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

import qemu-kvm-7.2.0-14.el9_2

This commit is contained in:
CentOS Sources 2023-05-09 05:17:27 +00:00 committed by Stepan Oksanichenko
parent 8f18a377be
commit 69ea50d792
293 changed files with 19200 additions and 18942 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.gitignore vendored
View File

@ -1 +1 @@
SOURCES/qemu-7.0.0.tar.xz
SOURCES/qemu-7.2.0.tar.xz

2
.qemu-kvm.metadata
View File

@ -1 +1 @@
c3fd2403106c33d0470bc9ba4fb4b946c0402248 SOURCES/qemu-7.0.0.tar.xz
634a3e4b381cbf13085eb1568accb85cbd9d89c4 SOURCES/qemu-7.2.0.tar.xz

73
SOURCES/0004-Initial-redhat-build.patch
View File

@ -1,4 +1,4 @@
From fc113ecd7c99646a7ced0b99570b5927ae6d595f Mon Sep 17 00:00:00 2001
From ccc4a5bdc8c2f27678312364a7c12aeafd009bb6 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-6.2.0-13.el9
This rebase is based on qemu-kvm-7.1.0-7.el9
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
--
@ -50,6 +50,22 @@ Rebase changes (7.0.0):
- Change permissions on installing tests/Makefile.include
- Remove ssh block driver
Rebase changes (7.1.0 rc0):
- --disable-vnc-png renamed to --disable-png (upstream)
- removed --disable-vhost-vsock and --disable-vhost-scsi
- capstone submodule removed
- Temporary include capstone build
Rebase changes (7.2.0 rc0):
- Switch --enable-slirp=system to --enable-slirp
Rebaes changes (7.2.0 rc2):
- Added new configure options (blkio and sndio, both disabled)
Rebase changes (7.2.0):
- Fix SRPM name generation to work on Fedora 37
- Switch back to system meson
Merged patches (6.0.0):
- 605758c902 Limit build on Power to qemu-img and qemu-ga only
@ -142,46 +158,34 @@ Merged patches (7.0.0):
- d46d2710b2 spec: Obsolete old usb redir subpackage
- 6f52a50b68 spec: Obsolete ssh driver
Merged patches (7.2.0 rc4):
- 8c6834feb6 Remove opengl display device subpackages (C9S MR 124)
- 0ecc97f29e spec: Add requires for packages with additional virtio-gpu variants (C9S MR 124)
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
fix
---
.distro/85-kvm.preset | 5 -
.distro/Makefile | 100 +
.distro/Makefile.common | 40 +
.distro/Makefile.common | 41 +
.distro/README.tests | 39 +
.distro/ksm.service | 13 -
.distro/ksm.sysconfig | 4 -
.distro/ksmctl.c | 77 -
.distro/ksmtuned | 139 -
.distro/ksmtuned.conf | 21 -
.distro/ksmtuned.service | 12 -
.distro/kvm-setup | 49 -
.distro/kvm-setup.service | 14 -
.distro/modules-load.conf | 4 +
.distro/qemu-guest-agent.service | 1 -
.distro/qemu-kvm.spec.template | 4034 +++++++++++++++++++++++
.distro/qemu-kvm.spec.template | 4315 +++++++++++++++++++++++
.distro/rpminspect.yaml | 6 +-
.distro/scripts/extract_build_cmd.py | 12 +
.distro/scripts/process-patches.sh | 4 +
.gitignore | 1 +
README.systemtap | 43 +
meson.build | 4 +-
scripts/qemu-guest-agent/fsfreeze-hook | 2 +-
scripts/systemtap/conf.d/qemu_kvm.conf | 4 +
scripts/systemtap/script.d/qemu_kvm.stp | 1 +
tests/check-block.sh | 2 +
ui/vnc-auth-sasl.c | 2 +-
25 files changed, 4290 insertions(+), 339 deletions(-)
delete mode 100644 .distro/85-kvm.preset
16 files changed, 4573 insertions(+), 4 deletions(-)
create mode 100644 .distro/Makefile
create mode 100644 .distro/Makefile.common
create mode 100644 .distro/README.tests
delete mode 100644 .distro/ksm.service
delete mode 100644 .distro/ksm.sysconfig
delete mode 100644 .distro/ksmctl.c
delete mode 100644 .distro/ksmtuned
delete mode 100644 .distro/ksmtuned.conf
delete mode 100644 .distro/ksmtuned.service
delete mode 100644 .distro/kvm-setup
delete mode 100644 .distro/kvm-setup.service
create mode 100644 .distro/modules-load.conf
create mode 100644 .distro/qemu-kvm.spec.template
create mode 100644 README.systemtap
@ -237,21 +241,6 @@ index 0000000000..ad913fc990
+
+3. Translate the trace record to readable format.
+ # /usr/share/qemu-kvm/simpletrace.py --no-header /usr/share/qemu-kvm/trace-events /tmp/trace.log
diff --git a/meson.build b/meson.build
index 861de93c4f..6f7e430f0f 100644
--- a/meson.build
+++ b/meson.build
@@ -2394,7 +2394,9 @@ if capstone_opt == 'internal'
# Include all configuration defines via a header file, which will wind up
# as a dependency on the object file, and thus changes here will result
# in a rebuild.
- '-include', 'capstone-defs.h'
+ '-include', 'capstone-defs.h',
+
+ '-Wp,-D_GLIBCXX_ASSERTIONS',
]
libcapstone = static_library('capstone',
diff --git a/scripts/qemu-guest-agent/fsfreeze-hook b/scripts/qemu-guest-agent/fsfreeze-hook
index 13aafd4845..e9b84ec028 100755
--- a/scripts/qemu-guest-agent/fsfreeze-hook
@ -283,11 +272,11 @@ index 0000000000..c04abf9449
@@ -0,0 +1 @@
+probe qemu.kvm.simpletrace.handle_qmp_command,qemu.kvm.simpletrace.monitor_protocol_*,qemu.kvm.simpletrace.migrate_set_state {}
diff --git a/tests/check-block.sh b/tests/check-block.sh
index f59496396c..d900d8b35e 100755
index 5de2c1ba0b..6af743f441 100755
--- a/tests/check-block.sh
+++ b/tests/check-block.sh
@@ -48,6 +48,8 @@ if LANG=C bash --version | grep -q 'GNU bash, version [123]' ; then
skip "bash version too old ==> Not running the qemu-iotests."
@@ -22,6 +22,8 @@ if [ -z "$(find . -name 'qemu-system-*' -print)" ]; then
skip "No qemu-system binary available ==> Not running the qemu-iotests."
fi
+exit 0

165
SOURCES/0005-Enable-disable-devices-for-RHEL.patch
View File

@ -1,6 +1,6 @@
From 51ec7495d69fe4b4d0b61642ca6c0e7fd7a1032d Mon Sep 17 00:00:00 2001
From 90366cd2ead5a5301aaceed56477d2e6d9f1b3cd Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Thu, 15 Jul 2021 03:22:36 -0400
Date: Wed, 7 Dec 2022 03:05:48 -0500
Subject: Enable/disable devices for RHEL
This commit adds all changes related to changes in supported devices.
@ -22,6 +22,16 @@ Rebase notes (7.0.0):
- Renamed CONFIG_ARM_GIC_TCG to CONFIG_ARM_GICV3_TCG
- Removed upstream devices
Rebase notes (7.1.0 rc0):
- Added CONFIG_VHOST_VSOCK and CONFIG_VHOST_USER_VSOCK configs
- Added CONFIG_CXL and CONFIG_CXL_MEM_DEVICE for aarch64 and x86_64
Rebase notes (7.1.0 rc3):
- Added CONFIG_VHOST_USER_FS option (all archs)
Rebase notes (7.2.0 rc20):
- Removed disabling a15mpcore.c as no longer needed
Merged patches (6.1.0):
- c51bf45304 Remove SPICE and QXL from x86_64-rh-devices.mak
- 02fc745601 aarch64-rh-devices: add CONFIG_PVPANIC_PCI
@ -37,17 +47,22 @@ Merged patches (6.2.0):
Merged patches (7.0.0):
- fd7c45a5a8 redhat: Enable virtio-mem as tech-preview on x86-64
- c9e68ea451 Enable SGX -- RH Only
Merged patches (7.1.0 rc0):
- 38b89dc245 pc: Move s3/s4 suspend disabling to compat (only hw/acpi/ich9.c chunk)
- 8f663466c6 configs/devices/aarch64-softmmu: Enable CONFIG_VIRTIO_MEM
- 1bf372717a Enable virtio-iommu-pci on aarch64
- ae3f269458 Enable virtio-iommu-pci on x86_64
---
.distro/qemu-kvm.spec.template | 18 +--
.../aarch64-softmmu/aarch64-rh-devices.mak | 34 ++++++
.../ppc64-softmmu/ppc64-rh-devices.mak | 35 ++++++
.../aarch64-softmmu/aarch64-rh-devices.mak | 41 +++++++
.../ppc64-softmmu/ppc64-rh-devices.mak | 37 ++++++
configs/devices/rh-virtio.mak | 10 ++
.../s390x-softmmu/s390x-rh-devices.mak | 15 +++
.../x86_64-softmmu/x86_64-rh-devices.mak | 103 ++++++++++++++++++
hw/acpi/ich9.c | 4 +-
.../s390x-softmmu/s390x-rh-devices.mak | 18 +++
.../x86_64-softmmu/x86_64-rh-devices.mak | 109 ++++++++++++++++++
hw/arm/meson.build | 2 +-
hw/block/fdc.c | 10 ++
hw/cpu/meson.build | 5 +-
hw/cpu/meson.build | 3 +-
hw/display/cirrus_vga.c | 5 +-
hw/ide/piix.c | 5 +-
hw/input/pckbd.c | 2 +
@ -58,7 +73,7 @@ Merged patches (7.0.0):
target/ppc/cpu-models.c | 9 ++
target/s390x/cpu_models_sysemu.c | 3 +
target/s390x/kvm/kvm.c | 8 ++
20 files changed, 269 insertions(+), 15 deletions(-)
19 files changed, 283 insertions(+), 13 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
@ -67,10 +82,10 @@ Merged patches (7.0.0):
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..5f6ee1de5b
index 0000000000..720ec0cb57
--- /dev/null
+++ b/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak
@@ -0,0 +1,34 @@
@@ -0,0 +1,41 @@
+include ../rh-virtio.mak
+
+CONFIG_ARM_GIC_KVM=y
@ -79,6 +94,8 @@ index 0000000000..5f6ee1de5b
+CONFIG_ARM_SMMUV3=y
+CONFIG_ARM_V7M=y
+CONFIG_ARM_VIRT=y
+CONFIG_CXL=y
+CONFIG_CXL_MEM_DEVICE=y
+CONFIG_EDID=y
+CONFIG_PCIE_PORT=y
+CONFIG_PCI_DEVICES=y
@ -95,6 +112,8 @@ index 0000000000..5f6ee1de5b
+CONFIG_VFIO_PCI=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_VIRTIO_PCI=y
+CONFIG_VIRTIO_MEM=y
+CONFIG_VIRTIO_IOMMU=y
+CONFIG_XIO3130=y
+CONFIG_NVDIMM=y
+CONFIG_ACPI_APEI=y
@ -105,12 +124,15 @@ index 0000000000..5f6ee1de5b
+CONFIG_ARM_COMPATIBLE_SEMIHOSTING=y
+CONFIG_PVPANIC_PCI=y
+CONFIG_PXB=y
+CONFIG_VHOST_VSOCK=y
+CONFIG_VHOST_USER_VSOCK=y
+CONFIG_VHOST_USER_FS=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..6a3e3f0227
index 0000000000..dbb7d30829
--- /dev/null
+++ b/configs/devices/ppc64-softmmu/ppc64-rh-devices.mak
@@ -0,0 +1,35 @@
@@ -0,0 +1,37 @@
+include ../rh-virtio.mak
+
+CONFIG_DIMM=y
@ -146,6 +168,8 @@ index 0000000000..6a3e3f0227
+CONFIG_TPM=y
+CONFIG_TPM_SPAPR=y
+CONFIG_TPM_EMULATOR=y
+CONFIG_VHOST_VSOCK=y
+CONFIG_VHOST_USER_VSOCK=y
diff --git a/configs/devices/rh-virtio.mak b/configs/devices/rh-virtio.mak
new file mode 100644
index 0000000000..94ede1b5f6
@ -164,10 +188,10 @@ 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..d3b38312e1
index 0000000000..69a799adbd
--- /dev/null
+++ b/configs/devices/s390x-softmmu/s390x-rh-devices.mak
@@ -0,0 +1,15 @@
@@ -0,0 +1,18 @@
+include ../rh-virtio.mak
+
+CONFIG_PCI=y
@ -183,12 +207,15 @@ index 0000000000..d3b38312e1
+CONFIG_VHOST_USER=y
+CONFIG_VIRTIO_CCW=y
+CONFIG_WDT_DIAG288=y
+CONFIG_VHOST_VSOCK=y
+CONFIG_VHOST_USER_VSOCK=y
+CONFIG_VHOST_USER_FS=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..d0c9e66641
index 0000000000..10cb0a14e0
--- /dev/null
+++ b/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak
@@ -0,0 +1,103 @@
@@ -0,0 +1,109 @@
+include ../rh-virtio.mak
+
+CONFIG_ACPI=y
@ -204,6 +231,8 @@ index 0000000000..d0c9e66641
+CONFIG_APIC=y
+CONFIG_APM=y
+CONFIG_BOCHS_DISPLAY=y
+CONFIG_CXL=y
+CONFIG_CXL_MEM_DEVICE=y
+CONFIG_DIMM=y
+CONFIG_E1000E_PCI_EXPRESS=y
+CONFIG_E1000_PCI=y
@ -281,6 +310,7 @@ index 0000000000..d0c9e66641
+CONFIG_VIRTIO_MEM=y
+CONFIG_VIRTIO_PCI=y
+CONFIG_VIRTIO_VGA=y
+CONFIG_VIRTIO_IOMMU=y
+CONFIG_VMMOUSE=y
+CONFIG_VMPORT=y
+CONFIG_VTD=y
@ -292,26 +322,14 @@ index 0000000000..d0c9e66641
+CONFIG_TPM_TIS_ISA=y
+CONFIG_TPM_EMULATOR=y
+CONFIG_SGX=y
diff --git a/hw/acpi/ich9.c b/hw/acpi/ich9.c
index bd9bbade70..de1e401cdf 100644
--- a/hw/acpi/ich9.c
+++ b/hw/acpi/ich9.c
@@ -435,8 +435,8 @@ void ich9_pm_add_properties(Object *obj, ICH9LPCPMRegs *pm)
static const uint32_t gpe0_len = ICH9_PMIO_GPE0_LEN;
pm->acpi_memory_hotplug.is_enabled = true;
pm->cpu_hotplug_legacy = true;
- pm->disable_s3 = 0;
- pm->disable_s4 = 0;
+ pm->disable_s3 = 1;
+ pm->disable_s4 = 1;
pm->s4_val = 2;
pm->use_acpi_hotplug_bridge = true;
pm->keep_pci_slot_hpc = true;
+CONFIG_VHOST_VSOCK=y
+CONFIG_VHOST_USER_VSOCK=y
+CONFIG_VHOST_USER_FS=y
diff --git a/hw/arm/meson.build b/hw/arm/meson.build
index 721a8eb8be..87ed4dd914 100644
index 92f9f6e000..c5e94c997c 100644
--- a/hw/arm/meson.build
+++ b/hw/arm/meson.build
@@ -31,7 +31,7 @@ arm_ss.add(when: 'CONFIG_VEXPRESS', if_true: files('vexpress.c'))
@@ -30,7 +30,7 @@ arm_ss.add(when: 'CONFIG_VEXPRESS', if_true: files('vexpress.c'))
arm_ss.add(when: 'CONFIG_ZYNQ', if_true: files('xilinx_zynq.c'))
arm_ss.add(when: 'CONFIG_SABRELITE', if_true: files('sabrelite.c'))
@ -321,7 +339,7 @@ index 721a8eb8be..87ed4dd914 100644
arm_ss.add(when: 'CONFIG_PXA2XX', if_true: files('pxa2xx.c', 'pxa2xx_gpio.c', 'pxa2xx_pic.c'))
arm_ss.add(when: 'CONFIG_DIGIC', if_true: files('digic.c'))
diff --git a/hw/block/fdc.c b/hw/block/fdc.c
index 347875a0cd..ca1776121f 100644
index 64ae4a6899..9b8e782c19 100644
--- a/hw/block/fdc.c
+++ b/hw/block/fdc.c
@@ -49,6 +49,8 @@
@ -333,7 +351,7 @@ index 347875a0cd..ca1776121f 100644
/********************************************************/
/* debug Floppy devices */
@@ -2338,6 +2340,14 @@ void fdctrl_realize_common(DeviceState *dev, FDCtrl *fdctrl, Error **errp)
@@ -2346,6 +2348,14 @@ void fdctrl_realize_common(DeviceState *dev, FDCtrl *fdctrl, Error **errp)
FDrive *drive;
static int command_tables_inited = 0;
@ -349,24 +367,21 @@ index 347875a0cd..ca1776121f 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 9e52fee9e7..bb71c9f3e7 100644
index 9e52fee9e7..87c209a754 100644
--- a/hw/cpu/meson.build
+++ b/hw/cpu/meson.build
@@ -1,6 +1,7 @@
@@ -1,4 +1,5 @@
-softmmu_ss.add(files('core.c', 'cluster.c'))
+#softmmu_ss.add(files('core.c', 'cluster.c'))
+softmmu_ss.add(files('core.c'))
specific_ss.add(when: 'CONFIG_ARM11MPCORE', if_true: files('arm11mpcore.c'))
specific_ss.add(when: 'CONFIG_REALVIEW', if_true: files('realview_mpcore.c'))
specific_ss.add(when: 'CONFIG_A9MPCORE', if_true: files('a9mpcore.c'))
-specific_ss.add(when: 'CONFIG_A15MPCORE', if_true: files('a15mpcore.c'))
+#specific_ss.add(when: 'CONFIG_A15MPCORE', if_true: files('a15mpcore.c'))
diff --git a/hw/display/cirrus_vga.c b/hw/display/cirrus_vga.c
index 3bb6a58698..6447fdb02e 100644
index 6e8c747c46..1948ebee8e 100644
--- a/hw/display/cirrus_vga.c
+++ b/hw/display/cirrus_vga.c
@@ -2945,7 +2945,10 @@ static void pci_cirrus_vga_realize(PCIDevice *dev, Error **errp)
@@ -2946,7 +2946,10 @@ static void pci_cirrus_vga_realize(PCIDevice *dev, Error **errp)
PCIDeviceClass *pc = PCI_DEVICE_GET_CLASS(dev);
int16_t device_id = pc->device_id;
@ -379,10 +394,10 @@ index 3bb6a58698..6447fdb02e 100644
* Also accept 8 MB/16 MB for backward compatibility.
*/
diff --git a/hw/ide/piix.c b/hw/ide/piix.c
index ce89fd0aa3..fbcf802b13 100644
index 267dbf37db..87fcda4062 100644
--- a/hw/ide/piix.c
+++ b/hw/ide/piix.c
@@ -232,7 +232,8 @@ static void piix3_ide_class_init(ObjectClass *klass, void *data)
@@ -199,7 +199,8 @@ 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);
@ -392,7 +407,7 @@ index ce89fd0aa3..fbcf802b13 100644
}
static const TypeInfo piix3_ide_info = {
@@ -261,6 +262,8 @@ static void piix4_ide_class_init(ObjectClass *klass, void *data)
@@ -222,6 +223,8 @@ 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;
@ -402,12 +417,12 @@ index ce89fd0aa3..fbcf802b13 100644
static const TypeInfo piix4_ide_info = {
diff --git a/hw/input/pckbd.c b/hw/input/pckbd.c
index 4efdf75620..5143ebaa27 100644
index b92b63bedc..3b6235dde6 100644
--- a/hw/input/pckbd.c
+++ b/hw/input/pckbd.c
@@ -814,6 +814,8 @@ static void i8042_class_initfn(ObjectClass *klass, void *data)
@@ -957,6 +957,8 @@ static void i8042_class_initfn(ObjectClass *klass, void *data)
dc->vmsd = &vmstate_kbd_isa;
isa->build_aml = i8042_build_aml;
adevc->build_dev_aml = i8042_build_aml;
set_bit(DEVICE_CATEGORY_INPUT, dc->categories);
+ /* Disabled for Red Hat Enterprise Linux: */
+ dc->user_creatable = false;
@ -415,10 +430,10 @@ index 4efdf75620..5143ebaa27 100644
static const TypeInfo i8042_info = {
diff --git a/hw/net/e1000.c b/hw/net/e1000.c
index f5bc81296d..282d01e374 100644
index e26e0a64c1..41492fae79 100644
--- a/hw/net/e1000.c
+++ b/hw/net/e1000.c
@@ -1821,6 +1821,7 @@ static const E1000Info e1000_devices[] = {
@@ -1824,6 +1824,7 @@ static const E1000Info e1000_devices[] = {
.revision = 0x03,
.phy_id2 = E1000_PHY_ID2_8254xx_DEFAULT,
},
@ -426,7 +441,7 @@ index f5bc81296d..282d01e374 100644
{
.name = "e1000-82544gc",
.device_id = E1000_DEV_ID_82544GC_COPPER,
@@ -1833,6 +1834,7 @@ static const E1000Info e1000_devices[] = {
@@ -1836,6 +1837,7 @@ static const E1000Info e1000_devices[] = {
.revision = 0x03,
.phy_id2 = E1000_PHY_ID2_8254xx_DEFAULT,
},
@ -452,7 +467,7 @@ index 8a4861f45a..fcb5dfe792 100644
DEFINE_SPAPR_CPU_CORE_TYPE("power7+_v2.1"),
DEFINE_SPAPR_CPU_CORE_TYPE("power8_v2.0"),
diff --git a/hw/usb/meson.build b/hw/usb/meson.build
index de853d780d..0776ae6a20 100644
index 793df42e21..cd3c305471 100644
--- a/hw/usb/meson.build
+++ b/hw/usb/meson.build
@@ -52,7 +52,7 @@ softmmu_ss.add(when: 'CONFIG_USB_SMARTCARD', if_true: files('dev-smartcard-reade
@ -465,10 +480,10 @@ index de853d780d..0776ae6a20 100644
endif
diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c
index 13d0e9b195..3826fa5122 100644
index 9a2cef7d05..a528ff9a3d 100644
--- a/target/arm/cpu_tcg.c
+++ b/target/arm/cpu_tcg.c
@@ -22,6 +22,7 @@
@@ -151,6 +151,7 @@ void define_cortex_a72_a57_a53_cp_reginfo(ARMCPU *cpu)
/* CPU models. These are not needed for the AArch64 linux-user build. */
#if !defined(CONFIG_USER_ONLY) || !defined(TARGET_AARCH64)
@ -476,31 +491,31 @@ index 13d0e9b195..3826fa5122 100644
#if !defined(CONFIG_USER_ONLY) && defined(CONFIG_TCG)
static bool arm_v7m_cpu_exec_interrupt(CPUState *cs, int interrupt_request)
{
@@ -375,6 +376,7 @@ static void cortex_a9_initfn(Object *obj)
cpu->ccsidr[1] = 0x200fe019; /* 16k L1 icache. */
@@ -504,6 +505,7 @@ static void cortex_a9_initfn(Object *obj)
cpu->isar.reset_pmcr_el0 = 0x41093000;
define_arm_cp_regs(cpu, cortexa9_cp_reginfo);
}
+#endif /* disabled for RHEL */
#ifndef CONFIG_USER_ONLY
static uint64_t a15_l2ctlr_read(CPUARMState *env, const ARMCPRegInfo *ri)
@@ -400,6 +402,7 @@ static const ARMCPRegInfo cortexa15_cp_reginfo[] = {
REGINFO_SENTINEL
@@ -528,6 +530,7 @@ static const ARMCPRegInfo cortexa15_cp_reginfo[] = {
.access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 },
};
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void cortex_a7_initfn(Object *obj)
{
ARMCPU *cpu = ARM_CPU(obj);
@@ -445,6 +448,7 @@ static void cortex_a7_initfn(Object *obj)
cpu->ccsidr[2] = 0x711fe07a; /* 4096K L2 unified cache */
@@ -576,6 +579,7 @@ static void cortex_a7_initfn(Object *obj)
cpu->isar.reset_pmcr_el0 = 0x41072000;
define_arm_cp_regs(cpu, cortexa15_cp_reginfo); /* Same as A15 */
}
+#endif /* disabled for RHEL */
static void cortex_a15_initfn(Object *obj)
{
@@ -488,6 +492,7 @@ static void cortex_a15_initfn(Object *obj)
@@ -624,6 +628,7 @@ static void cortex_a15_initfn(Object *obj)
define_arm_cp_regs(cpu, cortexa15_cp_reginfo);
}
@ -508,7 +523,7 @@ index 13d0e9b195..3826fa5122 100644
static void cortex_m0_initfn(Object *obj)
{
ARMCPU *cpu = ARM_CPU(obj);
@@ -928,6 +933,7 @@ static void arm_v7m_class_init(ObjectClass *oc, void *data)
@@ -1065,6 +1070,7 @@ static void arm_v7m_class_init(ObjectClass *oc, void *data)
cc->gdb_core_xml_file = "arm-m-profile.xml";
}
@ -516,7 +531,7 @@ index 13d0e9b195..3826fa5122 100644
#ifndef TARGET_AARCH64
/*
@@ -1007,6 +1013,7 @@ static void arm_max_initfn(Object *obj)
@@ -1132,6 +1138,7 @@ static void arm_max_initfn(Object *obj)
#endif /* !TARGET_AARCH64 */
static const ARMCPUInfo arm_tcg_cpus[] = {
@ -524,7 +539,7 @@ index 13d0e9b195..3826fa5122 100644
{ .name = "arm926", .initfn = arm926_initfn },
{ .name = "arm946", .initfn = arm946_initfn },
{ .name = "arm1026", .initfn = arm1026_initfn },
@@ -1022,7 +1029,9 @@ static const ARMCPUInfo arm_tcg_cpus[] = {
@@ -1147,7 +1154,9 @@ static const ARMCPUInfo arm_tcg_cpus[] = {
{ .name = "cortex-a7", .initfn = cortex_a7_initfn },
{ .name = "cortex-a8", .initfn = cortex_a8_initfn },
{ .name = "cortex-a9", .initfn = cortex_a9_initfn },
@ -534,7 +549,7 @@ index 13d0e9b195..3826fa5122 100644
{ .name = "cortex-m0", .initfn = cortex_m0_initfn,
.class_init = arm_v7m_class_init },
{ .name = "cortex-m3", .initfn = cortex_m3_initfn,
@@ -1053,6 +1062,7 @@ static const ARMCPUInfo arm_tcg_cpus[] = {
@@ -1178,6 +1187,7 @@ static const ARMCPUInfo arm_tcg_cpus[] = {
{ .name = "pxa270-b1", .initfn = pxa270b1_initfn },
{ .name = "pxa270-c0", .initfn = pxa270c0_initfn },
{ .name = "pxa270-c5", .initfn = pxa270c5_initfn },
@ -543,7 +558,7 @@ index 13d0e9b195..3826fa5122 100644
{ .name = "max", .initfn = arm_max_initfn },
#endif
diff --git a/target/ppc/cpu-models.c b/target/ppc/cpu-models.c
index 976be5e0d1..dd78883410 100644
index 912b037c63..cd3ff700ac 100644
--- a/target/ppc/cpu-models.c
+++ b/target/ppc/cpu-models.c
@@ -66,6 +66,7 @@
@ -573,7 +588,7 @@ index 976be5e0d1..dd78883410 100644
POWERPC_DEF("power7_v2.3", CPU_POWERPC_POWER7_v23, POWER7,
"POWER7 v2.3")
POWERPC_DEF("power7+_v2.1", CPU_POWERPC_POWER7P_v21, POWER7,
@@ -897,12 +901,15 @@ PowerPCCPUAlias ppc_cpu_aliases[] = {
@@ -896,12 +900,15 @@ PowerPCCPUAlias ppc_cpu_aliases[] = {
{ "7447a", "7447a_v1.2" },
{ "7457a", "7457a_v1.2" },
{ "apollo7pm", "7457a_v1.0" },
@ -589,7 +604,7 @@ index 976be5e0d1..dd78883410 100644
{ "power7", "power7_v2.3" },
{ "power7+", "power7+_v2.1" },
{ "power8e", "power8e_v2.1" },
@@ -912,6 +919,7 @@ PowerPCCPUAlias ppc_cpu_aliases[] = {
@@ -911,12 +918,14 @@ PowerPCCPUAlias ppc_cpu_aliases[] = {
{ "power10", "power10_v2.0" },
#endif
@ -597,18 +612,18 @@ index 976be5e0d1..dd78883410 100644
/* Generic PowerPCs */
#if defined(TARGET_PPC64)
{ "ppc64", "970fx_v3.1" },
@@ -919,5 +927,6 @@ PowerPCCPUAlias ppc_cpu_aliases[] = {
#endif
{ "ppc32", "604" },
{ "ppc", "604" },
{ "default", "604" },
+#endif
{ NULL, NULL }
};
diff --git a/target/s390x/cpu_models_sysemu.c b/target/s390x/cpu_models_sysemu.c
index 05c3ccaaff..6a04ccab1b 100644
index d8a141a023..d086b1c39c 100644
--- a/target/s390x/cpu_models_sysemu.c
+++ b/target/s390x/cpu_models_sysemu.c
@@ -36,6 +36,9 @@ static void check_unavailable_features(const S390CPUModel *max_model,
@@ -35,6 +35,9 @@ 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);
@ -619,10 +634,10 @@ index 05c3ccaaff..6a04ccab1b 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 6acf14d5ec..74f089d87f 100644
index 3ac7ec9acf..97da1a6424 100644
--- a/target/s390x/kvm/kvm.c
+++ b/target/s390x/kvm/kvm.c
@@ -2512,6 +2512,14 @@ void kvm_s390_apply_cpu_model(const S390CPUModel *model, Error **errp)
@@ -2529,6 +2529,14 @@ void kvm_s390_apply_cpu_model(const S390CPUModel *model, Error **errp)
error_setg(errp, "KVM doesn't support CPU models");
return;
}

140
SOURCES/0006-Machine-type-related-general-changes.patch
View File

@ -1,4 +1,4 @@
From a525db3951dc68c469d1f51bdc69ab6e75e72c37 Mon Sep 17 00:00:00 2001
From 0208f38671b9de4036c0d56142a7f22e5091bae0 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
@ -19,6 +19,10 @@ Rebase notes (7.0.0):
- Remove downstream changes leftovers in hw/rtc/mc146818rtc.c
- Remove unnecessary change in hw/usb/hcd-uhci.c
Rebase notes (7.1.0 rc0):
- Moved adding rhel_old_machine_deprecation variable from s390x to general machine types commit
- Moved adding hw_compat_rhel_8_6 struct from x86_64 to general machine types commit
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
@ -35,28 +39,35 @@ Merged patches (6.2.0):
Merged patches (7.0.0):
- ef5afcc86d Fix virtio-net-pci* "vectors" compat
- 168f0d56e3 compat: Update hw_compat_rhel_8_5 with 6.2.0 RC2 changes
Merged patches (7.1.0 rc0):
- 38b89dc245 pc: Move s3/s4 suspend disabling to compat (only hw/acpi/piix4.c chunk)
- 1d6439527a WRB: Introduce RHEL 9.0.0 hw compat structure (only hw/core/machine.c and include/hw/boards.h chunk)
Merged patches (7.2.0 rc0):
- 0be2889fa2 Introduce upstream 7.0 compat changes (only applicable parts)
---
hw/acpi/piix4.c | 6 +-
hw/acpi/piix4.c | 2 +-
hw/arm/virt.c | 2 +-
hw/core/machine.c | 186 +++++++++++++++++++++++++++++++++++
hw/core/machine.c | 222 +++++++++++++++++++++++++++++++++++
hw/display/vga-isa.c | 2 +-
hw/i386/pc_piix.c | 2 +
hw/i386/pc_q35.c | 2 +
hw/net/rtl8139.c | 4 +-
hw/smbios/smbios.c | 46 ++++++++-
hw/smbios/smbios.c | 46 +++++++-
hw/timer/i8254_common.c | 2 +-
hw/usb/hcd-xhci-pci.c | 59 ++++++++---
hw/usb/hcd-xhci-pci.c | 59 +++++++---
hw/usb/hcd-xhci-pci.h | 1 +
include/hw/boards.h | 21 ++++
include/hw/boards.h | 31 +++++
include/hw/firmware/smbios.h | 5 +-
include/hw/i386/pc.h | 3 +
14 files changed, 316 insertions(+), 25 deletions(-)
14 files changed, 360 insertions(+), 23 deletions(-)
diff --git a/hw/acpi/piix4.c b/hw/acpi/piix4.c
index fe5625d07a..28544e78c3 100644
index 0a81f1ad93..dbfb362a8f 100644
--- a/hw/acpi/piix4.c
+++ b/hw/acpi/piix4.c
@@ -287,7 +287,7 @@ static bool vmstate_test_migrate_acpi_index(void *opaque, int version_id)
@@ -248,7 +248,7 @@ static bool vmstate_test_migrate_acpi_index(void *opaque, int version_id)
static const VMStateDescription vmstate_acpi = {
.name = "piix4_pm",
.version_id = 3,
@ -65,22 +76,11 @@ index fe5625d07a..28544e78c3 100644
.post_load = vmstate_acpi_post_load,
.fields = (VMStateField[]) {
VMSTATE_PCI_DEVICE(parent_obj, PIIX4PMState),
@@ -653,8 +653,8 @@ static void piix4_send_gpe(AcpiDeviceIf *adev, AcpiEventStatusBits ev)
static Property piix4_pm_properties[] = {
DEFINE_PROP_UINT32("smb_io_base", PIIX4PMState, smb_io_base, 0),
- DEFINE_PROP_UINT8(ACPI_PM_PROP_S3_DISABLED, PIIX4PMState, disable_s3, 0),
- DEFINE_PROP_UINT8(ACPI_PM_PROP_S4_DISABLED, PIIX4PMState, disable_s4, 0),
+ DEFINE_PROP_UINT8(ACPI_PM_PROP_S3_DISABLED, PIIX4PMState, disable_s3, 1),
+ DEFINE_PROP_UINT8(ACPI_PM_PROP_S4_DISABLED, PIIX4PMState, disable_s4, 1),
DEFINE_PROP_UINT8(ACPI_PM_PROP_S4_VAL, PIIX4PMState, s4_val, 2),
DEFINE_PROP_BOOL(ACPI_PM_PROP_ACPI_PCIHP_BRIDGE, PIIX4PMState,
use_acpi_hotplug_bridge, true),
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index d2e5ecd234..6a84031fd7 100644
index b871350856..d633300fdc 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -1596,7 +1596,7 @@ static void virt_build_smbios(VirtMachineState *vms)
@@ -1619,7 +1619,7 @@ static void virt_build_smbios(VirtMachineState *vms)
smbios_set_defaults("QEMU", product,
vmc->smbios_old_sys_ver ? "1.0" : mc->name, false,
@ -90,13 +90,49 @@ index d2e5ecd234..6a84031fd7 100644
smbios_get_tables(MACHINE(vms), NULL, 0,
&smbios_tables, &smbios_tables_len,
diff --git a/hw/core/machine.c b/hw/core/machine.c
index 1e23fdc14b..ea430d844e 100644
index 8d34caa31d..9edec1ca05 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -37,6 +37,192 @@
#include "hw/virtio/virtio.h"
@@ -40,6 +40,228 @@
#include "hw/virtio/virtio-pci.h"
#include "qom/object_interfaces.h"
+/*
+ * RHEL only: machine types for previous major releases are deprecated
+ */
+const char *rhel_old_machine_deprecation =
+ "machine types for previous major releases are deprecated";
+
+/*
+ * Mostly the same as hw_compat_7_0
+ */
+GlobalProperty hw_compat_rhel_9_1[] = {
+ /* hw_compat_rhel_9_1 from hw_compat_7_0 */
+ { "arm-gicv3-common", "force-8-bit-prio", "on" },
+ /* hw_compat_rhel_9_1 from hw_compat_7_0 */
+ { "nvme-ns", "eui64-default", "on"},
+};
+const size_t hw_compat_rhel_9_1_len = G_N_ELEMENTS(hw_compat_rhel_9_1);
+
+/*
+ * Mostly the same as hw_compat_6_2
+ */
+GlobalProperty hw_compat_rhel_9_0[] = {
+ /* hw_compat_rhel_9_0 from hw_compat_6_2 */
+ { "PIIX4_PM", "x-not-migrate-acpi-index", "on"},
+};
+const size_t hw_compat_rhel_9_0_len = G_N_ELEMENTS(hw_compat_rhel_9_0);
+
+GlobalProperty hw_compat_rhel_8_6[] = {
+ /* hw_compat_rhel_8_6 bz 2065589 */
+ /*
+ * vhost-vsock device in RHEL 8 kernels doesn't support seqpacket, so
+ * we need do disable it downstream on the latest hw_compat_rhel_8.
+ */
+ { "vhost-vsock-device", "seqpacket", "off" },
+};
+const size_t hw_compat_rhel_8_6_len = G_N_ELEMENTS(hw_compat_rhel_8_6);
+
+/*
+ * Mostly the same as hw_compat_6_0 and hw_compat_6_1
+ */
@ -283,14 +319,14 @@ index 1e23fdc14b..ea430d844e 100644
+};
+const size_t hw_compat_rhel_7_6_len = G_N_ELEMENTS(hw_compat_rhel_7_6);
+
GlobalProperty hw_compat_6_2[] = {
{ "PIIX4_PM", "x-not-migrate-acpi-index", "on"},
GlobalProperty hw_compat_7_1[] = {
{ "virtio-device", "queue_reset", "false" },
};
diff --git a/hw/display/vga-isa.c b/hw/display/vga-isa.c
index 46abbc5653..505467059b 100644
index 2a5437d803..0db2c2b2a1 100644
--- a/hw/display/vga-isa.c
+++ b/hw/display/vga-isa.c
@@ -88,7 +88,7 @@ static void vga_isa_realizefn(DeviceState *dev, Error **errp)
@@ -89,7 +89,7 @@ static void vga_isa_realizefn(DeviceState *dev, Error **errp)
}
static Property vga_isa_properties[] = {
@ -300,10 +336,10 @@ index 46abbc5653..505467059b 100644
};
diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index b72c03d0a6..c797e98312 100644
index 0ad0ed1603..0985ff67d2 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -177,6 +177,8 @@ static void pc_init1(MachineState *machine,
@@ -187,6 +187,8 @@ static void pc_init1(MachineState *machine,
smbios_set_defaults("QEMU", "Standard PC (i440FX + PIIX, 1996)",
mc->name, pcmc->smbios_legacy_mode,
pcmc->smbios_uuid_encoded,
@ -313,10 +349,10 @@ index b72c03d0a6..c797e98312 100644
}
diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index 1780f79bc1..b695f88c45 100644
index a496bd6e74..ea582254e3 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -200,6 +200,8 @@ static void pc_q35_init(MachineState *machine)
@@ -201,6 +201,8 @@ static void pc_q35_init(MachineState *machine)
smbios_set_defaults("QEMU", "Standard PC (Q35 + ICH9, 2009)",
mc->name, pcmc->smbios_legacy_mode,
pcmc->smbios_uuid_encoded,
@ -326,10 +362,10 @@ index 1780f79bc1..b695f88c45 100644
}
diff --git a/hw/net/rtl8139.c b/hw/net/rtl8139.c
index 6b65823b4b..75dacabc43 100644
index 700b1b66b6..13693aeb4f 100644
--- a/hw/net/rtl8139.c
+++ b/hw/net/rtl8139.c
@@ -3179,7 +3179,7 @@ static int rtl8139_pre_save(void *opaque)
@@ -3178,7 +3178,7 @@ static int rtl8139_pre_save(void *opaque)
static const VMStateDescription vmstate_rtl8139 = {
.name = "rtl8139",
@ -338,7 +374,7 @@ index 6b65823b4b..75dacabc43 100644
.minimum_version_id = 3,
.post_load = rtl8139_post_load,
.pre_save = rtl8139_pre_save,
@@ -3260,7 +3260,9 @@ static const VMStateDescription vmstate_rtl8139 = {
@@ -3259,7 +3259,9 @@ static const VMStateDescription vmstate_rtl8139 = {
VMSTATE_UINT32(tally_counters.TxMCol, RTL8139State),
VMSTATE_UINT64(tally_counters.RxOkPhy, RTL8139State),
VMSTATE_UINT64(tally_counters.RxOkBrd, RTL8139State),
@ -349,7 +385,7 @@ index 6b65823b4b..75dacabc43 100644
VMSTATE_UINT16(tally_counters.TxUndrn, RTL8139State),
diff --git a/hw/smbios/smbios.c b/hw/smbios/smbios.c
index 60349ee402..0edcc98434 100644
index b4243de735..c5ad69237e 100644
--- a/hw/smbios/smbios.c
+++ b/hw/smbios/smbios.c
@@ -57,6 +57,9 @@ static bool smbios_legacy = true;
@ -362,7 +398,7 @@ index 60349ee402..0edcc98434 100644
uint8_t *smbios_tables;
size_t smbios_tables_len;
@@ -639,7 +642,7 @@ static void smbios_build_type_1_table(void)
@@ -669,7 +672,7 @@ static void smbios_build_type_1_table(void)
static void smbios_build_type_2_table(void)
{
@ -371,7 +407,7 @@ index 60349ee402..0edcc98434 100644
SMBIOS_TABLE_SET_STR(2, manufacturer_str, type2.manufacturer);
SMBIOS_TABLE_SET_STR(2, product_str, type2.product);
@@ -914,7 +917,10 @@ void smbios_set_cpuid(uint32_t version, uint32_t features)
@@ -977,7 +980,10 @@ 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,
@ -383,7 +419,7 @@ index 60349ee402..0edcc98434 100644
{
smbios_have_defaults = true;
smbios_legacy = legacy_mode;
@@ -935,11 +941,45 @@ void smbios_set_defaults(const char *manufacturer, const char *product,
@@ -998,11 +1004,45 @@ void smbios_set_defaults(const char *manufacturer, const char *product,
g_free(smbios_entries);
}
@ -444,7 +480,7 @@ index 050875b497..32935da46c 100644
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 e934b1a5b1..e18b05e528 100644
index 643d4643e4..529bad9366 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)
@ -555,13 +591,22 @@ index c193f79443..086a1feb1e 100644
#endif
diff --git a/include/hw/boards.h b/include/hw/boards.h
index c92ac8815c..c90a19b4d1 100644
index 90f1dd3aeb..2209d4e416 100644
--- a/include/hw/boards.h
+++ b/include/hw/boards.h
@@ -449,4 +449,25 @@ extern const size_t hw_compat_2_2_len;
@@ -454,4 +454,35 @@ 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_1[];
+extern const size_t hw_compat_rhel_9_1_len;
+
+extern GlobalProperty hw_compat_rhel_9_0[];
+extern const size_t hw_compat_rhel_9_0_len;
+
+extern GlobalProperty hw_compat_rhel_8_6[];
+extern const size_t hw_compat_rhel_8_6_len;
+
+extern GlobalProperty hw_compat_rhel_8_5[];
+extern const size_t hw_compat_rhel_8_5_len;
+
@ -583,12 +628,13 @@ index c92ac8815c..c90a19b4d1 100644
+extern GlobalProperty hw_compat_rhel_7_6[];
+extern const size_t hw_compat_rhel_7_6_len;
+
+extern const char *rhel_old_machine_deprecation;
#endif
diff --git a/include/hw/firmware/smbios.h b/include/hw/firmware/smbios.h
index 4b7ad77a44..9acff96a86 100644
index 7f3259a630..d24b3ccd32 100644
--- a/include/hw/firmware/smbios.h
+++ b/include/hw/firmware/smbios.h
@@ -272,7 +272,10 @@ void smbios_entry_add(QemuOpts *opts, Error **errp);
@@ -294,7 +294,10 @@ 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,
@ -601,10 +647,10 @@ index 4b7ad77a44..9acff96a86 100644
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 1a27de9c8b..91331059d9 100644
index c95333514e..3754eaa97d 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_defaults;
bool smbios_legacy_mode;
bool smbios_uuid_encoded;

367
SOURCES/0007-Add-aarch64-machine-types.patch
View File

@ -1,4 +1,4 @@
From 697aaa43e3c0f20fc312f06be6c1093f1ba907e1 Mon Sep 17 00:00:00 2001
From 8501581c99760ed8a800d0c98eeb17a4bf450366 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
@ -17,6 +17,15 @@ Rebase notes (7.0.0):
- Added dtb-kaslr-seed option
- Set no_tcg_lpa2 to true
Rebase notes (7.1.0 rc0):
- replace dtb_kaslr_seed by dtb_randomness
Rebase notes (7.1.0 rc3):
- Updated dtb_randomness comment
Rebase notes (7.2.0 rc0):
- Disabled cortex-a35
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
@ -29,13 +38,31 @@ Merged patches (7.0.0):
- a1d1b6eeb6 hw/arm/virt: Expose the 'RAS' option
- 47f8fe1b82 hw/arm/virt: Add 9.0 machine type and remove 8.5 one
- ed2346788f hw/arm/virt: Check no_tcg_its and minor style changes
Merged patches (7.0.0):
- f79b31bdef hw/arm/virt: Remove the dtb-kaslr-seed machine option
- b6fca85f4a hw/arm/virt: Fix missing initialization in instance/class_init()
Merged patches (7.1.0 rc0):
- ac97dd4f9f RHEL-only: AArch64: Drop unsupported CPU types
- e9c0a70664 target/arm: deprecate named CPU models
Merged patches (7.2.0 rc0):
- 0be2889fa2 Introduce upstream 7.0 compat changes (only applicable parts)
---
hw/arm/virt.c | 234 +++++++++++++++++++++++++++++++++++++++++-
include/hw/arm/virt.h | 8 ++
2 files changed, 241 insertions(+), 1 deletion(-)
hw/arm/virt.c | 237 ++++++++++++++++++++++++++++++++-
include/hw/arm/virt.h | 8 ++
target/arm/cpu-qom.h | 1 +
target/arm/cpu.c | 5 +
target/arm/cpu.h | 2 +
target/arm/cpu64.c | 16 ++-
target/arm/cpu_tcg.c | 12 +-
target/arm/helper.c | 2 +
tests/qtest/arm-cpu-features.c | 6 +
9 files changed, 277 insertions(+), 12 deletions(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 6a84031fd7..e06862d22a 100644
index d633300fdc..dfcab40a73 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -80,6 +80,7 @@
@ -96,7 +123,27 @@ index 6a84031fd7..e06862d22a 100644
/* Number of external interrupt lines to configure the GIC with */
#define NUM_IRQS 256
@@ -2250,6 +2292,7 @@ static void machvirt_init(MachineState *machine)
@@ -197,15 +239,19 @@ static const int a15irqmap[] = {
};
static const char *valid_cpus[] = {
+#if 0 /* Disabled for Red Hat Enterprise Linux */
ARM_CPU_TYPE_NAME("cortex-a7"),
ARM_CPU_TYPE_NAME("cortex-a15"),
ARM_CPU_TYPE_NAME("cortex-a35"),
ARM_CPU_TYPE_NAME("cortex-a53"),
+#endif /* disabled for RHEL */
ARM_CPU_TYPE_NAME("cortex-a57"),
+#if 0 /* Disabled for Red Hat Enterprise Linux */
ARM_CPU_TYPE_NAME("cortex-a72"),
ARM_CPU_TYPE_NAME("cortex-a76"),
ARM_CPU_TYPE_NAME("a64fx"),
ARM_CPU_TYPE_NAME("neoverse-n1"),
+#endif /* disabled for RHEL */
ARM_CPU_TYPE_NAME("host"),
ARM_CPU_TYPE_NAME("max"),
};
@@ -2290,6 +2336,7 @@ static void machvirt_init(MachineState *machine)
qemu_add_machine_init_done_notifier(&vms->machine_done);
}
@ -104,7 +151,7 @@ index 6a84031fd7..e06862d22a 100644
static bool virt_get_secure(Object *obj, Error **errp)
{
VirtMachineState *vms = VIRT_MACHINE(obj);
@@ -2277,6 +2320,7 @@ static void virt_set_virt(Object *obj, bool value, Error **errp)
@@ -2317,6 +2364,7 @@ static void virt_set_virt(Object *obj, bool value, Error **errp)
vms->virt = value;
}
@ -112,7 +159,23 @@ index 6a84031fd7..e06862d22a 100644
static bool virt_get_highmem(Object *obj, Error **errp)
{
@@ -2402,6 +2446,7 @@ static void virt_set_ras(Object *obj, bool value, Error **errp)
@@ -2346,6 +2394,7 @@ static void virt_set_its(Object *obj, bool value, Error **errp)
vms->its = value;
}
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static bool virt_get_dtb_randomness(Object *obj, Error **errp)
{
VirtMachineState *vms = VIRT_MACHINE(obj);
@@ -2359,6 +2408,7 @@ static void virt_set_dtb_randomness(Object *obj, bool value, Error **errp)
vms->dtb_randomness = value;
}
+#endif /* disabled for RHEL */
static char *virt_get_oem_id(Object *obj, Error **errp)
{
@@ -2442,6 +2492,7 @@ static void virt_set_ras(Object *obj, bool value, Error **errp)
vms->ras = value;
}
@ -120,7 +183,7 @@ index 6a84031fd7..e06862d22a 100644
static bool virt_get_mte(Object *obj, Error **errp)
{
VirtMachineState *vms = VIRT_MACHINE(obj);
@@ -2415,6 +2460,7 @@ static void virt_set_mte(Object *obj, bool value, Error **errp)
@@ -2455,6 +2506,7 @@ static void virt_set_mte(Object *obj, bool value, Error **errp)
vms->mte = value;
}
@ -128,7 +191,7 @@ index 6a84031fd7..e06862d22a 100644
static char *virt_get_gic_version(Object *obj, Error **errp)
{
@@ -2818,6 +2864,7 @@ static int virt_kvm_type(MachineState *ms, const char *type_str)
@@ -2886,6 +2938,7 @@ static int virt_kvm_type(MachineState *ms, const char *type_str)
return fixed_ipa ? 0 : requested_pa_size;
}
@ -136,7 +199,7 @@ index 6a84031fd7..e06862d22a 100644
static void virt_machine_class_init(ObjectClass *oc, void *data)
{
MachineClass *mc = MACHINE_CLASS(oc);
@@ -3206,3 +3253,188 @@ static void virt_machine_2_6_options(MachineClass *mc)
@@ -3294,3 +3347,185 @@ static void virt_machine_2_6_options(MachineClass *mc)
vmc->no_pmu = true;
}
DEFINE_VIRT_MACHINE(2, 6)
@ -171,6 +234,7 @@ index 6a84031fd7..e06862d22a 100644
+ hc->unplug_request = virt_machine_device_unplug_request_cb;
+ hc->unplug = virt_machine_device_unplug_cb;
+ mc->nvdimm_supported = true;
+ mc->smp_props.clusters_supported = true;
+ mc->auto_enable_numa_with_memhp = true;
+ mc->auto_enable_numa_with_memdev = true;
+ mc->default_ram_id = "mach-virt.ram";
@ -233,13 +297,6 @@ index 6a84031fd7..e06862d22a 100644
+ "Override the default value of field OEM Table ID "
+ "in ACPI table header."
+ "The string may be up to 8 bytes in size");
+
+ object_class_property_add_bool(oc, "dtb-kaslr-seed",
+ virt_get_dtb_kaslr_seed,
+ virt_set_dtb_kaslr_seed);
+ object_class_property_set_description(oc, "dtb-kaslr-seed",
+ "Set off to disable passing of kaslr-seed "
+ "dtb node to guest");
+}
+
+static void rhel_virt_instance_init(Object *obj)
@ -258,6 +315,8 @@ index 6a84031fd7..e06862d22a 100644
+ vms->gic_version = VIRT_GIC_VERSION_NOSEL;
+
+ vms->highmem_ecam = !vmc->no_highmem_ecam;
+ vms->highmem_mmio = true;
+ vms->highmem_redists = true;
+
+ if (vmc->no_its) {
+ vms->its = false;
@ -284,8 +343,8 @@ index 6a84031fd7..e06862d22a 100644
+ /* MTE is disabled by default and non-configurable for RHEL */
+ vms->mte = false;
+
+ /* Supply a kaslr-seed by default */
+ vms->dtb_kaslr_seed = true;
+ /* Supply kaslr-seed and rng-seed by default, non-configurable for RHEL */
+ vms->dtb_randomness = true;
+
+ vms->irqmap = a15irqmap;
+
@ -320,16 +379,17 @@ index 6a84031fd7..e06862d22a 100644
+ VirtMachineClass *vmc = VIRT_MACHINE_CLASS(OBJECT_CLASS(mc));
+
+ compat_props_add(mc->compat_props, arm_rhel_compat, arm_rhel_compat_len);
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_1, hw_compat_rhel_9_1_len);
+
+ /* Disable FEAT_LPA2 since old kernels (<= v5.12) don't boot with that feature */
+ vmc->no_tcg_lpa2 = true;
+}
+DEFINE_RHEL_MACHINE_AS_LATEST(9, 0, 0)
diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h
index 7e76ee2619..9b1efe8f0e 100644
index 6ec479ca2b..22b54ec510 100644
--- a/include/hw/arm/virt.h
+++ b/include/hw/arm/virt.h
@@ -179,9 +179,17 @@ struct VirtMachineState {
@@ -180,9 +180,17 @@ struct VirtMachineState {
#define VIRT_ECAM_ID(high) (high ? VIRT_HIGH_PCIE_ECAM : VIRT_PCIE_ECAM)
@ -347,6 +407,269 @@ index 7e76ee2619..9b1efe8f0e 100644
void virt_acpi_setup(VirtMachineState *vms);
bool virt_is_acpi_enabled(VirtMachineState *vms);
diff --git a/target/arm/cpu-qom.h b/target/arm/cpu-qom.h
index 64c44cef2d..82e97249bc 100644
--- a/target/arm/cpu-qom.h
+++ b/target/arm/cpu-qom.h
@@ -35,6 +35,7 @@ typedef struct ARMCPUInfo {
const char *name;
void (*initfn)(Object *obj);
void (*class_init)(ObjectClass *oc, void *data);
+ const char *deprecation_note;
} ARMCPUInfo;
void arm_cpu_register(const ARMCPUInfo *info);
diff --git a/target/arm/cpu.c b/target/arm/cpu.c
index 38d066c294..a845814bfb 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -2250,8 +2250,13 @@ static void arm_cpu_instance_init(Object *obj)
static void cpu_register_class_init(ObjectClass *oc, void *data)
{
ARMCPUClass *acc = ARM_CPU_CLASS(oc);
+ CPUClass *cc = CPU_CLASS(oc);
acc->info = data;
+
+ if (acc->info->deprecation_note) {
+ cc->deprecation_note = acc->info->deprecation_note;
+ }
}
void arm_cpu_register(const ARMCPUInfo *info)
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index 9aeed3c848..f9f504d89e 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -34,6 +34,8 @@
#define KVM_HAVE_MCE_INJECTION 1
#endif
+#define RHEL_CPU_DEPRECATION "use 'host' / 'max'"
+
#define EXCP_UDEF 1 /* undefined instruction */
#define EXCP_SWI 2 /* software interrupt */
#define EXCP_PREFETCH_ABORT 3
diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c
index 3d74f134f5..4b330a52b5 100644
--- a/target/arm/cpu64.c
+++ b/target/arm/cpu64.c
@@ -36,6 +36,7 @@
#include "hw/qdev-properties.h"
#include "internals.h"
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void aarch64_a35_initfn(Object *obj)
{
ARMCPU *cpu = ARM_CPU(obj);
@@ -115,6 +116,7 @@ static void aarch64_a35_initfn(Object *obj)
/* These values are the same with A53/A57/A72. */
define_cortex_a72_a57_a53_cp_reginfo(cpu);
}
+#endif /* disabled for RHEL */
void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp)
{
@@ -735,6 +737,7 @@ static void aarch64_a57_initfn(Object *obj)
define_cortex_a72_a57_a53_cp_reginfo(cpu);
}
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void aarch64_a53_initfn(Object *obj)
{
ARMCPU *cpu = ARM_CPU(obj);
@@ -1033,6 +1036,7 @@ static void aarch64_neoverse_n1_initfn(Object *obj)
/* From D5.1 AArch64 PMU register summary */
cpu->isar.reset_pmcr_el0 = 0x410c3000;
}
+#endif /* disabled for RHEL */
static void aarch64_host_initfn(Object *obj)
{
@@ -1240,13 +1244,18 @@ static void aarch64_max_initfn(Object *obj)
}
static const ARMCPUInfo aarch64_cpus[] = {
+#if 0 /* Disabled for Red Hat Enterprise Linux */
{ .name = "cortex-a35", .initfn = aarch64_a35_initfn },
- { .name = "cortex-a57", .initfn = aarch64_a57_initfn },
+#endif /* disabled for RHEL */
+ { .name = "cortex-a57", .initfn = aarch64_a57_initfn,
+ .deprecation_note = RHEL_CPU_DEPRECATION },
+#if 0 /* Disabled for Red Hat Enterprise Linux */
{ .name = "cortex-a53", .initfn = aarch64_a53_initfn },
{ .name = "cortex-a72", .initfn = aarch64_a72_initfn },
{ .name = "cortex-a76", .initfn = aarch64_a76_initfn },
{ .name = "a64fx", .initfn = aarch64_a64fx_initfn },
{ .name = "neoverse-n1", .initfn = aarch64_neoverse_n1_initfn },
+#endif /* disabled for RHEL */
{ .name = "max", .initfn = aarch64_max_initfn },
#if defined(CONFIG_KVM) || defined(CONFIG_HVF)
{ .name = "host", .initfn = aarch64_host_initfn },
@@ -1318,8 +1327,13 @@ static void aarch64_cpu_instance_init(Object *obj)
static void cpu_register_class_init(ObjectClass *oc, void *data)
{
ARMCPUClass *acc = ARM_CPU_CLASS(oc);
+ CPUClass *cc = CPU_CLASS(oc);
acc->info = data;
+
+ if (acc->info->deprecation_note) {
+ cc->deprecation_note = acc->info->deprecation_note;
+ }
}
void aarch64_cpu_register(const ARMCPUInfo *info)
diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c
index a528ff9a3d..053f70e399 100644
--- a/target/arm/cpu_tcg.c
+++ b/target/arm/cpu_tcg.c
@@ -148,10 +148,10 @@ void define_cortex_a72_a57_a53_cp_reginfo(ARMCPU *cpu)
}
#endif /* !CONFIG_USER_ONLY */
+#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) && defined(CONFIG_TCG)
static bool arm_v7m_cpu_exec_interrupt(CPUState *cs, int interrupt_request)
{
@@ -505,7 +505,6 @@ static void cortex_a9_initfn(Object *obj)
cpu->isar.reset_pmcr_el0 = 0x41093000;
define_arm_cp_regs(cpu, cortexa9_cp_reginfo);
}
-#endif /* disabled for RHEL */
#ifndef CONFIG_USER_ONLY
static uint64_t a15_l2ctlr_read(CPUARMState *env, const ARMCPRegInfo *ri)
@@ -530,7 +529,6 @@ static const ARMCPRegInfo cortexa15_cp_reginfo[] = {
.access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 },
};
-#if 0 /* Disabled for Red Hat Enterprise Linux */
static void cortex_a7_initfn(Object *obj)
{
ARMCPU *cpu = ARM_CPU(obj);
@@ -579,7 +577,6 @@ static void cortex_a7_initfn(Object *obj)
cpu->isar.reset_pmcr_el0 = 0x41072000;
define_arm_cp_regs(cpu, cortexa15_cp_reginfo); /* Same as A15 */
}
-#endif /* disabled for RHEL */
static void cortex_a15_initfn(Object *obj)
{
@@ -628,7 +625,6 @@ static void cortex_a15_initfn(Object *obj)
define_arm_cp_regs(cpu, cortexa15_cp_reginfo);
}
-#if 0 /* Disabled for Red Hat Enterprise Linux */
static void cortex_m0_initfn(Object *obj)
{
ARMCPU *cpu = ARM_CPU(obj);
@@ -1070,7 +1066,6 @@ static void arm_v7m_class_init(ObjectClass *oc, void *data)
cc->gdb_core_xml_file = "arm-m-profile.xml";
}
-#endif /* disabled for RHEL */
#ifndef TARGET_AARCH64
/*
@@ -1138,7 +1133,6 @@ static void arm_max_initfn(Object *obj)
#endif /* !TARGET_AARCH64 */
static const ARMCPUInfo arm_tcg_cpus[] = {
-#if 0 /* Disabled for Red Hat Enterprise Linux */
{ .name = "arm926", .initfn = arm926_initfn },
{ .name = "arm946", .initfn = arm946_initfn },
{ .name = "arm1026", .initfn = arm1026_initfn },
@@ -1154,9 +1148,7 @@ static const ARMCPUInfo arm_tcg_cpus[] = {
{ .name = "cortex-a7", .initfn = cortex_a7_initfn },
{ .name = "cortex-a8", .initfn = cortex_a8_initfn },
{ .name = "cortex-a9", .initfn = cortex_a9_initfn },
-#endif /* disabled for RHEL */
{ .name = "cortex-a15", .initfn = cortex_a15_initfn },
-#if 0 /* Disabled for Red Hat Enterprise Linux */
{ .name = "cortex-m0", .initfn = cortex_m0_initfn,
.class_init = arm_v7m_class_init },
{ .name = "cortex-m3", .initfn = cortex_m3_initfn,
@@ -1187,7 +1179,6 @@ static const ARMCPUInfo arm_tcg_cpus[] = {
{ .name = "pxa270-b1", .initfn = pxa270b1_initfn },
{ .name = "pxa270-c0", .initfn = pxa270c0_initfn },
{ .name = "pxa270-c5", .initfn = pxa270c5_initfn },
-#endif /* disabled for RHEL */
#ifndef TARGET_AARCH64
{ .name = "max", .initfn = arm_max_initfn },
#endif
@@ -1215,3 +1206,4 @@ 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/helper.c b/target/arm/helper.c
index d8c8223ec3..ad9d235773 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -8476,6 +8476,7 @@ void arm_cpu_list(void)
static void arm_cpu_add_definition(gpointer data, gpointer user_data)
{
ObjectClass *oc = data;
+ CPUClass *cc = CPU_CLASS(oc);
CpuDefinitionInfoList **cpu_list = user_data;
CpuDefinitionInfo *info;
const char *typename;
@@ -8485,6 +8486,7 @@ static void arm_cpu_add_definition(gpointer data, gpointer user_data)
info->name = g_strndup(typename,
strlen(typename) - strlen("-" TYPE_ARM_CPU));
info->q_typename = g_strdup(typename);
+ info->deprecated = !!cc->deprecation_note;
QAPI_LIST_PREPEND(*cpu_list, info);
}
diff --git a/tests/qtest/arm-cpu-features.c b/tests/qtest/arm-cpu-features.c
index 5a14527386..a3579fc303 100644
--- a/tests/qtest/arm-cpu-features.c
+++ b/tests/qtest/arm-cpu-features.c
@@ -440,8 +440,10 @@ 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 */
+#if 0 /* Disabled for Red Hat Enterprise Linux */
assert_has_feature_enabled(qts, "cortex-a15", "pmu");
assert_has_not_feature(qts, "cortex-a15", "aarch64");
+#endif /* disabled for RHEL */
/* Enabling and disabling pmu should always work. */
assert_has_feature_enabled(qts, "max", "pmu");
@@ -458,6 +460,7 @@ 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");
+#if 0 /* Disabled for Red Hat Enterprise Linux */
assert_has_feature_enabled(qts, "a64fx", "pmu");
assert_has_feature_enabled(qts, "a64fx", "aarch64");
/*
@@ -470,6 +473,7 @@ static void test_query_cpu_model_expansion(const void *data)
"{ 'sve384': true }");
assert_error(qts, "a64fx", "cannot enable sve640",
"{ 'sve640': true }");
+#endif /* disabled for RHEL */
sve_tests_default(qts, "max");
pauth_tests_default(qts, "max");
@@ -505,9 +509,11 @@ static void test_query_cpu_model_expansion_kvm(const void *data)
QDict *resp;
char *error;
+#if 0 /* Disabled for Red Hat Enterprise Linux */
assert_error(qts, "cortex-a15",
"We cannot guarantee the CPU type 'cortex-a15' works "
"with KVM on this host", NULL);
+#endif /* disabled for RHEL */
assert_has_feature_enabled(qts, "host", "aarch64");
--
2.31.1

60
SOURCES/0008-Add-ppc64-machine-types.patch
View File

@ -1,4 +1,4 @@
From f61b3d7dc000886e23943457ee9baf1d4cae43b4 Mon Sep 17 00:00:00 2001
From 2c523f1b6c9470e1cd517ba99e414cde02727e16 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
@ -19,21 +19,25 @@ Merged patches (6.1.0):
- 0215eb3356 Remove RHEL 7.3.0 machine types (only ppc64 changes)
- af69d1ca6e Remove RHEL 7.4.0 machine types (only ppc64 changes)
- 8f7a74ab78 Remove RHEL 7.5.0 machine types (only ppc64 changes)
Merged patches (7.1.0 rc0):
- baa6790171 target/ppc/cpu-models: Fix ppc_cpu_aliases list for RHEL
---
hw/ppc/spapr.c | 243 ++++++++++++++++++++++++++++++++++++++++
hw/ppc/spapr_cpu_core.c | 13 +++
include/hw/ppc/spapr.h | 4 +
target/ppc/compat.c | 13 ++-
target/ppc/cpu-models.c | 1 +
target/ppc/cpu.h | 1 +
target/ppc/kvm.c | 27 +++++
target/ppc/kvm_ppc.h | 13 +++
7 files changed, 313 insertions(+), 1 deletion(-)
8 files changed, 314 insertions(+), 1 deletion(-)
diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index a4372ba189..5fdf8b506d 100644
index 66b414d2e9..499eb49253 100644
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -1622,6 +1622,9 @@ static void spapr_machine_reset(MachineState *machine)
@@ -1633,6 +1633,9 @@ static void spapr_machine_reset(MachineState *machine, ShutdownCause reason)
pef_kvm_reset(machine->cgs, &error_fatal);
spapr_caps_apply(spapr);
@ -43,7 +47,7 @@ index a4372ba189..5fdf8b506d 100644
first_ppc_cpu = POWERPC_CPU(first_cpu);
if (kvm_enabled() && kvmppc_has_cap_mmu_radix() &&
@@ -3317,6 +3320,20 @@ static void spapr_set_host_serial(Object *obj, const char *value, Error **errp)
@@ -3347,6 +3350,20 @@ static void spapr_set_host_serial(Object *obj, const char *value, Error **errp)
spapr->host_serial = g_strdup(value);
}
@ -64,7 +68,7 @@ index a4372ba189..5fdf8b506d 100644
static void spapr_instance_init(Object *obj)
{
SpaprMachineState *spapr = SPAPR_MACHINE(obj);
@@ -3395,6 +3412,12 @@ static void spapr_instance_init(Object *obj)
@@ -3425,6 +3442,12 @@ 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");
@ -77,7 +81,7 @@ index a4372ba189..5fdf8b506d 100644
}
static void spapr_machine_finalizefn(Object *obj)
@@ -4652,6 +4675,7 @@ static void spapr_machine_class_init(ObjectClass *oc, void *data)
@@ -4682,6 +4705,7 @@ 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;
@ -85,15 +89,15 @@ index a4372ba189..5fdf8b506d 100644
}
static const TypeInfo spapr_machine_info = {
@@ -4703,6 +4727,7 @@ static void spapr_machine_latest_class_options(MachineClass *mc)
@@ -4733,6 +4757,7 @@ static void spapr_machine_latest_class_options(MachineClass *mc)
} \
type_init(spapr_machine_register_##suffix)
+#if 0 /* Disabled for Red Hat Enterprise Linux */
/*
* pseries-7.0
* pseries-7.2
*/
@@ -4830,6 +4855,7 @@ static void spapr_machine_4_1_class_options(MachineClass *mc)
@@ -4882,6 +4907,7 @@ static void spapr_machine_4_1_class_options(MachineClass *mc)
}
DEFINE_SPAPR_MACHINE(4_1, "4.1", false);
@ -101,7 +105,7 @@ index a4372ba189..5fdf8b506d 100644
/*
* pseries-4.0
@@ -4849,6 +4875,8 @@ static bool phb_placement_4_0(SpaprMachineState *spapr, uint32_t index,
@@ -4901,6 +4927,8 @@ static bool phb_placement_4_0(SpaprMachineState *spapr, uint32_t index,
*nv2atsd = 0;
return true;
}
@ -110,7 +114,7 @@ index a4372ba189..5fdf8b506d 100644
static void spapr_machine_4_0_class_options(MachineClass *mc)
{
SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc);
@@ -5176,6 +5204,221 @@ static void spapr_machine_2_1_class_options(MachineClass *mc)
@@ -5228,6 +5256,221 @@ 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);
@ -371,7 +375,7 @@ index fcb5dfe792..ab8fb5bf62 100644
qdev_unrealize(DEVICE(cpu));
return false;
diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h
index f5c33dcc86..4a68e0a901 100644
index 04a95669ab..d5f4cf5e03 100644
--- a/include/hw/ppc/spapr.h
+++ b/include/hw/ppc/spapr.h
@@ -154,6 +154,7 @@ struct SpaprMachineClass {
@ -382,7 +386,7 @@ index f5c33dcc86..4a68e0a901 100644
bool (*phb_placement)(SpaprMachineState *spapr, uint32_t index,
uint64_t *buid, hwaddr *pio,
hwaddr *mmio32, hwaddr *mmio64,
@@ -241,6 +242,9 @@ struct SpaprMachineState {
@@ -256,6 +257,9 @@ struct SpaprMachineState {
/* Set by -boot */
char *boot_device;
@ -417,11 +421,23 @@ index 7949a24f5a..f207a9ba01 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 cd3ff700ac..1cb49c8087 100644
--- a/target/ppc/cpu-models.c
+++ b/target/ppc/cpu-models.c
@@ -746,6 +746,7 @@
/* PowerPC CPU aliases */
PowerPCCPUAlias ppc_cpu_aliases[] = {
+#if 0 /* Disabled for Red Hat Enterprise Linux */
{ "405", "405d4" },
{ "405cr", "405crc" },
{ "405gp", "405gpd" },
diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h
index 047b24ba50..79c5ac50b9 100644
index 81d4263a07..508fbed90b 100644
--- a/target/ppc/cpu.h
+++ b/target/ppc/cpu.h
@@ -1462,6 +1462,7 @@ static inline int cpu_mmu_index(CPUPPCState *env, bool ifetch)
@@ -1467,6 +1467,7 @@ static inline int cpu_mmu_index(CPUPPCState *env, bool ifetch)
/* Compatibility modes */
#if defined(TARGET_PPC64)
@ -430,10 +446,10 @@ index 047b24ba50..79c5ac50b9 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 dc93b99189..154888cce5 100644
index 7c25348b7b..83671c955f 100644
--- a/target/ppc/kvm.c
+++ b/target/ppc/kvm.c
@@ -90,6 +90,7 @@ static int cap_ppc_nested_kvm_hv;
@@ -89,6 +89,7 @@ static int cap_ppc_nested_kvm_hv;
static int cap_large_decr;
static int cap_fwnmi;
static int cap_rpt_invalidate;
@ -441,7 +457,7 @@ index dc93b99189..154888cce5 100644
static uint32_t debug_inst_opcode;
@@ -137,6 +138,7 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
@@ -136,6 +137,7 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
cap_resize_hpt = kvm_vm_check_extension(s, KVM_CAP_SPAPR_RESIZE_HPT);
kvmppc_get_cpu_characteristics(s);
cap_ppc_nested_kvm_hv = kvm_vm_check_extension(s, KVM_CAP_PPC_NESTED_HV);
@ -449,7 +465,7 @@ index dc93b99189..154888cce5 100644
cap_large_decr = kvmppc_get_dec_bits();
cap_fwnmi = kvm_vm_check_extension(s, KVM_CAP_PPC_FWNMI);
/*
@@ -2563,6 +2565,16 @@ int kvmppc_has_cap_rpt_invalidate(void)
@@ -2570,6 +2572,16 @@ int kvmppc_has_cap_rpt_invalidate(void)
return cap_rpt_invalidate;
}
@ -466,9 +482,9 @@ index dc93b99189..154888cce5 100644
PowerPCCPUClass *kvm_ppc_get_host_cpu_class(void)
{
uint32_t host_pvr = mfpvr();
@@ -2959,3 +2971,18 @@ bool kvm_arch_cpu_check_are_resettable(void)
@@ -2970,3 +2982,18 @@ bool kvm_arch_cpu_check_are_resettable(void)
void kvm_arch_accel_class_init(ObjectClass *oc)
{
return true;
}
+
+void kvmppc_svm_allow(Error **errp)

152
SOURCES/0009-Add-s390x-machine-types.patch
View File

@ -1,4 +1,4 @@
From 680f343e58a50a99d17bc7dedd3ee90980912023 Mon Sep 17 00:00:00 2001
From 1973257ed781a93943f27f1518933e8c09c50f88 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
@ -7,6 +7,10 @@ Adding changes to add RHEL machine types for s390x architecture.
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
--
Rebase changes (7.1.0 rc0):
- Moved adding rhel_old_machine_deprecation variable to general machine types commit
Merged patches (6.1.0):
- 64a9a5c971 hw/s390x: Remove the RHEL7-only machine type
- 395516d62b redhat: s390x: add rhel-8.5.0 compat machine
@ -18,62 +22,51 @@ Merged patches (7.0.0):
- e6ff4de4f7 redhat: Add s390x machine type compatibility handling for the rebase to v6.2
- 4b0efa7e21 redhat: Add rhel8.6.0 and rhel9.0.0 machine types for s390x
- dcc64971bf RHEL: mark old machine types as deprecated (partialy)
---
hw/core/machine.c | 6 +++
hw/s390x/s390-virtio-ccw.c | 104 ++++++++++++++++++++++++++++++++++++-
include/hw/boards.h | 2 +
3 files changed, 111 insertions(+), 1 deletion(-)
diff --git a/hw/core/machine.c b/hw/core/machine.c
index ea430d844e..77202a3570 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -37,6 +37,12 @@
#include "hw/virtio/virtio.h"
#include "hw/virtio/virtio-pci.h"
+/*
+ * RHEL only: machine types for previous major releases are deprecated
+ */
+const char *rhel_old_machine_deprecation =
+ "machine types for previous major releases are deprecated";
+
/*
* Mostly the same as hw_compat_6_0 and hw_compat_6_1
*/
Merged patches (7.1.0 rc0):
- 1d6439527a WRB: Introduce RHEL 9.0.0 hw compat structure (only hw/s390x/s390-virtio-ccw.c chunk)
- c8ad21ca31 redhat: Update s390x machine type compatibility for rebase to QEMU 7.0.0
- 5bcf8d874c target/s390x: deprecate CPUs older than z14
Merged patches (7.2.0 rc0):
- 0be2889fa2 Introduce upstream 7.0 compat changes (only applicable parts)
---
hw/s390x/s390-virtio-ccw.c | 108 +++++++++++++++++++++++++++++++
target/s390x/cpu_models.c | 11 ++++
target/s390x/cpu_models.h | 2 +
target/s390x/cpu_models_sysemu.c | 2 +
4 files changed, 123 insertions(+)
diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
index 90480e7cf9..ec4176a1e0 100644
index 2e64ffab45..8d5221fbb1 100644
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -767,7 +767,7 @@ bool css_migration_enabled(void)
{ \
MachineClass *mc = MACHINE_CLASS(oc); \
ccw_machine_##suffix##_class_options(mc); \
- mc->desc = "VirtIO-ccw based S390 machine v" verstr; \
+ mc->desc = "VirtIO-ccw based S390 machine " verstr; \
if (latest) { \
mc->alias = "s390-ccw-virtio"; \
mc->is_default = true; \
@@ -791,6 +791,7 @@ bool css_migration_enabled(void)
@@ -823,6 +823,7 @@ bool css_migration_enabled(void)
} \
type_init(ccw_machine_register_##suffix)
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void ccw_machine_7_0_instance_options(MachineState *machine)
static void ccw_machine_7_2_instance_options(MachineState *machine)
{
}
@@ -1115,6 +1116,107 @@ static void ccw_machine_2_4_class_options(MachineClass *mc)
@@ -1186,6 +1187,113 @@ 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);
+#endif
+
+
+static void ccw_machine_rhel900_instance_options(MachineState *machine)
+{
+ static const S390FeatInit qemu_cpu_feat = { S390_FEAT_LIST_QEMU_V6_2 };
+
+ s390_set_qemu_cpu_model(0x3906, 14, 2, qemu_cpu_feat);
+}
+
+static void ccw_machine_rhel900_class_options(MachineClass *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);
+}
+DEFINE_CCW_MACHINE(rhel900, "rhel9.0.0", true);
+
@ -170,17 +163,84 @@ index 90480e7cf9..ec4176a1e0 100644
static void ccw_machine_register_types(void)
{
diff --git a/include/hw/boards.h b/include/hw/boards.h
index c90a19b4d1..bf59275f18 100644
--- a/include/hw/boards.h
+++ b/include/hw/boards.h
@@ -470,4 +470,6 @@ extern const size_t hw_compat_rhel_8_0_len;
extern GlobalProperty hw_compat_rhel_7_6[];
extern const size_t hw_compat_rhel_7_6_len;
+extern const char *rhel_old_machine_deprecation;
diff --git a/target/s390x/cpu_models.c b/target/s390x/cpu_models.c
index c3a4f80633..739770dc15 100644
--- a/target/s390x/cpu_models.c
+++ b/target/s390x/cpu_models.c
@@ -45,6 +45,9 @@
* of a following release have been a superset of the previous release. With
* generation 15 one base feature and one optional feature have been deprecated.
*/
+
#endif
+#define RHEL_CPU_DEPRECATION "use at least 'z14', or 'host' / 'qemu' / 'max'"
+
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"),
@@ -854,22 +857,30 @@ 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);
+ CPUClass *cc = CPU_CLASS(oc);
/* all base models are migration safe */
xcc->cpu_def = (const S390CPUDef *) data;
xcc->is_migration_safe = true;
xcc->is_static = true;
xcc->desc = xcc->cpu_def->desc;
+ if (xcc->cpu_def->gen < 14) {
+ cc->deprecation_note = RHEL_CPU_DEPRECATION;
+ }
}
static void s390_cpu_model_class_init(ObjectClass *oc, void *data)
{
S390CPUClass *xcc = S390_CPU_CLASS(oc);
+ CPUClass *cc = CPU_CLASS(oc);
/* model that can change between QEMU versions */
xcc->cpu_def = (const S390CPUDef *) data;
xcc->is_migration_safe = true;
xcc->desc = xcc->cpu_def->desc;
+ if (xcc->cpu_def->gen < 14) {
+ cc->deprecation_note = RHEL_CPU_DEPRECATION;
+ }
}
static void s390_qemu_cpu_model_class_init(ObjectClass *oc, void *data)
diff --git a/target/s390x/cpu_models.h b/target/s390x/cpu_models.h
index fb1adc8b21..d76745afa9 100644
--- a/target/s390x/cpu_models.h
+++ b/target/s390x/cpu_models.h
@@ -38,6 +38,8 @@ struct S390CPUDef {
S390FeatBitmap full_feat;
/* used to init full_feat from generated data */
S390FeatInit full_init;
+ /* if deprecated, provides a suggestion */
+ const char *deprecation_note;
};
/* CPU model based on a CPU definition */
diff --git a/target/s390x/cpu_models_sysemu.c b/target/s390x/cpu_models_sysemu.c
index d086b1c39c..1b9cc66405 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)
CpuDefinitionInfo *info;
char *name = g_strdup(object_class_get_name(klass));
S390CPUClass *scc = S390_CPU_CLASS(klass);
+ CPUClass *cc = CPU_CLASS(klass);
/* 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)
info->migration_safe = scc->is_migration_safe;
info->q_static = scc->is_static;
info->q_typename = g_strdup(object_class_get_name(klass));
+ info->deprecated = !!cc->deprecation_note;
/* check for unavailable features */
if (cpu_list_data->model) {
Object *obj;
--
2.31.1

288
SOURCES/0010-Add-x86_64-machine-types.patch
View File

@ -1,4 +1,4 @@
From 427a575ca57966bc72e1ebf218081da530d435d7 Mon Sep 17 00:00:00 2001
From 0935624ccdddc286d6eeeb0c1b70d78983c21aa2 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
@ -31,45 +31,32 @@ Merged patches (7.0.0):
- 6110d865e5 x86: Add q35 RHEL 9.0.0 machine type
- dcc64971bf RHEL: mark old machine types as deprecated (partialy)
- 6b396f182b RHEL: disable "seqpacket" for "vhost-vsock-device" in rhel8.6.0
Merged patches (7.1.0 rc0):
- 38b89dc245 pc: Move s3/s4 suspend disabling to compat (only hw/i386/pc.c chunk)
- 1d6439527a WRB: Introduce RHEL 9.0.0 hw compat structure (x86_64 specific changes)
- 35b5c8554f target/i386: deprecate CPUs older than x86_64-v2 ABI
Merged patches (7.2.0 rc0):
- 0be2889fa2 Introduce upstream 7.0 compat changes (only applicable parts)
---
hw/core/machine.c | 10 ++
hw/i386/pc.c | 135 +++++++++++++++++++++-
hw/i386/pc_piix.c | 79 ++++++++++++-
hw/i386/pc_q35.c | 227 ++++++++++++++++++++++++++++++++++++-
hw/i386/pc.c | 147 ++++++++++++++++++++++-
hw/i386/pc_piix.c | 86 +++++++++++++-
hw/i386/pc_q35.c | 234 ++++++++++++++++++++++++++++++++++++-
hw/s390x/s390-virtio-ccw.c | 1 +
include/hw/boards.h | 5 +
include/hw/i386/pc.h | 24 ++++
include/hw/boards.h | 2 +
include/hw/i386/pc.h | 27 +++++
target/i386/cpu.c | 21 ++++
target/i386/kvm/kvm-cpu.c | 1 +
target/i386/kvm/kvm.c | 4 +
tests/qtest/pvpanic-test.c | 5 +-
10 files changed, 484 insertions(+), 7 deletions(-)
10 files changed, 521 insertions(+), 7 deletions(-)
diff --git a/hw/core/machine.c b/hw/core/machine.c
index 77202a3570..28989b6e7b 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -43,6 +43,16 @@
const char *rhel_old_machine_deprecation =
"machine types for previous major releases are deprecated";
+GlobalProperty hw_compat_rhel_8_6[] = {
+ /* hw_compat_rhel_8_6 bz 2065589 */
+ /*
+ * vhost-vsock device in RHEL 8 kernels doesn't support seqpacket, so
+ * we need do disable it downstream on the latest hw_compat_rhel_8.
+ */
+ { "vhost-vsock-device", "seqpacket", "off" },
+};
+const size_t hw_compat_rhel_8_6_len = G_N_ELEMENTS(hw_compat_rhel_8_6);
+
/*
* Mostly the same as hw_compat_6_0 and hw_compat_6_1
*/
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index fd55fc725c..263d882af6 100644
index 546b703cb4..c7b1350e64 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -375,6 +375,137 @@ GlobalProperty pc_compat_1_4[] = {
@@ -393,6 +393,149 @@ GlobalProperty pc_compat_1_4[] = {
};
const size_t pc_compat_1_4_len = G_N_ELEMENTS(pc_compat_1_4);
@ -78,6 +65,12 @@ index fd55fc725c..263d882af6 100644
+ * machine type.
+ */
+GlobalProperty pc_rhel_compat[] = {
+ /* we don't support s3/s4 suspend */
+ { "PIIX4_PM", "disable_s3", "1" },
+ { "PIIX4_PM", "disable_s4", "1" },
+ { "ICH9-LPC", "disable_s3", "1" },
+ { "ICH9-LPC", "disable_s4", "1" },
+
+ { TYPE_X86_CPU, "host-phys-bits", "on" },
+ { TYPE_X86_CPU, "host-phys-bits-limit", "48" },
+ { TYPE_X86_CPU, "vmx-entry-load-perf-global-ctrl", "off" },
@ -89,6 +82,12 @@ index fd55fc725c..263d882af6 100644
+};
+const size_t pc_rhel_compat_len = G_N_ELEMENTS(pc_rhel_compat);
+
+GlobalProperty pc_rhel_9_0_compat[] = {
+ /* pc_rhel_9_0_compat from pc_compat_6_2 */
+ { "virtio-mem", "unplugged-inaccessible", "off" },
+};
+const size_t pc_rhel_9_0_compat_len = G_N_ELEMENTS(pc_rhel_9_0_compat);
+
+GlobalProperty pc_rhel_8_5_compat[] = {
+ /* pc_rhel_8_5_compat from pc_compat_6_0 */
+ { "qemu64" "-" TYPE_X86_CPU, "family", "6" },
@ -207,7 +206,7 @@ index fd55fc725c..263d882af6 100644
GSIState *pc_gsi_create(qemu_irq **irqs, bool pci_enabled)
{
GSIState *s;
@@ -1738,6 +1869,7 @@ static void pc_machine_class_init(ObjectClass *oc, void *data)
@@ -1907,6 +2050,7 @@ static void pc_machine_class_init(ObjectClass *oc, void *data)
pcmc->pvh_enabled = true;
pcmc->kvmclock_create_always = true;
assert(!mc->get_hotplug_handler);
@ -215,7 +214,7 @@ index fd55fc725c..263d882af6 100644
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;
@@ -1748,7 +1880,8 @@ static void pc_machine_class_init(ObjectClass *oc, void *data)
@@ -1917,7 +2061,8 @@ 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;
@ -226,10 +225,10 @@ index fd55fc725c..263d882af6 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 c797e98312..0cacc0d623 100644
index 0985ff67d2..173a1fd10b 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -50,6 +50,7 @@
@@ -53,6 +53,7 @@
#include "qapi/error.h"
#include "qemu/error-report.h"
#include "sysemu/xen.h"
@ -237,7 +236,7 @@ index c797e98312..0cacc0d623 100644
#ifdef CONFIG_XEN
#include <xen/hvm/hvm_info_table.h>
#include "hw/xen/xen_pt.h"
@@ -174,8 +175,8 @@ static void pc_init1(MachineState *machine,
@@ -184,8 +185,8 @@ static void pc_init1(MachineState *machine,
if (pcmc->smbios_defaults) {
MachineClass *mc = MACHINE_GET_CLASS(machine);
/* These values are guest ABI, do not change */
@ -248,7 +247,7 @@ index c797e98312..0cacc0d623 100644
pcmc->smbios_uuid_encoded,
pcmc->smbios_stream_product,
pcmc->smbios_stream_version,
@@ -314,6 +315,7 @@ static void pc_init1(MachineState *machine,
@@ -334,6 +335,7 @@ static void pc_init1(MachineState *machine,
* hw_compat_*, pc_compat_*, or * pc_*_machine_options().
*/
@ -256,7 +255,7 @@ index c797e98312..0cacc0d623 100644
static void pc_compat_2_3_fn(MachineState *machine)
{
X86MachineState *x86ms = X86_MACHINE(machine);
@@ -967,3 +969,76 @@ static void xenfv_3_1_machine_options(MachineClass *m)
@@ -896,3 +898,83 @@ 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
@ -305,6 +304,13 @@ index c797e98312..0cacc0d623 100644
+ pcmc->kvmclock_create_always = false;
+ /* From pc_i440fx_5_1_machine_options() */
+ pcmc->pci_root_uid = 1;
+ pcmc->legacy_no_rng_seed = true;
+ compat_props_add(m->compat_props, hw_compat_rhel_9_1,
+ hw_compat_rhel_9_1_len);
+ compat_props_add(m->compat_props, hw_compat_rhel_9_0,
+ hw_compat_rhel_9_0_len);
+ compat_props_add(m->compat_props, pc_rhel_9_0_compat,
+ pc_rhel_9_0_compat_len);
+ compat_props_add(m->compat_props, hw_compat_rhel_8_6,
+ hw_compat_rhel_8_6_len);
+ compat_props_add(m->compat_props, hw_compat_rhel_8_5,
@ -334,10 +340,10 @@ index c797e98312..0cacc0d623 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 b695f88c45..157160e069 100644
index ea582254e3..97c3630021 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -197,8 +197,8 @@ static void pc_q35_init(MachineState *machine)
@@ -198,8 +198,8 @@ static void pc_q35_init(MachineState *machine)
if (pcmc->smbios_defaults) {
/* These values are guest ABI, do not change */
@ -348,7 +354,7 @@ index b695f88c45..157160e069 100644
pcmc->smbios_uuid_encoded,
pcmc->smbios_stream_product,
pcmc->smbios_stream_version,
@@ -342,6 +342,7 @@ static void pc_q35_init(MachineState *machine)
@@ -352,6 +352,7 @@ static void pc_q35_init(MachineState *machine)
DEFINE_PC_MACHINE(suffix, name, pc_init_##suffix, optionfn)
@ -356,7 +362,7 @@ index b695f88c45..157160e069 100644
static void pc_q35_machine_options(MachineClass *m)
{
PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
@@ -631,3 +632,225 @@ static void pc_q35_2_4_machine_options(MachineClass *m)
@@ -666,3 +667,232 @@ 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);
@ -397,6 +403,13 @@ index b695f88c45..157160e069 100644
+ m->desc = "RHEL-9.0.0 PC (Q35 + ICH9, 2009)";
+ pcmc->smbios_stream_product = "RHEL";
+ pcmc->smbios_stream_version = "9.0.0";
+ pcmc->legacy_no_rng_seed = true;
+ compat_props_add(m->compat_props, hw_compat_rhel_9_1,
+ hw_compat_rhel_9_1_len);
+ compat_props_add(m->compat_props, hw_compat_rhel_9_0,
+ hw_compat_rhel_9_0_len);
+ compat_props_add(m->compat_props, pc_rhel_9_0_compat,
+ pc_rhel_9_0_compat_len);
+}
+
+DEFINE_PC_MACHINE(q35_rhel900, "pc-q35-rhel9.0.0", pc_q35_init_rhel900,
@ -583,10 +596,10 @@ index b695f88c45..157160e069 100644
+DEFINE_PC_MACHINE(q35_rhel760, "pc-q35-rhel7.6.0", pc_q35_init_rhel760,
+ pc_q35_machine_rhel760_options);
diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
index ec4176a1e0..465a2a09d2 100644
index 8d5221fbb1..ba640e3d9e 100644
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -1136,6 +1136,7 @@ static void ccw_machine_rhel860_instance_options(MachineState *machine)
@@ -1213,6 +1213,7 @@ static void ccw_machine_rhel860_instance_options(MachineState *machine)
static void ccw_machine_rhel860_class_options(MachineClass *mc)
{
ccw_machine_rhel900_class_options(mc);
@ -595,7 +608,7 @@ index ec4176a1e0..465a2a09d2 100644
/* All RHEL machines for prior major releases are deprecated */
mc->deprecation_reason = rhel_old_machine_deprecation;
diff --git a/include/hw/boards.h b/include/hw/boards.h
index bf59275f18..d1555665df 100644
index 2209d4e416..fd75f551b1 100644
--- a/include/hw/boards.h
+++ b/include/hw/boards.h
@@ -266,6 +266,8 @@ struct MachineClass {
@ -607,27 +620,20 @@ index bf59275f18..d1555665df 100644
bool ignore_boot_device_suffixes;
bool smbus_no_migration_support;
bool nvdimm_supported;
@@ -449,6 +451,9 @@ 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_8_6[];
+extern const size_t hw_compat_rhel_8_6_len;
+
extern GlobalProperty hw_compat_rhel_8_5[];
extern const size_t hw_compat_rhel_8_5_len;
diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h
index 91331059d9..419a6ec24b 100644
index 3754eaa97d..4266fe2fdb 100644
--- a/include/hw/i386/pc.h
+++ b/include/hw/i386/pc.h
@@ -289,6 +289,30 @@ extern const size_t pc_compat_1_5_len;
@@ -293,6 +293,33 @@ extern const size_t pc_compat_1_5_len;
extern GlobalProperty pc_compat_1_4[];
extern const size_t pc_compat_1_4_len;
+extern GlobalProperty pc_rhel_compat[];
+extern const size_t pc_rhel_compat_len;
+
+extern GlobalProperty pc_rhel_9_0_compat[];
+extern const size_t pc_rhel_9_0_compat_len;
+
+extern GlobalProperty pc_rhel_8_5_compat[];
+extern const size_t pc_rhel_8_5_compat_len;
+
@ -649,11 +655,165 @@ index 91331059d9..419a6ec24b 100644
+extern GlobalProperty pc_rhel_7_6_compat[];
+extern const size_t pc_rhel_7_6_compat_len;
+
/* Helper for setting model-id for CPU models that changed model-id
* depending on QEMU versions up to QEMU 2.4.
#define DEFINE_PC_MACHINE(suffix, namestr, initfn, optsfn) \
static void pc_machine_##suffix##_class_init(ObjectClass *oc, void *data) \
{ \
diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index 22b681ca37..f7c526cbe6 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -1832,9 +1832,13 @@ static const CPUCaches epyc_milan_cache_info = {
* PT in VMX operation
*/
+#define RHEL_CPU_DEPRECATION \
+ "use at least 'Nehalem' / 'Opteron_G4', or 'host' / 'max'"
+
static const X86CPUDefinition builtin_x86_defs[] = {
{
.name = "qemu64",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 0xd,
.vendor = CPUID_VENDOR_AMD,
.family = 15,
@@ -1855,6 +1859,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "phenom",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 5,
.vendor = CPUID_VENDOR_AMD,
.family = 16,
@@ -1887,6 +1892,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "core2duo",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 10,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -1929,6 +1935,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "kvm64",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 0xd,
.vendor = CPUID_VENDOR_INTEL,
.family = 15,
@@ -1970,6 +1977,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "qemu32",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 4,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -1984,6 +1992,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "kvm32",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 5,
.vendor = CPUID_VENDOR_INTEL,
.family = 15,
@@ -2014,6 +2023,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "coreduo",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 10,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -2047,6 +2057,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "486",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 1,
.vendor = CPUID_VENDOR_INTEL,
.family = 4,
@@ -2059,6 +2070,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "pentium",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 1,
.vendor = CPUID_VENDOR_INTEL,
.family = 5,
@@ -2071,6 +2083,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "pentium2",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 2,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -2083,6 +2096,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "pentium3",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 3,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -2095,6 +2109,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "athlon",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 2,
.vendor = CPUID_VENDOR_AMD,
.family = 6,
@@ -2110,6 +2125,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "n270",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 10,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -2135,6 +2151,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "Conroe",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 10,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -2175,6 +2192,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "Penryn",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 10,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -3762,6 +3780,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "Opteron_G1",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 5,
.vendor = CPUID_VENDOR_AMD,
.family = 15,
@@ -3782,6 +3801,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "Opteron_G2",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 5,
.vendor = CPUID_VENDOR_AMD,
.family = 15,
@@ -3804,6 +3824,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "Opteron_G3",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 5,
.vendor = CPUID_VENDOR_AMD,
.family = 16,
diff --git a/target/i386/kvm/kvm-cpu.c b/target/i386/kvm/kvm-cpu.c
index 5eb955ce9a..74c1396a93 100644
index 7237378a7d..7b8a3d5af0 100644
--- a/target/i386/kvm/kvm-cpu.c
+++ b/target/i386/kvm/kvm-cpu.c
@@ -137,6 +137,7 @@ static PropValue kvm_default_props[] = {
@ -665,10 +825,10 @@ index 5eb955ce9a..74c1396a93 100644
};
diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
index 9cf8e03669..6d1e009443 100644
index a213209379..81526a1575 100644
--- a/target/i386/kvm/kvm.c
+++ b/target/i386/kvm/kvm.c
@@ -3488,6 +3488,7 @@ static int kvm_get_msrs(X86CPU *cpu)
@@ -3707,6 +3707,7 @@ 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;
@ -676,7 +836,7 @@ index 9cf8e03669..6d1e009443 100644
kvm_msr_buf_reset(cpu);
@@ -3822,6 +3823,9 @@ static int kvm_get_msrs(X86CPU *cpu)
@@ -4062,6 +4063,9 @@ static int kvm_get_msrs(X86CPU *cpu)
break;
case MSR_KVM_ASYNC_PF_EN:
env->async_pf_en_msr = msrs[i].data;
@ -687,7 +847,7 @@ index 9cf8e03669..6d1e009443 100644
case MSR_KVM_ASYNC_PF_INT:
env->async_pf_int_msr = msrs[i].data;
diff --git a/tests/qtest/pvpanic-test.c b/tests/qtest/pvpanic-test.c
index 6dcad2db49..580c2c43d2 100644
index bc7b7dfc39..96e6dee3a1 100644
--- a/tests/qtest/pvpanic-test.c
+++ b/tests/qtest/pvpanic-test.c
@@ -17,7 +17,7 @@ static void test_panic_nopause(void)

115
SOURCES/0011-Enable-make-check.patch
View File

@ -1,4 +1,4 @@
From 5e419e5e0a721bdbbfa6d9b82c8be5c5b3d26a01 Mon Sep 17 00:00:00 2001
From badfb1290c8eea8a2e1769b2392c7899d5077698 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
@ -24,22 +24,88 @@ Rebase changes (7.0.0):
- Remove unnecessary changes in iotest 051
- Remove changes in bios-tables-test.c and prom-env-test.c qtests
Rebase changes (7.1.0 rc0):
- Disable bcm2835-dma-test (added upstream)
Merged patches (6.1.0):
- 2f129df7d3 redhat: Enable the 'test-block-iothread' test again
Merged patches (7.1.0 rc0):
- 64d736640e RHEL-only: tests/avocado: Switch aarch64 tests from a53 to a57
---
.distro/qemu-kvm.spec.template | 5 ++---
tests/avocado/replay_kernel.py | 2 +-
tests/avocado/reverse_debugging.py | 2 +-
tests/avocado/tcg_plugins.py | 6 +++---
tests/qtest/fuzz-e1000e-test.c | 2 +-
tests/qtest/fuzz-virtio-scsi-test.c | 2 +-
tests/qtest/intel-hda-test.c | 2 +-
tests/qtest/libqos/meson.build | 2 +-
tests/qtest/lpc-ich9-test.c | 2 +-
tests/qtest/meson.build | 4 ----
tests/qtest/meson.build | 7 +------
tests/qtest/usb-hcd-xhci-test.c | 4 ++++
tests/qtest/virtio-net-failover.c | 1 +
9 files changed, 12 insertions(+), 12 deletions(-)
12 files changed, 18 insertions(+), 19 deletions(-)
diff --git a/tests/avocado/replay_kernel.py b/tests/avocado/replay_kernel.py
index 00a26e4a0c..fe5ecf238a 100644
--- a/tests/avocado/replay_kernel.py
+++ b/tests/avocado/replay_kernel.py
@@ -147,7 +147,7 @@ def test_aarch64_virt(self):
"""
:avocado: tags=arch:aarch64
:avocado: tags=machine:virt
- :avocado: tags=cpu:cortex-a53
+ :avocado: tags=cpu:cortex-a57
"""
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 d2921e70c3..66d185ed42 100644
--- a/tests/avocado/reverse_debugging.py
+++ b/tests/avocado/reverse_debugging.py
@@ -198,7 +198,7 @@ def test_aarch64_virt(self):
"""
:avocado: tags=arch:aarch64
:avocado: tags=machine:virt
- :avocado: tags=cpu:cortex-a53
+ :avocado: tags=cpu:cortex-a57
"""
kernel_url = ('https://archives.fedoraproject.org/pub/archive/fedora'
'/linux/releases/29/Everything/aarch64/os/images/pxeboot'
diff --git a/tests/avocado/tcg_plugins.py b/tests/avocado/tcg_plugins.py
index 642d2e49e3..93b3afd823 100644
--- a/tests/avocado/tcg_plugins.py
+++ b/tests/avocado/tcg_plugins.py
@@ -68,7 +68,7 @@ def test_aarch64_virt_insn(self):
:avocado: tags=accel:tcg
:avocado: tags=arch:aarch64
:avocado: tags=machine:virt
- :avocado: tags=cpu:cortex-a53
+ :avocado: tags=cpu:cortex-a57
"""
kernel_path = self._grab_aarch64_kernel()
kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE +
@@ -94,7 +94,7 @@ def test_aarch64_virt_insn_icount(self):
:avocado: tags=accel:tcg
:avocado: tags=arch:aarch64
:avocado: tags=machine:virt
- :avocado: tags=cpu:cortex-a53
+ :avocado: tags=cpu:cortex-a57
"""
kernel_path = self._grab_aarch64_kernel()
kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE +
@@ -120,7 +120,7 @@ def test_aarch64_virt_mem_icount(self):
:avocado: tags=accel:tcg
:avocado: tags=arch:aarch64
:avocado: tags=machine:virt
- :avocado: tags=cpu:cortex-a53
+ :avocado: tags=cpu:cortex-a57
"""
kernel_path = self._grab_aarch64_kernel()
kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE +
diff --git a/tests/qtest/fuzz-e1000e-test.c b/tests/qtest/fuzz-e1000e-test.c
index 66229e6096..947fba73b7 100644
index 5052883fb6..b5286f4b12 100644
--- a/tests/qtest/fuzz-e1000e-test.c
+++ b/tests/qtest/fuzz-e1000e-test.c
@@ -17,7 +17,7 @@ static void test_lp1879531_eth_get_rss_ex_dst_addr(void)
@ -52,20 +118,20 @@ index 66229e6096..947fba73b7 100644
qtest_outl(s, 0xcf8, 0x80001010);
qtest_outl(s, 0xcfc, 0xe1020000);
diff --git a/tests/qtest/fuzz-virtio-scsi-test.c b/tests/qtest/fuzz-virtio-scsi-test.c
index aaf6d10e18..43727d62ac 100644
index e37b48b2cc..88647da054 100644
--- a/tests/qtest/fuzz-virtio-scsi-test.c
+++ b/tests/qtest/fuzz-virtio-scsi-test.c
@@ -19,7 +19,7 @@ static void test_mmio_oob_from_memory_region_cache(void)
{
QTestState *s;
- s = qtest_init("-M pc-q35-5.2 -display none -m 512M "
+ s = qtest_init("-M pc-q35-rhel8.4.0 -display none -m 512M "
- s = qtest_init("-M pc-q35-5.2 -m 512M "
+ s = qtest_init("-M pc-q35-rhel8.4.0 -m 512M "
"-device virtio-scsi,num_queues=8,addr=03.0 ");
qtest_outl(s, 0xcf8, 0x80001811);
diff --git a/tests/qtest/intel-hda-test.c b/tests/qtest/intel-hda-test.c
index a58c98e4d1..c8387e39ce 100644
index d4a8db6fd6..1a796ec15a 100644
--- a/tests/qtest/intel-hda-test.c
+++ b/tests/qtest/intel-hda-test.c
@@ -38,7 +38,7 @@ static void test_issue542_ich6(void)
@ -78,20 +144,20 @@ index a58c98e4d1..c8387e39ce 100644
qtest_outl(s, 0xcf8, 0x80000804);
diff --git a/tests/qtest/libqos/meson.build b/tests/qtest/libqos/meson.build
index e988d15791..46f7dcb81a 100644
index 32f028872c..1e78a1a055 100644
--- a/tests/qtest/libqos/meson.build
+++ b/tests/qtest/libqos/meson.build
@@ -41,7 +41,7 @@ libqos_srcs = files('../libqtest.c',
@@ -43,7 +43,7 @@ libqos_srcs = files(
'virtio-rng.c',
'virtio-scsi.c',
'virtio-serial.c',
- 'virtio-iommu.c',
+# 'virtio-iommu.c',
'virtio-gpio.c',
'generic-pcihost.c',
# qgraph machines:
'aarch64-xlnx-zcu102-machine.c',
diff --git a/tests/qtest/lpc-ich9-test.c b/tests/qtest/lpc-ich9-test.c
index fe0bef9980..7a9d51579b 100644
index 8ac95b89f7..cd2102555c 100644
--- a/tests/qtest/lpc-ich9-test.c
+++ b/tests/qtest/lpc-ich9-test.c
@@ -15,7 +15,7 @@ static void test_lp1878642_pci_bus_get_irq_level_assert(void)
@ -104,18 +170,18 @@ index fe0bef9980..7a9d51579b 100644
qtest_outl(s, 0xcf8, 0x8000f840); /* PMBASE */
diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build
index d25f82bb5a..67cd32def1 100644
index c07a5b1a5f..9df3f9f8b9 100644
--- a/tests/qtest/meson.build
+++ b/tests/qtest/meson.build
@@ -73,7 +73,6 @@ qtests_i386 = \
@@ -82,7 +82,6 @@ qtests_i386 = \
config_all_devices.has_key('CONFIG_Q35') and \
config_all_devices.has_key('CONFIG_VIRTIO_PCI') and \
slirp.found() ? ['virtio-net-failover'] : []) + \
- (unpack_edk2_blobs ? ['bios-tables-test'] : []) + \
qtests_pci + \
qtests_cxl + \
['fdc-test',
'ide-test',
@@ -86,7 +85,6 @@ qtests_i386 = \
@@ -96,7 +95,6 @@ qtests_i386 = \
'drive_del-test',
'tco-test',
'cpu-plug-test',
@ -123,7 +189,7 @@ index d25f82bb5a..67cd32def1 100644
'vmgenid-test',
'migration-test',
'test-x86-cpuid-compat',
@@ -216,7 +214,6 @@ qtests_arm = \
@@ -209,15 +207,13 @@ qtests_arm = \
# TODO: once aarch64 TCG is fixed on ARM 32 bit host, make bios-tables-test unconditional
qtests_aarch64 = \
@ -131,7 +197,16 @@ index d25f82bb5a..67cd32def1 100644
(config_all_devices.has_key('CONFIG_TPM_TIS_SYSBUS') ? ['tpm-tis-device-test'] : []) + \
(config_all_devices.has_key('CONFIG_TPM_TIS_SYSBUS') ? ['tpm-tis-device-swtpm-test'] : []) + \
(config_all_devices.has_key('CONFIG_XLNX_ZYNQMP_ARM') ? ['xlnx-can-test', 'fuzz-xlnx-dp-test'] : []) + \
@@ -231,7 +228,6 @@ qtests_s390x = \
['arm-cpu-features',
'numa-test',
'boot-serial-test',
- 'migration-test',
- 'bcm2835-dma-test']
+ 'migration-test']
qtests_s390x = \
(slirp.found() ? ['pxe-test', 'test-netfilter'] : []) + \
@@ -225,7 +221,6 @@ qtests_s390x = \
(config_host.has_key('CONFIG_POSIX') ? ['test-filter-redirector'] : []) + \
['boot-serial-test',
'drive_del-test',
@ -170,7 +245,7 @@ index 10ef9d2a91..3855873050 100644
qtest_start("-device nec-usb-xhci,id=xhci"
diff --git a/tests/qtest/virtio-net-failover.c b/tests/qtest/virtio-net-failover.c
index 78811f1c92..44de8af00c 100644
index 4a809590bf..1bf3fa641c 100644
--- a/tests/qtest/virtio-net-failover.c
+++ b/tests/qtest/virtio-net-failover.c
@@ -25,6 +25,7 @@

22
SOURCES/0012-vfio-cap-number-of-devices-that-can-be-assigned.patch
View File

@ -1,4 +1,4 @@
From c358fd4c224a9c3f64b4a8fff34cc6b1dc201fa0 Mon Sep 17 00:00:00 2001
From 0804844e4755377be6d2ebad578794ad9f4f3f31 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
@ -32,20 +32,20 @@ Signed-off-by: Bandan Das <bsd@redhat.com>
2 files changed, 29 insertions(+), 1 deletion(-)
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 67a183f17b..1e20f9fd59 100644
index 939dcc3d4a..acbc6673ce 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -45,6 +45,9 @@
#define TYPE_VFIO_PCI_NOHOTPLUG "vfio-pci-nohotplug"
@@ -48,6 +48,9 @@
/* Protected by BQL */
static KVMRouteChange vfio_route_change;
+/* RHEL only: Set once for the first assigned dev */
+static uint16_t device_limit;
+
static void vfio_disable_interrupts(VFIOPCIDevice *vdev);
static void vfio_mmap_set_enabled(VFIOPCIDevice *vdev, bool enabled);
@@ -2810,9 +2813,30 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
static void vfio_msi_disable_common(VFIOPCIDevice *vdev);
@@ -2854,9 +2857,30 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
ssize_t len;
struct stat st;
int groupid;
@ -74,10 +74,10 @@ index 67a183f17b..1e20f9fd59 100644
+ return;
+ }
+
if (!vdev->vbasedev.sysfsdev) {
if (!vbasedev->sysfsdev) {
if (!(~vdev->host.domain || ~vdev->host.bus ||
~vdev->host.slot || ~vdev->host.function)) {
@@ -3249,6 +3273,9 @@ static Property vfio_pci_dev_properties[] = {
@@ -3293,6 +3317,9 @@ 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),
@ -88,10 +88,10 @@ index 67a183f17b..1e20f9fd59 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 64777516d1..e0fe6ca97e 100644
index 7c236a52f4..7b7d036a8f 100644
--- a/hw/vfio/pci.h
+++ b/hw/vfio/pci.h
@@ -139,6 +139,7 @@ struct VFIOPCIDevice {
@@ -140,6 +140,7 @@ struct VFIOPCIDevice {
EventNotifier err_notifier;
EventNotifier req_notifier;
int (*resetfn)(struct VFIOPCIDevice *);

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

@ -1,4 +1,4 @@
From ba0c7a5f6b9a1f75666db6b3b795ddf03695dc26 Mon Sep 17 00:00:00 2001
From 283a0e258dc2f3b83c58e6f948bafe430cd2c1d5 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/softmmu/vl.c b/softmmu/vl.c
index 6f646531a0..9d5dab43d2 100644
index 5115221efe..17188df528 100644
--- a/softmmu/vl.c
+++ b/softmmu/vl.c
@@ -831,9 +831,17 @@ static void version(void)
@@ -834,9 +834,17 @@ static void version(void)
QEMU_COPYRIGHT "\n");
}
@ -42,7 +42,7 @@ index 6f646531a0..9d5dab43d2 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());
@@ -859,6 +867,7 @@ static void help(int exitcode)
@@ -862,6 +870,7 @@ static void help(int exitcode)
"\n"
QEMU_HELP_BOTTOM "\n");

8
SOURCES/0015-Use-qemu-kvm-in-documentation-instead-of-qemu-system.patch → SOURCES/0014-Use-qemu-kvm-in-documentation-instead-of-qemu-system.patch
View File

@ -1,4 +1,4 @@
From 4b6c8cdc52fdf94d4098d278defb3833dce1d189 Mon Sep 17 00:00:00 2001
From d8ded821aa698b3b03bd9089fbd6c2b33da87b9e 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 34e9b32a5c..924f61ab6d 100644
index 7f99d15b23..ea02ca3a45 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -3233,11 +3233,11 @@ SRST
@@ -3300,11 +3300,11 @@ SRST
::
@ -54,7 +54,7 @@ index 34e9b32a5c..924f61ab6d 100644
+ -netdev type=vhost-user,id=net0,chardev=chr0 \
+ -device virtio-net-pci,netdev=net0
``-netdev vhost-vdpa,vhostdev=/path/to/dev``
``-netdev vhost-vdpa[,vhostdev=/path/to/dev][,vhostfd=h]``
Establish a vhost-vdpa netdev.
--
2.31.1

45
SOURCES/0014-globally-limit-the-maximum-number-of-CPUs.patch
View File

@ -1,45 +0,0 @@
From 9ebfd2f6cfa8e79c92e58fd169f90cc768fb865a Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Tue, 21 Jan 2014 10:46:52 +0100
Subject: globally limit the maximum number of CPUs
We now globally limit the number of VCPUs.
Especially, there is no way one can specify more than
max_cpus VCPUs for a VM.
This allows us the restore the ppc max_cpus limitation to the upstream
default and minimize the ppc hack in kvm-all.c.
Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
Signed-off-by: Danilo Cesar Lemes de Paula <ddepaula@redhat.com>
---
accel/kvm/kvm-all.c | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index 5f1377ca04..fdf0e4d429 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -2430,6 +2430,18 @@ static int kvm_init(MachineState *ms)
soft_vcpus_limit = kvm_recommended_vcpus(s);
hard_vcpus_limit = kvm_max_vcpus(s);
+#ifdef HOST_PPC64
+ /*
+ * On POWER, the kernel advertises a soft limit based on the
+ * number of CPU threads on the host. We want to allow exceeding
+ * this for testing purposes, so we don't want to set hard limit
+ * to soft limit as on x86.
+ */
+#else
+ /* RHEL doesn't support nr_vcpus > soft_vcpus_limit */
+ hard_vcpus_limit = soft_vcpus_limit;
+#endif
+
while (nc->name) {
if (nc->num > soft_vcpus_limit) {
warn_report("Number of %s cpus requested (%d) exceeds "
--
2.31.1

4
SOURCES/0017-BZ1653590-Require-at-least-64kiB-pages-for-downstrea.patch → SOURCES/0015-BZ1653590-Require-at-least-64kiB-pages-for-downstrea.patch
View File

@ -1,4 +1,4 @@
From 64a06662cdea0ff62efb122be4eab506b2a842d9 Mon Sep 17 00:00:00 2001
From 9c6acadb444c9300d7c18b6939ce4f96484aeacc Mon Sep 17 00:00:00 2001
From: David Gibson <dgibson@redhat.com>
Date: Wed, 6 Feb 2019 03:58:56 +0000
Subject: BZ1653590: Require at least 64kiB pages for downstream guests & hosts
@ -32,7 +32,7 @@ Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
1 file changed, 7 insertions(+)
diff --git a/hw/ppc/spapr_caps.c b/hw/ppc/spapr_caps.c
index 655ab856a0..6aa7f93df9 100644
index b4283055c1..59b88aadff 100644
--- a/hw/ppc/spapr_caps.c
+++ b/hw/ppc/spapr_caps.c
@@ -329,12 +329,19 @@ bool spapr_check_pagesize(SpaprMachineState *spapr, hwaddr pagesize,

6
SOURCES/0018-qcow2-Deprecation-warning-when-opening-v2-images-rw.patch → SOURCES/0016-qcow2-Deprecation-warning-when-opening-v2-images-rw.patch
View File

@ -1,4 +1,4 @@
From 54f9157a918e1404f2f17ce89a9c8b9088c1bc06 Mon Sep 17 00:00:00 2001
From 02fde2a0cbd679ebd4104fe5522572c31ec23abd 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
@ -44,10 +44,10 @@ Rebase notes (6.1.0):
2 files changed, 7 insertions(+)
diff --git a/block/qcow2.c b/block/qcow2.c
index b5c47931ef..a795e457ac 100644
index 4d6666d3ff..d2ba263e9d 100644
--- a/block/qcow2.c
+++ b/block/qcow2.c
@@ -1337,6 +1337,12 @@ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options,
@@ -1336,6 +1336,12 @@ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options,
ret = -ENOTSUP;
goto fail;
}

66
SOURCES/0016-virtio-scsi-Reject-scsi-cd-if-data-plane-enabled-RHE.patch
View File

@ -1,66 +0,0 @@
From b72e04cb7e417d9e1c973223747ab3a27abda8b4 Mon Sep 17 00:00:00 2001
From: Fam Zheng <famz@redhat.com>
Date: Wed, 14 Jun 2017 15:37:01 +0200
Subject: virtio-scsi: Reject scsi-cd if data plane enabled [RHEL only]
RH-Author: Fam Zheng <famz@redhat.com>
Message-id: <20170614153701.14757-1-famz@redhat.com>
Patchwork-id: 75613
O-Subject: [RHV-7.4 qemu-kvm-rhev PATCH v3] virtio-scsi: Reject scsi-cd if data plane enabled [RHEL only]
Bugzilla: 1378816
RH-Acked-by: Paolo Bonzini <pbonzini@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Max Reitz <mreitz@redhat.com>
We need a fix for RHEL 7.4 and 7.3.z, but unfortunately upstream isn't
ready. If it were, the changes will be too invasive. To have an idea:
https://lists.gnu.org/archive/html/qemu-devel/2017-05/msg05400.html
is an incomplete attempt to fix part of the issue, and the remaining
work unfortunately involve even more complex changes.
As a band-aid, this partially reverts the effect of ef8875b
(virtio-scsi: Remove op blocker for dataplane, since v2.7). We cannot
simply revert that commit as a whole because we already shipped it in
qemu-kvm-rhev 7.3, since when, block jobs has been possible. We should
only block what has been broken. Also, faithfully reverting the above
commit means adding back the removed op blocker, but that is not enough,
because it still crashes when inserting media into an initially empty
scsi-cd.
All in all, scsi-cd on virtio-scsi-dataplane has basically been unusable
unless the scsi-cd never enters an empty state, so, disable it
altogether. Otherwise it would be much more difficult to avoid
crashing.
Signed-off-by: Fam Zheng <famz@redhat.com>
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
hw/scsi/virtio-scsi.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/hw/scsi/virtio-scsi.c b/hw/scsi/virtio-scsi.c
index 34a968ecfb..7f6da33a8a 100644
--- a/hw/scsi/virtio-scsi.c
+++ b/hw/scsi/virtio-scsi.c
@@ -896,6 +896,15 @@ static void virtio_scsi_hotplug(HotplugHandler *hotplug_dev, DeviceState *dev,
AioContext *old_context;
int ret;
+ /* XXX: Remove this check once block backend is capable of handling
+ * AioContext change upon eject/insert.
+ * s->ctx is NULL if ioeventfd is off, s->ctx is qemu_get_aio_context() if
+ * data plane is not used, both cases are safe for scsi-cd. */
+ if (s->ctx && s->ctx != qemu_get_aio_context() &&
+ object_dynamic_cast(OBJECT(dev), "scsi-cd")) {
+ error_setg(errp, "scsi-cd is not supported by data plane");
+ return;
+ }
if (s->ctx && !s->dataplane_fenced) {
if (blk_op_is_blocked(sd->conf.blk, BLOCK_OP_TYPE_DATAPLANE, errp)) {
return;
--
2.31.1

26
SOURCES/0018-Addd-7.2-compat-bits-for-RHEL-9.1-machine-type.patch Normal file
View File

@ -0,0 +1,26 @@
From 21ed34787b9492c2cfe3d8fc12a32748bcf02307 Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Wed, 9 Nov 2022 07:08:32 -0500
Subject: Addd 7.2 compat bits for RHEL 9.1 machine type
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
---
hw/core/machine.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/hw/core/machine.c b/hw/core/machine.c
index 9edec1ca05..3d851d34da 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -54,6 +54,8 @@ GlobalProperty hw_compat_rhel_9_1[] = {
{ "arm-gicv3-common", "force-8-bit-prio", "on" },
/* hw_compat_rhel_9_1 from hw_compat_7_0 */
{ "nvme-ns", "eui64-default", "on"},
+ /* hw_compat_rhel_9_1 from hw_compat_7_1 */
+ { "virtio-device", "queue_reset", "false" },
};
const size_t hw_compat_rhel_9_1_len = G_N_ELEMENTS(hw_compat_rhel_9_1);
--
2.31.1

135
SOURCES/0019-WRB-Introduce-RHEL-9.0.0-hw-compat-structure.patch
View File

@ -1,135 +0,0 @@
From 1d6439527aa6ccabb58208c94417778ccc19de39 Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Wed, 9 Feb 2022 04:16:25 -0500
Subject: WRB: Introduce RHEL 9.0.0 hw compat structure
General compatibility structure for post RHEL 9.0.0 rebase.
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
---
hw/core/machine.c | 9 +++++++++
hw/i386/pc.c | 6 ++++++
hw/i386/pc_piix.c | 4 ++++
hw/i386/pc_q35.c | 4 ++++
hw/s390x/s390-virtio-ccw.c | 2 ++
include/hw/boards.h | 3 +++
include/hw/i386/pc.h | 3 +++
7 files changed, 31 insertions(+)
diff --git a/hw/core/machine.c b/hw/core/machine.c
index 28989b6e7b..dffc3ef4ab 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -53,6 +53,15 @@ GlobalProperty hw_compat_rhel_8_6[] = {
};
const size_t hw_compat_rhel_8_6_len = G_N_ELEMENTS(hw_compat_rhel_8_6);
+/*
+ * Mostly the same as hw_compat_6_2
+ */
+GlobalProperty hw_compat_rhel_9_0[] = {
+ /* hw_compat_rhel_9_0 from hw_compat_6_2 */
+ { "PIIX4_PM", "x-not-migrate-acpi-index", "on"},
+};
+const size_t hw_compat_rhel_9_0_len = G_N_ELEMENTS(hw_compat_rhel_9_0);
+
/*
* Mostly the same as hw_compat_6_0 and hw_compat_6_1
*/
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 263d882af6..0886cfe3fe 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -391,6 +391,12 @@ GlobalProperty pc_rhel_compat[] = {
};
const size_t pc_rhel_compat_len = G_N_ELEMENTS(pc_rhel_compat);
+GlobalProperty pc_rhel_9_0_compat[] = {
+ /* pc_rhel_9_0_compat from pc_compat_6_2 */
+ { "virtio-mem", "unplugged-inaccessible", "off" },
+};
+const size_t pc_rhel_9_0_compat_len = G_N_ELEMENTS(pc_rhel_9_0_compat);
+
GlobalProperty pc_rhel_8_5_compat[] = {
/* pc_rhel_8_5_compat from pc_compat_6_0 */
{ "qemu64" "-" TYPE_X86_CPU, "family", "6" },
diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index 0cacc0d623..dc987fe93b 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -1014,6 +1014,10 @@ static void pc_machine_rhel760_options(MachineClass *m)
pcmc->kvmclock_create_always = false;
/* From pc_i440fx_5_1_machine_options() */
pcmc->pci_root_uid = 1;
+ compat_props_add(m->compat_props, hw_compat_rhel_9_0,
+ hw_compat_rhel_9_0_len);
+ compat_props_add(m->compat_props, pc_rhel_9_0_compat,
+ pc_rhel_9_0_compat_len);
compat_props_add(m->compat_props, hw_compat_rhel_8_6,
hw_compat_rhel_8_6_len);
compat_props_add(m->compat_props, hw_compat_rhel_8_5,
diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index 157160e069..52c253c570 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -669,6 +669,10 @@ static void pc_q35_machine_rhel900_options(MachineClass *m)
m->desc = "RHEL-9.0.0 PC (Q35 + ICH9, 2009)";
pcmc->smbios_stream_product = "RHEL";
pcmc->smbios_stream_version = "9.0.0";
+ compat_props_add(m->compat_props, hw_compat_rhel_9_0,
+ hw_compat_rhel_9_0_len);
+ compat_props_add(m->compat_props, pc_rhel_9_0_compat,
+ pc_rhel_9_0_compat_len);
}
DEFINE_PC_MACHINE(q35_rhel900, "pc-q35-rhel9.0.0", pc_q35_init_rhel900,
diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
index 465a2a09d2..08e0f6a79b 100644
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -1118,12 +1118,14 @@ static void ccw_machine_2_4_class_options(MachineClass *mc)
DEFINE_CCW_MACHINE(2_4, "2.4", false);
#endif
+
static void ccw_machine_rhel900_instance_options(MachineState *machine)
{
}
static void ccw_machine_rhel900_class_options(MachineClass *mc)
{
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_0, hw_compat_rhel_9_0_len);
}
DEFINE_CCW_MACHINE(rhel900, "rhel9.0.0", true);
diff --git a/include/hw/boards.h b/include/hw/boards.h
index d1555665df..635e45dd71 100644
--- a/include/hw/boards.h
+++ b/include/hw/boards.h
@@ -451,6 +451,9 @@ 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_0[];
+extern const size_t hw_compat_rhel_9_0_len;
+
extern GlobalProperty hw_compat_rhel_8_6[];
extern const size_t hw_compat_rhel_8_6_len;
diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h
index 419a6ec24b..a492c420b5 100644
--- a/include/hw/i386/pc.h
+++ b/include/hw/i386/pc.h
@@ -292,6 +292,9 @@ extern const size_t pc_compat_1_4_len;
extern GlobalProperty pc_rhel_compat[];
extern const size_t pc_rhel_compat_len;
+extern GlobalProperty pc_rhel_9_0_compat[];
+extern const size_t pc_rhel_9_0_compat_len;
+
extern GlobalProperty pc_rhel_8_5_compat[];
extern const size_t pc_rhel_8_5_compat_len;
--
2.31.1

47
SOURCES/0019-redhat-Update-s390x-machine-type-compatibility-for-Q.patch Normal file
View File

@ -0,0 +1,47 @@
From 27c188c6a4cbd908269cf06affd24025708ecb5c Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Thu, 17 Nov 2022 16:47:16 +0100
Subject: redhat: Update s390x machine type compatibility for QEMU 7.2.0 update
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2143585
Upstream Status: n/a (rhel-only)
Add the compatibility handling for the rebase from QEMU 7.1 to 7.2,
i.e. the settings from ccw_machine_7_1_class_options() and
ccw_machine_7_1_instance_options() to the rhel9.1.0 machine type
(earlier settings have been added by previous rebases already).
Signed-off-by: Thomas Huth <thuth@redhat.com>
---
hw/s390x/s390-virtio-ccw.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
index ba640e3d9e..97e868ada0 100644
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -1195,12 +1195,21 @@ static void ccw_machine_rhel900_instance_options(MachineState *machine)
static const S390FeatInit qemu_cpu_feat = { S390_FEAT_LIST_QEMU_V6_2 };
s390_set_qemu_cpu_model(0x3906, 14, 2, qemu_cpu_feat);
+ s390_cpudef_featoff_greater(16, 1, S390_FEAT_PAIE);
}
static void ccw_machine_rhel900_class_options(MachineClass *mc)
{
+ S390CcwMachineClass *s390mc = S390_CCW_MACHINE_CLASS(mc);
+ static GlobalProperty compat[] = {
+ { TYPE_S390_PCI_DEVICE, "interpret", "off", },
+ { TYPE_S390_PCI_DEVICE, "forwarding-assist", "off", },
+ };
+
+ compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat));
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);
+ s390mc->max_threads = S390_MAX_CPUS;
}
DEFINE_CCW_MACHINE(rhel900, "rhel9.0.0", true);
--
2.31.1

38
SOURCES/0020-redhat-Update-s390x-machine-type-compatibility-for-r.patch
View File

@ -1,38 +0,0 @@
From c8ad21ca31892f8798cf82508c2b2c61bf3b9895 Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Mon, 4 Apr 2022 12:15:50 +0200
Subject: redhat: Update s390x machine type compatibility for rebase to QEMU
7.0.0
RH-Author: Thomas Huth <thuth@redhat.com>
RH-MergeRequest: 143: Update machine type compatibility for QEMU 7.0.0 update [s390x]
RH-Commit: [23/23] 0ecf97d7bdddc50565b5779c64744b353f715cbd
RH-Bugzilla: 2064782
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
No s390x-specific machine class property updates required this time,
only an update to the default qemu cpu model.
Signed-off-by: Thomas Huth <thuth@redhat.com>
---
hw/s390x/s390-virtio-ccw.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
index 08e0f6a79b..4a491d4988 100644
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -1121,6 +1121,9 @@ DEFINE_CCW_MACHINE(2_4, "2.4", false);
static void ccw_machine_rhel900_instance_options(MachineState *machine)
{
+ static const S390FeatInit qemu_cpu_feat = { S390_FEAT_LIST_QEMU_V6_2 };
+
+ s390_set_qemu_cpu_model(0x3906, 14, 2, qemu_cpu_feat);
}
static void ccw_machine_rhel900_class_options(MachineClass *mc)
--
2.31.1

43
SOURCES/0020-redhat-aarch64-add-rhel9.2.0-virt-machine-type.patch Normal file
View File

@ -0,0 +1,43 @@
From c1a21266d8bed27f1ef1f705818fde5f9350b73f Mon Sep 17 00:00:00 2001
From: Cornelia Huck <cohuck@redhat.com>
Date: Wed, 23 Nov 2022 14:15:37 +0100
Subject: redhat: aarch64: add rhel9.2.0 virt machine type
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2131982
Upstream: RHEL only
Signed-off-by: Cornelia Huck <cohuck@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 dfcab40a73..0a94f31dd1 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -3518,14 +3518,21 @@ static void rhel_machine_init(void)
}
type_init(rhel_machine_init);
+static void rhel920_virt_options(MachineClass *mc)
+{
+}
+DEFINE_RHEL_MACHINE_AS_LATEST(9, 2, 0)
+
static void rhel900_virt_options(MachineClass *mc)
{
VirtMachineClass *vmc = VIRT_MACHINE_CLASS(OBJECT_CLASS(mc));
+ rhel920_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_1, hw_compat_rhel_9_1_len);
/* Disable FEAT_LPA2 since old kernels (<= v5.12) don't boot with that feature */
vmc->no_tcg_lpa2 = true;
}
-DEFINE_RHEL_MACHINE_AS_LATEST(9, 0, 0)
+DEFINE_RHEL_MACHINE(9, 0, 0)
--
2.31.1

70
SOURCES/0021-pc-Move-s3-s4-suspend-disabling-to-compat.patch
View File

@ -1,70 +0,0 @@
From 38b89dc24551258b630f09d1c654b6c72b265c79 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Date: Thu, 14 Apr 2022 14:58:43 +0100
Subject: pc: Move s3/s4 suspend disabling to compat
RH-Author: Dr. David Alan Gilbert <dgilbert@redhat.com>
RH-MergeRequest: 155: 7.0 machine type fixes (x86)
RH-Commit: [26/26] 7d666032d5f5dab1444ebba085f92f2de4e86699
RH-Bugzilla: 2064771
Our downstream patches currently have tweaks in the C code to disable
s3/s4; Thomas pointed out we can just set the property.
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
---
hw/acpi/ich9.c | 4 ++--
hw/acpi/piix4.c | 4 ++--
hw/i386/pc.c | 6 ++++++
3 files changed, 10 insertions(+), 4 deletions(-)
diff --git a/hw/acpi/ich9.c b/hw/acpi/ich9.c
index de1e401cdf..bd9bbade70 100644
--- a/hw/acpi/ich9.c
+++ b/hw/acpi/ich9.c
@@ -435,8 +435,8 @@ void ich9_pm_add_properties(Object *obj, ICH9LPCPMRegs *pm)
static const uint32_t gpe0_len = ICH9_PMIO_GPE0_LEN;
pm->acpi_memory_hotplug.is_enabled = true;
pm->cpu_hotplug_legacy = true;
- pm->disable_s3 = 1;
- pm->disable_s4 = 1;
+ pm->disable_s3 = 0;
+ pm->disable_s4 = 0;
pm->s4_val = 2;
pm->use_acpi_hotplug_bridge = true;
pm->keep_pci_slot_hpc = true;
diff --git a/hw/acpi/piix4.c b/hw/acpi/piix4.c
index 28544e78c3..2fb2b43248 100644
--- a/hw/acpi/piix4.c
+++ b/hw/acpi/piix4.c
@@ -653,8 +653,8 @@ static void piix4_send_gpe(AcpiDeviceIf *adev, AcpiEventStatusBits ev)
static Property piix4_pm_properties[] = {
DEFINE_PROP_UINT32("smb_io_base", PIIX4PMState, smb_io_base, 0),
- DEFINE_PROP_UINT8(ACPI_PM_PROP_S3_DISABLED, PIIX4PMState, disable_s3, 1),
- DEFINE_PROP_UINT8(ACPI_PM_PROP_S4_DISABLED, PIIX4PMState, disable_s4, 1),
+ DEFINE_PROP_UINT8(ACPI_PM_PROP_S3_DISABLED, PIIX4PMState, disable_s3, 0),
+ DEFINE_PROP_UINT8(ACPI_PM_PROP_S4_DISABLED, PIIX4PMState, disable_s4, 0),
DEFINE_PROP_UINT8(ACPI_PM_PROP_S4_VAL, PIIX4PMState, s4_val, 2),
DEFINE_PROP_BOOL(ACPI_PM_PROP_ACPI_PCIHP_BRIDGE, PIIX4PMState,
use_acpi_hotplug_bridge, true),
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 0886cfe3fe..f98f842f80 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -380,6 +380,12 @@ const size_t pc_compat_1_4_len = G_N_ELEMENTS(pc_compat_1_4);
* machine type.
*/
GlobalProperty pc_rhel_compat[] = {
+ /* we don't support s3/s4 suspend */
+ { "PIIX4_PM", "disable_s3", "1" },
+ { "PIIX4_PM", "disable_s4", "1" },
+ { "ICH9-LPC", "disable_s3", "1" },
+ { "ICH9-LPC", "disable_s4", "1" },
+
{ TYPE_X86_CPU, "host-phys-bits", "on" },
{ TYPE_X86_CPU, "host-phys-bits-limit", "48" },
{ TYPE_X86_CPU, "vmx-entry-load-perf-global-ctrl", "off" },
--
2.31.1

62
SOURCES/0021-redhat-Add-new-rhel-9.2.0-s390x-machine-type.patch Normal file
View File

@ -0,0 +1,62 @@
From a932b8d4296066be01613ada84241b501488f99f Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Thu, 17 Nov 2022 17:03:24 +0100
Subject: redhat: Add new rhel-9.2.0 s390x machine type
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2136473
Upstream Status: n/a (rhel-only)
RHEL 9.2 will be an EUS release - we want to have a new machine
type here to make sure that we have a spot where we can wire up
fixes later.
Signed-off-by: Thomas Huth <thuth@redhat.com>
---
hw/s390x/s390-virtio-ccw.c | 15 ++++++++++++++-
1 file changed, 14 insertions(+), 1 deletion(-)
diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
index 97e868ada0..aa142a1a4e 100644
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -1190,10 +1190,21 @@ DEFINE_CCW_MACHINE(2_4, "2.4", false);
#endif
+static void ccw_machine_rhel920_instance_options(MachineState *machine)
+{
+}
+
+static void ccw_machine_rhel920_class_options(MachineClass *mc)
+{
+}
+DEFINE_CCW_MACHINE(rhel920, "rhel9.2.0", true);
+
static void ccw_machine_rhel900_instance_options(MachineState *machine)
{
static const S390FeatInit qemu_cpu_feat = { S390_FEAT_LIST_QEMU_V6_2 };
+ ccw_machine_rhel920_instance_options(machine);
+
s390_set_qemu_cpu_model(0x3906, 14, 2, qemu_cpu_feat);
s390_cpudef_featoff_greater(16, 1, S390_FEAT_PAIE);
}
@@ -1206,12 +1217,14 @@ static void ccw_machine_rhel900_class_options(MachineClass *mc)
{ TYPE_S390_PCI_DEVICE, "forwarding-assist", "off", },
};
+ ccw_machine_rhel920_class_options(mc);
+
compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat));
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);
s390mc->max_threads = S390_MAX_CPUS;
}
-DEFINE_CCW_MACHINE(rhel900, "rhel9.0.0", true);
+DEFINE_CCW_MACHINE(rhel900, "rhel9.0.0", false);
static void ccw_machine_rhel860_instance_options(MachineState *machine)
{
--
2.31.1

75
SOURCES/0022-x86-rhel-9.2.0-machine-type.patch Normal file
View File

@ -0,0 +1,75 @@
From f33ca8aed4744238230f1f2cc47df77aa4c9e0ac Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Date: Thu, 17 Nov 2022 12:36:30 +0000
Subject: x86: rhel 9.2.0 machine type
Add a 9.2.0 x86 machine type, and fix up the compatibility
for 9.0.0 and older.
pc_compat_7_1 and pc_compat_7_0 are both empty upstream so there's
nothing to do there.
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
---
hw/i386/pc_piix.c | 1 +
hw/i386/pc_q35.c | 21 ++++++++++++++++++++-
2 files changed, 21 insertions(+), 1 deletion(-)
diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index 173a1fd10b..fc06877344 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -944,6 +944,7 @@ static void pc_machine_rhel760_options(MachineClass *m)
/* From pc_i440fx_5_1_machine_options() */
pcmc->pci_root_uid = 1;
pcmc->legacy_no_rng_seed = true;
+ pcmc->enforce_amd_1tb_hole = false;
compat_props_add(m->compat_props, hw_compat_rhel_9_1,
hw_compat_rhel_9_1_len);
compat_props_add(m->compat_props, hw_compat_rhel_9_0,
diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index 97c3630021..52cfe3bf45 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -692,6 +692,23 @@ static void pc_q35_machine_rhel_options(MachineClass *m)
compat_props_add(m->compat_props, pc_rhel_compat, pc_rhel_compat_len);
}
+static void pc_q35_init_rhel920(MachineState *machine)
+{
+ pc_q35_init(machine);
+}
+
+static void pc_q35_machine_rhel920_options(MachineClass *m)
+{
+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
+ pc_q35_machine_rhel_options(m);
+ m->desc = "RHEL-9.2.0 PC (Q35 + ICH9, 2009)";
+ pcmc->smbios_stream_product = "RHEL";
+ pcmc->smbios_stream_version = "9.2.0";
+}
+
+DEFINE_PC_MACHINE(q35_rhel920, "pc-q35-rhel9.2.0", pc_q35_init_rhel920,
+ pc_q35_machine_rhel920_options);
+
static void pc_q35_init_rhel900(MachineState *machine)
{
pc_q35_init(machine);
@@ -700,11 +717,13 @@ static void pc_q35_init_rhel900(MachineState *machine)
static void pc_q35_machine_rhel900_options(MachineClass *m)
{
PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
- pc_q35_machine_rhel_options(m);
+ pc_q35_machine_rhel920_options(m);
m->desc = "RHEL-9.0.0 PC (Q35 + ICH9, 2009)";
+ m->alias = NULL;
pcmc->smbios_stream_product = "RHEL";
pcmc->smbios_stream_version = "9.0.0";
pcmc->legacy_no_rng_seed = true;
+ pcmc->enforce_amd_1tb_hole = false;
compat_props_add(m->compat_props, hw_compat_rhel_9_1,
hw_compat_rhel_9_1_len);
compat_props_add(m->compat_props, hw_compat_rhel_9_0,
--
2.31.1

87
SOURCES/kvm-Add-dirty-sync-missed-zero-copy-migration-stat.patch
View File

@ -1,87 +0,0 @@
From ac346634c5731407baa9de709dbd4d5cc6f45301 Mon Sep 17 00:00:00 2001
From: Leonardo Bras <leobras@redhat.com>
Date: Mon, 11 Jul 2022 18:11:12 -0300
Subject: [PATCH 02/11] Add dirty-sync-missed-zero-copy migration stat
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Leonardo Brás <leobras@redhat.com>
RH-MergeRequest: 111: zero-copy-send fixes & improvements
RH-Commit: [2/6] 115035fd0a4e4b9439c91fb0f5d1a2f9244ba369 (LeoBras/centos-qemu-kvm)
RH-Bugzilla: 2107466
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Leonardo Bras <leobras@redhat.com>
Acked-by: Markus Armbruster <armbru@redhat.com>
Acked-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Message-Id: <20220711211112.18951-3-leobras@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
(cherry picked from commit cf20c897338067ab4b70a4596fdccaf90c7e29a1)
Signed-off-by: Leonardo Bras <leobras@redhat.com>
---
migration/migration.c | 2 ++
monitor/hmp-cmds.c | 5 +++++
qapi/migration.json | 7 ++++++-
3 files changed, 13 insertions(+), 1 deletion(-)
diff --git a/migration/migration.c b/migration/migration.c
index 8fb3eae910..3a3a7a4a50 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -1017,6 +1017,8 @@ static void populate_ram_info(MigrationInfo *info, MigrationState *s)
info->ram->normal_bytes = ram_counters.normal * page_size;
info->ram->mbps = s->mbps;
info->ram->dirty_sync_count = ram_counters.dirty_sync_count;
+ info->ram->dirty_sync_missed_zero_copy =
+ ram_counters.dirty_sync_missed_zero_copy;
info->ram->postcopy_requests = ram_counters.postcopy_requests;
info->ram->page_size = page_size;
info->ram->multifd_bytes = ram_counters.multifd_bytes;
diff --git a/monitor/hmp-cmds.c b/monitor/hmp-cmds.c
index 634968498b..9cec01de38 100644
--- a/monitor/hmp-cmds.c
+++ b/monitor/hmp-cmds.c
@@ -305,6 +305,11 @@ void hmp_info_migrate(Monitor *mon, const QDict *qdict)
monitor_printf(mon, "postcopy ram: %" PRIu64 " kbytes\n",
info->ram->postcopy_bytes >> 10);
}
+ if (info->ram->dirty_sync_missed_zero_copy) {
+ monitor_printf(mon,
+ "Zero-copy-send fallbacks happened: %" PRIu64 " times\n",
+ info->ram->dirty_sync_missed_zero_copy);
+ }
}
if (info->has_disk) {
diff --git a/qapi/migration.json b/qapi/migration.json
index 5105790cd0..9b38b3c21c 100644
--- a/qapi/migration.json
+++ b/qapi/migration.json
@@ -55,6 +55,10 @@
# @postcopy-bytes: The number of bytes sent during the post-copy phase
# (since 7.0).
#
+# @dirty-sync-missed-zero-copy: Number of times dirty RAM synchronization could
+# not avoid copying dirty pages. This is between
+# 0 and @dirty-sync-count * @multifd-channels.
+# (since 7.1)
# Since: 0.14
##
{ 'struct': 'MigrationStats',
@@ -65,7 +69,8 @@
'postcopy-requests' : 'int', 'page-size' : 'int',
'multifd-bytes' : 'uint64', 'pages-per-second' : 'uint64',
'precopy-bytes' : 'uint64', 'downtime-bytes' : 'uint64',
- 'postcopy-bytes' : 'uint64' } }
+ 'postcopy-bytes' : 'uint64',
+ 'dirty-sync-missed-zero-copy' : 'uint64' } }
##
# @XBZRLECacheStats:
--
2.31.1

41
SOURCES/kvm-Enable-virtio-iommu-pci-on-aarch64.patch
View File

@ -1,41 +0,0 @@
From 85781b8745fa1581a66f64011d61a4f0c4e103dc Mon Sep 17 00:00:00 2001
From: Eric Auger <eric.auger@redhat.com>
Date: Fri, 6 May 2022 17:03:11 +0200
Subject: [PATCH 3/5] Enable virtio-iommu-pci on aarch64
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 83: Enable virtio-iommu-pci on aarch64
RH-Commit: [1/1] 23e5c0832e52c66adf5fd6daccdc3edddc7ecb8b (eauger1/centos-qemu-kvm)
RH-Bugzilla: 1477099
RH-Acked-by: Gavin Shan <gshan@redhat.com>
RH-Acked-by: Andrew Jones <drjones@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1477099
Brew: https://brewweb.engineering.redhat.com/brew/taskinfo?taskID=45128798
Upstream Status: RHEL-only
Tested: With virtio-net-pci and virtio-block-pci
let's enable the virtio-iommu-pci device on aarch64 by
turning CONFIG_VIRTIO_IOMMU on.
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 187938573f..1618d31b89 100644
--- a/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak
+++ b/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak
@@ -23,6 +23,7 @@ CONFIG_VFIO_PCI=y
CONFIG_VIRTIO_MMIO=y
CONFIG_VIRTIO_PCI=y
CONFIG_VIRTIO_MEM=y
+CONFIG_VIRTIO_IOMMU=y
CONFIG_XIO3130=y
CONFIG_NVDIMM=y
CONFIG_ACPI_APEI=y
--
2.31.1

41
SOURCES/kvm-Enable-virtio-iommu-pci-on-x86_64.patch
View File

@ -1,41 +0,0 @@
From c531a39171201f8a1d063e6af752e5d629c1b4bf Mon Sep 17 00:00:00 2001
From: Eric Auger <eric.auger@redhat.com>
Date: Thu, 9 Jun 2022 11:35:18 +0200
Subject: [PATCH 4/6] Enable virtio-iommu-pci on x86_64
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 100: Enable virtio-iommu-pci on x86_64
RH-Commit: [1/1] a164af477efc7cb9d3d76a0e644f198f7c9fb2b5 (eauger1/centos-qemu-kvm)
RH-Bugzilla: 2094252
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: MST <mst@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2094252
Brew: https://brewweb.engineering.redhat.com/brew/taskinfo?taskID=45871185
Upstream Status: RHEL-only
Tested: With virtio-net-pci and virtio-block-pci
let's enable the virtio-iommu-pci device on x86_64 by
turning CONFIG_VIRTIO_IOMMU on.
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 d0c9e66641..3850b9de72 100644
--- a/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak
+++ b/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak
@@ -90,6 +90,7 @@ CONFIG_VHOST_USER_BLK=y
CONFIG_VIRTIO_MEM=y
CONFIG_VIRTIO_PCI=y
CONFIG_VIRTIO_VGA=y
+CONFIG_VIRTIO_IOMMU=y
CONFIG_VMMOUSE=y
CONFIG_VMPORT=y
CONFIG_VTD=y
--
2.31.1

503
SOURCES/kvm-Introduce-event-loop-base-abstract-class.patch
View File

@ -1,503 +0,0 @@
From 1163da281c178359dd7e1cf1ced5c98caa600f8e Mon Sep 17 00:00:00 2001
From: Nicolas Saenz Julienne <nsaenzju@redhat.com>
Date: Mon, 25 Apr 2022 09:57:21 +0200
Subject: [PATCH 01/16] Introduce event-loop-base abstract class
RH-Author: Nicolas Saenz Julienne <nsaenzju@redhat.com>
RH-MergeRequest: 93: util/thread-pool: Expose minimum and maximum size
RH-Commit: [1/3] 5817205d8f56cc4aa98bd5963ecac54a59bad990
RH-Bugzilla: 2031024
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
Introduce the 'event-loop-base' abstract class, it'll hold the
properties common to all event loops and provide the necessary hooks for
their creation and maintenance. Then have iothread inherit from it.
EventLoopBaseClass is defined as user creatable and provides a hook for
its children to attach themselves to the user creatable class 'complete'
function. It also provides an update_params() callback to propagate
property changes onto its children.
The new 'event-loop-base' class will live in the root directory. It is
built on its own using the 'link_whole' option (there are no direct
function dependencies between the class and its children, it all happens
trough 'constructor' magic). And also imposes new compilation
dependencies:
qom <- event-loop-base <- blockdev (iothread.c)
And in subsequent patches:
qom <- event-loop-base <- qemuutil (util/main-loop.c)
All this forced some amount of reordering in meson.build:
- Moved qom build definition before qemuutil. Doing it the other way
around (i.e. moving qemuutil after qom) isn't possible as a lot of
core libraries that live in between the two depend on it.
- Process the 'hw' subdir earlier, as it introduces files into the
'qom' source set.
No functional changes intended.
Signed-off-by: Nicolas Saenz Julienne <nsaenzju@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Acked-by: Markus Armbruster <armbru@redhat.com>
Message-id: 20220425075723.20019-2-nsaenzju@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit 7d5983e3c8c40b1d0668faba31d79905c4fadd7d)
---
event-loop-base.c | 104 +++++++++++++++++++++++++++++++
include/sysemu/event-loop-base.h | 36 +++++++++++
include/sysemu/iothread.h | 6 +-
iothread.c | 65 ++++++-------------
meson.build | 23 ++++---
qapi/qom.json | 22 +++++--
6 files changed, 192 insertions(+), 64 deletions(-)
create mode 100644 event-loop-base.c
create mode 100644 include/sysemu/event-loop-base.h
diff --git a/event-loop-base.c b/event-loop-base.c
new file mode 100644
index 0000000000..a924c73a7c
--- /dev/null
+++ b/event-loop-base.c
@@ -0,0 +1,104 @@
+/*
+ * QEMU event-loop base
+ *
+ * Copyright (C) 2022 Red Hat Inc
+ *
+ * Authors:
+ * Stefan Hajnoczi <stefanha@redhat.com>
+ * Nicolas Saenz Julienne <nsaenzju@redhat.com>
+ *
+ * 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 "qom/object_interfaces.h"
+#include "qapi/error.h"
+#include "sysemu/event-loop-base.h"
+
+typedef struct {
+ const char *name;
+ ptrdiff_t offset; /* field's byte offset in EventLoopBase struct */
+} EventLoopBaseParamInfo;
+
+static EventLoopBaseParamInfo aio_max_batch_info = {
+ "aio-max-batch", offsetof(EventLoopBase, aio_max_batch),
+};
+
+static void event_loop_base_get_param(Object *obj, Visitor *v,
+ const char *name, void *opaque, Error **errp)
+{
+ EventLoopBase *event_loop_base = EVENT_LOOP_BASE(obj);
+ EventLoopBaseParamInfo *info = opaque;
+ int64_t *field = (void *)event_loop_base + info->offset;
+
+ visit_type_int64(v, name, field, errp);
+}
+
+static void event_loop_base_set_param(Object *obj, Visitor *v,
+ const char *name, void *opaque, Error **errp)
+{
+ EventLoopBaseClass *bc = EVENT_LOOP_BASE_GET_CLASS(obj);
+ EventLoopBase *base = EVENT_LOOP_BASE(obj);
+ EventLoopBaseParamInfo *info = opaque;
+ int64_t *field = (void *)base + info->offset;
+ int64_t value;
+
+ if (!visit_type_int64(v, name, &value, errp)) {
+ return;
+ }
+
+ if (value < 0) {
+ error_setg(errp, "%s value must be in range [0, %" PRId64 "]",
+ info->name, INT64_MAX);
+ return;
+ }
+
+ *field = value;
+
+ if (bc->update_params) {
+ bc->update_params(base, errp);
+ }
+
+ return;
+}
+
+static void event_loop_base_complete(UserCreatable *uc, Error **errp)
+{
+ EventLoopBaseClass *bc = EVENT_LOOP_BASE_GET_CLASS(uc);
+ EventLoopBase *base = EVENT_LOOP_BASE(uc);
+
+ if (bc->init) {
+ bc->init(base, errp);
+ }
+}
+
+static void event_loop_base_class_init(ObjectClass *klass, void *class_data)
+{
+ UserCreatableClass *ucc = USER_CREATABLE_CLASS(klass);
+ ucc->complete = event_loop_base_complete;
+
+ object_class_property_add(klass, "aio-max-batch", "int",
+ event_loop_base_get_param,
+ event_loop_base_set_param,
+ NULL, &aio_max_batch_info);
+}
+
+static const TypeInfo event_loop_base_info = {
+ .name = TYPE_EVENT_LOOP_BASE,
+ .parent = TYPE_OBJECT,
+ .instance_size = sizeof(EventLoopBase),
+ .class_size = sizeof(EventLoopBaseClass),
+ .class_init = event_loop_base_class_init,
+ .abstract = true,
+ .interfaces = (InterfaceInfo[]) {
+ { TYPE_USER_CREATABLE },
+ { }
+ }
+};
+
+static void register_types(void)
+{
+ type_register_static(&event_loop_base_info);
+}
+type_init(register_types);
diff --git a/include/sysemu/event-loop-base.h b/include/sysemu/event-loop-base.h
new file mode 100644
index 0000000000..8e77d8b69f
--- /dev/null
+++ b/include/sysemu/event-loop-base.h
@@ -0,0 +1,36 @@
+/*
+ * QEMU event-loop backend
+ *
+ * Copyright (C) 2022 Red Hat Inc
+ *
+ * Authors:
+ * Nicolas Saenz Julienne <nsaenzju@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+#ifndef QEMU_EVENT_LOOP_BASE_H
+#define QEMU_EVENT_LOOP_BASE_H
+
+#include "qom/object.h"
+#include "block/aio.h"
+#include "qemu/typedefs.h"
+
+#define TYPE_EVENT_LOOP_BASE "event-loop-base"
+OBJECT_DECLARE_TYPE(EventLoopBase, EventLoopBaseClass,
+ EVENT_LOOP_BASE)
+
+struct EventLoopBaseClass {
+ ObjectClass parent_class;
+
+ void (*init)(EventLoopBase *base, Error **errp);
+ void (*update_params)(EventLoopBase *base, Error **errp);
+};
+
+struct EventLoopBase {
+ Object parent;
+
+ /* AioContext AIO engine parameters */
+ int64_t aio_max_batch;
+};
+#endif
diff --git a/include/sysemu/iothread.h b/include/sysemu/iothread.h
index 7f714bd136..8f8601d6ab 100644
--- a/include/sysemu/iothread.h
+++ b/include/sysemu/iothread.h
@@ -17,11 +17,12 @@
#include "block/aio.h"
#include "qemu/thread.h"
#include "qom/object.h"
+#include "sysemu/event-loop-base.h"
#define TYPE_IOTHREAD "iothread"
struct IOThread {
- Object parent_obj;
+ EventLoopBase parent_obj;
QemuThread thread;
AioContext *ctx;
@@ -37,9 +38,6 @@ struct IOThread {
int64_t poll_max_ns;
int64_t poll_grow;
int64_t poll_shrink;
-
- /* AioContext AIO engine parameters */
- int64_t aio_max_batch;
};
typedef struct IOThread IOThread;
diff --git a/iothread.c b/iothread.c
index 0f98af0f2a..8fa2f3bfb8 100644
--- a/iothread.c
+++ b/iothread.c
@@ -17,6 +17,7 @@
#include "qemu/module.h"
#include "block/aio.h"
#include "block/block.h"
+#include "sysemu/event-loop-base.h"
#include "sysemu/iothread.h"
#include "qapi/error.h"
#include "qapi/qapi-commands-misc.h"
@@ -152,10 +153,15 @@ static void iothread_init_gcontext(IOThread *iothread)
iothread->main_loop = g_main_loop_new(iothread->worker_context, TRUE);
}
-static void iothread_set_aio_context_params(IOThread *iothread, Error **errp)
+static void iothread_set_aio_context_params(EventLoopBase *base, Error **errp)
{
+ IOThread *iothread = IOTHREAD(base);
ERRP_GUARD();
+ if (!iothread->ctx) {
+ return;
+ }
+
aio_context_set_poll_params(iothread->ctx,
iothread->poll_max_ns,
iothread->poll_grow,
@@ -166,14 +172,15 @@ static void iothread_set_aio_context_params(IOThread *iothread, Error **errp)
}
aio_context_set_aio_params(iothread->ctx,
- iothread->aio_max_batch,
+ iothread->parent_obj.aio_max_batch,
errp);
}
-static void iothread_complete(UserCreatable *obj, Error **errp)
+
+static void iothread_init(EventLoopBase *base, Error **errp)
{
Error *local_error = NULL;
- IOThread *iothread = IOTHREAD(obj);
+ IOThread *iothread = IOTHREAD(base);
char *thread_name;
iothread->stopping = false;
@@ -189,7 +196,7 @@ static void iothread_complete(UserCreatable *obj, Error **errp)
*/
iothread_init_gcontext(iothread);
- iothread_set_aio_context_params(iothread, &local_error);
+ iothread_set_aio_context_params(base, &local_error);
if (local_error) {
error_propagate(errp, local_error);
aio_context_unref(iothread->ctx);
@@ -201,7 +208,7 @@ static void iothread_complete(UserCreatable *obj, Error **errp)
* to inherit.
*/
thread_name = g_strdup_printf("IO %s",
- object_get_canonical_path_component(OBJECT(obj)));
+ object_get_canonical_path_component(OBJECT(base)));
qemu_thread_create(&iothread->thread, thread_name, iothread_run,
iothread, QEMU_THREAD_JOINABLE);
g_free(thread_name);
@@ -226,9 +233,6 @@ static IOThreadParamInfo poll_grow_info = {
static IOThreadParamInfo poll_shrink_info = {
"poll-shrink", offsetof(IOThread, poll_shrink),
};
-static IOThreadParamInfo aio_max_batch_info = {
- "aio-max-batch", offsetof(IOThread, aio_max_batch),
-};
static void iothread_get_param(Object *obj, Visitor *v,
const char *name, IOThreadParamInfo *info, Error **errp)
@@ -288,35 +292,12 @@ static void iothread_set_poll_param(Object *obj, Visitor *v,
}
}
-static void iothread_get_aio_param(Object *obj, Visitor *v,
- const char *name, void *opaque, Error **errp)
-{
- IOThreadParamInfo *info = opaque;
-
- iothread_get_param(obj, v, name, info, errp);
-}
-
-static void iothread_set_aio_param(Object *obj, Visitor *v,
- const char *name, void *opaque, Error **errp)
-{
- IOThread *iothread = IOTHREAD(obj);
- IOThreadParamInfo *info = opaque;
-
- if (!iothread_set_param(obj, v, name, info, errp)) {
- return;
- }
-
- if (iothread->ctx) {
- aio_context_set_aio_params(iothread->ctx,
- iothread->aio_max_batch,
- errp);
- }
-}
-
static void iothread_class_init(ObjectClass *klass, void *class_data)
{
- UserCreatableClass *ucc = USER_CREATABLE_CLASS(klass);
- ucc->complete = iothread_complete;
+ EventLoopBaseClass *bc = EVENT_LOOP_BASE_CLASS(klass);
+
+ bc->init = iothread_init;
+ bc->update_params = iothread_set_aio_context_params;
object_class_property_add(klass, "poll-max-ns", "int",
iothread_get_poll_param,
@@ -330,23 +311,15 @@ static void iothread_class_init(ObjectClass *klass, void *class_data)
iothread_get_poll_param,
iothread_set_poll_param,
NULL, &poll_shrink_info);
- object_class_property_add(klass, "aio-max-batch", "int",
- iothread_get_aio_param,
- iothread_set_aio_param,
- NULL, &aio_max_batch_info);
}
static const TypeInfo iothread_info = {
.name = TYPE_IOTHREAD,
- .parent = TYPE_OBJECT,
+ .parent = TYPE_EVENT_LOOP_BASE,
.class_init = iothread_class_init,
.instance_size = sizeof(IOThread),
.instance_init = iothread_instance_init,
.instance_finalize = iothread_instance_finalize,
- .interfaces = (InterfaceInfo[]) {
- {TYPE_USER_CREATABLE},
- {}
- },
};
static void iothread_register_types(void)
@@ -383,7 +356,7 @@ static int query_one_iothread(Object *object, void *opaque)
info->poll_max_ns = iothread->poll_max_ns;
info->poll_grow = iothread->poll_grow;
info->poll_shrink = iothread->poll_shrink;
- info->aio_max_batch = iothread->aio_max_batch;
+ info->aio_max_batch = iothread->parent_obj.aio_max_batch;
QAPI_LIST_APPEND(*tail, info);
return 0;
diff --git a/meson.build b/meson.build
index 6f7e430f0f..b9c919a55e 100644
--- a/meson.build
+++ b/meson.build
@@ -2804,6 +2804,7 @@ subdir('qom')
subdir('authz')
subdir('crypto')
subdir('ui')
+subdir('hw')
if enable_modules
@@ -2811,6 +2812,18 @@ if enable_modules
modulecommon = declare_dependency(link_whole: libmodulecommon, compile_args: '-DBUILD_DSO')
endif
+qom_ss = qom_ss.apply(config_host, strict: false)
+libqom = static_library('qom', qom_ss.sources() + genh,
+ dependencies: [qom_ss.dependencies()],
+ name_suffix: 'fa')
+qom = declare_dependency(link_whole: libqom)
+
+event_loop_base = files('event-loop-base.c')
+event_loop_base = static_library('event-loop-base', sources: event_loop_base + genh,
+ build_by_default: true)
+event_loop_base = declare_dependency(link_whole: event_loop_base,
+ dependencies: [qom])
+
stub_ss = stub_ss.apply(config_all, strict: false)
util_ss.add_all(trace_ss)
@@ -2897,7 +2910,6 @@ subdir('monitor')
subdir('net')
subdir('replay')
subdir('semihosting')
-subdir('hw')
subdir('tcg')
subdir('fpu')
subdir('accel')
@@ -3022,13 +3034,6 @@ qemu_syms = custom_target('qemu.syms', output: 'qemu.syms',
capture: true,
command: [undefsym, nm, '@INPUT@'])
-qom_ss = qom_ss.apply(config_host, strict: false)
-libqom = static_library('qom', qom_ss.sources() + genh,
- dependencies: [qom_ss.dependencies()],
- name_suffix: 'fa')
-
-qom = declare_dependency(link_whole: libqom)
-
authz_ss = authz_ss.apply(config_host, strict: false)
libauthz = static_library('authz', authz_ss.sources() + genh,
dependencies: [authz_ss.dependencies()],
@@ -3081,7 +3086,7 @@ libblockdev = static_library('blockdev', blockdev_ss.sources() + genh,
build_by_default: false)
blockdev = declare_dependency(link_whole: [libblockdev],
- dependencies: [block])
+ dependencies: [block, event_loop_base])
qmp_ss = qmp_ss.apply(config_host, strict: false)
libqmp = static_library('qmp', qmp_ss.sources() + genh,
diff --git a/qapi/qom.json b/qapi/qom.json
index eeb5395ff3..a2439533c5 100644
--- a/qapi/qom.json
+++ b/qapi/qom.json
@@ -499,6 +499,20 @@
'*repeat': 'bool',
'*grab-toggle': 'GrabToggleKeys' } }
+##
+# @EventLoopBaseProperties:
+#
+# Common properties for event loops
+#
+# @aio-max-batch: maximum number of requests in a batch for the AIO engine,
+# 0 means that the engine will use its default.
+# (default: 0)
+#
+# Since: 7.1
+##
+{ 'struct': 'EventLoopBaseProperties',
+ 'data': { '*aio-max-batch': 'int' } }
+
##
# @IothreadProperties:
#
@@ -516,17 +530,15 @@
# algorithm detects it is spending too long polling without
# encountering events. 0 selects a default behaviour (default: 0)
#
-# @aio-max-batch: maximum number of requests in a batch for the AIO engine,
-# 0 means that the engine will use its default
-# (default:0, since 6.1)
+# The @aio-max-batch option is available since 6.1.
#
# Since: 2.0
##
{ 'struct': 'IothreadProperties',
+ 'base': 'EventLoopBaseProperties',
'data': { '*poll-max-ns': 'int',
'*poll-grow': 'int',
- '*poll-shrink': 'int',
- '*aio-max-batch': 'int' } }
+ '*poll-shrink': 'int' } }
##
# @MemoryBackendProperties:
--
2.31.1

82
SOURCES/kvm-KVM-keep-track-of-running-ioctls.patch Normal file
View File

@ -0,0 +1,82 @@
From 6aebc271d95f9c59cb63c923b6ce35f16fce10e4 Mon Sep 17 00:00:00 2001
From: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Date: Mon, 16 Jan 2023 07:17:23 -0500
Subject: [PATCH 30/31] KVM: keep track of running ioctls
RH-Author: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-MergeRequest: 138: accel: introduce accelerator blocker API
RH-Bugzilla: 1979276
RH-Acked-by: Paolo Bonzini <pbonzini@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [2/3] f566f81dda26ae733008f32261ecd1253ec1796d (eesposit/qemu-kvm)
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1979276
commit a27dd2de68f37ba96fe164a42121daa5f0750afc
Author: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Date: Fri Nov 11 10:47:57 2022 -0500
KVM: keep track of running ioctls
Using the new accel-blocker API, mark where ioctls are being called
in KVM. Next, we will implement the critical section that will take
care of performing memslots modifications atomically, therefore
preventing any new ioctl from running and allowing the running ones
to finish.
Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Message-Id: <20221111154758.1372674-3-eesposit@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
---
accel/kvm/kvm-all.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index f99b0becd8..ff660fd469 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -2310,6 +2310,7 @@ static int kvm_init(MachineState *ms)
assert(TARGET_PAGE_SIZE <= qemu_real_host_page_size());
s->sigmask_len = 8;
+ accel_blocker_init();
#ifdef KVM_CAP_SET_GUEST_DEBUG
QTAILQ_INIT(&s->kvm_sw_breakpoints);
@@ -3014,7 +3015,9 @@ int kvm_vm_ioctl(KVMState *s, int type, ...)
va_end(ap);
trace_kvm_vm_ioctl(type, arg);
+ accel_ioctl_begin();
ret = ioctl(s->vmfd, type, arg);
+ accel_ioctl_end();
if (ret == -1) {
ret = -errno;
}
@@ -3032,7 +3035,9 @@ int kvm_vcpu_ioctl(CPUState *cpu, int type, ...)
va_end(ap);
trace_kvm_vcpu_ioctl(cpu->cpu_index, type, arg);
+ accel_cpu_ioctl_begin(cpu);
ret = ioctl(cpu->kvm_fd, type, arg);
+ accel_cpu_ioctl_end(cpu);
if (ret == -1) {
ret = -errno;
}
@@ -3050,7 +3055,9 @@ int kvm_device_ioctl(int fd, int type, ...)
va_end(ap);
trace_kvm_device_ioctl(fd, type, arg);
+ accel_ioctl_begin();
ret = ioctl(fd, type, arg);
+ accel_ioctl_end();
if (ret == -1) {
ret = -errno;
}
--
2.31.1

420
SOURCES/kvm-QIOChannel-Add-flags-on-io_writev-and-introduce-io_f.patch
View File

@ -1,420 +0,0 @@
From cda3fcf14f2883fea633e25256f6c14a71271adf Mon Sep 17 00:00:00 2001
From: Leonardo Bras <leobras@redhat.com>
Date: Fri, 13 May 2022 03:28:31 -0300
Subject: [PATCH 08/18] QIOChannel: Add flags on io_writev and introduce
io_flush callback
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Leonardo Brás <leobras@redhat.com>
RH-MergeRequest: 95: MSG_ZEROCOPY + Multifd
RH-Commit: [2/11] 06acfb6b0cb2c25733c2eb198011f7623b5a7024 (LeoBras/centos-qemu-kvm)
RH-Bugzilla: 1968509
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
RH-Acked-by: Peter Xu <peterx@redhat.com>
Add flags to io_writev and introduce io_flush as optional callback to
QIOChannelClass, allowing the implementation of zero copy writes by
subclasses.
How to use them:
- Write data using qio_channel_writev*(...,QIO_CHANNEL_WRITE_FLAG_ZERO_COPY),
- Wait write completion with qio_channel_flush().
Notes:
As some zero copy write implementations work asynchronously, it's
recommended to keep the write buffer untouched until the return of
qio_channel_flush(), to avoid the risk of sending an updated buffer
instead of the buffer state during write.
As io_flush callback is optional, if a subclass does not implement it, then:
- io_flush will return 0 without changing anything.
Also, some functions like qio_channel_writev_full_all() were adapted to
receive a flag parameter. That allows shared code between zero copy and
non-zero copy writev, and also an easier implementation on new flags.
Signed-off-by: Leonardo Bras <leobras@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Message-Id: <20220513062836.965425-3-leobras@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
(cherry picked from commit b88651cb4d4fa416fdbb6afaf5b26ec8c035eaad)
Signed-off-by: Leonardo Bras <leobras@redhat.com>
---
chardev/char-io.c | 2 +-
hw/remote/mpqemu-link.c | 2 +-
include/io/channel.h | 38 +++++++++++++++++++++-
io/channel-buffer.c | 1 +
io/channel-command.c | 1 +
io/channel-file.c | 1 +
io/channel-socket.c | 2 ++
io/channel-tls.c | 1 +
io/channel-websock.c | 1 +
io/channel.c | 49 +++++++++++++++++++++++------
migration/rdma.c | 1 +
scsi/pr-manager-helper.c | 2 +-
tests/unit/test-io-channel-socket.c | 1 +
13 files changed, 88 insertions(+), 14 deletions(-)
diff --git a/chardev/char-io.c b/chardev/char-io.c
index 8ced184160..4451128cba 100644
--- a/chardev/char-io.c
+++ b/chardev/char-io.c
@@ -122,7 +122,7 @@ int io_channel_send_full(QIOChannel *ioc,
ret = qio_channel_writev_full(
ioc, &iov, 1,
- fds, nfds, NULL);
+ fds, nfds, 0, NULL);
if (ret == QIO_CHANNEL_ERR_BLOCK) {
if (offset) {
return offset;
diff --git a/hw/remote/mpqemu-link.c b/hw/remote/mpqemu-link.c
index 7e841820e5..e8f556bd27 100644
--- a/hw/remote/mpqemu-link.c
+++ b/hw/remote/mpqemu-link.c
@@ -69,7 +69,7 @@ bool mpqemu_msg_send(MPQemuMsg *msg, QIOChannel *ioc, Error **errp)
}
if (!qio_channel_writev_full_all(ioc, send, G_N_ELEMENTS(send),
- fds, nfds, errp)) {
+ fds, nfds, 0, errp)) {
ret = true;
} else {
trace_mpqemu_send_io_error(msg->cmd, msg->size, nfds);
diff --git a/include/io/channel.h b/include/io/channel.h
index 88988979f8..c680ee7480 100644
--- a/include/io/channel.h
+++ b/include/io/channel.h
@@ -32,12 +32,15 @@ OBJECT_DECLARE_TYPE(QIOChannel, QIOChannelClass,
#define QIO_CHANNEL_ERR_BLOCK -2
+#define QIO_CHANNEL_WRITE_FLAG_ZERO_COPY 0x1
+
typedef enum QIOChannelFeature QIOChannelFeature;
enum QIOChannelFeature {
QIO_CHANNEL_FEATURE_FD_PASS,
QIO_CHANNEL_FEATURE_SHUTDOWN,
QIO_CHANNEL_FEATURE_LISTEN,
+ QIO_CHANNEL_FEATURE_WRITE_ZERO_COPY,
};
@@ -104,6 +107,7 @@ struct QIOChannelClass {
size_t niov,
int *fds,
size_t nfds,
+ int flags,
Error **errp);
ssize_t (*io_readv)(QIOChannel *ioc,
const struct iovec *iov,
@@ -136,6 +140,8 @@ struct QIOChannelClass {
IOHandler *io_read,
IOHandler *io_write,
void *opaque);
+ int (*io_flush)(QIOChannel *ioc,
+ Error **errp);
};
/* General I/O handling functions */
@@ -228,6 +234,7 @@ ssize_t qio_channel_readv_full(QIOChannel *ioc,
* @niov: the length of the @iov array
* @fds: an array of file handles to send
* @nfds: number of file handles in @fds
+ * @flags: write flags (QIO_CHANNEL_WRITE_FLAG_*)
* @errp: pointer to a NULL-initialized error object
*
* Write data to the IO channel, reading it from the
@@ -260,6 +267,7 @@ ssize_t qio_channel_writev_full(QIOChannel *ioc,
size_t niov,
int *fds,
size_t nfds,
+ int flags,
Error **errp);
/**
@@ -837,6 +845,7 @@ int qio_channel_readv_full_all(QIOChannel *ioc,
* @niov: the length of the @iov array
* @fds: an array of file handles to send
* @nfds: number of file handles in @fds
+ * @flags: write flags (QIO_CHANNEL_WRITE_FLAG_*)
* @errp: pointer to a NULL-initialized error object
*
*
@@ -846,6 +855,14 @@ int qio_channel_readv_full_all(QIOChannel *ioc,
* to be written, yielding from the current coroutine
* if required.
*
+ * If QIO_CHANNEL_WRITE_FLAG_ZERO_COPY is passed in flags,
+ * instead of waiting for all requested data to be written,
+ * this function will wait until it's all queued for writing.
+ * In this case, if the buffer gets changed between queueing and
+ * sending, the updated buffer will be sent. If this is not a
+ * desired behavior, it's suggested to call qio_channel_flush()
+ * before reusing the buffer.
+ *
* Returns: 0 if all bytes were written, or -1 on error
*/
@@ -853,6 +870,25 @@ int qio_channel_writev_full_all(QIOChannel *ioc,
const struct iovec *iov,
size_t niov,
int *fds, size_t nfds,
- Error **errp);
+ int flags, Error **errp);
+
+/**
+ * qio_channel_flush:
+ * @ioc: the channel object
+ * @errp: pointer to a NULL-initialized error object
+ *
+ * Will block until every packet queued with
+ * qio_channel_writev_full() + QIO_CHANNEL_WRITE_FLAG_ZERO_COPY
+ * is sent, or return in case of any error.
+ *
+ * If not implemented, acts as a no-op, and returns 0.
+ *
+ * Returns -1 if any error is found,
+ * 1 if every send failed to use zero copy.
+ * 0 otherwise.
+ */
+
+int qio_channel_flush(QIOChannel *ioc,
+ Error **errp);
#endif /* QIO_CHANNEL_H */
diff --git a/io/channel-buffer.c b/io/channel-buffer.c
index baa4e2b089..bf52011be2 100644
--- a/io/channel-buffer.c
+++ b/io/channel-buffer.c
@@ -81,6 +81,7 @@ static ssize_t qio_channel_buffer_writev(QIOChannel *ioc,
size_t niov,
int *fds,
size_t nfds,
+ int flags,
Error **errp)
{
QIOChannelBuffer *bioc = QIO_CHANNEL_BUFFER(ioc);
diff --git a/io/channel-command.c b/io/channel-command.c
index 338da73ade..54560464ae 100644
--- a/io/channel-command.c
+++ b/io/channel-command.c
@@ -258,6 +258,7 @@ static ssize_t qio_channel_command_writev(QIOChannel *ioc,
size_t niov,
int *fds,
size_t nfds,
+ int flags,
Error **errp)
{
QIOChannelCommand *cioc = QIO_CHANNEL_COMMAND(ioc);
diff --git a/io/channel-file.c b/io/channel-file.c
index d7cf6d278f..ef6807a6be 100644
--- a/io/channel-file.c
+++ b/io/channel-file.c
@@ -114,6 +114,7 @@ static ssize_t qio_channel_file_writev(QIOChannel *ioc,
size_t niov,
int *fds,
size_t nfds,
+ int flags,
Error **errp)
{
QIOChannelFile *fioc = QIO_CHANNEL_FILE(ioc);
diff --git a/io/channel-socket.c b/io/channel-socket.c
index 7a8d9f69c9..a1be2197ca 100644
--- a/io/channel-socket.c
+++ b/io/channel-socket.c
@@ -525,6 +525,7 @@ static ssize_t qio_channel_socket_writev(QIOChannel *ioc,
size_t niov,
int *fds,
size_t nfds,
+ int flags,
Error **errp)
{
QIOChannelSocket *sioc = QIO_CHANNEL_SOCKET(ioc);
@@ -620,6 +621,7 @@ static ssize_t qio_channel_socket_writev(QIOChannel *ioc,
size_t niov,
int *fds,
size_t nfds,
+ int flags,
Error **errp)
{
QIOChannelSocket *sioc = QIO_CHANNEL_SOCKET(ioc);
diff --git a/io/channel-tls.c b/io/channel-tls.c
index 2ae1b92fc0..4ce890a538 100644
--- a/io/channel-tls.c
+++ b/io/channel-tls.c
@@ -301,6 +301,7 @@ static ssize_t qio_channel_tls_writev(QIOChannel *ioc,
size_t niov,
int *fds,
size_t nfds,
+ int flags,
Error **errp)
{
QIOChannelTLS *tioc = QIO_CHANNEL_TLS(ioc);
diff --git a/io/channel-websock.c b/io/channel-websock.c
index 55145a6a8c..9619906ac3 100644
--- a/io/channel-websock.c
+++ b/io/channel-websock.c
@@ -1127,6 +1127,7 @@ static ssize_t qio_channel_websock_writev(QIOChannel *ioc,
size_t niov,
int *fds,
size_t nfds,
+ int flags,
Error **errp)
{
QIOChannelWebsock *wioc = QIO_CHANNEL_WEBSOCK(ioc);
diff --git a/io/channel.c b/io/channel.c
index e8b019dc36..0640941ac5 100644
--- a/io/channel.c
+++ b/io/channel.c
@@ -72,18 +72,32 @@ ssize_t qio_channel_writev_full(QIOChannel *ioc,
size_t niov,
int *fds,
size_t nfds,
+ int flags,
Error **errp)
{
QIOChannelClass *klass = QIO_CHANNEL_GET_CLASS(ioc);
- if ((fds || nfds) &&
- !qio_channel_has_feature(ioc, QIO_CHANNEL_FEATURE_FD_PASS)) {
+ if (fds || nfds) {
+ if (!qio_channel_has_feature(ioc, QIO_CHANNEL_FEATURE_FD_PASS)) {
+ error_setg_errno(errp, EINVAL,
+ "Channel does not support file descriptor passing");
+ return -1;
+ }
+ if (flags & QIO_CHANNEL_WRITE_FLAG_ZERO_COPY) {
+ error_setg_errno(errp, EINVAL,
+ "Zero Copy does not support file descriptor passing");
+ return -1;
+ }
+ }
+
+ if ((flags & QIO_CHANNEL_WRITE_FLAG_ZERO_COPY) &&
+ !qio_channel_has_feature(ioc, QIO_CHANNEL_FEATURE_WRITE_ZERO_COPY)) {
error_setg_errno(errp, EINVAL,
- "Channel does not support file descriptor passing");
+ "Requested Zero Copy feature is not available");
return -1;
}
- return klass->io_writev(ioc, iov, niov, fds, nfds, errp);
+ return klass->io_writev(ioc, iov, niov, fds, nfds, flags, errp);
}
@@ -217,14 +231,14 @@ int qio_channel_writev_all(QIOChannel *ioc,
size_t niov,
Error **errp)
{
- return qio_channel_writev_full_all(ioc, iov, niov, NULL, 0, errp);
+ return qio_channel_writev_full_all(ioc, iov, niov, NULL, 0, 0, errp);
}
int qio_channel_writev_full_all(QIOChannel *ioc,
const struct iovec *iov,
size_t niov,
int *fds, size_t nfds,
- Error **errp)
+ int flags, Error **errp)
{
int ret = -1;
struct iovec *local_iov = g_new(struct iovec, niov);
@@ -237,8 +251,10 @@ int qio_channel_writev_full_all(QIOChannel *ioc,
while (nlocal_iov > 0) {
ssize_t len;
- len = qio_channel_writev_full(ioc, local_iov, nlocal_iov, fds, nfds,
- errp);
+
+ len = qio_channel_writev_full(ioc, local_iov, nlocal_iov, fds,
+ nfds, flags, errp);
+
if (len == QIO_CHANNEL_ERR_BLOCK) {
if (qemu_in_coroutine()) {
qio_channel_yield(ioc, G_IO_OUT);
@@ -277,7 +293,7 @@ ssize_t qio_channel_writev(QIOChannel *ioc,
size_t niov,
Error **errp)
{
- return qio_channel_writev_full(ioc, iov, niov, NULL, 0, errp);
+ return qio_channel_writev_full(ioc, iov, niov, NULL, 0, 0, errp);
}
@@ -297,7 +313,7 @@ ssize_t qio_channel_write(QIOChannel *ioc,
Error **errp)
{
struct iovec iov = { .iov_base = (char *)buf, .iov_len = buflen };
- return qio_channel_writev_full(ioc, &iov, 1, NULL, 0, errp);
+ return qio_channel_writev_full(ioc, &iov, 1, NULL, 0, 0, errp);
}
@@ -473,6 +489,19 @@ off_t qio_channel_io_seek(QIOChannel *ioc,
return klass->io_seek(ioc, offset, whence, errp);
}
+int qio_channel_flush(QIOChannel *ioc,
+ Error **errp)
+{
+ QIOChannelClass *klass = QIO_CHANNEL_GET_CLASS(ioc);
+
+ if (!klass->io_flush ||
+ !qio_channel_has_feature(ioc, QIO_CHANNEL_FEATURE_WRITE_ZERO_COPY)) {
+ return 0;
+ }
+
+ return klass->io_flush(ioc, errp);
+}
+
static void qio_channel_restart_read(void *opaque)
{
diff --git a/migration/rdma.c b/migration/rdma.c
index ef1e65ec36..672d1958a9 100644
--- a/migration/rdma.c
+++ b/migration/rdma.c
@@ -2840,6 +2840,7 @@ static ssize_t qio_channel_rdma_writev(QIOChannel *ioc,
size_t niov,
int *fds,
size_t nfds,
+ int flags,
Error **errp)
{
QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(ioc);
diff --git a/scsi/pr-manager-helper.c b/scsi/pr-manager-helper.c
index 451c7631b7..3be52a98d5 100644
--- a/scsi/pr-manager-helper.c
+++ b/scsi/pr-manager-helper.c
@@ -77,7 +77,7 @@ static int pr_manager_helper_write(PRManagerHelper *pr_mgr,
iov.iov_base = (void *)buf;
iov.iov_len = sz;
n_written = qio_channel_writev_full(QIO_CHANNEL(pr_mgr->ioc), &iov, 1,
- nfds ? &fd : NULL, nfds, errp);
+ nfds ? &fd : NULL, nfds, 0, errp);
if (n_written <= 0) {
assert(n_written != QIO_CHANNEL_ERR_BLOCK);
diff --git a/tests/unit/test-io-channel-socket.c b/tests/unit/test-io-channel-socket.c
index c49eec1f03..6713886d02 100644
--- a/tests/unit/test-io-channel-socket.c
+++ b/tests/unit/test-io-channel-socket.c
@@ -444,6 +444,7 @@ static void test_io_channel_unix_fd_pass(void)
G_N_ELEMENTS(iosend),
fdsend,
G_N_ELEMENTS(fdsend),
+ 0,
&error_abort);
qio_channel_readv_full(dst,
--
2.35.3

56
SOURCES/kvm-QIOChannelSocket-Add-support-for-MSG_ZEROCOPY-IPV6.patch
View File

@ -1,56 +0,0 @@
From cb6dc39a5e5d2d981b4b1e983042b3fbb529d5d1 Mon Sep 17 00:00:00 2001
From: Leonardo Bras <leobras@redhat.com>
Date: Thu, 4 Aug 2022 04:10:43 -0300
Subject: [PATCH 06/11] QIOChannelSocket: Add support for MSG_ZEROCOPY + IPV6
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Leonardo Brás <leobras@redhat.com>
RH-MergeRequest: 111: zero-copy-send fixes & improvements
RH-Commit: [6/6] 2eb1aba8ebf267a6f67cfba2e489dc88619c7fd4 (LeoBras/centos-qemu-kvm)
RH-Bugzilla: 2107466
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
For using MSG_ZEROCOPY, there are two steps:
1 - io_writev() the packet, which enqueues the packet for sending, and
2 - io_flush(), which gets confirmation that all packets got correctly sent
Currently, if MSG_ZEROCOPY is used to send packets over IPV6, no error will
be reported in (1), but it will fail in the first time (2) happens.
This happens because (2) currently checks for cmsg_level & cmsg_type
associated with IPV4 only, before reporting any error.
Add checks for cmsg_level & cmsg_type associated with IPV6, and thus enable
support for MSG_ZEROCOPY + IPV6
Fixes: 2bc58ffc29 ("QIOChannelSocket: Implement io_writev zero copy flag & io_flush for CONFIG_LINUX")
Signed-off-by: Leonardo Bras <leobras@redhat.com>
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
(cherry picked from commit 5258a7e2c0677d16e9e1d06845f60171adf0b290)
Signed-off-by: Leonardo Bras <leobras@redhat.com>
---
io/channel-socket.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/io/channel-socket.c b/io/channel-socket.c
index eb7baa2184..efd5f60808 100644
--- a/io/channel-socket.c
+++ b/io/channel-socket.c
@@ -747,8 +747,8 @@ static int qio_channel_socket_flush(QIOChannel *ioc,
}
cm = CMSG_FIRSTHDR(&msg);
- if (cm->cmsg_level != SOL_IP &&
- cm->cmsg_type != IP_RECVERR) {
+ if (cm->cmsg_level != SOL_IP && cm->cmsg_type != IP_RECVERR &&
+ cm->cmsg_level != SOL_IPV6 && cm->cmsg_type != IPV6_RECVERR) {
error_setg_errno(errp, EPROTOTYPE,
"Wrong cmsg in errqueue");
return -1;
--
2.31.1

65
SOURCES/kvm-QIOChannelSocket-Fix-zero-copy-flush-returning-code-.patch
View File

@ -1,65 +0,0 @@
From 678981c6bb7c964e1591f6f8aba49e9602f64852 Mon Sep 17 00:00:00 2001
From: Leonardo Bras <leobras@redhat.com>
Date: Mon, 11 Jul 2022 18:11:11 -0300
Subject: [PATCH 01/11] QIOChannelSocket: Fix zero-copy flush returning code 1
when nothing sent
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Leonardo Brás <leobras@redhat.com>
RH-MergeRequest: 111: zero-copy-send fixes & improvements
RH-Commit: [1/6] cebc887cb61de1572d8ae3232cde45e80c339404 (LeoBras/centos-qemu-kvm)
RH-Bugzilla: 2107466
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
If flush is called when no buffer was sent with MSG_ZEROCOPY, it currently
returns 1. This return code should be used only when Linux fails to use
MSG_ZEROCOPY on a lot of sendmsg().
Fix this by returning early from flush if no sendmsg(...,MSG_ZEROCOPY)
was attempted.
Fixes: 2bc58ffc2926 ("QIOChannelSocket: Implement io_writev zero copy flag & io_flush for CONFIG_LINUX")
Signed-off-by: Leonardo Bras <leobras@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Acked-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Message-Id: <20220711211112.18951-2-leobras@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
(cherry picked from commit 927f93e099c4f9184e60a1bc61624ac2d04d0223)
Signed-off-by: Leonardo Bras <leobras@redhat.com>
---
io/channel-socket.c | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/io/channel-socket.c b/io/channel-socket.c
index 8ae8b212cf..eb7baa2184 100644
--- a/io/channel-socket.c
+++ b/io/channel-socket.c
@@ -717,12 +717,18 @@ static int qio_channel_socket_flush(QIOChannel *ioc,
struct cmsghdr *cm;
char control[CMSG_SPACE(sizeof(*serr))];
int received;
- int ret = 1;
+ int ret;
+
+ if (sioc->zero_copy_queued == sioc->zero_copy_sent) {
+ return 0;
+ }
msg.msg_control = control;
msg.msg_controllen = sizeof(control);
memset(control, 0, sizeof(control));
+ ret = 1;
+
while (sioc->zero_copy_sent < sioc->zero_copy_queued) {
received = recvmsg(sioc->fd, &msg, MSG_ERRQUEUE);
if (received < 0) {
--
2.31.1

58
SOURCES/kvm-QIOChannelSocket-Fix-zero-copy-send-so-socket-flush-.patch
View File

@ -1,58 +0,0 @@
From e70f01749addd7d0b7aa7fa4fdedb664f98e6b9b Mon Sep 17 00:00:00 2001
From: Leonardo Bras <leobras@redhat.com>
Date: Mon, 20 Jun 2022 02:39:43 -0300
Subject: [PATCH 16/18] QIOChannelSocket: Fix zero-copy send so socket flush
works
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Leonardo Brás <leobras@redhat.com>
RH-MergeRequest: 95: MSG_ZEROCOPY + Multifd
RH-Commit: [10/11] a2dfac987e24026b1a78e90b86234ca206b6401f (LeoBras/centos-qemu-kvm)
RH-Bugzilla: 1968509
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
RH-Acked-by: Peter Xu <peterx@redhat.com>
Somewhere between v6 and v7 the of the zero-copy-send patchset a crucial
part of the flushing mechanism got missing: incrementing zero_copy_queued.
Without that, the flushing interface becomes a no-op, and there is no
guarantee the buffer is really sent.
This can go as bad as causing a corruption in RAM during migration.
Fixes: 2bc58ffc2926 ("QIOChannelSocket: Implement io_writev zero copy flag & io_flush for CONFIG_LINUX")
Reported-by: 徐闯 <xuchuangxclwt@bytedance.com>
Signed-off-by: Leonardo Bras <leobras@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
(cherry picked from commit 4f5a09714c983a3471fd12e3c7f3196e95c650c1)
Signed-off-by: Leonardo Bras <leobras@redhat.com>
---
io/channel-socket.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/io/channel-socket.c b/io/channel-socket.c
index 7490e5943d..8ae8b212cf 100644
--- a/io/channel-socket.c
+++ b/io/channel-socket.c
@@ -612,6 +612,11 @@ static ssize_t qio_channel_socket_writev(QIOChannel *ioc,
"Unable to write to socket");
return -1;
}
+
+ if (flags & QIO_CHANNEL_WRITE_FLAG_ZERO_COPY) {
+ sioc->zero_copy_queued++;
+ }
+
return ret;
}
#else /* WIN32 */
--
2.35.3

249
SOURCES/kvm-QIOChannelSocket-Implement-io_writev-zero-copy-flag-.patch
View File

@ -1,249 +0,0 @@
From 4aeba0365d30dabe2e70dc172683f0878a4a9621 Mon Sep 17 00:00:00 2001
From: Leonardo Bras <leobras@redhat.com>
Date: Fri, 13 May 2022 03:28:32 -0300
Subject: [PATCH 09/18] QIOChannelSocket: Implement io_writev zero copy flag &
io_flush for CONFIG_LINUX
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Leonardo Brás <leobras@redhat.com>
RH-MergeRequest: 95: MSG_ZEROCOPY + Multifd
RH-Commit: [3/11] 9afeac1f5ac7675624660a0281726c09c8321180 (LeoBras/centos-qemu-kvm)
RH-Bugzilla: 1968509
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
RH-Acked-by: Peter Xu <peterx@redhat.com>
For CONFIG_LINUX, implement the new zero copy flag and the optional callback
io_flush on QIOChannelSocket, but enables it only when MSG_ZEROCOPY
feature is available in the host kernel, which is checked on
qio_channel_socket_connect_sync()
qio_channel_socket_flush() was implemented by counting how many times
sendmsg(...,MSG_ZEROCOPY) was successfully called, and then reading the
socket's error queue, in order to find how many of them finished sending.
Flush will loop until those counters are the same, or until some error occurs.
Notes on using writev() with QIO_CHANNEL_WRITE_FLAG_ZERO_COPY:
1: Buffer
- As MSG_ZEROCOPY tells the kernel to use the same user buffer to avoid copying,
some caution is necessary to avoid overwriting any buffer before it's sent.
If something like this happen, a newer version of the buffer may be sent instead.
- If this is a problem, it's recommended to call qio_channel_flush() before freeing
or re-using the buffer.
2: Locked memory
- When using MSG_ZERCOCOPY, the buffer memory will be locked after queued, and
unlocked after it's sent.
- Depending on the size of each buffer, and how often it's sent, it may require
a larger amount of locked memory than usually available to non-root user.
- If the required amount of locked memory is not available, writev_zero_copy
will return an error, which can abort an operation like migration,
- Because of this, when an user code wants to add zero copy as a feature, it
requires a mechanism to disable it, so it can still be accessible to less
privileged users.
Signed-off-by: Leonardo Bras <leobras@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Message-Id: <20220513062836.965425-4-leobras@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
(cherry picked from commit 2bc58ffc2926a4efdd03edfb5909861fefc68c3d)
Signed-off-by: Leonardo Bras <leobras@redhat.com>
---
include/io/channel-socket.h | 2 +
io/channel-socket.c | 116 ++++++++++++++++++++++++++++++++++--
2 files changed, 114 insertions(+), 4 deletions(-)
diff --git a/include/io/channel-socket.h b/include/io/channel-socket.h
index e747e63514..513c428fe4 100644
--- a/include/io/channel-socket.h
+++ b/include/io/channel-socket.h
@@ -47,6 +47,8 @@ struct QIOChannelSocket {
socklen_t localAddrLen;
struct sockaddr_storage remoteAddr;
socklen_t remoteAddrLen;
+ ssize_t zero_copy_queued;
+ ssize_t zero_copy_sent;
};
diff --git a/io/channel-socket.c b/io/channel-socket.c
index a1be2197ca..fbd2214d20 100644
--- a/io/channel-socket.c
+++ b/io/channel-socket.c
@@ -26,6 +26,14 @@
#include "io/channel-watch.h"
#include "trace.h"
#include "qapi/clone-visitor.h"
+#ifdef CONFIG_LINUX
+#include <linux/errqueue.h>
+#include <sys/socket.h>
+
+#if (defined(MSG_ZEROCOPY) && defined(SO_ZEROCOPY))
+#define QEMU_MSG_ZEROCOPY
+#endif
+#endif
#define SOCKET_MAX_FDS 16
@@ -55,6 +63,8 @@ qio_channel_socket_new(void)
sioc = QIO_CHANNEL_SOCKET(object_new(TYPE_QIO_CHANNEL_SOCKET));
sioc->fd = -1;
+ sioc->zero_copy_queued = 0;
+ sioc->zero_copy_sent = 0;
ioc = QIO_CHANNEL(sioc);
qio_channel_set_feature(ioc, QIO_CHANNEL_FEATURE_SHUTDOWN);
@@ -154,6 +164,16 @@ int qio_channel_socket_connect_sync(QIOChannelSocket *ioc,
return -1;
}
+#ifdef QEMU_MSG_ZEROCOPY
+ int ret, v = 1;
+ ret = setsockopt(fd, SOL_SOCKET, SO_ZEROCOPY, &v, sizeof(v));
+ if (ret == 0) {
+ /* Zero copy available on host */
+ qio_channel_set_feature(QIO_CHANNEL(ioc),
+ QIO_CHANNEL_FEATURE_WRITE_ZERO_COPY);
+ }
+#endif
+
return 0;
}
@@ -534,6 +554,7 @@ static ssize_t qio_channel_socket_writev(QIOChannel *ioc,
char control[CMSG_SPACE(sizeof(int) * SOCKET_MAX_FDS)];
size_t fdsize = sizeof(int) * nfds;
struct cmsghdr *cmsg;
+ int sflags = 0;
memset(control, 0, CMSG_SPACE(sizeof(int) * SOCKET_MAX_FDS));
@@ -558,15 +579,31 @@ static ssize_t qio_channel_socket_writev(QIOChannel *ioc,
memcpy(CMSG_DATA(cmsg), fds, fdsize);
}
+#ifdef QEMU_MSG_ZEROCOPY
+ if (flags & QIO_CHANNEL_WRITE_FLAG_ZERO_COPY) {
+ sflags = MSG_ZEROCOPY;
+ }
+#endif
+
retry:
- ret = sendmsg(sioc->fd, &msg, 0);
+ ret = sendmsg(sioc->fd, &msg, sflags);
if (ret <= 0) {
- if (errno == EAGAIN) {
+ switch (errno) {
+ case EAGAIN:
return QIO_CHANNEL_ERR_BLOCK;
- }
- if (errno == EINTR) {
+ case EINTR:
goto retry;
+#ifdef QEMU_MSG_ZEROCOPY
+ case ENOBUFS:
+ if (sflags & MSG_ZEROCOPY) {
+ error_setg_errno(errp, errno,
+ "Process can't lock enough memory for using MSG_ZEROCOPY");
+ return -1;
+ }
+ break;
+#endif
}
+
error_setg_errno(errp, errno,
"Unable to write to socket");
return -1;
@@ -660,6 +697,74 @@ static ssize_t qio_channel_socket_writev(QIOChannel *ioc,
}
#endif /* WIN32 */
+
+#ifdef QEMU_MSG_ZEROCOPY
+static int qio_channel_socket_flush(QIOChannel *ioc,
+ Error **errp)
+{
+ QIOChannelSocket *sioc = QIO_CHANNEL_SOCKET(ioc);
+ struct msghdr msg = {};
+ struct sock_extended_err *serr;
+ struct cmsghdr *cm;
+ char control[CMSG_SPACE(sizeof(*serr))];
+ int received;
+ int ret = 1;
+
+ msg.msg_control = control;
+ msg.msg_controllen = sizeof(control);
+ memset(control, 0, sizeof(control));
+
+ while (sioc->zero_copy_sent < sioc->zero_copy_queued) {
+ received = recvmsg(sioc->fd, &msg, MSG_ERRQUEUE);
+ if (received < 0) {
+ switch (errno) {
+ case EAGAIN:
+ /* Nothing on errqueue, wait until something is available */
+ qio_channel_wait(ioc, G_IO_ERR);
+ continue;
+ case EINTR:
+ continue;
+ default:
+ error_setg_errno(errp, errno,
+ "Unable to read errqueue");
+ return -1;
+ }
+ }
+
+ cm = CMSG_FIRSTHDR(&msg);
+ if (cm->cmsg_level != SOL_IP &&
+ cm->cmsg_type != IP_RECVERR) {
+ error_setg_errno(errp, EPROTOTYPE,
+ "Wrong cmsg in errqueue");
+ return -1;
+ }
+
+ serr = (void *) CMSG_DATA(cm);
+ if (serr->ee_errno != SO_EE_ORIGIN_NONE) {
+ error_setg_errno(errp, serr->ee_errno,
+ "Error on socket");
+ return -1;
+ }
+ if (serr->ee_origin != SO_EE_ORIGIN_ZEROCOPY) {
+ error_setg_errno(errp, serr->ee_origin,
+ "Error not from zero copy");
+ return -1;
+ }
+
+ /* No errors, count successfully finished sendmsg()*/
+ sioc->zero_copy_sent += serr->ee_data - serr->ee_info + 1;
+
+ /* If any sendmsg() succeeded using zero copy, return 0 at the end */
+ if (serr->ee_code != SO_EE_CODE_ZEROCOPY_COPIED) {
+ ret = 0;
+ }
+ }
+
+ return ret;
+}
+
+#endif /* QEMU_MSG_ZEROCOPY */
+
static int
qio_channel_socket_set_blocking(QIOChannel *ioc,
bool enabled,
@@ -790,6 +895,9 @@ static void qio_channel_socket_class_init(ObjectClass *klass,
ioc_klass->io_set_delay = qio_channel_socket_set_delay;
ioc_klass->io_create_watch = qio_channel_socket_create_watch;
ioc_klass->io_set_aio_fd_handler = qio_channel_socket_set_aio_fd_handler;
+#ifdef QEMU_MSG_ZEROCOPY
+ ioc_klass->io_flush = qio_channel_socket_flush;
+#endif
}
static const TypeInfo qio_channel_socket_info = {
--
2.35.3

82
SOURCES/kvm-QIOChannelSocket-Introduce-assert-and-reduce-ifdefs-.patch
View File

@ -1,82 +0,0 @@
From 60bf942a58db12c821f2a6a49e2e0b04b99bec30 Mon Sep 17 00:00:00 2001
From: Leonardo Bras <leobras@redhat.com>
Date: Mon, 20 Jun 2022 02:39:42 -0300
Subject: [PATCH 15/18] QIOChannelSocket: Introduce assert and reduce ifdefs to
improve readability
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Leonardo Brás <leobras@redhat.com>
RH-MergeRequest: 95: MSG_ZEROCOPY + Multifd
RH-Commit: [9/11] eaa02d68301852ccc98bdacc7387d8d03be1cb05 (LeoBras/centos-qemu-kvm)
RH-Bugzilla: 1968509
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
RH-Acked-by: Peter Xu <peterx@redhat.com>
During implementation of MSG_ZEROCOPY feature, a lot of #ifdefs were
introduced, particularly at qio_channel_socket_writev().
Rewrite some of those changes so it's easier to read.
Also, introduce an assert to help detect incorrect zero-copy usage is when
it's disabled on build.
Signed-off-by: Leonardo Bras <leobras@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
dgilbert: Fixed up thinko'd g_assert_unreachable->g_assert_not_reached
(cherry picked from commit 803ca43e4c7fcf32f9f68c118301ccd0c83ece3f)
Signed-off-by: Leonardo Bras <leobras@redhat.com>
---
io/channel-socket.c | 14 +++++++++-----
1 file changed, 9 insertions(+), 5 deletions(-)
diff --git a/io/channel-socket.c b/io/channel-socket.c
index fbd2214d20..7490e5943d 100644
--- a/io/channel-socket.c
+++ b/io/channel-socket.c
@@ -579,11 +579,17 @@ static ssize_t qio_channel_socket_writev(QIOChannel *ioc,
memcpy(CMSG_DATA(cmsg), fds, fdsize);
}
-#ifdef QEMU_MSG_ZEROCOPY
if (flags & QIO_CHANNEL_WRITE_FLAG_ZERO_COPY) {
+#ifdef QEMU_MSG_ZEROCOPY
sflags = MSG_ZEROCOPY;
- }
+#else
+ /*
+ * We expect QIOChannel class entry point to have
+ * blocked this code path already
+ */
+ g_assert_not_reached();
#endif
+ }
retry:
ret = sendmsg(sioc->fd, &msg, sflags);
@@ -593,15 +599,13 @@ static ssize_t qio_channel_socket_writev(QIOChannel *ioc,
return QIO_CHANNEL_ERR_BLOCK;
case EINTR:
goto retry;
-#ifdef QEMU_MSG_ZEROCOPY
case ENOBUFS:
- if (sflags & MSG_ZEROCOPY) {
+ if (flags & QIO_CHANNEL_WRITE_FLAG_ZERO_COPY) {
error_setg_errno(errp, errno,
"Process can't lock enough memory for using MSG_ZEROCOPY");
return -1;
}
break;
-#endif
}
error_setg_errno(errp, errno,
--
2.35.3

237
SOURCES/kvm-RHEL-only-AArch64-Drop-unsupported-CPU-types.patch
View File

@ -1,237 +0,0 @@
From 055edf068196622a3e1868c9e4c991d410272a6d Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Wed, 15 Jun 2022 15:28:27 +0200
Subject: [PATCH 03/18] RHEL-only: AArch64: Drop unsupported CPU types
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: 94: i386, aarch64, s390x: deprecate many named CPU models
RH-Commit: [3/6] 21f54c86dc87e5e75a64459b5a385686bc09640c (berrange/centos-src-qemu)
RH-Bugzilla: 2060839
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2066824
Upstream Status: RHEL only
We only need to support AArch64 cpu types and we only need three
types:
1) A base type to use with TCG, i.e. a cpu type with only base
features. 'cortex-a57' serves this role and is currently used
by libguestfs.
2) The 'max' type, which is for both KVM and TCG and is good for
tests that just specify 'max' but run under both. 'max' with
TCG also provides the VM with all the CPU features TCG
supports, which is good for VMs that need features not
provided by the basic cortex-a57.
3) The host type which is used with KVM.
Signed-off-by: Andrew Jones <drjones@redhat.com>
---
hw/arm/virt.c | 4 ++++
target/arm/cpu64.c | 6 ++++++
target/arm/cpu_tcg.c | 12 ++----------
tests/qtest/arm-cpu-features.c | 6 ++++++
4 files changed, 18 insertions(+), 10 deletions(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 95d012d6eb..74119976d3 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -239,12 +239,16 @@ static const int a15irqmap[] = {
};
static const char *valid_cpus[] = {
+#if 0 /* Disabled for Red Hat Enterprise Linux */
ARM_CPU_TYPE_NAME("cortex-a7"),
ARM_CPU_TYPE_NAME("cortex-a15"),
ARM_CPU_TYPE_NAME("cortex-a53"),
+#endif /* disabled for RHEL */
ARM_CPU_TYPE_NAME("cortex-a57"),
+#if 0 /* Disabled for Red Hat Enterprise Linux */
ARM_CPU_TYPE_NAME("cortex-a72"),
ARM_CPU_TYPE_NAME("a64fx"),
+#endif /* disabled for RHEL */
ARM_CPU_TYPE_NAME("host"),
ARM_CPU_TYPE_NAME("max"),
};
diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c
index eb44c05822..e80b831073 100644
--- a/target/arm/cpu64.c
+++ b/target/arm/cpu64.c
@@ -146,6 +146,7 @@ static void aarch64_a57_initfn(Object *obj)
define_arm_cp_regs(cpu, cortex_a72_a57_a53_cp_reginfo);
}
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void aarch64_a53_initfn(Object *obj)
{
ARMCPU *cpu = ARM_CPU(obj);
@@ -249,6 +250,7 @@ static void aarch64_a72_initfn(Object *obj)
cpu->gic_vprebits = 5;
define_arm_cp_regs(cpu, cortex_a72_a57_a53_cp_reginfo);
}
+#endif /* disabled for RHEL */
void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp)
{
@@ -923,6 +925,7 @@ static void aarch64_max_initfn(Object *obj)
qdev_property_add_static(DEVICE(obj), &arm_cpu_lpa2_property);
}
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void aarch64_a64fx_initfn(Object *obj)
{
ARMCPU *cpu = ARM_CPU(obj);
@@ -969,12 +972,15 @@ static void aarch64_a64fx_initfn(Object *obj)
/* TODO: Add A64FX specific HPC extension registers */
}
+#endif /* disabled for RHEL */
static const ARMCPUInfo aarch64_cpus[] = {
{ .name = "cortex-a57", .initfn = aarch64_a57_initfn },
+#if 0 /* Disabled for Red Hat Enterprise Linux */
{ .name = "cortex-a53", .initfn = aarch64_a53_initfn },
{ .name = "cortex-a72", .initfn = aarch64_a72_initfn },
{ .name = "a64fx", .initfn = aarch64_a64fx_initfn },
+#endif /* disabled for RHEL */
{ .name = "max", .initfn = aarch64_max_initfn },
#if defined(CONFIG_KVM) || defined(CONFIG_HVF)
{ .name = "host", .initfn = aarch64_host_initfn },
diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c
index 3826fa5122..74727fc92c 100644
--- a/target/arm/cpu_tcg.c
+++ b/target/arm/cpu_tcg.c
@@ -19,10 +19,10 @@
#include "hw/boards.h"
#endif
+#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) && defined(CONFIG_TCG)
static bool arm_v7m_cpu_exec_interrupt(CPUState *cs, int interrupt_request)
{
@@ -376,7 +376,6 @@ static void cortex_a9_initfn(Object *obj)
cpu->ccsidr[1] = 0x200fe019; /* 16k L1 icache. */
define_arm_cp_regs(cpu, cortexa9_cp_reginfo);
}
-#endif /* disabled for RHEL */
#ifndef CONFIG_USER_ONLY
static uint64_t a15_l2ctlr_read(CPUARMState *env, const ARMCPRegInfo *ri)
@@ -402,7 +401,6 @@ static const ARMCPRegInfo cortexa15_cp_reginfo[] = {
REGINFO_SENTINEL
};
-#if 0 /* Disabled for Red Hat Enterprise Linux */
static void cortex_a7_initfn(Object *obj)
{
ARMCPU *cpu = ARM_CPU(obj);
@@ -448,7 +446,6 @@ static void cortex_a7_initfn(Object *obj)
cpu->ccsidr[2] = 0x711fe07a; /* 4096K L2 unified cache */
define_arm_cp_regs(cpu, cortexa15_cp_reginfo); /* Same as A15 */
}
-#endif /* disabled for RHEL */
static void cortex_a15_initfn(Object *obj)
{
@@ -492,7 +489,6 @@ static void cortex_a15_initfn(Object *obj)
define_arm_cp_regs(cpu, cortexa15_cp_reginfo);
}
-#if 0 /* Disabled for Red Hat Enterprise Linux */
static void cortex_m0_initfn(Object *obj)
{
ARMCPU *cpu = ARM_CPU(obj);
@@ -933,7 +929,6 @@ static void arm_v7m_class_init(ObjectClass *oc, void *data)
cc->gdb_core_xml_file = "arm-m-profile.xml";
}
-#endif /* disabled for RHEL */
#ifndef TARGET_AARCH64
/*
@@ -1013,7 +1008,6 @@ static void arm_max_initfn(Object *obj)
#endif /* !TARGET_AARCH64 */
static const ARMCPUInfo arm_tcg_cpus[] = {
-#if 0 /* Disabled for Red Hat Enterprise Linux */
{ .name = "arm926", .initfn = arm926_initfn },
{ .name = "arm946", .initfn = arm946_initfn },
{ .name = "arm1026", .initfn = arm1026_initfn },
@@ -1029,9 +1023,7 @@ static const ARMCPUInfo arm_tcg_cpus[] = {
{ .name = "cortex-a7", .initfn = cortex_a7_initfn },
{ .name = "cortex-a8", .initfn = cortex_a8_initfn },
{ .name = "cortex-a9", .initfn = cortex_a9_initfn },
-#endif /* disabled for RHEL */
{ .name = "cortex-a15", .initfn = cortex_a15_initfn },
-#if 0 /* Disabled for Red Hat Enterprise Linux */
{ .name = "cortex-m0", .initfn = cortex_m0_initfn,
.class_init = arm_v7m_class_init },
{ .name = "cortex-m3", .initfn = cortex_m3_initfn,
@@ -1062,7 +1054,6 @@ static const ARMCPUInfo arm_tcg_cpus[] = {
{ .name = "pxa270-b1", .initfn = pxa270b1_initfn },
{ .name = "pxa270-c0", .initfn = pxa270c0_initfn },
{ .name = "pxa270-c5", .initfn = pxa270c5_initfn },
-#endif /* disabled for RHEL */
#ifndef TARGET_AARCH64
{ .name = "max", .initfn = arm_max_initfn },
#endif
@@ -1090,3 +1081,4 @@ 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/tests/qtest/arm-cpu-features.c b/tests/qtest/arm-cpu-features.c
index f76652143a..fe2a0a070d 100644
--- a/tests/qtest/arm-cpu-features.c
+++ b/tests/qtest/arm-cpu-features.c
@@ -440,8 +440,10 @@ 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 */
+#if 0 /* Disabled for Red Hat Enterprise Linux */
assert_has_feature_enabled(qts, "cortex-a15", "pmu");
assert_has_not_feature(qts, "cortex-a15", "aarch64");
+#endif /* disabled for RHEL */
/* Enabling and disabling pmu should always work. */
assert_has_feature_enabled(qts, "max", "pmu");
@@ -458,6 +460,7 @@ 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");
+#if 0 /* Disabled for Red Hat Enterprise Linux */
assert_has_feature_enabled(qts, "a64fx", "pmu");
assert_has_feature_enabled(qts, "a64fx", "aarch64");
/*
@@ -470,6 +473,7 @@ static void test_query_cpu_model_expansion(const void *data)
"{ 'sve384': true }");
assert_error(qts, "a64fx", "cannot enable sve640",
"{ 'sve640': true }");
+#endif /* disabled for RHEL */
sve_tests_default(qts, "max");
pauth_tests_default(qts, "max");
@@ -505,9 +509,11 @@ static void test_query_cpu_model_expansion_kvm(const void *data)
QDict *resp;
char *error;
+#if 0 /* Disabled for Red Hat Enterprise Linux */
assert_error(qts, "cortex-a15",
"We cannot guarantee the CPU type 'cortex-a15' works "
"with KVM on this host", NULL);
+#endif /* disabled for RHEL */
assert_has_feature_enabled(qts, "host", "aarch64");
--
2.35.3

95
SOURCES/kvm-RHEL-only-tests-avocado-Switch-aarch64-tests-from-a5.patch
View File

@ -1,95 +0,0 @@
From d710394f68eb0b6116dd8ac76f619c192e0d5972 Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Wed, 15 Jun 2022 15:28:27 +0200
Subject: [PATCH 02/18] RHEL-only: tests/avocado: Switch aarch64 tests from a53
to a57
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: 94: i386, aarch64, s390x: deprecate many named CPU models
RH-Commit: [2/6] e85ef69b42c411a6997e4da10ba05176368769b3 (berrange/centos-src-qemu)
RH-Bugzilla: 2060839
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2066824
Upstream Status: RHEL only
We plan to remove the cortex-a53 from the supported cpu types. Switch
all avocado tests that use it to the cortex-a57, which will work the
same and we intend to keep. We don't want to try and upstream this
change since the better upstream change would be to switch from the
a53 to 'max', but the upstream tests also need to use later guest
kernels to use 'max' (see qemu upstream commit 0942820408dc
("hw/arm/virt: Disable LPA2 for -machine virt-6.2")
Signed-off-by: Andrew Jones <drjones@redhat.com>
---
tests/avocado/replay_kernel.py | 2 +-
tests/avocado/reverse_debugging.py | 2 +-
tests/avocado/tcg_plugins.py | 6 +++---
3 files changed, 5 insertions(+), 5 deletions(-)
diff --git a/tests/avocado/replay_kernel.py b/tests/avocado/replay_kernel.py
index 0b2b0dc692..3a7b5f0748 100644
--- a/tests/avocado/replay_kernel.py
+++ b/tests/avocado/replay_kernel.py
@@ -147,7 +147,7 @@ def test_aarch64_virt(self):
"""
:avocado: tags=arch:aarch64
:avocado: tags=machine:virt
- :avocado: tags=cpu:cortex-a53
+ :avocado: tags=cpu:cortex-a57
"""
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 d2921e70c3..66d185ed42 100644
--- a/tests/avocado/reverse_debugging.py
+++ b/tests/avocado/reverse_debugging.py
@@ -198,7 +198,7 @@ def test_aarch64_virt(self):
"""
:avocado: tags=arch:aarch64
:avocado: tags=machine:virt
- :avocado: tags=cpu:cortex-a53
+ :avocado: tags=cpu:cortex-a57
"""
kernel_url = ('https://archives.fedoraproject.org/pub/archive/fedora'
'/linux/releases/29/Everything/aarch64/os/images/pxeboot'
diff --git a/tests/avocado/tcg_plugins.py b/tests/avocado/tcg_plugins.py
index 642d2e49e3..93b3afd823 100644
--- a/tests/avocado/tcg_plugins.py
+++ b/tests/avocado/tcg_plugins.py
@@ -68,7 +68,7 @@ def test_aarch64_virt_insn(self):
:avocado: tags=accel:tcg
:avocado: tags=arch:aarch64
:avocado: tags=machine:virt
- :avocado: tags=cpu:cortex-a53
+ :avocado: tags=cpu:cortex-a57
"""
kernel_path = self._grab_aarch64_kernel()
kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE +
@@ -94,7 +94,7 @@ def test_aarch64_virt_insn_icount(self):
:avocado: tags=accel:tcg
:avocado: tags=arch:aarch64
:avocado: tags=machine:virt
- :avocado: tags=cpu:cortex-a53
+ :avocado: tags=cpu:cortex-a57
"""
kernel_path = self._grab_aarch64_kernel()
kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE +
@@ -120,7 +120,7 @@ def test_aarch64_virt_mem_icount(self):
:avocado: tags=accel:tcg
:avocado: tags=arch:aarch64
:avocado: tags=machine:virt
- :avocado: tags=cpu:cortex-a53
+ :avocado: tags=cpu:cortex-a57
"""
kernel_path = self._grab_aarch64_kernel()
kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE +
--
2.35.3

58
SOURCES/kvm-Revert-globally-limit-the-maximum-number-of-CPUs.patch
View File

@ -1,58 +0,0 @@
From 5ab8613582fd56b847fe75750acb5b7255900b35 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Thu, 9 Jun 2022 11:55:15 +0200
Subject: [PATCH 15/16] Revert "globally limit the maximum number of CPUs"
RH-Author: Vitaly Kuznetsov <vkuznets@redhat.com>
RH-MergeRequest: 99: Revert "globally limit the maximum number of CPUs"
RH-Commit: [1/1] 13100d4a2209b2190a3654c1f9cf4ebade1e8d24 (vkuznets/qemu-kvm-c9s)
RH-Bugzilla: 2094270
RH-Acked-by: Andrew Jones <drjones@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2094270
Brew: https://brewweb.engineering.redhat.com/brew/taskinfo?taskID=45871149
Upstream Status: RHEL-only
Tested: with upstream kernel
Downstream QEMU carries a patch that sets the hard limit of possible vCPUs
to the value that the KVM code of the kernel recommends as soft limit.
Upstream KVM code has been changed recently to not use an arbitrary soft
limit anymore, but to cap the value on the amount of available physical
CPUs of the host. This defeats the purpose of the downstream change in
QEMU completely. Drop the downstream-only patch to allow CPU overcommit.
This reverts commit 6669f6fa677d43144f39d6ad59725b7ba622f1c2.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
---
accel/kvm/kvm-all.c | 12 ------------
1 file changed, 12 deletions(-)
diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index fdf0e4d429..5f1377ca04 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -2430,18 +2430,6 @@ static int kvm_init(MachineState *ms)
soft_vcpus_limit = kvm_recommended_vcpus(s);
hard_vcpus_limit = kvm_max_vcpus(s);
-#ifdef HOST_PPC64
- /*
- * On POWER, the kernel advertises a soft limit based on the
- * number of CPU threads on the host. We want to allow exceeding
- * this for testing purposes, so we don't want to set hard limit
- * to soft limit as on x86.
- */
-#else
- /* RHEL doesn't support nr_vcpus > soft_vcpus_limit */
- hard_vcpus_limit = soft_vcpus_limit;
-#endif
-
while (nc->name) {
if (nc->num > soft_vcpus_limit) {
warn_report("Number of %s cpus requested (%d) exceeds "
--
2.31.1

134
SOURCES/kvm-Revert-migration-Simplify-unqueue_page.patch
View File

@ -1,134 +0,0 @@
From 5ea59b17866add54e5ae8c76d3cb472c67e1fa91 Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Tue, 2 Aug 2022 08:19:49 +0200
Subject: [PATCH 32/32] Revert "migration: Simplify unqueue_page()"
RH-Author: Thomas Huth <thuth@redhat.com>
RH-MergeRequest: 112: Fix postcopy migration on s390x
RH-Commit: [2/2] 3913c9ed3f27f4b66245913da29d0c46db0c6567 (thuth/qemu-kvm-cs9)
RH-Bugzilla: 2099934
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Peter Xu <peterx@redhat.com>
This reverts commit cfd66f30fb0f735df06ff4220e5000290a43dad3.
The simplification of unqueue_page() introduced a bug that sometimes
breaks migration on s390x hosts.
The problem is not fully understood yet, but since we are already in
the freeze for QEMU 7.1 and we need something working there, let's
revert this patch for the upcoming release. The optimization can be
redone later again in a proper way if necessary.
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2099934
Signed-off-by: Thomas Huth <thuth@redhat.com>
Message-Id: <20220802061949.331576-1-thuth@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
(cherry picked from commit 777f53c75983dd10756f5dbfc8af50fe11da81c1)
Conflicts:
migration/trace-events
(trivial contextual conflict)
Signed-off-by: Thomas Huth <thuth@redhat.com>
---
migration/ram.c | 37 ++++++++++++++++++++++++++-----------
migration/trace-events | 3 ++-
2 files changed, 28 insertions(+), 12 deletions(-)
diff --git a/migration/ram.c b/migration/ram.c
index fb6db54642..ee40e4a718 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -1548,7 +1548,6 @@ static RAMBlock *unqueue_page(RAMState *rs, ram_addr_t *offset)
{
struct RAMSrcPageRequest *entry;
RAMBlock *block = NULL;
- size_t page_size;
if (!postcopy_has_request(rs)) {
return NULL;
@@ -1565,13 +1564,10 @@ static RAMBlock *unqueue_page(RAMState *rs, ram_addr_t *offset)
entry = QSIMPLEQ_FIRST(&rs->src_page_requests);
block = entry->rb;
*offset = entry->offset;
- page_size = qemu_ram_pagesize(block);
- /* Each page request should only be multiple page size of the ramblock */
- assert((entry->len % page_size) == 0);
- if (entry->len > page_size) {
- entry->len -= page_size;
- entry->offset += page_size;
+ if (entry->len > TARGET_PAGE_SIZE) {
+ entry->len -= TARGET_PAGE_SIZE;
+ entry->offset += TARGET_PAGE_SIZE;
} else {
memory_region_unref(block->mr);
QSIMPLEQ_REMOVE_HEAD(&rs->src_page_requests, next_req);
@@ -1579,9 +1575,6 @@ static RAMBlock *unqueue_page(RAMState *rs, ram_addr_t *offset)
migration_consume_urgent_request();
}
- trace_unqueue_page(block->idstr, *offset,
- test_bit((*offset >> TARGET_PAGE_BITS), block->bmap));
-
return block;
}
@@ -1956,8 +1949,30 @@ static bool get_queued_page(RAMState *rs, PageSearchStatus *pss)
{
RAMBlock *block;
ram_addr_t offset;
+ bool dirty;
+
+ do {
+ block = unqueue_page(rs, &offset);
+ /*
+ * We're sending this page, and since it's postcopy nothing else
+ * will dirty it, and we must make sure it doesn't get sent again
+ * even if this queue request was received after the background
+ * search already sent it.
+ */
+ if (block) {
+ unsigned long page;
+
+ page = offset >> TARGET_PAGE_BITS;
+ dirty = test_bit(page, block->bmap);
+ if (!dirty) {
+ trace_get_queued_page_not_dirty(block->idstr, (uint64_t)offset,
+ page);
+ } else {
+ trace_get_queued_page(block->idstr, (uint64_t)offset, page);
+ }
+ }
- block = unqueue_page(rs, &offset);
+ } while (block && !dirty);
if (!block) {
/*
diff --git a/migration/trace-events b/migration/trace-events
index 1aec580e92..09d61ed1f4 100644
--- a/migration/trace-events
+++ b/migration/trace-events
@@ -85,6 +85,8 @@ put_qlist_end(const char *field_name, const char *vmsd_name) "%s(%s)"
qemu_file_fclose(void) ""
# ram.c
+get_queued_page(const char *block_name, uint64_t tmp_offset, unsigned long page_abs) "%s/0x%" PRIx64 " page_abs=0x%lx"
+get_queued_page_not_dirty(const char *block_name, uint64_t tmp_offset, unsigned long page_abs) "%s/0x%" PRIx64 " page_abs=0x%lx"
migration_bitmap_sync_start(void) ""
migration_bitmap_sync_end(uint64_t dirty_pages) "dirty_pages %" PRIu64
migration_bitmap_clear_dirty(char *str, uint64_t start, uint64_t size, unsigned long page) "rb %s start 0x%"PRIx64" size 0x%"PRIx64" page 0x%lx"
@@ -110,7 +112,6 @@ ram_save_iterate_big_wait(uint64_t milliconds, int iterations) "big wait: %" PRI
ram_load_complete(int ret, uint64_t seq_iter) "exit_code %d seq iteration %" PRIu64
ram_write_tracking_ramblock_start(const char *block_id, size_t page_size, void *addr, size_t length) "%s: page_size: %zu addr: %p length: %zu"
ram_write_tracking_ramblock_stop(const char *block_id, size_t page_size, void *addr, size_t length) "%s: page_size: %zu addr: %p length: %zu"
-unqueue_page(char *block, uint64_t offset, bool dirty) "ramblock '%s' offset 0x%"PRIx64" dirty %d"
# multifd.c
multifd_new_send_channel_async(uint8_t id) "channel %u"
--
2.31.1

140
SOURCES/kvm-Revert-vhost-user-Introduce-nested-event-loop-in-vho.patch Normal file
View File

@ -0,0 +1,140 @@
From 0c19fb7c4a22a30830152b224b2e66963f829a7a Mon Sep 17 00:00:00 2001
From: Greg Kurz <groug@kaod.org>
Date: Thu, 19 Jan 2023 18:24:24 +0100
Subject: [PATCH 19/20] Revert "vhost-user: Introduce nested event loop in
vhost_user_read()"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Laurent Vivier <lvivier@redhat.com>
RH-MergeRequest: 146: Fix vhost-user with dpdk
RH-Bugzilla: 2155173
RH-Acked-by: Cindy Lu <lulu@redhat.com>
RH-Acked-by: Greg Kurz (RH) <gkurz@redhat.com>
RH-Acked-by: Eugenio Pérez <eperezma@redhat.com>
RH-Commit: [2/2] 9b67041f92f29f70b7ccb41d8087801e4e4e38af (lvivier/qemu-kvm-centos)
This reverts commit a7f523c7d114d445c5d83aecdba3efc038e5a692.
The nested event loop is broken by design. It's only user was removed.
Drop the code as well so that nobody ever tries to use it again.
I had to fix a couple of trivial conflicts around return values because
of 025faa872bcf ("vhost-user: stick to -errno error return convention").
Signed-off-by: Greg Kurz <groug@kaod.org>
Message-Id: <20230119172424.478268-3-groug@kaod.org>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Maxime Coquelin <maxime.coquelin@redhat.com>
(cherry picked from commit 4382138f642f69fdbc79ebf4e93d84be8061191f)
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
---
hw/virtio/vhost-user.c | 65 ++++--------------------------------------
1 file changed, 5 insertions(+), 60 deletions(-)
diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
index 0ac00eb901..7cb49c50f9 100644
--- a/hw/virtio/vhost-user.c
+++ b/hw/virtio/vhost-user.c
@@ -305,19 +305,8 @@ static int vhost_user_read_header(struct vhost_dev *dev, VhostUserMsg *msg)
return 0;
}
-struct vhost_user_read_cb_data {
- struct vhost_dev *dev;
- VhostUserMsg *msg;
- GMainLoop *loop;
- int ret;
-};
-
-static gboolean vhost_user_read_cb(void *do_not_use, GIOCondition condition,
- gpointer opaque)
+static int vhost_user_read(struct vhost_dev *dev, VhostUserMsg *msg)
{
- struct vhost_user_read_cb_data *data = opaque;
- struct vhost_dev *dev = data->dev;
- VhostUserMsg *msg = data->msg;
struct vhost_user *u = dev->opaque;
CharBackend *chr = u->user->chr;
uint8_t *p = (uint8_t *) msg;
@@ -325,8 +314,7 @@ static gboolean vhost_user_read_cb(void *do_not_use, GIOCondition condition,
r = vhost_user_read_header(dev, msg);
if (r < 0) {
- data->ret = r;
- goto end;
+ return r;
}
/* validate message size is sane */
@@ -334,8 +322,7 @@ static gboolean vhost_user_read_cb(void *do_not_use, GIOCondition condition,
error_report("Failed to read msg header."
" Size %d exceeds the maximum %zu.", msg->hdr.size,
VHOST_USER_PAYLOAD_SIZE);
- data->ret = -EPROTO;
- goto end;
+ return -EPROTO;
}
if (msg->hdr.size) {
@@ -346,53 +333,11 @@ static gboolean vhost_user_read_cb(void *do_not_use, GIOCondition condition,
int saved_errno = errno;
error_report("Failed to read msg payload."
" Read %d instead of %d.", r, msg->hdr.size);
- data->ret = r < 0 ? -saved_errno : -EIO;
- goto end;
+ return r < 0 ? -saved_errno : -EIO;
}
}
-end:
- g_main_loop_quit(data->loop);
- return G_SOURCE_REMOVE;
-}
-
-static int vhost_user_read(struct vhost_dev *dev, VhostUserMsg *msg)
-{
- struct vhost_user *u = dev->opaque;
- CharBackend *chr = u->user->chr;
- GMainContext *prev_ctxt = chr->chr->gcontext;
- GMainContext *ctxt = g_main_context_new();
- GMainLoop *loop = g_main_loop_new(ctxt, FALSE);
- struct vhost_user_read_cb_data data = {
- .dev = dev,
- .loop = loop,
- .msg = msg,
- .ret = 0
- };
-
- /*
- * We want to be able to monitor the slave channel fd while waiting
- * for chr I/O. This requires an event loop, but we can't nest the
- * one to which chr is currently attached : its fd handlers might not
- * be prepared for re-entrancy. So we create a new one and switch chr
- * to use it.
- */
- qemu_chr_be_update_read_handlers(chr->chr, ctxt);
- qemu_chr_fe_add_watch(chr, G_IO_IN | G_IO_HUP, vhost_user_read_cb, &data);
-
- g_main_loop_run(loop);
-
- /*
- * Restore the previous event loop context. This also destroys/recreates
- * event sources : this guarantees that all pending events in the original
- * context that have been processed by the nested loop are purged.
- */
- qemu_chr_be_update_read_handlers(chr->chr, prev_ctxt);
-
- g_main_loop_unref(loop);
- g_main_context_unref(ctxt);
-
- return data.ret;
+ return 0;
}
static int process_message_reply(struct vhost_dev *dev,
--
2.31.1

143
SOURCES/kvm-Revert-vhost-user-Monitor-slave-channel-in-vhost_use.patch Normal file
View File

@ -0,0 +1,143 @@
From 9fb47ad317ad8cdda9960190d499ad6c3a9817f0 Mon Sep 17 00:00:00 2001
From: Greg Kurz <groug@kaod.org>
Date: Thu, 19 Jan 2023 18:24:23 +0100
Subject: [PATCH 18/20] Revert "vhost-user: Monitor slave channel in
vhost_user_read()"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Laurent Vivier <lvivier@redhat.com>
RH-MergeRequest: 146: Fix vhost-user with dpdk
RH-Bugzilla: 2155173
RH-Acked-by: Cindy Lu <lulu@redhat.com>
RH-Acked-by: Greg Kurz (RH) <gkurz@redhat.com>
RH-Acked-by: Eugenio Pérez <eperezma@redhat.com>
RH-Commit: [1/2] c583a7f121ca9c93c9a2ad17bf0ccf5c1241dc99 (lvivier/qemu-kvm-centos)
This reverts commit db8a3772e300c1a656331a92da0785d81667dc81.
Motivation : this is breaking vhost-user with DPDK as reported in [0].
Received unexpected msg type. Expected 22 received 40
Fail to update device iotlb
Received unexpected msg type. Expected 40 received 22
Received unexpected msg type. Expected 22 received 11
Fail to update device iotlb
Received unexpected msg type. Expected 11 received 22
vhost VQ 1 ring restore failed: -71: Protocol error (71)
Received unexpected msg type. Expected 22 received 11
Fail to update device iotlb
Received unexpected msg type. Expected 11 received 22
vhost VQ 0 ring restore failed: -71: Protocol error (71)
unable to start vhost net: 71: falling back on userspace virtio
The failing sequence that leads to the first error is :
- QEMU sends a VHOST_USER_GET_STATUS (40) request to DPDK on the master
socket
- QEMU starts a nested event loop in order to wait for the
VHOST_USER_GET_STATUS response and to be able to process messages from
the slave channel
- DPDK sends a couple of legitimate IOTLB miss messages on the slave
channel
- QEMU processes each IOTLB request and sends VHOST_USER_IOTLB_MSG (22)
updates on the master socket
- QEMU assumes to receive a response for the latest VHOST_USER_IOTLB_MSG
but it gets the response for the VHOST_USER_GET_STATUS instead
The subsequent errors have the same root cause : the nested event loop
breaks the order by design. It lures QEMU to expect responses to the
latest message sent on the master socket to arrive first.
Since this was only needed for DAX enablement which is still not merged
upstream, just drop the code for now. A working solution will have to
be merged later on. Likely protect the master socket with a mutex
and service the slave channel with a separate thread, as discussed with
Maxime in the mail thread below.
[0] https://lore.kernel.org/qemu-devel/43145ede-89dc-280e-b953-6a2b436de395@redhat.com/
Reported-by: Yanghang Liu <yanghliu@redhat.com>
Buglink: https://bugzilla.redhat.com/show_bug.cgi?id=2155173
Signed-off-by: Greg Kurz <groug@kaod.org>
Message-Id: <20230119172424.478268-2-groug@kaod.org>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
Acked-by: Maxime Coquelin <maxime.coquelin@redhat.com>
(cherry picked from commit f340a59d5a852d75ae34555723694c7e8eafbd0c)
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
---
hw/virtio/vhost-user.c | 35 +++--------------------------------
1 file changed, 3 insertions(+), 32 deletions(-)
diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
index 8f635844af..0ac00eb901 100644
--- a/hw/virtio/vhost-user.c
+++ b/hw/virtio/vhost-user.c
@@ -356,35 +356,6 @@ end:
return G_SOURCE_REMOVE;
}
-static gboolean slave_read(QIOChannel *ioc, GIOCondition condition,
- gpointer opaque);
-
-/*
- * This updates the read handler to use a new event loop context.
- * Event sources are removed from the previous context : this ensures
- * that events detected in the previous context are purged. They will
- * be re-detected and processed in the new context.
- */
-static void slave_update_read_handler(struct vhost_dev *dev,
- GMainContext *ctxt)
-{
- struct vhost_user *u = dev->opaque;
-
- if (!u->slave_ioc) {
- return;
- }
-
- if (u->slave_src) {
- g_source_destroy(u->slave_src);
- g_source_unref(u->slave_src);
- }
-
- u->slave_src = qio_channel_add_watch_source(u->slave_ioc,
- G_IO_IN | G_IO_HUP,
- slave_read, dev, NULL,
- ctxt);
-}
-
static int vhost_user_read(struct vhost_dev *dev, VhostUserMsg *msg)
{
struct vhost_user *u = dev->opaque;
@@ -406,7 +377,6 @@ static int vhost_user_read(struct vhost_dev *dev, VhostUserMsg *msg)
* be prepared for re-entrancy. So we create a new one and switch chr
* to use it.
*/
- slave_update_read_handler(dev, ctxt);
qemu_chr_be_update_read_handlers(chr->chr, ctxt);
qemu_chr_fe_add_watch(chr, G_IO_IN | G_IO_HUP, vhost_user_read_cb, &data);
@@ -418,7 +388,6 @@ static int vhost_user_read(struct vhost_dev *dev, VhostUserMsg *msg)
* context that have been processed by the nested loop are purged.
*/
qemu_chr_be_update_read_handlers(chr->chr, prev_ctxt);
- slave_update_read_handler(dev, NULL);
g_main_loop_unref(loop);
g_main_context_unref(ctxt);
@@ -1802,7 +1771,9 @@ static int vhost_setup_slave_channel(struct vhost_dev *dev)
return -ECONNREFUSED;
}
u->slave_ioc = ioc;
- slave_update_read_handler(dev, NULL);
+ u->slave_src = qio_channel_add_watch_source(u->slave_ioc,
+ G_IO_IN | G_IO_HUP,
+ slave_read, dev, NULL, NULL);
if (reply_supported) {
msg.hdr.flags |= VHOST_USER_NEED_REPLY_MASK;
--
2.31.1

51
SOURCES/kvm-Revert-virtio-scsi-Reject-scsi-cd-if-data-plane-enab.patch
View File

@ -1,51 +0,0 @@
From 733acef2caea0758edd74fb634b095ce09bf5914 Mon Sep 17 00:00:00 2001
From: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Date: Mon, 9 May 2022 03:46:23 -0400
Subject: [PATCH 15/16] Revert "virtio-scsi: Reject scsi-cd if data plane
enabled [RHEL only]"
RH-Author: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-MergeRequest: 91: Revert "virtio-scsi: Reject scsi-cd if data plane enabled [RHEL only]"
RH-Commit: [1/1] 1af55d792bc9166e5c86272afe8093c76ab41bb4 (eesposit/qemu-kvm)
RH-Bugzilla: 1995710
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
This reverts commit 4e17b1126e.
Over time AioContext usage and coverage has increased, and now block
backend is capable of handling AioContext change upon eject and insert.
Therefore the above downstream-only commit is not necessary anymore,
and can be safely reverted.
X-downstream-only: true
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
---
hw/scsi/virtio-scsi.c | 9 ---------
1 file changed, 9 deletions(-)
diff --git a/hw/scsi/virtio-scsi.c b/hw/scsi/virtio-scsi.c
index 2450c9438c..db54d104be 100644
--- a/hw/scsi/virtio-scsi.c
+++ b/hw/scsi/virtio-scsi.c
@@ -937,15 +937,6 @@ static void virtio_scsi_hotplug(HotplugHandler *hotplug_dev, DeviceState *dev,
AioContext *old_context;
int ret;
- /* XXX: Remove this check once block backend is capable of handling
- * AioContext change upon eject/insert.
- * s->ctx is NULL if ioeventfd is off, s->ctx is qemu_get_aio_context() if
- * data plane is not used, both cases are safe for scsi-cd. */
- if (s->ctx && s->ctx != qemu_get_aio_context() &&
- object_dynamic_cast(OBJECT(dev), "scsi-cd")) {
- error_setg(errp, "scsi-cd is not supported by data plane");
- return;
- }
if (s->ctx && !s->dataplane_fenced) {
if (blk_op_is_blocked(sd->conf.blk, BLOCK_OP_TYPE_DATAPLANE, errp)) {
return;
--
2.31.1

348
SOURCES/kvm-accel-introduce-accelerator-blocker-API.patch Normal file
View File

@ -0,0 +1,348 @@
From ae2077fd5d351a68c313c64f07fb225dff694a8f Mon Sep 17 00:00:00 2001
From: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Date: Mon, 16 Jan 2023 07:16:41 -0500
Subject: [PATCH 29/31] accel: introduce accelerator blocker API
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-MergeRequest: 138: accel: introduce accelerator blocker API
RH-Bugzilla: 1979276
RH-Acked-by: Paolo Bonzini <pbonzini@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [1/3] 56b07cd7db516c5066e6d66b4695064fdf73abbf (eesposit/qemu-kvm)
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1979276
commit bd688fc93120fb3e28aa70e3dfdf567ccc1e0bc1
Author: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Date: Fri Nov 11 10:47:56 2022 -0500
accel: introduce accelerator blocker API
This API allows the accelerators to prevent vcpus from issuing
new ioctls while execting a critical section marked with the
accel_ioctl_inhibit_begin/end functions.
Note that all functions submitting ioctls must mark where the
ioctl is being called with accel_{cpu_}ioctl_begin/end().
This API requires the caller to always hold the BQL.
API documentation is in sysemu/accel-blocker.h
Internally, it uses a QemuLockCnt together with a per-CPU QemuLockCnt
(to minimize cache line bouncing) to keep avoid that new ioctls
run when the critical section starts, and a QemuEvent to wait
that all running ioctls finish.
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-Id: <20221111154758.1372674-2-eesposit@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Conflicts:
util/meson.build: "interval-tree.c" does not exist
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
---
accel/accel-blocker.c | 154 +++++++++++++++++++++++++++++++++
accel/meson.build | 2 +-
hw/core/cpu-common.c | 2 +
include/hw/core/cpu.h | 3 +
include/sysemu/accel-blocker.h | 56 ++++++++++++
util/meson.build | 2 +-
6 files changed, 217 insertions(+), 2 deletions(-)
create mode 100644 accel/accel-blocker.c
create mode 100644 include/sysemu/accel-blocker.h
diff --git a/accel/accel-blocker.c b/accel/accel-blocker.c
new file mode 100644
index 0000000000..1e7f423462
--- /dev/null
+++ b/accel/accel-blocker.c
@@ -0,0 +1,154 @@
+/*
+ * Lock to inhibit accelerator ioctls
+ *
+ * Copyright (c) 2022 Red Hat Inc.
+ *
+ * Author: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "qemu/osdep.h"
+#include "qemu/thread.h"
+#include "qemu/main-loop.h"
+#include "hw/core/cpu.h"
+#include "sysemu/accel-blocker.h"
+
+static QemuLockCnt accel_in_ioctl_lock;
+static QemuEvent accel_in_ioctl_event;
+
+void accel_blocker_init(void)
+{
+ qemu_lockcnt_init(&accel_in_ioctl_lock);
+ qemu_event_init(&accel_in_ioctl_event, false);
+}
+
+void accel_ioctl_begin(void)
+{
+ if (likely(qemu_mutex_iothread_locked())) {
+ return;
+ }
+
+ /* block if lock is taken in kvm_ioctl_inhibit_begin() */
+ qemu_lockcnt_inc(&accel_in_ioctl_lock);
+}
+
+void accel_ioctl_end(void)
+{
+ if (likely(qemu_mutex_iothread_locked())) {
+ return;
+ }
+
+ qemu_lockcnt_dec(&accel_in_ioctl_lock);
+ /* change event to SET. If event was BUSY, wake up all waiters */
+ qemu_event_set(&accel_in_ioctl_event);
+}
+
+void accel_cpu_ioctl_begin(CPUState *cpu)
+{
+ if (unlikely(qemu_mutex_iothread_locked())) {
+ return;
+ }
+
+ /* block if lock is taken in kvm_ioctl_inhibit_begin() */
+ qemu_lockcnt_inc(&cpu->in_ioctl_lock);
+}
+
+void accel_cpu_ioctl_end(CPUState *cpu)
+{
+ if (unlikely(qemu_mutex_iothread_locked())) {
+ return;
+ }
+
+ qemu_lockcnt_dec(&cpu->in_ioctl_lock);
+ /* change event to SET. If event was BUSY, wake up all waiters */
+ qemu_event_set(&accel_in_ioctl_event);
+}
+
+static bool accel_has_to_wait(void)
+{
+ CPUState *cpu;
+ bool needs_to_wait = false;
+
+ CPU_FOREACH(cpu) {
+ if (qemu_lockcnt_count(&cpu->in_ioctl_lock)) {
+ /* exit the ioctl, if vcpu is running it */
+ qemu_cpu_kick(cpu);
+ needs_to_wait = true;
+ }
+ }
+
+ return needs_to_wait || qemu_lockcnt_count(&accel_in_ioctl_lock);
+}
+
+void accel_ioctl_inhibit_begin(void)
+{
+ CPUState *cpu;
+
+ /*
+ * We allow to inhibit only when holding the BQL, so we can identify
+ * when an inhibitor wants to issue an ioctl easily.
+ */
+ g_assert(qemu_mutex_iothread_locked());
+
+ /* Block further invocations of the ioctls outside the BQL. */
+ CPU_FOREACH(cpu) {
+ qemu_lockcnt_lock(&cpu->in_ioctl_lock);
+ }
+ qemu_lockcnt_lock(&accel_in_ioctl_lock);
+
+ /* Keep waiting until there are running ioctls */
+ while (true) {
+
+ /* Reset event to FREE. */
+ qemu_event_reset(&accel_in_ioctl_event);
+
+ if (accel_has_to_wait()) {
+ /*
+ * If event is still FREE, and there are ioctls still in progress,
+ * wait.
+ *
+ * If an ioctl finishes before qemu_event_wait(), it will change
+ * the event state to SET. This will prevent qemu_event_wait() from
+ * blocking, but it's not a problem because if other ioctls are
+ * still running the loop will iterate once more and reset the event
+ * status to FREE so that it can wait properly.
+ *
+ * If an ioctls finishes while qemu_event_wait() is blocking, then
+ * it will be waken up, but also here the while loop makes sure
+ * to re-enter the wait if there are other running ioctls.
+ */
+ qemu_event_wait(&accel_in_ioctl_event);
+ } else {
+ /* No ioctl is running */
+ return;
+ }
+ }
+}
+
+void accel_ioctl_inhibit_end(void)
+{
+ CPUState *cpu;
+
+ qemu_lockcnt_unlock(&accel_in_ioctl_lock);
+ CPU_FOREACH(cpu) {
+ qemu_lockcnt_unlock(&cpu->in_ioctl_lock);
+ }
+}
+
diff --git a/accel/meson.build b/accel/meson.build
index 259c35c4c8..061332610f 100644
--- a/accel/meson.build
+++ b/accel/meson.build
@@ -1,4 +1,4 @@
-specific_ss.add(files('accel-common.c'))
+specific_ss.add(files('accel-common.c', 'accel-blocker.c'))
softmmu_ss.add(files('accel-softmmu.c'))
user_ss.add(files('accel-user.c'))
diff --git a/hw/core/cpu-common.c b/hw/core/cpu-common.c
index f9fdd46b9d..8d6a4b1b65 100644
--- a/hw/core/cpu-common.c
+++ b/hw/core/cpu-common.c
@@ -237,6 +237,7 @@ static void cpu_common_initfn(Object *obj)
cpu->nr_threads = 1;
qemu_mutex_init(&cpu->work_mutex);
+ qemu_lockcnt_init(&cpu->in_ioctl_lock);
QSIMPLEQ_INIT(&cpu->work_list);
QTAILQ_INIT(&cpu->breakpoints);
QTAILQ_INIT(&cpu->watchpoints);
@@ -248,6 +249,7 @@ static void cpu_common_finalize(Object *obj)
{
CPUState *cpu = CPU(obj);
+ qemu_lockcnt_destroy(&cpu->in_ioctl_lock);
qemu_mutex_destroy(&cpu->work_mutex);
}
diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h
index 8830546121..2417597236 100644
--- a/include/hw/core/cpu.h
+++ b/include/hw/core/cpu.h
@@ -398,6 +398,9 @@ struct CPUState {
uint32_t kvm_fetch_index;
uint64_t dirty_pages;
+ /* Use by accel-block: CPU is executing an ioctl() */
+ QemuLockCnt in_ioctl_lock;
+
/* Used for events with 'vcpu' and *without* the 'disabled' properties */
DECLARE_BITMAP(trace_dstate_delayed, CPU_TRACE_DSTATE_MAX_EVENTS);
DECLARE_BITMAP(trace_dstate, CPU_TRACE_DSTATE_MAX_EVENTS);
diff --git a/include/sysemu/accel-blocker.h b/include/sysemu/accel-blocker.h
new file mode 100644
index 0000000000..72020529ef
--- /dev/null
+++ b/include/sysemu/accel-blocker.h
@@ -0,0 +1,56 @@
+/*
+ * Accelerator blocking API, to prevent new ioctls from starting and wait the
+ * running ones finish.
+ * This mechanism differs from pause/resume_all_vcpus() in that it does not
+ * release the BQL.
+ *
+ * Copyright (c) 2022 Red Hat Inc.
+ *
+ * Author: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+#ifndef ACCEL_BLOCKER_H
+#define ACCEL_BLOCKER_H
+
+#include "qemu/osdep.h"
+#include "sysemu/cpus.h"
+
+extern void accel_blocker_init(void);
+
+/*
+ * accel_{cpu_}ioctl_begin/end:
+ * Mark when ioctl is about to run or just finished.
+ *
+ * accel_{cpu_}ioctl_begin will block after accel_ioctl_inhibit_begin() is
+ * called, preventing new ioctls to run. They will continue only after
+ * accel_ioctl_inibith_end().
+ */
+extern void accel_ioctl_begin(void);
+extern void accel_ioctl_end(void);
+extern void accel_cpu_ioctl_begin(CPUState *cpu);
+extern void accel_cpu_ioctl_end(CPUState *cpu);
+
+/*
+ * accel_ioctl_inhibit_begin: start critical section
+ *
+ * This function makes sure that:
+ * 1) incoming accel_{cpu_}ioctl_begin() calls block
+ * 2) wait that all ioctls that were already running reach
+ * accel_{cpu_}ioctl_end(), kicking vcpus if necessary.
+ *
+ * This allows the caller to access shared data or perform operations without
+ * worrying of concurrent vcpus accesses.
+ */
+extern void accel_ioctl_inhibit_begin(void);
+
+/*
+ * accel_ioctl_inhibit_end: end critical section started by
+ * accel_ioctl_inhibit_begin()
+ *
+ * This function allows blocked accel_{cpu_}ioctl_begin() to continue.
+ */
+extern void accel_ioctl_inhibit_end(void);
+
+#endif /* ACCEL_BLOCKER_H */
diff --git a/util/meson.build b/util/meson.build
index 25b9b61f98..85a5504c4d 100644
--- a/util/meson.build
+++ b/util/meson.build
@@ -57,6 +57,7 @@ util_ss.add(files('guest-random.c'))
util_ss.add(files('yank.c'))
util_ss.add(files('int128.c'))
util_ss.add(files('memalign.c'))
+util_ss.add(files('lockcnt.c'))
if have_user
util_ss.add(files('selfmap.c'))
@@ -71,7 +72,6 @@ endif
if have_block or have_ga
util_ss.add(files('aiocb.c', 'async.c'))
util_ss.add(files('base64.c'))
- util_ss.add(files('lockcnt.c'))
util_ss.add(files('main-loop.c'))
util_ss.add(files('qemu-coroutine.c', 'qemu-coroutine-lock.c', 'qemu-coroutine-io.c'))
util_ss.add(files('coroutine-@0@.c'.format(config_host['CONFIG_COROUTINE_BACKEND'])))
--
2.31.1

58
SOURCES/kvm-accel-tcg-Test-CPUJumpCache-in-tb_jmp_cache_clear_pa.patch Normal file
View File

@ -0,0 +1,58 @@
From ab68e13b7628f2348d41a4518a92508542af712f Mon Sep 17 00:00:00 2001
From: Eric Auger <eric.auger@redhat.com>
Date: Fri, 3 Feb 2023 18:15:10 +0100
Subject: [PATCH 05/20] accel/tcg: Test CPUJumpCache in tb_jmp_cache_clear_page
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 144: accel/tcg: Test CPUJumpCache in tb_jmp_cache_clear_page
RH-Bugzilla: 2165280
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Gavin Shan <gshan@redhat.com>
RH-Acked-by: Shaoqin Huang <None>
RH-Commit: [1/1] 5b0863c34ba06c01c4e343d1ecd72402779c7de3 (eauger1/centos-qemu-kvm)
Bugzilla: https://bugzilla.redhat.com/2165280
Upstream: yes
Brew: https://brewweb.engineering.redhat.com/brew/taskinfo?taskID=50530041
Test: 'kvm unit test ./run_tests.sh -g debug' does not SIGSEV anymore
After commit 4e4fa6c12d ("accel/tcg: Complete cpu initialization
before registration"), it looks the CPUJumpCache pointer can be NULL.
This causes a SIGSEV when running debug-wp-migration kvm unit test.
At the first place it should be clarified why this TCG code is called
with KVM acceleration. This may hide another bug.
Fixes: 4e4fa6c12d ("accel/tcg: Complete cpu initialization before registration")
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Message-Id: <20230203171510.2867451-1-eric.auger@redhat.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
(cherry picked from commit 99ab4d500af638ba3ebb20e8aa89d72201b70860)
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
accel/tcg/cputlb.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c
index 6f1c00682b..4244b0e4e3 100644
--- a/accel/tcg/cputlb.c
+++ b/accel/tcg/cputlb.c
@@ -100,9 +100,14 @@ static void tlb_window_reset(CPUTLBDesc *desc, int64_t ns,
static void tb_jmp_cache_clear_page(CPUState *cpu, target_ulong page_addr)
{
- int i, i0 = tb_jmp_cache_hash_page(page_addr);
CPUJumpCache *jc = cpu->tb_jmp_cache;
+ int i, i0;
+ if (unlikely(!jc)) {
+ return;
+ }
+
+ i0 = tb_jmp_cache_hash_page(page_addr);
for (i = 0; i < TB_JMP_PAGE_SIZE; i++) {
qatomic_set(&jc->array[i0 + i].tb, NULL);
}
--
2.31.1

50
SOURCES/kvm-aio-wait-switch-to-smp_mb__after_rmw.patch Normal file
View File

@ -0,0 +1,50 @@
From e9a9c0b023ae0dcbb14543b74063cca931d8230f Mon Sep 17 00:00:00 2001
From: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Date: Thu, 9 Mar 2023 08:24:36 -0500
Subject: [PATCH 08/12] aio-wait: switch to smp_mb__after_rmw()
RH-Author: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-MergeRequest: 158: qatomic: add smp_mb__before/after_rmw()
RH-Bugzilla: 2175660
RH-Acked-by: Paolo Bonzini <pbonzini@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Commit: [5/9] a90c96d148fdbec340a45dc6cedf3660d8be2aab (eesposit/qemu-kvm)
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2175660
commit b532526a07ef3b903ead2e055fe6cc87b41057a3
Author: Paolo Bonzini <pbonzini@redhat.com>
Date: Fri Mar 3 11:03:52 2023 +0100
aio-wait: switch to smp_mb__after_rmw()
The barrier comes after an atomic increment, so it is enough to use
smp_mb__after_rmw(); this avoids a double barrier on x86 systems.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
---
include/block/aio-wait.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/include/block/aio-wait.h b/include/block/aio-wait.h
index dd9a7f6461..da13357bb8 100644
--- a/include/block/aio-wait.h
+++ b/include/block/aio-wait.h
@@ -85,7 +85,7 @@ extern AioWait global_aio_wait;
/* Increment wait_->num_waiters before evaluating cond. */ \
qatomic_inc(&wait_->num_waiters); \
/* Paired with smp_mb in aio_wait_kick(). */ \
- smp_mb(); \
+ smp_mb__after_rmw(); \
if (ctx_ && in_aio_context_home_thread(ctx_)) { \
while ((cond)) { \
aio_poll(ctx_, true); \
--
2.39.1

66
SOURCES/kvm-async-clarify-usage-of-barriers-in-the-polling-case.patch Normal file
View File

@ -0,0 +1,66 @@
From 3d823dda6832b76fd3d776131008107b0b0f7166 Mon Sep 17 00:00:00 2001
From: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Date: Thu, 9 Mar 2023 08:24:36 -0500
Subject: [PATCH 12/12] async: clarify usage of barriers in the polling case
RH-Author: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-MergeRequest: 158: qatomic: add smp_mb__before/after_rmw()
RH-Bugzilla: 2175660
RH-Acked-by: Paolo Bonzini <pbonzini@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Commit: [9/9] b4ea298d75a75bb61e07a27d1296e0095fbc2bbf (eesposit/qemu-kvm)
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2175660
commit 6229438cca037d42f44a96d38feb15cb102a444f
Author: Paolo Bonzini <pbonzini@redhat.com>
Date: Mon Mar 6 10:43:52 2023 +0100
async: clarify usage of barriers in the polling case
Explain that aio_context_notifier_poll() relies on
aio_notify_accept() to catch all the memory writes that were
done before ctx->notified was set to true.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
---
util/async.c | 10 ++++++++--
1 file changed, 8 insertions(+), 2 deletions(-)
diff --git a/util/async.c b/util/async.c
index 37d3e6036d..e0846baf93 100644
--- a/util/async.c
+++ b/util/async.c
@@ -472,8 +472,9 @@ void aio_notify_accept(AioContext *ctx)
qatomic_set(&ctx->notified, false);
/*
- * Write ctx->notified before reading e.g. bh->flags. Pairs with smp_wmb
- * in aio_notify.
+ * Order reads of ctx->notified (in aio_context_notifier_poll()) and the
+ * above clearing of ctx->notified before reads of e.g. bh->flags. Pairs
+ * with smp_wmb() in aio_notify.
*/
smp_mb();
}
@@ -496,6 +497,11 @@ static bool aio_context_notifier_poll(void *opaque)
EventNotifier *e = opaque;
AioContext *ctx = container_of(e, AioContext, notifier);
+ /*
+ * No need for load-acquire because we just want to kick the
+ * event loop. aio_notify_accept() takes care of synchronizing
+ * the event loop with the producers.
+ */
return qatomic_read(&ctx->notified);
}
--
2.39.1

111
SOURCES/kvm-async-update-documentation-of-the-memory-barriers.patch Normal file
View File

@ -0,0 +1,111 @@
From 29bcf843d796ffc2a0906dea947e4cdfe9f7ec60 Mon Sep 17 00:00:00 2001
From: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Date: Thu, 9 Mar 2023 08:24:36 -0500
Subject: [PATCH 11/12] async: update documentation of the memory barriers
RH-Author: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-MergeRequest: 158: qatomic: add smp_mb__before/after_rmw()
RH-Bugzilla: 2175660
RH-Acked-by: Paolo Bonzini <pbonzini@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Commit: [8/9] 5ca20e4c8983e0bc1ecee66bead3472777abe4d1 (eesposit/qemu-kvm)
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2175660
commit 8dd48650b43dfde4ebea34191ac267e474bcc29e
Author: Paolo Bonzini <pbonzini@redhat.com>
Date: Mon Mar 6 10:15:06 2023 +0100
async: update documentation of the memory barriers
Ever since commit 8c6b0356b539 ("util/async: make bh_aio_poll() O(1)",
2020-02-22), synchronization between qemu_bh_schedule() and aio_bh_poll()
is happening when the bottom half is enqueued in the bh_list; not
when the flags are set. Update the documentation to match.
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
---
util/async.c | 33 +++++++++++++++++++--------------
1 file changed, 19 insertions(+), 14 deletions(-)
diff --git a/util/async.c b/util/async.c
index 63434ddae4..37d3e6036d 100644
--- a/util/async.c
+++ b/util/async.c
@@ -73,14 +73,21 @@ static void aio_bh_enqueue(QEMUBH *bh, unsigned new_flags)
unsigned old_flags;
/*
- * The memory barrier implicit in qatomic_fetch_or makes sure that:
- * 1. idle & any writes needed by the callback are done before the
- * locations are read in the aio_bh_poll.
- * 2. ctx is loaded before the callback has a chance to execute and bh
- * could be freed.
+ * Synchronizes with atomic_fetch_and() in aio_bh_dequeue(), ensuring that
+ * insertion starts after BH_PENDING is set.
*/
old_flags = qatomic_fetch_or(&bh->flags, BH_PENDING | new_flags);
+
if (!(old_flags & BH_PENDING)) {
+ /*
+ * At this point the bottom half becomes visible to aio_bh_poll().
+ * This insertion thus synchronizes with QSLIST_MOVE_ATOMIC in
+ * aio_bh_poll(), ensuring that:
+ * 1. any writes needed by the callback are visible from the callback
+ * after aio_bh_dequeue() returns bh.
+ * 2. ctx is loaded before the callback has a chance to execute and bh
+ * could be freed.
+ */
QSLIST_INSERT_HEAD_ATOMIC(&ctx->bh_list, bh, next);
}
@@ -106,11 +113,8 @@ static QEMUBH *aio_bh_dequeue(BHList *head, unsigned *flags)
QSLIST_REMOVE_HEAD(head, next);
/*
- * The qatomic_and is paired with aio_bh_enqueue(). The implicit memory
- * barrier ensures that the callback sees all writes done by the scheduling
- * thread. It also ensures that the scheduling thread sees the cleared
- * flag before bh->cb has run, and thus will call aio_notify again if
- * necessary.
+ * Synchronizes with qatomic_fetch_or() in aio_bh_enqueue(), ensuring that
+ * the removal finishes before BH_PENDING is reset.
*/
*flags = qatomic_fetch_and(&bh->flags,
~(BH_PENDING | BH_SCHEDULED | BH_IDLE));
@@ -157,6 +161,7 @@ int aio_bh_poll(AioContext *ctx)
BHListSlice *s;
int ret = 0;
+ /* Synchronizes with QSLIST_INSERT_HEAD_ATOMIC in aio_bh_enqueue(). */
QSLIST_MOVE_ATOMIC(&slice.bh_list, &ctx->bh_list);
QSIMPLEQ_INSERT_TAIL(&ctx->bh_slice_list, &slice, next);
@@ -446,15 +451,15 @@ LuringState *aio_get_linux_io_uring(AioContext *ctx)
void aio_notify(AioContext *ctx)
{
/*
- * Write e.g. bh->flags before writing ctx->notified. Pairs with smp_mb in
- * aio_notify_accept.
+ * Write e.g. ctx->bh_list before writing ctx->notified. Pairs with
+ * smp_mb() in aio_notify_accept().
*/
smp_wmb();
qatomic_set(&ctx->notified, true);
/*
- * Write ctx->notified before reading ctx->notify_me. Pairs
- * with smp_mb in aio_ctx_prepare or aio_poll.
+ * Write ctx->notified (and also ctx->bh_list) before reading ctx->notify_me.
+ * Pairs with smp_mb() in aio_ctx_prepare or aio_poll.
*/
smp_mb();
if (qatomic_read(&ctx->notify_me)) {
--
2.39.1

250
SOURCES/kvm-block-Call-drain-callbacks-only-once.patch Normal file
View File

@ -0,0 +1,250 @@
From 9bb9cafd736057fd2a8ebfa6f5769668f125fbe6 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Fri, 18 Nov 2022 18:41:06 +0100
Subject: [PATCH 24/31] block: Call drain callbacks only once
RH-Author: Stefano Garzarella <sgarzare@redhat.com>
RH-MergeRequest: 135: block: Simplify drain to prevent QEMU from crashing during snapshot
RH-Bugzilla: 2155112
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [12/16] ea9a433dc01d1b8539a2d4ea12887f2a3ce830ea (sgarzarella/qemu-kvm-c-9-s)
We only need to call both the BlockDriver's callback and the parent
callbacks when going from undrained to drained or vice versa. A second
drain section doesn't make a difference for the driver or the parent,
they weren't supposed to send new requests before and after the second
drain.
One thing that gets in the way is the 'ignore_bds_parents' parameter in
bdrv_do_drained_begin_quiesce() and bdrv_do_drained_end(): It means that
bdrv_drain_all_begin() increases bs->quiesce_counter, but does not
quiesce the parent through BdrvChildClass callbacks. If an additional
drain section is started now, bs->quiesce_counter will be non-zero, but
we would still need to quiesce the parent through BdrvChildClass in
order to keep things consistent (and unquiesce it on the matching
bdrv_drained_end(), even though the counter would not reach 0 yet as
long as the bdrv_drain_all() section is still active).
Instead of keeping track of this, let's just get rid of the parameter.
It was introduced in commit 6cd5c9d7b2d as an optimisation so that
during bdrv_drain_all(), we wouldn't recursively drain all parents up to
the root for each node, resulting in quadratic complexity. As it happens,
calling the callbacks only once solves the same problem, so as of this
patch, we'll still have O(n) complexity and ignore_bds_parents is not
needed any more.
This patch only ignores the 'ignore_bds_parents' parameter. It will be
removed in a separate patch.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20221118174110.55183-12-kwolf@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 57e05be343f33f4e5899a8d8946a8596d68424a1)
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
block.c | 25 +++++++------------------
block/io.c | 30 ++++++++++++++++++------------
include/block/block_int-common.h | 8 ++++----
tests/unit/test-bdrv-drain.c | 16 ++++++++++------
4 files changed, 39 insertions(+), 40 deletions(-)
diff --git a/block.c b/block.c
index e0e3b21790..5a583e260d 100644
--- a/block.c
+++ b/block.c
@@ -2824,7 +2824,6 @@ static void bdrv_replace_child_noperm(BdrvChild *child,
{
BlockDriverState *old_bs = child->bs;
int new_bs_quiesce_counter;
- int drain_saldo;
assert(!child->frozen);
assert(old_bs != new_bs);
@@ -2834,16 +2833,13 @@ static void bdrv_replace_child_noperm(BdrvChild *child,
assert(bdrv_get_aio_context(old_bs) == bdrv_get_aio_context(new_bs));
}
- new_bs_quiesce_counter = (new_bs ? new_bs->quiesce_counter : 0);
- drain_saldo = new_bs_quiesce_counter - child->parent_quiesce_counter;
-
/*
* If the new child node is drained but the old one was not, flush
* all outstanding requests to the old child node.
*/
- while (drain_saldo > 0 && child->klass->drained_begin) {
+ new_bs_quiesce_counter = (new_bs ? new_bs->quiesce_counter : 0);
+ if (new_bs_quiesce_counter && !child->quiesced_parent) {
bdrv_parent_drained_begin_single(child, true);
- drain_saldo--;
}
if (old_bs) {
@@ -2859,16 +2855,6 @@ static void bdrv_replace_child_noperm(BdrvChild *child,
if (new_bs) {
assert_bdrv_graph_writable(new_bs);
QLIST_INSERT_HEAD(&new_bs->parents, child, next_parent);
-
- /*
- * Polling in bdrv_parent_drained_begin_single() may have led to the new
- * node's quiesce_counter having been decreased. Not a problem, we just
- * need to recognize this here and then invoke drained_end appropriately
- * more often.
- */
- assert(new_bs->quiesce_counter <= new_bs_quiesce_counter);
- drain_saldo += new_bs->quiesce_counter - new_bs_quiesce_counter;
-
if (child->klass->attach) {
child->klass->attach(child);
}
@@ -2877,10 +2863,13 @@ static void bdrv_replace_child_noperm(BdrvChild *child,
/*
* If the old child node was drained but the new one is not, allow
* requests to come in only after the new node has been attached.
+ *
+ * Update new_bs_quiesce_counter because bdrv_parent_drained_begin_single()
+ * polls, which could have changed the value.
*/
- while (drain_saldo < 0 && child->klass->drained_end) {
+ new_bs_quiesce_counter = (new_bs ? new_bs->quiesce_counter : 0);
+ if (!new_bs_quiesce_counter && child->quiesced_parent) {
bdrv_parent_drained_end_single(child);
- drain_saldo++;
}
}
diff --git a/block/io.c b/block/io.c
index 75224480d0..87d6f22ec4 100644
--- a/block/io.c
+++ b/block/io.c
@@ -62,8 +62,9 @@ void bdrv_parent_drained_end_single(BdrvChild *c)
{
IO_OR_GS_CODE();
- assert(c->parent_quiesce_counter > 0);
- c->parent_quiesce_counter--;
+ assert(c->quiesced_parent);
+ c->quiesced_parent = false;
+
if (c->klass->drained_end) {
c->klass->drained_end(c);
}
@@ -110,7 +111,10 @@ void bdrv_parent_drained_begin_single(BdrvChild *c, bool poll)
{
AioContext *ctx = bdrv_child_get_parent_aio_context(c);
IO_OR_GS_CODE();
- c->parent_quiesce_counter++;
+
+ assert(!c->quiesced_parent);
+ c->quiesced_parent = true;
+
if (c->klass->drained_begin) {
c->klass->drained_begin(c);
}
@@ -358,11 +362,12 @@ void bdrv_do_drained_begin_quiesce(BlockDriverState *bs,
/* Stop things in parent-to-child order */
if (qatomic_fetch_inc(&bs->quiesce_counter) == 0) {
aio_disable_external(bdrv_get_aio_context(bs));
- }
- bdrv_parent_drained_begin(bs, parent, ignore_bds_parents);
- if (bs->drv && bs->drv->bdrv_drain_begin) {
- bs->drv->bdrv_drain_begin(bs);
+ /* TODO Remove ignore_bds_parents, we don't consider it any more */
+ bdrv_parent_drained_begin(bs, parent, false);
+ if (bs->drv && bs->drv->bdrv_drain_begin) {
+ bs->drv->bdrv_drain_begin(bs);
+ }
}
}
@@ -413,13 +418,14 @@ static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent,
assert(bs->quiesce_counter > 0);
/* Re-enable things in child-to-parent order */
- if (bs->drv && bs->drv->bdrv_drain_end) {
- bs->drv->bdrv_drain_end(bs);
- }
- bdrv_parent_drained_end(bs, parent, ignore_bds_parents);
-
old_quiesce_counter = qatomic_fetch_dec(&bs->quiesce_counter);
if (old_quiesce_counter == 1) {
+ if (bs->drv && bs->drv->bdrv_drain_end) {
+ bs->drv->bdrv_drain_end(bs);
+ }
+ /* TODO Remove ignore_bds_parents, we don't consider it any more */
+ bdrv_parent_drained_end(bs, parent, false);
+
aio_enable_external(bdrv_get_aio_context(bs));
}
}
diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h
index 791dddfd7d..a6bc6b7fe9 100644
--- a/include/block/block_int-common.h
+++ b/include/block/block_int-common.h
@@ -980,13 +980,13 @@ struct BdrvChild {
bool frozen;
/*
- * How many times the parent of this child has been drained
+ * True if the parent of this child has been drained by this BdrvChild
* (through klass->drained_*).
- * Usually, this is equal to bs->quiesce_counter (potentially
- * reduced by bdrv_drain_all_count). It may differ while the
+ *
+ * It is generally true if bs->quiesce_counter > 0. It may differ while the
* child is entering or leaving a drained section.
*/
- int parent_quiesce_counter;
+ bool quiesced_parent;
QLIST_ENTRY(BdrvChild) next;
QLIST_ENTRY(BdrvChild) next_parent;
diff --git a/tests/unit/test-bdrv-drain.c b/tests/unit/test-bdrv-drain.c
index dda08de8db..172bc6debc 100644
--- a/tests/unit/test-bdrv-drain.c
+++ b/tests/unit/test-bdrv-drain.c
@@ -296,7 +296,11 @@ static void test_quiesce_common(enum drain_type drain_type, bool recursive)
do_drain_begin(drain_type, bs);
- g_assert_cmpint(bs->quiesce_counter, ==, 1);
+ if (drain_type == BDRV_DRAIN_ALL) {
+ g_assert_cmpint(bs->quiesce_counter, ==, 2);
+ } else {
+ g_assert_cmpint(bs->quiesce_counter, ==, 1);
+ }
g_assert_cmpint(backing->quiesce_counter, ==, !!recursive);
do_drain_end(drain_type, bs);
@@ -348,8 +352,8 @@ static void test_nested(void)
for (outer = 0; outer < DRAIN_TYPE_MAX; outer++) {
for (inner = 0; inner < DRAIN_TYPE_MAX; inner++) {
- int backing_quiesce = (outer != BDRV_DRAIN) +
- (inner != BDRV_DRAIN);
+ int backing_quiesce = (outer == BDRV_DRAIN_ALL) +
+ (inner == BDRV_DRAIN_ALL);
g_assert_cmpint(bs->quiesce_counter, ==, 0);
g_assert_cmpint(backing->quiesce_counter, ==, 0);
@@ -359,10 +363,10 @@ static void test_nested(void)
do_drain_begin(outer, bs);
do_drain_begin(inner, bs);
- g_assert_cmpint(bs->quiesce_counter, ==, 2);
+ g_assert_cmpint(bs->quiesce_counter, ==, 2 + !!backing_quiesce);
g_assert_cmpint(backing->quiesce_counter, ==, backing_quiesce);
- g_assert_cmpint(s->drain_count, ==, 2);
- g_assert_cmpint(backing_s->drain_count, ==, backing_quiesce);
+ g_assert_cmpint(s->drain_count, ==, 1);
+ g_assert_cmpint(backing_s->drain_count, ==, !!backing_quiesce);
do_drain_end(inner, bs);
do_drain_end(outer, bs);
--
2.31.1

298
SOURCES/kvm-block-Don-t-poll-in-bdrv_replace_child_noperm.patch Normal file
View File

@ -0,0 +1,298 @@
From 150ef3356cc6732fede7ca059168fc0565ed0b76 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Fri, 18 Nov 2022 18:41:09 +0100
Subject: [PATCH 27/31] block: Don't poll in bdrv_replace_child_noperm()
RH-Author: Stefano Garzarella <sgarzare@redhat.com>
RH-MergeRequest: 135: block: Simplify drain to prevent QEMU from crashing during snapshot
RH-Bugzilla: 2155112
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [15/16] 5fc7d6b703a2d6c1118d875056f0afbd6ba5cca9 (sgarzarella/qemu-kvm-c-9-s)
In order to make sure that bdrv_replace_child_noperm() doesn't have to
poll any more, get rid of the bdrv_parent_drained_begin_single() call.
This is possible now because we can require that the parent is already
drained through the child in question when the function is called and we
don't call the parent drain callbacks more than once.
The additional drain calls needed in callers cause the test case to run
its code in the drain handler too early (bdrv_attach_child() drains
now), so modify it to only enable the code after the test setup has
completed.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20221118174110.55183-15-kwolf@redhat.com>
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 23987471285a26397e3152a9244b652445fd36c4)
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
block.c | 103 ++++++++++++++++++++++++++++++-----
block/io.c | 2 +-
include/block/block-io.h | 8 +++
tests/unit/test-bdrv-drain.c | 10 ++++
4 files changed, 108 insertions(+), 15 deletions(-)
diff --git a/block.c b/block.c
index af31a94863..65588d313a 100644
--- a/block.c
+++ b/block.c
@@ -2407,6 +2407,20 @@ static void bdrv_replace_child_abort(void *opaque)
GLOBAL_STATE_CODE();
/* old_bs reference is transparently moved from @s to @s->child */
+ if (!s->child->bs) {
+ /*
+ * The parents were undrained when removing old_bs from the child. New
+ * requests can't have been made, though, because the child was empty.
+ *
+ * TODO Make bdrv_replace_child_noperm() transactionable to avoid
+ * undraining the parent in the first place. Once this is done, having
+ * new_bs drained when calling bdrv_replace_child_tran() is not a
+ * requirement any more.
+ */
+ bdrv_parent_drained_begin_single(s->child, false);
+ assert(!bdrv_parent_drained_poll_single(s->child));
+ }
+ assert(s->child->quiesced_parent);
bdrv_replace_child_noperm(s->child, s->old_bs);
bdrv_unref(new_bs);
}
@@ -2422,12 +2436,19 @@ static TransactionActionDrv bdrv_replace_child_drv = {
*
* Note: real unref of old_bs is done only on commit.
*
+ * Both @child->bs and @new_bs (if non-NULL) must be drained. @new_bs must be
+ * kept drained until the transaction is completed.
+ *
* The function doesn't update permissions, caller is responsible for this.
*/
static void bdrv_replace_child_tran(BdrvChild *child, BlockDriverState *new_bs,
Transaction *tran)
{
BdrvReplaceChildState *s = g_new(BdrvReplaceChildState, 1);
+
+ assert(child->quiesced_parent);
+ assert(!new_bs || new_bs->quiesce_counter);
+
*s = (BdrvReplaceChildState) {
.child = child,
.old_bs = child->bs,
@@ -2819,6 +2840,14 @@ uint64_t bdrv_qapi_perm_to_blk_perm(BlockPermission qapi_perm)
return permissions[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.
+ *
+ * This function does not poll.
+ */
static void bdrv_replace_child_noperm(BdrvChild *child,
BlockDriverState *new_bs)
{
@@ -2826,6 +2855,28 @@ static void bdrv_replace_child_noperm(BdrvChild *child,
int new_bs_quiesce_counter;
assert(!child->frozen);
+
+ /*
+ * If we want to change the BdrvChild to point to a drained node as its new
+ * child->bs, we need to make sure that its new parent is drained, too. In
+ * other words, either child->quiesce_parent must already be true or we must
+ * be able to set it and keep the parent's quiesce_counter consistent with
+ * that, but without polling or starting new requests (this function
+ * guarantees that it doesn't poll, and starting new requests would be
+ * against the invariants of drain sections).
+ *
+ * To keep things simple, we pick the first option (child->quiesce_parent
+ * must already be true). We also generalise the rule a bit to make it
+ * easier to verify in callers and more likely to be covered in test cases:
+ * The parent must be quiesced through this child even if new_bs isn't
+ * currently drained.
+ *
+ * The only exception is for callers that always pass new_bs == NULL. In
+ * this case, we obviously never need to consider the case of a drained
+ * new_bs, so we can keep the callers simpler by allowing them not to drain
+ * the parent.
+ */
+ assert(!new_bs || child->quiesced_parent);
assert(old_bs != new_bs);
GLOBAL_STATE_CODE();
@@ -2833,15 +2884,6 @@ static void bdrv_replace_child_noperm(BdrvChild *child,
assert(bdrv_get_aio_context(old_bs) == bdrv_get_aio_context(new_bs));
}
- /*
- * If the new child node is drained but the old one was not, flush
- * all outstanding requests to the old child node.
- */
- new_bs_quiesce_counter = (new_bs ? new_bs->quiesce_counter : 0);
- if (new_bs_quiesce_counter && !child->quiesced_parent) {
- bdrv_parent_drained_begin_single(child, true);
- }
-
if (old_bs) {
if (child->klass->detach) {
child->klass->detach(child);
@@ -2861,11 +2903,9 @@ static void bdrv_replace_child_noperm(BdrvChild *child,
}
/*
- * If the old child node was drained but the new one is not, allow
- * requests to come in only after the new node has been attached.
- *
- * Update new_bs_quiesce_counter because bdrv_parent_drained_begin_single()
- * polls, which could have changed the value.
+ * If the parent was drained through this BdrvChild previously, but new_bs
+ * is not drained, allow requests to come in only after the new node has
+ * been attached.
*/
new_bs_quiesce_counter = (new_bs ? new_bs->quiesce_counter : 0);
if (!new_bs_quiesce_counter && child->quiesced_parent) {
@@ -3002,6 +3042,24 @@ static BdrvChild *bdrv_attach_child_common(BlockDriverState *child_bs,
}
bdrv_ref(child_bs);
+ /*
+ * Let every new BdrvChild start with a drained parent. Inserting the child
+ * in the graph with bdrv_replace_child_noperm() will undrain it if
+ * @child_bs is not drained.
+ *
+ * The child was only just created and is not yet visible in global state
+ * until bdrv_replace_child_noperm() inserts it into the graph, so nobody
+ * could have sent requests and polling is not necessary.
+ *
+ * Note that this means that the parent isn't fully drained yet, we only
+ * stop new requests from coming in. This is fine, we don't care about the
+ * old requests here, they are not for this child. If another place enters a
+ * drain section for the same parent, but wants it to be fully quiesced, it
+ * will not run most of the the code in .drained_begin() again (which is not
+ * a problem, we already did this), but it will still poll until the parent
+ * is fully quiesced, so it will not be negatively affected either.
+ */
+ bdrv_parent_drained_begin_single(new_child, false);
bdrv_replace_child_noperm(new_child, child_bs);
BdrvAttachChildCommonState *s = g_new(BdrvAttachChildCommonState, 1);
@@ -5059,12 +5117,24 @@ static void bdrv_remove_child(BdrvChild *child, Transaction *tran)
}
if (child->bs) {
+ BlockDriverState *bs = child->bs;
+ bdrv_drained_begin(bs);
bdrv_replace_child_tran(child, NULL, tran);
+ bdrv_drained_end(bs);
}
tran_add(tran, &bdrv_remove_child_drv, child);
}
+static void undrain_on_clean_cb(void *opaque)
+{
+ bdrv_drained_end(opaque);
+}
+
+static TransactionActionDrv undrain_on_clean = {
+ .clean = undrain_on_clean_cb,
+};
+
static int bdrv_replace_node_noperm(BlockDriverState *from,
BlockDriverState *to,
bool auto_skip, Transaction *tran,
@@ -5074,6 +5144,11 @@ static int bdrv_replace_node_noperm(BlockDriverState *from,
GLOBAL_STATE_CODE();
+ bdrv_drained_begin(from);
+ bdrv_drained_begin(to);
+ tran_add(tran, &undrain_on_clean, from);
+ tran_add(tran, &undrain_on_clean, to);
+
QLIST_FOREACH_SAFE(c, &from->parents, next_parent, next) {
assert(c->bs == from);
if (!should_update_child(c, to)) {
diff --git a/block/io.c b/block/io.c
index 5e9150d92c..ae64830eac 100644
--- a/block/io.c
+++ b/block/io.c
@@ -81,7 +81,7 @@ static void bdrv_parent_drained_end(BlockDriverState *bs, BdrvChild *ignore)
}
}
-static bool bdrv_parent_drained_poll_single(BdrvChild *c)
+bool bdrv_parent_drained_poll_single(BdrvChild *c)
{
if (c->klass->drained_poll) {
return c->klass->drained_poll(c);
diff --git a/include/block/block-io.h b/include/block/block-io.h
index 8f5e75756a..65e6d2569b 100644
--- a/include/block/block-io.h
+++ b/include/block/block-io.h
@@ -292,6 +292,14 @@ bdrv_writev_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos);
*/
void bdrv_parent_drained_begin_single(BdrvChild *c, bool poll);
+/**
+ * bdrv_parent_drained_poll_single:
+ *
+ * Returns true if there is any pending activity to cease before @c can be
+ * called quiesced, false otherwise.
+ */
+bool bdrv_parent_drained_poll_single(BdrvChild *c);
+
/**
* bdrv_parent_drained_end_single:
*
diff --git a/tests/unit/test-bdrv-drain.c b/tests/unit/test-bdrv-drain.c
index 172bc6debc..2686a8acee 100644
--- a/tests/unit/test-bdrv-drain.c
+++ b/tests/unit/test-bdrv-drain.c
@@ -1654,6 +1654,7 @@ static void test_drop_intermediate_poll(void)
typedef struct BDRVReplaceTestState {
+ bool setup_completed;
bool was_drained;
bool was_undrained;
bool has_read;
@@ -1738,6 +1739,10 @@ static void bdrv_replace_test_drain_begin(BlockDriverState *bs)
{
BDRVReplaceTestState *s = bs->opaque;
+ if (!s->setup_completed) {
+ return;
+ }
+
if (!s->drain_count) {
s->drain_co = qemu_coroutine_create(bdrv_replace_test_drain_co, bs);
bdrv_inc_in_flight(bs);
@@ -1769,6 +1774,10 @@ static void bdrv_replace_test_drain_end(BlockDriverState *bs)
{
BDRVReplaceTestState *s = bs->opaque;
+ if (!s->setup_completed) {
+ return;
+ }
+
g_assert(s->drain_count > 0);
if (!--s->drain_count) {
s->was_undrained = true;
@@ -1867,6 +1876,7 @@ static void do_test_replace_child_mid_drain(int old_drain_count,
bdrv_ref(old_child_bs);
bdrv_attach_child(parent_bs, old_child_bs, "child", &child_of_bds,
BDRV_CHILD_COW, &error_abort);
+ parent_s->setup_completed = true;
for (i = 0; i < old_drain_count; i++) {
bdrv_drained_begin(old_child_bs);
--
2.31.1

54
SOURCES/kvm-block-Don-t-use-subtree-drains-in-bdrv_drop_intermed.patch Normal file
View File

@ -0,0 +1,54 @@
From 6af6de77dace29aa8548b3649dc9c6163740ac86 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Fri, 18 Nov 2022 18:41:03 +0100
Subject: [PATCH 21/31] block: Don't use subtree drains in
bdrv_drop_intermediate()
RH-Author: Stefano Garzarella <sgarzare@redhat.com>
RH-MergeRequest: 135: block: Simplify drain to prevent QEMU from crashing during snapshot
RH-Bugzilla: 2155112
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [9/16] 3c06fa826f262558f57d38b0155500c2e8e23a53 (sgarzarella/qemu-kvm-c-9-s)
Instead of using a subtree drain from the top node (which also drains
child nodes of base that we're not even interested in), use a normal
drain for base, which automatically drains all of the parents, too.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20221118174110.55183-9-kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 631086deefc32690ee56efed1c5b891dec31ae37)
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
block.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/block.c b/block.c
index cb5e96b1cf..b3449a312e 100644
--- a/block.c
+++ b/block.c
@@ -5586,7 +5586,7 @@ int bdrv_drop_intermediate(BlockDriverState *top, BlockDriverState *base,
GLOBAL_STATE_CODE();
bdrv_ref(top);
- bdrv_subtree_drained_begin(top);
+ bdrv_drained_begin(base);
if (!top->drv || !base->drv) {
goto exit;
@@ -5659,7 +5659,7 @@ int bdrv_drop_intermediate(BlockDriverState *top, BlockDriverState *base,
ret = 0;
exit:
- bdrv_subtree_drained_end(top);
+ bdrv_drained_end(base);
bdrv_unref(top);
return ret;
}
--
2.31.1

157
SOURCES/kvm-block-Drain-individual-nodes-during-reopen.patch Normal file
View File

@ -0,0 +1,157 @@
From ad52cb621daad45d3c2a0e2e670d6ca2e16690bd Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Fri, 18 Nov 2022 18:41:02 +0100
Subject: [PATCH 20/31] block: Drain individual nodes during reopen
RH-Author: Stefano Garzarella <sgarzare@redhat.com>
RH-MergeRequest: 135: block: Simplify drain to prevent QEMU from crashing during snapshot
RH-Bugzilla: 2155112
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [8/16] 5441b6f0ae9102ef40d1093e1db3084eea81e3b0 (sgarzarella/qemu-kvm-c-9-s)
bdrv_reopen() and friends use subtree drains as a lazy way of covering
all the nodes they touch. Turns out that this lazy way is a lot more
complicated than just draining the nodes individually, even not
accounting for the additional complexity in the drain mechanism itself.
Simplify the code by switching to draining the individual nodes that are
already managed in the BlockReopenQueue anyway.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20221118174110.55183-8-kwolf@redhat.com>
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit d22933acd2f470eeef779e4d444e848f76dcfaf8)
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
block.c | 16 +++++++++-------
block/replication.c | 6 ------
blockdev.c | 13 -------------
3 files changed, 9 insertions(+), 26 deletions(-)
diff --git a/block.c b/block.c
index 46df410b07..cb5e96b1cf 100644
--- a/block.c
+++ b/block.c
@@ -4150,7 +4150,7 @@ static bool bdrv_recurse_has_child(BlockDriverState *bs,
* returns a pointer to bs_queue, which is either the newly allocated
* bs_queue, or the existing bs_queue being used.
*
- * bs must be drained between bdrv_reopen_queue() and bdrv_reopen_multiple().
+ * bs is drained here and undrained by bdrv_reopen_queue_free().
*
* To be called with bs->aio_context locked.
*/
@@ -4172,12 +4172,10 @@ static BlockReopenQueue *bdrv_reopen_queue_child(BlockReopenQueue *bs_queue,
int flags;
QemuOpts *opts;
- /* Make sure that the caller remembered to use a drained section. This is
- * important to avoid graph changes between the recursive queuing here and
- * bdrv_reopen_multiple(). */
- assert(bs->quiesce_counter > 0);
GLOBAL_STATE_CODE();
+ bdrv_drained_begin(bs);
+
if (bs_queue == NULL) {
bs_queue = g_new0(BlockReopenQueue, 1);
QTAILQ_INIT(bs_queue);
@@ -4328,6 +4326,12 @@ void bdrv_reopen_queue_free(BlockReopenQueue *bs_queue)
if (bs_queue) {
BlockReopenQueueEntry *bs_entry, *next;
QTAILQ_FOREACH_SAFE(bs_entry, bs_queue, entry, next) {
+ AioContext *ctx = bdrv_get_aio_context(bs_entry->state.bs);
+
+ aio_context_acquire(ctx);
+ bdrv_drained_end(bs_entry->state.bs);
+ aio_context_release(ctx);
+
qobject_unref(bs_entry->state.explicit_options);
qobject_unref(bs_entry->state.options);
g_free(bs_entry);
@@ -4475,7 +4479,6 @@ int bdrv_reopen(BlockDriverState *bs, QDict *opts, bool keep_old_opts,
GLOBAL_STATE_CODE();
- bdrv_subtree_drained_begin(bs);
queue = bdrv_reopen_queue(NULL, bs, opts, keep_old_opts);
if (ctx != qemu_get_aio_context()) {
@@ -4486,7 +4489,6 @@ int bdrv_reopen(BlockDriverState *bs, QDict *opts, bool keep_old_opts,
if (ctx != qemu_get_aio_context()) {
aio_context_acquire(ctx);
}
- bdrv_subtree_drained_end(bs);
return ret;
}
diff --git a/block/replication.c b/block/replication.c
index f1eed25e43..c62f48a874 100644
--- a/block/replication.c
+++ b/block/replication.c
@@ -374,9 +374,6 @@ static void reopen_backing_file(BlockDriverState *bs, bool writable,
s->orig_secondary_read_only = bdrv_is_read_only(secondary_disk->bs);
}
- bdrv_subtree_drained_begin(hidden_disk->bs);
- bdrv_subtree_drained_begin(secondary_disk->bs);
-
if (s->orig_hidden_read_only) {
QDict *opts = qdict_new();
qdict_put_bool(opts, BDRV_OPT_READ_ONLY, !writable);
@@ -401,9 +398,6 @@ static void reopen_backing_file(BlockDriverState *bs, bool writable,
aio_context_acquire(ctx);
}
}
-
- bdrv_subtree_drained_end(hidden_disk->bs);
- bdrv_subtree_drained_end(secondary_disk->bs);
}
static void backup_job_cleanup(BlockDriverState *bs)
diff --git a/blockdev.c b/blockdev.c
index 3f1dec6242..8ffb3d9537 100644
--- a/blockdev.c
+++ b/blockdev.c
@@ -3547,8 +3547,6 @@ fail:
void qmp_blockdev_reopen(BlockdevOptionsList *reopen_list, Error **errp)
{
BlockReopenQueue *queue = NULL;
- GSList *drained = NULL;
- GSList *p;
/* Add each one of the BDS that we want to reopen to the queue */
for (; reopen_list != NULL; reopen_list = reopen_list->next) {
@@ -3585,9 +3583,7 @@ void qmp_blockdev_reopen(BlockdevOptionsList *reopen_list, Error **errp)
ctx = bdrv_get_aio_context(bs);
aio_context_acquire(ctx);
- bdrv_subtree_drained_begin(bs);
queue = bdrv_reopen_queue(queue, bs, qdict, false);
- drained = g_slist_prepend(drained, bs);
aio_context_release(ctx);
}
@@ -3598,15 +3594,6 @@ void qmp_blockdev_reopen(BlockdevOptionsList *reopen_list, Error **errp)
fail:
bdrv_reopen_queue_free(queue);
- for (p = drained; p; p = p->next) {
- BlockDriverState *bs = p->data;
- AioContext *ctx = bdrv_get_aio_context(bs);
-
- aio_context_acquire(ctx);
- bdrv_subtree_drained_end(bs);
- aio_context_release(ctx);
- }
- g_slist_free(drained);
}
void qmp_blockdev_del(const char *node_name, Error **errp)
--
2.31.1

96
SOURCES/kvm-block-Drop-out-of-coroutine-in-bdrv_do_drained_begin.patch Normal file
View File

@ -0,0 +1,96 @@
From 9a789d104a4a69031ad95d7fad6380ab21e82503 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Fri, 18 Nov 2022 18:41:08 +0100
Subject: [PATCH 26/31] block: Drop out of coroutine in
bdrv_do_drained_begin_quiesce()
RH-Author: Stefano Garzarella <sgarzare@redhat.com>
RH-MergeRequest: 135: block: Simplify drain to prevent QEMU from crashing during snapshot
RH-Bugzilla: 2155112
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [14/16] c9266663b822f703e55b6a07de98ceb56e69e924 (sgarzarella/qemu-kvm-c-9-s)
The next patch adds a parent drain to bdrv_attach_child_common(), which
shouldn't be, but is currently called from coroutines in some cases (e.g.
.bdrv_co_create implementations generally open new nodes). Therefore,
the assertion that we're not in a coroutine doesn't hold true any more.
We could just remove the assertion because there is nothing in the
function that should be in conflict with running in a coroutine, but
just to be on the safe side, we can reverse the caller relationship
between bdrv_do_drained_begin() and bdrv_do_drained_begin_quiesce() so
that the latter also just drops out of coroutine context and we can
still be certain in the future that any drain code doesn't run in
coroutines.
As a nice side effect, the structure of bdrv_do_drained_begin() is now
symmetrical with bdrv_do_drained_end().
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20221118174110.55183-14-kwolf@redhat.com>
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 05c272ff0cf1b16cc3606f746182dd99b774f553)
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
block/io.c | 25 ++++++++++++-------------
1 file changed, 12 insertions(+), 13 deletions(-)
diff --git a/block/io.c b/block/io.c
index 2e9503df6a..5e9150d92c 100644
--- a/block/io.c
+++ b/block/io.c
@@ -346,10 +346,15 @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs,
}
}
-void bdrv_do_drained_begin_quiesce(BlockDriverState *bs, BdrvChild *parent)
+static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent,
+ bool poll)
{
IO_OR_GS_CODE();
- assert(!qemu_in_coroutine());
+
+ if (qemu_in_coroutine()) {
+ bdrv_co_yield_to_drain(bs, true, parent, poll);
+ return;
+ }
/* Stop things in parent-to-child order */
if (qatomic_fetch_inc(&bs->quiesce_counter) == 0) {
@@ -359,17 +364,6 @@ void bdrv_do_drained_begin_quiesce(BlockDriverState *bs, BdrvChild *parent)
bs->drv->bdrv_drain_begin(bs);
}
}
-}
-
-static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent,
- bool poll)
-{
- if (qemu_in_coroutine()) {
- bdrv_co_yield_to_drain(bs, true, parent, poll);
- return;
- }
-
- bdrv_do_drained_begin_quiesce(bs, parent);
/*
* Wait for drained requests to finish.
@@ -385,6 +379,11 @@ static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent,
}
}
+void bdrv_do_drained_begin_quiesce(BlockDriverState *bs, BdrvChild *parent)
+{
+ bdrv_do_drained_begin(bs, parent, false);
+}
+
void bdrv_drained_begin(BlockDriverState *bs)
{
IO_OR_GS_CODE();
--
2.31.1

67
SOURCES/kvm-block-Fix-locking-for-bdrv_reopen_queue_child.patch Normal file
View File

@ -0,0 +1,67 @@
From e790b4c20a5124239fe93e91fbc87745e5f2cea6 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Fri, 18 Nov 2022 18:41:01 +0100
Subject: [PATCH 19/31] block: Fix locking for bdrv_reopen_queue_child()
RH-Author: Stefano Garzarella <sgarzare@redhat.com>
RH-MergeRequest: 135: block: Simplify drain to prevent QEMU from crashing during snapshot
RH-Bugzilla: 2155112
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [7/16] 46bb54506c4400b9a1bf66b6bd7987ff67260003 (sgarzarella/qemu-kvm-c-9-s)
Callers don't agree whether bdrv_reopen_queue_child() should be called
with the AioContext lock held or not. Standardise on holding the lock
(as done by QMP blockdev-reopen and the replication block driver) and
fix bdrv_reopen() to do the same.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20221118174110.55183-7-kwolf@redhat.com>
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 2e117866d7c96cc17e84cd2946fee1bf3292d814)
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
block.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/block.c b/block.c
index 7999fd08c5..46df410b07 100644
--- a/block.c
+++ b/block.c
@@ -4151,6 +4151,8 @@ static bool bdrv_recurse_has_child(BlockDriverState *bs,
* bs_queue, or the existing bs_queue being used.
*
* bs must be drained between bdrv_reopen_queue() and bdrv_reopen_multiple().
+ *
+ * To be called with bs->aio_context locked.
*/
static BlockReopenQueue *bdrv_reopen_queue_child(BlockReopenQueue *bs_queue,
BlockDriverState *bs,
@@ -4309,6 +4311,7 @@ static BlockReopenQueue *bdrv_reopen_queue_child(BlockReopenQueue *bs_queue,
return bs_queue;
}
+/* To be called with bs->aio_context locked */
BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue,
BlockDriverState *bs,
QDict *options, bool keep_old_opts)
@@ -4473,11 +4476,11 @@ int bdrv_reopen(BlockDriverState *bs, QDict *opts, bool keep_old_opts,
GLOBAL_STATE_CODE();
bdrv_subtree_drained_begin(bs);
+ queue = bdrv_reopen_queue(NULL, bs, opts, keep_old_opts);
+
if (ctx != qemu_get_aio_context()) {
aio_context_release(ctx);
}
-
- queue = bdrv_reopen_queue(NULL, bs, opts, keep_old_opts);
ret = bdrv_reopen_multiple(queue, errp);
if (ctx != qemu_get_aio_context()) {
--
2.31.1

132
SOURCES/kvm-block-Improve-empty-format-specific-info-dump.patch Normal file
View File

@ -0,0 +1,132 @@
From 074c89b05dae971c7118cb769fd34e22135c8f4c Mon Sep 17 00:00:00 2001
From: Hanna Reitz <hreitz@redhat.com>
Date: Mon, 20 Jun 2022 18:26:53 +0200
Subject: [PATCH 06/20] block: Improve empty format-specific info dump
RH-Author: Hanna Czenczek <hreitz@redhat.com>
RH-MergeRequest: 145: Show protocol-level information in qemu-img info
RH-Bugzilla: 1860292
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Commit: [1/12] be551e83f426e620e673302198b51368bfd324ce (hreitz/qemu-kvm-c-9-s)
When a block driver supports obtaining format-specific information, but
that object only contains optional fields, it is possible that none of
them are present, so that dump_qobject() (called by
bdrv_image_info_specific_dump()) will not print anything.
The callers of bdrv_image_info_specific_dump() put a header above this
information ("Format specific information:\n"), which will look strange
when there is nothing below. Modify bdrv_image_info_specific_dump() to
print this header instead of its callers, and only if there is indeed
something to be printed.
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220620162704.80987-2-hreitz@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 3716470b24f0f63090d59bcf28ad8fe6fb7835bd)
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
---
block/qapi.c | 41 +++++++++++++++++++++++++++++++++++++----
include/block/qapi.h | 3 ++-
qemu-io-cmds.c | 4 ++--
3 files changed, 41 insertions(+), 7 deletions(-)
diff --git a/block/qapi.c b/block/qapi.c
index cf557e3aea..51202b470a 100644
--- a/block/qapi.c
+++ b/block/qapi.c
@@ -777,7 +777,35 @@ static void dump_qdict(int indentation, QDict *dict)
}
}
-void bdrv_image_info_specific_dump(ImageInfoSpecific *info_spec)
+/*
+ * Return whether dumping the given QObject with dump_qobject() would
+ * yield an empty dump, i.e. not print anything.
+ */
+static bool qobject_is_empty_dump(const QObject *obj)
+{
+ switch (qobject_type(obj)) {
+ case QTYPE_QNUM:
+ case QTYPE_QSTRING:
+ case QTYPE_QBOOL:
+ return false;
+
+ case QTYPE_QDICT:
+ return qdict_size(qobject_to(QDict, obj)) == 0;
+
+ case QTYPE_QLIST:
+ return qlist_empty(qobject_to(QList, obj));
+
+ default:
+ abort();
+ }
+}
+
+/**
+ * Dumps the given ImageInfoSpecific object in a human-readable form,
+ * prepending an optional prefix if the dump is not empty.
+ */
+void bdrv_image_info_specific_dump(ImageInfoSpecific *info_spec,
+ const char *prefix)
{
QObject *obj, *data;
Visitor *v = qobject_output_visitor_new(&obj);
@@ -785,7 +813,12 @@ void bdrv_image_info_specific_dump(ImageInfoSpecific *info_spec)
visit_type_ImageInfoSpecific(v, NULL, &info_spec, &error_abort);
visit_complete(v, &obj);
data = qdict_get(qobject_to(QDict, obj), "data");
- dump_qobject(1, data);
+ if (!qobject_is_empty_dump(data)) {
+ if (prefix) {
+ qemu_printf("%s", prefix);
+ }
+ dump_qobject(1, data);
+ }
qobject_unref(obj);
visit_free(v);
}
@@ -866,7 +899,7 @@ void bdrv_image_info_dump(ImageInfo *info)
}
if (info->has_format_specific) {
- qemu_printf("Format specific information:\n");
- bdrv_image_info_specific_dump(info->format_specific);
+ bdrv_image_info_specific_dump(info->format_specific,
+ "Format specific information:\n");
}
}
diff --git a/include/block/qapi.h b/include/block/qapi.h
index 22c7807c89..c09859ea78 100644
--- a/include/block/qapi.h
+++ b/include/block/qapi.h
@@ -40,6 +40,7 @@ void bdrv_query_image_info(BlockDriverState *bs,
Error **errp);
void bdrv_snapshot_dump(QEMUSnapshotInfo *sn);
-void bdrv_image_info_specific_dump(ImageInfoSpecific *info_spec);
+void bdrv_image_info_specific_dump(ImageInfoSpecific *info_spec,
+ const char *prefix);
void bdrv_image_info_dump(ImageInfo *info);
#endif
diff --git a/qemu-io-cmds.c b/qemu-io-cmds.c
index 952dc940f1..f4a374528e 100644
--- a/qemu-io-cmds.c
+++ b/qemu-io-cmds.c
@@ -1825,8 +1825,8 @@ static int info_f(BlockBackend *blk, int argc, char **argv)
return -EIO;
}
if (spec_info) {
- printf("Format specific information:\n");
- bdrv_image_info_specific_dump(spec_info);
+ bdrv_image_info_specific_dump(spec_info,
+ "Format specific information:\n");
qapi_free_ImageInfoSpecific(spec_info);
}
--
2.31.1

81
SOURCES/kvm-block-Inline-bdrv_drain_invoke.patch Normal file
View File

@ -0,0 +1,81 @@
From 1808e560396872173f787f8e338e9837a4c3d626 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Fri, 18 Nov 2022 18:41:00 +0100
Subject: [PATCH 18/31] block: Inline bdrv_drain_invoke()
RH-Author: Stefano Garzarella <sgarzare@redhat.com>
RH-MergeRequest: 135: block: Simplify drain to prevent QEMU from crashing during snapshot
RH-Bugzilla: 2155112
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [6/16] 2c7473a36360eb43d94b967deb12308cb5ea0d3b (sgarzarella/qemu-kvm-c-9-s)
bdrv_drain_invoke() has now two entirely separate cases that share no
code any more and are selected depending on a bool parameter. Each case
has only one caller. Just inline the function.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20221118174110.55183-6-kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit c7bc05f78ab31fb02fc9635f60b9bd22efc8d121)
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
block/io.c | 23 ++++++-----------------
1 file changed, 6 insertions(+), 17 deletions(-)
diff --git a/block/io.c b/block/io.c
index f4ca62b034..a25103be6f 100644
--- a/block/io.c
+++ b/block/io.c
@@ -242,21 +242,6 @@ typedef struct {
bool ignore_bds_parents;
} BdrvCoDrainData;
-/* Recursively call BlockDriver.bdrv_drain_begin/end callbacks */
-static void bdrv_drain_invoke(BlockDriverState *bs, bool begin)
-{
- if (!bs->drv || (begin && !bs->drv->bdrv_drain_begin) ||
- (!begin && !bs->drv->bdrv_drain_end)) {
- return;
- }
-
- if (begin) {
- bs->drv->bdrv_drain_begin(bs);
- } else {
- bs->drv->bdrv_drain_end(bs);
- }
-}
-
/* Returns true if BDRV_POLL_WHILE() should go into a blocking aio_poll() */
bool bdrv_drain_poll(BlockDriverState *bs, bool recursive,
BdrvChild *ignore_parent, bool ignore_bds_parents)
@@ -390,7 +375,9 @@ void bdrv_do_drained_begin_quiesce(BlockDriverState *bs,
}
bdrv_parent_drained_begin(bs, parent, ignore_bds_parents);
- bdrv_drain_invoke(bs, true);
+ if (bs->drv && bs->drv->bdrv_drain_begin) {
+ bs->drv->bdrv_drain_begin(bs);
+ }
}
static void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive,
@@ -461,7 +448,9 @@ static void bdrv_do_drained_end(BlockDriverState *bs, bool recursive,
assert(bs->quiesce_counter > 0);
/* Re-enable things in child-to-parent order */
- bdrv_drain_invoke(bs, false);
+ if (bs->drv && bs->drv->bdrv_drain_end) {
+ bs->drv->bdrv_drain_end(bs);
+ }
bdrv_parent_drained_end(bs, parent, ignore_bds_parents);
old_quiesce_counter = qatomic_fetch_dec(&bs->quiesce_counter);
--
2.31.1

433
SOURCES/kvm-block-Remove-drained_end_counter.patch Normal file
View File

@ -0,0 +1,433 @@
From 3009e49f242ab371ffad35bb29c2c26ddfac75d4 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Fri, 18 Nov 2022 18:40:59 +0100
Subject: [PATCH 17/31] block: Remove drained_end_counter
RH-Author: Stefano Garzarella <sgarzare@redhat.com>
RH-MergeRequest: 135: block: Simplify drain to prevent QEMU from crashing during snapshot
RH-Bugzilla: 2155112
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [5/16] 5589e3f05dece5394a05641f7f42096e8dc62bdb (sgarzarella/qemu-kvm-c-9-s)
drained_end_counter is unused now, nobody changes its value any more. It
can be removed.
In cases where we had two almost identical functions that only differed
in whether the caller passes drained_end_counter, or whether they would
poll for a local drained_end_counter to reach 0, these become a single
function.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Reviewed-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Message-Id: <20221118174110.55183-5-kwolf@redhat.com>
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 2f65df6e16dea2d6e7212fa675f4779d9281e26f)
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
block.c | 5 +-
block/block-backend.c | 4 +-
block/io.c | 98 ++++++++------------------------
blockjob.c | 2 +-
include/block/block-io.h | 24 --------
include/block/block_int-common.h | 6 +-
6 files changed, 30 insertions(+), 109 deletions(-)
diff --git a/block.c b/block.c
index 16a62a329c..7999fd08c5 100644
--- a/block.c
+++ b/block.c
@@ -1235,11 +1235,10 @@ static bool bdrv_child_cb_drained_poll(BdrvChild *child)
return bdrv_drain_poll(bs, false, NULL, false);
}
-static void bdrv_child_cb_drained_end(BdrvChild *child,
- int *drained_end_counter)
+static void bdrv_child_cb_drained_end(BdrvChild *child)
{
BlockDriverState *bs = child->opaque;
- bdrv_drained_end_no_poll(bs, drained_end_counter);
+ bdrv_drained_end(bs);
}
static int bdrv_child_cb_inactivate(BdrvChild *child)
diff --git a/block/block-backend.c b/block/block-backend.c
index d98a96ff37..feaf2181fa 100644
--- a/block/block-backend.c
+++ b/block/block-backend.c
@@ -129,7 +129,7 @@ static void blk_root_inherit_options(BdrvChildRole role, bool parent_is_format,
}
static void blk_root_drained_begin(BdrvChild *child);
static bool blk_root_drained_poll(BdrvChild *child);
-static void blk_root_drained_end(BdrvChild *child, int *drained_end_counter);
+static void blk_root_drained_end(BdrvChild *child);
static void blk_root_change_media(BdrvChild *child, bool load);
static void blk_root_resize(BdrvChild *child);
@@ -2556,7 +2556,7 @@ static bool blk_root_drained_poll(BdrvChild *child)
return busy || !!blk->in_flight;
}
-static void blk_root_drained_end(BdrvChild *child, int *drained_end_counter)
+static void blk_root_drained_end(BdrvChild *child)
{
BlockBackend *blk = child->opaque;
assert(blk->quiesce_counter);
diff --git a/block/io.c b/block/io.c
index c2ed4b2af9..f4ca62b034 100644
--- a/block/io.c
+++ b/block/io.c
@@ -58,28 +58,19 @@ static void bdrv_parent_drained_begin(BlockDriverState *bs, BdrvChild *ignore,
}
}
-static void bdrv_parent_drained_end_single_no_poll(BdrvChild *c,
- int *drained_end_counter)
+void bdrv_parent_drained_end_single(BdrvChild *c)
{
+ IO_OR_GS_CODE();
+
assert(c->parent_quiesce_counter > 0);
c->parent_quiesce_counter--;
if (c->klass->drained_end) {
- c->klass->drained_end(c, drained_end_counter);
+ c->klass->drained_end(c);
}
}
-void bdrv_parent_drained_end_single(BdrvChild *c)
-{
- int drained_end_counter = 0;
- AioContext *ctx = bdrv_child_get_parent_aio_context(c);
- IO_OR_GS_CODE();
- bdrv_parent_drained_end_single_no_poll(c, &drained_end_counter);
- AIO_WAIT_WHILE(ctx, qatomic_read(&drained_end_counter) > 0);
-}
-
static void bdrv_parent_drained_end(BlockDriverState *bs, BdrvChild *ignore,
- bool ignore_bds_parents,
- int *drained_end_counter)
+ bool ignore_bds_parents)
{
BdrvChild *c;
@@ -87,7 +78,7 @@ static void bdrv_parent_drained_end(BlockDriverState *bs, BdrvChild *ignore,
if (c == ignore || (ignore_bds_parents && c->klass->parent_is_bds)) {
continue;
}
- bdrv_parent_drained_end_single_no_poll(c, drained_end_counter);
+ bdrv_parent_drained_end_single(c);
}
}
@@ -249,12 +240,10 @@ typedef struct {
bool poll;
BdrvChild *parent;
bool ignore_bds_parents;
- int *drained_end_counter;
} BdrvCoDrainData;
/* Recursively call BlockDriver.bdrv_drain_begin/end callbacks */
-static void bdrv_drain_invoke(BlockDriverState *bs, bool begin,
- int *drained_end_counter)
+static void bdrv_drain_invoke(BlockDriverState *bs, bool begin)
{
if (!bs->drv || (begin && !bs->drv->bdrv_drain_begin) ||
(!begin && !bs->drv->bdrv_drain_end)) {
@@ -305,8 +294,7 @@ static void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive,
BdrvChild *parent, bool ignore_bds_parents,
bool poll);
static void bdrv_do_drained_end(BlockDriverState *bs, bool recursive,
- BdrvChild *parent, bool ignore_bds_parents,
- int *drained_end_counter);
+ BdrvChild *parent, bool ignore_bds_parents);
static void bdrv_co_drain_bh_cb(void *opaque)
{
@@ -319,14 +307,12 @@ static void bdrv_co_drain_bh_cb(void *opaque)
aio_context_acquire(ctx);
bdrv_dec_in_flight(bs);
if (data->begin) {
- assert(!data->drained_end_counter);
bdrv_do_drained_begin(bs, data->recursive, data->parent,
data->ignore_bds_parents, data->poll);
} else {
assert(!data->poll);
bdrv_do_drained_end(bs, data->recursive, data->parent,
- data->ignore_bds_parents,
- data->drained_end_counter);
+ data->ignore_bds_parents);
}
aio_context_release(ctx);
} else {
@@ -342,8 +328,7 @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs,
bool begin, bool recursive,
BdrvChild *parent,
bool ignore_bds_parents,
- bool poll,
- int *drained_end_counter)
+ bool poll)
{
BdrvCoDrainData data;
Coroutine *self = qemu_coroutine_self();
@@ -363,7 +348,6 @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs,
.parent = parent,
.ignore_bds_parents = ignore_bds_parents,
.poll = poll,
- .drained_end_counter = drained_end_counter,
};
if (bs) {
@@ -406,7 +390,7 @@ void bdrv_do_drained_begin_quiesce(BlockDriverState *bs,
}
bdrv_parent_drained_begin(bs, parent, ignore_bds_parents);
- bdrv_drain_invoke(bs, true, NULL);
+ bdrv_drain_invoke(bs, true);
}
static void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive,
@@ -417,7 +401,7 @@ static void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive,
if (qemu_in_coroutine()) {
bdrv_co_yield_to_drain(bs, true, recursive, parent, ignore_bds_parents,
- poll, NULL);
+ poll);
return;
}
@@ -461,38 +445,24 @@ void bdrv_subtree_drained_begin(BlockDriverState *bs)
/**
* This function does not poll, nor must any of its recursively called
- * functions. The *drained_end_counter pointee will be incremented
- * once for every background operation scheduled, and decremented once
- * the operation settles. Therefore, the pointer must remain valid
- * until the pointee reaches 0. That implies that whoever sets up the
- * pointee has to poll until it is 0.
- *
- * We use atomic operations to access *drained_end_counter, because
- * (1) when called from bdrv_set_aio_context_ignore(), the subgraph of
- * @bs may contain nodes in different AioContexts,
- * (2) bdrv_drain_all_end() uses the same counter for all nodes,
- * regardless of which AioContext they are in.
+ * functions.
*/
static void bdrv_do_drained_end(BlockDriverState *bs, bool recursive,
- BdrvChild *parent, bool ignore_bds_parents,
- int *drained_end_counter)
+ BdrvChild *parent, bool ignore_bds_parents)
{
BdrvChild *child;
int old_quiesce_counter;
- assert(drained_end_counter != NULL);
-
if (qemu_in_coroutine()) {
bdrv_co_yield_to_drain(bs, false, recursive, parent, ignore_bds_parents,
- false, drained_end_counter);
+ false);
return;
}
assert(bs->quiesce_counter > 0);
/* Re-enable things in child-to-parent order */
- bdrv_drain_invoke(bs, false, drained_end_counter);
- bdrv_parent_drained_end(bs, parent, ignore_bds_parents,
- drained_end_counter);
+ bdrv_drain_invoke(bs, false);
+ bdrv_parent_drained_end(bs, parent, ignore_bds_parents);
old_quiesce_counter = qatomic_fetch_dec(&bs->quiesce_counter);
if (old_quiesce_counter == 1) {
@@ -503,32 +473,21 @@ static void bdrv_do_drained_end(BlockDriverState *bs, bool recursive,
assert(!ignore_bds_parents);
bs->recursive_quiesce_counter--;
QLIST_FOREACH(child, &bs->children, next) {
- bdrv_do_drained_end(child->bs, true, child, ignore_bds_parents,
- drained_end_counter);
+ bdrv_do_drained_end(child->bs, true, child, ignore_bds_parents);
}
}
}
void bdrv_drained_end(BlockDriverState *bs)
{
- int drained_end_counter = 0;
IO_OR_GS_CODE();
- bdrv_do_drained_end(bs, false, NULL, false, &drained_end_counter);
- BDRV_POLL_WHILE(bs, qatomic_read(&drained_end_counter) > 0);
-}
-
-void bdrv_drained_end_no_poll(BlockDriverState *bs, int *drained_end_counter)
-{
- IO_CODE();
- bdrv_do_drained_end(bs, false, NULL, false, drained_end_counter);
+ bdrv_do_drained_end(bs, false, NULL, false);
}
void bdrv_subtree_drained_end(BlockDriverState *bs)
{
- int drained_end_counter = 0;
IO_OR_GS_CODE();
- bdrv_do_drained_end(bs, true, NULL, false, &drained_end_counter);
- BDRV_POLL_WHILE(bs, qatomic_read(&drained_end_counter) > 0);
+ bdrv_do_drained_end(bs, true, NULL, false);
}
void bdrv_apply_subtree_drain(BdrvChild *child, BlockDriverState *new_parent)
@@ -543,16 +502,12 @@ void bdrv_apply_subtree_drain(BdrvChild *child, BlockDriverState *new_parent)
void bdrv_unapply_subtree_drain(BdrvChild *child, BlockDriverState *old_parent)
{
- int drained_end_counter = 0;
int i;
IO_OR_GS_CODE();
for (i = 0; i < old_parent->recursive_quiesce_counter; i++) {
- bdrv_do_drained_end(child->bs, true, child, false,
- &drained_end_counter);
+ bdrv_do_drained_end(child->bs, true, child, false);
}
-
- BDRV_POLL_WHILE(child->bs, qatomic_read(&drained_end_counter) > 0);
}
void bdrv_drain(BlockDriverState *bs)
@@ -610,7 +565,7 @@ void bdrv_drain_all_begin(void)
GLOBAL_STATE_CODE();
if (qemu_in_coroutine()) {
- bdrv_co_yield_to_drain(NULL, true, false, NULL, true, true, NULL);
+ bdrv_co_yield_to_drain(NULL, true, false, NULL, true, true);
return;
}
@@ -649,22 +604,19 @@ void bdrv_drain_all_begin(void)
void bdrv_drain_all_end_quiesce(BlockDriverState *bs)
{
- int drained_end_counter = 0;
GLOBAL_STATE_CODE();
g_assert(bs->quiesce_counter > 0);
g_assert(!bs->refcnt);
while (bs->quiesce_counter) {
- bdrv_do_drained_end(bs, false, NULL, true, &drained_end_counter);
+ bdrv_do_drained_end(bs, false, NULL, true);
}
- BDRV_POLL_WHILE(bs, qatomic_read(&drained_end_counter) > 0);
}
void bdrv_drain_all_end(void)
{
BlockDriverState *bs = NULL;
- int drained_end_counter = 0;
GLOBAL_STATE_CODE();
/*
@@ -680,13 +632,11 @@ void bdrv_drain_all_end(void)
AioContext *aio_context = bdrv_get_aio_context(bs);
aio_context_acquire(aio_context);
- bdrv_do_drained_end(bs, false, NULL, true, &drained_end_counter);
+ bdrv_do_drained_end(bs, false, NULL, true);
aio_context_release(aio_context);
}
assert(qemu_get_current_aio_context() == qemu_get_aio_context());
- AIO_WAIT_WHILE(NULL, qatomic_read(&drained_end_counter) > 0);
-
assert(bdrv_drain_all_count > 0);
bdrv_drain_all_count--;
}
diff --git a/blockjob.c b/blockjob.c
index f51d4e18f3..0ab721e139 100644
--- a/blockjob.c
+++ b/blockjob.c
@@ -120,7 +120,7 @@ static bool child_job_drained_poll(BdrvChild *c)
}
}
-static void child_job_drained_end(BdrvChild *c, int *drained_end_counter)
+static void child_job_drained_end(BdrvChild *c)
{
BlockJob *job = c->opaque;
job_resume(&job->job);
diff --git a/include/block/block-io.h b/include/block/block-io.h
index b099d7db45..054e964c9b 100644
--- a/include/block/block-io.h
+++ b/include/block/block-io.h
@@ -237,21 +237,6 @@ int coroutine_fn bdrv_co_copy_range(BdrvChild *src, int64_t src_offset,
int64_t bytes, BdrvRequestFlags read_flags,
BdrvRequestFlags write_flags);
-/**
- * bdrv_drained_end_no_poll:
- *
- * Same as bdrv_drained_end(), but do not poll for the subgraph to
- * actually become unquiesced. Therefore, no graph changes will occur
- * with this function.
- *
- * *drained_end_counter is incremented for every background operation
- * that is scheduled, and will be decremented for every operation once
- * it settles. The caller must poll until it reaches 0. The counter
- * should be accessed using atomic operations only.
- */
-void bdrv_drained_end_no_poll(BlockDriverState *bs, int *drained_end_counter);
-
-
/*
* "I/O or GS" API functions. These functions can run without
* the BQL, but only in one specific iothread/main loop.
@@ -311,9 +296,6 @@ void bdrv_parent_drained_begin_single(BdrvChild *c, bool poll);
* bdrv_parent_drained_end_single:
*
* End a quiesced section for the parent of @c.
- *
- * This polls @bs's AioContext until all scheduled sub-drained_ends
- * have settled, which may result in graph changes.
*/
void bdrv_parent_drained_end_single(BdrvChild *c);
@@ -361,12 +343,6 @@ void bdrv_subtree_drained_begin(BlockDriverState *bs);
* bdrv_drained_end:
*
* End a quiescent section started by bdrv_drained_begin().
- *
- * This polls @bs's AioContext until all scheduled sub-drained_ends
- * have settled. On one hand, that may result in graph changes. On
- * the other, this requires that the caller either runs in the main
- * loop; or that all involved nodes (@bs and all of its parents) are
- * in the caller's AioContext.
*/
void bdrv_drained_end(BlockDriverState *bs);
diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h
index 40d646d1ed..2b97576f6d 100644
--- a/include/block/block_int-common.h
+++ b/include/block/block_int-common.h
@@ -939,15 +939,11 @@ struct BdrvChildClass {
* These functions must not change the graph (and therefore also must not
* call aio_poll(), which could change the graph indirectly).
*
- * If drained_end() schedules background operations, it must atomically
- * increment *drained_end_counter for each such operation and atomically
- * decrement it once the operation has settled.
- *
* Note that this can be nested. If drained_begin() was called twice, new
* I/O is allowed only after drained_end() was called twice, too.
*/
void (*drained_begin)(BdrvChild *child);
- void (*drained_end)(BdrvChild *child, int *drained_end_counter);
+ void (*drained_end)(BdrvChild *child);
/*
* Returns whether the parent has pending requests for the child. This
--
2.31.1

274
SOURCES/kvm-block-Remove-ignore_bds_parents-parameter-from-drain.patch Normal file
View File

@ -0,0 +1,274 @@
From 0dc7990533cef41e58579ee96315aca1fdc44ea1 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Fri, 18 Nov 2022 18:41:07 +0100
Subject: [PATCH 25/31] block: Remove ignore_bds_parents parameter from
drain_begin/end.
RH-Author: Stefano Garzarella <sgarzare@redhat.com>
RH-MergeRequest: 135: block: Simplify drain to prevent QEMU from crashing during snapshot
RH-Bugzilla: 2155112
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [13/16] 1ed88d975a9569bffeb33ad847874417780ce408 (sgarzarella/qemu-kvm-c-9-s)
ignore_bds_parents is now ignored during drain_begin and drain_end, so
we can just remove it there. It is still a valid optimisation for
drain_all in bdrv_drained_poll(), so leave it around there.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20221118174110.55183-13-kwolf@redhat.com>
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit a82a3bd135078d14f1bb4b5e50f51e77d3748270)
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
block.c | 2 +-
block/io.c | 58 +++++++++++++++-------------------------
include/block/block-io.h | 3 +--
3 files changed, 24 insertions(+), 39 deletions(-)
diff --git a/block.c b/block.c
index 5a583e260d..af31a94863 100644
--- a/block.c
+++ b/block.c
@@ -1226,7 +1226,7 @@ static char *bdrv_child_get_parent_desc(BdrvChild *c)
static void bdrv_child_cb_drained_begin(BdrvChild *child)
{
BlockDriverState *bs = child->opaque;
- bdrv_do_drained_begin_quiesce(bs, NULL, false);
+ bdrv_do_drained_begin_quiesce(bs, NULL);
}
static bool bdrv_child_cb_drained_poll(BdrvChild *child)
diff --git a/block/io.c b/block/io.c
index 87d6f22ec4..2e9503df6a 100644
--- a/block/io.c
+++ b/block/io.c
@@ -45,13 +45,12 @@ static void bdrv_parent_cb_resize(BlockDriverState *bs);
static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs,
int64_t offset, int64_t bytes, BdrvRequestFlags flags);
-static void bdrv_parent_drained_begin(BlockDriverState *bs, BdrvChild *ignore,
- bool ignore_bds_parents)
+static void bdrv_parent_drained_begin(BlockDriverState *bs, BdrvChild *ignore)
{
BdrvChild *c, *next;
QLIST_FOREACH_SAFE(c, &bs->parents, next_parent, next) {
- if (c == ignore || (ignore_bds_parents && c->klass->parent_is_bds)) {
+ if (c == ignore) {
continue;
}
bdrv_parent_drained_begin_single(c, false);
@@ -70,13 +69,12 @@ void bdrv_parent_drained_end_single(BdrvChild *c)
}
}
-static void bdrv_parent_drained_end(BlockDriverState *bs, BdrvChild *ignore,
- bool ignore_bds_parents)
+static void bdrv_parent_drained_end(BlockDriverState *bs, BdrvChild *ignore)
{
BdrvChild *c;
QLIST_FOREACH(c, &bs->parents, next_parent) {
- if (c == ignore || (ignore_bds_parents && c->klass->parent_is_bds)) {
+ if (c == ignore) {
continue;
}
bdrv_parent_drained_end_single(c);
@@ -242,7 +240,6 @@ typedef struct {
bool begin;
bool poll;
BdrvChild *parent;
- bool ignore_bds_parents;
} BdrvCoDrainData;
/* Returns true if BDRV_POLL_WHILE() should go into a blocking aio_poll() */
@@ -269,9 +266,8 @@ static bool bdrv_drain_poll_top_level(BlockDriverState *bs,
}
static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent,
- bool ignore_bds_parents, bool poll);
-static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent,
- bool ignore_bds_parents);
+ bool poll);
+static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent);
static void bdrv_co_drain_bh_cb(void *opaque)
{
@@ -284,11 +280,10 @@ static void bdrv_co_drain_bh_cb(void *opaque)
aio_context_acquire(ctx);
bdrv_dec_in_flight(bs);
if (data->begin) {
- bdrv_do_drained_begin(bs, data->parent, data->ignore_bds_parents,
- data->poll);
+ bdrv_do_drained_begin(bs, data->parent, data->poll);
} else {
assert(!data->poll);
- bdrv_do_drained_end(bs, data->parent, data->ignore_bds_parents);
+ bdrv_do_drained_end(bs, data->parent);
}
aio_context_release(ctx);
} else {
@@ -303,7 +298,6 @@ static void bdrv_co_drain_bh_cb(void *opaque)
static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs,
bool begin,
BdrvChild *parent,
- bool ignore_bds_parents,
bool poll)
{
BdrvCoDrainData data;
@@ -321,7 +315,6 @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs,
.done = false,
.begin = begin,
.parent = parent,
- .ignore_bds_parents = ignore_bds_parents,
.poll = poll,
};
@@ -353,8 +346,7 @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs,
}
}
-void bdrv_do_drained_begin_quiesce(BlockDriverState *bs,
- BdrvChild *parent, bool ignore_bds_parents)
+void bdrv_do_drained_begin_quiesce(BlockDriverState *bs, BdrvChild *parent)
{
IO_OR_GS_CODE();
assert(!qemu_in_coroutine());
@@ -362,9 +354,7 @@ void bdrv_do_drained_begin_quiesce(BlockDriverState *bs,
/* Stop things in parent-to-child order */
if (qatomic_fetch_inc(&bs->quiesce_counter) == 0) {
aio_disable_external(bdrv_get_aio_context(bs));
-
- /* TODO Remove ignore_bds_parents, we don't consider it any more */
- bdrv_parent_drained_begin(bs, parent, false);
+ bdrv_parent_drained_begin(bs, parent);
if (bs->drv && bs->drv->bdrv_drain_begin) {
bs->drv->bdrv_drain_begin(bs);
}
@@ -372,14 +362,14 @@ void bdrv_do_drained_begin_quiesce(BlockDriverState *bs,
}
static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent,
- bool ignore_bds_parents, bool poll)
+ bool poll)
{
if (qemu_in_coroutine()) {
- bdrv_co_yield_to_drain(bs, true, parent, ignore_bds_parents, poll);
+ bdrv_co_yield_to_drain(bs, true, parent, poll);
return;
}
- bdrv_do_drained_begin_quiesce(bs, parent, ignore_bds_parents);
+ bdrv_do_drained_begin_quiesce(bs, parent);
/*
* Wait for drained requests to finish.
@@ -391,7 +381,6 @@ static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent,
* nodes.
*/
if (poll) {
- assert(!ignore_bds_parents);
BDRV_POLL_WHILE(bs, bdrv_drain_poll_top_level(bs, parent));
}
}
@@ -399,20 +388,19 @@ static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent,
void bdrv_drained_begin(BlockDriverState *bs)
{
IO_OR_GS_CODE();
- bdrv_do_drained_begin(bs, NULL, false, true);
+ bdrv_do_drained_begin(bs, NULL, true);
}
/**
* This function does not poll, nor must any of its recursively called
* functions.
*/
-static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent,
- bool ignore_bds_parents)
+static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent)
{
int old_quiesce_counter;
if (qemu_in_coroutine()) {
- bdrv_co_yield_to_drain(bs, false, parent, ignore_bds_parents, false);
+ bdrv_co_yield_to_drain(bs, false, parent, false);
return;
}
assert(bs->quiesce_counter > 0);
@@ -423,9 +411,7 @@ static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent,
if (bs->drv && bs->drv->bdrv_drain_end) {
bs->drv->bdrv_drain_end(bs);
}
- /* TODO Remove ignore_bds_parents, we don't consider it any more */
- bdrv_parent_drained_end(bs, parent, false);
-
+ bdrv_parent_drained_end(bs, parent);
aio_enable_external(bdrv_get_aio_context(bs));
}
}
@@ -433,7 +419,7 @@ static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent,
void bdrv_drained_end(BlockDriverState *bs)
{
IO_OR_GS_CODE();
- bdrv_do_drained_end(bs, NULL, false);
+ bdrv_do_drained_end(bs, NULL);
}
void bdrv_drain(BlockDriverState *bs)
@@ -491,7 +477,7 @@ void bdrv_drain_all_begin(void)
GLOBAL_STATE_CODE();
if (qemu_in_coroutine()) {
- bdrv_co_yield_to_drain(NULL, true, NULL, true, true);
+ bdrv_co_yield_to_drain(NULL, true, NULL, true);
return;
}
@@ -516,7 +502,7 @@ void bdrv_drain_all_begin(void)
AioContext *aio_context = bdrv_get_aio_context(bs);
aio_context_acquire(aio_context);
- bdrv_do_drained_begin(bs, NULL, true, false);
+ bdrv_do_drained_begin(bs, NULL, false);
aio_context_release(aio_context);
}
@@ -536,7 +522,7 @@ void bdrv_drain_all_end_quiesce(BlockDriverState *bs)
g_assert(!bs->refcnt);
while (bs->quiesce_counter) {
- bdrv_do_drained_end(bs, NULL, true);
+ bdrv_do_drained_end(bs, NULL);
}
}
@@ -558,7 +544,7 @@ void bdrv_drain_all_end(void)
AioContext *aio_context = bdrv_get_aio_context(bs);
aio_context_acquire(aio_context);
- bdrv_do_drained_end(bs, NULL, true);
+ bdrv_do_drained_end(bs, NULL);
aio_context_release(aio_context);
}
diff --git a/include/block/block-io.h b/include/block/block-io.h
index 9c36a16a1f..8f5e75756a 100644
--- a/include/block/block-io.h
+++ b/include/block/block-io.h
@@ -329,8 +329,7 @@ void bdrv_drained_begin(BlockDriverState *bs);
* Quiesces a BDS like bdrv_drained_begin(), but does not wait for already
* running requests to complete.
*/
-void bdrv_do_drained_begin_quiesce(BlockDriverState *bs,
- BdrvChild *parent, bool ignore_bds_parents);
+void bdrv_do_drained_begin_quiesce(BlockDriverState *bs, BdrvChild *parent);
/**
* bdrv_drained_end:
--
2.31.1

106
SOURCES/kvm-block-Remove-poll-parameter-from-bdrv_parent_drained.patch Normal file
View File

@ -0,0 +1,106 @@
From 60b66881fb972e1cdff1cd7b4c865e5e21c141b0 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Fri, 18 Nov 2022 18:41:10 +0100
Subject: [PATCH 28/31] block: Remove poll parameter from
bdrv_parent_drained_begin_single()
RH-Author: Stefano Garzarella <sgarzare@redhat.com>
RH-MergeRequest: 135: block: Simplify drain to prevent QEMU from crashing during snapshot
RH-Bugzilla: 2155112
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [16/16] fd526cc9e5bebeb256cfa56d23ec596f26caa37a (sgarzarella/qemu-kvm-c-9-s)
All callers of bdrv_parent_drained_begin_single() pass poll=false now,
so we don't need the parameter any more.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20221118174110.55183-16-kwolf@redhat.com>
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 606ed756c1d69cba4822be8923248d2fd714f069)
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
block.c | 4 ++--
block/io.c | 8 ++------
include/block/block-io.h | 5 ++---
3 files changed, 6 insertions(+), 11 deletions(-)
diff --git a/block.c b/block.c
index 65588d313a..0d78711416 100644
--- a/block.c
+++ b/block.c
@@ -2417,7 +2417,7 @@ static void bdrv_replace_child_abort(void *opaque)
* new_bs drained when calling bdrv_replace_child_tran() is not a
* requirement any more.
*/
- bdrv_parent_drained_begin_single(s->child, false);
+ bdrv_parent_drained_begin_single(s->child);
assert(!bdrv_parent_drained_poll_single(s->child));
}
assert(s->child->quiesced_parent);
@@ -3059,7 +3059,7 @@ static BdrvChild *bdrv_attach_child_common(BlockDriverState *child_bs,
* a problem, we already did this), but it will still poll until the parent
* is fully quiesced, so it will not be negatively affected either.
*/
- bdrv_parent_drained_begin_single(new_child, false);
+ bdrv_parent_drained_begin_single(new_child);
bdrv_replace_child_noperm(new_child, child_bs);
BdrvAttachChildCommonState *s = g_new(BdrvAttachChildCommonState, 1);
diff --git a/block/io.c b/block/io.c
index ae64830eac..38e57d1f67 100644
--- a/block/io.c
+++ b/block/io.c
@@ -53,7 +53,7 @@ static void bdrv_parent_drained_begin(BlockDriverState *bs, BdrvChild *ignore)
if (c == ignore) {
continue;
}
- bdrv_parent_drained_begin_single(c, false);
+ bdrv_parent_drained_begin_single(c);
}
}
@@ -105,9 +105,8 @@ static bool bdrv_parent_drained_poll(BlockDriverState *bs, BdrvChild *ignore,
return busy;
}
-void bdrv_parent_drained_begin_single(BdrvChild *c, bool poll)
+void bdrv_parent_drained_begin_single(BdrvChild *c)
{
- AioContext *ctx = bdrv_child_get_parent_aio_context(c);
IO_OR_GS_CODE();
assert(!c->quiesced_parent);
@@ -116,9 +115,6 @@ void bdrv_parent_drained_begin_single(BdrvChild *c, bool poll)
if (c->klass->drained_begin) {
c->klass->drained_begin(c);
}
- if (poll) {
- AIO_WAIT_WHILE(ctx, bdrv_parent_drained_poll_single(c));
- }
}
static void bdrv_merge_limits(BlockLimits *dst, const BlockLimits *src)
diff --git a/include/block/block-io.h b/include/block/block-io.h
index 65e6d2569b..92aaa7c1e9 100644
--- a/include/block/block-io.h
+++ b/include/block/block-io.h
@@ -287,10 +287,9 @@ bdrv_writev_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos);
/**
* bdrv_parent_drained_begin_single:
*
- * Begin a quiesced section for the parent of @c. If @poll is true, wait for
- * any pending activity to cease.
+ * Begin a quiesced section for the parent of @c.
*/
-void bdrv_parent_drained_begin_single(BdrvChild *c, bool poll);
+void bdrv_parent_drained_begin_single(BdrvChild *c);
/**
* bdrv_parent_drained_poll_single:
--
2.31.1

896
SOURCES/kvm-block-Remove-subtree-drains.patch Normal file
View File

@ -0,0 +1,896 @@
From 79063522861cb2baf921b204bcdf4c3bfb5697f4 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Fri, 18 Nov 2022 18:41:05 +0100
Subject: [PATCH 23/31] block: Remove subtree drains
RH-Author: Stefano Garzarella <sgarzare@redhat.com>
RH-MergeRequest: 135: block: Simplify drain to prevent QEMU from crashing during snapshot
RH-Bugzilla: 2155112
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [11/16] d92f5041cceeeec49a65441b22d20f692c0f1c77 (sgarzarella/qemu-kvm-c-9-s)
Subtree drains are not used any more. Remove them.
After this, BdrvChildClass.attach/detach() don't poll any more.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20221118174110.55183-11-kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 299403aedaeb7f08d8e98aa8614b29d4e5546066)
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
block.c | 20 +--
block/io.c | 121 +++-----------
include/block/block-io.h | 18 +--
include/block/block_int-common.h | 1 -
include/block/block_int-io.h | 12 --
tests/unit/test-bdrv-drain.c | 261 ++-----------------------------
6 files changed, 44 insertions(+), 389 deletions(-)
diff --git a/block.c b/block.c
index 5330e89903..e0e3b21790 100644
--- a/block.c
+++ b/block.c
@@ -1232,7 +1232,7 @@ static void bdrv_child_cb_drained_begin(BdrvChild *child)
static bool bdrv_child_cb_drained_poll(BdrvChild *child)
{
BlockDriverState *bs = child->opaque;
- return bdrv_drain_poll(bs, false, NULL, false);
+ return bdrv_drain_poll(bs, NULL, false);
}
static void bdrv_child_cb_drained_end(BdrvChild *child)
@@ -1482,8 +1482,6 @@ static void bdrv_child_cb_attach(BdrvChild *child)
assert(!bs->file);
bs->file = child;
}
-
- bdrv_apply_subtree_drain(child, bs);
}
static void bdrv_child_cb_detach(BdrvChild *child)
@@ -1494,8 +1492,6 @@ static void bdrv_child_cb_detach(BdrvChild *child)
bdrv_backing_detach(child);
}
- bdrv_unapply_subtree_drain(child, bs);
-
assert_bdrv_graph_writable(bs);
QLIST_REMOVE(child, next);
if (child == bs->backing) {
@@ -2851,9 +2847,6 @@ static void bdrv_replace_child_noperm(BdrvChild *child,
}
if (old_bs) {
- /* Detach first so that the recursive drain sections coming from @child
- * are already gone and we only end the drain sections that came from
- * elsewhere. */
if (child->klass->detach) {
child->klass->detach(child);
}
@@ -2868,17 +2861,14 @@ static void bdrv_replace_child_noperm(BdrvChild *child,
QLIST_INSERT_HEAD(&new_bs->parents, child, next_parent);
/*
- * Detaching the old node may have led to the new node's
- * quiesce_counter having been decreased. Not a problem, we
- * just need to recognize this here and then invoke
- * drained_end appropriately more often.
+ * Polling in bdrv_parent_drained_begin_single() may have led to the new
+ * node's quiesce_counter having been decreased. Not a problem, we just
+ * need to recognize this here and then invoke drained_end appropriately
+ * more often.
*/
assert(new_bs->quiesce_counter <= new_bs_quiesce_counter);
drain_saldo += new_bs->quiesce_counter - new_bs_quiesce_counter;
- /* Attach only after starting new drained sections, so that recursive
- * drain sections coming from @child don't get an extra .drained_begin
- * callback. */
if (child->klass->attach) {
child->klass->attach(child);
}
diff --git a/block/io.c b/block/io.c
index a25103be6f..75224480d0 100644
--- a/block/io.c
+++ b/block/io.c
@@ -236,17 +236,15 @@ typedef struct {
BlockDriverState *bs;
bool done;
bool begin;
- bool recursive;
bool poll;
BdrvChild *parent;
bool ignore_bds_parents;
} BdrvCoDrainData;
/* Returns true if BDRV_POLL_WHILE() should go into a blocking aio_poll() */
-bool bdrv_drain_poll(BlockDriverState *bs, bool recursive,
- BdrvChild *ignore_parent, bool ignore_bds_parents)
+bool bdrv_drain_poll(BlockDriverState *bs, BdrvChild *ignore_parent,
+ bool ignore_bds_parents)
{
- BdrvChild *child, *next;
IO_OR_GS_CODE();
if (bdrv_parent_drained_poll(bs, ignore_parent, ignore_bds_parents)) {
@@ -257,29 +255,19 @@ bool bdrv_drain_poll(BlockDriverState *bs, bool recursive,
return true;
}
- if (recursive) {
- assert(!ignore_bds_parents);
- QLIST_FOREACH_SAFE(child, &bs->children, next, next) {
- if (bdrv_drain_poll(child->bs, recursive, child, false)) {
- return true;
- }
- }
- }
-
return false;
}
-static bool bdrv_drain_poll_top_level(BlockDriverState *bs, bool recursive,
+static bool bdrv_drain_poll_top_level(BlockDriverState *bs,
BdrvChild *ignore_parent)
{
- return bdrv_drain_poll(bs, recursive, ignore_parent, false);
+ return bdrv_drain_poll(bs, ignore_parent, false);
}
-static void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive,
- BdrvChild *parent, bool ignore_bds_parents,
- bool poll);
-static void bdrv_do_drained_end(BlockDriverState *bs, bool recursive,
- BdrvChild *parent, bool ignore_bds_parents);
+static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent,
+ bool ignore_bds_parents, bool poll);
+static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent,
+ bool ignore_bds_parents);
static void bdrv_co_drain_bh_cb(void *opaque)
{
@@ -292,12 +280,11 @@ static void bdrv_co_drain_bh_cb(void *opaque)
aio_context_acquire(ctx);
bdrv_dec_in_flight(bs);
if (data->begin) {
- bdrv_do_drained_begin(bs, data->recursive, data->parent,
- data->ignore_bds_parents, data->poll);
+ bdrv_do_drained_begin(bs, data->parent, data->ignore_bds_parents,
+ data->poll);
} else {
assert(!data->poll);
- bdrv_do_drained_end(bs, data->recursive, data->parent,
- data->ignore_bds_parents);
+ bdrv_do_drained_end(bs, data->parent, data->ignore_bds_parents);
}
aio_context_release(ctx);
} else {
@@ -310,7 +297,7 @@ static void bdrv_co_drain_bh_cb(void *opaque)
}
static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs,
- bool begin, bool recursive,
+ bool begin,
BdrvChild *parent,
bool ignore_bds_parents,
bool poll)
@@ -329,7 +316,6 @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs,
.bs = bs,
.done = false,
.begin = begin,
- .recursive = recursive,
.parent = parent,
.ignore_bds_parents = ignore_bds_parents,
.poll = poll,
@@ -380,29 +366,16 @@ void bdrv_do_drained_begin_quiesce(BlockDriverState *bs,
}
}
-static void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive,
- BdrvChild *parent, bool ignore_bds_parents,
- bool poll)
+static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent,
+ bool ignore_bds_parents, bool poll)
{
- BdrvChild *child, *next;
-
if (qemu_in_coroutine()) {
- bdrv_co_yield_to_drain(bs, true, recursive, parent, ignore_bds_parents,
- poll);
+ bdrv_co_yield_to_drain(bs, true, parent, ignore_bds_parents, poll);
return;
}
bdrv_do_drained_begin_quiesce(bs, parent, ignore_bds_parents);
- if (recursive) {
- assert(!ignore_bds_parents);
- bs->recursive_quiesce_counter++;
- QLIST_FOREACH_SAFE(child, &bs->children, next, next) {
- bdrv_do_drained_begin(child->bs, true, child, ignore_bds_parents,
- false);
- }
- }
-
/*
* Wait for drained requests to finish.
*
@@ -414,35 +387,27 @@ static void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive,
*/
if (poll) {
assert(!ignore_bds_parents);
- BDRV_POLL_WHILE(bs, bdrv_drain_poll_top_level(bs, recursive, parent));
+ BDRV_POLL_WHILE(bs, bdrv_drain_poll_top_level(bs, parent));
}
}
void bdrv_drained_begin(BlockDriverState *bs)
{
IO_OR_GS_CODE();
- bdrv_do_drained_begin(bs, false, NULL, false, true);
-}
-
-void bdrv_subtree_drained_begin(BlockDriverState *bs)
-{
- IO_OR_GS_CODE();
- bdrv_do_drained_begin(bs, true, NULL, false, true);
+ bdrv_do_drained_begin(bs, NULL, false, true);
}
/**
* This function does not poll, nor must any of its recursively called
* functions.
*/
-static void bdrv_do_drained_end(BlockDriverState *bs, bool recursive,
- BdrvChild *parent, bool ignore_bds_parents)
+static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent,
+ bool ignore_bds_parents)
{
- BdrvChild *child;
int old_quiesce_counter;
if (qemu_in_coroutine()) {
- bdrv_co_yield_to_drain(bs, false, recursive, parent, ignore_bds_parents,
- false);
+ bdrv_co_yield_to_drain(bs, false, parent, ignore_bds_parents, false);
return;
}
assert(bs->quiesce_counter > 0);
@@ -457,46 +422,12 @@ static void bdrv_do_drained_end(BlockDriverState *bs, bool recursive,
if (old_quiesce_counter == 1) {
aio_enable_external(bdrv_get_aio_context(bs));
}
-
- if (recursive) {
- assert(!ignore_bds_parents);
- bs->recursive_quiesce_counter--;
- QLIST_FOREACH(child, &bs->children, next) {
- bdrv_do_drained_end(child->bs, true, child, ignore_bds_parents);
- }
- }
}
void bdrv_drained_end(BlockDriverState *bs)
{
IO_OR_GS_CODE();
- bdrv_do_drained_end(bs, false, NULL, false);
-}
-
-void bdrv_subtree_drained_end(BlockDriverState *bs)
-{
- IO_OR_GS_CODE();
- bdrv_do_drained_end(bs, true, NULL, false);
-}
-
-void bdrv_apply_subtree_drain(BdrvChild *child, BlockDriverState *new_parent)
-{
- int i;
- IO_OR_GS_CODE();
-
- for (i = 0; i < new_parent->recursive_quiesce_counter; i++) {
- bdrv_do_drained_begin(child->bs, true, child, false, true);
- }
-}
-
-void bdrv_unapply_subtree_drain(BdrvChild *child, BlockDriverState *old_parent)
-{
- int i;
- IO_OR_GS_CODE();
-
- for (i = 0; i < old_parent->recursive_quiesce_counter; i++) {
- bdrv_do_drained_end(child->bs, true, child, false);
- }
+ bdrv_do_drained_end(bs, NULL, false);
}
void bdrv_drain(BlockDriverState *bs)
@@ -529,7 +460,7 @@ static bool bdrv_drain_all_poll(void)
while ((bs = bdrv_next_all_states(bs))) {
AioContext *aio_context = bdrv_get_aio_context(bs);
aio_context_acquire(aio_context);
- result |= bdrv_drain_poll(bs, false, NULL, true);
+ result |= bdrv_drain_poll(bs, NULL, true);
aio_context_release(aio_context);
}
@@ -554,7 +485,7 @@ void bdrv_drain_all_begin(void)
GLOBAL_STATE_CODE();
if (qemu_in_coroutine()) {
- bdrv_co_yield_to_drain(NULL, true, false, NULL, true, true);
+ bdrv_co_yield_to_drain(NULL, true, NULL, true, true);
return;
}
@@ -579,7 +510,7 @@ void bdrv_drain_all_begin(void)
AioContext *aio_context = bdrv_get_aio_context(bs);
aio_context_acquire(aio_context);
- bdrv_do_drained_begin(bs, false, NULL, true, false);
+ bdrv_do_drained_begin(bs, NULL, true, false);
aio_context_release(aio_context);
}
@@ -599,7 +530,7 @@ void bdrv_drain_all_end_quiesce(BlockDriverState *bs)
g_assert(!bs->refcnt);
while (bs->quiesce_counter) {
- bdrv_do_drained_end(bs, false, NULL, true);
+ bdrv_do_drained_end(bs, NULL, true);
}
}
@@ -621,7 +552,7 @@ void bdrv_drain_all_end(void)
AioContext *aio_context = bdrv_get_aio_context(bs);
aio_context_acquire(aio_context);
- bdrv_do_drained_end(bs, false, NULL, true);
+ bdrv_do_drained_end(bs, NULL, true);
aio_context_release(aio_context);
}
diff --git a/include/block/block-io.h b/include/block/block-io.h
index 054e964c9b..9c36a16a1f 100644
--- a/include/block/block-io.h
+++ b/include/block/block-io.h
@@ -302,8 +302,7 @@ void bdrv_parent_drained_end_single(BdrvChild *c);
/**
* bdrv_drain_poll:
*
- * Poll for pending requests in @bs, its parents (except for @ignore_parent),
- * and if @recursive is true its children as well (used for subtree drain).
+ * Poll for pending requests in @bs and its parents (except for @ignore_parent).
*
* If @ignore_bds_parents is true, parents that are BlockDriverStates must
* ignore the drain request because they will be drained separately (used for
@@ -311,8 +310,8 @@ void bdrv_parent_drained_end_single(BdrvChild *c);
*
* This is part of bdrv_drained_begin.
*/
-bool bdrv_drain_poll(BlockDriverState *bs, bool recursive,
- BdrvChild *ignore_parent, bool ignore_bds_parents);
+bool bdrv_drain_poll(BlockDriverState *bs, BdrvChild *ignore_parent,
+ bool ignore_bds_parents);
/**
* bdrv_drained_begin:
@@ -333,12 +332,6 @@ void bdrv_drained_begin(BlockDriverState *bs);
void bdrv_do_drained_begin_quiesce(BlockDriverState *bs,
BdrvChild *parent, bool ignore_bds_parents);
-/**
- * Like bdrv_drained_begin, but recursively begins a quiesced section for
- * exclusive access to all child nodes as well.
- */
-void bdrv_subtree_drained_begin(BlockDriverState *bs);
-
/**
* bdrv_drained_end:
*
@@ -346,9 +339,4 @@ void bdrv_subtree_drained_begin(BlockDriverState *bs);
*/
void bdrv_drained_end(BlockDriverState *bs);
-/**
- * End a quiescent section started by bdrv_subtree_drained_begin().
- */
-void bdrv_subtree_drained_end(BlockDriverState *bs);
-
#endif /* BLOCK_IO_H */
diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h
index 2b97576f6d..791dddfd7d 100644
--- a/include/block/block_int-common.h
+++ b/include/block/block_int-common.h
@@ -1184,7 +1184,6 @@ struct BlockDriverState {
/* Accessed with atomic ops. */
int quiesce_counter;
- int recursive_quiesce_counter;
unsigned int write_gen; /* Current data generation */
diff --git a/include/block/block_int-io.h b/include/block/block_int-io.h
index 4b0b3e17ef..8bc061ebb8 100644
--- a/include/block/block_int-io.h
+++ b/include/block/block_int-io.h
@@ -179,16 +179,4 @@ void bdrv_bsc_invalidate_range(BlockDriverState *bs,
*/
void bdrv_bsc_fill(BlockDriverState *bs, int64_t offset, int64_t bytes);
-
-/*
- * "I/O or GS" API functions. These functions can run without
- * the BQL, but only in one specific iothread/main loop.
- *
- * See include/block/block-io.h for more information about
- * the "I/O or GS" API.
- */
-
-void bdrv_apply_subtree_drain(BdrvChild *child, BlockDriverState *new_parent);
-void bdrv_unapply_subtree_drain(BdrvChild *child, BlockDriverState *old_parent);
-
#endif /* BLOCK_INT_IO_H */
diff --git a/tests/unit/test-bdrv-drain.c b/tests/unit/test-bdrv-drain.c
index 695519ee02..dda08de8db 100644
--- a/tests/unit/test-bdrv-drain.c
+++ b/tests/unit/test-bdrv-drain.c
@@ -156,7 +156,6 @@ static void call_in_coroutine(void (*entry)(void))
enum drain_type {
BDRV_DRAIN_ALL,
BDRV_DRAIN,
- BDRV_SUBTREE_DRAIN,
DRAIN_TYPE_MAX,
};
@@ -165,7 +164,6 @@ static void do_drain_begin(enum drain_type drain_type, BlockDriverState *bs)
switch (drain_type) {
case BDRV_DRAIN_ALL: bdrv_drain_all_begin(); break;
case BDRV_DRAIN: bdrv_drained_begin(bs); break;
- case BDRV_SUBTREE_DRAIN: bdrv_subtree_drained_begin(bs); break;
default: g_assert_not_reached();
}
}
@@ -175,7 +173,6 @@ static void do_drain_end(enum drain_type drain_type, BlockDriverState *bs)
switch (drain_type) {
case BDRV_DRAIN_ALL: bdrv_drain_all_end(); break;
case BDRV_DRAIN: bdrv_drained_end(bs); break;
- case BDRV_SUBTREE_DRAIN: bdrv_subtree_drained_end(bs); break;
default: g_assert_not_reached();
}
}
@@ -271,11 +268,6 @@ static void test_drv_cb_drain(void)
test_drv_cb_common(BDRV_DRAIN, false);
}
-static void test_drv_cb_drain_subtree(void)
-{
- test_drv_cb_common(BDRV_SUBTREE_DRAIN, true);
-}
-
static void test_drv_cb_co_drain_all(void)
{
call_in_coroutine(test_drv_cb_drain_all);
@@ -286,11 +278,6 @@ static void test_drv_cb_co_drain(void)
call_in_coroutine(test_drv_cb_drain);
}
-static void test_drv_cb_co_drain_subtree(void)
-{
- call_in_coroutine(test_drv_cb_drain_subtree);
-}
-
static void test_quiesce_common(enum drain_type drain_type, bool recursive)
{
BlockBackend *blk;
@@ -332,11 +319,6 @@ static void test_quiesce_drain(void)
test_quiesce_common(BDRV_DRAIN, false);
}
-static void test_quiesce_drain_subtree(void)
-{
- test_quiesce_common(BDRV_SUBTREE_DRAIN, true);
-}
-
static void test_quiesce_co_drain_all(void)
{
call_in_coroutine(test_quiesce_drain_all);
@@ -347,11 +329,6 @@ static void test_quiesce_co_drain(void)
call_in_coroutine(test_quiesce_drain);
}
-static void test_quiesce_co_drain_subtree(void)
-{
- call_in_coroutine(test_quiesce_drain_subtree);
-}
-
static void test_nested(void)
{
BlockBackend *blk;
@@ -402,158 +379,6 @@ static void test_nested(void)
blk_unref(blk);
}
-static void test_multiparent(void)
-{
- BlockBackend *blk_a, *blk_b;
- BlockDriverState *bs_a, *bs_b, *backing;
- BDRVTestState *a_s, *b_s, *backing_s;
-
- blk_a = blk_new(qemu_get_aio_context(), BLK_PERM_ALL, BLK_PERM_ALL);
- bs_a = bdrv_new_open_driver(&bdrv_test, "test-node-a", BDRV_O_RDWR,
- &error_abort);
- a_s = bs_a->opaque;
- blk_insert_bs(blk_a, bs_a, &error_abort);
-
- blk_b = blk_new(qemu_get_aio_context(), BLK_PERM_ALL, BLK_PERM_ALL);
- bs_b = bdrv_new_open_driver(&bdrv_test, "test-node-b", BDRV_O_RDWR,
- &error_abort);
- b_s = bs_b->opaque;
- blk_insert_bs(blk_b, bs_b, &error_abort);
-
- backing = bdrv_new_open_driver(&bdrv_test, "backing", 0, &error_abort);
- backing_s = backing->opaque;
- bdrv_set_backing_hd(bs_a, backing, &error_abort);
- bdrv_set_backing_hd(bs_b, backing, &error_abort);
-
- g_assert_cmpint(bs_a->quiesce_counter, ==, 0);
- g_assert_cmpint(bs_b->quiesce_counter, ==, 0);
- g_assert_cmpint(backing->quiesce_counter, ==, 0);
- g_assert_cmpint(a_s->drain_count, ==, 0);
- g_assert_cmpint(b_s->drain_count, ==, 0);
- g_assert_cmpint(backing_s->drain_count, ==, 0);
-
- do_drain_begin(BDRV_SUBTREE_DRAIN, bs_a);
-
- g_assert_cmpint(bs_a->quiesce_counter, ==, 1);
- g_assert_cmpint(bs_b->quiesce_counter, ==, 1);
- g_assert_cmpint(backing->quiesce_counter, ==, 1);
- g_assert_cmpint(a_s->drain_count, ==, 1);
- g_assert_cmpint(b_s->drain_count, ==, 1);
- g_assert_cmpint(backing_s->drain_count, ==, 1);
-
- do_drain_begin(BDRV_SUBTREE_DRAIN, bs_b);
-
- g_assert_cmpint(bs_a->quiesce_counter, ==, 2);
- g_assert_cmpint(bs_b->quiesce_counter, ==, 2);
- g_assert_cmpint(backing->quiesce_counter, ==, 2);
- g_assert_cmpint(a_s->drain_count, ==, 2);
- g_assert_cmpint(b_s->drain_count, ==, 2);
- g_assert_cmpint(backing_s->drain_count, ==, 2);
-
- do_drain_end(BDRV_SUBTREE_DRAIN, bs_b);
-
- g_assert_cmpint(bs_a->quiesce_counter, ==, 1);
- g_assert_cmpint(bs_b->quiesce_counter, ==, 1);
- g_assert_cmpint(backing->quiesce_counter, ==, 1);
- g_assert_cmpint(a_s->drain_count, ==, 1);
- g_assert_cmpint(b_s->drain_count, ==, 1);
- g_assert_cmpint(backing_s->drain_count, ==, 1);
-
- do_drain_end(BDRV_SUBTREE_DRAIN, bs_a);
-
- g_assert_cmpint(bs_a->quiesce_counter, ==, 0);
- g_assert_cmpint(bs_b->quiesce_counter, ==, 0);
- g_assert_cmpint(backing->quiesce_counter, ==, 0);
- g_assert_cmpint(a_s->drain_count, ==, 0);
- g_assert_cmpint(b_s->drain_count, ==, 0);
- g_assert_cmpint(backing_s->drain_count, ==, 0);
-
- bdrv_unref(backing);
- bdrv_unref(bs_a);
- bdrv_unref(bs_b);
- blk_unref(blk_a);
- blk_unref(blk_b);
-}
-
-static void test_graph_change_drain_subtree(void)
-{
- BlockBackend *blk_a, *blk_b;
- BlockDriverState *bs_a, *bs_b, *backing;
- BDRVTestState *a_s, *b_s, *backing_s;
-
- blk_a = blk_new(qemu_get_aio_context(), BLK_PERM_ALL, BLK_PERM_ALL);
- bs_a = bdrv_new_open_driver(&bdrv_test, "test-node-a", BDRV_O_RDWR,
- &error_abort);
- a_s = bs_a->opaque;
- blk_insert_bs(blk_a, bs_a, &error_abort);
-
- blk_b = blk_new(qemu_get_aio_context(), BLK_PERM_ALL, BLK_PERM_ALL);
- bs_b = bdrv_new_open_driver(&bdrv_test, "test-node-b", BDRV_O_RDWR,
- &error_abort);
- b_s = bs_b->opaque;
- blk_insert_bs(blk_b, bs_b, &error_abort);
-
- backing = bdrv_new_open_driver(&bdrv_test, "backing", 0, &error_abort);
- backing_s = backing->opaque;
- bdrv_set_backing_hd(bs_a, backing, &error_abort);
-
- g_assert_cmpint(bs_a->quiesce_counter, ==, 0);
- g_assert_cmpint(bs_b->quiesce_counter, ==, 0);
- g_assert_cmpint(backing->quiesce_counter, ==, 0);
- g_assert_cmpint(a_s->drain_count, ==, 0);
- g_assert_cmpint(b_s->drain_count, ==, 0);
- g_assert_cmpint(backing_s->drain_count, ==, 0);
-
- do_drain_begin(BDRV_SUBTREE_DRAIN, bs_a);
- do_drain_begin(BDRV_SUBTREE_DRAIN, bs_a);
- do_drain_begin(BDRV_SUBTREE_DRAIN, bs_a);
- do_drain_begin(BDRV_SUBTREE_DRAIN, bs_b);
- do_drain_begin(BDRV_SUBTREE_DRAIN, bs_b);
-
- bdrv_set_backing_hd(bs_b, backing, &error_abort);
- g_assert_cmpint(bs_a->quiesce_counter, ==, 5);
- g_assert_cmpint(bs_b->quiesce_counter, ==, 5);
- g_assert_cmpint(backing->quiesce_counter, ==, 5);
- g_assert_cmpint(a_s->drain_count, ==, 5);
- g_assert_cmpint(b_s->drain_count, ==, 5);
- g_assert_cmpint(backing_s->drain_count, ==, 5);
-
- bdrv_set_backing_hd(bs_b, NULL, &error_abort);
- g_assert_cmpint(bs_a->quiesce_counter, ==, 3);
- g_assert_cmpint(bs_b->quiesce_counter, ==, 2);
- g_assert_cmpint(backing->quiesce_counter, ==, 3);
- g_assert_cmpint(a_s->drain_count, ==, 3);
- g_assert_cmpint(b_s->drain_count, ==, 2);
- g_assert_cmpint(backing_s->drain_count, ==, 3);
-
- bdrv_set_backing_hd(bs_b, backing, &error_abort);
- g_assert_cmpint(bs_a->quiesce_counter, ==, 5);
- g_assert_cmpint(bs_b->quiesce_counter, ==, 5);
- g_assert_cmpint(backing->quiesce_counter, ==, 5);
- g_assert_cmpint(a_s->drain_count, ==, 5);
- g_assert_cmpint(b_s->drain_count, ==, 5);
- g_assert_cmpint(backing_s->drain_count, ==, 5);
-
- do_drain_end(BDRV_SUBTREE_DRAIN, bs_b);
- do_drain_end(BDRV_SUBTREE_DRAIN, bs_b);
- do_drain_end(BDRV_SUBTREE_DRAIN, bs_a);
- do_drain_end(BDRV_SUBTREE_DRAIN, bs_a);
- do_drain_end(BDRV_SUBTREE_DRAIN, bs_a);
-
- g_assert_cmpint(bs_a->quiesce_counter, ==, 0);
- g_assert_cmpint(bs_b->quiesce_counter, ==, 0);
- g_assert_cmpint(backing->quiesce_counter, ==, 0);
- g_assert_cmpint(a_s->drain_count, ==, 0);
- g_assert_cmpint(b_s->drain_count, ==, 0);
- g_assert_cmpint(backing_s->drain_count, ==, 0);
-
- bdrv_unref(backing);
- bdrv_unref(bs_a);
- bdrv_unref(bs_b);
- blk_unref(blk_a);
- blk_unref(blk_b);
-}
-
static void test_graph_change_drain_all(void)
{
BlockBackend *blk_a, *blk_b;
@@ -773,12 +598,6 @@ static void test_iothread_drain(void)
test_iothread_common(BDRV_DRAIN, 1);
}
-static void test_iothread_drain_subtree(void)
-{
- test_iothread_common(BDRV_SUBTREE_DRAIN, 0);
- test_iothread_common(BDRV_SUBTREE_DRAIN, 1);
-}
-
typedef struct TestBlockJob {
BlockJob common;
@@ -863,7 +682,6 @@ enum test_job_result {
enum test_job_drain_node {
TEST_JOB_DRAIN_SRC,
TEST_JOB_DRAIN_SRC_CHILD,
- TEST_JOB_DRAIN_SRC_PARENT,
};
static void test_blockjob_common_drain_node(enum drain_type drain_type,
@@ -901,9 +719,6 @@ static void test_blockjob_common_drain_node(enum drain_type drain_type,
case TEST_JOB_DRAIN_SRC_CHILD:
drain_bs = src_backing;
break;
- case TEST_JOB_DRAIN_SRC_PARENT:
- drain_bs = src_overlay;
- break;
default:
g_assert_not_reached();
}
@@ -1055,10 +870,6 @@ static void test_blockjob_common(enum drain_type drain_type, bool use_iothread,
TEST_JOB_DRAIN_SRC);
test_blockjob_common_drain_node(drain_type, use_iothread, result,
TEST_JOB_DRAIN_SRC_CHILD);
- if (drain_type == BDRV_SUBTREE_DRAIN) {
- test_blockjob_common_drain_node(drain_type, use_iothread, result,
- TEST_JOB_DRAIN_SRC_PARENT);
- }
}
static void test_blockjob_drain_all(void)
@@ -1071,11 +882,6 @@ static void test_blockjob_drain(void)
test_blockjob_common(BDRV_DRAIN, false, TEST_JOB_SUCCESS);
}
-static void test_blockjob_drain_subtree(void)
-{
- test_blockjob_common(BDRV_SUBTREE_DRAIN, false, TEST_JOB_SUCCESS);
-}
-
static void test_blockjob_error_drain_all(void)
{
test_blockjob_common(BDRV_DRAIN_ALL, false, TEST_JOB_FAIL_RUN);
@@ -1088,12 +894,6 @@ static void test_blockjob_error_drain(void)
test_blockjob_common(BDRV_DRAIN, false, TEST_JOB_FAIL_PREPARE);
}
-static void test_blockjob_error_drain_subtree(void)
-{
- test_blockjob_common(BDRV_SUBTREE_DRAIN, false, TEST_JOB_FAIL_RUN);
- test_blockjob_common(BDRV_SUBTREE_DRAIN, false, TEST_JOB_FAIL_PREPARE);
-}
-
static void test_blockjob_iothread_drain_all(void)
{
test_blockjob_common(BDRV_DRAIN_ALL, true, TEST_JOB_SUCCESS);
@@ -1104,11 +904,6 @@ static void test_blockjob_iothread_drain(void)
test_blockjob_common(BDRV_DRAIN, true, TEST_JOB_SUCCESS);
}
-static void test_blockjob_iothread_drain_subtree(void)
-{
- test_blockjob_common(BDRV_SUBTREE_DRAIN, true, TEST_JOB_SUCCESS);
-}
-
static void test_blockjob_iothread_error_drain_all(void)
{
test_blockjob_common(BDRV_DRAIN_ALL, true, TEST_JOB_FAIL_RUN);
@@ -1121,12 +916,6 @@ static void test_blockjob_iothread_error_drain(void)
test_blockjob_common(BDRV_DRAIN, true, TEST_JOB_FAIL_PREPARE);
}
-static void test_blockjob_iothread_error_drain_subtree(void)
-{
- test_blockjob_common(BDRV_SUBTREE_DRAIN, true, TEST_JOB_FAIL_RUN);
- test_blockjob_common(BDRV_SUBTREE_DRAIN, true, TEST_JOB_FAIL_PREPARE);
-}
-
typedef struct BDRVTestTopState {
BdrvChild *wait_child;
@@ -1273,14 +1062,6 @@ static void do_test_delete_by_drain(bool detach_instead_of_delete,
bdrv_drain(child_bs);
bdrv_unref(child_bs);
break;
- case BDRV_SUBTREE_DRAIN:
- /* Would have to ref/unref bs here for !detach_instead_of_delete, but
- * then the whole test becomes pointless because the graph changes
- * don't occur during the drain any more. */
- assert(detach_instead_of_delete);
- bdrv_subtree_drained_begin(bs);
- bdrv_subtree_drained_end(bs);
- break;
case BDRV_DRAIN_ALL:
bdrv_drain_all_begin();
bdrv_drain_all_end();
@@ -1315,11 +1096,6 @@ static void test_detach_by_drain(void)
do_test_delete_by_drain(true, BDRV_DRAIN);
}
-static void test_detach_by_drain_subtree(void)
-{
- do_test_delete_by_drain(true, BDRV_SUBTREE_DRAIN);
-}
-
struct detach_by_parent_data {
BlockDriverState *parent_b;
@@ -1452,7 +1228,10 @@ static void test_detach_indirect(bool by_parent_cb)
g_assert(acb != NULL);
/* Drain and check the expected result */
- bdrv_subtree_drained_begin(parent_b);
+ bdrv_drained_begin(parent_b);
+ bdrv_drained_begin(a);
+ bdrv_drained_begin(b);
+ bdrv_drained_begin(c);
g_assert(detach_by_parent_data.child_c != NULL);
@@ -1467,12 +1246,15 @@ static void test_detach_indirect(bool by_parent_cb)
g_assert(QLIST_NEXT(child_a, next) == NULL);
g_assert_cmpint(parent_a->quiesce_counter, ==, 1);
- g_assert_cmpint(parent_b->quiesce_counter, ==, 1);
+ g_assert_cmpint(parent_b->quiesce_counter, ==, 3);
g_assert_cmpint(a->quiesce_counter, ==, 1);
- g_assert_cmpint(b->quiesce_counter, ==, 0);
+ g_assert_cmpint(b->quiesce_counter, ==, 1);
g_assert_cmpint(c->quiesce_counter, ==, 1);
- bdrv_subtree_drained_end(parent_b);
+ bdrv_drained_end(parent_b);
+ bdrv_drained_end(a);
+ bdrv_drained_end(b);
+ bdrv_drained_end(c);
bdrv_unref(parent_b);
blk_unref(blk);
@@ -2202,70 +1984,47 @@ int main(int argc, char **argv)
g_test_add_func("/bdrv-drain/driver-cb/drain_all", test_drv_cb_drain_all);
g_test_add_func("/bdrv-drain/driver-cb/drain", test_drv_cb_drain);
- g_test_add_func("/bdrv-drain/driver-cb/drain_subtree",
- test_drv_cb_drain_subtree);
g_test_add_func("/bdrv-drain/driver-cb/co/drain_all",
test_drv_cb_co_drain_all);
g_test_add_func("/bdrv-drain/driver-cb/co/drain", test_drv_cb_co_drain);
- g_test_add_func("/bdrv-drain/driver-cb/co/drain_subtree",
- test_drv_cb_co_drain_subtree);
-
g_test_add_func("/bdrv-drain/quiesce/drain_all", test_quiesce_drain_all);
g_test_add_func("/bdrv-drain/quiesce/drain", test_quiesce_drain);
- g_test_add_func("/bdrv-drain/quiesce/drain_subtree",
- test_quiesce_drain_subtree);
g_test_add_func("/bdrv-drain/quiesce/co/drain_all",
test_quiesce_co_drain_all);
g_test_add_func("/bdrv-drain/quiesce/co/drain", test_quiesce_co_drain);
- g_test_add_func("/bdrv-drain/quiesce/co/drain_subtree",
- test_quiesce_co_drain_subtree);
g_test_add_func("/bdrv-drain/nested", test_nested);
- g_test_add_func("/bdrv-drain/multiparent", test_multiparent);
- g_test_add_func("/bdrv-drain/graph-change/drain_subtree",
- test_graph_change_drain_subtree);
g_test_add_func("/bdrv-drain/graph-change/drain_all",
test_graph_change_drain_all);
g_test_add_func("/bdrv-drain/iothread/drain_all", test_iothread_drain_all);
g_test_add_func("/bdrv-drain/iothread/drain", test_iothread_drain);
- g_test_add_func("/bdrv-drain/iothread/drain_subtree",
- test_iothread_drain_subtree);
g_test_add_func("/bdrv-drain/blockjob/drain_all", test_blockjob_drain_all);
g_test_add_func("/bdrv-drain/blockjob/drain", test_blockjob_drain);
- g_test_add_func("/bdrv-drain/blockjob/drain_subtree",
- test_blockjob_drain_subtree);
g_test_add_func("/bdrv-drain/blockjob/error/drain_all",
test_blockjob_error_drain_all);
g_test_add_func("/bdrv-drain/blockjob/error/drain",
test_blockjob_error_drain);
- g_test_add_func("/bdrv-drain/blockjob/error/drain_subtree",
- test_blockjob_error_drain_subtree);
g_test_add_func("/bdrv-drain/blockjob/iothread/drain_all",
test_blockjob_iothread_drain_all);
g_test_add_func("/bdrv-drain/blockjob/iothread/drain",
test_blockjob_iothread_drain);
- g_test_add_func("/bdrv-drain/blockjob/iothread/drain_subtree",
- test_blockjob_iothread_drain_subtree);
g_test_add_func("/bdrv-drain/blockjob/iothread/error/drain_all",
test_blockjob_iothread_error_drain_all);
g_test_add_func("/bdrv-drain/blockjob/iothread/error/drain",
test_blockjob_iothread_error_drain);
- g_test_add_func("/bdrv-drain/blockjob/iothread/error/drain_subtree",
- test_blockjob_iothread_error_drain_subtree);
g_test_add_func("/bdrv-drain/deletion/drain", test_delete_by_drain);
g_test_add_func("/bdrv-drain/detach/drain_all", test_detach_by_drain_all);
g_test_add_func("/bdrv-drain/detach/drain", test_detach_by_drain);
- g_test_add_func("/bdrv-drain/detach/drain_subtree", test_detach_by_drain_subtree);
g_test_add_func("/bdrv-drain/detach/parent_cb", test_detach_by_parent_cb);
g_test_add_func("/bdrv-drain/detach/driver_cb", test_detach_by_driver_cb);
--
2.31.1

302
SOURCES/kvm-block-Revert-.bdrv_drained_begin-end-to-non-coroutin.patch Normal file
View File

@ -0,0 +1,302 @@
From 0e894c93cae97bb792dc483be8e295d097ebd7a1 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Fri, 18 Nov 2022 18:40:58 +0100
Subject: [PATCH 16/31] block: Revert .bdrv_drained_begin/end to
non-coroutine_fn
RH-Author: Stefano Garzarella <sgarzare@redhat.com>
RH-MergeRequest: 135: block: Simplify drain to prevent QEMU from crashing during snapshot
RH-Bugzilla: 2155112
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [4/16] 86d6049e40a99604e414c2572b67f74b85868832 (sgarzarella/qemu-kvm-c-9-s)
Polling during bdrv_drained_end() can be problematic (and in the future,
we may get cases for bdrv_drained_begin() where polling is forbidden,
and we don't care about already in-flight requests, but just want to
prevent new requests from arriving).
The .bdrv_drained_begin/end callbacks running in a coroutine is the only
reason why we have to do this polling, so make them non-coroutine
callbacks again. None of the callers actually yield any more.
This means that bdrv_drained_end() effectively doesn't poll any more,
even if AIO_WAIT_WHILE() loops are still there (their condition is false
from the beginning). This is generally not a problem, but in
test-bdrv-drain, some additional explicit aio_poll() calls need to be
added because the test case wants to verify the final state after BHs
have executed.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Reviewed-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20221118174110.55183-4-kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 5e8ac21717373cbe96ef7a91e216bf5788815d63)
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
block.c | 4 +--
block/io.c | 49 +++++---------------------------
block/qed.c | 6 ++--
block/throttle.c | 8 +++---
include/block/block_int-common.h | 10 ++++---
tests/unit/test-bdrv-drain.c | 18 ++++++------
6 files changed, 32 insertions(+), 63 deletions(-)
diff --git a/block.c b/block.c
index ec184150a2..16a62a329c 100644
--- a/block.c
+++ b/block.c
@@ -1713,8 +1713,8 @@ static int bdrv_open_driver(BlockDriverState *bs, BlockDriver *drv,
assert(is_power_of_2(bs->bl.request_alignment));
for (i = 0; i < bs->quiesce_counter; i++) {
- if (drv->bdrv_co_drain_begin) {
- drv->bdrv_co_drain_begin(bs);
+ if (drv->bdrv_drain_begin) {
+ drv->bdrv_drain_begin(bs);
}
}
diff --git a/block/io.c b/block/io.c
index b9424024f9..c2ed4b2af9 100644
--- a/block/io.c
+++ b/block/io.c
@@ -252,55 +252,20 @@ typedef struct {
int *drained_end_counter;
} BdrvCoDrainData;
-static void coroutine_fn bdrv_drain_invoke_entry(void *opaque)
-{
- BdrvCoDrainData *data = opaque;
- BlockDriverState *bs = data->bs;
-
- if (data->begin) {
- bs->drv->bdrv_co_drain_begin(bs);
- } else {
- bs->drv->bdrv_co_drain_end(bs);
- }
-
- /* Set data->done and decrement drained_end_counter before bdrv_wakeup() */
- qatomic_mb_set(&data->done, true);
- if (!data->begin) {
- qatomic_dec(data->drained_end_counter);
- }
- bdrv_dec_in_flight(bs);
-
- g_free(data);
-}
-
-/* Recursively call BlockDriver.bdrv_co_drain_begin/end callbacks */
+/* Recursively call BlockDriver.bdrv_drain_begin/end callbacks */
static void bdrv_drain_invoke(BlockDriverState *bs, bool begin,
int *drained_end_counter)
{
- BdrvCoDrainData *data;
-
- if (!bs->drv || (begin && !bs->drv->bdrv_co_drain_begin) ||
- (!begin && !bs->drv->bdrv_co_drain_end)) {
+ if (!bs->drv || (begin && !bs->drv->bdrv_drain_begin) ||
+ (!begin && !bs->drv->bdrv_drain_end)) {
return;
}
- data = g_new(BdrvCoDrainData, 1);
- *data = (BdrvCoDrainData) {
- .bs = bs,
- .done = false,
- .begin = begin,
- .drained_end_counter = drained_end_counter,
- };
-
- if (!begin) {
- qatomic_inc(drained_end_counter);
+ if (begin) {
+ bs->drv->bdrv_drain_begin(bs);
+ } else {
+ bs->drv->bdrv_drain_end(bs);
}
-
- /* Make sure the driver callback completes during the polling phase for
- * drain_begin. */
- bdrv_inc_in_flight(bs);
- data->co = qemu_coroutine_create(bdrv_drain_invoke_entry, data);
- aio_co_schedule(bdrv_get_aio_context(bs), data->co);
}
/* Returns true if BDRV_POLL_WHILE() should go into a blocking aio_poll() */
diff --git a/block/qed.c b/block/qed.c
index 013f826c44..c2691a85b1 100644
--- a/block/qed.c
+++ b/block/qed.c
@@ -262,7 +262,7 @@ static bool coroutine_fn qed_plug_allocating_write_reqs(BDRVQEDState *s)
assert(!s->allocating_write_reqs_plugged);
if (s->allocating_acb != NULL) {
/* Another allocating write came concurrently. This cannot happen
- * from bdrv_qed_co_drain_begin, but it can happen when the timer runs.
+ * from bdrv_qed_drain_begin, but it can happen when the timer runs.
*/
qemu_co_mutex_unlock(&s->table_lock);
return false;
@@ -365,7 +365,7 @@ static void bdrv_qed_attach_aio_context(BlockDriverState *bs,
}
}
-static void coroutine_fn bdrv_qed_co_drain_begin(BlockDriverState *bs)
+static void bdrv_qed_drain_begin(BlockDriverState *bs)
{
BDRVQEDState *s = bs->opaque;
@@ -1661,7 +1661,7 @@ static BlockDriver bdrv_qed = {
.bdrv_co_check = bdrv_qed_co_check,
.bdrv_detach_aio_context = bdrv_qed_detach_aio_context,
.bdrv_attach_aio_context = bdrv_qed_attach_aio_context,
- .bdrv_co_drain_begin = bdrv_qed_co_drain_begin,
+ .bdrv_drain_begin = bdrv_qed_drain_begin,
};
static void bdrv_qed_init(void)
diff --git a/block/throttle.c b/block/throttle.c
index 131eba3ab4..88851c84f4 100644
--- a/block/throttle.c
+++ b/block/throttle.c
@@ -214,7 +214,7 @@ static void throttle_reopen_abort(BDRVReopenState *reopen_state)
reopen_state->opaque = NULL;
}
-static void coroutine_fn throttle_co_drain_begin(BlockDriverState *bs)
+static void throttle_drain_begin(BlockDriverState *bs)
{
ThrottleGroupMember *tgm = bs->opaque;
if (qatomic_fetch_inc(&tgm->io_limits_disabled) == 0) {
@@ -222,7 +222,7 @@ static void coroutine_fn throttle_co_drain_begin(BlockDriverState *bs)
}
}
-static void coroutine_fn throttle_co_drain_end(BlockDriverState *bs)
+static void throttle_drain_end(BlockDriverState *bs)
{
ThrottleGroupMember *tgm = bs->opaque;
assert(tgm->io_limits_disabled);
@@ -261,8 +261,8 @@ static BlockDriver bdrv_throttle = {
.bdrv_reopen_commit = throttle_reopen_commit,
.bdrv_reopen_abort = throttle_reopen_abort,
- .bdrv_co_drain_begin = throttle_co_drain_begin,
- .bdrv_co_drain_end = throttle_co_drain_end,
+ .bdrv_drain_begin = throttle_drain_begin,
+ .bdrv_drain_end = throttle_drain_end,
.is_filter = true,
.strong_runtime_opts = throttle_strong_runtime_opts,
diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h
index 31ae91e56e..40d646d1ed 100644
--- a/include/block/block_int-common.h
+++ b/include/block/block_int-common.h
@@ -735,17 +735,19 @@ struct BlockDriver {
void (*bdrv_io_unplug)(BlockDriverState *bs);
/**
- * bdrv_co_drain_begin is called if implemented in the beginning of a
+ * bdrv_drain_begin is called if implemented in the beginning of a
* drain operation to drain and stop any internal sources of requests in
* the driver.
- * bdrv_co_drain_end is called if implemented at the end of the drain.
+ * bdrv_drain_end is called if implemented at the end of the drain.
*
* They should be used by the driver to e.g. manage scheduled I/O
* requests, or toggle an internal state. After the end of the drain new
* requests will continue normally.
+ *
+ * Implementations of both functions must not call aio_poll().
*/
- void coroutine_fn (*bdrv_co_drain_begin)(BlockDriverState *bs);
- void coroutine_fn (*bdrv_co_drain_end)(BlockDriverState *bs);
+ void (*bdrv_drain_begin)(BlockDriverState *bs);
+ void (*bdrv_drain_end)(BlockDriverState *bs);
bool (*bdrv_supports_persistent_dirty_bitmap)(BlockDriverState *bs);
bool coroutine_fn (*bdrv_co_can_store_new_dirty_bitmap)(
diff --git a/tests/unit/test-bdrv-drain.c b/tests/unit/test-bdrv-drain.c
index 24f34e24ad..695519ee02 100644
--- a/tests/unit/test-bdrv-drain.c
+++ b/tests/unit/test-bdrv-drain.c
@@ -46,7 +46,7 @@ static void coroutine_fn sleep_in_drain_begin(void *opaque)
bdrv_dec_in_flight(bs);
}
-static void coroutine_fn bdrv_test_co_drain_begin(BlockDriverState *bs)
+static void bdrv_test_drain_begin(BlockDriverState *bs)
{
BDRVTestState *s = bs->opaque;
s->drain_count++;
@@ -57,7 +57,7 @@ static void coroutine_fn bdrv_test_co_drain_begin(BlockDriverState *bs)
}
}
-static void coroutine_fn bdrv_test_co_drain_end(BlockDriverState *bs)
+static void bdrv_test_drain_end(BlockDriverState *bs)
{
BDRVTestState *s = bs->opaque;
s->drain_count--;
@@ -111,8 +111,8 @@ static BlockDriver bdrv_test = {
.bdrv_close = bdrv_test_close,
.bdrv_co_preadv = bdrv_test_co_preadv,
- .bdrv_co_drain_begin = bdrv_test_co_drain_begin,
- .bdrv_co_drain_end = bdrv_test_co_drain_end,
+ .bdrv_drain_begin = bdrv_test_drain_begin,
+ .bdrv_drain_end = bdrv_test_drain_end,
.bdrv_child_perm = bdrv_default_perms,
@@ -1703,6 +1703,7 @@ static void test_blockjob_commit_by_drained_end(void)
bdrv_drained_begin(bs_child);
g_assert(!job_has_completed);
bdrv_drained_end(bs_child);
+ aio_poll(qemu_get_aio_context(), false);
g_assert(job_has_completed);
bdrv_unref(bs_parents[0]);
@@ -1858,6 +1859,7 @@ static void test_drop_intermediate_poll(void)
g_assert(!job_has_completed);
ret = bdrv_drop_intermediate(chain[1], chain[0], NULL);
+ aio_poll(qemu_get_aio_context(), false);
g_assert(ret == 0);
g_assert(job_has_completed);
@@ -1946,7 +1948,7 @@ static void coroutine_fn bdrv_replace_test_drain_co(void *opaque)
* .was_drained.
* Increment .drain_count.
*/
-static void coroutine_fn bdrv_replace_test_co_drain_begin(BlockDriverState *bs)
+static void bdrv_replace_test_drain_begin(BlockDriverState *bs)
{
BDRVReplaceTestState *s = bs->opaque;
@@ -1977,7 +1979,7 @@ static void coroutine_fn bdrv_replace_test_read_entry(void *opaque)
* If .drain_count reaches 0 and the node has a backing file, issue a
* read request.
*/
-static void coroutine_fn bdrv_replace_test_co_drain_end(BlockDriverState *bs)
+static void bdrv_replace_test_drain_end(BlockDriverState *bs)
{
BDRVReplaceTestState *s = bs->opaque;
@@ -2002,8 +2004,8 @@ static BlockDriver bdrv_replace_test = {
.bdrv_close = bdrv_replace_test_close,
.bdrv_co_preadv = bdrv_replace_test_co_preadv,
- .bdrv_co_drain_begin = bdrv_replace_test_co_drain_begin,
- .bdrv_co_drain_end = bdrv_replace_test_co_drain_end,
+ .bdrv_drain_begin = bdrv_replace_test_drain_begin,
+ .bdrv_drain_end = bdrv_replace_test_drain_end,
.bdrv_child_perm = bdrv_default_perms,
};
--
2.31.1

246
SOURCES/kvm-block-Split-BlockNodeInfo-off-of-ImageInfo.patch Normal file
View File

@ -0,0 +1,246 @@
From 54e290df4bc1c9e83be7357caed6a2b1ba4f21f0 Mon Sep 17 00:00:00 2001
From: Hanna Reitz <hreitz@redhat.com>
Date: Mon, 20 Jun 2022 18:26:56 +0200
Subject: [PATCH 09/20] block: Split BlockNodeInfo off of ImageInfo
RH-Author: Hanna Czenczek <hreitz@redhat.com>
RH-MergeRequest: 145: Show protocol-level information in qemu-img info
RH-Bugzilla: 1860292
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Commit: [4/12] fc8d69d549bb9a929db218b91697ee3ae95c1ff6 (hreitz/qemu-kvm-c-9-s)
ImageInfo sometimes contains flat information, and sometimes it does
not. Split off a BlockNodeInfo struct, which only contains information
about a single node and has no link to the backing image.
We do this so we can extend BlockNodeInfo to a BlockGraphInfo struct,
which has links to all child nodes, not just the backing node. It would
be strange to base BlockGraphInfo on ImageInfo, because then this
extended struct would have two links to the backing node (one in
BlockGraphInfo as one of all the child links, and one in ImageInfo).
Furthermore, it is quite common to ignore the backing-image field
altogether: bdrv_query_image_info() does not set it, and
bdrv_image_info_dump() does not evaluate it. That signals that we
should have different structs for describing a single node and one that
has a link to the backing image.
Still, bdrv_query_image_info() and bdrv_image_info_dump() are not
changed too much in this patch. Follow-up patches will handle them.
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220620162704.80987-5-hreitz@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit a2085f8909377b6df738f6c3f7ee6db4d16da8f7)
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
---
block/qapi.c | 86 ++++++++++++++++++++++++++++++++------------
include/block/qapi.h | 3 ++
qapi/block-core.json | 24 +++++++++----
3 files changed, 85 insertions(+), 28 deletions(-)
diff --git a/block/qapi.c b/block/qapi.c
index 51202b470a..e5022b4481 100644
--- a/block/qapi.c
+++ b/block/qapi.c
@@ -241,30 +241,18 @@ int bdrv_query_snapshot_info_list(BlockDriverState *bs,
}
/**
- * bdrv_query_image_info:
- * @bs: block device to examine
- * @p_info: location to store image information
- * @errp: location to store error information
- *
- * Store "flat" image information in @p_info.
- *
- * "Flat" means it does *not* query backing image information,
- * i.e. (*pinfo)->has_backing_image will be set to false and
- * (*pinfo)->backing_image to NULL even when the image does in fact have
- * a backing image.
- *
- * @p_info will be set only on success. On error, store error in @errp.
+ * Helper function for other query info functions. Store information about @bs
+ * in @info, setting @errp on error.
*/
-void bdrv_query_image_info(BlockDriverState *bs,
- ImageInfo **p_info,
- Error **errp)
+static void bdrv_do_query_node_info(BlockDriverState *bs,
+ BlockNodeInfo *info,
+ Error **errp)
{
int64_t size;
const char *backing_filename;
BlockDriverInfo bdi;
int ret;
Error *err = NULL;
- ImageInfo *info;
aio_context_acquire(bdrv_get_aio_context(bs));
@@ -277,7 +265,6 @@ void bdrv_query_image_info(BlockDriverState *bs,
bdrv_refresh_filename(bs);
- info = g_new0(ImageInfo, 1);
info->filename = g_strdup(bs->filename);
info->format = g_strdup(bdrv_get_format_name(bs));
info->virtual_size = size;
@@ -298,7 +285,6 @@ void bdrv_query_image_info(BlockDriverState *bs,
info->format_specific = bdrv_get_specific_info(bs, &err);
if (err) {
error_propagate(errp, err);
- qapi_free_ImageInfo(info);
goto out;
}
info->has_format_specific = info->format_specific != NULL;
@@ -339,16 +325,72 @@ void bdrv_query_image_info(BlockDriverState *bs,
break;
default:
error_propagate(errp, err);
- qapi_free_ImageInfo(info);
goto out;
}
- *p_info = info;
-
out:
aio_context_release(bdrv_get_aio_context(bs));
}
+/**
+ * bdrv_query_block_node_info:
+ * @bs: block node to examine
+ * @p_info: location to store node information
+ * @errp: location to store error information
+ *
+ * Store image information about @bs in @p_info.
+ *
+ * @p_info will be set only on success. On error, store error in @errp.
+ */
+void bdrv_query_block_node_info(BlockDriverState *bs,
+ BlockNodeInfo **p_info,
+ Error **errp)
+{
+ BlockNodeInfo *info;
+ ERRP_GUARD();
+
+ info = g_new0(BlockNodeInfo, 1);
+ bdrv_do_query_node_info(bs, info, errp);
+ if (*errp) {
+ qapi_free_BlockNodeInfo(info);
+ return;
+ }
+
+ *p_info = info;
+}
+
+/**
+ * bdrv_query_image_info:
+ * @bs: block node to examine
+ * @p_info: location to store image information
+ * @errp: location to store error information
+ *
+ * Store "flat" image information in @p_info.
+ *
+ * "Flat" means it does *not* query backing image information,
+ * i.e. (*pinfo)->has_backing_image will be set to false and
+ * (*pinfo)->backing_image to NULL even when the image does in fact have
+ * a backing image.
+ *
+ * @p_info will be set only on success. On error, store error in @errp.
+ */
+void bdrv_query_image_info(BlockDriverState *bs,
+ ImageInfo **p_info,
+ Error **errp)
+{
+ ImageInfo *info;
+ ERRP_GUARD();
+
+ info = g_new0(ImageInfo, 1);
+ bdrv_do_query_node_info(bs, qapi_ImageInfo_base(info), errp);
+ if (*errp) {
+ qapi_free_ImageInfo(info);
+ return;
+ }
+
+ *p_info = info;
+}
+
/* @p_info will be set only on success. */
static void bdrv_query_info(BlockBackend *blk, BlockInfo **p_info,
Error **errp)
diff --git a/include/block/qapi.h b/include/block/qapi.h
index c09859ea78..c7de4e3fa9 100644
--- a/include/block/qapi.h
+++ b/include/block/qapi.h
@@ -35,6 +35,9 @@ BlockDeviceInfo *bdrv_block_device_info(BlockBackend *blk,
int bdrv_query_snapshot_info_list(BlockDriverState *bs,
SnapshotInfoList **p_list,
Error **errp);
+void bdrv_query_block_node_info(BlockDriverState *bs,
+ BlockNodeInfo **p_info,
+ Error **errp);
void bdrv_query_image_info(BlockDriverState *bs,
ImageInfo **p_info,
Error **errp);
diff --git a/qapi/block-core.json b/qapi/block-core.json
index 4b9365167f..7720da0498 100644
--- a/qapi/block-core.json
+++ b/qapi/block-core.json
@@ -251,7 +251,7 @@
} }
##
-# @ImageInfo:
+# @BlockNodeInfo:
#
# Information about a QEMU image file
#
@@ -279,22 +279,34 @@
#
# @snapshots: list of VM snapshots
#
-# @backing-image: info of the backing image (since 1.6)
-#
# @format-specific: structure supplying additional format-specific
# information (since 1.7)
#
-# Since: 1.3
+# Since: 8.0
##
-{ 'struct': 'ImageInfo',
+{ 'struct': 'BlockNodeInfo',
'data': {'filename': 'str', 'format': 'str', '*dirty-flag': 'bool',
'*actual-size': 'int', 'virtual-size': 'int',
'*cluster-size': 'int', '*encrypted': 'bool', '*compressed': 'bool',
'*backing-filename': 'str', '*full-backing-filename': 'str',
'*backing-filename-format': 'str', '*snapshots': ['SnapshotInfo'],
- '*backing-image': 'ImageInfo',
'*format-specific': 'ImageInfoSpecific' } }
+##
+# @ImageInfo:
+#
+# Information about a QEMU image file, and potentially its backing image
+#
+# @backing-image: info of the backing image
+#
+# Since: 1.3
+##
+{ 'struct': 'ImageInfo',
+ 'base': 'BlockNodeInfo',
+ 'data': {
+ '*backing-image': 'ImageInfo'
+ } }
+
##
# @ImageCheck:
#
--
2.31.1

70
SOURCES/kvm-block-drop-bdrv_remove_filter_or_cow_child.patch Normal file
View File

@ -0,0 +1,70 @@
From defd6b325264d94ffb1355a8b19f9a77bd694a2f Mon Sep 17 00:00:00 2001
From: Vladimir Sementsov-Ogievskiy <vladimir.sementsov-ogievskiy@openvz.org>
Date: Mon, 7 Nov 2022 19:35:56 +0300
Subject: [PATCH 13/31] block: drop bdrv_remove_filter_or_cow_child
RH-Author: Stefano Garzarella <sgarzare@redhat.com>
RH-MergeRequest: 135: block: Simplify drain to prevent QEMU from crashing during snapshot
RH-Bugzilla: 2155112
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [1/16] 6339edd738c3b79f8ecb6c1e012e52b6afb1a622 (sgarzarella/qemu-kvm-c-9-s)
Drop this simple wrapper used only in one place. We have too many graph
modifying functions even without it.
Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@openvz.org>
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20221107163558.618889-3-vsementsov@yandex-team.ru>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit f38eaec4c3618dfc4a23e20435cefb5bf8325264)
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
block.c | 15 +--------------
1 file changed, 1 insertion(+), 14 deletions(-)
diff --git a/block.c b/block.c
index a18f052374..ec184150a2 100644
--- a/block.c
+++ b/block.c
@@ -93,8 +93,6 @@ static bool bdrv_recurse_has_child(BlockDriverState *bs,
static void bdrv_replace_child_noperm(BdrvChild *child,
BlockDriverState *new_bs);
static void bdrv_remove_child(BdrvChild *child, Transaction *tran);
-static void bdrv_remove_filter_or_cow_child(BlockDriverState *bs,
- Transaction *tran);
static int bdrv_reopen_prepare(BDRVReopenState *reopen_state,
BlockReopenQueue *queue,
@@ -5073,17 +5071,6 @@ static void bdrv_remove_child(BdrvChild *child, Transaction *tran)
tran_add(tran, &bdrv_remove_child_drv, child);
}
-/*
- * A function to remove backing-chain child of @bs if exists: cow child for
- * format nodes (always .backing) and filter child for filters (may be .file or
- * .backing)
- */
-static void bdrv_remove_filter_or_cow_child(BlockDriverState *bs,
- Transaction *tran)
-{
- bdrv_remove_child(bdrv_filter_or_cow_child(bs), tran);
-}
-
static int bdrv_replace_node_noperm(BlockDriverState *from,
BlockDriverState *to,
bool auto_skip, Transaction *tran,
@@ -5168,7 +5155,7 @@ static int bdrv_replace_node_common(BlockDriverState *from,
}
if (detach_subchain) {
- bdrv_remove_filter_or_cow_child(to_cow_parent, tran);
+ bdrv_remove_child(bdrv_filter_or_cow_child(to_cow_parent), tran);
}
found = g_hash_table_new(NULL, NULL);
--
2.31.1

145
SOURCES/kvm-block-file-Add-file-specific-image-info.patch Normal file
View File

@ -0,0 +1,145 @@
From 4af86458d6bea2a6e15fd57d4d4bbe88e35f7e72 Mon Sep 17 00:00:00 2001
From: Hanna Reitz <hreitz@redhat.com>
Date: Mon, 20 Jun 2022 18:26:54 +0200
Subject: [PATCH 07/20] block/file: Add file-specific image info
RH-Author: Hanna Czenczek <hreitz@redhat.com>
RH-MergeRequest: 145: Show protocol-level information in qemu-img info
RH-Bugzilla: 1860292
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Commit: [2/12] d8cc351d6c16c41b2000e41dc555f13093a9edce (hreitz/qemu-kvm-c-9-s)
Add some (optional) information that the file driver can provide for
image files, namely the extent size hint.
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220620162704.80987-3-hreitz@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 7f36a50ab4e7d39369cac67be4ba9d6ee4081dc0)
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
---
block/file-posix.c | 30 ++++++++++++++++++++++++++++++
qapi/block-core.json | 26 ++++++++++++++++++++++++--
2 files changed, 54 insertions(+), 2 deletions(-)
diff --git a/block/file-posix.c b/block/file-posix.c
index b9647c5ffc..df3da79aed 100644
--- a/block/file-posix.c
+++ b/block/file-posix.c
@@ -3095,6 +3095,34 @@ static int raw_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
return 0;
}
+static ImageInfoSpecific *raw_get_specific_info(BlockDriverState *bs,
+ Error **errp)
+{
+ ImageInfoSpecificFile *file_info = g_new0(ImageInfoSpecificFile, 1);
+ ImageInfoSpecific *spec_info = g_new(ImageInfoSpecific, 1);
+
+ *spec_info = (ImageInfoSpecific){
+ .type = IMAGE_INFO_SPECIFIC_KIND_FILE,
+ .u.file.data = file_info,
+ };
+
+#ifdef FS_IOC_FSGETXATTR
+ {
+ BDRVRawState *s = bs->opaque;
+ struct fsxattr attr;
+ int ret;
+
+ ret = ioctl(s->fd, FS_IOC_FSGETXATTR, &attr);
+ if (!ret && attr.fsx_extsize != 0) {
+ file_info->has_extent_size_hint = true;
+ file_info->extent_size_hint = attr.fsx_extsize;
+ }
+ }
+#endif
+
+ return spec_info;
+}
+
static BlockStatsSpecificFile get_blockstats_specific_file(BlockDriverState *bs)
{
BDRVRawState *s = bs->opaque;
@@ -3328,6 +3356,7 @@ BlockDriver bdrv_file = {
.bdrv_co_truncate = raw_co_truncate,
.bdrv_getlength = raw_getlength,
.bdrv_get_info = raw_get_info,
+ .bdrv_get_specific_info = raw_get_specific_info,
.bdrv_get_allocated_file_size
= raw_get_allocated_file_size,
.bdrv_get_specific_stats = raw_get_specific_stats,
@@ -3700,6 +3729,7 @@ static BlockDriver bdrv_host_device = {
.bdrv_co_truncate = raw_co_truncate,
.bdrv_getlength = raw_getlength,
.bdrv_get_info = raw_get_info,
+ .bdrv_get_specific_info = raw_get_specific_info,
.bdrv_get_allocated_file_size
= raw_get_allocated_file_size,
.bdrv_get_specific_stats = hdev_get_specific_stats,
diff --git a/qapi/block-core.json b/qapi/block-core.json
index 95ac4fa634..f5d822cbd6 100644
--- a/qapi/block-core.json
+++ b/qapi/block-core.json
@@ -139,16 +139,29 @@
'*encryption-format': 'RbdImageEncryptionFormat'
} }
+##
+# @ImageInfoSpecificFile:
+#
+# @extent-size-hint: Extent size hint (if available)
+#
+# Since: 8.0
+##
+{ 'struct': 'ImageInfoSpecificFile',
+ 'data': {
+ '*extent-size-hint': 'size'
+ } }
+
##
# @ImageInfoSpecificKind:
#
# @luks: Since 2.7
# @rbd: Since 6.1
+# @file: Since 8.0
#
# Since: 1.7
##
{ 'enum': 'ImageInfoSpecificKind',
- 'data': [ 'qcow2', 'vmdk', 'luks', 'rbd' ] }
+ 'data': [ 'qcow2', 'vmdk', 'luks', 'rbd', 'file' ] }
##
# @ImageInfoSpecificQCow2Wrapper:
@@ -185,6 +198,14 @@
{ 'struct': 'ImageInfoSpecificRbdWrapper',
'data': { 'data': 'ImageInfoSpecificRbd' } }
+##
+# @ImageInfoSpecificFileWrapper:
+#
+# Since: 8.0
+##
+{ 'struct': 'ImageInfoSpecificFileWrapper',
+ 'data': { 'data': 'ImageInfoSpecificFile' } }
+
##
# @ImageInfoSpecific:
#
@@ -199,7 +220,8 @@
'qcow2': 'ImageInfoSpecificQCow2Wrapper',
'vmdk': 'ImageInfoSpecificVmdkWrapper',
'luks': 'ImageInfoSpecificLUKSWrapper',
- 'rbd': 'ImageInfoSpecificRbdWrapper'
+ 'rbd': 'ImageInfoSpecificRbdWrapper',
+ 'file': 'ImageInfoSpecificFileWrapper'
} }
##
--
2.31.1

206
SOURCES/kvm-block-qapi-Add-indentation-to-bdrv_node_info_dump.patch Normal file
View File

@ -0,0 +1,206 @@
From c8c282c2e1d74cfc5de6527f7e20dfc3e76b67ac Mon Sep 17 00:00:00 2001
From: Hanna Reitz <hreitz@redhat.com>
Date: Mon, 20 Jun 2022 18:27:00 +0200
Subject: [PATCH 13/20] block/qapi: Add indentation to bdrv_node_info_dump()
RH-Author: Hanna Czenczek <hreitz@redhat.com>
RH-MergeRequest: 145: Show protocol-level information in qemu-img info
RH-Bugzilla: 1860292
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Commit: [8/12] d3a697e81ab9828457198075e5815a592363c725 (hreitz/qemu-kvm-c-9-s)
In order to let qemu-img info present a block graph, add a parameter to
bdrv_node_info_dump() and bdrv_image_info_specific_dump() so that the
information of nodes below the root level can be given an indentation.
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220620162704.80987-9-hreitz@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 76c9e9750d1bd580e8ed4465f6be3a986434e7c3)
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
---
block/monitor/block-hmp-cmds.c | 2 +-
block/qapi.c | 47 +++++++++++++++++++---------------
include/block/qapi.h | 5 ++--
qemu-img.c | 2 +-
qemu-io-cmds.c | 3 ++-
5 files changed, 34 insertions(+), 25 deletions(-)
diff --git a/block/monitor/block-hmp-cmds.c b/block/monitor/block-hmp-cmds.c
index aa37faa601..72824d4e2e 100644
--- a/block/monitor/block-hmp-cmds.c
+++ b/block/monitor/block-hmp-cmds.c
@@ -734,7 +734,7 @@ static void print_block_info(Monitor *mon, BlockInfo *info,
monitor_printf(mon, "\nImages:\n");
image_info = inserted->image;
while (1) {
- bdrv_node_info_dump(qapi_ImageInfo_base(image_info));
+ bdrv_node_info_dump(qapi_ImageInfo_base(image_info), 0);
if (image_info->has_backing_image) {
image_info = image_info->backing_image;
} else {
diff --git a/block/qapi.c b/block/qapi.c
index f208c21ccf..3e35603f0c 100644
--- a/block/qapi.c
+++ b/block/qapi.c
@@ -915,7 +915,8 @@ static bool qobject_is_empty_dump(const QObject *obj)
* prepending an optional prefix if the dump is not empty.
*/
void bdrv_image_info_specific_dump(ImageInfoSpecific *info_spec,
- const char *prefix)
+ const char *prefix,
+ int indentation)
{
QObject *obj, *data;
Visitor *v = qobject_output_visitor_new(&obj);
@@ -925,48 +926,51 @@ void bdrv_image_info_specific_dump(ImageInfoSpecific *info_spec,
data = qdict_get(qobject_to(QDict, obj), "data");
if (!qobject_is_empty_dump(data)) {
if (prefix) {
- qemu_printf("%s", prefix);
+ qemu_printf("%*s%s", indentation * 4, "", prefix);
}
- dump_qobject(1, data);
+ dump_qobject(indentation + 1, data);
}
qobject_unref(obj);
visit_free(v);
}
-void bdrv_node_info_dump(BlockNodeInfo *info)
+void bdrv_node_info_dump(BlockNodeInfo *info, int indentation)
{
char *size_buf, *dsize_buf;
+ g_autofree char *ind_s = g_strdup_printf("%*s", indentation * 4, "");
+
if (!info->has_actual_size) {
dsize_buf = g_strdup("unavailable");
} else {
dsize_buf = size_to_str(info->actual_size);
}
size_buf = size_to_str(info->virtual_size);
- qemu_printf("image: %s\n"
- "file format: %s\n"
- "virtual size: %s (%" PRId64 " bytes)\n"
- "disk size: %s\n",
- info->filename, info->format, size_buf,
- info->virtual_size,
- dsize_buf);
+ qemu_printf("%simage: %s\n"
+ "%sfile format: %s\n"
+ "%svirtual size: %s (%" PRId64 " bytes)\n"
+ "%sdisk size: %s\n",
+ ind_s, info->filename,
+ ind_s, info->format,
+ ind_s, size_buf, info->virtual_size,
+ ind_s, dsize_buf);
g_free(size_buf);
g_free(dsize_buf);
if (info->has_encrypted && info->encrypted) {
- qemu_printf("encrypted: yes\n");
+ qemu_printf("%sencrypted: yes\n", ind_s);
}
if (info->has_cluster_size) {
- qemu_printf("cluster_size: %" PRId64 "\n",
- info->cluster_size);
+ qemu_printf("%scluster_size: %" PRId64 "\n",
+ ind_s, info->cluster_size);
}
if (info->has_dirty_flag && info->dirty_flag) {
- qemu_printf("cleanly shut down: no\n");
+ qemu_printf("%scleanly shut down: no\n", ind_s);
}
if (info->has_backing_filename) {
- qemu_printf("backing file: %s", info->backing_filename);
+ qemu_printf("%sbacking file: %s", ind_s, info->backing_filename);
if (!info->has_full_backing_filename) {
qemu_printf(" (cannot determine actual path)");
} else if (strcmp(info->backing_filename,
@@ -975,15 +979,16 @@ void bdrv_node_info_dump(BlockNodeInfo *info)
}
qemu_printf("\n");
if (info->has_backing_filename_format) {
- qemu_printf("backing file format: %s\n",
- info->backing_filename_format);
+ qemu_printf("%sbacking file format: %s\n",
+ ind_s, info->backing_filename_format);
}
}
if (info->has_snapshots) {
SnapshotInfoList *elem;
- qemu_printf("Snapshot list:\n");
+ qemu_printf("%sSnapshot list:\n", ind_s);
+ qemu_printf("%s", ind_s);
bdrv_snapshot_dump(NULL);
qemu_printf("\n");
@@ -1003,6 +1008,7 @@ void bdrv_node_info_dump(BlockNodeInfo *info)
pstrcpy(sn.id_str, sizeof(sn.id_str), elem->value->id);
pstrcpy(sn.name, sizeof(sn.name), elem->value->name);
+ qemu_printf("%s", ind_s);
bdrv_snapshot_dump(&sn);
qemu_printf("\n");
}
@@ -1010,6 +1016,7 @@ void bdrv_node_info_dump(BlockNodeInfo *info)
if (info->has_format_specific) {
bdrv_image_info_specific_dump(info->format_specific,
- "Format specific information:\n");
+ "Format specific information:\n",
+ indentation);
}
}
diff --git a/include/block/qapi.h b/include/block/qapi.h
index 196436020e..38855f2ae9 100644
--- a/include/block/qapi.h
+++ b/include/block/qapi.h
@@ -49,6 +49,7 @@ void bdrv_query_block_graph_info(BlockDriverState *bs,
void bdrv_snapshot_dump(QEMUSnapshotInfo *sn);
void bdrv_image_info_specific_dump(ImageInfoSpecific *info_spec,
- const char *prefix);
-void bdrv_node_info_dump(BlockNodeInfo *info);
+ const char *prefix,
+ int indentation);
+void bdrv_node_info_dump(BlockNodeInfo *info, int indentation);
#endif
diff --git a/qemu-img.c b/qemu-img.c
index 3b2ca3bbcb..30b4ea58bb 100644
--- a/qemu-img.c
+++ b/qemu-img.c
@@ -2859,7 +2859,7 @@ static void dump_human_image_info_list(BlockNodeInfoList *list)
}
delim = true;
- bdrv_node_info_dump(elem->value);
+ bdrv_node_info_dump(elem->value, 0);
}
}
diff --git a/qemu-io-cmds.c b/qemu-io-cmds.c
index f4a374528e..fdcb89211b 100644
--- a/qemu-io-cmds.c
+++ b/qemu-io-cmds.c
@@ -1826,7 +1826,8 @@ static int info_f(BlockBackend *blk, int argc, char **argv)
}
if (spec_info) {
bdrv_image_info_specific_dump(spec_info,
- "Format specific information:\n");
+ "Format specific information:\n",
+ 0);
qapi_free_ImageInfoSpecific(spec_info);
}
--
2.31.1

155
SOURCES/kvm-block-qapi-Introduce-BlockGraphInfo.patch Normal file
View File

@ -0,0 +1,155 @@
From 0044e3848b02ef6edba5961d1f4b6297d137d207 Mon Sep 17 00:00:00 2001
From: Hanna Reitz <hreitz@redhat.com>
Date: Mon, 20 Jun 2022 18:26:59 +0200
Subject: [PATCH 12/20] block/qapi: Introduce BlockGraphInfo
RH-Author: Hanna Czenczek <hreitz@redhat.com>
RH-MergeRequest: 145: Show protocol-level information in qemu-img info
RH-Bugzilla: 1860292
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Commit: [7/12] de47bac372cd552b812c774a2f35f95923af74ff (hreitz/qemu-kvm-c-9-s)
Introduce a new QAPI type BlockGraphInfo and an associated
bdrv_query_block_graph_info() function that recursively gathers
BlockNodeInfo objects through a block graph.
A follow-up patch is going to make "qemu-img info" use this to print
information about all nodes that are (usually implicitly) opened for a
given image file.
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220620162704.80987-8-hreitz@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 6cab33997b91eb86e82a6a2ae58a24f835249d4a)
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
---
block/qapi.c | 48 ++++++++++++++++++++++++++++++++++++++++++++
include/block/qapi.h | 3 +++
qapi/block-core.json | 35 ++++++++++++++++++++++++++++++++
3 files changed, 86 insertions(+)
diff --git a/block/qapi.c b/block/qapi.c
index 5d0a8d2ce3..f208c21ccf 100644
--- a/block/qapi.c
+++ b/block/qapi.c
@@ -411,6 +411,54 @@ fail:
qapi_free_ImageInfo(info);
}
+/**
+ * bdrv_query_block_graph_info:
+ * @bs: root node to start from
+ * @p_info: location to store image information
+ * @errp: location to store error information
+ *
+ * Store image information about the graph starting from @bs in @p_info.
+ *
+ * @p_info will be set only on success. On error, store error in @errp.
+ */
+void bdrv_query_block_graph_info(BlockDriverState *bs,
+ BlockGraphInfo **p_info,
+ Error **errp)
+{
+ BlockGraphInfo *info;
+ BlockChildInfoList **children_list_tail;
+ BdrvChild *c;
+ ERRP_GUARD();
+
+ info = g_new0(BlockGraphInfo, 1);
+ bdrv_do_query_node_info(bs, qapi_BlockGraphInfo_base(info), errp);
+ if (*errp) {
+ goto fail;
+ }
+
+ children_list_tail = &info->children;
+
+ QLIST_FOREACH(c, &bs->children, next) {
+ BlockChildInfo *c_info;
+
+ c_info = g_new0(BlockChildInfo, 1);
+ QAPI_LIST_APPEND(children_list_tail, c_info);
+
+ c_info->name = g_strdup(c->name);
+ bdrv_query_block_graph_info(c->bs, &c_info->info, errp);
+ if (*errp) {
+ goto fail;
+ }
+ }
+
+ *p_info = info;
+ return;
+
+fail:
+ assert(*errp != NULL);
+ qapi_free_BlockGraphInfo(info);
+}
+
/* @p_info will be set only on success. */
static void bdrv_query_info(BlockBackend *blk, BlockInfo **p_info,
Error **errp)
diff --git a/include/block/qapi.h b/include/block/qapi.h
index 2174bf8fa2..196436020e 100644
--- a/include/block/qapi.h
+++ b/include/block/qapi.h
@@ -43,6 +43,9 @@ void bdrv_query_image_info(BlockDriverState *bs,
bool flat,
bool skip_implicit_filters,
Error **errp);
+void bdrv_query_block_graph_info(BlockDriverState *bs,
+ BlockGraphInfo **p_info,
+ Error **errp);
void bdrv_snapshot_dump(QEMUSnapshotInfo *sn);
void bdrv_image_info_specific_dump(ImageInfoSpecific *info_spec,
diff --git a/qapi/block-core.json b/qapi/block-core.json
index 4cf2deeb6c..d703e0fb16 100644
--- a/qapi/block-core.json
+++ b/qapi/block-core.json
@@ -307,6 +307,41 @@
'*backing-image': 'ImageInfo'
} }
+##
+# @BlockChildInfo:
+#
+# Information about all nodes in the block graph starting at some node,
+# annotated with information about that node in relation to its parent.
+#
+# @name: Child name of the root node in the BlockGraphInfo struct, in its role
+# as the child of some undescribed parent node
+#
+# @info: Block graph information starting at this node
+#
+# Since: 8.0
+##
+{ 'struct': 'BlockChildInfo',
+ 'data': {
+ 'name': 'str',
+ 'info': 'BlockGraphInfo'
+ } }
+
+##
+# @BlockGraphInfo:
+#
+# Information about all nodes in a block (sub)graph in the form of BlockNodeInfo
+# data.
+# The base BlockNodeInfo struct contains the information for the (sub)graph's
+# root node.
+#
+# @children: Array of links to this node's child nodes' information
+#
+# Since: 8.0
+##
+{ 'struct': 'BlockGraphInfo',
+ 'base': 'BlockNodeInfo',
+ 'data': { 'children': ['BlockChildInfo'] } }
+
##
# @ImageCheck:
#
--
2.31.1

197
SOURCES/kvm-block-qapi-Let-bdrv_query_image_info-recurse.patch Normal file
View File

@ -0,0 +1,197 @@
From ae2c3df00d673d436fe4d8ec9103a3b76d7e6233 Mon Sep 17 00:00:00 2001
From: Hanna Reitz <hreitz@redhat.com>
Date: Mon, 20 Jun 2022 18:26:58 +0200
Subject: [PATCH 11/20] block/qapi: Let bdrv_query_image_info() recurse
RH-Author: Hanna Czenczek <hreitz@redhat.com>
RH-MergeRequest: 145: Show protocol-level information in qemu-img info
RH-Bugzilla: 1860292
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Commit: [6/12] 451a83fd682cd6dd6026c22974d18c2f12ee06e3 (hreitz/qemu-kvm-c-9-s)
There is no real reason why bdrv_query_image_info() should generally not
recurse. The ImageInfo struct has a pointer to the backing image, so it
should generally be filled, unless the caller explicitly opts out.
This moves the recursing code from bdrv_block_device_info() into
bdrv_query_image_info().
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220620162704.80987-7-hreitz@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 5d8813593f3f673fc96eed199beb35690cc46f58)
Conflicts:
block/qapi.c: Conflicts with
54fde4ff0621c22b15cbaaa3c74301cc0dbd1c9e ("qapi block: Elide
redundant has_FOO in generated C"), which dropped
`has_backing_image`. Without that commit (and 44ea9d9be before it),
we still need to set `has_backing_image` in
`bdrv_query_image_info()`.
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
---
block/qapi.c | 94 +++++++++++++++++++++++++++-----------------
include/block/qapi.h | 2 +
2 files changed, 59 insertions(+), 37 deletions(-)
diff --git a/block/qapi.c b/block/qapi.c
index ad88bf9b38..5d0a8d2ce3 100644
--- a/block/qapi.c
+++ b/block/qapi.c
@@ -47,8 +47,10 @@ BlockDeviceInfo *bdrv_block_device_info(BlockBackend *blk,
Error **errp)
{
ImageInfo **p_image_info;
+ ImageInfo *backing_info;
BlockDriverState *bs0, *backing;
BlockDeviceInfo *info;
+ ERRP_GUARD();
if (!bs->drv) {
error_setg(errp, "Block device %s is ejected", bs->node_name);
@@ -149,38 +151,21 @@ BlockDeviceInfo *bdrv_block_device_info(BlockBackend *blk,
bs0 = bs;
p_image_info = &info->image;
info->backing_file_depth = 0;
- while (1) {
- Error *local_err = NULL;
- bdrv_query_image_info(bs0, p_image_info, &local_err);
- if (local_err) {
- error_propagate(errp, local_err);
- qapi_free_BlockDeviceInfo(info);
- return NULL;
- }
-
- /* stop gathering data for flat output */
- if (flat) {
- break;
- }
- if (bs0->drv && bdrv_filter_or_cow_child(bs0)) {
- /*
- * Put any filtered child here (for backwards compatibility to when
- * we put bs0->backing here, which might be any filtered child).
- */
- info->backing_file_depth++;
- bs0 = bdrv_filter_or_cow_bs(bs0);
- (*p_image_info)->has_backing_image = true;
- p_image_info = &((*p_image_info)->backing_image);
- } else {
- break;
- }
+ /*
+ * Skip automatically inserted nodes that the user isn't aware of for
+ * query-block (blk != NULL), but not for query-named-block-nodes
+ */
+ bdrv_query_image_info(bs0, p_image_info, flat, blk != NULL, errp);
+ if (*errp) {
+ qapi_free_BlockDeviceInfo(info);
+ return NULL;
+ }
- /* Skip automatically inserted nodes that the user isn't aware of for
- * query-block (blk != NULL), but not for query-named-block-nodes */
- if (blk) {
- bs0 = bdrv_skip_implicit_filters(bs0);
- }
+ backing_info = info->image->backing_image;
+ while (backing_info) {
+ info->backing_file_depth++;
+ backing_info = backing_info->backing_image;
}
return info;
@@ -363,19 +348,28 @@ void bdrv_query_block_node_info(BlockDriverState *bs,
* bdrv_query_image_info:
* @bs: block node to examine
* @p_info: location to store image information
+ * @flat: skip backing node information
+ * @skip_implicit_filters: skip implicit filters in the backing chain
* @errp: location to store error information
*
- * Store "flat" image information in @p_info.
+ * Store image information in @p_info, potentially recursively covering the
+ * backing chain.
*
- * "Flat" means it does *not* query backing image information,
- * i.e. (*pinfo)->has_backing_image will be set to false and
- * (*pinfo)->backing_image to NULL even when the image does in fact have
- * a backing image.
+ * If @flat is true, do not query backing image information, i.e.
+ * (*p_info)->has_backing_image will be set to false and
+ * (*p_info)->backing_image to NULL even when the image does in fact have a
+ * backing image.
+ *
+ * If @skip_implicit_filters is true, implicit filter nodes in the backing chain
+ * will be skipped when querying backing image information.
+ * (@skip_implicit_filters is ignored when @flat is true.)
*
* @p_info will be set only on success. On error, store error in @errp.
*/
void bdrv_query_image_info(BlockDriverState *bs,
ImageInfo **p_info,
+ bool flat,
+ bool skip_implicit_filters,
Error **errp)
{
ImageInfo *info;
@@ -384,11 +378,37 @@ void bdrv_query_image_info(BlockDriverState *bs,
info = g_new0(ImageInfo, 1);
bdrv_do_query_node_info(bs, qapi_ImageInfo_base(info), errp);
if (*errp) {
- qapi_free_ImageInfo(info);
- return;
+ goto fail;
+ }
+
+ if (!flat) {
+ BlockDriverState *backing;
+
+ /*
+ * Use any filtered child here (for backwards compatibility to when
+ * we always took bs->backing, which might be any filtered child).
+ */
+ backing = bdrv_filter_or_cow_bs(bs);
+ if (skip_implicit_filters) {
+ backing = bdrv_skip_implicit_filters(backing);
+ }
+
+ if (backing) {
+ bdrv_query_image_info(backing, &info->backing_image, false,
+ skip_implicit_filters, errp);
+ if (*errp) {
+ goto fail;
+ }
+ info->has_backing_image = true;
+ }
}
*p_info = info;
+ return;
+
+fail:
+ assert(*errp);
+ qapi_free_ImageInfo(info);
}
/* @p_info will be set only on success. */
diff --git a/include/block/qapi.h b/include/block/qapi.h
index 22198dcd0c..2174bf8fa2 100644
--- a/include/block/qapi.h
+++ b/include/block/qapi.h
@@ -40,6 +40,8 @@ void bdrv_query_block_node_info(BlockDriverState *bs,
Error **errp);
void bdrv_query_image_info(BlockDriverState *bs,
ImageInfo **p_info,
+ bool flat,
+ bool skip_implicit_filters,
Error **errp);
void bdrv_snapshot_dump(QEMUSnapshotInfo *sn);
--
2.31.1

99
SOURCES/kvm-block-temporarily-hold-the-new-AioContext-of-bs_top-.patch Normal file
View File

@ -0,0 +1,99 @@
From b952c8f1da6f8597736c0e040565830139369359 Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Tue, 14 Feb 2023 18:16:21 +0100
Subject: [PATCH] block: temporarily hold the new AioContext of bs_top in
bdrv_append()
RH-Author: Stefano Garzarella <sgarzare@redhat.com>
RH-MergeRequest: 153: block: temporarily hold the new AioContext of bs_top in bdrv_append()
RH-Bugzilla: 2168209
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [1/1] 5b190426d996e8c9f7a781bd97aee8d25756dbd3 (sgarzarella/qemu-kvm-c-9-s)
bdrv_append() is called with bs_top AioContext held, but
bdrv_attach_child_noperm() could change the AioContext of bs_top.
bdrv_replace_node_noperm() calls bdrv_drained_begin() starting from
commit 2398747128 ("block: Don't poll in bdrv_replace_child_noperm()").
bdrv_drained_begin() can call BDRV_POLL_WHILE that assumes the new lock
is taken, so let's temporarily hold the new AioContext to prevent QEMU
from failing in BDRV_POLL_WHILE when it tries to release the wrong
AioContext.
Buglink: https://bugzilla.redhat.com/show_bug.cgi?id=2168209
Reported-by: Aihua Liang <aliang@redhat.com>
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Message-Id: <20230214171621.11574-1-sgarzare@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 60d90bf43c169b9d1dbcb17ed794b7b02c6862b1)
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
block.c | 23 +++++++++++++++++++++++
1 file changed, 23 insertions(+)
diff --git a/block.c b/block.c
index 0d78711416..9e1dcb9e47 100644
--- a/block.c
+++ b/block.c
@@ -5275,6 +5275,8 @@ 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)
@@ -5282,11 +5284,14 @@ int bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top,
int ret;
BdrvChild *child;
Transaction *tran = tran_new();
+ AioContext *old_context, *new_context = NULL;
GLOBAL_STATE_CODE();
assert(!bs_new->backing);
+ old_context = bdrv_get_aio_context(bs_top);
+
child = bdrv_attach_child_noperm(bs_new, bs_top, "backing",
&child_of_bds, bdrv_backing_role(bs_new),
tran, errp);
@@ -5295,6 +5300,19 @@ int bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top,
goto out;
}
+ /*
+ * bdrv_attach_child_noperm could change the AioContext of bs_top.
+ * bdrv_replace_node_noperm calls bdrv_drained_begin, so let's temporarily
+ * hold the new AioContext, since bdrv_drained_begin calls BDRV_POLL_WHILE
+ * that assumes the new lock is taken.
+ */
+ new_context = bdrv_get_aio_context(bs_top);
+
+ if (old_context != new_context) {
+ aio_context_release(old_context);
+ aio_context_acquire(new_context);
+ }
+
ret = bdrv_replace_node_noperm(bs_top, bs_new, true, tran, errp);
if (ret < 0) {
goto out;
@@ -5306,6 +5324,11 @@ out:
bdrv_refresh_limits(bs_top, NULL, NULL);
+ if (new_context && old_context != new_context) {
+ aio_context_release(new_context);
+ aio_context_acquire(old_context);
+ }
+
return ret;
}
--
2.31.1

140
SOURCES/kvm-block-vmdk-Change-extent-info-type.patch Normal file
View File

@ -0,0 +1,140 @@
From d8caed018afb0f60f449e971398d2a8d6c2992e7 Mon Sep 17 00:00:00 2001
From: Hanna Reitz <hreitz@redhat.com>
Date: Mon, 20 Jun 2022 18:26:55 +0200
Subject: [PATCH 08/20] block/vmdk: Change extent info type
RH-Author: Hanna Czenczek <hreitz@redhat.com>
RH-MergeRequest: 145: Show protocol-level information in qemu-img info
RH-Bugzilla: 1860292
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Commit: [3/12] efe50a2797c679ce6bb5faa423047461a34e6792 (hreitz/qemu-kvm-c-9-s)
VMDK's implementation of .bdrv_get_specific_info() returns information
about its extent files, ostensibly in the form of ImageInfo objects.
However, it does not get this information through
bdrv_query_image_info(), but fills only a select few fields with custom
information that does not always match the fields' purposes.
For example, @format, which is supposed to be a block driver name, is
filled with the extent type, e.g. SPARSE or FLAT.
In ImageInfo, @compressed shows whether the data that can be seen in the
image is stored in compressed form or not. For example, a compressed
qcow2 image will store compressed data in its data file, but when
accessing the qcow2 node, you will see normal data. This is not how
VMDK uses the @compressed field for its extent files: Instead, it
signifies whether accessing the extent file will yield compressed data
(which the VMDK driver then (de-)compresses).
Create a new structure to represent the extent information. This allows
us to clarify the fields' meanings, and it clearly shows that these are
not complete ImageInfo objects. (That is, if a user wants an extent
file's ImageInfo object, they will need to query it separately, and will
not get it from ImageInfoSpecificVmdk.extents.)
Note that this removes the last use of ['ImageInfo'] (i.e. an array of
ImageInfo objects), so the QAPI generator will no longer generate
ImageInfoList by default. However, we use it in qemu-img.c, so we need
to create a dummy object to force the generate to create that type,
similarly to DummyForceArrays in machine.json (introduced in commit
9f08c8ec73878122ad4b061ed334f0437afaaa32 ("qapi: Lazy creation of array
types")).
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220620162704.80987-4-hreitz@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 456e75171a85c19a5bfa202eefcbdc4ef1692f05)
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
---
block/vmdk.c | 8 ++++----
qapi/block-core.json | 38 +++++++++++++++++++++++++++++++++++++-
2 files changed, 41 insertions(+), 5 deletions(-)
diff --git a/block/vmdk.c b/block/vmdk.c
index 26376352b9..4435b9880b 100644
--- a/block/vmdk.c
+++ b/block/vmdk.c
@@ -2901,12 +2901,12 @@ static int vmdk_has_zero_init(BlockDriverState *bs)
return 1;
}
-static ImageInfo *vmdk_get_extent_info(VmdkExtent *extent)
+static VmdkExtentInfo *vmdk_get_extent_info(VmdkExtent *extent)
{
- ImageInfo *info = g_new0(ImageInfo, 1);
+ VmdkExtentInfo *info = g_new0(VmdkExtentInfo, 1);
bdrv_refresh_filename(extent->file->bs);
- *info = (ImageInfo){
+ *info = (VmdkExtentInfo){
.filename = g_strdup(extent->file->bs->filename),
.format = g_strdup(extent->type),
.virtual_size = extent->sectors * BDRV_SECTOR_SIZE,
@@ -2985,7 +2985,7 @@ static ImageInfoSpecific *vmdk_get_specific_info(BlockDriverState *bs,
int i;
BDRVVmdkState *s = bs->opaque;
ImageInfoSpecific *spec_info = g_new0(ImageInfoSpecific, 1);
- ImageInfoList **tail;
+ VmdkExtentInfoList **tail;
*spec_info = (ImageInfoSpecific){
.type = IMAGE_INFO_SPECIFIC_KIND_VMDK,
diff --git a/qapi/block-core.json b/qapi/block-core.json
index f5d822cbd6..4b9365167f 100644
--- a/qapi/block-core.json
+++ b/qapi/block-core.json
@@ -124,7 +124,33 @@
'create-type': 'str',
'cid': 'int',
'parent-cid': 'int',
- 'extents': ['ImageInfo']
+ 'extents': ['VmdkExtentInfo']
+ } }
+
+##
+# @VmdkExtentInfo:
+#
+# Information about a VMDK extent file
+#
+# @filename: Name of the extent file
+#
+# @format: Extent type (e.g. FLAT or SPARSE)
+#
+# @virtual-size: Number of bytes covered by this extent
+#
+# @cluster-size: Cluster size in bytes (for non-flat extents)
+#
+# @compressed: Whether this extent contains compressed data
+#
+# Since: 8.0
+##
+{ 'struct': 'VmdkExtentInfo',
+ 'data': {
+ 'filename': 'str',
+ 'format': 'str',
+ 'virtual-size': 'int',
+ '*cluster-size': 'int',
+ '*compressed': 'bool'
} }
##
@@ -5754,3 +5780,13 @@
'data': { 'device': 'str', '*id': 'str', '*name': 'str'},
'returns': 'SnapshotInfo',
'allow-preconfig': true }
+
+##
+# @DummyBlockCoreForceArrays:
+#
+# Not used by QMP; hack to let us use ImageInfoList internally
+#
+# Since: 8.0
+##
+{ 'struct': 'DummyBlockCoreForceArrays',
+ 'data': { 'unused-image-info': ['ImageInfo'] } }
--
2.31.1

41
SOURCES/kvm-configs-devices-aarch64-softmmu-Enable-CONFIG_VIRTIO.patch
View File

@ -1,41 +0,0 @@
From 3a0e9bb88e82cc76ca5efc0595ce94b5dc34749e Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Mon, 25 Apr 2022 13:42:46 +0800
Subject: [PATCH 1/2] configs/devices/aarch64-softmmu: Enable CONFIG_VIRTIO_MEM
RH-Author: Gavin Shan <gshan@redhat.com>
RH-MergeRequest: 80: Enable virtio-mem for aarch64
RH-Commit: [1/1] 1afbd08da6d7c860da8d617a0a932d3660514878 (gwshan/qemu-rhel-9)
RH-Bugzilla: 2044162
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2044162
This enables virtio-mem device on aarch64 since all needed commits
are ready.
b1b87327a9 hw/arm/virt: Support for virtio-mem-pci
1263615efe virtio-mem: Correct default THP size for ARM64
Signed-off-by: Gavin Shan <gshan@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 5f6ee1de5b..187938573f 100644
--- a/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak
+++ b/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak
@@ -22,6 +22,7 @@ CONFIG_VFIO=y
CONFIG_VFIO_PCI=y
CONFIG_VIRTIO_MMIO=y
CONFIG_VIRTIO_PCI=y
+CONFIG_VIRTIO_MEM=y
CONFIG_XIO3130=y
CONFIG_NVDIMM=y
CONFIG_ACPI_APEI=y
--
2.35.1

101
SOURCES/kvm-coroutine-Rename-qemu_coroutine_inc-dec_pool_size.patch
View File

@ -1,101 +0,0 @@
From e3cb8849862a9f0dd20f2913d540336a037d43c7 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Tue, 10 May 2022 17:10:19 +0200
Subject: [PATCH 07/16] coroutine: Rename qemu_coroutine_inc/dec_pool_size()
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 87: coroutine: Fix crashes due to too large pool batch size
RH-Commit: [1/2] 6389b11f70225f221784c270d9b90c1ea43ca8fb (kmwolf/centos-qemu-kvm)
RH-Bugzilla: 2079938
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
It's true that these functions currently affect the batch size in which
coroutines are reused (i.e. moved from the global release pool to the
allocation pool of a specific thread), but this is a bug and will be
fixed in a separate patch.
In fact, the comment in the header file already just promises that it
influences the pool size, so reflect this in the name of the functions.
As a nice side effect, the shorter function name makes some line
wrapping unnecessary.
Cc: qemu-stable@nongnu.org
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20220510151020.105528-2-kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 98e3ab35054b946f7c2aba5408822532b0920b53)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
hw/block/virtio-blk.c | 6 ++----
include/qemu/coroutine.h | 6 +++---
util/qemu-coroutine.c | 4 ++--
3 files changed, 7 insertions(+), 9 deletions(-)
diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c
index 540c38f829..6a1cc41877 100644
--- a/hw/block/virtio-blk.c
+++ b/hw/block/virtio-blk.c
@@ -1215,8 +1215,7 @@ static void virtio_blk_device_realize(DeviceState *dev, Error **errp)
for (i = 0; i < conf->num_queues; i++) {
virtio_add_queue(vdev, conf->queue_size, virtio_blk_handle_output);
}
- qemu_coroutine_increase_pool_batch_size(conf->num_queues * conf->queue_size
- / 2);
+ qemu_coroutine_inc_pool_size(conf->num_queues * conf->queue_size / 2);
virtio_blk_data_plane_create(vdev, conf, &s->dataplane, &err);
if (err != NULL) {
error_propagate(errp, err);
@@ -1253,8 +1252,7 @@ static void virtio_blk_device_unrealize(DeviceState *dev)
for (i = 0; i < conf->num_queues; i++) {
virtio_del_queue(vdev, i);
}
- qemu_coroutine_decrease_pool_batch_size(conf->num_queues * conf->queue_size
- / 2);
+ qemu_coroutine_dec_pool_size(conf->num_queues * conf->queue_size / 2);
qemu_del_vm_change_state_handler(s->change);
blockdev_mark_auto_del(s->blk);
virtio_cleanup(vdev);
diff --git a/include/qemu/coroutine.h b/include/qemu/coroutine.h
index c828a95ee0..5b621d1295 100644
--- a/include/qemu/coroutine.h
+++ b/include/qemu/coroutine.h
@@ -334,12 +334,12 @@ void coroutine_fn yield_until_fd_readable(int fd);
/**
* Increase coroutine pool size
*/
-void qemu_coroutine_increase_pool_batch_size(unsigned int additional_pool_size);
+void qemu_coroutine_inc_pool_size(unsigned int additional_pool_size);
/**
- * Devcrease coroutine pool size
+ * Decrease coroutine pool size
*/
-void qemu_coroutine_decrease_pool_batch_size(unsigned int additional_pool_size);
+void qemu_coroutine_dec_pool_size(unsigned int additional_pool_size);
#include "qemu/lockable.h"
diff --git a/util/qemu-coroutine.c b/util/qemu-coroutine.c
index c03b2422ff..faca0ca97c 100644
--- a/util/qemu-coroutine.c
+++ b/util/qemu-coroutine.c
@@ -205,12 +205,12 @@ AioContext *coroutine_fn qemu_coroutine_get_aio_context(Coroutine *co)
return co->ctx;
}
-void qemu_coroutine_increase_pool_batch_size(unsigned int additional_pool_size)
+void qemu_coroutine_inc_pool_size(unsigned int additional_pool_size)
{
qatomic_add(&pool_batch_size, additional_pool_size);
}
-void qemu_coroutine_decrease_pool_batch_size(unsigned int removing_pool_size)
+void qemu_coroutine_dec_pool_size(unsigned int removing_pool_size)
{
qatomic_sub(&pool_batch_size, removing_pool_size);
}
--
2.31.1

138
SOURCES/kvm-coroutine-Revert-to-constant-batch-size.patch
View File

@ -1,138 +0,0 @@
From 345107bfd5537b51f34aaeb97d6161858bb6feee Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Tue, 10 May 2022 17:10:20 +0200
Subject: [PATCH 08/16] coroutine: Revert to constant batch size
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 87: coroutine: Fix crashes due to too large pool batch size
RH-Commit: [2/2] 8a8a39af873854cdc8333d1a70f3479a97c3ec7a (kmwolf/centos-qemu-kvm)
RH-Bugzilla: 2079938
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
Commit 4c41c69e changed the way the coroutine pool is sized because for
virtio-blk devices with a large queue size and heavy I/O, it was just
too small and caused coroutines to be deleted and reallocated soon
afterwards. The change made the size dynamic based on the number of
queues and the queue size of virtio-blk devices.
There are two important numbers here: Slightly simplified, when a
coroutine terminates, it is generally stored in the global release pool
up to a certain pool size, and if the pool is full, it is freed.
Conversely, when allocating a new coroutine, the coroutines in the
release pool are reused if the pool already has reached a certain
minimum size (the batch size), otherwise we allocate new coroutines.
The problem after commit 4c41c69e is that it not only increases the
maximum pool size (which is the intended effect), but also the batch
size for reusing coroutines (which is a bug). It means that in cases
with many devices and/or a large queue size (which defaults to the
number of vcpus for virtio-blk-pci), many thousand coroutines could be
sitting in the release pool without being reused.
This is not only a waste of memory and allocations, but it actually
makes the QEMU process likely to hit the vm.max_map_count limit on Linux
because each coroutine requires two mappings (its stack and the guard
page for the stack), causing it to abort() in qemu_alloc_stack() because
when the limit is hit, mprotect() starts to fail with ENOMEM.
In order to fix the problem, change the batch size back to 64 to avoid
uselessly accumulating coroutines in the release pool, but keep the
dynamic maximum pool size so that coroutines aren't freed too early
in heavy I/O scenarios.
Note that this fix doesn't strictly make it impossible to hit the limit,
but this would only happen if most of the coroutines are actually in use
at the same time, not just sitting in a pool. This is the same behaviour
as we already had before commit 4c41c69e. Fully preventing this would
require allowing qemu_coroutine_create() to return an error, but it
doesn't seem to be a scenario that people hit in practice.
Cc: qemu-stable@nongnu.org
Resolves: https://bugzilla.redhat.com/show_bug.cgi?id=2079938
Fixes: 4c41c69e05fe28c0f95f8abd2ebf407e95a4f04b
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20220510151020.105528-3-kwolf@redhat.com>
Tested-by: Hiroki Narukawa <hnarukaw@yahoo-corp.jp>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 9ec7a59b5aad4b736871c378d30f5ef5ec51cb52)
Conflicts:
util/qemu-coroutine.c
Trivial merge conflict because we don't have commit ac387a08 downstream.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
util/qemu-coroutine.c | 22 ++++++++++++++--------
1 file changed, 14 insertions(+), 8 deletions(-)
diff --git a/util/qemu-coroutine.c b/util/qemu-coroutine.c
index faca0ca97c..804f672e0a 100644
--- a/util/qemu-coroutine.c
+++ b/util/qemu-coroutine.c
@@ -20,14 +20,20 @@
#include "qemu/coroutine_int.h"
#include "block/aio.h"
-/** Initial batch size is 64, and is increased on demand */
+/**
+ * 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_INITIAL_BATCH_SIZE = 64,
+ POOL_MIN_BATCH_SIZE = 64,
+ POOL_INITIAL_MAX_SIZE = 64,
};
/** Free list to speed up creation */
static QSLIST_HEAD(, Coroutine) release_pool = QSLIST_HEAD_INITIALIZER(pool);
-static unsigned int pool_batch_size = POOL_INITIAL_BATCH_SIZE;
+static unsigned int pool_max_size = POOL_INITIAL_MAX_SIZE;
static unsigned int release_pool_size;
static __thread QSLIST_HEAD(, Coroutine) alloc_pool = QSLIST_HEAD_INITIALIZER(pool);
static __thread unsigned int alloc_pool_size;
@@ -51,7 +57,7 @@ Coroutine *qemu_coroutine_create(CoroutineEntry *entry, void *opaque)
if (CONFIG_COROUTINE_POOL) {
co = QSLIST_FIRST(&alloc_pool);
if (!co) {
- if (release_pool_size > qatomic_read(&pool_batch_size)) {
+ if (release_pool_size > POOL_MIN_BATCH_SIZE) {
/* Slow path; a good place to register the destructor, too. */
if (!coroutine_pool_cleanup_notifier.notify) {
coroutine_pool_cleanup_notifier.notify = coroutine_pool_cleanup;
@@ -88,12 +94,12 @@ static void coroutine_delete(Coroutine *co)
co->caller = NULL;
if (CONFIG_COROUTINE_POOL) {
- if (release_pool_size < qatomic_read(&pool_batch_size) * 2) {
+ 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 (alloc_pool_size < qatomic_read(&pool_batch_size)) {
+ if (alloc_pool_size < qatomic_read(&pool_max_size)) {
QSLIST_INSERT_HEAD(&alloc_pool, co, pool_next);
alloc_pool_size++;
return;
@@ -207,10 +213,10 @@ AioContext *coroutine_fn qemu_coroutine_get_aio_context(Coroutine *co)
void qemu_coroutine_inc_pool_size(unsigned int additional_pool_size)
{
- qatomic_add(&pool_batch_size, additional_pool_size);
+ qatomic_add(&pool_max_size, additional_pool_size);
}
void qemu_coroutine_dec_pool_size(unsigned int removing_pool_size)
{
- qatomic_sub(&pool_batch_size, removing_pool_size);
+ qatomic_sub(&pool_max_size, removing_pool_size);
}
--
2.31.1

132
SOURCES/kvm-coroutine-ucontext-use-QEMU_DEFINE_STATIC_CO_TLS.patch
View File

@ -1,132 +0,0 @@
From ffbd90e5f4eba620c7cd631b04f0ed31beb22ffa Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Tue, 17 May 2022 12:07:56 +0100
Subject: [PATCH 1/6] coroutine-ucontext: use QEMU_DEFINE_STATIC_CO_TLS()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Stefan Hajnoczi <stefanha@redhat.com>
RH-MergeRequest: 89: coroutine: use coroutine TLS macros to protect thread-local variables
RH-Commit: [1/3] a9782fe8e919c4bd317b7e8744c7ff57d898add3 (stefanha/centos-stream-qemu-kvm)
RH-Bugzilla: 1952483
RH-Acked-by: Hanna Reitz <hreitz@redhat.com>
RH-Acked-by: Eric Blake <eblake@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
Thread-Local Storage variables cannot be used directly from coroutine
code because the compiler may optimize TLS variable accesses across
qemu_coroutine_yield() calls. When the coroutine is re-entered from
another thread the TLS variables from the old thread must no longer be
used.
Use QEMU_DEFINE_STATIC_CO_TLS() for the current and leader variables.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-Id: <20220307153853.602859-2-stefanha@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 34145a307d849d0b6734d0222a7aa0bb9eef7407)
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
util/coroutine-ucontext.c | 38 ++++++++++++++++++++++++--------------
1 file changed, 24 insertions(+), 14 deletions(-)
diff --git a/util/coroutine-ucontext.c b/util/coroutine-ucontext.c
index 904b375192..127d5a13c8 100644
--- a/util/coroutine-ucontext.c
+++ b/util/coroutine-ucontext.c
@@ -25,6 +25,7 @@
#include "qemu/osdep.h"
#include <ucontext.h>
#include "qemu/coroutine_int.h"
+#include "qemu/coroutine-tls.h"
#ifdef CONFIG_VALGRIND_H
#include <valgrind/valgrind.h>
@@ -66,8 +67,8 @@ typedef struct {
/**
* Per-thread coroutine bookkeeping
*/
-static __thread CoroutineUContext leader;
-static __thread Coroutine *current;
+QEMU_DEFINE_STATIC_CO_TLS(Coroutine *, current);
+QEMU_DEFINE_STATIC_CO_TLS(CoroutineUContext, leader);
/*
* va_args to makecontext() must be type 'int', so passing
@@ -97,14 +98,15 @@ static inline __attribute__((always_inline))
void finish_switch_fiber(void *fake_stack_save)
{
#ifdef CONFIG_ASAN
+ CoroutineUContext *leaderp = get_ptr_leader();
const void *bottom_old;
size_t size_old;
__sanitizer_finish_switch_fiber(fake_stack_save, &bottom_old, &size_old);
- if (!leader.stack) {
- leader.stack = (void *)bottom_old;
- leader.stack_size = size_old;
+ if (!leaderp->stack) {
+ leaderp->stack = (void *)bottom_old;
+ leaderp->stack_size = size_old;
}
#endif
#ifdef CONFIG_TSAN
@@ -161,8 +163,10 @@ static void coroutine_trampoline(int i0, int i1)
/* Initialize longjmp environment and switch back the caller */
if (!sigsetjmp(self->env, 0)) {
- start_switch_fiber_asan(COROUTINE_YIELD, &fake_stack_save, leader.stack,
- leader.stack_size);
+ CoroutineUContext *leaderp = get_ptr_leader();
+
+ start_switch_fiber_asan(COROUTINE_YIELD, &fake_stack_save,
+ leaderp->stack, leaderp->stack_size);
start_switch_fiber_tsan(&fake_stack_save, self, true); /* true=caller */
siglongjmp(*(sigjmp_buf *)co->entry_arg, 1);
}
@@ -297,7 +301,7 @@ qemu_coroutine_switch(Coroutine *from_, Coroutine *to_,
int ret;
void *fake_stack_save = NULL;
- current = to_;
+ set_current(to_);
ret = sigsetjmp(from->env, 0);
if (ret == 0) {
@@ -315,18 +319,24 @@ qemu_coroutine_switch(Coroutine *from_, Coroutine *to_,
Coroutine *qemu_coroutine_self(void)
{
- if (!current) {
- current = &leader.base;
+ Coroutine *self = get_current();
+ CoroutineUContext *leaderp = get_ptr_leader();
+
+ if (!self) {
+ self = &leaderp->base;
+ set_current(self);
}
#ifdef CONFIG_TSAN
- if (!leader.tsan_co_fiber) {
- leader.tsan_co_fiber = __tsan_get_current_fiber();
+ if (!leaderp->tsan_co_fiber) {
+ leaderp->tsan_co_fiber = __tsan_get_current_fiber();
}
#endif
- return current;
+ return self;
}
bool qemu_in_coroutine(void)
{
- return current && current->caller;
+ Coroutine *self = get_current();
+
+ return self && self->caller;
}
--
2.31.1

139
SOURCES/kvm-coroutine-use-QEMU_DEFINE_STATIC_CO_TLS.patch
View File

@ -1,139 +0,0 @@
From 9c2e55d25fec6ffb21e344513b7dbeed7e21f641 Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Tue, 17 May 2022 12:08:04 +0100
Subject: [PATCH 2/6] coroutine: use QEMU_DEFINE_STATIC_CO_TLS()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Stefan Hajnoczi <stefanha@redhat.com>
RH-MergeRequest: 89: coroutine: use coroutine TLS macros to protect thread-local variables
RH-Commit: [2/3] 68a8847e406e2eace6ddc31b0c5676a60600d606 (stefanha/centos-stream-qemu-kvm)
RH-Bugzilla: 1952483
RH-Acked-by: Hanna Reitz <hreitz@redhat.com>
RH-Acked-by: Eric Blake <eblake@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
Thread-Local Storage variables cannot be used directly from coroutine
code because the compiler may optimize TLS variable accesses across
qemu_coroutine_yield() calls. When the coroutine is re-entered from
another thread the TLS variables from the old thread must no longer be
used.
Use QEMU_DEFINE_STATIC_CO_TLS() for the current and leader variables.
The alloc_pool QSLIST needs a typedef so the return value of
get_ptr_alloc_pool() can be stored in a local variable.
One example of why this code is necessary: a coroutine that yields
before calling qemu_coroutine_create() to create another coroutine is
affected by the TLS issue.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-Id: <20220307153853.602859-3-stefanha@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit ac387a08a9c9f6b36757da912f0339c25f421f90)
Conflicts:
- Context conflicts due to commit 5411171c3ef4 ("coroutine: Revert to
constant batch size").
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
util/qemu-coroutine.c | 41 ++++++++++++++++++++++++-----------------
1 file changed, 24 insertions(+), 17 deletions(-)
diff --git a/util/qemu-coroutine.c b/util/qemu-coroutine.c
index 804f672e0a..4a8bd63ef0 100644
--- a/util/qemu-coroutine.c
+++ b/util/qemu-coroutine.c
@@ -18,6 +18,7 @@
#include "qemu/atomic.h"
#include "qemu/coroutine.h"
#include "qemu/coroutine_int.h"
+#include "qemu/coroutine-tls.h"
#include "block/aio.h"
/**
@@ -35,17 +36,20 @@ enum {
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;
-static __thread QSLIST_HEAD(, Coroutine) alloc_pool = QSLIST_HEAD_INITIALIZER(pool);
-static __thread unsigned int alloc_pool_size;
-static __thread Notifier coroutine_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 void coroutine_pool_cleanup(Notifier *n, void *value)
{
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, alloc_pool, pool_next, tmp) {
+ QSLIST_REMOVE_HEAD(alloc_pool, pool_next);
qemu_coroutine_delete(co);
}
}
@@ -55,27 +59,30 @@ Coroutine *qemu_coroutine_create(CoroutineEntry *entry, void *opaque)
Coroutine *co = NULL;
if (CONFIG_COROUTINE_POOL) {
- co = QSLIST_FIRST(&alloc_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. */
- if (!coroutine_pool_cleanup_notifier.notify) {
- coroutine_pool_cleanup_notifier.notify = coroutine_pool_cleanup;
- qemu_thread_atexit_add(&coroutine_pool_cleanup_notifier);
+ 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.
*/
- alloc_pool_size = qatomic_xchg(&release_pool_size, 0);
- QSLIST_MOVE_ATOMIC(&alloc_pool, &release_pool);
- co = QSLIST_FIRST(&alloc_pool);
+ 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);
- alloc_pool_size--;
+ QSLIST_REMOVE_HEAD(alloc_pool, pool_next);
+ set_alloc_pool_size(get_alloc_pool_size() - 1);
}
}
@@ -99,9 +106,9 @@ static void coroutine_delete(Coroutine *co)
qatomic_inc(&release_pool_size);
return;
}
- if (alloc_pool_size < qatomic_read(&pool_max_size)) {
- QSLIST_INSERT_HEAD(&alloc_pool, co, pool_next);
- alloc_pool_size++;
+ 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;
}
}
--
2.31.1

99
SOURCES/kvm-coroutine-win32-use-QEMU_DEFINE_STATIC_CO_TLS.patch
View File

@ -1,99 +0,0 @@
From 336581e6e9ace3f1ddd24ad0a258db9785f9b0ed Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Tue, 17 May 2022 12:08:12 +0100
Subject: [PATCH 3/6] coroutine-win32: use QEMU_DEFINE_STATIC_CO_TLS()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Stefan Hajnoczi <stefanha@redhat.com>
RH-MergeRequest: 89: coroutine: use coroutine TLS macros to protect thread-local variables
RH-Commit: [3/3] 55b35dfdae1bc7d6f614ac9f81a92f5c6431f713 (stefanha/centos-stream-qemu-kvm)
RH-Bugzilla: 1952483
RH-Acked-by: Hanna Reitz <hreitz@redhat.com>
RH-Acked-by: Eric Blake <eblake@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
Thread-Local Storage variables cannot be used directly from coroutine
code because the compiler may optimize TLS variable accesses across
qemu_coroutine_yield() calls. When the coroutine is re-entered from
another thread the TLS variables from the old thread must no longer be
used.
Use QEMU_DEFINE_STATIC_CO_TLS() for the current and leader variables.
I think coroutine-win32.c could get away with __thread because the
variables are only used in situations where either the stale value is
correct (current) or outside coroutine context (loading leader when
current is NULL). Due to the difficulty of being sure that this is
really safe in all scenarios it seems worth converting it anyway.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-Id: <20220307153853.602859-4-stefanha@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit c1fe694357a328c807ae3cc6961c19e923448fcc)
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
util/coroutine-win32.c | 18 +++++++++++++-----
1 file changed, 13 insertions(+), 5 deletions(-)
diff --git a/util/coroutine-win32.c b/util/coroutine-win32.c
index de6bd4fd3e..c02a62c896 100644
--- a/util/coroutine-win32.c
+++ b/util/coroutine-win32.c
@@ -25,6 +25,7 @@
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "qemu/coroutine_int.h"
+#include "qemu/coroutine-tls.h"
typedef struct
{
@@ -34,8 +35,8 @@ typedef struct
CoroutineAction action;
} CoroutineWin32;
-static __thread CoroutineWin32 leader;
-static __thread Coroutine *current;
+QEMU_DEFINE_STATIC_CO_TLS(CoroutineWin32, leader);
+QEMU_DEFINE_STATIC_CO_TLS(Coroutine *, current);
/* This function is marked noinline to prevent GCC from inlining it
* into coroutine_trampoline(). If we allow it to do that then it
@@ -52,7 +53,7 @@ qemu_coroutine_switch(Coroutine *from_, Coroutine *to_,
CoroutineWin32 *from = DO_UPCAST(CoroutineWin32, base, from_);
CoroutineWin32 *to = DO_UPCAST(CoroutineWin32, base, to_);
- current = to_;
+ set_current(to_);
to->action = action;
SwitchToFiber(to->fiber);
@@ -89,14 +90,21 @@ void qemu_coroutine_delete(Coroutine *co_)
Coroutine *qemu_coroutine_self(void)
{
+ Coroutine *current = get_current();
+
if (!current) {
- current = &leader.base;
- leader.fiber = ConvertThreadToFiber(NULL);
+ CoroutineWin32 *leader = get_ptr_leader();
+
+ current = &leader->base;
+ set_current(current);
+ leader->fiber = ConvertThreadToFiber(NULL);
}
return current;
}
bool qemu_in_coroutine(void)
{
+ Coroutine *current = get_current();
+
return current && current->caller;
}
--
2.31.1

127
SOURCES/kvm-dma-helpers-prevent-dma_blk_cb-vs-dma_aio_cancel-rac.patch Normal file
View File

@ -0,0 +1,127 @@
From b886411a682b56bfe674f0a35d40c67c8e9dc87a Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Tue, 21 Feb 2023 16:22:17 -0500
Subject: [PATCH 02/12] dma-helpers: prevent dma_blk_cb() vs dma_aio_cancel()
race
RH-Author: Stefan Hajnoczi <stefanha@redhat.com>
RH-MergeRequest: 155: virtio-scsi: reset SCSI devices from main loop thread
RH-Bugzilla: 2155748
RH-Acked-by: Eric Blake <eblake@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Laszlo Ersek <lersek@redhat.com>
RH-Commit: [2/3] eeeea43c25d8f4fa84591b05547fb77e4058abff (stefanha/centos-stream-qemu-kvm)
dma_blk_cb() only takes the AioContext lock around ->io_func(). That
means the rest of dma_blk_cb() is not protected. In particular, the
DMAAIOCB field accesses happen outside the lock.
There is a race when the main loop thread holds the AioContext lock and
invokes scsi_device_purge_requests() -> bdrv_aio_cancel() ->
dma_aio_cancel() while an IOThread executes dma_blk_cb(). The dbs->acb
field determines how cancellation proceeds. If dma_aio_cancel() sees
dbs->acb == NULL while dma_blk_cb() is still running, the request can be
completed twice (-ECANCELED and the actual return value).
The following assertion can occur with virtio-scsi when an IOThread is
used:
../hw/scsi/scsi-disk.c:368: scsi_dma_complete: Assertion `r->req.aiocb != NULL' failed.
Fix the race by holding the AioContext across dma_blk_cb(). Now
dma_aio_cancel() under the AioContext lock will not see
inconsistent/intermediate states.
Cc: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-Id: <20230221212218.1378734-3-stefanha@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit abfcd2760b3e70727bbc0792221b8b98a733dc32)
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
hw/scsi/scsi-disk.c | 4 +---
softmmu/dma-helpers.c | 12 +++++++-----
2 files changed, 8 insertions(+), 8 deletions(-)
diff --git a/hw/scsi/scsi-disk.c b/hw/scsi/scsi-disk.c
index 5327f93f4c..b12d8b0816 100644
--- a/hw/scsi/scsi-disk.c
+++ b/hw/scsi/scsi-disk.c
@@ -354,13 +354,12 @@ done:
scsi_req_unref(&r->req);
}
+/* Called with AioContext lock held */
static void scsi_dma_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;
@@ -370,7 +369,6 @@ static void scsi_dma_complete(void *opaque, int ret)
block_acct_done(blk_get_stats(s->qdev.conf.blk), &r->acct);
}
scsi_dma_complete_noio(r, ret);
- aio_context_release(blk_get_aio_context(s->qdev.conf.blk));
}
static void scsi_read_complete_noio(SCSIDiskReq *r, int ret)
diff --git a/softmmu/dma-helpers.c b/softmmu/dma-helpers.c
index 7820fec54c..2463964805 100644
--- a/softmmu/dma-helpers.c
+++ b/softmmu/dma-helpers.c
@@ -113,17 +113,19 @@ static void dma_complete(DMAAIOCB *dbs, int ret)
static void dma_blk_cb(void *opaque, int ret)
{
DMAAIOCB *dbs = (DMAAIOCB *)opaque;
+ AioContext *ctx = dbs->ctx;
dma_addr_t cur_addr, cur_len;
void *mem;
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);
- return;
+ goto out;
}
dma_blk_unmap(dbs);
@@ -164,9 +166,9 @@ static void dma_blk_cb(void *opaque, int ret)
if (dbs->iov.size == 0) {
trace_dma_map_wait(dbs);
- dbs->bh = aio_bh_new(dbs->ctx, reschedule_dma, dbs);
+ dbs->bh = aio_bh_new(ctx, reschedule_dma, dbs);
cpu_register_map_client(dbs->bh);
- return;
+ goto out;
}
if (!QEMU_IS_ALIGNED(dbs->iov.size, dbs->align)) {
@@ -174,11 +176,11 @@ static void dma_blk_cb(void *opaque, int ret)
QEMU_ALIGN_DOWN(dbs->iov.size, dbs->align));
}
- aio_context_acquire(dbs->ctx);
dbs->acb = dbs->io_func(dbs->offset, &dbs->iov,
dma_blk_cb, dbs, dbs->io_func_opaque);
- aio_context_release(dbs->ctx);
assert(dbs->acb);
+out:
+ aio_context_release(ctx);
}
static void dma_aio_cancel(BlockAIOCB *acb)
--
2.39.1

61
SOURCES/kvm-edu-add-smp_mb__after_rmw.patch Normal file
View File

@ -0,0 +1,61 @@
From 67bbeb056f75adc6c964468d876531ab68366fe0 Mon Sep 17 00:00:00 2001
From: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Date: Thu, 9 Mar 2023 08:24:36 -0500
Subject: [PATCH 07/12] edu: add smp_mb__after_rmw()
RH-Author: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-MergeRequest: 158: qatomic: add smp_mb__before/after_rmw()
RH-Bugzilla: 2175660
RH-Acked-by: Paolo Bonzini <pbonzini@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Commit: [4/9] 2ad6fd6cb33fde39d2d017d94c0dde2152ad70c4 (eesposit/qemu-kvm)
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2175660
commit 2482aeea4195ad84cf3d4e5b15b28ec5b420ed5a
Author: Paolo Bonzini <pbonzini@redhat.com>
Date: Thu Mar 2 11:16:13 2023 +0100
edu: add smp_mb__after_rmw()
Ensure ordering between clearing the COMPUTING flag and checking
IRQFACT, and between setting the IRQFACT flag and checking
COMPUTING. This ensures that no wakeups are lost.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
---
hw/misc/edu.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/hw/misc/edu.c b/hw/misc/edu.c
index e935c418d4..a1f8bc77e7 100644
--- a/hw/misc/edu.c
+++ b/hw/misc/edu.c
@@ -267,6 +267,8 @@ static void edu_mmio_write(void *opaque, hwaddr addr, uint64_t val,
case 0x20:
if (val & EDU_STATUS_IRQFACT) {
qatomic_or(&edu->status, EDU_STATUS_IRQFACT);
+ /* Order check of the COMPUTING flag after setting IRQFACT. */
+ smp_mb__after_rmw();
} else {
qatomic_and(&edu->status, ~EDU_STATUS_IRQFACT);
}
@@ -349,6 +351,9 @@ static void *edu_fact_thread(void *opaque)
qemu_mutex_unlock(&edu->thr_mutex);
qatomic_and(&edu->status, ~EDU_STATUS_COMPUTING);
+ /* Clear COMPUTING flag before checking IRQFACT. */
+ smp_mb__after_rmw();
+
if (qatomic_read(&edu->status) & EDU_STATUS_IRQFACT) {
qemu_mutex_lock_iothread();
edu_raise_irq(edu, FACT_IRQ);
--
2.39.1

179
SOURCES/kvm-hw-acpi-aml-build-Use-existing-CPU-topology-to-build.patch
View File

@ -1,179 +0,0 @@
From 8a12049e97149056f61f7748d9869606d282d16e Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Wed, 11 May 2022 18:01:35 +0800
Subject: [PATCH 06/16] hw/acpi/aml-build: Use existing CPU topology to build
PPTT table
RH-Author: Gavin Shan <gshan@redhat.com>
RH-MergeRequest: 86: hw/arm/virt: Fix the default CPU topology
RH-Commit: [6/6] 53fa376531c204cf706cc1a7a0499019756106cb (gwshan/qemu-rhel-9)
RH-Bugzilla: 2041823
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Andrew Jones <drjones@redhat.com>
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2041823
When the PPTT table is built, the CPU topology is re-calculated, but
it's unecessary because the CPU topology has been populated in
virt_possible_cpu_arch_ids() on arm/virt machine.
This reworks build_pptt() to avoid by reusing the existing IDs in
ms->possible_cpus. Currently, the only user of build_pptt() is
arm/virt machine.
Signed-off-by: Gavin Shan <gshan@redhat.com>
Tested-by: Yanan Wang <wangyanan55@huawei.com>
Reviewed-by: Yanan Wang <wangyanan55@huawei.com>
Acked-by: Igor Mammedov <imammedo@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Message-id: 20220503140304.855514-7-gshan@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit ae9141d4a3265553503bf07d3574b40f84615a34)
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
hw/acpi/aml-build.c | 111 +++++++++++++++++++-------------------------
1 file changed, 48 insertions(+), 63 deletions(-)
diff --git a/hw/acpi/aml-build.c b/hw/acpi/aml-build.c
index 4086879ebf..e6bfac95c7 100644
--- a/hw/acpi/aml-build.c
+++ b/hw/acpi/aml-build.c
@@ -2002,86 +2002,71 @@ void build_pptt(GArray *table_data, BIOSLinker *linker, MachineState *ms,
const char *oem_id, const char *oem_table_id)
{
MachineClass *mc = MACHINE_GET_CLASS(ms);
- GQueue *list = g_queue_new();
- guint pptt_start = table_data->len;
- guint parent_offset;
- guint length, i;
- int uid = 0;
- int socket;
+ CPUArchIdList *cpus = ms->possible_cpus;
+ int64_t socket_id = -1, cluster_id = -1, core_id = -1;
+ uint32_t socket_offset = 0, cluster_offset = 0, core_offset = 0;
+ uint32_t pptt_start = table_data->len;
+ int n;
AcpiTable table = { .sig = "PPTT", .rev = 2,
.oem_id = oem_id, .oem_table_id = oem_table_id };
acpi_table_begin(&table, table_data);
- for (socket = 0; socket < ms->smp.sockets; socket++) {
- g_queue_push_tail(list,
- GUINT_TO_POINTER(table_data->len - pptt_start));
- build_processor_hierarchy_node(
- table_data,
- /*
- * Physical package - represents the boundary
- * of a physical package
- */
- (1 << 0),
- 0, socket, NULL, 0);
- }
-
- if (mc->smp_props.clusters_supported) {
- length = g_queue_get_length(list);
- for (i = 0; i < length; i++) {
- int cluster;
-
- parent_offset = GPOINTER_TO_UINT(g_queue_pop_head(list));
- for (cluster = 0; cluster < ms->smp.clusters; cluster++) {
- g_queue_push_tail(list,
- GUINT_TO_POINTER(table_data->len - pptt_start));
- build_processor_hierarchy_node(
- table_data,
- (0 << 0), /* not a physical package */
- parent_offset, cluster, NULL, 0);
- }
+ /*
+ * This works with the assumption that cpus[n].props.*_id has been
+ * sorted from top to down levels in mc->possible_cpu_arch_ids().
+ * Otherwise, the unexpected and duplicated containers will be
+ * created.
+ */
+ for (n = 0; n < cpus->len; n++) {
+ if (cpus->cpus[n].props.socket_id != socket_id) {
+ assert(cpus->cpus[n].props.socket_id > socket_id);
+ socket_id = cpus->cpus[n].props.socket_id;
+ cluster_id = -1;
+ core_id = -1;
+ socket_offset = table_data->len - pptt_start;
+ build_processor_hierarchy_node(table_data,
+ (1 << 0), /* Physical package */
+ 0, socket_id, NULL, 0);
}
- }
- length = g_queue_get_length(list);
- for (i = 0; i < length; i++) {
- int core;
-
- parent_offset = GPOINTER_TO_UINT(g_queue_pop_head(list));
- for (core = 0; core < ms->smp.cores; core++) {
- if (ms->smp.threads > 1) {
- g_queue_push_tail(list,
- GUINT_TO_POINTER(table_data->len - pptt_start));
- build_processor_hierarchy_node(
- table_data,
- (0 << 0), /* not a physical package */
- parent_offset, core, NULL, 0);
- } else {
- build_processor_hierarchy_node(
- table_data,
- (1 << 1) | /* ACPI Processor ID valid */
- (1 << 3), /* Node is a Leaf */
- parent_offset, uid++, NULL, 0);
+ if (mc->smp_props.clusters_supported) {
+ if (cpus->cpus[n].props.cluster_id != cluster_id) {
+ assert(cpus->cpus[n].props.cluster_id > cluster_id);
+ cluster_id = cpus->cpus[n].props.cluster_id;
+ core_id = -1;
+ cluster_offset = table_data->len - pptt_start;
+ build_processor_hierarchy_node(table_data,
+ (0 << 0), /* Not a physical package */
+ socket_offset, cluster_id, NULL, 0);
}
+ } else {
+ cluster_offset = socket_offset;
}
- }
- length = g_queue_get_length(list);
- for (i = 0; i < length; i++) {
- int thread;
+ if (ms->smp.threads == 1) {
+ build_processor_hierarchy_node(table_data,
+ (1 << 1) | /* ACPI Processor ID valid */
+ (1 << 3), /* Node is a Leaf */
+ cluster_offset, n, NULL, 0);
+ } else {
+ if (cpus->cpus[n].props.core_id != core_id) {
+ assert(cpus->cpus[n].props.core_id > core_id);
+ core_id = cpus->cpus[n].props.core_id;
+ core_offset = table_data->len - pptt_start;
+ build_processor_hierarchy_node(table_data,
+ (0 << 0), /* Not a physical package */
+ cluster_offset, core_id, NULL, 0);
+ }
- parent_offset = GPOINTER_TO_UINT(g_queue_pop_head(list));
- for (thread = 0; thread < ms->smp.threads; thread++) {
- build_processor_hierarchy_node(
- table_data,
+ build_processor_hierarchy_node(table_data,
(1 << 1) | /* ACPI Processor ID valid */
(1 << 2) | /* Processor is a Thread */
(1 << 3), /* Node is a Leaf */
- parent_offset, uid++, NULL, 0);
+ core_offset, n, NULL, 0);
}
}
- g_queue_free(list);
acpi_table_end(linker, &table);
}
--
2.31.1

169
SOURCES/kvm-hw-arm-virt-Add-compact-highmem-property.patch Normal file
View File

@ -0,0 +1,169 @@
From 4ab2aff624908e49b099f00609875f4d03e9e1ec Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Wed, 21 Dec 2022 08:48:45 +0800
Subject: [PATCH 6/8] hw/arm/virt: Add 'compact-highmem' property
RH-Author: Gavin Shan <gshan@redhat.com>
RH-MergeRequest: 126: hw/arm/virt: Optimize high memory region address assignment
RH-Bugzilla: 2113840
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [6/8] 781506f3445493f05b511547370b6d88ef092457
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2113840
After the improvement to high memory region address assignment is
applied, the memory layout can be changed, introducing possible
migration breakage. For example, VIRT_HIGH_PCIE_MMIO memory region
is disabled or enabled when the optimization is applied or not, with
the following configuration. The configuration is only achievable by
modifying the source code until more properties are added to allow
users selectively disable those high memory regions.
pa_bits = 40;
vms->highmem_redists = false;
vms->highmem_ecam = false;
vms->highmem_mmio = true;
# qemu-system-aarch64 -accel kvm -cpu host \
-machine virt-7.2,compact-highmem={on, off} \
-m 4G,maxmem=511G -monitor stdio
Region compact-highmem=off compact-highmem=on
----------------------------------------------------------------
MEM [1GB 512GB] [1GB 512GB]
HIGH_GIC_REDISTS2 [512GB 512GB+64MB] [disabled]
HIGH_PCIE_ECAM [512GB+256MB 512GB+512MB] [disabled]
HIGH_PCIE_MMIO [disabled] [512GB 1TB]
In order to keep backwords compatibility, we need to disable the
optimization on machine, which is virt-7.1 or ealier than it. It
means the optimization is enabled by default from virt-7.2. Besides,
'compact-highmem' property is added so that the optimization can be
explicitly enabled or disabled on all machine types by users.
Signed-off-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Tested-by: Zhenyu Zhang <zhenyzha@redhat.com>
Message-id: 20221029224307.138822-7-gshan@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit f40408a9fe5d1db70a75a33d2b26c8af8a5d57b0)
Signed-off-by: Gavin Shan <gshan@redhat.com>
Conflicts:
hw/arm/virt.c
Comment out the handlers of property 'compact-highmem' since
the property isn't exposed.
---
docs/system/arm/virt.rst | 4 ++++
hw/arm/virt.c | 34 ++++++++++++++++++++++++++++++++++
include/hw/arm/virt.h | 1 +
3 files changed, 39 insertions(+)
diff --git a/docs/system/arm/virt.rst b/docs/system/arm/virt.rst
index 20442ea2c1..4454706392 100644
--- a/docs/system/arm/virt.rst
+++ b/docs/system/arm/virt.rst
@@ -94,6 +94,10 @@ highmem
address space above 32 bits. The default is ``on`` for machine types
later than ``virt-2.12``.
+compact-highmem
+ Set ``on``/``off`` to enable/disable the compact layout for high memory regions.
+ The default is ``on`` for machine types later than ``virt-7.2``.
+
gic-version
Specify the version of the Generic Interrupt Controller (GIC) to provide.
Valid values are:
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 6896e0ca0f..6087511ae9 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -216,6 +216,12 @@ static const MemMapEntry base_memmap[] = {
* Note the extended_memmap is sized so that it eventually also includes the
* base_memmap entries (VIRT_HIGH_GIC_REDIST2 index is greater than the last
* index of base_memmap).
+ *
+ * The memory map for these Highmem IO Regions can be in legacy or compact
+ * layout, depending on 'compact-highmem' property. With legacy layout, the
+ * PA space for one specific region is always reserved, even if the region
+ * has been disabled or doesn't fit into the PA space. However, the PA space
+ * for the region won't be reserved in these circumstances with compact layout.
*/
static MemMapEntry extended_memmap[] = {
/* Additional 64 MB redist region (can contain up to 512 redistributors) */
@@ -2400,6 +2406,22 @@ static void virt_set_highmem(Object *obj, bool value, Error **errp)
vms->highmem = value;
}
+#if 0 /* Disabled for Red Hat Enterprise Linux */
+static bool virt_get_compact_highmem(Object *obj, Error **errp)
+{
+ VirtMachineState *vms = VIRT_MACHINE(obj);
+
+ return vms->highmem_compact;
+}
+
+static void virt_set_compact_highmem(Object *obj, bool value, Error **errp)
+{
+ VirtMachineState *vms = VIRT_MACHINE(obj);
+
+ vms->highmem_compact = value;
+}
+#endif /* disabled for RHEL */
+
static bool virt_get_its(Object *obj, Error **errp)
{
VirtMachineState *vms = VIRT_MACHINE(obj);
@@ -3023,6 +3045,13 @@ static void virt_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, "compact-highmem",
+ virt_get_compact_highmem,
+ virt_set_compact_highmem);
+ object_class_property_set_description(oc, "compact-highmem",
+ "Set on/off to enable/disable compact "
+ "layout for high memory regions");
+
object_class_property_add_str(oc, "gic-version", virt_get_gic_version,
virt_set_gic_version);
object_class_property_set_description(oc, "gic-version",
@@ -3107,6 +3136,7 @@ static void virt_instance_init(Object *obj)
/* High memory is enabled by default */
vms->highmem = true;
+ vms->highmem_compact = !vmc->no_highmem_compact;
vms->gic_version = VIRT_GIC_VERSION_NOSEL;
vms->highmem_ecam = !vmc->no_highmem_ecam;
@@ -3176,8 +3206,12 @@ DEFINE_VIRT_MACHINE_AS_LATEST(7, 2)
static void virt_machine_7_1_options(MachineClass *mc)
{
+ VirtMachineClass *vmc = VIRT_MACHINE_CLASS(OBJECT_CLASS(mc));
+
virt_machine_7_2_options(mc);
compat_props_add(mc->compat_props, hw_compat_7_1, hw_compat_7_1_len);
+ /* Compact layout for high memory regions was introduced with 7.2 */
+ vmc->no_highmem_compact = true;
}
DEFINE_VIRT_MACHINE(7, 1)
diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h
index 15bd291311..85e7d61868 100644
--- a/include/hw/arm/virt.h
+++ b/include/hw/arm/virt.h
@@ -125,6 +125,7 @@ struct VirtMachineClass {
bool no_pmu;
bool claim_edge_triggered_timers;
bool smbios_old_sys_ver;
+ bool no_highmem_compact;
bool no_highmem_ecam;
bool no_ged; /* Machines < 4.2 have no support for ACPI GED device */
bool kvm_no_adjvtime;
--
2.31.1

179
SOURCES/kvm-hw-arm-virt-Add-properties-to-disable-high-memory-re.patch Normal file
View File

@ -0,0 +1,179 @@
From 30e86a7c4fbcdc95b74bcb2a15745cb221783091 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Wed, 21 Dec 2022 08:48:45 +0800
Subject: [PATCH 7/8] hw/arm/virt: Add properties to disable high memory
regions
RH-Author: Gavin Shan <gshan@redhat.com>
RH-MergeRequest: 126: hw/arm/virt: Optimize high memory region address assignment
RH-Bugzilla: 2113840
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [7/8] 16f8762393b447a590b31c9e4d8d3c58c6bc9fa8
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2113840
The 3 high memory regions are usually enabled by default, but they may
be not used. For example, VIRT_HIGH_GIC_REDIST2 isn't needed by GICv2.
This leads to waste in the PA space.
Add properties ("highmem-redists", "highmem-ecam", "highmem-mmio") to
allow users selectively disable them if needed. After that, the high
memory region for GICv3 or GICv4 redistributor can be disabled by user,
the number of maximal supported CPUs needs to be calculated based on
'vms->highmem_redists'. The follow-up error message is also improved
to indicate if the high memory region for GICv3 and GICv4 has been
enabled or not.
Suggested-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Message-id: 20221029224307.138822-8-gshan@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 6a48c64eec355ab1aff694eb4522d07a8e461368)
Signed-off-by: Gavin Shan <gshan@redhat.com>
Conflicts:
hw/arm/virt.c
Comment out the handlers of the property 'highmem-redists',
'highmem-ecam' and 'highmem-mmio' since they aren't exposed.
---
docs/system/arm/virt.rst | 13 +++++++
hw/arm/virt.c | 75 ++++++++++++++++++++++++++++++++++++++--
2 files changed, 86 insertions(+), 2 deletions(-)
diff --git a/docs/system/arm/virt.rst b/docs/system/arm/virt.rst
index 4454706392..188a4f211f 100644
--- a/docs/system/arm/virt.rst
+++ b/docs/system/arm/virt.rst
@@ -98,6 +98,19 @@ compact-highmem
Set ``on``/``off`` to enable/disable the compact layout for high memory regions.
The default is ``on`` for machine types later than ``virt-7.2``.
+highmem-redists
+ Set ``on``/``off`` to enable/disable the high memory region for GICv3 or
+ GICv4 redistributor. The default is ``on``. Setting this to ``off`` will
+ limit the maximum number of CPUs when GICv3 or GICv4 is used.
+
+highmem-ecam
+ Set ``on``/``off`` to enable/disable the high memory region for PCI ECAM.
+ The default is ``on`` for machine types later than ``virt-3.0``.
+
+highmem-mmio
+ Set ``on``/``off`` to enable/disable the high memory region for PCI MMIO.
+ The default is ``on``.
+
gic-version
Specify the version of the Generic Interrupt Controller (GIC) to provide.
Valid values are:
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 6087511ae9..304fa0d6e7 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -2142,14 +2142,20 @@ static void machvirt_init(MachineState *machine)
if (vms->gic_version == VIRT_GIC_VERSION_2) {
virt_max_cpus = GIC_NCPU;
} else {
- virt_max_cpus = virt_redist_capacity(vms, VIRT_GIC_REDIST) +
- virt_redist_capacity(vms, VIRT_HIGH_GIC_REDIST2);
+ virt_max_cpus = virt_redist_capacity(vms, VIRT_GIC_REDIST);
+ if (vms->highmem_redists) {
+ virt_max_cpus += virt_redist_capacity(vms, VIRT_HIGH_GIC_REDIST2);
+ }
}
if (max_cpus > virt_max_cpus) {
error_report("Number of SMP CPUs requested (%d) exceeds max CPUs "
"supported by machine 'mach-virt' (%d)",
max_cpus, virt_max_cpus);
+ if (vms->gic_version != VIRT_GIC_VERSION_2 && !vms->highmem_redists) {
+ error_printf("Try 'highmem-redists=on' for more CPUs\n");
+ }
+
exit(1);
}
@@ -2420,6 +2426,49 @@ static void virt_set_compact_highmem(Object *obj, bool value, Error **errp)
vms->highmem_compact = value;
}
+
+static bool virt_get_highmem_redists(Object *obj, Error **errp)
+{
+ VirtMachineState *vms = VIRT_MACHINE(obj);
+
+ return vms->highmem_redists;
+}
+
+static void virt_set_highmem_redists(Object *obj, bool value, Error **errp)
+{
+ VirtMachineState *vms = VIRT_MACHINE(obj);
+
+ vms->highmem_redists = value;
+}
+
+static bool virt_get_highmem_ecam(Object *obj, Error **errp)
+{
+ VirtMachineState *vms = VIRT_MACHINE(obj);
+
+ return vms->highmem_ecam;
+}
+
+static void virt_set_highmem_ecam(Object *obj, bool value, Error **errp)
+{
+ VirtMachineState *vms = VIRT_MACHINE(obj);
+
+ vms->highmem_ecam = value;
+}
+
+static bool virt_get_highmem_mmio(Object *obj, Error **errp)
+{
+ VirtMachineState *vms = VIRT_MACHINE(obj);
+
+ return vms->highmem_mmio;
+}
+
+static void virt_set_highmem_mmio(Object *obj, bool value, Error **errp)
+{
+ VirtMachineState *vms = VIRT_MACHINE(obj);
+
+ vms->highmem_mmio = value;
+}
+
#endif /* disabled for RHEL */
static bool virt_get_its(Object *obj, Error **errp)
@@ -3052,6 +3101,28 @@ static void virt_machine_class_init(ObjectClass *oc, void *data)
"Set on/off to enable/disable compact "
"layout for high memory regions");
+ 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",
--
2.31.1

74
SOURCES/kvm-hw-arm-virt-Consider-SMP-configuration-in-CPU-topolo.patch
View File

@ -1,74 +0,0 @@
From 3b05d3464945295112b5d02d142422f524a52054 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Wed, 11 May 2022 18:01:35 +0800
Subject: [PATCH 03/16] hw/arm/virt: Consider SMP configuration in CPU topology
RH-Author: Gavin Shan <gshan@redhat.com>
RH-MergeRequest: 86: hw/arm/virt: Fix the default CPU topology
RH-Commit: [3/6] 7125b41f038c2b1cb33377d0ef1222f1ea42b648 (gwshan/qemu-rhel-9)
RH-Bugzilla: 2041823
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Andrew Jones <drjones@redhat.com>
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2041823
Currently, the SMP configuration isn't considered when the CPU
topology is populated. In this case, it's impossible to provide
the default CPU-to-NUMA mapping or association based on the socket
ID of the given CPU.
This takes account of SMP configuration when the CPU topology
is populated. The die ID for the given CPU isn't assigned since
it's not supported on arm/virt machine. Besides, the used SMP
configuration in qtest/numa-test/aarch64_numa_cpu() is corrcted
to avoid testing failure
Signed-off-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Yanan Wang <wangyanan55@huawei.com>
Acked-by: Igor Mammedov <imammedo@redhat.com>
Message-id: 20220503140304.855514-4-gshan@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit c9ec4cb5e4936f980889e717524e73896b0200ed)
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
hw/arm/virt.c | 15 ++++++++++++++-
1 file changed, 14 insertions(+), 1 deletion(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 8be12e121d..a87c8d396a 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -2553,6 +2553,7 @@ static const CPUArchIdList *virt_possible_cpu_arch_ids(MachineState *ms)
int n;
unsigned int max_cpus = ms->smp.max_cpus;
VirtMachineState *vms = VIRT_MACHINE(ms);
+ MachineClass *mc = MACHINE_GET_CLASS(vms);
if (ms->possible_cpus) {
assert(ms->possible_cpus->len == max_cpus);
@@ -2566,8 +2567,20 @@ static const CPUArchIdList *virt_possible_cpu_arch_ids(MachineState *ms)
ms->possible_cpus->cpus[n].type = ms->cpu_type;
ms->possible_cpus->cpus[n].arch_id =
virt_cpu_mp_affinity(vms, n);
+
+ assert(!mc->smp_props.dies_supported);
+ ms->possible_cpus->cpus[n].props.has_socket_id = true;
+ ms->possible_cpus->cpus[n].props.socket_id =
+ n / (ms->smp.clusters * ms->smp.cores * ms->smp.threads);
+ ms->possible_cpus->cpus[n].props.has_cluster_id = true;
+ ms->possible_cpus->cpus[n].props.cluster_id =
+ (n / (ms->smp.cores * ms->smp.threads)) % ms->smp.clusters;
+ ms->possible_cpus->cpus[n].props.has_core_id = true;
+ ms->possible_cpus->cpus[n].props.core_id =
+ (n / ms->smp.threads) % ms->smp.cores;
ms->possible_cpus->cpus[n].props.has_thread_id = true;
- ms->possible_cpus->cpus[n].props.thread_id = n;
+ ms->possible_cpus->cpus[n].props.thread_id =
+ n % ms->smp.threads;
}
return ms->possible_cpus;
}
--
2.31.1

51
SOURCES/kvm-hw-arm-virt-Enable-compat-high-memory-region-address.patch Normal file
View File

@ -0,0 +1,51 @@
From 969ea1ff46b52c5fe6d87f2eeb1625871a2dfb2a Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Wed, 21 Dec 2022 08:48:45 +0800
Subject: [PATCH 8/8] hw/arm/virt: Enable compat high memory region address
assignment for 9.2.0 machine
RH-Author: Gavin Shan <gshan@redhat.com>
RH-MergeRequest: 126: hw/arm/virt: Optimize high memory region address assignment
RH-Bugzilla: 2113840
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [8/8] beda1791c0c35dce5c669efd47685302b8468032
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2113840
Upstream: RHEL only
The compact high memory region address assignment is enabled for 9.2.0,
but it's kept as disabled for 9.0.0, to keep the backwards compatibility
on 9.0.0. Note that these newly added properties ('compact-highmem',
'highmem-redists', 'highmem-ecam', and 'highmem-mmio') in the upstream
aren't exposed for the downstream.
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
hw/arm/virt.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 304fa0d6e7..e41c0b462c 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -3581,6 +3581,7 @@ static void rhel_virt_instance_init(Object *obj)
/* High memory is enabled by default */
vms->highmem = true;
+ vms->highmem_compact = !vmc->no_highmem_compact;
vms->gic_version = VIRT_GIC_VERSION_NOSEL;
vms->highmem_ecam = !vmc->no_highmem_ecam;
@@ -3659,5 +3660,7 @@ static void rhel900_virt_options(MachineClass *mc)
/* Disable FEAT_LPA2 since old kernels (<= v5.12) don't boot with that feature */
vmc->no_tcg_lpa2 = true;
+ /* Compact layout for high memory regions was introduced with 9.2.0 */
+ vmc->no_highmem_compact = true;
}
DEFINE_RHEL_MACHINE(9, 0, 0)
--
2.31.1

88
SOURCES/kvm-hw-arm-virt-Fix-CPU-s-default-NUMA-node-ID.patch
View File

@ -1,88 +0,0 @@
From 14e49ad3b98f01c1ad6fe456469d40a96a43dc3c Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Wed, 11 May 2022 18:01:35 +0800
Subject: [PATCH 05/16] hw/arm/virt: Fix CPU's default NUMA node ID
RH-Author: Gavin Shan <gshan@redhat.com>
RH-MergeRequest: 86: hw/arm/virt: Fix the default CPU topology
RH-Commit: [5/6] 5336f62bc0c53c0417db1d71ef89544907bc28c0 (gwshan/qemu-rhel-9)
RH-Bugzilla: 2041823
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Andrew Jones <drjones@redhat.com>
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2041823
When CPU-to-NUMA association isn't explicitly provided by users,
the default one is given by mc->get_default_cpu_node_id(). However,
the CPU topology isn't fully considered in the default association
and this causes CPU topology broken warnings on booting Linux guest.
For example, the following warning messages are observed when the
Linux guest is booted with the following command lines.
/home/gavin/sandbox/qemu.main/build/qemu-system-aarch64 \
-accel kvm -machine virt,gic-version=host \
-cpu host \
-smp 6,sockets=2,cores=3,threads=1 \
-m 1024M,slots=16,maxmem=64G \
-object memory-backend-ram,id=mem0,size=128M \
-object memory-backend-ram,id=mem1,size=128M \
-object memory-backend-ram,id=mem2,size=128M \
-object memory-backend-ram,id=mem3,size=128M \
-object memory-backend-ram,id=mem4,size=128M \
-object memory-backend-ram,id=mem4,size=384M \
-numa node,nodeid=0,memdev=mem0 \
-numa node,nodeid=1,memdev=mem1 \
-numa node,nodeid=2,memdev=mem2 \
-numa node,nodeid=3,memdev=mem3 \
-numa node,nodeid=4,memdev=mem4 \
-numa node,nodeid=5,memdev=mem5
:
alternatives: patching kernel code
BUG: arch topology borken
the CLS domain not a subset of the MC domain
<the above error log repeats>
BUG: arch topology borken
the DIE domain not a subset of the NODE domain
With current implementation of mc->get_default_cpu_node_id(),
CPU#0 to CPU#5 are associated with NODE#0 to NODE#5 separately.
That's incorrect because CPU#0/1/2 should be associated with same
NUMA node because they're seated in same socket.
This fixes the issue by considering the socket ID when the default
CPU-to-NUMA association is provided in virt_possible_cpu_arch_ids().
With this applied, no more CPU topology broken warnings are seen
from the Linux guest. The 6 CPUs are associated with NODE#0/1, but
there are no CPUs associated with NODE#2/3/4/5.
Signed-off-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Yanan Wang <wangyanan55@huawei.com>
Message-id: 20220503140304.855514-6-gshan@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 4c18bc192386dfbca530e7f550e0992df657818a)
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
hw/arm/virt.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index a87c8d396a..95d012d6eb 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -2545,7 +2545,9 @@ virt_cpu_index_to_props(MachineState *ms, unsigned cpu_index)
static int64_t virt_get_default_cpu_node_id(const MachineState *ms, int idx)
{
- return idx % ms->numa_state->num_nodes;
+ int64_t socket_id = ms->possible_cpus->cpus[idx].props.socket_id;
+
+ return socket_id % ms->numa_state->num_nodes;
}
static const CPUArchIdList *virt_possible_cpu_arch_ids(MachineState *ms)
--
2.31.1

56
SOURCES/kvm-hw-arm-virt-Fix-missing-initialization-in-instance-c.patch
View File

@ -1,56 +0,0 @@
From e25c40735d2f022c07481b548d20476222006657 Mon Sep 17 00:00:00 2001
From: Eric Auger <eric.auger@redhat.com>
Date: Wed, 4 May 2022 11:11:54 +0200
Subject: [PATCH 2/5] hw/arm/virt: Fix missing initialization in
instance/class_init()
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 82: hw/arm/virt: Remove the dtb-kaslr-seed machine option
RH-Commit: [2/2] 22cbbfc30cf57a09b8acfb25d8a4dff2754c630c (eauger1/centos-qemu-kvm)
RH-Bugzilla: 2046029
RH-Acked-by: Gavin Shan <gshan@redhat.com>
RH-Acked-by: Andrew Jones <drjones@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2046029
Brew: https://brewweb.engineering.redhat.com/brew/taskinfo?taskID=45133161
Upstream Status: RHEL-only
Tested: Boot RHEL guest and check migration from 8.6 to 9.1
(with custom additions)
During the 7.0 rebase, the initialization of highmem_mmio and
highmem_redists was forgotten in rhel_virt_instance_init().
Fix it to match virt_instance_init() code.
Also mc->smp_props.clusters_supported was missing in
rhel_machine_class_init().
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
hw/arm/virt.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index bde4f77994..8be12e121d 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -3286,6 +3286,7 @@ static void rhel_machine_class_init(ObjectClass *oc, void *data)
hc->unplug_request = virt_machine_device_unplug_request_cb;
hc->unplug = virt_machine_device_unplug_cb;
mc->nvdimm_supported = true;
+ mc->smp_props.clusters_supported = true;
mc->auto_enable_numa_with_memhp = true;
mc->auto_enable_numa_with_memdev = true;
mc->default_ram_id = "mach-virt.ram";
@@ -3366,6 +3367,8 @@ static void rhel_virt_instance_init(Object *obj)
vms->gic_version = VIRT_GIC_VERSION_NOSEL;
vms->highmem_ecam = !vmc->no_highmem_ecam;
+ vms->highmem_mmio = true;
+ vms->highmem_redists = true;
if (vmc->no_its) {
vms->its = false;
--
2.31.1

112
SOURCES/kvm-hw-arm-virt-Improve-high-memory-region-address-assig.patch Normal file
View File

@ -0,0 +1,112 @@
From 1c7fad3776a14ca35b24dc2fdb262d4ddf40d6eb Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Wed, 21 Dec 2022 08:48:45 +0800
Subject: [PATCH 5/8] hw/arm/virt: Improve high memory region address
assignment
RH-Author: Gavin Shan <gshan@redhat.com>
RH-MergeRequest: 126: hw/arm/virt: Optimize high memory region address assignment
RH-Bugzilla: 2113840
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [5/8] 4d77fa78b5258a1bd8d30405cec5ba3311d42f92
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2113840
There are three high memory regions, which are VIRT_HIGH_REDIST2,
VIRT_HIGH_PCIE_ECAM and VIRT_HIGH_PCIE_MMIO. Their base addresses
are floating on highest RAM address. However, they can be disabled
in several cases.
(1) One specific high memory region is likely to be disabled by
code by toggling vms->highmem_{redists, ecam, mmio}.
(2) VIRT_HIGH_PCIE_ECAM region is disabled on machine, which is
'virt-2.12' or ealier than it.
(3) VIRT_HIGH_PCIE_ECAM region is disabled when firmware is loaded
on 32-bits system.
(4) One specific high memory region is disabled when it breaks the
PA space limit.
The current implementation of virt_set_{memmap, high_memmap}() isn't
optimized because the high memory region's PA space is always reserved,
regardless of whatever the actual state in the corresponding
vms->highmem_{redists, ecam, mmio} flag. In the code, 'base' and
'vms->highest_gpa' are always increased for case (1), (2) and (3).
It's unnecessary since the assigned PA space for the disabled high
memory region won't be used afterwards.
Improve the address assignment for those three high memory region by
skipping the address assignment for one specific high memory region if
it has been disabled in case (1), (2) and (3). The memory layout may
be changed after the improvement is applied, which leads to potential
migration breakage. So 'vms->highmem_compact' is added to control if
the improvement should be applied. For now, 'vms->highmem_compact' is
set to false, meaning that we don't have memory layout change until it
becomes configurable through property 'compact-highmem' in next patch.
Signed-off-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Tested-by: Zhenyu Zhang <zhenyzha@redhat.com>
Message-id: 20221029224307.138822-6-gshan@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 4a4ff9edc6a8fdc76082af5b41b059217138c09b)
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
hw/arm/virt.c | 15 ++++++++++-----
include/hw/arm/virt.h | 1 +
2 files changed, 11 insertions(+), 5 deletions(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 6e3b9fc060..6896e0ca0f 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -1768,18 +1768,23 @@ static void virt_set_high_memmap(VirtMachineState *vms,
vms->memmap[i].size = region_size;
/*
- * Check each device to see if they fit in the PA space,
- * moving highest_gpa as we go.
+ * Check each device to see if it fits in the PA space,
+ * moving highest_gpa as we go. For compatibility, move
+ * highest_gpa for disabled fitting devices as well, if
+ * the compact layout has been disabled.
*
* For each device that doesn't fit, disable it.
*/
fits = (region_base + region_size) <= BIT_ULL(pa_bits);
- if (fits) {
- vms->highest_gpa = region_base + region_size - 1;
+ *region_enabled &= fits;
+ if (vms->highmem_compact && !*region_enabled) {
+ continue;
}
- *region_enabled &= fits;
base = region_base + region_size;
+ if (fits) {
+ vms->highest_gpa = base - 1;
+ }
}
}
diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h
index 22b54ec510..15bd291311 100644
--- a/include/hw/arm/virt.h
+++ b/include/hw/arm/virt.h
@@ -144,6 +144,7 @@ struct VirtMachineState {
PFlashCFI01 *flash[2];
bool secure;
bool highmem;
+ bool highmem_compact;
bool highmem_ecam;
bool highmem_mmio;
bool highmem_redists;
--
2.31.1

82
SOURCES/kvm-hw-arm-virt-Introduce-variable-region_base-in-virt_s.patch Normal file
View File

@ -0,0 +1,82 @@
From 305a369fd18f29914bf96cc181add532d435d8ed Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Wed, 21 Dec 2022 08:48:45 +0800
Subject: [PATCH 3/8] hw/arm/virt: Introduce variable region_base in
virt_set_high_memmap()
RH-Author: Gavin Shan <gshan@redhat.com>
RH-MergeRequest: 126: hw/arm/virt: Optimize high memory region address assignment
RH-Bugzilla: 2113840
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [3/8] 15de90df217d680ccc858b679898b3993e1c050a
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2113840
This introduces variable 'region_base' for the base address of the
specific high memory region. It's the preparatory work to optimize
high memory region address assignment.
No functional change intended.
Signed-off-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Tested-by: Zhenyu Zhang <zhenyzha@redhat.com>
Message-id: 20221029224307.138822-4-gshan@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit fa245799b9407fc7b561da185b3d889df5e16a88)
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
hw/arm/virt.c | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index ca098d40b8..ddcf7ee2f8 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -1739,15 +1739,15 @@ static uint64_t virt_cpu_mp_affinity(VirtMachineState *vms, int idx)
static void virt_set_high_memmap(VirtMachineState *vms,
hwaddr base, int pa_bits)
{
- hwaddr region_size;
+ hwaddr region_base, region_size;
bool fits;
int i;
for (i = VIRT_LOWMEMMAP_LAST; i < ARRAY_SIZE(extended_memmap); i++) {
+ region_base = ROUND_UP(base, extended_memmap[i].size);
region_size = extended_memmap[i].size;
- base = ROUND_UP(base, region_size);
- vms->memmap[i].base = base;
+ vms->memmap[i].base = region_base;
vms->memmap[i].size = region_size;
/*
@@ -1756,9 +1756,9 @@ static void virt_set_high_memmap(VirtMachineState *vms,
*
* For each device that doesn't fit, disable it.
*/
- fits = (base + region_size) <= BIT_ULL(pa_bits);
+ fits = (region_base + region_size) <= BIT_ULL(pa_bits);
if (fits) {
- vms->highest_gpa = base + region_size - 1;
+ vms->highest_gpa = region_base + region_size - 1;
}
switch (i) {
@@ -1773,7 +1773,7 @@ static void virt_set_high_memmap(VirtMachineState *vms,
break;
}
- base += region_size;
+ base = region_base + region_size;
}
}
--
2.31.1

95
SOURCES/kvm-hw-arm-virt-Introduce-virt_get_high_memmap_enabled-h.patch Normal file
View File

@ -0,0 +1,95 @@
From a2ddd68c8365ec602db6b2a9cf83bb441ca701cc Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Wed, 21 Dec 2022 08:48:45 +0800
Subject: [PATCH 4/8] hw/arm/virt: Introduce virt_get_high_memmap_enabled()
helper
RH-Author: Gavin Shan <gshan@redhat.com>
RH-MergeRequest: 126: hw/arm/virt: Optimize high memory region address assignment
RH-Bugzilla: 2113840
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [4/8] 65524de2fc106600bbaff641caa8c4f2f8027114
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2113840
This introduces virt_get_high_memmap_enabled() helper, which returns
the pointer to vms->highmem_{redists, ecam, mmio}. The pointer will
be used in the subsequent patches.
No functional change intended.
Signed-off-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Tested-by: Zhenyu Zhang <zhenyzha@redhat.com>
Message-id: 20221029224307.138822-5-gshan@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit a5cb1350b19a5c2a58ab4edddf609ed429c13085)
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
hw/arm/virt.c | 32 +++++++++++++++++++-------------
1 file changed, 19 insertions(+), 13 deletions(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index ddcf7ee2f8..6e3b9fc060 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -1736,14 +1736,31 @@ static uint64_t virt_cpu_mp_affinity(VirtMachineState *vms, int idx)
return arm_cpu_mp_affinity(idx, clustersz);
}
+static inline bool *virt_get_high_memmap_enabled(VirtMachineState *vms,
+ int index)
+{
+ bool *enabled_array[] = {
+ &vms->highmem_redists,
+ &vms->highmem_ecam,
+ &vms->highmem_mmio,
+ };
+
+ assert(ARRAY_SIZE(extended_memmap) - VIRT_LOWMEMMAP_LAST ==
+ ARRAY_SIZE(enabled_array));
+ assert(index - VIRT_LOWMEMMAP_LAST < ARRAY_SIZE(enabled_array));
+
+ return enabled_array[index - VIRT_LOWMEMMAP_LAST];
+}
+
static void virt_set_high_memmap(VirtMachineState *vms,
hwaddr base, int pa_bits)
{
hwaddr region_base, region_size;
- bool fits;
+ bool *region_enabled, fits;
int i;
for (i = VIRT_LOWMEMMAP_LAST; i < ARRAY_SIZE(extended_memmap); i++) {
+ region_enabled = virt_get_high_memmap_enabled(vms, i);
region_base = ROUND_UP(base, extended_memmap[i].size);
region_size = extended_memmap[i].size;
@@ -1761,18 +1778,7 @@ static void virt_set_high_memmap(VirtMachineState *vms,
vms->highest_gpa = region_base + region_size - 1;
}
- switch (i) {
- case VIRT_HIGH_GIC_REDIST2:
- vms->highmem_redists &= fits;
- break;
- case VIRT_HIGH_PCIE_ECAM:
- vms->highmem_ecam &= fits;
- break;
- case VIRT_HIGH_PCIE_MMIO:
- vms->highmem_mmio &= fits;
- break;
- }
-
+ *region_enabled &= fits;
base = region_base + region_size;
}
}
--
2.31.1

130
SOURCES/kvm-hw-arm-virt-Introduce-virt_set_high_memmap-helper.patch Normal file
View File

@ -0,0 +1,130 @@
From 5dff87c5ea60054709021025c9513ec259433ce2 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Wed, 21 Dec 2022 08:48:45 +0800
Subject: [PATCH 1/8] hw/arm/virt: Introduce virt_set_high_memmap() helper
RH-Author: Gavin Shan <gshan@redhat.com>
RH-MergeRequest: 126: hw/arm/virt: Optimize high memory region address assignment
RH-Bugzilla: 2113840
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [1/8] 5f6ba5af7a2c21d8473c58e088ee99b11336c673
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2113840
This introduces virt_set_high_memmap() helper. The logic of high
memory region address assignment is moved to the helper. The intention
is to make the subsequent optimization for high memory region address
assignment easier.
No functional change intended.
Signed-off-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Tested-by: Zhenyu Zhang <zhenyzha@redhat.com>
Message-id: 20221029224307.138822-2-gshan@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 4af6b6edece5ef273d29972d53547f823d2bc1c0)
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
hw/arm/virt.c | 74 ++++++++++++++++++++++++++++-----------------------
1 file changed, 41 insertions(+), 33 deletions(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index bf18838b87..bea5f54720 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -1736,6 +1736,46 @@ static uint64_t virt_cpu_mp_affinity(VirtMachineState *vms, int idx)
return arm_cpu_mp_affinity(idx, clustersz);
}
+static void virt_set_high_memmap(VirtMachineState *vms,
+ hwaddr base, int pa_bits)
+{
+ int i;
+
+ for (i = VIRT_LOWMEMMAP_LAST; i < ARRAY_SIZE(extended_memmap); i++) {
+ hwaddr size = extended_memmap[i].size;
+ bool fits;
+
+ base = ROUND_UP(base, size);
+ vms->memmap[i].base = base;
+ vms->memmap[i].size = size;
+
+ /*
+ * Check each device to see if they fit in the PA space,
+ * moving highest_gpa as we go.
+ *
+ * For each device that doesn't fit, disable it.
+ */
+ fits = (base + size) <= BIT_ULL(pa_bits);
+ if (fits) {
+ vms->highest_gpa = base + size - 1;
+ }
+
+ switch (i) {
+ case VIRT_HIGH_GIC_REDIST2:
+ vms->highmem_redists &= fits;
+ break;
+ case VIRT_HIGH_PCIE_ECAM:
+ vms->highmem_ecam &= fits;
+ break;
+ case VIRT_HIGH_PCIE_MMIO:
+ vms->highmem_mmio &= fits;
+ break;
+ }
+
+ base += size;
+ }
+}
+
static void virt_set_memmap(VirtMachineState *vms, int pa_bits)
{
MachineState *ms = MACHINE(vms);
@@ -1791,39 +1831,7 @@ static void virt_set_memmap(VirtMachineState *vms, int pa_bits)
/* We know for sure that at least the memory fits in the PA space */
vms->highest_gpa = memtop - 1;
- for (i = VIRT_LOWMEMMAP_LAST; i < ARRAY_SIZE(extended_memmap); i++) {
- hwaddr size = extended_memmap[i].size;
- bool fits;
-
- base = ROUND_UP(base, size);
- vms->memmap[i].base = base;
- vms->memmap[i].size = size;
-
- /*
- * Check each device to see if they fit in the PA space,
- * moving highest_gpa as we go.
- *
- * For each device that doesn't fit, disable it.
- */
- fits = (base + size) <= BIT_ULL(pa_bits);
- if (fits) {
- vms->highest_gpa = base + size - 1;
- }
-
- switch (i) {
- case VIRT_HIGH_GIC_REDIST2:
- vms->highmem_redists &= fits;
- break;
- case VIRT_HIGH_PCIE_ECAM:
- vms->highmem_ecam &= fits;
- break;
- case VIRT_HIGH_PCIE_MMIO:
- vms->highmem_mmio &= fits;
- break;
- }
-
- base += size;
- }
+ virt_set_high_memmap(vms, base, pa_bits);
if (device_memory_size > 0) {
ms->device_memory = g_malloc0(sizeof(*ms->device_memory));
--
2.31.1

76
SOURCES/kvm-hw-arm-virt-Remove-the-dtb-kaslr-seed-machine-option.patch
View File

@ -1,76 +0,0 @@
From 69f771c3dc641431f3e98497cbd3832edb69284f Mon Sep 17 00:00:00 2001
From: Eric Auger <eric.auger@redhat.com>
Date: Tue, 3 May 2022 08:56:52 +0200
Subject: [PATCH 1/5] hw/arm/virt: Remove the dtb-kaslr-seed machine option
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 82: hw/arm/virt: Remove the dtb-kaslr-seed machine option
RH-Commit: [1/2] a89dcd7f22e04ae39de99795d3f34cdd0b831bc0 (eauger1/centos-qemu-kvm)
RH-Bugzilla: 2046029
RH-Acked-by: Gavin Shan <gshan@redhat.com>
RH-Acked-by: Andrew Jones <drjones@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2046029
Brew: https://brewweb.engineering.redhat.com/brew/taskinfo?taskID=45133161
Upstream Status: RHEL-only
Tested: Boot RHEL guest and check the option is not available
In RHEL we do not want to expose the dtb-kaslr-seed virt machine
option. Indeed the default 'on' value matches our need as
random data in the DTB does not cause any boot failure and we
want to support KASLR for the guest.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
---
hw/arm/virt.c | 11 +++--------
1 file changed, 3 insertions(+), 8 deletions(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index e06862d22a..bde4f77994 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -2350,6 +2350,7 @@ static void virt_set_its(Object *obj, bool value, Error **errp)
vms->its = value;
}
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static bool virt_get_dtb_kaslr_seed(Object *obj, Error **errp)
{
VirtMachineState *vms = VIRT_MACHINE(obj);
@@ -2363,6 +2364,7 @@ static void virt_set_dtb_kaslr_seed(Object *obj, bool value, Error **errp)
vms->dtb_kaslr_seed = value;
}
+#endif /* disabled for RHEL */
static char *virt_get_oem_id(Object *obj, Error **errp)
{
@@ -3346,13 +3348,6 @@ static void rhel_machine_class_init(ObjectClass *oc, void *data)
"Override the default value of field OEM Table ID "
"in ACPI table header."
"The string may be up to 8 bytes in size");
-
- object_class_property_add_bool(oc, "dtb-kaslr-seed",
- virt_get_dtb_kaslr_seed,
- virt_set_dtb_kaslr_seed);
- object_class_property_set_description(oc, "dtb-kaslr-seed",
- "Set off to disable passing of kaslr-seed "
- "dtb node to guest");
}
static void rhel_virt_instance_init(Object *obj)
@@ -3397,7 +3392,7 @@ static void rhel_virt_instance_init(Object *obj)
/* MTE is disabled by default and non-configurable for RHEL */
vms->mte = false;
- /* Supply a kaslr-seed by default */
+ /* Supply a kaslr-seed by default and non-configurable for RHEL */
vms->dtb_kaslr_seed = true;
vms->irqmap = a15irqmap;
--
2.31.1

83
SOURCES/kvm-hw-arm-virt-Rename-variable-size-to-region_size-in-v.patch Normal file
View File

@ -0,0 +1,83 @@
From bd5b7edbf8f4425f4b4e0d49a00cbdd48d9c6f48 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Wed, 21 Dec 2022 08:48:45 +0800
Subject: [PATCH 2/8] hw/arm/virt: Rename variable size to region_size in
virt_set_high_memmap()
RH-Author: Gavin Shan <gshan@redhat.com>
RH-MergeRequest: 126: hw/arm/virt: Optimize high memory region address assignment
RH-Bugzilla: 2113840
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [2/8] 1cadf1b00686cceb45821a58fdcb509bc5da335d
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2113840
This renames variable 'size' to 'region_size' in virt_set_high_memmap().
Its counterpart ('region_base') will be introduced in next patch.
No functional change intended.
Signed-off-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Tested-by: Zhenyu Zhang <zhenyzha@redhat.com>
Message-id: 20221029224307.138822-3-gshan@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 370bea9d1c78796eec235ed6cb4310f489931a62)
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
hw/arm/virt.c | 15 ++++++++-------
1 file changed, 8 insertions(+), 7 deletions(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index bea5f54720..ca098d40b8 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -1739,15 +1739,16 @@ static uint64_t virt_cpu_mp_affinity(VirtMachineState *vms, int idx)
static void virt_set_high_memmap(VirtMachineState *vms,
hwaddr base, int pa_bits)
{
+ hwaddr region_size;
+ bool fits;
int i;
for (i = VIRT_LOWMEMMAP_LAST; i < ARRAY_SIZE(extended_memmap); i++) {
- hwaddr size = extended_memmap[i].size;
- bool fits;
+ region_size = extended_memmap[i].size;
- base = ROUND_UP(base, size);
+ base = ROUND_UP(base, region_size);
vms->memmap[i].base = base;
- vms->memmap[i].size = size;
+ vms->memmap[i].size = region_size;
/*
* Check each device to see if they fit in the PA space,
@@ -1755,9 +1756,9 @@ static void virt_set_high_memmap(VirtMachineState *vms,
*
* For each device that doesn't fit, disable it.
*/
- fits = (base + size) <= BIT_ULL(pa_bits);
+ fits = (base + region_size) <= BIT_ULL(pa_bits);
if (fits) {
- vms->highest_gpa = base + size - 1;
+ vms->highest_gpa = base + region_size - 1;
}
switch (i) {
@@ -1772,7 +1773,7 @@ static void virt_set_high_memmap(VirtMachineState *vms,
break;
}
- base += size;
+ base += region_size;
}
}
--
2.31.1

96
SOURCES/kvm-hw-block-fdc-Prevent-end-of-track-overrun-CVE-2021-3.patch
View File

@ -1,96 +0,0 @@
From 6ee4a8718dcce2d6da43ee200534b75baf1d7bbe Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Philippe=20Mathieu-Daud=C3=A9?= <philmd@redhat.com>
Date: Thu, 18 Nov 2021 12:57:32 +0100
Subject: [PATCH 16/17] hw/block/fdc: Prevent end-of-track overrun
(CVE-2021-3507)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Jon Maloy <jmaloy@redhat.com>
RH-MergeRequest: 107: hw/block/fdc: Prevent end-of-track overrun (CVE-2021-3507)
RH-Commit: [1/2] 9ffc5290348884d20b894fa79f4d0c8089247f8b (mrezanin/centos-src-qemu-kvm)
RH-Bugzilla: 1951522
RH-Acked-by: Hanna Reitz <hreitz@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
Per the 82078 datasheet, if the end-of-track (EOT byte in
the FIFO) is more than the number of sectors per side, the
command is terminated unsuccessfully:
* 5.2.5 DATA TRANSFER TERMINATION
The 82078 supports terminal count explicitly through
the TC pin and implicitly through the underrun/over-
run and end-of-track (EOT) functions. For full sector
transfers, the EOT parameter can define the last
sector to be transferred in a single or multisector
transfer. If the last sector to be transferred is a par-
tial sector, the host can stop transferring the data in
mid-sector, and the 82078 will continue to complete
the sector as if a hardware TC was received. The
only difference between these implicit functions and
TC is that they return "abnormal termination" result
status. Such status indications can be ignored if they
were expected.
* 6.1.3 READ TRACK
This command terminates when the EOT specified
number of sectors have been read. If the 82078
does not find an I D Address Mark on the diskette
after the second· occurrence of a pulse on the
INDX# pin, then it sets the IC code in Status Regis-
ter 0 to "01" (Abnormal termination), sets the MA bit
in Status Register 1 to "1", and terminates the com-
mand.
* 6.1.6 VERIFY
Refer to Table 6-6 and Table 6-7 for information
concerning the values of MT and EC versus SC and
EOT value.
* Table 6·6. Result Phase Table
* Table 6-7. Verify Command Result Phase Table
Fix by aborting the transfer when EOT > # Sectors Per Side.
Cc: qemu-stable@nongnu.org
Cc: Hervé Poussineau <hpoussin@reactos.org>
Fixes: baca51faff0 ("floppy driver: disk geometry auto detect")
Reported-by: Alexander Bulekov <alxndr@bu.edu>
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/339
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Message-Id: <20211118115733.4038610-2-philmd@redhat.com>
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit defac5e2fbddf8423a354ff0454283a2115e1367)
Signed-off-by: Jon Maloy <jmaloy@redhat.com>
---
hw/block/fdc.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/hw/block/fdc.c b/hw/block/fdc.c
index ca1776121f..6481ec0cfb 100644
--- a/hw/block/fdc.c
+++ b/hw/block/fdc.c
@@ -1532,6 +1532,14 @@ static void fdctrl_start_transfer(FDCtrl *fdctrl, int direction)
int tmp;
fdctrl->data_len = 128 << (fdctrl->fifo[5] > 7 ? 7 : fdctrl->fifo[5]);
tmp = (fdctrl->fifo[6] - ks + 1);
+ if (tmp < 0) {
+ FLOPPY_DPRINTF("invalid EOT: %d\n", tmp);
+ fdctrl_stop_transfer(fdctrl, FD_SR0_ABNTERM, FD_SR1_MA, 0x00);
+ fdctrl->fifo[3] = kt;
+ fdctrl->fifo[4] = kh;
+ fdctrl->fifo[5] = ks;
+ return;
+ }
if (fdctrl->fifo[0] & 0x80)
tmp += fdctrl->fifo[6];
fdctrl->data_len *= tmp;
--
2.31.1

59
SOURCES/kvm-hw-smbios-fix-field-corruption-in-type-4-table.patch Normal file
View File

@ -0,0 +1,59 @@
From 8b0c5c6d356fd6cce9092727e20097b70e07bba9 Mon Sep 17 00:00:00 2001
From: Julia Suvorova <jusual@redhat.com>
Date: Thu, 23 Feb 2023 13:57:47 +0100
Subject: [PATCH] hw/smbios: fix field corruption in type 4 table
RH-Author: Julia Suvorova <None>
RH-MergeRequest: 156: hw/smbios: fix field corruption in type 4 table
RH-Bugzilla: 2169904
RH-Acked-by: Igor Mammedov <imammedo@redhat.com>
RH-Acked-by: MST <mst@redhat.com>
RH-Acked-by: Ani Sinha <None>
RH-Commit: [1/1] ee6d9bb6dfa0fb2625915947072cb91a0926c4ec
Since table type 4 of SMBIOS version 2.6 is shorter than 3.0, the
strings which follow immediately after the struct fields have been
overwritten by unconditional filling of later fields such as core_count2.
Make these fields dependent on the SMBIOS version.
Fixes: 05e27d74c7 ("hw/smbios: add core_count2 to smbios table type 4")
Resolves: https://bugzilla.redhat.com/show_bug.cgi?id=2169904
Signed-off-by: Julia Suvorova <jusual@redhat.com>
Message-Id: <20230223125747.254914-1-jusual@redhat.com>
Reviewed-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Ani Sinha <ani@anisinha.ca>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
(cherry picked from commit 60d09b8dc7dd4256d664ad680795cb1327805b2b)
---
hw/smbios/smbios.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/hw/smbios/smbios.c b/hw/smbios/smbios.c
index c5ad69237e..2d2ece3edb 100644
--- a/hw/smbios/smbios.c
+++ b/hw/smbios/smbios.c
@@ -752,14 +752,16 @@ static void smbios_build_type_4_table(MachineState *ms, unsigned instance)
t->core_count = (ms->smp.cores > 255) ? 0xFF : ms->smp.cores;
t->core_enabled = t->core_count;
- t->core_count2 = t->core_enabled2 = cpu_to_le16(ms->smp.cores);
-
t->thread_count = (ms->smp.threads > 255) ? 0xFF : ms->smp.threads;
- t->thread_count2 = cpu_to_le16(ms->smp.threads);
t->processor_characteristics = cpu_to_le16(0x02); /* Unknown */
t->processor_family2 = cpu_to_le16(0x01); /* Other */
+ if (tbl_len == SMBIOS_TYPE_4_LEN_V30) {
+ t->core_count2 = t->core_enabled2 = cpu_to_le16(ms->smp.cores);
+ t->thread_count2 = cpu_to_le16(ms->smp.threads);
+ }
+
SMBIOS_BUILD_TABLE_POST;
smbios_type4_count++;
}
--
2.31.1

95
SOURCES/kvm-hw-virtio-Replace-g_memdup-by-g_memdup2.patch
View File

@ -1,95 +0,0 @@
From 4dad0e9abbc843fba4e5fee6e7aa1b0db13f5898 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= <eperezma@redhat.com>
Date: Thu, 21 Jul 2022 15:27:35 +0200
Subject: [PATCH 03/32] hw/virtio: Replace g_memdup() by g_memdup2()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eugenio Pérez <eperezma@redhat.com>
RH-MergeRequest: 108: Net Control Virtqueue shadow Support
RH-Commit: [3/27] ae196903eb1a7aebbf999100e997cf82e5024cb6 (eperezmartin/qemu-kvm)
RH-Bugzilla: 1939363
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Acked-by: Cindy Lu <lulu@redhat.com>
RH-Acked-by: Laurent Vivier <lvivier@redhat.com>
Bugzilla: https://bugzilla.redhat.com/1939363
Upstream Status: git://git.qemu.org/qemu.git
commit d792199de55ca5cb5334016884039c740290b5c7
Author: Philippe Mathieu-Daudé <f4bug@amsat.org>
Date: Thu May 12 19:57:46 2022 +0200
hw/virtio: Replace g_memdup() by g_memdup2()
Per https://discourse.gnome.org/t/port-your-module-from-g-memdup-to-g-memdup2-now/5538
The old API took the size of the memory to duplicate as a guint,
whereas most memory functions take memory sizes as a gsize. This
made it easy to accidentally pass a gsize to g_memdup(). For large
values, that would lead to a silent truncation of the size from 64
to 32 bits, and result in a heap area being returned which is
significantly smaller than what the caller expects. This can likely
be exploited in various modules to cause a heap buffer overflow.
Replace g_memdup() by the safer g_memdup2() wrapper.
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Eugenio Pérez <eperezma@redhat.com>
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Message-Id: <20220512175747.142058-6-eperezma@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
---
hw/net/virtio-net.c | 3 ++-
hw/virtio/virtio-crypto.c | 6 +++---
2 files changed, 5 insertions(+), 4 deletions(-)
diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index 099e65036d..633de61513 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -1458,7 +1458,8 @@ static void virtio_net_handle_ctrl(VirtIODevice *vdev, VirtQueue *vq)
}
iov_cnt = elem->out_num;
- iov2 = iov = g_memdup(elem->out_sg, sizeof(struct iovec) * elem->out_num);
+ iov2 = iov = g_memdup2(elem->out_sg,
+ sizeof(struct iovec) * elem->out_num);
s = iov_to_buf(iov, iov_cnt, 0, &ctrl, sizeof(ctrl));
iov_discard_front(&iov, &iov_cnt, sizeof(ctrl));
if (s != sizeof(ctrl)) {
diff --git a/hw/virtio/virtio-crypto.c b/hw/virtio/virtio-crypto.c
index dcd80b904d..0e31e3cc04 100644
--- a/hw/virtio/virtio-crypto.c
+++ b/hw/virtio/virtio-crypto.c
@@ -242,7 +242,7 @@ static void virtio_crypto_handle_ctrl(VirtIODevice *vdev, VirtQueue *vq)
}
out_num = elem->out_num;
- out_iov_copy = g_memdup(elem->out_sg, sizeof(out_iov[0]) * out_num);
+ out_iov_copy = g_memdup2(elem->out_sg, sizeof(out_iov[0]) * out_num);
out_iov = out_iov_copy;
in_num = elem->in_num;
@@ -605,11 +605,11 @@ virtio_crypto_handle_request(VirtIOCryptoReq *request)
}
out_num = elem->out_num;
- out_iov_copy = g_memdup(elem->out_sg, sizeof(out_iov[0]) * out_num);
+ out_iov_copy = g_memdup2(elem->out_sg, sizeof(out_iov[0]) * out_num);
out_iov = out_iov_copy;
in_num = elem->in_num;
- in_iov_copy = g_memdup(elem->in_sg, sizeof(in_iov[0]) * in_num);
+ in_iov_copy = g_memdup2(elem->in_sg, sizeof(in_iov[0]) * in_num);
in_iov = in_iov_copy;
if (unlikely(iov_to_buf(out_iov, out_num, 0, &req, sizeof(req))
--
2.31.1

68
SOURCES/kvm-i386-do-kvm_put_msr_feature_control-first-thing-when.patch
View File

@ -1,68 +0,0 @@
From 8452a7925e18d6d57e2ac787b192097d4136b104 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Thu, 18 Aug 2022 17:01:13 +0200
Subject: [PATCH 2/2] i386: do kvm_put_msr_feature_control() first thing when
vCPU is reset
RH-Author: Vitaly Kuznetsov <vkuznets@redhat.com>
RH-MergeRequest: 217: i386: fix 'system_reset' when the VM is in VMX root operation
RH-Bugzilla: 2117546
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Peter Xu <peterx@redhat.com>
RH-Commit: [2/2] 08d5992691ba70561ce0a5b7f4504618f96a2ee6
kvm_put_sregs2() fails to reset 'locked' CR4/CR0 bits upon vCPU reset when
it is in VMX root operation. Do kvm_put_msr_feature_control() before
kvm_put_sregs2() to (possibly) kick vCPU out of VMX root operation. It also
seems logical to do kvm_put_msr_feature_control() before
kvm_put_nested_state() and not after it, especially when 'real' nested
state is set.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20220818150113.479917-3-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 45ed68a1a3a19754ade954d75a3c9d13ff560e5c)
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
---
target/i386/kvm/kvm.c | 17 ++++++++++++-----
1 file changed, 12 insertions(+), 5 deletions(-)
diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
index 9feb98fe0b..ef70e2c85f 100644
--- a/target/i386/kvm/kvm.c
+++ b/target/i386/kvm/kvm.c
@@ -4356,6 +4356,18 @@ int kvm_arch_put_registers(CPUState *cpu, int level)
assert(cpu_is_stopped(cpu) || qemu_cpu_is_self(cpu));
+ /*
+ * Put MSR_IA32_FEATURE_CONTROL first, this ensures the VM gets out of VMX
+ * root operation upon vCPU reset. kvm_put_msr_feature_control() should also
+ * preceed kvm_put_nested_state() when 'real' nested state is set.
+ */
+ if (level >= KVM_PUT_RESET_STATE) {
+ ret = kvm_put_msr_feature_control(x86_cpu);
+ if (ret < 0) {
+ return ret;
+ }
+ }
+
/* must be before kvm_put_nested_state so that EFER.SVME is set */
ret = has_sregs2 ? kvm_put_sregs2(x86_cpu) : kvm_put_sregs(x86_cpu);
if (ret < 0) {
@@ -4367,11 +4379,6 @@ int kvm_arch_put_registers(CPUState *cpu, int level)
if (ret < 0) {
return ret;
}
-
- ret = kvm_put_msr_feature_control(x86_cpu);
- if (ret < 0) {
- return ret;
- }
}
if (level == KVM_PUT_FULL_STATE) {
--
2.31.1

95
SOURCES/kvm-i386-reset-KVM-nested-state-upon-CPU-reset.patch
View File

@ -1,95 +0,0 @@
From b84bb71165c97b475548edc1c07decccca53cf16 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Thu, 18 Aug 2022 17:01:12 +0200
Subject: [PATCH 1/2] i386: reset KVM nested state upon CPU reset
RH-Author: Vitaly Kuznetsov <vkuznets@redhat.com>
RH-MergeRequest: 217: i386: fix 'system_reset' when the VM is in VMX root operation
RH-Bugzilla: 2117546
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Peter Xu <peterx@redhat.com>
RH-Commit: [1/2] b329f053a027761f50187e4ca7fd6b50ac32d2ad
Make sure env->nested_state is cleaned up when a vCPU is reset, it may
be stale after an incoming migration, kvm_arch_put_registers() may
end up failing or putting vCPU in a weird state.
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20220818150113.479917-2-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 3cafdb67504a34a0305260f0c86a73d5a3fb000b)
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
---
target/i386/kvm/kvm.c | 37 +++++++++++++++++++++++++++----------
1 file changed, 27 insertions(+), 10 deletions(-)
diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
index 6d1e009443..9feb98fe0b 100644
--- a/target/i386/kvm/kvm.c
+++ b/target/i386/kvm/kvm.c
@@ -1617,6 +1617,30 @@ static void kvm_init_xsave(CPUX86State *env)
env->xsave_buf_len);
}
+static void kvm_init_nested_state(CPUX86State *env)
+{
+ struct kvm_vmx_nested_state_hdr *vmx_hdr;
+ uint32_t size;
+
+ if (!env->nested_state) {
+ return;
+ }
+
+ size = env->nested_state->size;
+
+ memset(env->nested_state, 0, size);
+ env->nested_state->size = size;
+
+ if (cpu_has_vmx(env)) {
+ env->nested_state->format = KVM_STATE_NESTED_FORMAT_VMX;
+ vmx_hdr = &env->nested_state->hdr.vmx;
+ vmx_hdr->vmxon_pa = -1ull;
+ vmx_hdr->vmcs12_pa = -1ull;
+ } else if (cpu_has_svm(env)) {
+ env->nested_state->format = KVM_STATE_NESTED_FORMAT_SVM;
+ }
+}
+
int kvm_arch_init_vcpu(CPUState *cs)
{
struct {
@@ -2044,19 +2068,10 @@ int kvm_arch_init_vcpu(CPUState *cs)
assert(max_nested_state_len >= offsetof(struct kvm_nested_state, data));
if (cpu_has_vmx(env) || cpu_has_svm(env)) {
- struct kvm_vmx_nested_state_hdr *vmx_hdr;
-
env->nested_state = g_malloc0(max_nested_state_len);
env->nested_state->size = max_nested_state_len;
- if (cpu_has_vmx(env)) {
- env->nested_state->format = KVM_STATE_NESTED_FORMAT_VMX;
- vmx_hdr = &env->nested_state->hdr.vmx;
- vmx_hdr->vmxon_pa = -1ull;
- vmx_hdr->vmcs12_pa = -1ull;
- } else {
- env->nested_state->format = KVM_STATE_NESTED_FORMAT_SVM;
- }
+ kvm_init_nested_state(env);
}
}
@@ -2121,6 +2136,8 @@ void kvm_arch_reset_vcpu(X86CPU *cpu)
/* enabled by default */
env->poll_control_msr = 1;
+ kvm_init_nested_state(env);
+
sev_es_set_reset_vector(CPU(cpu));
}
--
2.31.1

64
SOURCES/kvm-intel-iommu-fail-DEVIOTLB_UNMAP-without-dt-mode.patch Normal file
View File

@ -0,0 +1,64 @@
From cadcc1c6a001622d971c86d44925516905e3d104 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Thu, 23 Feb 2023 14:59:21 +0800
Subject: [PATCH 8/8] intel-iommu: fail DEVIOTLB_UNMAP without dt mode
RH-Author: Laurent Vivier <lvivier@redhat.com>
RH-MergeRequest: 157: intel-iommu: fail DEVIOTLB_UNMAP without dt mode
RH-Bugzilla: 2156876
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: Peter Xu <peterx@redhat.com>
RH-Acked-by: MST <mst@redhat.com>
RH-Commit: [1/1] eb9dbae6140ef4ba10d90b9e66abd75540f6892d (lvivier/qemu-kvm-centos)
Without dt mode, device IOTLB notifier won't work since guest won't
send device IOTLB invalidation descriptor in this case. Let's fail
early instead of misbehaving silently.
Reviewed-by: Laurent Vivier <lvivier@redhat.com>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Tested-by: Viktor Prutyanov <viktor@daynix.com>
Buglink: https://bugzilla.redhat.com/2156876
Signed-off-by: Jason Wang <jasowang@redhat.com>
Message-Id: <20230223065924.42503-3-jasowang@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
(cherry picked from commit 09adb0e021207b60a0c51a68939b4539d98d3ef3)
Conflict in hw/i386/intel_iommu.c because of missing commit:
4ce27463ccce ("intel-iommu: fail MAP notifier without caching mode")
---
hw/i386/intel_iommu.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c
index a08ee85edf..d2983f40d3 100644
--- a/hw/i386/intel_iommu.c
+++ b/hw/i386/intel_iommu.c
@@ -3179,6 +3179,7 @@ static int vtd_iommu_notify_flag_changed(IOMMUMemoryRegion *iommu,
{
VTDAddressSpace *vtd_as = container_of(iommu, VTDAddressSpace, iommu);
IntelIOMMUState *s = vtd_as->iommu_state;
+ X86IOMMUState *x86_iommu = X86_IOMMU_DEVICE(s);
/* TODO: add support for VFIO and vhost users */
if (s->snoop_control) {
@@ -3186,6 +3187,13 @@ static int vtd_iommu_notify_flag_changed(IOMMUMemoryRegion *iommu,
"Snoop Control with vhost or VFIO is not supported");
return -ENOTSUP;
}
+ if (!x86_iommu->dt_supported && (new & IOMMU_NOTIFIER_DEVIOTLB_UNMAP)) {
+ error_setg_errno(errp, ENOTSUP,
+ "device %02x.%02x.%x requires device IOTLB mode",
+ pci_bus_num(vtd_as->bus), PCI_SLOT(vtd_as->devfn),
+ PCI_FUNC(vtd_as->devfn));
+ return -ENOTSUP;
+ }
/* Update per-address-space notifier flags */
vtd_as->notifier_flags = new;
--
2.39.1

386
SOURCES/kvm-io-Add-support-for-MSG_PEEK-for-socket-channel.patch Normal file
View File

@ -0,0 +1,386 @@
From 3a29b50036b972caae5bca0e5dfc34d910b1d5e9 Mon Sep 17 00:00:00 2001
From: "manish.mishra" <manish.mishra@nutanix.com>
Date: Tue, 20 Dec 2022 18:44:17 +0000
Subject: [PATCH 6/8] io: Add support for MSG_PEEK for socket channel
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Peter Xu <peterx@redhat.com>
RH-MergeRequest: 150: migration: Fix multifd crash on channel disorders
RH-Bugzilla: 2169732
RH-Acked-by: quintela1 <quintela@redhat.com>
RH-Acked-by: Leonardo Brás <leobras@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
RH-Commit: [1/2] 266563f3e387e97ec710d9bc179e5de26dfd09f1 (peterx/qemu-kvm)
MSG_PEEK peeks at the channel, The data is treated as unread and
the next read shall still return this data. This support is
currently added only for socket class. Extra parameter 'flags'
is added to io_readv calls to pass extra read flags like MSG_PEEK.
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Daniel P. Berrange <berrange@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Suggested-by: Daniel P. Berrange <berrange@redhat.com>
Signed-off-by: manish.mishra <manish.mishra@nutanix.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit 84615a19ddf2bfb38d7b3a0d487d2397ee55e4f3)
Signed-off-by: Peter Xu <peterx@redhat.com>
---
chardev/char-socket.c | 4 ++--
include/io/channel.h | 6 ++++++
io/channel-buffer.c | 1 +
io/channel-command.c | 1 +
io/channel-file.c | 1 +
io/channel-null.c | 1 +
io/channel-socket.c | 19 ++++++++++++++++++-
io/channel-tls.c | 1 +
io/channel-websock.c | 1 +
io/channel.c | 16 ++++++++++++----
migration/channel-block.c | 1 +
migration/rdma.c | 1 +
scsi/qemu-pr-helper.c | 2 +-
tests/qtest/tpm-emu.c | 2 +-
tests/unit/test-io-channel-socket.c | 1 +
util/vhost-user-server.c | 2 +-
16 files changed, 50 insertions(+), 10 deletions(-)
diff --git a/chardev/char-socket.c b/chardev/char-socket.c
index 879564aa8a..5afce9a464 100644
--- a/chardev/char-socket.c
+++ b/chardev/char-socket.c
@@ -283,11 +283,11 @@ static ssize_t tcp_chr_recv(Chardev *chr, char *buf, size_t len)
if (qio_channel_has_feature(s->ioc, QIO_CHANNEL_FEATURE_FD_PASS)) {
ret = qio_channel_readv_full(s->ioc, &iov, 1,
&msgfds, &msgfds_num,
- NULL);
+ 0, NULL);
} else {
ret = qio_channel_readv_full(s->ioc, &iov, 1,
NULL, NULL,
- NULL);
+ 0, NULL);
}
if (msgfds_num) {
diff --git a/include/io/channel.h b/include/io/channel.h
index c680ee7480..716235d496 100644
--- a/include/io/channel.h
+++ b/include/io/channel.h
@@ -34,6 +34,8 @@ OBJECT_DECLARE_TYPE(QIOChannel, QIOChannelClass,
#define QIO_CHANNEL_WRITE_FLAG_ZERO_COPY 0x1
+#define QIO_CHANNEL_READ_FLAG_MSG_PEEK 0x1
+
typedef enum QIOChannelFeature QIOChannelFeature;
enum QIOChannelFeature {
@@ -41,6 +43,7 @@ enum QIOChannelFeature {
QIO_CHANNEL_FEATURE_SHUTDOWN,
QIO_CHANNEL_FEATURE_LISTEN,
QIO_CHANNEL_FEATURE_WRITE_ZERO_COPY,
+ QIO_CHANNEL_FEATURE_READ_MSG_PEEK,
};
@@ -114,6 +117,7 @@ struct QIOChannelClass {
size_t niov,
int **fds,
size_t *nfds,
+ int flags,
Error **errp);
int (*io_close)(QIOChannel *ioc,
Error **errp);
@@ -188,6 +192,7 @@ void qio_channel_set_name(QIOChannel *ioc,
* @niov: the length of the @iov array
* @fds: pointer to an array that will received file handles
* @nfds: pointer filled with number of elements in @fds on return
+ * @flags: read flags (QIO_CHANNEL_READ_FLAG_*)
* @errp: pointer to a NULL-initialized error object
*
* Read data from the IO channel, storing it in the
@@ -224,6 +229,7 @@ ssize_t qio_channel_readv_full(QIOChannel *ioc,
size_t niov,
int **fds,
size_t *nfds,
+ int flags,
Error **errp);
diff --git a/io/channel-buffer.c b/io/channel-buffer.c
index bf52011be2..8096180f85 100644
--- a/io/channel-buffer.c
+++ b/io/channel-buffer.c
@@ -54,6 +54,7 @@ static ssize_t qio_channel_buffer_readv(QIOChannel *ioc,
size_t niov,
int **fds,
size_t *nfds,
+ int flags,
Error **errp)
{
QIOChannelBuffer *bioc = QIO_CHANNEL_BUFFER(ioc);
diff --git a/io/channel-command.c b/io/channel-command.c
index 74516252ba..e7edd091af 100644
--- a/io/channel-command.c
+++ b/io/channel-command.c
@@ -203,6 +203,7 @@ static ssize_t qio_channel_command_readv(QIOChannel *ioc,
size_t niov,
int **fds,
size_t *nfds,
+ int flags,
Error **errp)
{
QIOChannelCommand *cioc = QIO_CHANNEL_COMMAND(ioc);
diff --git a/io/channel-file.c b/io/channel-file.c
index b67687c2aa..d76663e6ae 100644
--- a/io/channel-file.c
+++ b/io/channel-file.c
@@ -86,6 +86,7 @@ static ssize_t qio_channel_file_readv(QIOChannel *ioc,
size_t niov,
int **fds,
size_t *nfds,
+ int flags,
Error **errp)
{
QIOChannelFile *fioc = QIO_CHANNEL_FILE(ioc);
diff --git a/io/channel-null.c b/io/channel-null.c
index 75e3781507..4fafdb770d 100644
--- a/io/channel-null.c
+++ b/io/channel-null.c
@@ -60,6 +60,7 @@ qio_channel_null_readv(QIOChannel *ioc,
size_t niov,
int **fds G_GNUC_UNUSED,
size_t *nfds G_GNUC_UNUSED,
+ int flags,
Error **errp)
{
QIOChannelNull *nioc = QIO_CHANNEL_NULL(ioc);
diff --git a/io/channel-socket.c b/io/channel-socket.c
index b76dca9cc1..7aca84f61a 100644
--- a/io/channel-socket.c
+++ b/io/channel-socket.c
@@ -173,6 +173,9 @@ int qio_channel_socket_connect_sync(QIOChannelSocket *ioc,
}
#endif
+ qio_channel_set_feature(QIO_CHANNEL(ioc),
+ QIO_CHANNEL_FEATURE_READ_MSG_PEEK);
+
return 0;
}
@@ -406,6 +409,9 @@ qio_channel_socket_accept(QIOChannelSocket *ioc,
}
#endif /* WIN32 */
+ qio_channel_set_feature(QIO_CHANNEL(cioc),
+ QIO_CHANNEL_FEATURE_READ_MSG_PEEK);
+
trace_qio_channel_socket_accept_complete(ioc, cioc, cioc->fd);
return cioc;
@@ -496,6 +502,7 @@ static ssize_t qio_channel_socket_readv(QIOChannel *ioc,
size_t niov,
int **fds,
size_t *nfds,
+ int flags,
Error **errp)
{
QIOChannelSocket *sioc = QIO_CHANNEL_SOCKET(ioc);
@@ -517,6 +524,10 @@ static ssize_t qio_channel_socket_readv(QIOChannel *ioc,
}
+ if (flags & QIO_CHANNEL_READ_FLAG_MSG_PEEK) {
+ sflags |= MSG_PEEK;
+ }
+
retry:
ret = recvmsg(sioc->fd, &msg, sflags);
if (ret < 0) {
@@ -624,11 +635,17 @@ static ssize_t qio_channel_socket_readv(QIOChannel *ioc,
size_t niov,
int **fds,
size_t *nfds,
+ int flags,
Error **errp)
{
QIOChannelSocket *sioc = QIO_CHANNEL_SOCKET(ioc);
ssize_t done = 0;
ssize_t i;
+ int sflags = 0;
+
+ if (flags & QIO_CHANNEL_READ_FLAG_MSG_PEEK) {
+ sflags |= MSG_PEEK;
+ }
for (i = 0; i < niov; i++) {
ssize_t ret;
@@ -636,7 +653,7 @@ static ssize_t qio_channel_socket_readv(QIOChannel *ioc,
ret = recv(sioc->fd,
iov[i].iov_base,
iov[i].iov_len,
- 0);
+ sflags);
if (ret < 0) {
if (errno == EAGAIN) {
if (done) {
diff --git a/io/channel-tls.c b/io/channel-tls.c
index 4ce890a538..c730cb8ec5 100644
--- a/io/channel-tls.c
+++ b/io/channel-tls.c
@@ -260,6 +260,7 @@ static ssize_t qio_channel_tls_readv(QIOChannel *ioc,
size_t niov,
int **fds,
size_t *nfds,
+ int flags,
Error **errp)
{
QIOChannelTLS *tioc = QIO_CHANNEL_TLS(ioc);
diff --git a/io/channel-websock.c b/io/channel-websock.c
index fb4932ade7..a12acc27cf 100644
--- a/io/channel-websock.c
+++ b/io/channel-websock.c
@@ -1081,6 +1081,7 @@ static ssize_t qio_channel_websock_readv(QIOChannel *ioc,
size_t niov,
int **fds,
size_t *nfds,
+ int flags,
Error **errp)
{
QIOChannelWebsock *wioc = QIO_CHANNEL_WEBSOCK(ioc);
diff --git a/io/channel.c b/io/channel.c
index 0640941ac5..a8c7f11649 100644
--- a/io/channel.c
+++ b/io/channel.c
@@ -52,6 +52,7 @@ ssize_t qio_channel_readv_full(QIOChannel *ioc,
size_t niov,
int **fds,
size_t *nfds,
+ int flags,
Error **errp)
{
QIOChannelClass *klass = QIO_CHANNEL_GET_CLASS(ioc);
@@ -63,7 +64,14 @@ ssize_t qio_channel_readv_full(QIOChannel *ioc,
return -1;
}
- return klass->io_readv(ioc, iov, niov, fds, nfds, errp);
+ if ((flags & QIO_CHANNEL_READ_FLAG_MSG_PEEK) &&
+ !qio_channel_has_feature(ioc, QIO_CHANNEL_FEATURE_READ_MSG_PEEK)) {
+ error_setg_errno(errp, EINVAL,
+ "Channel does not support peek read");
+ return -1;
+ }
+
+ return klass->io_readv(ioc, iov, niov, fds, nfds, flags, errp);
}
@@ -146,7 +154,7 @@ int qio_channel_readv_full_all_eof(QIOChannel *ioc,
while ((nlocal_iov > 0) || local_fds) {
ssize_t len;
len = qio_channel_readv_full(ioc, local_iov, nlocal_iov, local_fds,
- local_nfds, errp);
+ local_nfds, 0, errp);
if (len == QIO_CHANNEL_ERR_BLOCK) {
if (qemu_in_coroutine()) {
qio_channel_yield(ioc, G_IO_IN);
@@ -284,7 +292,7 @@ ssize_t qio_channel_readv(QIOChannel *ioc,
size_t niov,
Error **errp)
{
- return qio_channel_readv_full(ioc, iov, niov, NULL, NULL, errp);
+ return qio_channel_readv_full(ioc, iov, niov, NULL, NULL, 0, errp);
}
@@ -303,7 +311,7 @@ ssize_t qio_channel_read(QIOChannel *ioc,
Error **errp)
{
struct iovec iov = { .iov_base = buf, .iov_len = buflen };
- return qio_channel_readv_full(ioc, &iov, 1, NULL, NULL, errp);
+ return qio_channel_readv_full(ioc, &iov, 1, NULL, NULL, 0, errp);
}
diff --git a/migration/channel-block.c b/migration/channel-block.c
index f4ab53acdb..b7374363c3 100644
--- a/migration/channel-block.c
+++ b/migration/channel-block.c
@@ -53,6 +53,7 @@ qio_channel_block_readv(QIOChannel *ioc,
size_t niov,
int **fds,
size_t *nfds,
+ int flags,
Error **errp)
{
QIOChannelBlock *bioc = QIO_CHANNEL_BLOCK(ioc);
diff --git a/migration/rdma.c b/migration/rdma.c
index 94a55dd95b..d8b4632094 100644
--- a/migration/rdma.c
+++ b/migration/rdma.c
@@ -2854,6 +2854,7 @@ static ssize_t qio_channel_rdma_readv(QIOChannel *ioc,
size_t niov,
int **fds,
size_t *nfds,
+ int flags,
Error **errp)
{
QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(ioc);
diff --git a/scsi/qemu-pr-helper.c b/scsi/qemu-pr-helper.c
index 196b78c00d..199227a556 100644
--- a/scsi/qemu-pr-helper.c
+++ b/scsi/qemu-pr-helper.c
@@ -614,7 +614,7 @@ static int coroutine_fn prh_read(PRHelperClient *client, void *buf, int sz,
iov.iov_base = buf;
iov.iov_len = sz;
n_read = qio_channel_readv_full(QIO_CHANNEL(client->ioc), &iov, 1,
- &fds, &nfds, errp);
+ &fds, &nfds, 0, errp);
if (n_read == QIO_CHANNEL_ERR_BLOCK) {
qio_channel_yield(QIO_CHANNEL(client->ioc), G_IO_IN);
diff --git a/tests/qtest/tpm-emu.c b/tests/qtest/tpm-emu.c
index 2994d1cf42..3cf1acaf7d 100644
--- a/tests/qtest/tpm-emu.c
+++ b/tests/qtest/tpm-emu.c
@@ -106,7 +106,7 @@ void *tpm_emu_ctrl_thread(void *data)
int *pfd = NULL;
size_t nfd = 0;
- qio_channel_readv_full(ioc, &iov, 1, &pfd, &nfd, &error_abort);
+ qio_channel_readv_full(ioc, &iov, 1, &pfd, &nfd, 0, &error_abort);
cmd = be32_to_cpu(cmd);
g_assert_cmpint(cmd, ==, CMD_SET_DATAFD);
g_assert_cmpint(nfd, ==, 1);
diff --git a/tests/unit/test-io-channel-socket.c b/tests/unit/test-io-channel-socket.c
index b36a5d972a..b964bb202d 100644
--- a/tests/unit/test-io-channel-socket.c
+++ b/tests/unit/test-io-channel-socket.c
@@ -460,6 +460,7 @@ static void test_io_channel_unix_fd_pass(void)
G_N_ELEMENTS(iorecv),
&fdrecv,
&nfdrecv,
+ 0,
&error_abort);
g_assert(nfdrecv == G_N_ELEMENTS(fdsend));
diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c
index 232984ace6..145eb17c08 100644
--- a/util/vhost-user-server.c
+++ b/util/vhost-user-server.c
@@ -116,7 +116,7 @@ vu_message_read(VuDev *vu_dev, int conn_fd, VhostUserMsg *vmsg)
* qio_channel_readv_full may have short reads, keeping calling it
* until getting VHOST_USER_HDR_SIZE or 0 bytes in total
*/
- rc = qio_channel_readv_full(ioc, &iov, 1, &fds, &nfds, &local_err);
+ rc = qio_channel_readv_full(ioc, &iov, 1, &fds, &nfds, 0, &local_err);
if (rc < 0) {
if (rc == QIO_CHANNEL_ERR_BLOCK) {
assert(local_err == NULL);
--
2.31.1

99
SOURCES/kvm-iotests-106-214-308-Read-only-one-size-line.patch Normal file
View File

@ -0,0 +1,99 @@
From 6727e92a97f8ee9f367a41111bef3f5cad4a479a Mon Sep 17 00:00:00 2001
From: Hanna Reitz <hreitz@redhat.com>
Date: Mon, 20 Jun 2022 18:27:02 +0200
Subject: [PATCH 15/20] iotests/106, 214, 308: Read only one size line
RH-Author: Hanna Czenczek <hreitz@redhat.com>
RH-MergeRequest: 145: Show protocol-level information in qemu-img info
RH-Bugzilla: 1860292
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Commit: [10/12] 1554e0a92b92ed101a251478ccae43f45f6e071e (hreitz/qemu-kvm-c-9-s)
These tests read size information (sometimes disk size, sometimes
virtual size) from qemu-img info's output. Once qemu-img starts
printing info about child nodes, we are going to see multiple instances
of that per image, but these tests are only interested in the first one,
so use "head -n 1" to get it.
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220620162704.80987-11-hreitz@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 74163adda3101b127943f7cbbf8fcccd2d472426)
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
---
tests/qemu-iotests/106 | 4 ++--
tests/qemu-iotests/214 | 6 ++++--
tests/qemu-iotests/308 | 4 ++--
3 files changed, 8 insertions(+), 6 deletions(-)
diff --git a/tests/qemu-iotests/106 b/tests/qemu-iotests/106
index 9d6adb542d..ae0fc46691 100755
--- a/tests/qemu-iotests/106
+++ b/tests/qemu-iotests/106
@@ -66,7 +66,7 @@ for create_mode in off falloc full; do
expected_size=$((expected_size + $GROWTH_SIZE))
fi
- actual_size=$($QEMU_IMG info -f "$IMGFMT" "$TEST_IMG" | grep 'disk size')
+ actual_size=$($QEMU_IMG info -f "$IMGFMT" "$TEST_IMG" | grep 'disk size' | head -n 1)
actual_size=$(echo "$actual_size" | sed -e 's/^[^0-9]*\([0-9]\+\).*$/\1/')
# The actual size may exceed the expected size, depending on the file
@@ -105,7 +105,7 @@ for growth_mode in falloc full; do
_make_test_img -o "extent_size_hint=0" 2G
$QEMU_IMG resize -f "$IMGFMT" --preallocation=$growth_mode "$TEST_IMG" +${GROWTH_SIZE}K
- actual_size=$($QEMU_IMG info -f "$IMGFMT" "$TEST_IMG" | grep 'disk size')
+ actual_size=$($QEMU_IMG info -f "$IMGFMT" "$TEST_IMG" | grep 'disk size' | head -n 1)
actual_size=$(echo "$actual_size" | sed -e 's/^[^0-9]*\([0-9]\+\).*$/\1/')
if [ $actual_size -lt $GROWTH_SIZE ]; then
diff --git a/tests/qemu-iotests/214 b/tests/qemu-iotests/214
index c66e246ba2..55ffcd7f44 100755
--- a/tests/qemu-iotests/214
+++ b/tests/qemu-iotests/214
@@ -102,7 +102,8 @@ let data_size="8 * $cluster_size"
$QEMU_IO -c "write -P 0xaa 0 $data_size" "$TEST_IMG" \
2>&1 | _filter_qemu_io | _filter_testdir
sizeA=$($QEMU_IMG info --output=json "$TEST_IMG" |
- sed -n '/"actual-size":/ s/[^0-9]//gp')
+ sed -n '/"actual-size":/ s/[^0-9]//gp' |
+ head -n 1)
_make_test_img 2M -o cluster_size=$cluster_size
echo "Write compressed data:"
@@ -124,7 +125,8 @@ $QEMU_IO -c "write -P 0xcc $offset $data_size" "json:{\
_filter_qemu_io | _filter_testdir
sizeB=$($QEMU_IMG info --output=json "$TEST_IMG" |
- sed -n '/"actual-size":/ s/[^0-9]//gp')
+ sed -n '/"actual-size":/ s/[^0-9]//gp' |
+ head -n 1)
if [ $sizeA -lt $sizeB ]
then
diff --git a/tests/qemu-iotests/308 b/tests/qemu-iotests/308
index bde4aac2fa..09275e9a10 100755
--- a/tests/qemu-iotests/308
+++ b/tests/qemu-iotests/308
@@ -217,12 +217,12 @@ echo
echo '=== Remove export ==='
# Double-check that $EXT_MP appears as a non-empty file (the raw image)
-$QEMU_IMG info -f raw "$EXT_MP" | grep 'virtual size'
+$QEMU_IMG info -f raw "$EXT_MP" | grep 'virtual size' | head -n 1
fuse_export_del 'export-mp'
# See that the file appears empty again
-$QEMU_IMG info -f raw "$EXT_MP" | grep 'virtual size'
+$QEMU_IMG info -f raw "$EXT_MP" | grep 'virtual size' | head -n 1
echo
echo '=== Writable export ==='
--
2.31.1

52
SOURCES/kvm-iotests-108-Fix-when-missing-user_allow_other.patch
View File

@ -1,52 +0,0 @@
From 447bca651c9156d7aba6b7495c75f19b5e4ed53f Mon Sep 17 00:00:00 2001
From: Hanna Reitz <hreitz@redhat.com>
Date: Thu, 21 Apr 2022 16:24:35 +0200
Subject: [PATCH 07/16] iotests/108: Fix when missing user_allow_other
RH-Author: Hanna Reitz <hreitz@redhat.com>
RH-MergeRequest: 96: qcow2: Improve refcount structure rebuilding
RH-Commit: [4/4] a51ab8606fc9d8dea2b6539f4e795d5813892a5c (hreitz/qemu-kvm-c-9-s)
RH-Bugzilla: 2072379
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Eric Blake <eblake@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
FUSE exports' allow-other option defaults to "auto", which means that it
will try passing allow_other as a mount option, and fall back to not
using it when an error occurs. We make no effort to hide fusermount's
error message (because it would be difficult, and because users might
want to know about the fallback occurring), and so when allow_other does
not work (primarily when /etc/fuse.conf does not contain
user_allow_other), this error message will appear and break the
reference output.
We do not need allow_other here, though, so we can just pass
allow-other=off to fix that.
Reported-by: Markus Armbruster <armbru@redhat.com>
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220421142435.569600-1-hreitz@redhat.com>
Tested-by: Markus Armbruster <armbru@redhat.com>
Tested-by: Eric Blake <eblake@redhat.com>
(cherry picked from commit 348a0740afc5b313599533eb69bbb2b95d2f1bba)
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
---
tests/qemu-iotests/108 | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tests/qemu-iotests/108 b/tests/qemu-iotests/108
index a3090e2875..4681c7c769 100755
--- a/tests/qemu-iotests/108
+++ b/tests/qemu-iotests/108
@@ -326,7 +326,7 @@ else
$QSD \
--blockdev file,node-name=export-node,filename="$TEST_IMG" \
- --export fuse,id=fuse-export,node-name=export-node,mountpoint="$export_mp",writable=on,growable=off \
+ --export fuse,id=fuse-export,node-name=export-node,mountpoint="$export_mp",writable=on,growable=off,allow-other=off \
--pidfile "$TEST_DIR/qsd.pid" \
&
--
2.31.1

445
SOURCES/kvm-iotests-108-Test-new-refcount-rebuild-algorithm.patch
View File

@ -1,445 +0,0 @@
From ed69e01352b5e9a06173daab53bfa373c8535732 Mon Sep 17 00:00:00 2001
From: Hanna Reitz <hreitz@redhat.com>
Date: Tue, 5 Apr 2022 15:46:51 +0200
Subject: [PATCH 05/16] iotests/108: Test new refcount rebuild algorithm
RH-Author: Hanna Reitz <hreitz@redhat.com>
RH-MergeRequest: 96: qcow2: Improve refcount structure rebuilding
RH-Commit: [2/4] b68310a9fee8465dd3f568c8e867e1b7ae52bdaf (hreitz/qemu-kvm-c-9-s)
RH-Bugzilla: 2072379
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Eric Blake <eblake@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
One clear problem with how qcow2's refcount structure rebuild algorithm
used to be before "qcow2: Improve refcount structure rebuilding" was
that it is prone to failure for qcow2 images on block devices: There is
generally unused space after the actual image, and if that exceeds what
one refblock covers, the old algorithm would invariably write the
reftable past the block device's end, which cannot work. The new
algorithm does not have this problem.
Test it with three tests:
(1) Create an image with more empty space at the end than what one
refblock covers, see whether rebuilding the refcount structures
results in a change in the image file length. (It should not.)
(2) Leave precisely enough space somewhere at the beginning of the image
for the new reftable (and the refblock for that place), see whether
the new algorithm puts the reftable there. (It should.)
(3) Test the original problem: Create (something like) a block device
with a fixed size, then create a qcow2 image in there, write some
data, and then have qemu-img check rebuild the refcount structures.
Before HEAD^, the reftable would have been written past the image
file end, i.e. outside of what the block device provides, which
cannot work. HEAD^ should have fixed that.
("Something like a block device" means a loop device if we can use
one ("sudo -n losetup" works), or a FUSE block export with
growable=false otherwise.)
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220405134652.19278-3-hreitz@redhat.com>
(cherry picked from commit 9ffd6d646d1d5ee9087a8cbf0b7d2f96c5656162)
Conflicts:
- 108: The downstream qemu-storage-daemon does not support --daemonize,
so this switch has been replaced by a loop waiting for the PID file to
appear
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
---
tests/qemu-iotests/108 | 263 ++++++++++++++++++++++++++++++++++++-
tests/qemu-iotests/108.out | 81 ++++++++++++
2 files changed, 343 insertions(+), 1 deletion(-)
diff --git a/tests/qemu-iotests/108 b/tests/qemu-iotests/108
index 56339ab2c5..a3090e2875 100755
--- a/tests/qemu-iotests/108
+++ b/tests/qemu-iotests/108
@@ -30,13 +30,20 @@ status=1 # failure is the default!
_cleanup()
{
- _cleanup_test_img
+ _cleanup_test_img
+ if [ -f "$TEST_DIR/qsd.pid" ]; then
+ qsd_pid=$(cat "$TEST_DIR/qsd.pid")
+ kill -KILL "$qsd_pid"
+ fusermount -u "$TEST_DIR/fuse-export" &>/dev/null
+ fi
+ rm -f "$TEST_DIR/fuse-export"
}
trap "_cleanup; exit \$status" 0 1 2 3 15
# get standard environment, filters and checks
. ./common.rc
. ./common.filter
+. ./common.qemu
# This tests qcow2-specific low-level functionality
_supported_fmt qcow2
@@ -47,6 +54,22 @@ _supported_os Linux
# files
_unsupported_imgopts 'refcount_bits=\([^1]\|.\([^6]\|$\)\)' data_file
+# This test either needs sudo -n losetup or FUSE exports to work
+if sudo -n losetup &>/dev/null; then
+ loopdev=true
+else
+ loopdev=false
+
+ # QSD --export fuse will either yield "Parameter 'id' is missing"
+ # or "Invalid parameter 'fuse'", depending on whether there is
+ # FUSE support or not.
+ error=$($QSD --export fuse 2>&1)
+ if [[ $error = *"'fuse'"* ]]; then
+ _notrun 'Passwordless sudo for losetup or FUSE support required, but' \
+ 'neither is available'
+ fi
+fi
+
echo
echo '=== Repairing an image without any refcount table ==='
echo
@@ -138,6 +161,244 @@ _make_test_img 64M
poke_file "$TEST_IMG" $((0x10008)) "\xff\xff\xff\xff\xff\xff\x00\x00"
_check_test_img -r all
+echo
+echo '=== Check rebuilt reftable location ==='
+
+# In an earlier version of the refcount rebuild algorithm, the
+# reftable was generally placed at the image end (unless something was
+# allocated in the area covered by the refblock right before the image
+# file end, then we would try to place the reftable in that refblock).
+# This was later changed so the reftable would be placed in the
+# earliest possible location. Test this.
+
+echo
+echo '--- Does the image size increase? ---'
+echo
+
+# First test: Just create some image, write some data to it, and
+# resize it so there is free space at the end of the image (enough
+# that it spans at least one full refblock, which for cluster_size=512
+# images, spans 128k). With the old algorithm, the reftable would
+# have then been placed at the end of the image file, but with the new
+# one, it will be put in that free space.
+# We want to check whether the size of the image file increases due to
+# rebuilding the refcount structures (it should not).
+
+_make_test_img -o 'cluster_size=512' 1M
+# Write something
+$QEMU_IO -c 'write 0 64k' "$TEST_IMG" | _filter_qemu_io
+
+# Add free space
+file_len=$(stat -c '%s' "$TEST_IMG")
+truncate -s $((file_len + 256 * 1024)) "$TEST_IMG"
+
+# Corrupt the image by saying the image header was not allocated
+rt_offset=$(peek_file_be "$TEST_IMG" 48 8)
+rb_offset=$(peek_file_be "$TEST_IMG" $rt_offset 8)
+poke_file "$TEST_IMG" $rb_offset "\x00\x00"
+
+# Check whether rebuilding the refcount structures increases the image
+# file size
+file_len=$(stat -c '%s' "$TEST_IMG")
+echo
+# The only leaks there can be are the old refcount structures that are
+# leaked during rebuilding, no need to clutter the output with them
+_check_test_img -r all | grep -v '^Repairing cluster.*refcount=1 reference=0'
+echo
+post_repair_file_len=$(stat -c '%s' "$TEST_IMG")
+
+if [[ $file_len -eq $post_repair_file_len ]]; then
+ echo 'OK: Image size did not change'
+else
+ echo 'ERROR: Image size differs' \
+ "($file_len before, $post_repair_file_len after)"
+fi
+
+echo
+echo '--- Will the reftable occupy a hole specifically left for it? ---'
+echo
+
+# Note: With cluster_size=512, every refblock covers 128k.
+# The reftable covers 8M per reftable cluster.
+
+# Create an image that requires two reftable clusters (just because
+# this is more interesting than a single-clustered reftable).
+_make_test_img -o 'cluster_size=512' 9M
+$QEMU_IO -c 'write 0 8M' "$TEST_IMG" | _filter_qemu_io
+
+# Writing 8M will have resized the reftable. Unfortunately, doing so
+# will leave holes in the file, so we need to fill them up so we can
+# be sure the whole file is allocated. Do that by writing
+# consecutively smaller chunks starting from 8 MB, until the file
+# length increases even with a chunk size of 512. Then we must have
+# filled all holes.
+ofs=$((8 * 1024 * 1024))
+block_len=$((16 * 1024))
+while [[ $block_len -ge 512 ]]; do
+ file_len=$(stat -c '%s' "$TEST_IMG")
+ while [[ $(stat -c '%s' "$TEST_IMG") -eq $file_len ]]; do
+ # Do not include this in the reference output, it does not
+ # really matter which qemu-io calls we do here exactly
+ $QEMU_IO -c "write $ofs $block_len" "$TEST_IMG" >/dev/null
+ ofs=$((ofs + block_len))
+ done
+ block_len=$((block_len / 2))
+done
+
+# Fill up to 9M (do not include this in the reference output either,
+# $ofs is random for all we know)
+$QEMU_IO -c "write $ofs $((9 * 1024 * 1024 - ofs))" "$TEST_IMG" >/dev/null
+
+# Make space as follows:
+# - For the first refblock: Right at the beginning of the image (this
+# refblock is placed in the first place possible),
+# - For the reftable somewhere soon afterwards, still near the
+# beginning of the image (i.e. covered by the first refblock); the
+# reftable too is placed in the first place possible, but only after
+# all refblocks have been placed)
+# No space is needed for the other refblocks, because no refblock is
+# put before the space it covers. In this test case, we do not mind
+# if they are placed at the image file's end.
+
+# Before we make that space, we have to find out the host offset of
+# the area that belonged to the two data clusters at guest offset 4k,
+# because we expect the reftable to be placed there, and we will have
+# to verify that it is.
+
+l1_offset=$(peek_file_be "$TEST_IMG" 40 8)
+l2_offset=$(peek_file_be "$TEST_IMG" $l1_offset 8)
+l2_offset=$((l2_offset & 0x00fffffffffffe00))
+data_4k_offset=$(peek_file_be "$TEST_IMG" \
+ $((l2_offset + 4096 / 512 * 8)) 8)
+data_4k_offset=$((data_4k_offset & 0x00fffffffffffe00))
+
+$QEMU_IO -c "discard 0 512" -c "discard 4k 1k" "$TEST_IMG" | _filter_qemu_io
+
+# Corrupt the image by saying the image header was not allocated
+rt_offset=$(peek_file_be "$TEST_IMG" 48 8)
+rb_offset=$(peek_file_be "$TEST_IMG" $rt_offset 8)
+poke_file "$TEST_IMG" $rb_offset "\x00\x00"
+
+echo
+# The only leaks there can be are the old refcount structures that are
+# leaked during rebuilding, no need to clutter the output with them
+_check_test_img -r all | grep -v '^Repairing cluster.*refcount=1 reference=0'
+echo
+
+# Check whether the reftable was put where we expected
+rt_offset=$(peek_file_be "$TEST_IMG" 48 8)
+if [[ $rt_offset -eq $data_4k_offset ]]; then
+ echo 'OK: Reftable is where we expect it'
+else
+ echo "ERROR: Reftable is at $rt_offset, but was expected at $data_4k_offset"
+fi
+
+echo
+echo '--- Rebuilding refcount structures on block devices ---'
+echo
+
+# A block device cannot really grow, at least not during qemu-img
+# check. As mentioned in the above cases, rebuilding the refcount
+# structure may lead to new refcount structures being written after
+# the end of the image, and in the past that happened even if there
+# was more than sufficient space in the image. Such post-EOF writes
+# will not work on block devices, so test that the new algorithm
+# avoids it.
+
+# If we have passwordless sudo and losetup, we can use those to create
+# a block device. Otherwise, we can resort to qemu's FUSE export to
+# create a file that isn't growable, which effectively tests the same
+# thing.
+
+_cleanup_test_img
+truncate -s $((64 * 1024 * 1024)) "$TEST_IMG"
+
+if $loopdev; then
+ export_mp=$(sudo -n losetup --show -f "$TEST_IMG")
+ export_mp_driver=host_device
+ sudo -n chmod go+rw "$export_mp"
+else
+ # Create non-growable FUSE export that is a bit like an empty
+ # block device
+ export_mp="$TEST_DIR/fuse-export"
+ export_mp_driver=file
+ touch "$export_mp"
+
+ $QSD \
+ --blockdev file,node-name=export-node,filename="$TEST_IMG" \
+ --export fuse,id=fuse-export,node-name=export-node,mountpoint="$export_mp",writable=on,growable=off \
+ --pidfile "$TEST_DIR/qsd.pid" \
+ &
+
+ while [ ! -f "$TEST_DIR/qsd.pid" ]; do
+ sleep 0.1
+ done
+fi
+
+# Now create a qcow2 image on the device -- unfortunately, qemu-img
+# create force-creates the file, so we have to resort to the
+# blockdev-create job.
+_launch_qemu \
+ --blockdev $export_mp_driver,node-name=file,filename="$export_mp"
+
+_send_qemu_cmd \
+ $QEMU_HANDLE \
+ '{ "execute": "qmp_capabilities" }' \
+ 'return'
+
+# Small cluster size again, so the image needs multiple refblocks
+_send_qemu_cmd \
+ $QEMU_HANDLE \
+ '{ "execute": "blockdev-create",
+ "arguments": {
+ "job-id": "create",
+ "options": {
+ "driver": "qcow2",
+ "file": "file",
+ "size": '$((64 * 1024 * 1024))',
+ "cluster-size": 512
+ } } }' \
+ '"concluded"'
+
+_send_qemu_cmd \
+ $QEMU_HANDLE \
+ '{ "execute": "job-dismiss", "arguments": { "id": "create" } }' \
+ 'return'
+
+_send_qemu_cmd \
+ $QEMU_HANDLE \
+ '{ "execute": "quit" }' \
+ 'return'
+
+wait=y _cleanup_qemu
+echo
+
+# Write some data
+$QEMU_IO -c 'write 0 64k' "$export_mp" | _filter_qemu_io
+
+# Corrupt the image by saying the image header was not allocated
+rt_offset=$(peek_file_be "$export_mp" 48 8)
+rb_offset=$(peek_file_be "$export_mp" $rt_offset 8)
+poke_file "$export_mp" $rb_offset "\x00\x00"
+
+# Repairing such a simple case should just work
+# (We used to put the reftable at the end of the image file, which can
+# never work for non-growable devices.)
+echo
+TEST_IMG="$export_mp" _check_test_img -r all \
+ | grep -v '^Repairing cluster.*refcount=1 reference=0'
+
+if $loopdev; then
+ sudo -n losetup -d "$export_mp"
+else
+ qsd_pid=$(cat "$TEST_DIR/qsd.pid")
+ kill -TERM "$qsd_pid"
+ # Wait for process to exit (cannot `wait` because the QSD is daemonized)
+ while [ -f "$TEST_DIR/qsd.pid" ]; do
+ true
+ done
+fi
+
# success, all done
echo '*** done'
rm -f $seq.full
diff --git a/tests/qemu-iotests/108.out b/tests/qemu-iotests/108.out
index 75bab8dc84..b5401d788d 100644
--- a/tests/qemu-iotests/108.out
+++ b/tests/qemu-iotests/108.out
@@ -105,6 +105,87 @@ The following inconsistencies were found and repaired:
0 leaked clusters
1 corruptions
+Double checking the fixed image now...
+No errors were found on the image.
+
+=== Check rebuilt reftable location ===
+
+--- Does the image size increase? ---
+
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576
+wrote 65536/65536 bytes at offset 0
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+
+ERROR cluster 0 refcount=0 reference=1
+Rebuilding refcount structure
+The following inconsistencies were found and repaired:
+
+ 0 leaked clusters
+ 1 corruptions
+
+Double checking the fixed image now...
+No errors were found on the image.
+
+OK: Image size did not change
+
+--- Will the reftable occupy a hole specifically left for it? ---
+
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=9437184
+wrote 8388608/8388608 bytes at offset 0
+8 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+discard 512/512 bytes at offset 0
+512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+discard 1024/1024 bytes at offset 4096
+1 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+
+ERROR cluster 0 refcount=0 reference=1
+Rebuilding refcount structure
+The following inconsistencies were found and repaired:
+
+ 0 leaked clusters
+ 1 corruptions
+
+Double checking the fixed image now...
+No errors were found on the image.
+
+OK: Reftable is where we expect it
+
+--- Rebuilding refcount structures on block devices ---
+
+{ "execute": "qmp_capabilities" }
+{"return": {}}
+{ "execute": "blockdev-create",
+ "arguments": {
+ "job-id": "create",
+ "options": {
+ "driver": "IMGFMT",
+ "file": "file",
+ "size": 67108864,
+ "cluster-size": 512
+ } } }
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "create"}}
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "create"}}
+{"return": {}}
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "create"}}
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "create"}}
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "concluded", "id": "create"}}
+{ "execute": "job-dismiss", "arguments": { "id": "create" } }
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "null", "id": "create"}}
+{"return": {}}
+{ "execute": "quit" }
+{"return": {}}
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false, "reason": "host-qmp-quit"}}
+
+wrote 65536/65536 bytes at offset 0
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+
+ERROR cluster 0 refcount=0 reference=1
+Rebuilding refcount structure
+The following inconsistencies were found and repaired:
+
+ 0 leaked clusters
+ 1 corruptions
+
Double checking the fixed image now...
No errors were found on the image.
*** done
--
2.31.1

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