
+{
+ g_autofree SCSIDeviceForEachReqAsyncData *data = opaque;
+ SCSIDevice *s = data->s;
+ AioContext *ctx;
+ SCSIRequest *req;
+ SCSIRequest *next;
+
+ /*
+ * If the AioContext changed before this BH was called then reschedule into
+ * the new AioContext before accessing ->requests. This can happen when
+ * scsi_device_for_each_req_async() is called and then the AioContext is
+ * changed before BHs are run.
+ */
+ ctx = blk_get_aio_context(s->conf.blk);
+ if (ctx != qemu_get_current_aio_context()) {
+ aio_bh_schedule_oneshot(ctx, scsi_device_for_each_req_async_bh,
+ g_steal_pointer(&data));
+ return;
+ }
+
+ QTAILQ_FOREACH_SAFE(req, &s->requests, next, next) {
+ data->fn(req, data->fn_opaque);
+ }
+
+ /* Drop the reference taken by scsi_device_for_each_req_async() */
+ object_unref(OBJECT(s));
+}
+
+/*
+ * Schedule @fn() to be invoked for each enqueued request in device @s. @fn()
+ * runs in the AioContext that is executing the request.
+ */
+static void scsi_device_for_each_req_async(SCSIDevice *s,
+ void (*fn)(SCSIRequest *, void *),
+ void *opaque)
+{
+ assert(qemu_in_main_thread());
+
+ SCSIDeviceForEachReqAsyncData *data =
+ g_new(SCSIDeviceForEachReqAsyncData, 1);
+
+ data->s = s;
+ data->fn = fn;
+ data->fn_opaque = opaque;
+
+ /*
+ * Hold a reference to the SCSIDevice until
+ * scsi_device_for_each_req_async_bh() finishes.
+ */
+ object_ref(OBJECT(s));
+
+ aio_bh_schedule_oneshot(blk_get_aio_context(s->conf.blk),
+ scsi_device_for_each_req_async_bh,
+ data);
+}
+
static void scsi_device_realize(SCSIDevice *s, Error **errp)
{
SCSIDeviceClass *sc = SCSI_DEVICE_GET_CLASS(s);
@@ -144,20 +227,18 @@ void scsi_bus_init_named(SCSIBus *bus, size_t bus_size, DeviceState *host,
qbus_set_bus_hotplug_handler(BUS(bus));
}
-static void scsi_dma_restart_bh(void *opaque)
+void scsi_req_retry(SCSIRequest *req)
{
- SCSIDevice *s = opaque;
- SCSIRequest *req, *next;
-
- qemu_bh_delete(s->bh);
- s->bh = NULL;
+ req->retry = true;
+}
- aio_context_acquire(blk_get_aio_context(s->conf.blk));
- QTAILQ_FOREACH_SAFE(req, &s->requests, next, next) {
- scsi_req_ref(req);
- if (req->retry) {
- req->retry = false;
- switch (req->cmd.mode) {
+/* Called in the AioContext that is executing the request */
+static void scsi_dma_restart_req(SCSIRequest *req, void *opaque)
+{
+ scsi_req_ref(req);
+ if (req->retry) {
+ req->retry = false;
+ switch (req->cmd.mode) {
case SCSI_XFER_FROM_DEV:
case SCSI_XFER_TO_DEV:
scsi_req_continue(req);
@@ -166,37 +247,22 @@ static void scsi_dma_restart_bh(void *opaque)
scsi_req_dequeue(req);
scsi_req_enqueue(req);
break;
- }
}
- scsi_req_unref(req);
}
- aio_context_release(blk_get_aio_context(s->conf.blk));
- /* Drop the reference that was acquired in scsi_dma_restart_cb */
- object_unref(OBJECT(s));
-}
-
-void scsi_req_retry(SCSIRequest *req)
-{
- /* No need to save a reference, because scsi_dma_restart_bh just
- * looks at the request list. */
- req->retry = true;
+ scsi_req_unref(req);
}
static void scsi_dma_restart_cb(void *opaque, bool running, RunState state)
{
SCSIDevice *s = opaque;
+ assert(qemu_in_main_thread());
+
if (!running) {
return;
}
- if (!s->bh) {
- AioContext *ctx = blk_get_aio_context(s->conf.blk);
- /* The reference is dropped in scsi_dma_restart_bh.*/
- object_ref(OBJECT(s));
- s->bh = aio_bh_new_guarded(ctx, scsi_dma_restart_bh, s,
- &DEVICE(s)->mem_reentrancy_guard);
- qemu_bh_schedule(s->bh);
- }
+
+ scsi_device_for_each_req_async(s, scsi_dma_restart_req, NULL);
}
static bool scsi_bus_is_address_free(SCSIBus *bus,
@@ -1657,15 +1723,16 @@ void scsi_device_set_ua(SCSIDevice *sdev, SCSISense sense)
}
}
+static void scsi_device_purge_one_req(SCSIRequest *req, void *opaque)
+{
+ scsi_req_cancel_async(req, NULL);
+}
+
void scsi_device_purge_requests(SCSIDevice *sdev, SCSISense sense)
{
- SCSIRequest *req;
+ scsi_device_for_each_req_async(sdev, scsi_device_purge_one_req, NULL);
aio_context_acquire(blk_get_aio_context(sdev->conf.blk));
- while (!QTAILQ_EMPTY(&sdev->requests)) {
- req = QTAILQ_FIRST(&sdev->requests);
- scsi_req_cancel_async(req, NULL);
- }
blk_drain(sdev->conf.blk);
aio_context_release(blk_get_aio_context(sdev->conf.blk));
scsi_device_set_ua(sdev, sense);
@@ -1737,31 +1804,33 @@ static char *scsibus_get_fw_dev_path(DeviceState *dev)
/* SCSI request list. For simplicity, pv points to the whole device */
+static void put_scsi_req(SCSIRequest *req, void *opaque)
+{
+ QEMUFile *f = opaque;
+
+ assert(!req->io_canceled);
+ assert(req->status == -1 && req->host_status == -1);
+ assert(req->enqueued);
+
+ qemu_put_sbyte(f, req->retry ? 1 : 2);
+ qemu_put_buffer(f, req->cmd.buf, sizeof(req->cmd.buf));
+ qemu_put_be32s(f, &req->tag);
+ qemu_put_be32s(f, &req->lun);
+ if (req->bus->info->save_request) {
+ req->bus->info->save_request(f, req);
+ }
+ if (req->ops->save_request) {
+ req->ops->save_request(f, req);
+ }
+}
+
static int put_scsi_requests(QEMUFile *f, void *pv, size_t size,
const VMStateField *field, JSONWriter *vmdesc)
{
SCSIDevice *s = pv;
- SCSIBus *bus = DO_UPCAST(SCSIBus, qbus, s->qdev.parent_bus);
- SCSIRequest *req;
- QTAILQ_FOREACH(req, &s->requests, next) {
- assert(!req->io_canceled);
- assert(req->status == -1 && req->host_status == -1);
- assert(req->enqueued);
-
- qemu_put_sbyte(f, req->retry ? 1 : 2);
- qemu_put_buffer(f, req->cmd.buf, sizeof(req->cmd.buf));
- qemu_put_be32s(f, &req->tag);
- qemu_put_be32s(f, &req->lun);
- if (bus->info->save_request) {
- bus->info->save_request(f, req);
- }
- if (req->ops->save_request) {
- req->ops->save_request(f, req);
- }
- }
+ scsi_device_for_each_req_sync(s, put_scsi_req, f);
qemu_put_sbyte(f, 0);
-
return 0;
}
diff --git a/include/hw/scsi/scsi.h b/include/hw/scsi/scsi.h
index 3692ca82f3..10c4e8288d 100644
--- a/include/hw/scsi/scsi.h
+++ b/include/hw/scsi/scsi.h
@@ -69,14 +69,19 @@ struct SCSIDevice
{
DeviceState qdev;
VMChangeStateEntry *vmsentry;
- QEMUBH *bh;
uint32_t id;
BlockConf conf;
SCSISense unit_attention;
bool sense_is_ua;
uint8_t sense[SCSI_SENSE_BUF_SIZE];
uint32_t sense_len;
+
+ /*
+ * The requests list is only accessed from the AioContext that executes
+ * requests or from the main loop when IOThread processing is stopped.
+ */
QTAILQ_HEAD(, SCSIRequest) requests;
+
uint32_t channel;
uint32_t lun;
int blocksize;
--
2.39.3

280
kvm-scsi-remove-AioContext-locking.patch
View File

@ -1,280 +0,0 @@
From 61d605433a5edfcc7fe836fd399106ed1e1907bb Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Tue, 5 Dec 2023 13:20:05 -0500
Subject: [PATCH 088/101] scsi: remove AioContext locking
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 214: Remove AioContext lock
RH-Jira: RHEL-15965
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Commit: [19/26] 12a8e26670074a17dd2b0cfac06e0aea03b3068f (kmwolf/centos-qemu-kvm)
The AioContext lock no longer has any effect. Remove it.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-ID: <20231205182011.1976568-9-stefanha@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
hw/scsi/scsi-bus.c | 2 --
hw/scsi/scsi-disk.c | 31 +++++--------------------------
hw/scsi/virtio-scsi.c | 18 ------------------
include/hw/virtio/virtio-scsi.h | 14 --------------
4 files changed, 5 insertions(+), 60 deletions(-)
diff --git a/hw/scsi/scsi-bus.c b/hw/scsi/scsi-bus.c
index b649cdf555..5b08cbf60a 100644
--- a/hw/scsi/scsi-bus.c
+++ b/hw/scsi/scsi-bus.c
@@ -1732,9 +1732,7 @@ void scsi_device_purge_requests(SCSIDevice *sdev, SCSISense sense)
{
scsi_device_for_each_req_async(sdev, scsi_device_purge_one_req, NULL);
- aio_context_acquire(blk_get_aio_context(sdev->conf.blk));
blk_drain(sdev->conf.blk);
- aio_context_release(blk_get_aio_context(sdev->conf.blk));
scsi_device_set_ua(sdev, sense);
}
diff --git a/hw/scsi/scsi-disk.c b/hw/scsi/scsi-disk.c
index a5048e0aaf..61be3d395a 100644
--- a/hw/scsi/scsi-disk.c
+++ b/hw/scsi/scsi-disk.c
@@ -2339,14 +2339,10 @@ static void scsi_disk_reset(DeviceState *dev)
{
SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev.qdev, dev);
uint64_t nb_sectors;
- AioContext *ctx;
scsi_device_purge_requests(&s->qdev, SENSE_CODE(RESET));
- ctx = blk_get_aio_context(s->qdev.conf.blk);
- aio_context_acquire(ctx);
blk_get_geometry(s->qdev.conf.blk, &nb_sectors);
- aio_context_release(ctx);
nb_sectors /= s->qdev.blocksize / BDRV_SECTOR_SIZE;
if (nb_sectors) {
@@ -2545,15 +2541,13 @@ static void scsi_unrealize(SCSIDevice *dev)
static void scsi_hd_realize(SCSIDevice *dev, Error **errp)
{
SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, dev);
- AioContext *ctx = NULL;
+
/* can happen for devices without drive. The error message for missing
* backend will be issued in scsi_realize
*/
if (s->qdev.conf.blk) {
- ctx = blk_get_aio_context(s->qdev.conf.blk);
- aio_context_acquire(ctx);
if (!blkconf_blocksizes(&s->qdev.conf, errp)) {
- goto out;
+ return;
}
}
s->qdev.blocksize = s->qdev.conf.logical_block_size;
@@ -2562,16 +2556,11 @@ static void scsi_hd_realize(SCSIDevice *dev, Error **errp)
s->product = g_strdup("QEMU HARDDISK");
}
scsi_realize(&s->qdev, errp);
-out:
- if (ctx) {
- aio_context_release(ctx);
- }
}
static void scsi_cd_realize(SCSIDevice *dev, Error **errp)
{
SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, dev);
- AioContext *ctx;
int ret;
uint32_t blocksize = 2048;
@@ -2587,8 +2576,6 @@ static void scsi_cd_realize(SCSIDevice *dev, Error **errp)
blocksize = dev->conf.physical_block_size;
}
- ctx = blk_get_aio_context(dev->conf.blk);
- aio_context_acquire(ctx);
s->qdev.blocksize = blocksize;
s->qdev.type = TYPE_ROM;
s->features |= 1 << SCSI_DISK_F_REMOVABLE;
@@ -2596,7 +2583,6 @@ static void scsi_cd_realize(SCSIDevice *dev, Error **errp)
s->product = g_strdup("QEMU CD-ROM");
}
scsi_realize(&s->qdev, errp);
- aio_context_release(ctx);
}
@@ -2727,7 +2713,6 @@ static int get_device_type(SCSIDiskState *s)
static void scsi_block_realize(SCSIDevice *dev, Error **errp)
{
SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, dev);
- AioContext *ctx;
int sg_version;
int rc;
@@ -2742,9 +2727,6 @@ static void scsi_block_realize(SCSIDevice *dev, Error **errp)
"be removed in a future version");
}
- ctx = blk_get_aio_context(s->qdev.conf.blk);
- aio_context_acquire(ctx);
-
/* check we are using a driver managing SG_IO (version 3 and after) */
rc = blk_ioctl(s->qdev.conf.blk, SG_GET_VERSION_NUM, &sg_version);
if (rc < 0) {
@@ -2752,18 +2734,18 @@ static void scsi_block_realize(SCSIDevice *dev, Error **errp)
if (rc != -EPERM) {
error_append_hint(errp, "Is this a SCSI device?\n");
}
- goto out;
+ return;
}
if (sg_version < 30000) {
error_setg(errp, "scsi generic interface too old");
- goto out;
+ return;
}
/* get device type from INQUIRY data */
rc = get_device_type(s);
if (rc < 0) {
error_setg(errp, "INQUIRY failed");
- goto out;
+ return;
}
/* Make a guess for the block size, we'll fix it when the guest sends.
@@ -2783,9 +2765,6 @@ static void scsi_block_realize(SCSIDevice *dev, Error **errp)
scsi_realize(&s->qdev, errp);
scsi_generic_read_device_inquiry(&s->qdev);
-
-out:
- aio_context_release(ctx);
}
typedef struct SCSIBlockReq {
diff --git a/hw/scsi/virtio-scsi.c b/hw/scsi/virtio-scsi.c
index 4f8d35facc..ca365a70e9 100644
--- a/hw/scsi/virtio-scsi.c
+++ b/hw/scsi/virtio-scsi.c
@@ -642,9 +642,7 @@ static void virtio_scsi_handle_ctrl(VirtIODevice *vdev, VirtQueue *vq)
return;
}
- virtio_scsi_acquire(s);
virtio_scsi_handle_ctrl_vq(s, vq);
- virtio_scsi_release(s);
}
static void virtio_scsi_complete_cmd_req(VirtIOSCSIReq *req)
@@ -882,9 +880,7 @@ static void virtio_scsi_handle_cmd(VirtIODevice *vdev, VirtQueue *vq)
return;
}
- virtio_scsi_acquire(s);
virtio_scsi_handle_cmd_vq(s, vq);
- virtio_scsi_release(s);
}
static void virtio_scsi_get_config(VirtIODevice *vdev,
@@ -1031,9 +1027,7 @@ static void virtio_scsi_handle_event(VirtIODevice *vdev, VirtQueue *vq)
return;
}
- virtio_scsi_acquire(s);
virtio_scsi_handle_event_vq(s, vq);
- virtio_scsi_release(s);
}
static void virtio_scsi_change(SCSIBus *bus, SCSIDevice *dev, SCSISense sense)
@@ -1052,9 +1046,7 @@ static void virtio_scsi_change(SCSIBus *bus, SCSIDevice *dev, SCSISense sense)
},
};
- virtio_scsi_acquire(s);
virtio_scsi_push_event(s, &info);
- virtio_scsi_release(s);
}
}
@@ -1071,17 +1063,13 @@ static void virtio_scsi_hotplug(HotplugHandler *hotplug_dev, DeviceState *dev,
VirtIODevice *vdev = VIRTIO_DEVICE(hotplug_dev);
VirtIOSCSI *s = VIRTIO_SCSI(vdev);
SCSIDevice *sd = SCSI_DEVICE(dev);
- AioContext *old_context;
int ret;
if (s->ctx && !s->dataplane_fenced) {
if (blk_op_is_blocked(sd->conf.blk, BLOCK_OP_TYPE_DATAPLANE, errp)) {
return;
}
- old_context = blk_get_aio_context(sd->conf.blk);
- aio_context_acquire(old_context);
ret = blk_set_aio_context(sd->conf.blk, s->ctx, errp);
- aio_context_release(old_context);
if (ret < 0) {
return;
}
@@ -1097,10 +1085,8 @@ static void virtio_scsi_hotplug(HotplugHandler *hotplug_dev, DeviceState *dev,
},
};
- virtio_scsi_acquire(s);
virtio_scsi_push_event(s, &info);
scsi_bus_set_ua(&s->bus, SENSE_CODE(REPORTED_LUNS_CHANGED));
- virtio_scsi_release(s);
}
}
@@ -1122,17 +1108,13 @@ static void virtio_scsi_hotunplug(HotplugHandler *hotplug_dev, DeviceState *dev,
qdev_simple_device_unplug_cb(hotplug_dev, dev, errp);
if (s->ctx) {
- virtio_scsi_acquire(s);
/* If other users keep the BlockBackend in the iothread, that's ok */
blk_set_aio_context(sd->conf.blk, qemu_get_aio_context(), NULL);
- virtio_scsi_release(s);
}
if (virtio_vdev_has_feature(vdev, VIRTIO_SCSI_F_HOTPLUG)) {
- virtio_scsi_acquire(s);
virtio_scsi_push_event(s, &info);
scsi_bus_set_ua(&s->bus, SENSE_CODE(REPORTED_LUNS_CHANGED));
- virtio_scsi_release(s);
}
}
diff --git a/include/hw/virtio/virtio-scsi.h b/include/hw/virtio/virtio-scsi.h
index da8cb928d9..7f0573b1bf 100644
--- a/include/hw/virtio/virtio-scsi.h
+++ b/include/hw/virtio/virtio-scsi.h
@@ -101,20 +101,6 @@ struct VirtIOSCSI {
uint32_t host_features;
};
-static inline void virtio_scsi_acquire(VirtIOSCSI *s)
-{
- if (s->ctx) {
- aio_context_acquire(s->ctx);
- }
-}
-
-static inline void virtio_scsi_release(VirtIOSCSI *s)
-{
- if (s->ctx) {
- aio_context_release(s->ctx);
- }
-}
-
void virtio_scsi_common_realize(DeviceState *dev,
VirtIOHandleOutput ctrl,
VirtIOHandleOutput evt,
--
2.39.3

41
kvm-scsi-remove-outdated-AioContext-lock-comment.patch
View File

@ -1,41 +0,0 @@
From 9f5c6dbe907fe6227006ab51179eaa50a63559cb Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Tue, 5 Dec 2023 13:20:09 -0500
Subject: [PATCH 092/101] scsi: remove outdated AioContext lock comment
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 214: Remove AioContext lock
RH-Jira: RHEL-15965
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Commit: [23/26] 96e2e7d2e6a160ce4d695060f902d21030b3b1d8 (kmwolf/centos-qemu-kvm)
The SCSI subsystem no longer uses the AioContext lock. Request
processing runs exclusively in the BlockBackend's AioContext since
"scsi: only access SCSIDevice->requests from one thread" and hence the
lock is unnecessary.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-ID: <20231205182011.1976568-13-stefanha@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
hw/scsi/scsi-disk.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/hw/scsi/scsi-disk.c b/hw/scsi/scsi-disk.c
index 61be3d395a..2e7e1e9a1c 100644
--- a/hw/scsi/scsi-disk.c
+++ b/hw/scsi/scsi-disk.c
@@ -355,7 +355,6 @@ done:
scsi_req_unref(&r->req);
}
-/* Called with AioContext lock held */
static void scsi_dma_complete(void *opaque, int ret)
{
SCSIDiskReq *r = (SCSIDiskReq *)opaque;
--
2.39.3

62
kvm-smbios-add-smbios_add_usr_blob_size-helper.patch
View File

@ -1,62 +0,0 @@
From 93cf5b82771f1d1e8182be168dae7a45d42069e9 Mon Sep 17 00:00:00 2001
From: Igor Mammedov <imammedo@redhat.com>
Date: Mon, 4 Mar 2024 15:39:57 +0100
Subject: [PATCH 11/20] smbios: add smbios_add_usr_blob_size() helper
RH-Author: Igor Mammedov <imammedo@redhat.com>
RH-MergeRequest: 230: Workaround Windows failing to find 64bit SMBIOS entry point with SeaBIOS
RH-Jira: RHEL-21705
RH-Acked-by: MST <mst@redhat.com>
RH-Acked-by: Ani Sinha <None>
RH-Commit: [9/18] 8c698fb9e186d2b1d2b7f75a74305f356450ad68
JIRA: https://issues.redhat.com/browse/RHEL-21705
it will be used by follow up patch when legacy handling
is moved out into a separate file.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Ani Sinha <anisinha@redhat.com>
---
hw/smbios/smbios.c | 18 ++++++++++++++----
1 file changed, 14 insertions(+), 4 deletions(-)
diff --git a/hw/smbios/smbios.c b/hw/smbios/smbios.c
index 441517cf24..c48a290478 100644
--- a/hw/smbios/smbios.c
+++ b/hw/smbios/smbios.c
@@ -1426,6 +1426,14 @@ static bool save_opt_list(size_t *ndest, char ***dest, QemuOpts *opts,
return true;
}
+static void smbios_add_usr_blob_size(size_t size)
+{
+ if (!usr_blobs_sizes) {
+ usr_blobs_sizes = g_array_new(false, false, sizeof(size_t));
+ }
+ g_array_append_val(usr_blobs_sizes, size);
+}
+
void smbios_entry_add(QemuOpts *opts, Error **errp)
{
const char *val;
@@ -1473,10 +1481,12 @@ void smbios_entry_add(QemuOpts *opts, Error **errp)
smbios_type4_count++;
}
- if (!usr_blobs_sizes) {
- usr_blobs_sizes = g_array_new(false, false, sizeof(size_t));
- }
- g_array_append_val(usr_blobs_sizes, size);
+ /*
+ * preserve blob size for legacy mode so it could build its
+ * blobs flavor from 'usr_blobs'
+ */
+ smbios_add_usr_blob_size(size);
+
usr_blobs_len += size;
if (size > usr_table_max) {
usr_table_max = size;
--
2.39.3

309
kvm-smbios-avoid-mangling-user-provided-tables.patch
View File

@ -1,309 +0,0 @@
From 15d293b706ca6c9e6ad569becda8da5f70461c30 Mon Sep 17 00:00:00 2001
From: Igor Mammedov <imammedo@redhat.com>
Date: Tue, 13 Feb 2024 09:25:11 +0100
Subject: [PATCH 09/20] smbios: avoid mangling user provided tables
RH-Author: Igor Mammedov <imammedo@redhat.com>
RH-MergeRequest: 230: Workaround Windows failing to find 64bit SMBIOS entry point with SeaBIOS
RH-Jira: RHEL-21705
RH-Acked-by: MST <mst@redhat.com>
RH-Acked-by: Ani Sinha <None>
RH-Commit: [7/18] fa2c7372f55f29e5834eee94ba98f19ea02e7a82
JIRA: https://issues.redhat.com/browse/RHEL-21705
currently smbios_entry_add() preserves internally '-smbios type='
options but tables provided with '-smbios file=' are stored directly
into blob that eventually will be exposed to VM. And then later
QEMU adds default/'-smbios type' entries on top into the same blob.
It makes impossible to generate tables more than once, hence
'immutable' guard was used.
Make it possible to regenerate final blob by storing user provided
blobs into a dedicated area (usr_blobs) and then copy it when
composing final blob. Which also makes handling of -smbios
options consistent.
As side effect of this and previous commits there is no need to
generate legacy smbios_entries at the time options are parsed.
Instead compose smbios_entries on demand from usr_blobs like
it is done for non-legacy SMBIOS tables.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Tested-by: Fiona Ebner <f.ebner@proxmox.com>
Reviewed-by: Ani Sinha <anisinha@redhat.com>
Conflicts: hw/smbios/smbios.c
caused by downstream smbios_type2_required
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
---
hw/smbios/smbios.c | 181 +++++++++++++++++++++++----------------------
1 file changed, 93 insertions(+), 88 deletions(-)
diff --git a/hw/smbios/smbios.c b/hw/smbios/smbios.c
index 0c8c439859..d8d68716d4 100644
--- a/hw/smbios/smbios.c
+++ b/hw/smbios/smbios.c
@@ -60,6 +60,14 @@ static bool smbios_uuid_encoded = true;
/* Set to true for modern Windows 10 HardwareID-6 compat */
static bool smbios_type2_required;
+/*
+ * SMBIOS tables provided by user with '-smbios file=<foo>' option
+ */
+uint8_t *usr_blobs;
+size_t usr_blobs_len;
+static GArray *usr_blobs_sizes;
+static unsigned usr_table_max;
+static unsigned usr_table_cnt;
uint8_t *smbios_tables;
size_t smbios_tables_len;
@@ -70,7 +78,6 @@ static SmbiosEntryPointType smbios_ep_type = SMBIOS_ENTRY_POINT_TYPE_32;
static SmbiosEntryPoint ep;
static int smbios_type4_count = 0;
-static bool smbios_immutable;
static bool smbios_have_defaults;
static uint32_t smbios_cpuid_version, smbios_cpuid_features;
@@ -617,9 +624,8 @@ static void smbios_build_type_1_fields(void)
uint8_t *smbios_get_table_legacy(uint32_t expected_t4_count, size_t *length)
{
- /* drop unwanted version of command-line file blob(s) */
- g_free(smbios_tables);
- smbios_tables = NULL;
+ int i;
+ size_t usr_offset;
/* also complain if fields were given for types > 1 */
if (find_next_bit(have_fields_bitmap,
@@ -629,12 +635,33 @@ uint8_t *smbios_get_table_legacy(uint32_t expected_t4_count, size_t *length)
exit(1);
}
- if (!smbios_immutable) {
- smbios_build_type_0_fields();
- smbios_build_type_1_fields();
- smbios_validate_table(expected_t4_count);
- smbios_immutable = true;
+ g_free(smbios_entries);
+ smbios_entries_len = sizeof(uint16_t);
+ smbios_entries = g_malloc0(smbios_entries_len);
+
+ for (i = 0, usr_offset = 0; usr_blobs_sizes && i < usr_blobs_sizes->len;
+ i++)
+ {
+ struct smbios_table *table;
+ struct smbios_structure_header *header;
+ size_t size = g_array_index(usr_blobs_sizes, size_t, i);
+
+ header = (struct smbios_structure_header *)(usr_blobs + usr_offset);
+ smbios_entries = g_realloc(smbios_entries, smbios_entries_len +
+ size + sizeof(*table));
+ table = (struct smbios_table *)(smbios_entries + smbios_entries_len);
+ table->header.type = SMBIOS_TABLE_ENTRY;
+ table->header.length = cpu_to_le16(sizeof(*table) + size);
+ memcpy(table->data, header, size);
+ smbios_entries_len += sizeof(*table) + size;
+ (*(uint16_t *)smbios_entries) =
+ cpu_to_le16(le16_to_cpu(*(uint16_t *)smbios_entries) + 1);
+ usr_offset += size;
}
+
+ smbios_build_type_0_fields();
+ smbios_build_type_1_fields();
+ smbios_validate_table(expected_t4_count);
*length = smbios_entries_len;
return smbios_entries;
}
@@ -1232,68 +1259,68 @@ void smbios_get_tables(MachineState *ms,
{
unsigned i, dimm_cnt, offset;
- /* drop unwanted (legacy) version of command-line file blob(s) */
- g_free(smbios_entries);
- smbios_entries = NULL;
+ g_free(smbios_tables);
+ smbios_tables = g_memdup2(usr_blobs, usr_blobs_len);
+ smbios_tables_len = usr_blobs_len;
+ smbios_table_max = usr_table_max;
+ smbios_table_cnt = usr_table_cnt;
- if (!smbios_immutable) {
- smbios_build_type_0_table();
- smbios_build_type_1_table();
- smbios_build_type_2_table();
- smbios_build_type_3_table();
+ smbios_build_type_0_table();
+ smbios_build_type_1_table();
+ smbios_build_type_2_table();
+ smbios_build_type_3_table();
- assert(ms->smp.sockets >= 1);
+ assert(ms->smp.sockets >= 1);
- for (i = 0; i < ms->smp.sockets; i++) {
- smbios_build_type_4_table(ms, i);
- }
+ for (i = 0; i < ms->smp.sockets; i++) {
+ smbios_build_type_4_table(ms, i);
+ }
- smbios_build_type_8_table();
- smbios_build_type_9_table(errp);
- smbios_build_type_11_table();
+ smbios_build_type_8_table();
+ smbios_build_type_9_table(errp);
+ smbios_build_type_11_table();
#define MAX_DIMM_SZ (16 * GiB)
#define GET_DIMM_SZ ((i < dimm_cnt - 1) ? MAX_DIMM_SZ \
: ((current_machine->ram_size - 1) % MAX_DIMM_SZ) + 1)
- dimm_cnt = QEMU_ALIGN_UP(current_machine->ram_size, MAX_DIMM_SZ) / MAX_DIMM_SZ;
+ dimm_cnt = QEMU_ALIGN_UP(current_machine->ram_size, MAX_DIMM_SZ) /
+ MAX_DIMM_SZ;
- /*
- * The offset determines if we need to keep additional space between
- * table 17 and table 19 header handle numbers so that they do
- * not overlap. For example, for a VM with larger than 8 TB guest
- * memory and DIMM like chunks of 16 GiB, the default space between
- * the two tables (T19_BASE - T17_BASE = 512) is not enough.
- */
- offset = (dimm_cnt > (T19_BASE - T17_BASE)) ? \
- dimm_cnt - (T19_BASE - T17_BASE) : 0;
+ /*
+ * The offset determines if we need to keep additional space between
+ * table 17 and table 19 header handle numbers so that they do
+ * not overlap. For example, for a VM with larger than 8 TB guest
+ * memory and DIMM like chunks of 16 GiB, the default space between
+ * the two tables (T19_BASE - T17_BASE = 512) is not enough.
+ */
+ offset = (dimm_cnt > (T19_BASE - T17_BASE)) ? \
+ dimm_cnt - (T19_BASE - T17_BASE) : 0;
- smbios_build_type_16_table(dimm_cnt);
+ smbios_build_type_16_table(dimm_cnt);
- for (i = 0; i < dimm_cnt; i++) {
- smbios_build_type_17_table(i, GET_DIMM_SZ);
- }
+ for (i = 0; i < dimm_cnt; i++) {
+ smbios_build_type_17_table(i, GET_DIMM_SZ);
+ }
- for (i = 0; i < mem_array_size; i++) {
- smbios_build_type_19_table(i, offset, mem_array[i].address,
- mem_array[i].length);
- }
+ for (i = 0; i < mem_array_size; i++) {
+ smbios_build_type_19_table(i, offset, mem_array[i].address,
+ mem_array[i].length);
+ }
- /*
- * make sure 16 bit handle numbers in the headers of tables 19
- * and 32 do not overlap.
- */
- assert((mem_array_size + offset) < (T32_BASE - T19_BASE));
+ /*
+ * make sure 16 bit handle numbers in the headers of tables 19
+ * and 32 do not overlap.
+ */
+ assert((mem_array_size + offset) < (T32_BASE - T19_BASE));
- smbios_build_type_32_table();
- smbios_build_type_38_table();
- smbios_build_type_41_table(errp);
- smbios_build_type_127_table();
+ smbios_build_type_32_table();
+ smbios_build_type_38_table();
+ smbios_build_type_41_table(errp);
+ smbios_build_type_127_table();
- smbios_validate_table(ms->smp.sockets);
- smbios_entry_point_setup();
- smbios_immutable = true;
- }
+ smbios_validate_table(ms->smp.sockets);
+ smbios_entry_point_setup();
/* return tables blob and entry point (anchor), and their sizes */
*tables = smbios_tables;
@@ -1393,13 +1420,10 @@ void smbios_entry_add(QemuOpts *opts, Error **errp)
{
const char *val;
- assert(!smbios_immutable);
-
val = qemu_opt_get(opts, "file");
if (val) {
struct smbios_structure_header *header;
- int size;
- struct smbios_table *table; /* legacy mode only */
+ size_t size;
if (!qemu_opts_validate(opts, qemu_smbios_file_opts, errp)) {
return;
@@ -1416,9 +1440,9 @@ void smbios_entry_add(QemuOpts *opts, Error **errp)
* (except in legacy mode, where the second '\0' is implicit and
* will be inserted by the BIOS).
*/
- smbios_tables = g_realloc(smbios_tables, smbios_tables_len + size);
- header = (struct smbios_structure_header *)(smbios_tables +
- smbios_tables_len);
+ usr_blobs = g_realloc(usr_blobs, usr_blobs_len + size);
+ header = (struct smbios_structure_header *)(usr_blobs +
+ usr_blobs_len);
if (load_image_size(val, (uint8_t *)header, size) != size) {
error_setg(errp, "Failed to load SMBIOS file %s", val);
@@ -1439,34 +1463,15 @@ void smbios_entry_add(QemuOpts *opts, Error **errp)
smbios_type4_count++;
}
- smbios_tables_len += size;
- if (size > smbios_table_max) {
- smbios_table_max = size;
+ if (!usr_blobs_sizes) {
+ usr_blobs_sizes = g_array_new(false, false, sizeof(size_t));
}
- smbios_table_cnt++;
-
- /* add a copy of the newly loaded blob to legacy smbios_entries */
- /* NOTE: This code runs before smbios_set_defaults(), so we don't
- * yet know which mode (legacy vs. aggregate-table) will be
- * required. We therefore add the binary blob to both legacy
- * (smbios_entries) and aggregate (smbios_tables) tables, and
- * delete the one we don't need from smbios_set_defaults(),
- * once we know which machine version has been requested.
- */
- if (!smbios_entries) {
- smbios_entries_len = sizeof(uint16_t);
- smbios_entries = g_malloc0(smbios_entries_len);
+ g_array_append_val(usr_blobs_sizes, size);
+ usr_blobs_len += size;
+ if (size > usr_table_max) {
+ usr_table_max = size;
}
- smbios_entries = g_realloc(smbios_entries, smbios_entries_len +
- size + sizeof(*table));
- table = (struct smbios_table *)(smbios_entries + smbios_entries_len);
- table->header.type = SMBIOS_TABLE_ENTRY;
- table->header.length = cpu_to_le16(sizeof(*table) + size);
- memcpy(table->data, header, size);
- smbios_entries_len += sizeof(*table) + size;
- (*(uint16_t *)smbios_entries) =
- cpu_to_le16(le16_to_cpu(*(uint16_t *)smbios_entries) + 1);
- /* end: add a copy of the newly loaded blob to legacy smbios_entries */
+ usr_table_cnt++;
return;
}
--
2.39.3

517
kvm-smbios-build-legacy-mode-code-only-for-pc-machine.patch
View File

@ -1,517 +0,0 @@
From 7ebb314a4f81d6d1a7dd4980b757fb5e556f5837 Mon Sep 17 00:00:00 2001
From: Igor Mammedov <imammedo@redhat.com>
Date: Tue, 13 Feb 2024 16:45:18 +0100
Subject: [PATCH 13/20] smbios: build legacy mode code only for 'pc' machine
RH-Author: Igor Mammedov <imammedo@redhat.com>
RH-MergeRequest: 230: Workaround Windows failing to find 64bit SMBIOS entry point with SeaBIOS
RH-Jira: RHEL-21705
RH-Acked-by: MST <mst@redhat.com>
RH-Acked-by: Ani Sinha <None>
RH-Commit: [11/18] 06e639be03e0d151fb9bcf5f728388edcb84219a
JIRA: https://issues.redhat.com/browse/RHEL-21705
basically moving code around without functional change.
And exposing some symbols so that they could be shared
between smbbios.c and new smbios_legacy.c
plus some meson magic to build smbios_legacy.c only
for 'pc' machine and otherwise replace it with stub
if not selected.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Ani Sinha <anisinha@redhat.com>
Conflicts: hw/smbios/smbios.c
context change due to downstream smbios_type2_required
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
---
hw/i386/Kconfig | 1 +
hw/smbios/Kconfig | 2 +
hw/smbios/meson.build | 5 +
hw/smbios/smbios.c | 163 +-----------------------------
hw/smbios/smbios_legacy.c | 179 +++++++++++++++++++++++++++++++++
hw/smbios/smbios_legacy_stub.c | 15 +++
include/hw/firmware/smbios.h | 5 +
7 files changed, 208 insertions(+), 162 deletions(-)
create mode 100644 hw/smbios/smbios_legacy.c
create mode 100644 hw/smbios/smbios_legacy_stub.c
diff --git a/hw/i386/Kconfig b/hw/i386/Kconfig
index a1846be6f7..a6ee052f9a 100644
--- a/hw/i386/Kconfig
+++ b/hw/i386/Kconfig
@@ -76,6 +76,7 @@ config I440FX
select PIIX
select DIMM
select SMBIOS
+ select SMBIOS_LEGACY
select FW_CFG_DMA
config ISAPC
diff --git a/hw/smbios/Kconfig b/hw/smbios/Kconfig
index 553adf4bfc..8d989a2f1b 100644
--- a/hw/smbios/Kconfig
+++ b/hw/smbios/Kconfig
@@ -1,2 +1,4 @@
config SMBIOS
bool
+config SMBIOS_LEGACY
+ bool
diff --git a/hw/smbios/meson.build b/hw/smbios/meson.build
index 6eeae4b35c..fcac1d7490 100644
--- a/hw/smbios/meson.build
+++ b/hw/smbios/meson.build
@@ -4,10 +4,15 @@ smbios_ss.add(when: 'CONFIG_IPMI',
if_true: files('smbios_type_38.c'),
if_false: files('smbios_type_38-stub.c'))
+smbios_ss.add(when: 'CONFIG_SMBIOS_LEGACY',
+ if_true: files('smbios_legacy.c'),
+ if_false: files('smbios_legacy_stub.c'))
+
system_ss.add_all(when: 'CONFIG_SMBIOS', if_true: smbios_ss)
system_ss.add(when: 'CONFIG_SMBIOS', if_false: files('smbios-stub.c'))
system_ss.add(when: 'CONFIG_ALL', if_true: files(
'smbios-stub.c',
'smbios_type_38-stub.c',
+ 'smbios_legacy_stub.c',
))
diff --git a/hw/smbios/smbios.c b/hw/smbios/smbios.c
index eb9927335d..e40204550e 100644
--- a/hw/smbios/smbios.c
+++ b/hw/smbios/smbios.c
@@ -31,31 +31,7 @@
#include "hw/pci/pci_device.h"
#include "smbios_build.h"
-/* legacy structures and constants for <= 2.0 machines */
-struct smbios_header {
- uint16_t length;
- uint8_t type;
-} QEMU_PACKED;
-
-struct smbios_field {
- struct smbios_header header;
- uint8_t type;
- uint16_t offset;
- uint8_t data[];
-} QEMU_PACKED;
-
-struct smbios_table {
- struct smbios_header header;
- uint8_t data[];
-} QEMU_PACKED;
-
-#define SMBIOS_FIELD_ENTRY 0
-#define SMBIOS_TABLE_ENTRY 1
-
-static uint8_t *smbios_entries;
-static size_t smbios_entries_len;
static bool smbios_uuid_encoded = true;
-/* end: legacy structures & constants for <= 2.0 machines */
/* Set to true for modern Windows 10 HardwareID-6 compat */
static bool smbios_type2_required;
@@ -65,7 +41,6 @@ static bool smbios_type2_required;
*/
uint8_t *usr_blobs;
size_t usr_blobs_len;
-static GArray *usr_blobs_sizes;
static unsigned usr_table_max;
static unsigned usr_table_cnt;
@@ -531,7 +506,7 @@ static void smbios_check_type4_count(uint32_t expected_t4_count)
}
}
-static void smbios_validate_table(void)
+void smbios_validate_table(void)
{
if (smbios_ep_type == SMBIOS_ENTRY_POINT_TYPE_32 &&
smbios_tables_len > SMBIOS_21_MAX_TABLES_LEN) {
@@ -541,134 +516,6 @@ static void smbios_validate_table(void)
}
}
-
-/* legacy setup functions for <= 2.0 machines */
-static void smbios_add_field(int type, int offset, const void *data, size_t len)
-{
- struct smbios_field *field;
-
- if (!smbios_entries) {
- smbios_entries_len = sizeof(uint16_t);
- smbios_entries = g_malloc0(smbios_entries_len);
- }
- smbios_entries = g_realloc(smbios_entries, smbios_entries_len +
- sizeof(*field) + len);
- field = (struct smbios_field *)(smbios_entries + smbios_entries_len);
- field->header.type = SMBIOS_FIELD_ENTRY;
- field->header.length = cpu_to_le16(sizeof(*field) + len);
-
- field->type = type;
- field->offset = cpu_to_le16(offset);
- memcpy(field->data, data, len);
-
- smbios_entries_len += sizeof(*field) + len;
- (*(uint16_t *)smbios_entries) =
- cpu_to_le16(le16_to_cpu(*(uint16_t *)smbios_entries) + 1);
-}
-
-static void smbios_maybe_add_str(int type, int offset, const char *data)
-{
- if (data) {
- smbios_add_field(type, offset, data, strlen(data) + 1);
- }
-}
-
-static void smbios_build_type_0_fields(void)
-{
- smbios_maybe_add_str(0, offsetof(struct smbios_type_0, vendor_str),
- smbios_type0.vendor);
- smbios_maybe_add_str(0, offsetof(struct smbios_type_0, bios_version_str),
- smbios_type0.version);
- smbios_maybe_add_str(0, offsetof(struct smbios_type_0,
- bios_release_date_str),
- smbios_type0.date);
- if (smbios_type0.have_major_minor) {
- smbios_add_field(0, offsetof(struct smbios_type_0,
- system_bios_major_release),
- &smbios_type0.major, 1);
- smbios_add_field(0, offsetof(struct smbios_type_0,
- system_bios_minor_release),
- &smbios_type0.minor, 1);
- }
-}
-
-static void smbios_build_type_1_fields(void)
-{
- smbios_maybe_add_str(1, offsetof(struct smbios_type_1, manufacturer_str),
- smbios_type1.manufacturer);
- smbios_maybe_add_str(1, offsetof(struct smbios_type_1, product_name_str),
- smbios_type1.product);
- smbios_maybe_add_str(1, offsetof(struct smbios_type_1, version_str),
- smbios_type1.version);
- smbios_maybe_add_str(1, offsetof(struct smbios_type_1, serial_number_str),
- smbios_type1.serial);
- smbios_maybe_add_str(1, offsetof(struct smbios_type_1, sku_number_str),
- smbios_type1.sku);
- smbios_maybe_add_str(1, offsetof(struct smbios_type_1, family_str),
- smbios_type1.family);
- if (qemu_uuid_set) {
- /* We don't encode the UUID in the "wire format" here because this
- * function is for legacy mode and needs to keep the guest ABI, and
- * because we don't know what's the SMBIOS version advertised by the
- * BIOS.
- */
- smbios_add_field(1, offsetof(struct smbios_type_1, uuid),
- &qemu_uuid, 16);
- }
-}
-
-uint8_t *smbios_get_table_legacy(size_t *length)
-{
- int i;
- size_t usr_offset;
-
- /* also complain if fields were given for types > 1 */
- if (find_next_bit(smbios_have_fields_bitmap,
- SMBIOS_MAX_TYPE + 1, 2) < SMBIOS_MAX_TYPE + 1) {
- error_report("can't process fields for smbios "
- "types > 1 on machine versions < 2.1!");
- exit(1);
- }
-
- if (test_bit(4, smbios_have_binfile_bitmap)) {
- error_report("can't process table for smbios "
- "type 4 on machine versions < 2.1!");
- exit(1);
- }
-
- g_free(smbios_entries);
- smbios_entries_len = sizeof(uint16_t);
- smbios_entries = g_malloc0(smbios_entries_len);
-
- for (i = 0, usr_offset = 0; usr_blobs_sizes && i < usr_blobs_sizes->len;
- i++)
- {
- struct smbios_table *table;
- struct smbios_structure_header *header;
- size_t size = g_array_index(usr_blobs_sizes, size_t, i);
-
- header = (struct smbios_structure_header *)(usr_blobs + usr_offset);
- smbios_entries = g_realloc(smbios_entries, smbios_entries_len +
- size + sizeof(*table));
- table = (struct smbios_table *)(smbios_entries + smbios_entries_len);
- table->header.type = SMBIOS_TABLE_ENTRY;
- table->header.length = cpu_to_le16(sizeof(*table) + size);
- memcpy(table->data, header, size);
- smbios_entries_len += sizeof(*table) + size;
- (*(uint16_t *)smbios_entries) =
- cpu_to_le16(le16_to_cpu(*(uint16_t *)smbios_entries) + 1);
- usr_offset += size;
- }
-
- smbios_build_type_0_fields();
- smbios_build_type_1_fields();
- smbios_validate_table();
- *length = smbios_entries_len;
- return smbios_entries;
-}
-/* end: legacy setup functions for <= 2.0 machines */
-
-
bool smbios_skip_table(uint8_t type, bool required_table)
{
if (test_bit(type, smbios_have_binfile_bitmap)) {
@@ -1418,14 +1265,6 @@ static bool save_opt_list(size_t *ndest, char ***dest, QemuOpts *opts,
return true;
}
-static void smbios_add_usr_blob_size(size_t size)
-{
- if (!usr_blobs_sizes) {
- usr_blobs_sizes = g_array_new(false, false, sizeof(size_t));
- }
- g_array_append_val(usr_blobs_sizes, size);
-}
-
void smbios_entry_add(QemuOpts *opts, Error **errp)
{
const char *val;
diff --git a/hw/smbios/smbios_legacy.c b/hw/smbios/smbios_legacy.c
new file mode 100644
index 0000000000..21f143e738
--- /dev/null
+++ b/hw/smbios/smbios_legacy.c
@@ -0,0 +1,179 @@
+/*
+ * SMBIOS legacy support
+ *
+ * Copyright (C) 2009 Hewlett-Packard Development Company, L.P.
+ * Copyright (C) 2013 Red Hat, Inc.
+ *
+ * Authors:
+ * Alex Williamson <alex.williamson@hp.com>
+ * Markus Armbruster <armbru@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ *
+ * Contributions after 2012-01-13 are licensed under the terms of the
+ * GNU GPL, version 2 or (at your option) any later version.
+ */
+
+#include "qemu/osdep.h"
+#include "qemu/bswap.h"
+#include "hw/firmware/smbios.h"
+#include "sysemu/sysemu.h"
+#include "qemu/error-report.h"
+
+struct smbios_header {
+ uint16_t length;
+ uint8_t type;
+} QEMU_PACKED;
+
+struct smbios_field {
+ struct smbios_header header;
+ uint8_t type;
+ uint16_t offset;
+ uint8_t data[];
+} QEMU_PACKED;
+
+struct smbios_table {
+ struct smbios_header header;
+ uint8_t data[];
+} QEMU_PACKED;
+
+#define SMBIOS_FIELD_ENTRY 0
+#define SMBIOS_TABLE_ENTRY 1
+
+static uint8_t *smbios_entries;
+static size_t smbios_entries_len;
+GArray *usr_blobs_sizes;
+
+void smbios_add_usr_blob_size(size_t size)
+{
+ if (!usr_blobs_sizes) {
+ usr_blobs_sizes = g_array_new(false, false, sizeof(size_t));
+ }
+ g_array_append_val(usr_blobs_sizes, size);
+}
+
+static void smbios_add_field(int type, int offset, const void *data, size_t len)
+{
+ struct smbios_field *field;
+
+ if (!smbios_entries) {
+ smbios_entries_len = sizeof(uint16_t);
+ smbios_entries = g_malloc0(smbios_entries_len);
+ }
+ smbios_entries = g_realloc(smbios_entries, smbios_entries_len +
+ sizeof(*field) + len);
+ field = (struct smbios_field *)(smbios_entries + smbios_entries_len);
+ field->header.type = SMBIOS_FIELD_ENTRY;
+ field->header.length = cpu_to_le16(sizeof(*field) + len);
+
+ field->type = type;
+ field->offset = cpu_to_le16(offset);
+ memcpy(field->data, data, len);
+
+ smbios_entries_len += sizeof(*field) + len;
+ (*(uint16_t *)smbios_entries) =
+ cpu_to_le16(le16_to_cpu(*(uint16_t *)smbios_entries) + 1);
+}
+
+static void smbios_maybe_add_str(int type, int offset, const char *data)
+{
+ if (data) {
+ smbios_add_field(type, offset, data, strlen(data) + 1);
+ }
+}
+
+static void smbios_build_type_0_fields(void)
+{
+ smbios_maybe_add_str(0, offsetof(struct smbios_type_0, vendor_str),
+ smbios_type0.vendor);
+ smbios_maybe_add_str(0, offsetof(struct smbios_type_0, bios_version_str),
+ smbios_type0.version);
+ smbios_maybe_add_str(0, offsetof(struct smbios_type_0,
+ bios_release_date_str),
+ smbios_type0.date);
+ if (smbios_type0.have_major_minor) {
+ smbios_add_field(0, offsetof(struct smbios_type_0,
+ system_bios_major_release),
+ &smbios_type0.major, 1);
+ smbios_add_field(0, offsetof(struct smbios_type_0,
+ system_bios_minor_release),
+ &smbios_type0.minor, 1);
+ }
+}
+
+static void smbios_build_type_1_fields(void)
+{
+ smbios_maybe_add_str(1, offsetof(struct smbios_type_1, manufacturer_str),
+ smbios_type1.manufacturer);
+ smbios_maybe_add_str(1, offsetof(struct smbios_type_1, product_name_str),
+ smbios_type1.product);
+ smbios_maybe_add_str(1, offsetof(struct smbios_type_1, version_str),
+ smbios_type1.version);
+ smbios_maybe_add_str(1, offsetof(struct smbios_type_1, serial_number_str),
+ smbios_type1.serial);
+ smbios_maybe_add_str(1, offsetof(struct smbios_type_1, sku_number_str),
+ smbios_type1.sku);
+ smbios_maybe_add_str(1, offsetof(struct smbios_type_1, family_str),
+ smbios_type1.family);
+ if (qemu_uuid_set) {
+ /*
+ * We don't encode the UUID in the "wire format" here because this
+ * function is for legacy mode and needs to keep the guest ABI, and
+ * because we don't know what's the SMBIOS version advertised by the
+ * BIOS.
+ */
+ smbios_add_field(1, offsetof(struct smbios_type_1, uuid),
+ &qemu_uuid, 16);
+ }
+}
+
+uint8_t *smbios_get_table_legacy(size_t *length)
+{
+ int i;
+ size_t usr_offset;
+
+ /* complain if fields were given for types > 1 */
+ if (find_next_bit(smbios_have_fields_bitmap,
+ SMBIOS_MAX_TYPE + 1, 2) < SMBIOS_MAX_TYPE + 1) {
+ error_report("can't process fields for smbios "
+ "types > 1 on machine versions < 2.1!");
+ exit(1);
+ }
+
+ if (test_bit(4, smbios_have_binfile_bitmap)) {
+ error_report("can't process table for smbios "
+ "type 4 on machine versions < 2.1!");
+ exit(1);
+ }
+
+ g_free(smbios_entries);
+ smbios_entries_len = sizeof(uint16_t);
+ smbios_entries = g_malloc0(smbios_entries_len);
+
+ for (i = 0, usr_offset = 0; usr_blobs_sizes && i < usr_blobs_sizes->len;
+ i++)
+ {
+ struct smbios_table *table;
+ struct smbios_structure_header *header;
+ size_t size = g_array_index(usr_blobs_sizes, size_t, i);
+
+ header = (struct smbios_structure_header *)(usr_blobs + usr_offset);
+ smbios_entries = g_realloc(smbios_entries, smbios_entries_len +
+ size + sizeof(*table));
+ table = (struct smbios_table *)(smbios_entries + smbios_entries_len);
+ table->header.type = SMBIOS_TABLE_ENTRY;
+ table->header.length = cpu_to_le16(sizeof(*table) + size);
+ memcpy(table->data, header, size);
+ smbios_entries_len += sizeof(*table) + size;
+ (*(uint16_t *)smbios_entries) =
+ cpu_to_le16(le16_to_cpu(*(uint16_t *)smbios_entries) + 1);
+ usr_offset += size;
+ }
+
+ smbios_build_type_0_fields();
+ smbios_build_type_1_fields();
+ smbios_validate_table();
+ *length = smbios_entries_len;
+ return smbios_entries;
+}
diff --git a/hw/smbios/smbios_legacy_stub.c b/hw/smbios/smbios_legacy_stub.c
new file mode 100644
index 0000000000..f29b15316c
--- /dev/null
+++ b/hw/smbios/smbios_legacy_stub.c
@@ -0,0 +1,15 @@
+/*
+ * IPMI SMBIOS firmware handling
+ *
+ * Copyright (c) 2024 Igor Mammedov, Red Hat, Inc.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#include "qemu/osdep.h"
+#include "hw/firmware/smbios.h"
+
+void smbios_add_usr_blob_size(size_t size)
+{
+}
diff --git a/include/hw/firmware/smbios.h b/include/hw/firmware/smbios.h
index 333de0d5fc..92e9aba415 100644
--- a/include/hw/firmware/smbios.h
+++ b/include/hw/firmware/smbios.h
@@ -17,6 +17,9 @@
*
*/
+extern uint8_t *usr_blobs;
+extern GArray *usr_blobs_sizes;
+
typedef struct {
const char *vendor, *version, *date;
bool have_major_minor, uefi;
@@ -323,6 +326,8 @@ struct smbios_type_127 {
struct smbios_structure_header header;
} QEMU_PACKED;
+void smbios_validate_table(void);
+void smbios_add_usr_blob_size(size_t size);
void smbios_entry_add(QemuOpts *opts, Error **errp);
void smbios_set_cpuid(uint32_t version, uint32_t features);
void smbios_set_defaults(const char *manufacturer, const char *product,
--
2.39.3

65
kvm-smbios-cleanup-smbios_get_tables-from-legacy-handlin.patch
View File

@ -1,65 +0,0 @@
From 07f6ef2d032cda3e746ac2477c0a9bc1ac636f45 Mon Sep 17 00:00:00 2001
From: Igor Mammedov <imammedo@redhat.com>
Date: Fri, 29 Dec 2023 14:08:13 +0100
Subject: [PATCH 06/20] smbios: cleanup smbios_get_tables() from legacy
handling
RH-Author: Igor Mammedov <imammedo@redhat.com>
RH-MergeRequest: 230: Workaround Windows failing to find 64bit SMBIOS entry point with SeaBIOS
RH-Jira: RHEL-21705
RH-Acked-by: MST <mst@redhat.com>
RH-Acked-by: Ani Sinha <None>
RH-Commit: [4/18] a5e09ce1df72293fecad863edd146a8c4b1a734f
JIRA: https://issues.redhat.com/browse/RHEL-21705
smbios_get_tables() bails out right away if leagacy mode is enabled
and won't generate any SMBIOS tables. At the same time x86 specific
fw_cfg_build_smbios() will genarate legacy tables and then proceed
to preparing temporary mem_array for useless call to
smbios_get_tables() and then discard it.
Drop legacy related check in smbios_get_tables() and return from
fw_cfg_build_smbios() early if legacy tables where built without
proceeding to non legacy part of the function.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Ani Sinha <anisinha@redhat.com>
Tested-by: Fiona Ebner <f.ebner@proxmox.com>
---
hw/i386/fw_cfg.c | 1 +
hw/smbios/smbios.c | 6 ------
2 files changed, 1 insertion(+), 6 deletions(-)
diff --git a/hw/i386/fw_cfg.c b/hw/i386/fw_cfg.c
index 6a5466faf0..ed72b1442d 100644
--- a/hw/i386/fw_cfg.c
+++ b/hw/i386/fw_cfg.c
@@ -76,6 +76,7 @@ void fw_cfg_build_smbios(PCMachineState *pcms, FWCfgState *fw_cfg)
if (smbios_tables) {
fw_cfg_add_bytes(fw_cfg, FW_CFG_SMBIOS_ENTRIES,
smbios_tables, smbios_tables_len);
+ return;
}
/* build the array of physical mem area from e820 table */
diff --git a/hw/smbios/smbios.c b/hw/smbios/smbios.c
index 074705fa4c..b13e40bae2 100644
--- a/hw/smbios/smbios.c
+++ b/hw/smbios/smbios.c
@@ -1244,12 +1244,6 @@ void smbios_get_tables(MachineState *ms,
{
unsigned i, dimm_cnt, offset;
- if (smbios_legacy) {
- *tables = *anchor = NULL;
- *tables_len = *anchor_len = 0;
- return;
- }
-
if (!smbios_immutable) {
smbios_build_type_0_table();
smbios_build_type_1_table();
--
2.39.3

38
kvm-smbios-clear-smbios_type4_count-before-building-tabl.patch
View File

@ -1,38 +0,0 @@
From c0282a842a912aacac28a6ae229de5854c3fb5df Mon Sep 17 00:00:00 2001
From: Igor Mammedov <imammedo@redhat.com>
Date: Mon, 26 Feb 2024 13:20:22 +0100
Subject: [PATCH 16/20] smbios: clear smbios_type4_count before building tables
RH-Author: Igor Mammedov <imammedo@redhat.com>
RH-MergeRequest: 230: Workaround Windows failing to find 64bit SMBIOS entry point with SeaBIOS
RH-Jira: RHEL-21705
RH-Acked-by: MST <mst@redhat.com>
RH-Acked-by: Ani Sinha <None>
RH-Commit: [14/18] f809595d2934ae975c0b7d17a4a79645e062ba42
JIRA: https://issues.redhat.com/browse/RHEL-21705
it will help to keep type 4 tables accounting correct in case
SMBIOS tables are built multiple times.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Tested-by: Fiona Ebner <f.ebner@proxmox.com>
---
hw/smbios/smbios.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/hw/smbios/smbios.c b/hw/smbios/smbios.c
index 7e32430b85..4521ea386c 100644
--- a/hw/smbios/smbios.c
+++ b/hw/smbios/smbios.c
@@ -1111,6 +1111,7 @@ void smbios_get_tables(MachineState *ms,
ep_type == SMBIOS_ENTRY_POINT_TYPE_64);
g_free(smbios_tables);
+ smbios_type4_count = 0;
smbios_tables = g_memdup2(usr_blobs, usr_blobs_len);
smbios_tables_len = usr_blobs_len;
smbios_table_max = usr_table_max;
--
2.39.3

133
kvm-smbios-don-t-check-type4-structures-in-legacy-mode.patch
View File

@ -1,133 +0,0 @@
From 2b76d95ec07aba6d96070ee90c5015c1676be091 Mon Sep 17 00:00:00 2001
From: Igor Mammedov <imammedo@redhat.com>
Date: Tue, 13 Feb 2024 16:25:54 +0100
Subject: [PATCH 10/20] smbios: don't check type4 structures in legacy mode
RH-Author: Igor Mammedov <imammedo@redhat.com>
RH-MergeRequest: 230: Workaround Windows failing to find 64bit SMBIOS entry point with SeaBIOS
RH-Jira: RHEL-21705
RH-Acked-by: MST <mst@redhat.com>
RH-Acked-by: Ani Sinha <None>
RH-Commit: [8/18] c1f8409ea0d916f333c9373535bf21b521c62855
JIRA: https://issues.redhat.com/browse/RHEL-21705
legacy mode doesn't support structures of type 2 and more,
and CLI has a check for '-smbios type' option, however it's
still possible to sneak in type4 as a blob with '-smbios file'
option. However doing the later makes SMBIOS tables broken
since SeaBIOS doesn't expect that.
Rather than trying to add support for type4 to legacy code
(both QEMU and SeaBIOS), simplify smbios_get_table_legacy()
by dropping not relevant check in legacy code and error out
on type4 blob.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Ani Sinha <anisinha@redhat.com>
Tested-by: Fiona Ebner <f.ebner@proxmox.com>
Conflicts: include/hw/firmware/smbios.h
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Please enter the commit message for your changes. Lines starting
---
hw/i386/fw_cfg.c | 3 +--
hw/smbios/smbios.c | 18 ++++++++++++++----
include/hw/firmware/smbios.h | 2 +-
3 files changed, 16 insertions(+), 7 deletions(-)
diff --git a/hw/i386/fw_cfg.c b/hw/i386/fw_cfg.c
index bb7149c4c3..a25793a68f 100644
--- a/hw/i386/fw_cfg.c
+++ b/hw/i386/fw_cfg.c
@@ -73,8 +73,7 @@ void fw_cfg_build_smbios(PCMachineState *pcms, FWCfgState *fw_cfg)
smbios_set_cpuid(cpu->env.cpuid_version, cpu->env.features[FEAT_1_EDX]);
if (pcmc->smbios_legacy_mode) {
- smbios_tables = smbios_get_table_legacy(ms->smp.cpus,
- &smbios_tables_len);
+ smbios_tables = smbios_get_table_legacy(&smbios_tables_len);
fw_cfg_add_bytes(fw_cfg, FW_CFG_SMBIOS_ENTRIES,
smbios_tables, smbios_tables_len);
return;
diff --git a/hw/smbios/smbios.c b/hw/smbios/smbios.c
index d8d68716d4..441517cf24 100644
--- a/hw/smbios/smbios.c
+++ b/hw/smbios/smbios.c
@@ -530,14 +530,17 @@ opts_init(smbios_register_config);
*/
#define SMBIOS_21_MAX_TABLES_LEN 0xffff
-static void smbios_validate_table(uint32_t expected_t4_count)
+static void smbios_check_type4_count(uint32_t expected_t4_count)
{
if (smbios_type4_count && smbios_type4_count != expected_t4_count) {
error_report("Expected %d SMBIOS Type 4 tables, got %d instead",
expected_t4_count, smbios_type4_count);
exit(1);
}
+}
+static void smbios_validate_table(void)
+{
if (smbios_ep_type == SMBIOS_ENTRY_POINT_TYPE_32 &&
smbios_tables_len > SMBIOS_21_MAX_TABLES_LEN) {
error_report("SMBIOS 2.1 table length %zu exceeds %d",
@@ -622,7 +625,7 @@ static void smbios_build_type_1_fields(void)
}
}
-uint8_t *smbios_get_table_legacy(uint32_t expected_t4_count, size_t *length)
+uint8_t *smbios_get_table_legacy(size_t *length)
{
int i;
size_t usr_offset;
@@ -635,6 +638,12 @@ uint8_t *smbios_get_table_legacy(uint32_t expected_t4_count, size_t *length)
exit(1);
}
+ if (test_bit(4, have_binfile_bitmap)) {
+ error_report("can't process table for smbios "
+ "type 4 on machine versions < 2.1!");
+ exit(1);
+ }
+
g_free(smbios_entries);
smbios_entries_len = sizeof(uint16_t);
smbios_entries = g_malloc0(smbios_entries_len);
@@ -661,7 +670,7 @@ uint8_t *smbios_get_table_legacy(uint32_t expected_t4_count, size_t *length)
smbios_build_type_0_fields();
smbios_build_type_1_fields();
- smbios_validate_table(expected_t4_count);
+ smbios_validate_table();
*length = smbios_entries_len;
return smbios_entries;
}
@@ -1319,7 +1328,8 @@ void smbios_get_tables(MachineState *ms,
smbios_build_type_41_table(errp);
smbios_build_type_127_table();
- smbios_validate_table(ms->smp.sockets);
+ smbios_check_type4_count(ms->smp.sockets);
+ smbios_validate_table();
smbios_entry_point_setup();
/* return tables blob and entry point (anchor), and their sizes */
diff --git a/include/hw/firmware/smbios.h b/include/hw/firmware/smbios.h
index b9fc9a0f42..d55018e5e3 100644
--- a/include/hw/firmware/smbios.h
+++ b/include/hw/firmware/smbios.h
@@ -315,7 +315,7 @@ void smbios_set_defaults(const char *manufacturer, const char *product,
SmbiosEntryPointType ep_type,
const char *stream_product,
const char *stream_version);
-uint8_t *smbios_get_table_legacy(uint32_t expected_t4_count, size_t *length);
+uint8_t *smbios_get_table_legacy(size_t *length);
void smbios_get_tables(MachineState *ms,
const struct smbios_phys_mem_area *mem_array,
const unsigned int mem_array_size,
--
2.39.3

72
kvm-smbios-error-out-when-building-type-4-table-is-not-p.patch
View File

@ -1,72 +0,0 @@
From bbb2d260e6f33380b9df28c74421055bd8dccda5 Mon Sep 17 00:00:00 2001
From: Igor Mammedov <imammedo@redhat.com>
Date: Mon, 26 Feb 2024 12:59:33 +0100
Subject: [PATCH 19/20] smbios: error out when building type 4 table is not
possible
RH-Author: Igor Mammedov <imammedo@redhat.com>
RH-MergeRequest: 230: Workaround Windows failing to find 64bit SMBIOS entry point with SeaBIOS
RH-Jira: RHEL-21705
RH-Acked-by: MST <mst@redhat.com>
RH-Acked-by: Ani Sinha <None>
RH-Commit: [17/18] 86b1c67bfbe9c0c14a190cd1204b6ccd1de1630f
JIRA: https://issues.redhat.com/browse/RHEL-21705
If SMBIOS v2 version is requested but number of cores/threads
are more than it's possible to describe with v2, error out
instead of silently ignoring the fact and filling core/thread
count with bogus values.
This will help caller to decide if it should fallback to
SMBIOSv3 when smbios-entry-point-type='auto'
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Ani Sinha <anisinha@redhat.com>
Tested-by: Fiona Ebner <f.ebner@proxmox.com>
---
hw/smbios/smbios.c | 14 ++++++++++++--
1 file changed, 12 insertions(+), 2 deletions(-)
diff --git a/hw/smbios/smbios.c b/hw/smbios/smbios.c
index 3d9dcb0d31..637aa952f5 100644
--- a/hw/smbios/smbios.c
+++ b/hw/smbios/smbios.c
@@ -655,7 +655,8 @@ static void smbios_build_type_3_table(void)
}
static void smbios_build_type_4_table(MachineState *ms, unsigned instance,
- SmbiosEntryPointType ep_type)
+ SmbiosEntryPointType ep_type,
+ Error **errp)
{
char sock_str[128];
size_t tbl_len = SMBIOS_TYPE_4_LEN_V28;
@@ -709,6 +710,12 @@ static void smbios_build_type_4_table(MachineState *ms, unsigned instance,
if (tbl_len == SMBIOS_TYPE_4_LEN_V30) {
t->core_count2 = t->core_enabled2 = cpu_to_le16(cores_per_socket);
t->thread_count2 = cpu_to_le16(threads_per_socket);
+ } else if (t->core_count == 0xFF || t->thread_count == 0xFF) {
+ error_setg(errp, "SMBIOS 2.0 doesn't support number of processor "
+ "cores/threads more than 255, use "
+ "-machine smbios-entry-point-type=64 option to enable "
+ "SMBIOS 3.0 support");
+ return;
}
SMBIOS_BUILD_TABLE_POST;
@@ -1126,7 +1133,10 @@ static bool smbios_get_tables_ep(MachineState *ms,
assert(ms->smp.sockets >= 1);
for (i = 0; i < ms->smp.sockets; i++) {
- smbios_build_type_4_table(ms, i, ep_type);
+ smbios_build_type_4_table(ms, i, ep_type, errp);
+ if (*errp) {
+ goto err_exit;
+ }
}
smbios_build_type_8_table();
--
2.39.3

48
kvm-smbios-extend-smbios-entry-point-type-with-auto-valu.patch
View File

@ -1,48 +0,0 @@
From c083959c963fde33f4769fd4c6e122dd16ce6d3c Mon Sep 17 00:00:00 2001
From: Igor Mammedov <imammedo@redhat.com>
Date: Wed, 21 Feb 2024 16:04:36 +0100
Subject: [PATCH 17/20] smbios: extend smbios-entry-point-type with 'auto'
value
RH-Author: Igor Mammedov <imammedo@redhat.com>
RH-MergeRequest: 230: Workaround Windows failing to find 64bit SMBIOS entry point with SeaBIOS
RH-Jira: RHEL-21705
RH-Acked-by: MST <mst@redhat.com>
RH-Acked-by: Ani Sinha <None>
RH-Commit: [15/18] 202563dcf77e062a238aa2a10ec14c25d3f5a7d0
JIRA: https://issues.redhat.com/browse/RHEL-21705
later patches will use it to pick SMBIOS version at runtime
depending on configuration.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Acked-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Ani Sinha <anisinha@redhat.com>
Tested-by: Fiona Ebner <f.ebner@proxmox.com>
---
qapi/machine.json | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/qapi/machine.json b/qapi/machine.json
index b6d634b30d..99f6368fa6 100644
--- a/qapi/machine.json
+++ b/qapi/machine.json
@@ -1788,10 +1788,13 @@
#
# @64: SMBIOS version 3.0 (64-bit) Entry Point
#
+# @auto: Either 2.x or 3.x SMBIOS version, 2.x if configuration can be
+# described by it and 3.x otherwise (since: 9.0)
+#
# Since: 7.0
##
{ 'enum': 'SmbiosEntryPointType',
- 'data': [ '32', '64' ] }
+ 'data': [ '32', '64', 'auto' ] }
##
# @MemorySizeConfiguration:
--
2.39.3

281
kvm-smbios-get-rid-of-global-smbios_ep_type.patch
View File

@ -1,281 +0,0 @@
From be0abbf3f7845847b46486704c46c5de5a2b2323 Mon Sep 17 00:00:00 2001
From: Igor Mammedov <imammedo@redhat.com>
Date: Mon, 26 Feb 2024 13:49:14 +0100
Subject: [PATCH 15/20] smbios: get rid of global smbios_ep_type
RH-Author: Igor Mammedov <imammedo@redhat.com>
RH-MergeRequest: 230: Workaround Windows failing to find 64bit SMBIOS entry point with SeaBIOS
RH-Jira: RHEL-21705
RH-Acked-by: MST <mst@redhat.com>
RH-Acked-by: Ani Sinha <None>
RH-Commit: [13/18] 2e838ed0d03989e2e4ee08041b5ba64d5d7f5820
JIRA: https://issues.redhat.com/browse/RHEL-21705
Conflicts: hw/arm/virt.c, hw/i386/fw_cfg.c, hw/riscv/virt.c, hw/smbios/smbios.c,
include/hw/firmware/smbios.h
due to downstream specific smbios_set_defaults()
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Acked-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Ani Sinha <anisinha@redhat.com>
Tested-by: Fiona Ebner <f.ebner@proxmox.com>
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
---
hw/arm/virt.c | 4 ++--
hw/i386/fw_cfg.c | 6 +++---
hw/i386/fw_cfg.h | 3 ++-
hw/i386/pc.c | 2 +-
hw/loongarch/virt.c | 7 ++++---
hw/smbios/smbios.c | 26 ++++++++++++++------------
hw/smbios/smbios_legacy.c | 2 +-
include/hw/firmware/smbios.h | 4 ++--
8 files changed, 29 insertions(+), 25 deletions(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index e5cfc19c08..e4a66affcb 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -1695,14 +1695,14 @@ static void virt_build_smbios(VirtMachineState *vms)
smbios_set_defaults("QEMU", product,
vmc->smbios_old_sys_ver ? "1.0" : mc->name,
- true, SMBIOS_ENTRY_POINT_TYPE_64,
+ true,
NULL, NULL);
/* build the array of physical mem area from base_memmap */
mem_array.address = vms->memmap[VIRT_MEM].base;
mem_array.length = ms->ram_size;
- smbios_get_tables(ms, &mem_array, 1,
+ smbios_get_tables(ms, SMBIOS_ENTRY_POINT_TYPE_64, &mem_array, 1,
&smbios_tables, &smbios_tables_len,
&smbios_anchor, &smbios_anchor_len,
&error_fatal);
diff --git a/hw/i386/fw_cfg.c b/hw/i386/fw_cfg.c
index bdc3cc4556..58429bb78d 100644
--- a/hw/i386/fw_cfg.c
+++ b/hw/i386/fw_cfg.c
@@ -48,7 +48,8 @@ const char *fw_cfg_arch_key_name(uint16_t key)
return NULL;
}
-void fw_cfg_build_smbios(PCMachineState *pcms, FWCfgState *fw_cfg)
+void fw_cfg_build_smbios(PCMachineState *pcms, FWCfgState *fw_cfg,
+ SmbiosEntryPointType ep_type)
{
#ifdef CONFIG_SMBIOS
uint8_t *smbios_tables, *smbios_anchor;
@@ -64,7 +65,6 @@ void fw_cfg_build_smbios(PCMachineState *pcms, FWCfgState *fw_cfg)
/* These values are guest ABI, do not change */
smbios_set_defaults("QEMU", mc->desc, mc->name,
pcmc->smbios_uuid_encoded,
- pcms->smbios_entry_point_type,
pcmc->smbios_stream_product,
pcmc->smbios_stream_version);
}
@@ -91,7 +91,7 @@ void fw_cfg_build_smbios(PCMachineState *pcms, FWCfgState *fw_cfg)
array_count++;
}
}
- smbios_get_tables(ms, mem_array, array_count,
+ smbios_get_tables(ms, ep_type, mem_array, array_count,
&smbios_tables, &smbios_tables_len,
&smbios_anchor, &smbios_anchor_len,
&error_fatal);
diff --git a/hw/i386/fw_cfg.h b/hw/i386/fw_cfg.h
index 1e1de6b4a3..92e310f5fd 100644
--- a/hw/i386/fw_cfg.h
+++ b/hw/i386/fw_cfg.h
@@ -23,7 +23,8 @@
FWCfgState *fw_cfg_arch_create(MachineState *ms,
uint16_t boot_cpus,
uint16_t apic_id_limit);
-void fw_cfg_build_smbios(PCMachineState *ms, FWCfgState *fw_cfg);
+void fw_cfg_build_smbios(PCMachineState *pcms, FWCfgState *fw_cfg,
+ SmbiosEntryPointType ep_type);
void fw_cfg_build_feature_control(MachineState *ms, FWCfgState *fw_cfg);
void fw_cfg_add_acpi_dsdt(Aml *scope, FWCfgState *fw_cfg);
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 16de2a59e8..ae6777fc1a 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -847,7 +847,7 @@ void pc_machine_done(Notifier *notifier, void *data)
acpi_setup();
if (x86ms->fw_cfg) {
- fw_cfg_build_smbios(pcms, x86ms->fw_cfg);
+ fw_cfg_build_smbios(pcms, x86ms->fw_cfg, pcms->smbios_entry_point_type);
fw_cfg_build_feature_control(MACHINE(pcms), x86ms->fw_cfg);
/* update FW_CFG_NB_CPUS to account for -device added CPUs */
fw_cfg_modify_i16(x86ms->fw_cfg, FW_CFG_NB_CPUS, x86ms->boot_cpus);
diff --git a/hw/loongarch/virt.c b/hw/loongarch/virt.c
index 7358a023d3..77956b5ada 100644
--- a/hw/loongarch/virt.c
+++ b/hw/loongarch/virt.c
@@ -320,10 +320,11 @@ static void virt_build_smbios(LoongArchMachineState *lams)
return;
}
- smbios_set_defaults("QEMU", product, mc->name,
- true, SMBIOS_ENTRY_POINT_TYPE_64);
+ smbios_set_defaults("QEMU", product, mc->name, true);
- smbios_get_tables(ms, NULL, 0, &smbios_tables, &smbios_tables_len,
+ smbios_get_tables(ms, SMBIOS_ENTRY_POINT_TYPE_64,
+ NULL, 0,
+ &smbios_tables, &smbios_tables_len,
&smbios_anchor, &smbios_anchor_len, &error_fatal);
if (smbios_anchor) {
diff --git a/hw/smbios/smbios.c b/hw/smbios/smbios.c
index b5745c6c2d..7e32430b85 100644
--- a/hw/smbios/smbios.c
+++ b/hw/smbios/smbios.c
@@ -47,7 +47,6 @@ uint8_t *smbios_tables;
size_t smbios_tables_len;
unsigned smbios_table_max;
unsigned smbios_table_cnt;
-static SmbiosEntryPointType smbios_ep_type = SMBIOS_ENTRY_POINT_TYPE_32;
static SmbiosEntryPoint ep;
@@ -506,9 +505,9 @@ static bool smbios_check_type4_count(uint32_t expected_t4_count, Error **errp)
return true;
}
-bool smbios_validate_table(Error **errp)
+bool smbios_validate_table(SmbiosEntryPointType ep_type, Error **errp)
{
- if (smbios_ep_type == SMBIOS_ENTRY_POINT_TYPE_32 &&
+ if (ep_type == SMBIOS_ENTRY_POINT_TYPE_32 &&
smbios_tables_len > SMBIOS_21_MAX_TABLES_LEN) {
error_setg(errp, "SMBIOS 2.1 table length %zu exceeds %d",
smbios_tables_len, SMBIOS_21_MAX_TABLES_LEN);
@@ -655,14 +654,15 @@ static void smbios_build_type_3_table(void)
SMBIOS_BUILD_TABLE_POST;
}
-static void smbios_build_type_4_table(MachineState *ms, unsigned instance)
+static void smbios_build_type_4_table(MachineState *ms, unsigned instance,
+ SmbiosEntryPointType ep_type)
{
char sock_str[128];
size_t tbl_len = SMBIOS_TYPE_4_LEN_V28;
unsigned threads_per_socket;
unsigned cores_per_socket;
- if (smbios_ep_type == SMBIOS_ENTRY_POINT_TYPE_64) {
+ if (ep_type == SMBIOS_ENTRY_POINT_TYPE_64) {
tbl_len = SMBIOS_TYPE_4_LEN_V30;
}
@@ -991,13 +991,11 @@ void smbios_set_cpuid(uint32_t version, uint32_t features)
void smbios_set_defaults(const char *manufacturer, const char *product,
const char *version,
bool uuid_encoded,
- SmbiosEntryPointType ep_type,
const char *stream_product,
const char *stream_version)
{
smbios_have_defaults = true;
smbios_uuid_encoded = uuid_encoded;
- smbios_ep_type = ep_type;
/*
* If @stream_product & @stream_version are non-NULL, then
@@ -1048,9 +1046,9 @@ void smbios_set_defaults(const char *manufacturer, const char *product,
SMBIOS_SET_DEFAULT(type17.manufacturer, manufacturer);
}
-static void smbios_entry_point_setup(void)
+static void smbios_entry_point_setup(SmbiosEntryPointType ep_type)
{
- switch (smbios_ep_type) {
+ switch (ep_type) {
case SMBIOS_ENTRY_POINT_TYPE_32:
memcpy(ep.ep21.anchor_string, "_SM_", 4);
memcpy(ep.ep21.intermediate_anchor_string, "_DMI_", 5);
@@ -1100,6 +1098,7 @@ static void smbios_entry_point_setup(void)
}
void smbios_get_tables(MachineState *ms,
+ SmbiosEntryPointType ep_type,
const struct smbios_phys_mem_area *mem_array,
const unsigned int mem_array_size,
uint8_t **tables, size_t *tables_len,
@@ -1108,6 +1107,9 @@ void smbios_get_tables(MachineState *ms,
{
unsigned i, dimm_cnt, offset;
+ assert(ep_type == SMBIOS_ENTRY_POINT_TYPE_32 ||
+ ep_type == SMBIOS_ENTRY_POINT_TYPE_64);
+
g_free(smbios_tables);
smbios_tables = g_memdup2(usr_blobs, usr_blobs_len);
smbios_tables_len = usr_blobs_len;
@@ -1122,7 +1124,7 @@ void smbios_get_tables(MachineState *ms,
assert(ms->smp.sockets >= 1);
for (i = 0; i < ms->smp.sockets; i++) {
- smbios_build_type_4_table(ms, i);
+ smbios_build_type_4_table(ms, i, ep_type);
}
smbios_build_type_8_table();
@@ -1171,10 +1173,10 @@ void smbios_get_tables(MachineState *ms,
if (!smbios_check_type4_count(ms->smp.sockets, errp)) {
goto err_exit;
}
- if (!smbios_validate_table(errp)) {
+ if (!smbios_validate_table(ep_type, errp)) {
goto err_exit;
}
- smbios_entry_point_setup();
+ smbios_entry_point_setup(ep_type);
/* return tables blob and entry point (anchor), and their sizes */
*tables = smbios_tables;
diff --git a/hw/smbios/smbios_legacy.c b/hw/smbios/smbios_legacy.c
index a6544bf55a..06907cd16c 100644
--- a/hw/smbios/smbios_legacy.c
+++ b/hw/smbios/smbios_legacy.c
@@ -173,7 +173,7 @@ uint8_t *smbios_get_table_legacy(size_t *length, Error **errp)
smbios_build_type_0_fields();
smbios_build_type_1_fields();
- if (!smbios_validate_table(errp)) {
+ if (!smbios_validate_table(SMBIOS_ENTRY_POINT_TYPE_32, errp)) {
goto err_exit;
}
diff --git a/include/hw/firmware/smbios.h b/include/hw/firmware/smbios.h
index 44af3a0d82..781298f594 100644
--- a/include/hw/firmware/smbios.h
+++ b/include/hw/firmware/smbios.h
@@ -326,18 +326,18 @@ struct smbios_type_127 {
struct smbios_structure_header header;
} QEMU_PACKED;
-bool smbios_validate_table(Error **errp);
+bool smbios_validate_table(SmbiosEntryPointType ep_type, Error **errp);
void smbios_add_usr_blob_size(size_t size);
void smbios_entry_add(QemuOpts *opts, Error **errp);
void smbios_set_cpuid(uint32_t version, uint32_t features);
void smbios_set_defaults(const char *manufacturer, const char *product,
const char *version,
bool uuid_encoded,
- SmbiosEntryPointType ep_type,
const char *stream_product,
const char *stream_version);
uint8_t *smbios_get_table_legacy(size_t *length, Error **errp);
void smbios_get_tables(MachineState *ms,
+ SmbiosEntryPointType ep_type,
const struct smbios_phys_mem_area *mem_array,
const unsigned int mem_array_size,
uint8_t **tables, size_t *tables_len,
--
2.39.3

198
kvm-smbios-get-rid-of-smbios_legacy-global.patch
View File

@ -1,198 +0,0 @@
From 0802fa7199c8085d018fc38dd4beaa5062d383d1 Mon Sep 17 00:00:00 2001
From: Igor Mammedov <imammedo@redhat.com>
Date: Fri, 29 Dec 2023 15:37:29 +0100
Subject: [PATCH 08/20] smbios: get rid of smbios_legacy global
RH-Author: Igor Mammedov <imammedo@redhat.com>
RH-MergeRequest: 230: Workaround Windows failing to find 64bit SMBIOS entry point with SeaBIOS
RH-Jira: RHEL-21705
RH-Acked-by: MST <mst@redhat.com>
RH-Acked-by: Ani Sinha <None>
RH-Commit: [6/18] 684dd1dca8d611c6de97b26ef8c1cda6ca509d54
JIRA: https://issues.redhat.com/browse/RHEL-21705
clean up smbios_set_defaults() which is reused by legacy
and non legacy machines from being aware of 'legacy' notion
and need to turn it off. And push legacy handling up to
PC machine code where it's relevant.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Ani Sinha <anisinha@redhat.com>
Acked-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Tested-by: Fiona Ebner <f.ebner@proxmox.com>
Conflicts: hw/arm/virt.c, hw/i386/fw_cfg.c, hw/loongarch/virt.c,
hw/smbios/smbios.c, include/hw/firmware/smbios.h
due to downstream specifc signature of smbios_set_defaults()
PS:
while fixing conflicts move RHEL specific
smbios_stream_product/smbios_stream_version
at the end of arguments list
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
---
hw/arm/virt.c | 5 +++--
hw/i386/fw_cfg.c | 11 +++++-----
hw/loongarch/virt.c | 2 +-
hw/smbios/smbios.c | 39 ++++++++++++++++--------------------
include/hw/firmware/smbios.h | 6 +++---
5 files changed, 30 insertions(+), 33 deletions(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 943c563391..e5cfc19c08 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -1694,8 +1694,9 @@ static void virt_build_smbios(VirtMachineState *vms)
}
smbios_set_defaults("QEMU", product,
- vmc->smbios_old_sys_ver ? "1.0" : mc->name, false,
- true, NULL, NULL, SMBIOS_ENTRY_POINT_TYPE_64);
+ vmc->smbios_old_sys_ver ? "1.0" : mc->name,
+ true, SMBIOS_ENTRY_POINT_TYPE_64,
+ NULL, NULL);
/* build the array of physical mem area from base_memmap */
mem_array.address = vms->memmap[VIRT_MEM].base;
diff --git a/hw/i386/fw_cfg.c b/hw/i386/fw_cfg.c
index 79ff7f7225..bb7149c4c3 100644
--- a/hw/i386/fw_cfg.c
+++ b/hw/i386/fw_cfg.c
@@ -63,17 +63,18 @@ void fw_cfg_build_smbios(PCMachineState *pcms, FWCfgState *fw_cfg)
if (pcmc->smbios_defaults) {
/* These values are guest ABI, do not change */
smbios_set_defaults("QEMU", mc->desc, mc->name,
- pcmc->smbios_legacy_mode, pcmc->smbios_uuid_encoded,
+ pcmc->smbios_uuid_encoded,
+ pcms->smbios_entry_point_type,
pcmc->smbios_stream_product,
- pcmc->smbios_stream_version,
- pcms->smbios_entry_point_type);
+ pcmc->smbios_stream_version);
}
/* tell smbios about cpuid version and features */
smbios_set_cpuid(cpu->env.cpuid_version, cpu->env.features[FEAT_1_EDX]);
- smbios_tables = smbios_get_table_legacy(ms->smp.cpus, &smbios_tables_len);
- if (smbios_tables) {
+ if (pcmc->smbios_legacy_mode) {
+ smbios_tables = smbios_get_table_legacy(ms->smp.cpus,
+ &smbios_tables_len);
fw_cfg_add_bytes(fw_cfg, FW_CFG_SMBIOS_ENTRIES,
smbios_tables, smbios_tables_len);
return;
diff --git a/hw/loongarch/virt.c b/hw/loongarch/virt.c
index 4b7dc67a2d..7358a023d3 100644
--- a/hw/loongarch/virt.c
+++ b/hw/loongarch/virt.c
@@ -320,7 +320,7 @@ static void virt_build_smbios(LoongArchMachineState *lams)
return;
}
- smbios_set_defaults("QEMU", product, mc->name, false,
+ smbios_set_defaults("QEMU", product, mc->name,
true, SMBIOS_ENTRY_POINT_TYPE_64);
smbios_get_tables(ms, NULL, 0, &smbios_tables, &smbios_tables_len,
diff --git a/hw/smbios/smbios.c b/hw/smbios/smbios.c
index 8129d396d1..0c8c439859 100644
--- a/hw/smbios/smbios.c
+++ b/hw/smbios/smbios.c
@@ -54,7 +54,6 @@ struct smbios_table {
static uint8_t *smbios_entries;
static size_t smbios_entries_len;
-static bool smbios_legacy = true;
static bool smbios_uuid_encoded = true;
/* end: legacy structures & constants for <= 2.0 machines */
@@ -618,9 +617,16 @@ static void smbios_build_type_1_fields(void)
uint8_t *smbios_get_table_legacy(uint32_t expected_t4_count, size_t *length)
{
- if (!smbios_legacy) {
- *length = 0;
- return NULL;
+ /* drop unwanted version of command-line file blob(s) */
+ g_free(smbios_tables);
+ smbios_tables = NULL;
+
+ /* also complain if fields were given for types > 1 */
+ if (find_next_bit(have_fields_bitmap,
+ SMBIOS_MAX_TYPE + 1, 2) < SMBIOS_MAX_TYPE + 1) {
+ error_report("can't process fields for smbios "
+ "types > 1 on machine versions < 2.1!");
+ exit(1);
}
if (!smbios_immutable) {
@@ -1107,31 +1113,16 @@ void smbios_set_cpuid(uint32_t version, uint32_t features)
}
void smbios_set_defaults(const char *manufacturer, const char *product,
- const char *version, bool legacy_mode,
+ const char *version,
bool uuid_encoded,
+ SmbiosEntryPointType ep_type,
const char *stream_product,
- const char *stream_version,
- SmbiosEntryPointType ep_type)
+ const char *stream_version)
{
smbios_have_defaults = true;
- smbios_legacy = legacy_mode;
smbios_uuid_encoded = uuid_encoded;
smbios_ep_type = ep_type;
- /* drop unwanted version of command-line file blob(s) */
- if (smbios_legacy) {
- g_free(smbios_tables);
- /* in legacy mode, also complain if fields were given for types > 1 */
- if (find_next_bit(have_fields_bitmap,
- SMBIOS_MAX_TYPE+1, 2) < SMBIOS_MAX_TYPE+1) {
- error_report("can't process fields for smbios "
- "types > 1 on machine versions < 2.1!");
- exit(1);
- }
- } else {
- g_free(smbios_entries);
- }
-
/*
* If @stream_product & @stream_version are non-NULL, then
* we're following rules for new Windows driver support.
@@ -1241,6 +1232,10 @@ void smbios_get_tables(MachineState *ms,
{
unsigned i, dimm_cnt, offset;
+ /* drop unwanted (legacy) version of command-line file blob(s) */
+ g_free(smbios_entries);
+ smbios_entries = NULL;
+
if (!smbios_immutable) {
smbios_build_type_0_table();
smbios_build_type_1_table();
diff --git a/include/hw/firmware/smbios.h b/include/hw/firmware/smbios.h
index 95ec64ce2c..b9fc9a0f42 100644
--- a/include/hw/firmware/smbios.h
+++ b/include/hw/firmware/smbios.h
@@ -310,11 +310,11 @@ struct smbios_type_127 {
void smbios_entry_add(QemuOpts *opts, Error **errp);
void smbios_set_cpuid(uint32_t version, uint32_t features);
void smbios_set_defaults(const char *manufacturer, const char *product,
- const char *version, bool legacy_mode,
+ const char *version,
bool uuid_encoded,
+ SmbiosEntryPointType ep_type,
const char *stream_product,
- const char *stream_version,
- SmbiosEntryPointType ep_type);
+ const char *stream_version);
uint8_t *smbios_get_table_legacy(uint32_t expected_t4_count, size_t *length);
void smbios_get_tables(MachineState *ms,
const struct smbios_phys_mem_area *mem_array,
--
2.39.3

134
kvm-smbios-get-rid-of-smbios_smp_sockets-global.patch
View File

@ -1,134 +0,0 @@
From 1536f1ec00ddc1729854b381cc0d54814bb6c19f Mon Sep 17 00:00:00 2001
From: Igor Mammedov <imammedo@redhat.com>
Date: Fri, 29 Dec 2023 15:04:55 +0100
Subject: [PATCH 07/20] smbios: get rid of smbios_smp_sockets global
RH-Author: Igor Mammedov <imammedo@redhat.com>
RH-MergeRequest: 230: Workaround Windows failing to find 64bit SMBIOS entry point with SeaBIOS
RH-Jira: RHEL-21705
RH-Acked-by: MST <mst@redhat.com>
RH-Acked-by: Ani Sinha <None>
RH-Commit: [5/18] f59bfeb547b7febcf1de2b6179af006e7fa0bccd
JIRA: https://issues.redhat.com/browse/RHEL-21705
it makes smbios_validate_table() independent from
smbios_smp_sockets global, which in turn lets
smbios_get_tables() avoid using not related legacy code.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Ani Sinha <anisinha@redhat.com>
Tested-by: Fiona Ebner <f.ebner@proxmox.com>
Conflicts:
include/hw/firmware/smbios.h due to down-stream
(d9ff466c980d Machine type related general changes)
adding custom stream_product/stream_version
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
---
hw/i386/fw_cfg.c | 2 +-
hw/smbios/smbios.c | 22 +++++++++-------------
include/hw/firmware/smbios.h | 2 +-
3 files changed, 11 insertions(+), 15 deletions(-)
diff --git a/hw/i386/fw_cfg.c b/hw/i386/fw_cfg.c
index ed72b1442d..79ff7f7225 100644
--- a/hw/i386/fw_cfg.c
+++ b/hw/i386/fw_cfg.c
@@ -72,7 +72,7 @@ void fw_cfg_build_smbios(PCMachineState *pcms, FWCfgState *fw_cfg)
/* tell smbios about cpuid version and features */
smbios_set_cpuid(cpu->env.cpuid_version, cpu->env.features[FEAT_1_EDX]);
- smbios_tables = smbios_get_table_legacy(ms, &smbios_tables_len);
+ smbios_tables = smbios_get_table_legacy(ms->smp.cpus, &smbios_tables_len);
if (smbios_tables) {
fw_cfg_add_bytes(fw_cfg, FW_CFG_SMBIOS_ENTRIES,
smbios_tables, smbios_tables_len);
diff --git a/hw/smbios/smbios.c b/hw/smbios/smbios.c
index b13e40bae2..8129d396d1 100644
--- a/hw/smbios/smbios.c
+++ b/hw/smbios/smbios.c
@@ -73,7 +73,7 @@ static SmbiosEntryPoint ep;
static int smbios_type4_count = 0;
static bool smbios_immutable;
static bool smbios_have_defaults;
-static uint32_t smbios_cpuid_version, smbios_cpuid_features, smbios_smp_sockets;
+static uint32_t smbios_cpuid_version, smbios_cpuid_features;
static DECLARE_BITMAP(have_binfile_bitmap, SMBIOS_MAX_TYPE+1);
static DECLARE_BITMAP(have_fields_bitmap, SMBIOS_MAX_TYPE+1);
@@ -524,14 +524,11 @@ opts_init(smbios_register_config);
*/
#define SMBIOS_21_MAX_TABLES_LEN 0xffff
-static void smbios_validate_table(MachineState *ms)
+static void smbios_validate_table(uint32_t expected_t4_count)
{
- uint32_t expect_t4_count = smbios_legacy ?
- ms->smp.cpus : smbios_smp_sockets;
-
- if (smbios_type4_count && smbios_type4_count != expect_t4_count) {
+ if (smbios_type4_count && smbios_type4_count != expected_t4_count) {
error_report("Expected %d SMBIOS Type 4 tables, got %d instead",
- expect_t4_count, smbios_type4_count);
+ expected_t4_count, smbios_type4_count);
exit(1);
}
@@ -619,7 +616,7 @@ static void smbios_build_type_1_fields(void)
}
}
-uint8_t *smbios_get_table_legacy(MachineState *ms, size_t *length)
+uint8_t *smbios_get_table_legacy(uint32_t expected_t4_count, size_t *length)
{
if (!smbios_legacy) {
*length = 0;
@@ -629,7 +626,7 @@ uint8_t *smbios_get_table_legacy(MachineState *ms, size_t *length)
if (!smbios_immutable) {
smbios_build_type_0_fields();
smbios_build_type_1_fields();
- smbios_validate_table(ms);
+ smbios_validate_table(expected_t4_count);
smbios_immutable = true;
}
*length = smbios_entries_len;
@@ -1250,10 +1247,9 @@ void smbios_get_tables(MachineState *ms,
smbios_build_type_2_table();
smbios_build_type_3_table();
- smbios_smp_sockets = ms->smp.sockets;
- assert(smbios_smp_sockets >= 1);
+ assert(ms->smp.sockets >= 1);
- for (i = 0; i < smbios_smp_sockets; i++) {
+ for (i = 0; i < ms->smp.sockets; i++) {
smbios_build_type_4_table(ms, i);
}
@@ -1299,7 +1295,7 @@ void smbios_get_tables(MachineState *ms,
smbios_build_type_41_table(errp);
smbios_build_type_127_table();
- smbios_validate_table(ms);
+ smbios_validate_table(ms->smp.sockets);
smbios_entry_point_setup();
smbios_immutable = true;
}
diff --git a/include/hw/firmware/smbios.h b/include/hw/firmware/smbios.h
index f8dd07fe4c..95ec64ce2c 100644
--- a/include/hw/firmware/smbios.h
+++ b/include/hw/firmware/smbios.h
@@ -315,7 +315,7 @@ void smbios_set_defaults(const char *manufacturer, const char *product,
const char *stream_product,
const char *stream_version,
SmbiosEntryPointType ep_type);
-uint8_t *smbios_get_table_legacy(MachineState *ms, size_t *length);
+uint8_t *smbios_get_table_legacy(uint32_t expected_t4_count, size_t *length);
void smbios_get_tables(MachineState *ms,
const struct smbios_phys_mem_area *mem_array,
const unsigned int mem_array_size,
--
2.39.3

217
kvm-smbios-handle-errors-consistently.patch
View File

@ -1,217 +0,0 @@
From 7271c4424c6d90f0bb34f8090eb4e192eb2b2537 Mon Sep 17 00:00:00 2001
From: Igor Mammedov <imammedo@redhat.com>
Date: Tue, 20 Feb 2024 10:30:28 +0100
Subject: [PATCH 14/20] smbios: handle errors consistently
RH-Author: Igor Mammedov <imammedo@redhat.com>
RH-MergeRequest: 230: Workaround Windows failing to find 64bit SMBIOS entry point with SeaBIOS
RH-Jira: RHEL-21705
RH-Acked-by: MST <mst@redhat.com>
RH-Acked-by: Ani Sinha <None>
RH-Commit: [12/18] d8a5a70602ae0665ce35e5bf87b2d8420f9189bc
JIRA: https://issues.redhat.com/browse/RHEL-21705
Current code uses mix of error_report()+exit(1)
and error_setg() to handle errors.
Use newer error_setg() everywhere, beside consistency
it will allow to detect error condition without killing
QEMU and attempt switch-over to SMBIOS3.x tables/entrypoint
in follow up patch.
while at it, clear smbios_tables pointer after freeing.
that will avoid double free if smbios_get_tables() is called
multiple times.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Ani Sinha <anisinha@redhat.com>
Conflicts: include/hw/firmware/smbios.h
due to downstream specific smbios_set_defaults()
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
---
hw/i386/fw_cfg.c | 3 ++-
hw/smbios/smbios.c | 34 ++++++++++++++++++++++------------
hw/smbios/smbios_legacy.c | 22 ++++++++++++++--------
include/hw/firmware/smbios.h | 4 ++--
4 files changed, 40 insertions(+), 23 deletions(-)
diff --git a/hw/i386/fw_cfg.c b/hw/i386/fw_cfg.c
index a25793a68f..bdc3cc4556 100644
--- a/hw/i386/fw_cfg.c
+++ b/hw/i386/fw_cfg.c
@@ -73,7 +73,8 @@ void fw_cfg_build_smbios(PCMachineState *pcms, FWCfgState *fw_cfg)
smbios_set_cpuid(cpu->env.cpuid_version, cpu->env.features[FEAT_1_EDX]);
if (pcmc->smbios_legacy_mode) {
- smbios_tables = smbios_get_table_legacy(&smbios_tables_len);
+ smbios_tables = smbios_get_table_legacy(&smbios_tables_len,
+ &error_fatal);
fw_cfg_add_bytes(fw_cfg, FW_CFG_SMBIOS_ENTRIES,
smbios_tables, smbios_tables_len);
return;
diff --git a/hw/smbios/smbios.c b/hw/smbios/smbios.c
index e40204550e..b5745c6c2d 100644
--- a/hw/smbios/smbios.c
+++ b/hw/smbios/smbios.c
@@ -19,7 +19,6 @@
#include "qemu/units.h"
#include "qapi/error.h"
#include "qemu/config-file.h"
-#include "qemu/error-report.h"
#include "qemu/module.h"
#include "qemu/option.h"
#include "sysemu/sysemu.h"
@@ -497,23 +496,25 @@ opts_init(smbios_register_config);
*/
#define SMBIOS_21_MAX_TABLES_LEN 0xffff
-static void smbios_check_type4_count(uint32_t expected_t4_count)
+static bool smbios_check_type4_count(uint32_t expected_t4_count, Error **errp)
{
if (smbios_type4_count && smbios_type4_count != expected_t4_count) {
- error_report("Expected %d SMBIOS Type 4 tables, got %d instead",
- expected_t4_count, smbios_type4_count);
- exit(1);
+ error_setg(errp, "Expected %d SMBIOS Type 4 tables, got %d instead",
+ expected_t4_count, smbios_type4_count);
+ return false;
}
+ return true;
}
-void smbios_validate_table(void)
+bool smbios_validate_table(Error **errp)
{
if (smbios_ep_type == SMBIOS_ENTRY_POINT_TYPE_32 &&
smbios_tables_len > SMBIOS_21_MAX_TABLES_LEN) {
- error_report("SMBIOS 2.1 table length %zu exceeds %d",
- smbios_tables_len, SMBIOS_21_MAX_TABLES_LEN);
- exit(1);
+ error_setg(errp, "SMBIOS 2.1 table length %zu exceeds %d",
+ smbios_tables_len, SMBIOS_21_MAX_TABLES_LEN);
+ return false;
}
+ return true;
}
bool smbios_skip_table(uint8_t type, bool required_table)
@@ -1167,15 +1168,18 @@ void smbios_get_tables(MachineState *ms,
smbios_build_type_41_table(errp);
smbios_build_type_127_table();
- smbios_check_type4_count(ms->smp.sockets);
- smbios_validate_table();
+ if (!smbios_check_type4_count(ms->smp.sockets, errp)) {
+ goto err_exit;
+ }
+ if (!smbios_validate_table(errp)) {
+ goto err_exit;
+ }
smbios_entry_point_setup();
/* return tables blob and entry point (anchor), and their sizes */
*tables = smbios_tables;
*tables_len = smbios_tables_len;
*anchor = (uint8_t *)&ep;
-
/* calculate length based on anchor string */
if (!strncmp((char *)&ep, "_SM_", 4)) {
*anchor_len = sizeof(struct smbios_21_entry_point);
@@ -1184,6 +1188,12 @@ void smbios_get_tables(MachineState *ms,
} else {
abort();
}
+
+ return;
+err_exit:
+ g_free(smbios_tables);
+ smbios_tables = NULL;
+ return;
}
static void save_opt(const char **dest, QemuOpts *opts, const char *name)
diff --git a/hw/smbios/smbios_legacy.c b/hw/smbios/smbios_legacy.c
index 21f143e738..a6544bf55a 100644
--- a/hw/smbios/smbios_legacy.c
+++ b/hw/smbios/smbios_legacy.c
@@ -19,7 +19,7 @@
#include "qemu/bswap.h"
#include "hw/firmware/smbios.h"
#include "sysemu/sysemu.h"
-#include "qemu/error-report.h"
+#include "qapi/error.h"
struct smbios_header {
uint16_t length;
@@ -128,7 +128,7 @@ static void smbios_build_type_1_fields(void)
}
}
-uint8_t *smbios_get_table_legacy(size_t *length)
+uint8_t *smbios_get_table_legacy(size_t *length, Error **errp)
{
int i;
size_t usr_offset;
@@ -136,15 +136,15 @@ uint8_t *smbios_get_table_legacy(size_t *length)
/* complain if fields were given for types > 1 */
if (find_next_bit(smbios_have_fields_bitmap,
SMBIOS_MAX_TYPE + 1, 2) < SMBIOS_MAX_TYPE + 1) {
- error_report("can't process fields for smbios "
+ error_setg(errp, "can't process fields for smbios "
"types > 1 on machine versions < 2.1!");
- exit(1);
+ goto err_exit;
}
if (test_bit(4, smbios_have_binfile_bitmap)) {
- error_report("can't process table for smbios "
- "type 4 on machine versions < 2.1!");
- exit(1);
+ error_setg(errp, "can't process table for smbios "
+ "type 4 on machine versions < 2.1!");
+ goto err_exit;
}
g_free(smbios_entries);
@@ -173,7 +173,13 @@ uint8_t *smbios_get_table_legacy(size_t *length)
smbios_build_type_0_fields();
smbios_build_type_1_fields();
- smbios_validate_table();
+ if (!smbios_validate_table(errp)) {
+ goto err_exit;
+ }
+
*length = smbios_entries_len;
return smbios_entries;
+err_exit:
+ g_free(smbios_entries);
+ return NULL;
}
diff --git a/include/hw/firmware/smbios.h b/include/hw/firmware/smbios.h
index 92e9aba415..44af3a0d82 100644
--- a/include/hw/firmware/smbios.h
+++ b/include/hw/firmware/smbios.h
@@ -326,7 +326,7 @@ struct smbios_type_127 {
struct smbios_structure_header header;
} QEMU_PACKED;
-void smbios_validate_table(void);
+bool smbios_validate_table(Error **errp);
void smbios_add_usr_blob_size(size_t size);
void smbios_entry_add(QemuOpts *opts, Error **errp);
void smbios_set_cpuid(uint32_t version, uint32_t features);
@@ -336,7 +336,7 @@ void smbios_set_defaults(const char *manufacturer, const char *product,
SmbiosEntryPointType ep_type,
const char *stream_product,
const char *stream_version);
-uint8_t *smbios_get_table_legacy(size_t *length);
+uint8_t *smbios_get_table_legacy(size_t *length, Error **errp);
void smbios_get_tables(MachineState *ms,
const struct smbios_phys_mem_area *mem_array,
const unsigned int mem_array_size,
--
2.39.3

131
kvm-smbios-in-case-of-entry-point-is-auto-try-to-build-v.patch
View File

@ -1,131 +0,0 @@
From 38220bc61bdb1614f34a53481f7604720c9e9e5a Mon Sep 17 00:00:00 2001
From: Igor Mammedov <imammedo@redhat.com>
Date: Tue, 20 Feb 2024 10:41:06 +0100
Subject: [PATCH 18/20] smbios: in case of entry point is 'auto' try to build
v2 tables 1st
RH-Author: Igor Mammedov <imammedo@redhat.com>
RH-MergeRequest: 230: Workaround Windows failing to find 64bit SMBIOS entry point with SeaBIOS
RH-Jira: RHEL-21705
RH-Acked-by: MST <mst@redhat.com>
RH-Acked-by: Ani Sinha <None>
RH-Commit: [16/18] becbcb3d8dad4842e5939bb75e21f4e737a4a325
JIRA: https://issues.redhat.com/browse/RHEL-21705
QEMU for some time now uses SMBIOS 3.0 for PC/Q35 machines by
default, however Windows has a bug in locating SMBIOS 3.0
entrypoint and fails to find tables when booted on SeaBIOS
(on UEFI SMBIOS 3.0 tables work fine since firmware hands
over tables in another way)
Missing SMBIOS tables may lead to some issues for guest
though (worst are: possible reactiveation, inability to
get virtio drivers from 'Windows Update')
It's unclear at this point if MS will fix the issue on their
side. So instead of it (or rather in addition) this patch
will try to workaround the issue.
aka, use smbios-entry-point-type=auto to make QEMU try
generating conservative SMBIOS 2.0 tables and if that
fails (due to limits/requested configuration) fallback
to SMBIOS 3.0 tables.
With this in place majority of users will use SMBIOS 2.0
tables which work fine with (Windows + legacy BIOS).
The configurations that is not to possible to describe
with SMBIOS 2.0 will switch automatically to SMBIOS 3.0
(which will trigger Windows bug but there is nothing
QEMU can do here, so go and aks Microsoft to real fix).
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Ani Sinha <anisinha@redhat.com>
Tested-by: Fiona Ebner <f.ebner@proxmox.com>
---
hw/smbios/smbios.c | 52 +++++++++++++++++++++++++++++++++++++++++++---
1 file changed, 49 insertions(+), 3 deletions(-)
diff --git a/hw/smbios/smbios.c b/hw/smbios/smbios.c
index 4521ea386c..3d9dcb0d31 100644
--- a/hw/smbios/smbios.c
+++ b/hw/smbios/smbios.c
@@ -1097,7 +1097,7 @@ static void smbios_entry_point_setup(SmbiosEntryPointType ep_type)
}
}
-void smbios_get_tables(MachineState *ms,
+static bool smbios_get_tables_ep(MachineState *ms,
SmbiosEntryPointType ep_type,
const struct smbios_phys_mem_area *mem_array,
const unsigned int mem_array_size,
@@ -1106,6 +1106,7 @@ void smbios_get_tables(MachineState *ms,
Error **errp)
{
unsigned i, dimm_cnt, offset;
+ ERRP_GUARD();
assert(ep_type == SMBIOS_ENTRY_POINT_TYPE_32 ||
ep_type == SMBIOS_ENTRY_POINT_TYPE_64);
@@ -1192,11 +1193,56 @@ void smbios_get_tables(MachineState *ms,
abort();
}
- return;
+ return true;
err_exit:
g_free(smbios_tables);
smbios_tables = NULL;
- return;
+ return false;
+}
+
+void smbios_get_tables(MachineState *ms,
+ SmbiosEntryPointType ep_type,
+ const struct smbios_phys_mem_area *mem_array,
+ const unsigned int mem_array_size,
+ uint8_t **tables, size_t *tables_len,
+ uint8_t **anchor, size_t *anchor_len,
+ Error **errp)
+{
+ Error *local_err = NULL;
+ bool is_valid;
+ ERRP_GUARD();
+
+ switch (ep_type) {
+ case SMBIOS_ENTRY_POINT_TYPE_AUTO:
+ case SMBIOS_ENTRY_POINT_TYPE_32:
+ is_valid = smbios_get_tables_ep(ms, SMBIOS_ENTRY_POINT_TYPE_32,
+ mem_array, mem_array_size,
+ tables, tables_len,
+ anchor, anchor_len,
+ &local_err);
+ if (is_valid || ep_type != SMBIOS_ENTRY_POINT_TYPE_AUTO) {
+ break;
+ }
+ /*
+ * fall through in case AUTO endpoint is selected and
+ * SMBIOS 2.x tables can't be generated, to try if SMBIOS 3.x
+ * tables would work
+ */
+ case SMBIOS_ENTRY_POINT_TYPE_64:
+ error_free(local_err);
+ local_err = NULL;
+ is_valid = smbios_get_tables_ep(ms, SMBIOS_ENTRY_POINT_TYPE_64,
+ mem_array, mem_array_size,
+ tables, tables_len,
+ anchor, anchor_len,
+ &local_err);
+ break;
+ default:
+ abort();
+ }
+ if (!is_valid) {
+ error_propagate(errp, local_err);
+ }
}
static void save_opt(const char **dest, QemuOpts *opts, const char *name)
--
2.39.3

330
kvm-smbios-rename-expose-structures-bitmaps-used-by-both.patch
View File

@ -1,330 +0,0 @@
From 36b0256e27f9d5268c5413891b4a7322819ae9db Mon Sep 17 00:00:00 2001
From: Igor Mammedov <imammedo@redhat.com>
Date: Mon, 4 Mar 2024 15:56:19 +0100
Subject: [PATCH 12/20] smbios: rename/expose structures/bitmaps used by both
legacy and modern code
RH-Author: Igor Mammedov <imammedo@redhat.com>
RH-MergeRequest: 230: Workaround Windows failing to find 64bit SMBIOS entry point with SeaBIOS
RH-Jira: RHEL-21705
RH-Acked-by: MST <mst@redhat.com>
RH-Acked-by: Ani Sinha <None>
RH-Commit: [10/18] 59fe438d5b7f6e584a6bb02597e4d4724fe2cece
JIRA: https://issues.redhat.com/browse/RHEL-21705
As a preparation to move legacy handling into a separate file,
add prefix 'smbios_' to type0/type1/have_binfile_bitmap/have_fields_bitmap
and expose them in smbios.h so that they can be reused in
legacy and modern code.
Doing it as a separate patch to avoid rename cluttering follow-up
patch which will move legacy code into a separate file.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Ani Sinha <anisinha@redhat.com>
Conflicts: hw/smbios/smbios.c
due to setting downstream type1.family/type1.sku defaults
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
---
hw/smbios/smbios.c | 117 ++++++++++++++++-------------------
include/hw/firmware/smbios.h | 16 +++++
2 files changed, 71 insertions(+), 62 deletions(-)
diff --git a/hw/smbios/smbios.c b/hw/smbios/smbios.c
index c48a290478..eb9927335d 100644
--- a/hw/smbios/smbios.c
+++ b/hw/smbios/smbios.c
@@ -81,19 +81,11 @@ static int smbios_type4_count = 0;
static bool smbios_have_defaults;
static uint32_t smbios_cpuid_version, smbios_cpuid_features;
-static DECLARE_BITMAP(have_binfile_bitmap, SMBIOS_MAX_TYPE+1);
-static DECLARE_BITMAP(have_fields_bitmap, SMBIOS_MAX_TYPE+1);
+DECLARE_BITMAP(smbios_have_binfile_bitmap, SMBIOS_MAX_TYPE + 1);
+DECLARE_BITMAP(smbios_have_fields_bitmap, SMBIOS_MAX_TYPE + 1);
-static struct {
- const char *vendor, *version, *date;
- bool have_major_minor, uefi;
- uint8_t major, minor;
-} type0;
-
-static struct {
- const char *manufacturer, *product, *version, *serial, *sku, *family;
- /* uuid is in qemu_uuid */
-} type1;
+smbios_type0_t smbios_type0;
+smbios_type1_t smbios_type1;
static struct {
const char *manufacturer, *product, *version, *serial, *asset, *location;
@@ -584,36 +576,36 @@ static void smbios_maybe_add_str(int type, int offset, const char *data)
static void smbios_build_type_0_fields(void)
{
smbios_maybe_add_str(0, offsetof(struct smbios_type_0, vendor_str),
- type0.vendor);
+ smbios_type0.vendor);
smbios_maybe_add_str(0, offsetof(struct smbios_type_0, bios_version_str),
- type0.version);
+ smbios_type0.version);
smbios_maybe_add_str(0, offsetof(struct smbios_type_0,
bios_release_date_str),
- type0.date);
- if (type0.have_major_minor) {
+ smbios_type0.date);
+ if (smbios_type0.have_major_minor) {
smbios_add_field(0, offsetof(struct smbios_type_0,
system_bios_major_release),
- &type0.major, 1);
+ &smbios_type0.major, 1);
smbios_add_field(0, offsetof(struct smbios_type_0,
system_bios_minor_release),
- &type0.minor, 1);
+ &smbios_type0.minor, 1);
}
}
static void smbios_build_type_1_fields(void)
{
smbios_maybe_add_str(1, offsetof(struct smbios_type_1, manufacturer_str),
- type1.manufacturer);
+ smbios_type1.manufacturer);
smbios_maybe_add_str(1, offsetof(struct smbios_type_1, product_name_str),
- type1.product);
+ smbios_type1.product);
smbios_maybe_add_str(1, offsetof(struct smbios_type_1, version_str),
- type1.version);
+ smbios_type1.version);
smbios_maybe_add_str(1, offsetof(struct smbios_type_1, serial_number_str),
- type1.serial);
+ smbios_type1.serial);
smbios_maybe_add_str(1, offsetof(struct smbios_type_1, sku_number_str),
- type1.sku);
+ smbios_type1.sku);
smbios_maybe_add_str(1, offsetof(struct smbios_type_1, family_str),
- type1.family);
+ smbios_type1.family);
if (qemu_uuid_set) {
/* We don't encode the UUID in the "wire format" here because this
* function is for legacy mode and needs to keep the guest ABI, and
@@ -631,14 +623,14 @@ uint8_t *smbios_get_table_legacy(size_t *length)
size_t usr_offset;
/* also complain if fields were given for types > 1 */
- if (find_next_bit(have_fields_bitmap,
+ if (find_next_bit(smbios_have_fields_bitmap,
SMBIOS_MAX_TYPE + 1, 2) < SMBIOS_MAX_TYPE + 1) {
error_report("can't process fields for smbios "
"types > 1 on machine versions < 2.1!");
exit(1);
}
- if (test_bit(4, have_binfile_bitmap)) {
+ if (test_bit(4, smbios_have_binfile_bitmap)) {
error_report("can't process table for smbios "
"type 4 on machine versions < 2.1!");
exit(1);
@@ -679,10 +671,10 @@ uint8_t *smbios_get_table_legacy(size_t *length)
bool smbios_skip_table(uint8_t type, bool required_table)
{
- if (test_bit(type, have_binfile_bitmap)) {
+ if (test_bit(type, smbios_have_binfile_bitmap)) {
return true; /* user provided their own binary blob(s) */
}
- if (test_bit(type, have_fields_bitmap)) {
+ if (test_bit(type, smbios_have_fields_bitmap)) {
return false; /* user provided fields via command line */
}
if (smbios_have_defaults && required_table) {
@@ -710,25 +702,25 @@ static void smbios_build_type_0_table(void)
{
SMBIOS_BUILD_TABLE_PRE(0, T0_BASE, false); /* optional, leave up to BIOS */
- SMBIOS_TABLE_SET_STR(0, vendor_str, type0.vendor);
- SMBIOS_TABLE_SET_STR(0, bios_version_str, type0.version);
+ SMBIOS_TABLE_SET_STR(0, vendor_str, smbios_type0.vendor);
+ SMBIOS_TABLE_SET_STR(0, bios_version_str, smbios_type0.version);
t->bios_starting_address_segment = cpu_to_le16(0xE800); /* from SeaBIOS */
- SMBIOS_TABLE_SET_STR(0, bios_release_date_str, type0.date);
+ SMBIOS_TABLE_SET_STR(0, bios_release_date_str, smbios_type0.date);
t->bios_rom_size = 0; /* hardcoded in SeaBIOS with FIXME comment */
t->bios_characteristics = cpu_to_le64(0x08); /* Not supported */
t->bios_characteristics_extension_bytes[0] = 0;
t->bios_characteristics_extension_bytes[1] = 0x14; /* TCD/SVVP | VM */
- if (type0.uefi) {
+ if (smbios_type0.uefi) {
t->bios_characteristics_extension_bytes[1] |= 0x08; /* |= UEFI */
}
- if (type0.have_major_minor) {
- t->system_bios_major_release = type0.major;
- t->system_bios_minor_release = type0.minor;
+ if (smbios_type0.have_major_minor) {
+ t->system_bios_major_release = smbios_type0.major;
+ t->system_bios_minor_release = smbios_type0.minor;
} else {
t->system_bios_major_release = 0;
t->system_bios_minor_release = 0;
@@ -758,18 +750,18 @@ static void smbios_build_type_1_table(void)
{
SMBIOS_BUILD_TABLE_PRE(1, T1_BASE, true); /* required */
- SMBIOS_TABLE_SET_STR(1, manufacturer_str, type1.manufacturer);
- SMBIOS_TABLE_SET_STR(1, product_name_str, type1.product);
- SMBIOS_TABLE_SET_STR(1, version_str, type1.version);
- SMBIOS_TABLE_SET_STR(1, serial_number_str, type1.serial);
+ SMBIOS_TABLE_SET_STR(1, manufacturer_str, smbios_type1.manufacturer);
+ SMBIOS_TABLE_SET_STR(1, product_name_str, smbios_type1.product);
+ SMBIOS_TABLE_SET_STR(1, version_str, smbios_type1.version);
+ SMBIOS_TABLE_SET_STR(1, serial_number_str, smbios_type1.serial);
if (qemu_uuid_set) {
smbios_encode_uuid(&t->uuid, &qemu_uuid);
} else {
memset(&t->uuid, 0, 16);
}
t->wake_up_type = 0x06; /* power switch */
- SMBIOS_TABLE_SET_STR(1, sku_number_str, type1.sku);
- SMBIOS_TABLE_SET_STR(1, family_str, type1.family);
+ SMBIOS_TABLE_SET_STR(1, sku_number_str, smbios_type1.sku);
+ SMBIOS_TABLE_SET_STR(1, family_str, smbios_type1.family);
SMBIOS_BUILD_TABLE_POST;
}
@@ -1184,12 +1176,12 @@ void smbios_set_defaults(const char *manufacturer, const char *product,
*
* We get 'System Manufacturer' and 'Baseboard Manufacturer'
*/
- SMBIOS_SET_DEFAULT(type1.manufacturer, manufacturer);
- SMBIOS_SET_DEFAULT(type1.product, product);
- SMBIOS_SET_DEFAULT(type1.version, version);
- SMBIOS_SET_DEFAULT(type1.family, "Red Hat Enterprise Linux");
+ SMBIOS_SET_DEFAULT(smbios_type1.manufacturer, manufacturer);
+ SMBIOS_SET_DEFAULT(smbios_type1.product, product);
+ SMBIOS_SET_DEFAULT(smbios_type1.version, version);
+ SMBIOS_SET_DEFAULT(smbios_type1.family, "Red Hat Enterprise Linux");
if (stream_version != NULL) {
- SMBIOS_SET_DEFAULT(type1.sku, stream_version);
+ SMBIOS_SET_DEFAULT(smbios_type1.sku, stream_version);
}
SMBIOS_SET_DEFAULT(type2.manufacturer, manufacturer);
if (stream_product != NULL) {
@@ -1468,13 +1460,13 @@ void smbios_entry_add(QemuOpts *opts, Error **errp)
}
if (header->type <= SMBIOS_MAX_TYPE) {
- if (test_bit(header->type, have_fields_bitmap)) {
+ if (test_bit(header->type, smbios_have_fields_bitmap)) {
error_setg(errp,
"can't load type %d struct, fields already specified!",
header->type);
return;
}
- set_bit(header->type, have_binfile_bitmap);
+ set_bit(header->type, smbios_have_binfile_bitmap);
}
if (header->type == 4) {
@@ -1505,41 +1497,42 @@ void smbios_entry_add(QemuOpts *opts, Error **errp)
return;
}
- if (test_bit(type, have_binfile_bitmap)) {
+ if (test_bit(type, smbios_have_binfile_bitmap)) {
error_setg(errp, "can't add fields, binary file already loaded!");
return;
}
- set_bit(type, have_fields_bitmap);
+ set_bit(type, smbios_have_fields_bitmap);
switch (type) {
case 0:
if (!qemu_opts_validate(opts, qemu_smbios_type0_opts, errp)) {
return;
}
- save_opt(&type0.vendor, opts, "vendor");
- save_opt(&type0.version, opts, "version");
- save_opt(&type0.date, opts, "date");
- type0.uefi = qemu_opt_get_bool(opts, "uefi", false);
+ save_opt(&smbios_type0.vendor, opts, "vendor");
+ save_opt(&smbios_type0.version, opts, "version");
+ save_opt(&smbios_type0.date, opts, "date");
+ smbios_type0.uefi = qemu_opt_get_bool(opts, "uefi", false);
val = qemu_opt_get(opts, "release");
if (val) {
- if (sscanf(val, "%hhu.%hhu", &type0.major, &type0.minor) != 2) {
+ if (sscanf(val, "%hhu.%hhu", &smbios_type0.major,
+ &smbios_type0.minor) != 2) {
error_setg(errp, "Invalid release");
return;
}
- type0.have_major_minor = true;
+ smbios_type0.have_major_minor = true;
}
return;
case 1:
if (!qemu_opts_validate(opts, qemu_smbios_type1_opts, errp)) {
return;
}
- save_opt(&type1.manufacturer, opts, "manufacturer");
- save_opt(&type1.product, opts, "product");
- save_opt(&type1.version, opts, "version");
- save_opt(&type1.serial, opts, "serial");
- save_opt(&type1.sku, opts, "sku");
- save_opt(&type1.family, opts, "family");
+ save_opt(&smbios_type1.manufacturer, opts, "manufacturer");
+ save_opt(&smbios_type1.product, opts, "product");
+ save_opt(&smbios_type1.version, opts, "version");
+ save_opt(&smbios_type1.serial, opts, "serial");
+ save_opt(&smbios_type1.sku, opts, "sku");
+ save_opt(&smbios_type1.family, opts, "family");
val = qemu_opt_get(opts, "uuid");
if (val) {
diff --git a/include/hw/firmware/smbios.h b/include/hw/firmware/smbios.h
index d55018e5e3..333de0d5fc 100644
--- a/include/hw/firmware/smbios.h
+++ b/include/hw/firmware/smbios.h
@@ -2,6 +2,7 @@
#define QEMU_SMBIOS_H
#include "qapi/qapi-types-machine.h"
+#include "qemu/bitmap.h"
/*
* SMBIOS Support
@@ -16,8 +17,23 @@
*
*/
+typedef struct {
+ const char *vendor, *version, *date;
+ bool have_major_minor, uefi;
+ uint8_t major, minor;
+} smbios_type0_t;
+extern smbios_type0_t smbios_type0;
+
+typedef struct {
+ const char *manufacturer, *product, *version, *serial, *sku, *family;
+ /* uuid is in qemu_uuid */
+} smbios_type1_t;
+extern smbios_type1_t smbios_type1;
#define SMBIOS_MAX_TYPE 127
+extern DECLARE_BITMAP(smbios_have_binfile_bitmap, SMBIOS_MAX_TYPE + 1);
+extern DECLARE_BITMAP(smbios_have_fields_bitmap, SMBIOS_MAX_TYPE + 1);
+
#define offsetofend(TYPE, MEMBER) \
(offsetof(TYPE, MEMBER) + sizeof_field(TYPE, MEMBER))
--
2.39.3

190
kvm-string-output-visitor-Fix-pseudo-struct-handling.patch
View File

@ -1,190 +0,0 @@
From c5f9e92cd49a2171a5b0223cafd7fab3f45edb82 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Tue, 9 Jan 2024 19:17:17 +0100
Subject: [PATCH 06/22] string-output-visitor: Fix (pseudo) struct handling
RH-Author: Stefan Hajnoczi <stefanha@redhat.com>
RH-MergeRequest: 219: virtio-blk: add iothread-vq-mapping parameter
RH-Jira: RHEL-17369 RHEL-20764 RHEL-7356
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Commit: [2/17] 84e226f161680dd61b6635e213203d062c1aa556 (stefanha/centos-stream-qemu-kvm)
Commit ff32bb53 tried to get minimal struct support into the string
output visitor by just making it return "<omitted>". Unfortunately, it
forgot that the caller will still make more visitor calls for the
content of the struct.
If the struct is contained in a list, such as IOThreadVirtQueueMapping,
in the better case its fields show up as separate list entries. In the
worse case, it contains another list, and the string output visitor
doesn't support nested lists and asserts that this doesn't happen. So as
soon as the optional "vqs" field in IOThreadVirtQueueMapping is
specified, we get a crash.
This can be reproduced with the following command line:
echo "info qtree" | ./qemu-system-x86_64 \
-object iothread,id=t0 \
-blockdev null-co,node-name=disk \
-device '{"driver": "virtio-blk-pci", "drive": "disk",
"iothread-vq-mapping": [{"iothread": "t0", "vqs": [0]}]}' \
-monitor stdio
Fix the problem by counting the nesting level of structs and ignoring
any visitor calls for values (apart from start/end_struct) while we're
not on the top level.
Lists nested directly within lists remain unimplemented, as we don't
currently have a use case for them.
Fixes: ff32bb53476539d352653f4ed56372dced73a388
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/2069
Reported-by: Aihua Liang <aliang@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-ID: <20240109181717.42493-1-kwolf@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 014b99a8e41c8cd1e895137654b44dec5430122c)
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
qapi/string-output-visitor.c | 46 ++++++++++++++++++++++++++++++++++++
1 file changed, 46 insertions(+)
diff --git a/qapi/string-output-visitor.c b/qapi/string-output-visitor.c
index f0c1dea89e..5115536b15 100644
--- a/qapi/string-output-visitor.c
+++ b/qapi/string-output-visitor.c
@@ -65,6 +65,7 @@ struct StringOutputVisitor
} range_start, range_end;
GList *ranges;
void *list; /* Only needed for sanity checking the caller */
+ unsigned int struct_nesting;
};
static StringOutputVisitor *to_sov(Visitor *v)
@@ -144,6 +145,10 @@ static bool print_type_int64(Visitor *v, const char *name, int64_t *obj,
StringOutputVisitor *sov = to_sov(v);
GList *l;
+ if (sov->struct_nesting) {
+ return true;
+ }
+
switch (sov->list_mode) {
case LM_NONE:
string_output_append(sov, *obj);
@@ -231,6 +236,10 @@ static bool print_type_size(Visitor *v, const char *name, uint64_t *obj,
uint64_t val;
char *out, *psize;
+ if (sov->struct_nesting) {
+ return true;
+ }
+
if (!sov->human) {
out = g_strdup_printf("%"PRIu64, *obj);
string_output_set(sov, out);
@@ -250,6 +259,11 @@ static bool print_type_bool(Visitor *v, const char *name, bool *obj,
Error **errp)
{
StringOutputVisitor *sov = to_sov(v);
+
+ if (sov->struct_nesting) {
+ return true;
+ }
+
string_output_set(sov, g_strdup(*obj ? "true" : "false"));
return true;
}
@@ -260,6 +274,10 @@ static bool print_type_str(Visitor *v, const char *name, char **obj,
StringOutputVisitor *sov = to_sov(v);
char *out;
+ if (sov->struct_nesting) {
+ return true;
+ }
+
if (sov->human) {
out = *obj ? g_strdup_printf("\"%s\"", *obj) : g_strdup("<null>");
} else {
@@ -273,6 +291,11 @@ static bool print_type_number(Visitor *v, const char *name, double *obj,
Error **errp)
{
StringOutputVisitor *sov = to_sov(v);
+
+ if (sov->struct_nesting) {
+ return true;
+ }
+
string_output_set(sov, g_strdup_printf("%.17g", *obj));
return true;
}
@@ -283,6 +306,10 @@ static bool print_type_null(Visitor *v, const char *name, QNull **obj,
StringOutputVisitor *sov = to_sov(v);
char *out;
+ if (sov->struct_nesting) {
+ return true;
+ }
+
if (sov->human) {
out = g_strdup("<null>");
} else {
@@ -295,6 +322,9 @@ static bool print_type_null(Visitor *v, const char *name, QNull **obj,
static bool start_struct(Visitor *v, const char *name, void **obj,
size_t size, Error **errp)
{
+ StringOutputVisitor *sov = to_sov(v);
+
+ sov->struct_nesting++;
return true;
}
@@ -302,6 +332,10 @@ static void end_struct(Visitor *v, void **obj)
{
StringOutputVisitor *sov = to_sov(v);
+ if (--sov->struct_nesting) {
+ return;
+ }
+
/* TODO actually print struct fields */
string_output_set(sov, g_strdup("<omitted>"));
}
@@ -312,6 +346,10 @@ start_list(Visitor *v, const char *name, GenericList **list, size_t size,
{
StringOutputVisitor *sov = to_sov(v);
+ if (sov->struct_nesting) {
+ return true;
+ }
+
/* we can't traverse a list in a list */
assert(sov->list_mode == LM_NONE);
/* We don't support visits without a list */
@@ -329,6 +367,10 @@ static GenericList *next_list(Visitor *v, GenericList *tail, size_t size)
StringOutputVisitor *sov = to_sov(v);
GenericList *ret = tail->next;
+ if (sov->struct_nesting) {
+ return ret;
+ }
+
if (ret && !ret->next) {
sov->list_mode = LM_END;
}
@@ -339,6 +381,10 @@ static void end_list(Visitor *v, void **obj)
{
StringOutputVisitor *sov = to_sov(v);
+ if (sov->struct_nesting) {
+ return;
+ }
+
assert(sov->list == obj);
assert(sov->list_mode == LM_STARTED ||
sov->list_mode == LM_END ||
--
2.39.3

90
kvm-string-output-visitor-show-structs-as-omitted.patch
View File

@ -1,90 +0,0 @@
From fb2069be402ec1322834c555714f0e993778cc9d Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Tue, 12 Dec 2023 08:49:34 -0500
Subject: [PATCH 05/22] string-output-visitor: show structs as "<omitted>"
RH-Author: Stefan Hajnoczi <stefanha@redhat.com>
RH-MergeRequest: 219: virtio-blk: add iothread-vq-mapping parameter
RH-Jira: RHEL-17369 RHEL-20764 RHEL-7356
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Commit: [1/17] 0c08e8237d28fbdbdbc7576d4c17d2eeeb413c2a (stefanha/centos-stream-qemu-kvm)
StringOutputVisitor crashes when it visits a struct because
->start_struct() is NULL.
Show "<omitted>" instead of crashing. This is necessary because the
virtio-blk-pci iothread-vq-mapping parameter that I'd like to introduce
soon is a list of IOThreadMapping structs.
This patch is a quick fix to solve the crash, but the long-term solution
is replacing StringOutputVisitor with something that can handle the full
gamut of values in QEMU.
Cc: Markus Armbruster <armbru@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-ID: <20231212134934.500289-1-stefanha@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit ff32bb53476539d352653f4ed56372dced73a388)
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
include/qapi/string-output-visitor.h | 6 +++---
qapi/string-output-visitor.c | 16 ++++++++++++++++
2 files changed, 19 insertions(+), 3 deletions(-)
diff --git a/include/qapi/string-output-visitor.h b/include/qapi/string-output-visitor.h
index 268dfe9986..b1ee473b30 100644
--- a/include/qapi/string-output-visitor.h
+++ b/include/qapi/string-output-visitor.h
@@ -26,9 +26,9 @@ typedef struct StringOutputVisitor StringOutputVisitor;
* If everything else succeeds, pass @result to visit_complete() to
* collect the result of the visit.
*
- * The string output visitor does not implement support for visiting
- * QAPI structs, alternates, null, or arbitrary QTypes. It also
- * requires a non-null list argument to visit_start_list().
+ * The string output visitor does not implement support for alternates, null,
+ * or arbitrary QTypes. Struct fields are not shown. It also requires a
+ * non-null list argument to visit_start_list().
*/
Visitor *string_output_visitor_new(bool human, char **result);
diff --git a/qapi/string-output-visitor.c b/qapi/string-output-visitor.c
index c0cb72dbe4..f0c1dea89e 100644
--- a/qapi/string-output-visitor.c
+++ b/qapi/string-output-visitor.c
@@ -292,6 +292,20 @@ static bool print_type_null(Visitor *v, const char *name, QNull **obj,
return true;
}
+static bool start_struct(Visitor *v, const char *name, void **obj,
+ size_t size, Error **errp)
+{
+ return true;
+}
+
+static void end_struct(Visitor *v, void **obj)
+{
+ StringOutputVisitor *sov = to_sov(v);
+
+ /* TODO actually print struct fields */
+ string_output_set(sov, g_strdup("<omitted>"));
+}
+
static bool
start_list(Visitor *v, const char *name, GenericList **list, size_t size,
Error **errp)
@@ -379,6 +393,8 @@ Visitor *string_output_visitor_new(bool human, char **result)
v->visitor.type_str = print_type_str;
v->visitor.type_number = print_type_number;
v->visitor.type_null = print_type_null;
+ v->visitor.start_struct = start_struct;
+ v->visitor.end_struct = end_struct;
v->visitor.start_list = start_list;
v->visitor.next_list = next_list;
v->visitor.end_list = end_list;
--
2.39.3

205
kvm-target-s390x-kvm-pv-Provide-some-more-useful-informa.patch
View File

@ -1,205 +0,0 @@
From cc8d794932e26df7c7f3c8cc0c1f42da8d52f12b Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Mon, 15 Jan 2024 10:26:52 +0100
Subject: [PATCH 069/101] target/s390x/kvm/pv: Provide some more useful
information if decryption fails
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Thomas Huth <thuth@redhat.com>
RH-MergeRequest: 213: s390x: Provide some more useful information if decryption of a PV image fails
RH-Jira: RHEL-18212
RH-Acked-by: Cédric Le Goater <clg@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Commit: [1/1] 4ffb61869f7df33e23d3e0ebf8c29e386e3f6cbc (thuth/qemu-kvm-cs9)
JIRA: https://issues.redhat.com/browse/RHEL-18212
commit 7af51621b16ae86646cc2dc9dee30de8176ff761
Author: Thomas Huth <thuth@redhat.com>
Date: Wed Jan 10 15:29:16 2024 +0100
target/s390x/kvm/pv: Provide some more useful information if decryption fails
It's a common scenario to copy guest images from one host to another
to run the guest on the other machine. This (of course) does not work
with "secure execution" guests since they are encrypted with one certain
host key. However, if you still (accidentally) do it, you only get a
very user-unfriendly error message that looks like this:
qemu-system-s390x: KVM PV command 2 (KVM_PV_SET_SEC_PARMS) failed:
header rc 108 rrc 5 IOCTL rc: -22
Let's provide at least a somewhat nicer hint to the users so that they
are able to figure out what might have gone wrong.
Buglink: https://issues.redhat.com/browse/RHEL-18212
Message-ID: <20240110142916.850605-1-thuth@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Reviewed-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
---
hw/s390x/ipl.c | 5 ++---
hw/s390x/ipl.h | 2 +-
hw/s390x/s390-virtio-ccw.c | 5 ++++-
target/s390x/kvm/pv.c | 25 ++++++++++++++++++++-----
target/s390x/kvm/pv.h | 5 +++--
5 files changed, 30 insertions(+), 12 deletions(-)
diff --git a/hw/s390x/ipl.c b/hw/s390x/ipl.c
index 515dcf51b5..b23a6a0ef3 100644
--- a/hw/s390x/ipl.c
+++ b/hw/s390x/ipl.c
@@ -703,7 +703,7 @@ static void s390_ipl_prepare_qipl(S390CPU *cpu)
cpu_physical_memory_unmap(addr, len, 1, len);
}
-int s390_ipl_prepare_pv_header(void)
+int s390_ipl_prepare_pv_header(Error **errp)
{
IplParameterBlock *ipib = s390_ipl_get_iplb_pv();
IPLBlockPV *ipib_pv = &ipib->pv;
@@ -712,8 +712,7 @@ int s390_ipl_prepare_pv_header(void)
cpu_physical_memory_read(ipib_pv->pv_header_addr, hdr,
ipib_pv->pv_header_len);
- rc = s390_pv_set_sec_parms((uintptr_t)hdr,
- ipib_pv->pv_header_len);
+ rc = s390_pv_set_sec_parms((uintptr_t)hdr, ipib_pv->pv_header_len, errp);
g_free(hdr);
return rc;
}
diff --git a/hw/s390x/ipl.h b/hw/s390x/ipl.h
index 7fc86e7905..57cd125769 100644
--- a/hw/s390x/ipl.h
+++ b/hw/s390x/ipl.h
@@ -107,7 +107,7 @@ typedef union IplParameterBlock IplParameterBlock;
int s390_ipl_set_loadparm(uint8_t *loadparm);
void s390_ipl_update_diag308(IplParameterBlock *iplb);
-int s390_ipl_prepare_pv_header(void);
+int s390_ipl_prepare_pv_header(Error **errp);
int s390_ipl_pv_unpack(void);
void s390_ipl_prepare_cpu(S390CPU *cpu);
IplParameterBlock *s390_ipl_get_iplb(void);
diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
index 984891b82a..e26ce26f5a 100644
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -391,7 +391,7 @@ static int s390_machine_protect(S390CcwMachineState *ms)
}
/* Set SE header and unpack */
- rc = s390_ipl_prepare_pv_header();
+ rc = s390_ipl_prepare_pv_header(&local_err);
if (rc) {
goto out_err;
}
@@ -410,6 +410,9 @@ static int s390_machine_protect(S390CcwMachineState *ms)
return rc;
out_err:
+ if (local_err) {
+ error_report_err(local_err);
+ }
s390_machine_unprotect(ms);
return rc;
}
diff --git a/target/s390x/kvm/pv.c b/target/s390x/kvm/pv.c
index 6a69be7e5c..7ca7faec73 100644
--- a/target/s390x/kvm/pv.c
+++ b/target/s390x/kvm/pv.c
@@ -29,7 +29,8 @@ static bool info_valid;
static struct kvm_s390_pv_info_vm info_vm;
static struct kvm_s390_pv_info_dump info_dump;
-static int __s390_pv_cmd(uint32_t cmd, const char *cmdname, void *data)
+static int __s390_pv_cmd(uint32_t cmd, const char *cmdname, void *data,
+ int *pvrc)
{
struct kvm_pv_cmd pv_cmd = {
.cmd = cmd,
@@ -46,6 +47,9 @@ static int __s390_pv_cmd(uint32_t cmd, const char *cmdname, void *data)
"IOCTL rc: %d", cmd, cmdname, pv_cmd.rc, pv_cmd.rrc,
rc);
}
+ if (pvrc) {
+ *pvrc = pv_cmd.rc;
+ }
return rc;
}
@@ -53,12 +57,13 @@ static int __s390_pv_cmd(uint32_t cmd, const char *cmdname, void *data)
* This macro lets us pass the command as a string to the function so
* we can print it on an error.
*/
-#define s390_pv_cmd(cmd, data) __s390_pv_cmd(cmd, #cmd, data)
+#define s390_pv_cmd(cmd, data) __s390_pv_cmd(cmd, #cmd, data, NULL)
+#define s390_pv_cmd_pvrc(cmd, data, pvrc) __s390_pv_cmd(cmd, #cmd, data, pvrc)
#define s390_pv_cmd_exit(cmd, data) \
{ \
int rc; \
\
- rc = __s390_pv_cmd(cmd, #cmd, data);\
+ rc = __s390_pv_cmd(cmd, #cmd, data, NULL); \
if (rc) { \
exit(1); \
} \
@@ -142,14 +147,24 @@ bool s390_pv_vm_try_disable_async(S390CcwMachineState *ms)
return true;
}
-int s390_pv_set_sec_parms(uint64_t origin, uint64_t length)
+int s390_pv_set_sec_parms(uint64_t origin, uint64_t length, Error **errp)
{
+ int ret, pvrc;
struct kvm_s390_pv_sec_parm args = {
.origin = origin,
.length = length,
};
- return s390_pv_cmd(KVM_PV_SET_SEC_PARMS, &args);
+ ret = s390_pv_cmd_pvrc(KVM_PV_SET_SEC_PARMS, &args, &pvrc);
+ if (ret) {
+ error_setg(errp, "Failed to set secure execution parameters");
+ if (pvrc == 0x108) {
+ error_append_hint(errp, "Please check whether the image is "
+ "correctly encrypted for this host\n");
+ }
+ }
+
+ return ret;
}
/*
diff --git a/target/s390x/kvm/pv.h b/target/s390x/kvm/pv.h
index 7b935e2246..5877d28ff1 100644
--- a/target/s390x/kvm/pv.h
+++ b/target/s390x/kvm/pv.h
@@ -42,7 +42,7 @@ int s390_pv_query_info(void);
int s390_pv_vm_enable(void);
void s390_pv_vm_disable(void);
bool s390_pv_vm_try_disable_async(S390CcwMachineState *ms);
-int s390_pv_set_sec_parms(uint64_t origin, uint64_t length);
+int s390_pv_set_sec_parms(uint64_t origin, uint64_t length, Error **errp);
int s390_pv_unpack(uint64_t addr, uint64_t size, uint64_t tweak);
void s390_pv_prep_reset(void);
int s390_pv_verify(void);
@@ -62,7 +62,8 @@ static inline int s390_pv_query_info(void) { return 0; }
static inline int s390_pv_vm_enable(void) { return 0; }
static inline void s390_pv_vm_disable(void) {}
static inline bool s390_pv_vm_try_disable_async(S390CcwMachineState *ms) { return false; }
-static inline int s390_pv_set_sec_parms(uint64_t origin, uint64_t length) { return 0; }
+static inline int s390_pv_set_sec_parms(uint64_t origin, uint64_t length,
+ Error **errp) { return 0; }
static inline int s390_pv_unpack(uint64_t addr, uint64_t size, uint64_t tweak) { return 0; }
static inline void s390_pv_prep_reset(void) {}
static inline int s390_pv_verify(void) { return 0; }
--
2.39.3

125
kvm-tests-remove-aio_context_acquire-tests.patch
View File

@ -1,125 +0,0 @@
From 420bf75353286324822c3bbca3b52a7a56ed668c Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Tue, 5 Dec 2023 13:20:00 -0500
Subject: [PATCH 083/101] tests: remove aio_context_acquire() tests
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 214: Remove AioContext lock
RH-Jira: RHEL-15965
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Commit: [14/26] f6421037c1523bc957f3be0f4ad05571ae012dba (kmwolf/centos-qemu-kvm)
The aio_context_acquire() API is being removed. Drop the test case that
calls the API.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Message-ID: <20231205182011.1976568-4-stefanha@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
tests/unit/test-aio.c | 67 +------------------------------------------
1 file changed, 1 insertion(+), 66 deletions(-)
diff --git a/tests/unit/test-aio.c b/tests/unit/test-aio.c
index 337b6e4ea7..e77d86be87 100644
--- a/tests/unit/test-aio.c
+++ b/tests/unit/test-aio.c
@@ -100,76 +100,12 @@ static void event_ready_cb(EventNotifier *e)
/* Tests using aio_*. */
-typedef struct {
- QemuMutex start_lock;
- EventNotifier notifier;
- bool thread_acquired;
-} AcquireTestData;
-
-static void *test_acquire_thread(void *opaque)
-{
- AcquireTestData *data = opaque;
-
- /* Wait for other thread to let us start */
- qemu_mutex_lock(&data->start_lock);
- qemu_mutex_unlock(&data->start_lock);
-
- /* event_notifier_set might be called either before or after
- * the main thread's call to poll(). The test case's outcome
- * should be the same in either case.
- */
- event_notifier_set(&data->notifier);
- aio_context_acquire(ctx);
- aio_context_release(ctx);
-
- data->thread_acquired = true; /* success, we got here */
-
- return NULL;
-}
-
static void set_event_notifier(AioContext *nctx, EventNotifier *notifier,
EventNotifierHandler *handler)
{
aio_set_event_notifier(nctx, notifier, handler, NULL, NULL);
}
-static void dummy_notifier_read(EventNotifier *n)
-{
- event_notifier_test_and_clear(n);
-}
-
-static void test_acquire(void)
-{
- QemuThread thread;
- AcquireTestData data;
-
- /* Dummy event notifier ensures aio_poll() will block */
- event_notifier_init(&data.notifier, false);
- set_event_notifier(ctx, &data.notifier, dummy_notifier_read);
- g_assert(!aio_poll(ctx, false)); /* consume aio_notify() */
-
- qemu_mutex_init(&data.start_lock);
- qemu_mutex_lock(&data.start_lock);
- data.thread_acquired = false;
-
- qemu_thread_create(&thread, "test_acquire_thread",
- test_acquire_thread,
- &data, QEMU_THREAD_JOINABLE);
-
- /* Block in aio_poll(), let other thread kick us and acquire context */
- aio_context_acquire(ctx);
- qemu_mutex_unlock(&data.start_lock); /* let the thread run */
- g_assert(aio_poll(ctx, true));
- g_assert(!data.thread_acquired);
- aio_context_release(ctx);
-
- qemu_thread_join(&thread);
- set_event_notifier(ctx, &data.notifier, NULL);
- event_notifier_cleanup(&data.notifier);
-
- g_assert(data.thread_acquired);
-}
-
static void test_bh_schedule(void)
{
BHTestData data = { .n = 0 };
@@ -879,7 +815,7 @@ static void test_worker_thread_co_enter(void)
qemu_thread_get_self(&this_thread);
co = qemu_coroutine_create(co_check_current_thread, &this_thread);
- qemu_thread_create(&worker_thread, "test_acquire_thread",
+ qemu_thread_create(&worker_thread, "test_aio_co_enter",
test_aio_co_enter,
co, QEMU_THREAD_JOINABLE);
@@ -899,7 +835,6 @@ int main(int argc, char **argv)
while (g_main_context_iteration(NULL, false));
g_test_init(&argc, &argv, NULL);
- g_test_add_func("/aio/acquire", test_acquire);
g_test_add_func("/aio/bh/schedule", test_bh_schedule);
g_test_add_func("/aio/bh/schedule10", test_bh_schedule10);
g_test_add_func("/aio/bh/cancel", test_bh_cancel);
--
2.39.3

46
kvm-tests-unit-Bump-test-replication-timeout-to-60-secon.patch
View File

@ -1,46 +0,0 @@
From bbe64d706b3cb8b10ecd22bd71cf76b21eea257f Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Thu, 25 Jan 2024 17:58:03 +0100
Subject: [PATCH 20/22] tests/unit: Bump test-replication timeout to 60 seconds
RH-Author: Stefan Hajnoczi <stefanha@redhat.com>
RH-MergeRequest: 219: virtio-blk: add iothread-vq-mapping parameter
RH-Jira: RHEL-17369 RHEL-20764 RHEL-7356
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Commit: [16/17] 200768aedee44d10aa8d199b92a9c17a9002fc3f (stefanha/centos-stream-qemu-kvm)
We're seeing timeouts for this test on CI runs (specifically for
ubuntu-20.04-s390x-all). It doesn't fail consistently, but even the
successful runs take about 27 or 28 seconds, which is not very far from
the 30 seconds timeout.
Bump the timeout a bit to make failure less likely even on this CI host.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-ID: <20240125165803.48373-1-kwolf@redhat.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 63b18312d14ac984acaf13c7c55d9baa2d61496e)
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
tests/unit/meson.build | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/tests/unit/meson.build b/tests/unit/meson.build
index a05d471090..28db6adea8 100644
--- a/tests/unit/meson.build
+++ b/tests/unit/meson.build
@@ -173,7 +173,8 @@ test_env.set('G_TEST_BUILDDIR', meson.current_build_dir())
slow_tests = {
'test-crypto-tlscredsx509': 45,
- 'test-crypto-tlssession': 45
+ 'test-crypto-tlssession': 45,
+ 'test-replication': 60,
}
foreach test_name, extra: tests
--
2.39.3

81
kvm-ui-clipboard-add-asserts-for-update-and-request.patch
View File

@ -1,81 +0,0 @@
From 6e4f68e9ba3fe75ca6f200f189f96bb402f0ee8e Mon Sep 17 00:00:00 2001
From: Fiona Ebner <f.ebner@proxmox.com>
Date: Wed, 24 Jan 2024 11:57:49 +0100
Subject: [PATCH 02/20] ui/clipboard: add asserts for update and request
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Jon Maloy <jmaloy@redhat.com>
RH-MergeRequest: 228: ui/clipboard: mark type as not available when there is no data
RH-Jira: RHEL-19629
RH-Acked-by: Marc-André Lureau <marcandre.lureau@redhat.com>
RH-Acked-by: Gerd Hoffmann <None>
RH-Commit: [2/2] 176b4b835fd8aa226f2fa93fd334b9384080cf21 (jmaloy/jmaloy-qemu-kvm-2)
JIRA: https://issues.redhat.com/browse/RHEL-19629
CVE: CVE-2023-6683
Upstream: Merged
ui/clipboard: add asserts for update and request
commit 9c416582611b7495bdddb4c5456c7acb64b78938
Author: Fiona Ebner <f.ebner@proxmox.com>
Date: Wed Jan 24 11:57:49 2024 +0100
ui/clipboard: add asserts for update and request
Should an issue like CVE-2023-6683 ever appear again in the future,
it will be more obvious which assumption was violated.
Suggested-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Message-ID: <20240124105749.204610-2-f.ebner@proxmox.com>
Signed-off-by: Jon Maloy <jmaloy@redhat.com>
---
ui/clipboard.c | 14 ++++++++++++++
1 file changed, 14 insertions(+)
diff --git a/ui/clipboard.c b/ui/clipboard.c
index b3f6fa3c9e..4264884a6c 100644
--- a/ui/clipboard.c
+++ b/ui/clipboard.c
@@ -65,12 +65,24 @@ bool qemu_clipboard_check_serial(QemuClipboardInfo *info, bool client)
void qemu_clipboard_update(QemuClipboardInfo *info)
{
+ uint32_t type;
QemuClipboardNotify notify = {
.type = QEMU_CLIPBOARD_UPDATE_INFO,
.info = info,
};
assert(info->selection < QEMU_CLIPBOARD_SELECTION__COUNT);
+ for (type = 0; type < QEMU_CLIPBOARD_TYPE__COUNT; type++) {
+ /*
+ * If data is missing, the clipboard owner's 'request' callback needs to
+ * be set. Otherwise, there is no way to get the clipboard data and
+ * qemu_clipboard_request() cannot be called.
+ */
+ if (info->types[type].available && !info->types[type].data) {
+ assert(info->owner && info->owner->request);
+ }
+ }
+
notifier_list_notify(&clipboard_notifiers, &notify);
if (cbinfo[info->selection] != info) {
@@ -132,6 +144,8 @@ void qemu_clipboard_request(QemuClipboardInfo *info,
!info->owner)
return;
+ assert(info->owner->request);
+
info->types[type].requested = true;
info->owner->request(info, type);
}
--
2.39.3

Some files were not shown because too many files have changed in this diff Show More