diff --git a/.gitignore b/.gitignore index f5dae2e..98eebcb 100644 --- a/.gitignore +++ b/.gitignore @@ -1 +1 @@ -SOURCES/qemu-6.2.0.tar.xz +SOURCES/qemu-7.0.0.tar.xz diff --git a/.qemu-kvm.metadata b/.qemu-kvm.metadata index 6f39e05..75efcde 100644 --- a/.qemu-kvm.metadata +++ b/.qemu-kvm.metadata @@ -1 +1 @@ -68cd61a466170115b88817e2d52db2cd7a92f43a SOURCES/qemu-6.2.0.tar.xz +c3fd2403106c33d0470bc9ba4fb4b946c0402248 SOURCES/qemu-7.0.0.tar.xz diff --git a/SOURCES/0001-ui-clipboard-Don-t-use-g_autoptr-just-to-free-a-vari.patch b/SOURCES/0001-ui-clipboard-Don-t-use-g_autoptr-just-to-free-a-vari.patch deleted file mode 100644 index 5dcba33..0000000 --- a/SOURCES/0001-ui-clipboard-Don-t-use-g_autoptr-just-to-free-a-vari.patch +++ /dev/null @@ -1,49 +0,0 @@ -From cc2f3e2ce9e2a9ab9e52e8f44bee4876e69843da Mon Sep 17 00:00:00 2001 -From: John Snow -Date: Wed, 17 Nov 2021 09:51:46 -0500 -Subject: ui/clipboard: Don't use g_autoptr just to free a variable - -Clang doesn't recognize that the variable is being "used" and will emit -a warning: - - ../ui/clipboard.c:47:34: error: variable 'old' set but not used [-Werror,-Wunused-but-set-variable] - g_autoptr(QemuClipboardInfo) old = NULL; - ^ - 1 error generated. - -OK, fine. Just do things the old way. - -Signed-off-by: John Snow -Signed-off-by: Miroslav Rezanina - ---- - -This is temporary commit from upstream submission necessary for build to pass. -We expect proper fix included upstream later. ---- - ui/clipboard.c | 3 ++- - 1 file changed, 2 insertions(+), 1 deletion(-) - -diff --git a/ui/clipboard.c b/ui/clipboard.c -index d7b008d62a..d53576b0f6 100644 ---- a/ui/clipboard.c -+++ b/ui/clipboard.c -@@ -44,13 +44,14 @@ void qemu_clipboard_peer_release(QemuClipboardPeer *peer, - - void qemu_clipboard_update(QemuClipboardInfo *info) - { -- g_autoptr(QemuClipboardInfo) old = NULL; -+ QemuClipboardInfo *old = NULL; - assert(info->selection < QEMU_CLIPBOARD_SELECTION__COUNT); - - notifier_list_notify(&clipboard_notifiers, info); - - old = cbinfo[info->selection]; - cbinfo[info->selection] = qemu_clipboard_info_ref(info); -+ g_free(old); - } - - QemuClipboardInfo *qemu_clipboard_info(QemuClipboardSelection selection) --- -2.27.0 - diff --git a/SOURCES/0004-Initial-redhat-build.patch b/SOURCES/0004-Initial-redhat-build.patch new file mode 100644 index 0000000..94cf91c --- /dev/null +++ b/SOURCES/0004-Initial-redhat-build.patch @@ -0,0 +1,313 @@ +From fc113ecd7c99646a7ced0b99570b5927ae6d595f Mon Sep 17 00:00:00 2001 +From: Miroslav Rezanina +Date: Wed, 26 May 2021 10:56:02 +0200 +Subject: Initial redhat build + +This patch introduces redhat build structure in redhat subdirectory. In addition, +several issues are fixed in QEMU tree: + +- Change of app name for sasl_server_init in VNC code from qemu to qemu-kvm + - As we use qemu-kvm as name in all places, this is updated to be consistent +- Man page renamed from qemu to qemu-kvm + - man page is installed using make install so we have to fix it 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 + +Signed-off-by: Miroslav Rezanina +-- +Rebase changes (6.1.0): +- Move build to .distro +- Move changes for support file to related commit +- Added dependency for python3-sphinx-rtd_theme +- Removed --disable-sheepdog configure option +- Added new hw-display modules +- SASL initialization moved to ui/vnc-auth-sasl.c +- Add accel-qtest- and accel-tcg-x86_64 libraries +- Added hw-usb-host module +- Disable new configure options (bpf, nvmm, slirp-smbd) +- Use -pie for ksmctl build (annocheck complain fix) + +Rebase changes (6.2.0): +- removed --disable-jemalloc and --disable-tcmalloc configure options +- added audio-oss.so +- added fdt requirement for x86_64 +- tests/acceptance renamed to tests/avocado +- added multiboot_dma.bin +- Add -Wno-string-plus-int to extra flags +- Updated configure options + +Rebase changes (7.0.0): +- Do not use -mlittle CFLAG on ppc64le +- Used upstream handling issue with ui/clipboard.c +- Use -mlittle-endian on ppc64le instead of deleteing it in configure +- Drop --disable-libxml2 option for configure (upstream) +- Remove vof roms +- Disable AVX2 support +- Use internal meson +- Disable new configure options (dbus-display and qga-vss) +- Change permissions on installing tests/Makefile.include +- Remove ssh block driver + +Merged patches (6.0.0): + - 605758c902 Limit build on Power to qemu-img and qemu-ga only + +Merged patches (6.1.0): +- f04f91751f Use cached tarballs +- 6581165c65 Remove message with running VM count +- 03c3cac9fc spec-file: build qemu-kvm without SPICE and QXL +- e0ae6c1f6c spec-file: Obsolete qemu-kvm-ui-spice +- 9d2e9f9ecf spec: Do not build qemu-kvm-block-gluster +- cf470b4234 spec: Do not link pcnet and ne2k_pci roms +- e981284a6b redhat: Install the s390-netboot.img that we've built +- 24ef557f33 spec: Remove usage of Group: tag +- c40d69b4f4 spec: Drop %defattr usage +- f8e98798ce spec: Clean up BuildRequires +- 47246b43ee spec: Remove iasl BuildRequires +- 170dc1cbe0 spec: Remove redundant 0 in conditionals +- 8718f6fa11 spec: Add more have_XXX conditionals +- a001269ce9 spec: Remove binutils versioned Requires +- 34545ee641 spec: Remove diffutils BuildRequires +- c2c82beac9 spec: Remove redundant Requires: +- 9314c231f4 spec: Add XXX_version macros +- c43db0bf0f spec: Add have_block_rbd +- 3ecb0c0319 qga: drop StandardError=syslog +- 018049dc80 Remove iscsi support +- a2edf18777 redhat: Replace the kvm-setup.service with a /etc/modules-load.d config file +- 387b5fbcfe redhat: Move qemu-kvm-docs dependency to qemu-kvm +- 4ead693178 redhat: introducting qemu-kvm-hw-usbredir +- 4dc6fc3035 redhat: use the standard vhost-user JSON path +- 84757178b4 Fix local build +- 8c394227dd spec: Restrict block drivers in tools +- b6aa7c1fae Move tools to separate package +- eafd82e509 Split qemu-pr-helper to separate package +- 2c0182e2aa spec: RPM_BUILD_ROOT -> %{buildroot} +- 91bd55ca13 spec: More use of %{name} instead of 'qemu-kvm' +- 50ba299c61 spec: Use qemu-pr-helper.service from qemu.git (partial) +- ee08d4e0a3 spec: Use %{_sourcedir} for referencing sources +- 039e7f7d02 spec: Add tools_only +- 884ba71617 spec: %build: Add run_configure helper +- 8ebd864d65 spec: %build: Disable more bits with %{disable_everything} (partial) +- f23fdb53f5 spec: %build: Add macros for some 'configure' parameters +- fe951a8bd8 spec: %files: Move qemu-guest-agent and qemu-img earlier +- 353b632e37 spec: %install: Remove redundant bits +- 9d2015b752 spec: %install: Add %{modprobe_kvm_conf} macro +- 6d05134e8c spec: %install: Remove qemu-guest-agent /etc/qemu-kvm usage +- 985b226467 spec: %install: clean up qemu-ga section +- dfaf9c600d spec: %install: Use a single %{tools_only} section +- f6978ddb46 spec: Make tools_only not cross spec sections +- 071c211098 spec: %install: Limit time spent in %{qemu_kvm_build} +- 1b65c674be spec: misc syntactic merges with Fedora +- 4da16294cf spec: Use Fedora's pattern for specifying rc version +- d7ee259a79 spec: %files: don't use fine grained -docs file list +- 64cad0c60f spec: %files: Add licenses to qemu-common too +- c3de4f080a spec: %install: Drop python3 shebang fixup +- 46fc216115 Update local build to work with spec file improvements +- bab9531548 spec: Remove buildldflags +- c8360ab6a9 spec: Use %make_build macro +- f6966c66e9 spec: Drop make install sharedir and datadir usage +- 86982421bc spec: use %make_install macro +- 191c405d22 spec: parallelize `make check` +- 251a1fb958 spec: Drop explicit --build-id +- 44c7dda6c3 spec: use %{build_ldflags} +- 0009a34354 Move virtiofsd to separate package +- 34d1b200b3 Utilize --firmware configure option +- 2800e1dd03 spec: Switch toolchain to Clang/LLVM (except process-patches.sh) +- e8a70f500f spec: Use safe-stack for x86_64 +- e29445d50d spec: Reenable write support for VMDK etc. in tools +- a4fe2a3e16 redhat: Disable LTO on non-x86 architectures + +Merged patches (6.2.0): +- 333452440b remove sgabios dependency +- 7d3633f184 enable pulseaudio +- bd898709b0 spec: disable use of gcrypt for crypto backends in favour of gnutls +- e4f0c6dee6 spec: Remove block-curl and block-ssh dependency +- 4dc13bfe63 spec: Build the VDI block driver +- d2f2ff3c74 spec: Explicitly include compress filter +- a7d047f9c2 Move ksmtuned files to separate package + +Merged patches (7.0.0): +- 098d4d08d0 spec: Rename qemu-kvm-hw-usbredir to qemu-kvm-device-usb-redirect +- c2bd0d6834 spec: Split qemu-kvm-ui-opengl +- 2c9cda805d spec: Introduce packages for virtio-gpu-* modules (changed as rhel device tree not set) +- d0414a3e0b spec: Introduce device-display-virtio-vga* packages +- 3534ec46d4 spec: Move usb-host module to separate package +- ddc14d4737 spec: Move qtest accel module to tests package +- 6f2c4befa6 spec: Extend qemu-kvm-core description +- 6f11866e4e (rhel/rhel-9.0.0) Update to qemu-kvm-6.2.0-6.el9 +- da0a28758f ui/clipboard: fix use-after-free regression +- 895d4d52eb spec: Remove qemu-virtiofsd +- c8c8c8bd84 spec: Fix obsolete for spice subpackages +- d46d2710b2 spec: Obsolete old usb redir subpackage +- 6f52a50b68 spec: Obsolete ssh driver + +Signed-off-by: Miroslav Rezanina +--- + .distro/85-kvm.preset | 5 - + .distro/Makefile | 100 + + .distro/Makefile.common | 40 + + .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/rpminspect.yaml | 6 +- + .distro/scripts/extract_build_cmd.py | 12 + + .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 + 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 + create mode 100644 scripts/systemtap/conf.d/qemu_kvm.conf + create mode 100644 scripts/systemtap/script.d/qemu_kvm.stp + +diff --git a/README.systemtap b/README.systemtap +new file mode 100644 +index 0000000000..ad913fc990 +--- /dev/null ++++ b/README.systemtap +@@ -0,0 +1,43 @@ ++QEMU tracing using systemtap-initscript ++--------------------------------------- ++ ++You can capture QEMU trace data all the time using systemtap-initscript. This ++uses SystemTap's flight recorder mode to trace all running guests to a ++fixed-size buffer on the host. Old trace entries are overwritten by new ++entries when the buffer size wraps. ++ ++1. Install the systemtap-initscript package: ++ # yum install systemtap-initscript ++ ++2. Install the systemtap scripts and the conf file: ++ # cp /usr/share/qemu-kvm/systemtap/script.d/qemu_kvm.stp /etc/systemtap/script.d/ ++ # cp /usr/share/qemu-kvm/systemtap/conf.d/qemu_kvm.conf /etc/systemtap/conf.d/ ++ ++The set of trace events to enable is given in qemu_kvm.stp. This SystemTap ++script can be customized to add or remove trace events provided in ++/usr/share/systemtap/tapset/qemu-kvm-simpletrace.stp. ++ ++SystemTap customizations can be made to qemu_kvm.conf to control the flight ++recorder buffer size and whether to store traces in memory only or disk too. ++See stap(1) for option documentation. ++ ++3. Start the systemtap service. ++　# service systemtap start qemu_kvm ++ ++4. Make the service start at boot time. ++　# chkconfig systemtap on ++ ++5. Confirm that the service works. ++ # service systemtap status qemu_kvm ++ qemu_kvm is running... ++ ++When you want to inspect the trace buffer, perform the following steps: ++ ++1. Dump the trace buffer. ++ # staprun -A qemu_kvm >/tmp/trace.log ++ ++2. Start the systemtap service because the preceding step stops the service. ++ # service systemtap start qemu_kvm ++ ++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 ++++ b/scripts/qemu-guest-agent/fsfreeze-hook +@@ -8,7 +8,7 @@ + # request, it is issued with "thaw" argument after filesystem is thawed. + + LOGFILE=/var/log/qga-fsfreeze-hook.log +-FSFREEZE_D=$(dirname -- "$0")/fsfreeze-hook.d ++FSFREEZE_D=$(dirname -- "$(realpath $0)")/fsfreeze-hook.d + + # Check whether file $1 is a backup or rpm-generated file and should be ignored + is_ignored_file() { +diff --git a/scripts/systemtap/conf.d/qemu_kvm.conf b/scripts/systemtap/conf.d/qemu_kvm.conf +new file mode 100644 +index 0000000000..372d8160a4 +--- /dev/null ++++ b/scripts/systemtap/conf.d/qemu_kvm.conf +@@ -0,0 +1,4 @@ ++# Force load uprobes (see BZ#1118352) ++stap -e 'probe process("/usr/libexec/qemu-kvm").function("main") { printf("") }' -c true ++ ++qemu_kvm_OPT="-s4" # per-CPU buffer size, in megabytes +diff --git a/scripts/systemtap/script.d/qemu_kvm.stp b/scripts/systemtap/script.d/qemu_kvm.stp +new file mode 100644 +index 0000000000..c04abf9449 +--- /dev/null ++++ b/scripts/systemtap/script.d/qemu_kvm.stp +@@ -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 +--- 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." + fi + ++exit 0 ++ + cd tests/qemu-iotests + + # QEMU_CHECK_BLOCK_AUTO is used to disable some unstable sub-tests +diff --git a/ui/vnc-auth-sasl.c b/ui/vnc-auth-sasl.c +index 47fdae5b21..2a950caa2a 100644 +--- a/ui/vnc-auth-sasl.c ++++ b/ui/vnc-auth-sasl.c +@@ -42,7 +42,7 @@ + + bool vnc_sasl_server_init(Error **errp) + { +- int saslErr = sasl_server_init(NULL, "qemu"); ++ int saslErr = sasl_server_init(NULL, "qemu-kvm"); + + if (saslErr != SASL_OK) { + error_setg(errp, "Failed to initialize SASL auth: %s", +-- +2.31.1 + diff --git a/SOURCES/0005-Enable-disable-devices-for-RHEL.patch b/SOURCES/0005-Enable-disable-devices-for-RHEL.patch new file mode 100644 index 0000000..1ffbe97 --- /dev/null +++ b/SOURCES/0005-Enable-disable-devices-for-RHEL.patch @@ -0,0 +1,642 @@ +From 51ec7495d69fe4b4d0b61642ca6c0e7fd7a1032d Mon Sep 17 00:00:00 2001 +From: Miroslav Rezanina +Date: Thu, 15 Jul 2021 03:22:36 -0400 +Subject: Enable/disable devices for RHEL + +This commit adds all changes related to changes in supported devices. + +Signed-off-by: Miroslav Rezanina +-- +Rebase notes (6.1.0): +- Added CONFIG_TPM (except s390x) +- default-configs moved to configs +- Use --with-device- configure option to use rhel configs + +Rebase notes (6.2.0): +- Add CONFIG_ISA_FDC +- Do not remove -no-hpet documentation + +Rebase notes (7.0.0): +- Added CONFIG_ARM_GIC_TCG option for aarch64 +- Fixes necessary for layout change fixes +- Renamed CONFIG_ARM_GIC_TCG to CONFIG_ARM_GICV3_TCG +- Removed upstream devices + +Merged patches (6.1.0): +- c51bf45304 Remove SPICE and QXL from x86_64-rh-devices.mak +- 02fc745601 aarch64-rh-devices: add CONFIG_PVPANIC_PCI +- f2fe835153 aarch64-rh-devices: add CONFIG_PXB +- b5431733ad disable CONFIG_USB_STORAGE_BOT +- 478ba0cdf6 Disable TPM passthrough +- 2504d68a7c aarch64: Add USB storage devices +- 51c2a3253c disable ac97 audio + +Merged patches (6.2.0): +- 9f2f9fa2ba disable sga device + +Merged patches (7.0.0): +- fd7c45a5a8 redhat: Enable virtio-mem as tech-preview on x86-64 +- c9e68ea451 Enable SGX -- RH Only +--- + .distro/qemu-kvm.spec.template | 18 +-- + .../aarch64-softmmu/aarch64-rh-devices.mak | 34 ++++++ + .../ppc64-softmmu/ppc64-rh-devices.mak | 35 ++++++ + 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 +- + hw/arm/meson.build | 2 +- + hw/block/fdc.c | 10 ++ + hw/cpu/meson.build | 5 +- + hw/display/cirrus_vga.c | 5 +- + hw/ide/piix.c | 5 +- + hw/input/pckbd.c | 2 + + hw/net/e1000.c | 2 + + hw/ppc/spapr_cpu_core.c | 2 + + hw/usb/meson.build | 2 +- + target/arm/cpu_tcg.c | 10 ++ + 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(-) + 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 + create mode 100644 configs/devices/s390x-softmmu/s390x-rh-devices.mak + create mode 100644 configs/devices/x86_64-softmmu/x86_64-rh-devices.mak + +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 +--- /dev/null ++++ b/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak +@@ -0,0 +1,34 @@ ++include ../rh-virtio.mak ++ ++CONFIG_ARM_GIC_KVM=y ++CONFIG_ARM_GICV3_TCG=y ++CONFIG_ARM_GIC=y ++CONFIG_ARM_SMMUV3=y ++CONFIG_ARM_V7M=y ++CONFIG_ARM_VIRT=y ++CONFIG_EDID=y ++CONFIG_PCIE_PORT=y ++CONFIG_PCI_DEVICES=y ++CONFIG_PCI_TESTDEV=y ++CONFIG_PFLASH_CFI01=y ++CONFIG_SCSI=y ++CONFIG_SEMIHOSTING=y ++CONFIG_USB=y ++CONFIG_USB_XHCI=y ++CONFIG_USB_XHCI_PCI=y ++CONFIG_USB_STORAGE_CORE=y ++CONFIG_USB_STORAGE_CLASSIC=y ++CONFIG_VFIO=y ++CONFIG_VFIO_PCI=y ++CONFIG_VIRTIO_MMIO=y ++CONFIG_VIRTIO_PCI=y ++CONFIG_XIO3130=y ++CONFIG_NVDIMM=y ++CONFIG_ACPI_APEI=y ++CONFIG_TPM=y ++CONFIG_TPM_EMULATOR=y ++CONFIG_TPM_TIS_SYSBUS=y ++CONFIG_PTIMER=y ++CONFIG_ARM_COMPATIBLE_SEMIHOSTING=y ++CONFIG_PVPANIC_PCI=y ++CONFIG_PXB=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 +--- /dev/null ++++ b/configs/devices/ppc64-softmmu/ppc64-rh-devices.mak +@@ -0,0 +1,35 @@ ++include ../rh-virtio.mak ++ ++CONFIG_DIMM=y ++CONFIG_MEM_DEVICE=y ++CONFIG_NVDIMM=y ++CONFIG_PCI=y ++CONFIG_PCI_DEVICES=y ++CONFIG_PCI_TESTDEV=y ++CONFIG_PCI_EXPRESS=y ++CONFIG_PSERIES=y ++CONFIG_SCSI=y ++CONFIG_SPAPR_VSCSI=y ++CONFIG_TEST_DEVICES=y ++CONFIG_USB=y ++CONFIG_USB_OHCI=y ++CONFIG_USB_OHCI_PCI=y ++CONFIG_USB_SMARTCARD=y ++CONFIG_USB_STORAGE_CORE=y ++CONFIG_USB_STORAGE_CLASSIC=y ++CONFIG_USB_XHCI=y ++CONFIG_USB_XHCI_NEC=y ++CONFIG_USB_XHCI_PCI=y ++CONFIG_VFIO=y ++CONFIG_VFIO_PCI=y ++CONFIG_VGA=y ++CONFIG_VGA_PCI=y ++CONFIG_VHOST_USER=y ++CONFIG_VIRTIO_PCI=y ++CONFIG_VIRTIO_VGA=y ++CONFIG_WDT_IB6300ESB=y ++CONFIG_XICS=y ++CONFIG_XIVE=y ++CONFIG_TPM=y ++CONFIG_TPM_SPAPR=y ++CONFIG_TPM_EMULATOR=y +diff --git a/configs/devices/rh-virtio.mak b/configs/devices/rh-virtio.mak +new file mode 100644 +index 0000000000..94ede1b5f6 +--- /dev/null ++++ b/configs/devices/rh-virtio.mak +@@ -0,0 +1,10 @@ ++CONFIG_VIRTIO=y ++CONFIG_VIRTIO_BALLOON=y ++CONFIG_VIRTIO_BLK=y ++CONFIG_VIRTIO_GPU=y ++CONFIG_VIRTIO_INPUT=y ++CONFIG_VIRTIO_INPUT_HOST=y ++CONFIG_VIRTIO_NET=y ++CONFIG_VIRTIO_RNG=y ++CONFIG_VIRTIO_SCSI=y ++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 +--- /dev/null ++++ b/configs/devices/s390x-softmmu/s390x-rh-devices.mak +@@ -0,0 +1,15 @@ ++include ../rh-virtio.mak ++ ++CONFIG_PCI=y ++CONFIG_S390_CCW_VIRTIO=y ++CONFIG_S390_FLIC=y ++CONFIG_S390_FLIC_KVM=y ++CONFIG_SCLPCONSOLE=y ++CONFIG_SCSI=y ++CONFIG_VFIO=y ++CONFIG_VFIO_AP=y ++CONFIG_VFIO_CCW=y ++CONFIG_VFIO_PCI=y ++CONFIG_VHOST_USER=y ++CONFIG_VIRTIO_CCW=y ++CONFIG_WDT_DIAG288=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 +--- /dev/null ++++ b/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak +@@ -0,0 +1,103 @@ ++include ../rh-virtio.mak ++ ++CONFIG_ACPI=y ++CONFIG_ACPI_PCI=y ++CONFIG_ACPI_CPU_HOTPLUG=y ++CONFIG_ACPI_MEMORY_HOTPLUG=y ++CONFIG_ACPI_NVDIMM=y ++CONFIG_ACPI_SMBUS=y ++CONFIG_ACPI_VMGENID=y ++CONFIG_ACPI_X86=y ++CONFIG_ACPI_X86_ICH=y ++CONFIG_AHCI=y ++CONFIG_APIC=y ++CONFIG_APM=y ++CONFIG_BOCHS_DISPLAY=y ++CONFIG_DIMM=y ++CONFIG_E1000E_PCI_EXPRESS=y ++CONFIG_E1000_PCI=y ++CONFIG_EDU=y ++CONFIG_FDC=y ++CONFIG_FDC_SYSBUS=y ++CONFIG_FDC_ISA=y ++CONFIG_FW_CFG_DMA=y ++CONFIG_HDA=y ++CONFIG_HYPERV=y ++CONFIG_HYPERV_TESTDEV=y ++CONFIG_I2C=y ++CONFIG_I440FX=y ++CONFIG_I8254=y ++CONFIG_I8257=y ++CONFIG_I8259=y ++CONFIG_I82801B11=y ++CONFIG_IDE_CORE=y ++CONFIG_IDE_PCI=y ++CONFIG_IDE_PIIX=y ++CONFIG_IDE_QDEV=y ++CONFIG_IOAPIC=y ++CONFIG_IOH3420=y ++CONFIG_ISA_BUS=y ++CONFIG_ISA_DEBUG=y ++CONFIG_ISA_TESTDEV=y ++CONFIG_LPC_ICH9=y ++CONFIG_MC146818RTC=y ++CONFIG_MEM_DEVICE=y ++CONFIG_NVDIMM=y ++CONFIG_OPENGL=y ++CONFIG_PAM=y ++CONFIG_PC=y ++CONFIG_PCI=y ++CONFIG_PCIE_PORT=y ++CONFIG_PCI_DEVICES=y ++CONFIG_PCI_EXPRESS=y ++CONFIG_PCI_EXPRESS_Q35=y ++CONFIG_PCI_I440FX=y ++CONFIG_PCI_TESTDEV=y ++CONFIG_PCKBD=y ++CONFIG_PCSPK=y ++CONFIG_PC_ACPI=y ++CONFIG_PC_PCI=y ++CONFIG_PFLASH_CFI01=y ++CONFIG_PVPANIC_ISA=y ++CONFIG_PXB=y ++CONFIG_Q35=y ++CONFIG_RTL8139_PCI=y ++CONFIG_SCSI=y ++CONFIG_SERIAL=y ++CONFIG_SERIAL_ISA=y ++CONFIG_SERIAL_PCI=y ++CONFIG_SEV=y ++CONFIG_SMBIOS=y ++CONFIG_SMBUS_EEPROM=y ++CONFIG_TEST_DEVICES=y ++CONFIG_USB=y ++CONFIG_USB_EHCI=y ++CONFIG_USB_EHCI_PCI=y ++CONFIG_USB_SMARTCARD=y ++CONFIG_USB_STORAGE_CORE=y ++CONFIG_USB_STORAGE_CLASSIC=y ++CONFIG_USB_UHCI=y ++CONFIG_USB_XHCI=y ++CONFIG_USB_XHCI_NEC=y ++CONFIG_USB_XHCI_PCI=y ++CONFIG_VFIO=y ++CONFIG_VFIO_PCI=y ++CONFIG_VGA=y ++CONFIG_VGA_CIRRUS=y ++CONFIG_VGA_PCI=y ++CONFIG_VHOST_USER=y ++CONFIG_VHOST_USER_BLK=y ++CONFIG_VIRTIO_MEM=y ++CONFIG_VIRTIO_PCI=y ++CONFIG_VIRTIO_VGA=y ++CONFIG_VMMOUSE=y ++CONFIG_VMPORT=y ++CONFIG_VTD=y ++CONFIG_WDT_IB6300ESB=y ++CONFIG_WDT_IB700=y ++CONFIG_XIO3130=y ++CONFIG_TPM=y ++CONFIG_TPM_CRB=y ++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; +diff --git a/hw/arm/meson.build b/hw/arm/meson.build +index 721a8eb8be..87ed4dd914 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')) + arm_ss.add(when: 'CONFIG_ZYNQ', if_true: files('xilinx_zynq.c')) + arm_ss.add(when: 'CONFIG_SABRELITE', if_true: files('sabrelite.c')) + +-arm_ss.add(when: 'CONFIG_ARM_V7M', if_true: files('armv7m.c')) ++#arm_ss.add(when: 'CONFIG_ARM_V7M', if_true: files('armv7m.c')) + arm_ss.add(when: 'CONFIG_EXYNOS4', if_true: files('exynos4210.c')) + 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 +--- a/hw/block/fdc.c ++++ b/hw/block/fdc.c +@@ -49,6 +49,8 @@ + #include "qom/object.h" + #include "fdc-internal.h" + ++#include "hw/boards.h" ++ + /********************************************************/ + /* debug Floppy devices */ + +@@ -2338,6 +2340,14 @@ void fdctrl_realize_common(DeviceState *dev, FDCtrl *fdctrl, Error **errp) + FDrive *drive; + static int command_tables_inited = 0; + ++ /* Restricted for Red Hat Enterprise Linux: */ ++ MachineClass *mc = MACHINE_GET_CLASS(qdev_get_machine()); ++ if (!strstr(mc->name, "-rhel7.")) { ++ error_setg(errp, "Device %s is not supported with machine type %s", ++ object_get_typename(OBJECT(dev)), mc->name); ++ return; ++ } ++ + if (fdctrl->fallback == FLOPPY_DRIVE_TYPE_AUTO) { + 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 +--- a/hw/cpu/meson.build ++++ b/hw/cpu/meson.build +@@ -1,6 +1,7 @@ +-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 +--- 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) + PCIDeviceClass *pc = PCI_DEVICE_GET_CLASS(dev); + int16_t device_id = pc->device_id; + +- /* ++ warn_report("'cirrus-vga' is deprecated, " ++ "please use a different VGA card instead"); ++ ++ /* + * Follow real hardware, cirrus card emulated has 4 MB video memory. + * Also accept 8 MB/16 MB for backward compatibility. + */ +diff --git a/hw/ide/piix.c b/hw/ide/piix.c +index ce89fd0aa3..fbcf802b13 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) + k->device_id = PCI_DEVICE_ID_INTEL_82371SB_1; + k->class_id = PCI_CLASS_STORAGE_IDE; + set_bit(DEVICE_CATEGORY_STORAGE, dc->categories); +- dc->hotpluggable = false; ++ /* Disabled for Red Hat Enterprise Linux: */ ++ dc->user_creatable = false; + } + + static const TypeInfo piix3_ide_info = { +@@ -261,6 +262,8 @@ 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; ++ /* Disabled for Red Hat Enterprise Linux: */ ++ dc->user_creatable = false; + } + + static const TypeInfo piix4_ide_info = { +diff --git a/hw/input/pckbd.c b/hw/input/pckbd.c +index 4efdf75620..5143ebaa27 100644 +--- a/hw/input/pckbd.c ++++ b/hw/input/pckbd.c +@@ -814,6 +814,8 @@ static void i8042_class_initfn(ObjectClass *klass, void *data) + dc->vmsd = &vmstate_kbd_isa; + isa->build_aml = i8042_build_aml; + set_bit(DEVICE_CATEGORY_INPUT, dc->categories); ++ /* Disabled for Red Hat Enterprise Linux: */ ++ dc->user_creatable = false; + } + + static const TypeInfo i8042_info = { +diff --git a/hw/net/e1000.c b/hw/net/e1000.c +index f5bc81296d..282d01e374 100644 +--- a/hw/net/e1000.c ++++ b/hw/net/e1000.c +@@ -1821,6 +1821,7 @@ static const E1000Info e1000_devices[] = { + .revision = 0x03, + .phy_id2 = E1000_PHY_ID2_8254xx_DEFAULT, + }, ++#if 0 /* Disabled for Red Hat Enterprise Linux 7 */ + { + .name = "e1000-82544gc", + .device_id = E1000_DEV_ID_82544GC_COPPER, +@@ -1833,6 +1834,7 @@ static const E1000Info e1000_devices[] = { + .revision = 0x03, + .phy_id2 = E1000_PHY_ID2_8254xx_DEFAULT, + }, ++#endif + }; + + static void e1000_register_types(void) +diff --git a/hw/ppc/spapr_cpu_core.c b/hw/ppc/spapr_cpu_core.c +index 8a4861f45a..fcb5dfe792 100644 +--- a/hw/ppc/spapr_cpu_core.c ++++ b/hw/ppc/spapr_cpu_core.c +@@ -379,10 +379,12 @@ static const TypeInfo spapr_cpu_core_type_infos[] = { + .instance_size = sizeof(SpaprCpuCore), + .class_size = sizeof(SpaprCpuCoreClass), + }, ++#if 0 /* Disabled for Red Hat Enterprise Linux */ + DEFINE_SPAPR_CPU_CORE_TYPE("970_v2.2"), + DEFINE_SPAPR_CPU_CORE_TYPE("970mp_v1.0"), + DEFINE_SPAPR_CPU_CORE_TYPE("970mp_v1.1"), + DEFINE_SPAPR_CPU_CORE_TYPE("power5+_v2.1"), ++#endif + DEFINE_SPAPR_CPU_CORE_TYPE("power7_v2.3"), + 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 +--- 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 + if cacard.found() + usbsmartcard_ss = ss.source_set() + usbsmartcard_ss.add(when: 'CONFIG_USB_SMARTCARD', +- if_true: [cacard, files('ccid-card-emulated.c', 'ccid-card-passthru.c')]) ++ if_true: [cacard, files('ccid-card-passthru.c')]) + hw_usb_modules += {'smartcard': usbsmartcard_ss} + endif + +diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c +index 13d0e9b195..3826fa5122 100644 +--- a/target/arm/cpu_tcg.c ++++ b/target/arm/cpu_tcg.c +@@ -22,6 +22,7 @@ + /* 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) + { +@@ -375,6 +376,7 @@ 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) +@@ -400,6 +402,7 @@ 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); +@@ -445,6 +448,7 @@ 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) + { +@@ -488,6 +492,7 @@ 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); +@@ -928,6 +933,7 @@ 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 + /* +@@ -1007,6 +1013,7 @@ 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 }, +@@ -1022,7 +1029,9 @@ 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 }, ++#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, +@@ -1053,6 +1062,7 @@ static const ARMCPUInfo arm_tcg_cpus[] = { + { .name = "pxa270-b1", .initfn = pxa270b1_initfn }, + { .name = "pxa270-c0", .initfn = pxa270c0_initfn }, + { .name = "pxa270-c5", .initfn = pxa270c5_initfn }, ++#endif /* disabled for RHEL */ + #ifndef TARGET_AARCH64 + { .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 +--- a/target/ppc/cpu-models.c ++++ b/target/ppc/cpu-models.c +@@ -66,6 +66,7 @@ + #define POWERPC_DEF(_name, _pvr, _type, _desc) \ + POWERPC_DEF_SVR(_name, _desc, _pvr, POWERPC_SVR_NONE, _type) + ++#if 0 /* Embedded and 32-bit CPUs disabled for Red Hat Enterprise Linux */ + /* Embedded PowerPC */ + /* PowerPC 405 family */ + /* PowerPC 405 cores */ +@@ -698,8 +699,10 @@ + "PowerPC 7447A v1.2 (G4)") + POWERPC_DEF("7457a_v1.2", CPU_POWERPC_74x7A_v12, 7455, + "PowerPC 7457A v1.2 (G4)") ++#endif + /* 64 bits PowerPC */ + #if defined(TARGET_PPC64) ++#if 0 /* Disabled for Red Hat Enterprise Linux */ + POWERPC_DEF("970_v2.2", CPU_POWERPC_970_v22, 970, + "PowerPC 970 v2.2") + POWERPC_DEF("970fx_v1.0", CPU_POWERPC_970FX_v10, 970, +@@ -718,6 +721,7 @@ + "PowerPC 970MP v1.1") + POWERPC_DEF("power5+_v2.1", CPU_POWERPC_POWER5P_v21, POWER5P, + "POWER5+ v2.1") ++#endif + POWERPC_DEF("power7_v2.3", CPU_POWERPC_POWER7_v23, POWER7, + "POWER7 v2.3") + POWERPC_DEF("power7+_v2.1", CPU_POWERPC_POWER7P_v21, POWER7, +@@ -897,12 +901,15 @@ PowerPCCPUAlias ppc_cpu_aliases[] = { + { "7447a", "7447a_v1.2" }, + { "7457a", "7457a_v1.2" }, + { "apollo7pm", "7457a_v1.0" }, ++#endif + #if defined(TARGET_PPC64) ++#if 0 /* Disabled for Red Hat Enterprise Linux */ + { "970", "970_v2.2" }, + { "970fx", "970fx_v3.1" }, + { "970mp", "970mp_v1.1" }, + { "power5+", "power5+_v2.1" }, + { "power5gs", "power5+_v2.1" }, ++#endif + { "power7", "power7_v2.3" }, + { "power7+", "power7+_v2.1" }, + { "power8e", "power8e_v2.1" }, +@@ -912,6 +919,7 @@ PowerPCCPUAlias ppc_cpu_aliases[] = { + { "power10", "power10_v2.0" }, + #endif + ++#if 0 /* Disabled for Red Hat Enterprise Linux */ + /* Generic PowerPCs */ + #if defined(TARGET_PPC64) + { "ppc64", "970fx_v3.1" }, +@@ -919,5 +927,6 @@ PowerPCCPUAlias ppc_cpu_aliases[] = { + { "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 +--- 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, + (max_model->def->gen == model->def->gen && + max_model->def->ec_ga < model->def->ec_ga)) { + list_add_feat("type", unavailable); ++ } else if (model->def->gen < 11 && kvm_enabled()) { ++ /* Older CPU models are not supported on Red Hat Enterprise Linux */ ++ list_add_feat("type", unavailable); + } + + /* 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 +--- 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) + error_setg(errp, "KVM doesn't support CPU models"); + return; + } ++ ++ /* Older CPU models are not supported on Red Hat Enterprise Linux */ ++ if (model->def->gen < 11) { ++ error_setg(errp, "KVM: Unsupported CPU type specified: %s", ++ MACHINE(qdev_get_machine())->cpu_type); ++ return; ++ } ++ + prop.cpuid = s390_cpuid_from_cpu_model(model); + prop.ibc = s390_ibc_from_cpu_model(model); + /* configure cpu features indicated via STFL(e) */ +-- +2.31.1 + diff --git a/SOURCES/0005-Initial-redhat-build.patch b/SOURCES/0005-Initial-redhat-build.patch deleted file mode 100644 index 3ff2dce..0000000 --- a/SOURCES/0005-Initial-redhat-build.patch +++ /dev/null @@ -1,301 +0,0 @@ -From 3308eb892f03c7169f712fe88e74dacd6f05b1fe Mon Sep 17 00:00:00 2001 -From: Miroslav Rezanina -Date: Wed, 26 May 2021 10:56:02 +0200 -Subject: Initial redhat build - -This patch introduces redhat build structure in redhat subdirectory. In addition, -several issues are fixed in QEMU tree: - -- Change of app name for sasl_server_init in VNC code from qemu to qemu-kvm - - As we use qemu-kvm as name in all places, this is updated to be consistent -- Man page renamed from qemu to qemu-kvm - - man page is installed using make install so we have to fix it in qemu tree - -We disable make check due to issues with some of the tests. - -This rebase is based on qemu-kvm-6.1.0-8.el9 - -Signed-off-by: Miroslav Rezanina --- -Rebase changes (6.1.0): -- Move build to .distro -- Move changes for support file to related commit -- Added dependency for python3-sphinx-rtd_theme -- Removed --disable-sheepdog configure option -- Added new hw-display modules -- SASL initialization moved to ui/vnc-auth-sasl.c -- Add accel-qtest- and accel-tcg-x86_64 libraries -- Added hw-usb-host module -- Disable new configure options (bpf, nvmm, slirp-smbd) -- Use -pie for ksmctl build (annocheck complain fix) - -Rebase changes (6.2.0): -- removed --disable-jemalloc and --disable-tcmalloc configure options -- added audio-oss.so -- added fdt requirement for x86_64 -- tests/acceptance renamed to tests/avocado -- added multiboot_dma.bin -- Add -Wno-string-plus-int to extra flags -- Updated configure options - -Merged patches (6.0.0): - - 605758c902 Limit build on Power to qemu-img and qemu-ga only - -Merged patches (6.1.0): -- f04f91751f Use cached tarballs -- 6581165c65 Remove message with running VM count -- 03c3cac9fc spec-file: build qemu-kvm without SPICE and QXL -- e0ae6c1f6c spec-file: Obsolete qemu-kvm-ui-spice -- 9d2e9f9ecf spec: Do not build qemu-kvm-block-gluster -- cf470b4234 spec: Do not link pcnet and ne2k_pci roms -- e981284a6b redhat: Install the s390-netboot.img that we've built -- 24ef557f33 spec: Remove usage of Group: tag -- c40d69b4f4 spec: Drop %defattr usage -- f8e98798ce spec: Clean up BuildRequires -- 47246b43ee spec: Remove iasl BuildRequires -- 170dc1cbe0 spec: Remove redundant 0 in conditionals -- 8718f6fa11 spec: Add more have_XXX conditionals -- a001269ce9 spec: Remove binutils versioned Requires -- 34545ee641 spec: Remove diffutils BuildRequires -- c2c82beac9 spec: Remove redundant Requires: -- 9314c231f4 spec: Add XXX_version macros -- c43db0bf0f spec: Add have_block_rbd -- 3ecb0c0319 qga: drop StandardError=syslog -- 018049dc80 Remove iscsi support -- a2edf18777 redhat: Replace the kvm-setup.service with a /etc/modules-load.d config file -- 387b5fbcfe redhat: Move qemu-kvm-docs dependency to qemu-kvm -- 4ead693178 redhat: introducting qemu-kvm-hw-usbredir -- 4dc6fc3035 redhat: use the standard vhost-user JSON path -- 84757178b4 Fix local build -- 8c394227dd spec: Restrict block drivers in tools -- b6aa7c1fae Move tools to separate package -- eafd82e509 Split qemu-pr-helper to separate package -- 2c0182e2aa spec: RPM_BUILD_ROOT -> %{buildroot} -- 91bd55ca13 spec: More use of %{name} instead of 'qemu-kvm' -- 50ba299c61 spec: Use qemu-pr-helper.service from qemu.git (partial) -- ee08d4e0a3 spec: Use %{_sourcedir} for referencing sources -- 039e7f7d02 spec: Add tools_only -- 884ba71617 spec: %build: Add run_configure helper -- 8ebd864d65 spec: %build: Disable more bits with %{disable_everything} (partial) -- f23fdb53f5 spec: %build: Add macros for some 'configure' parameters -- fe951a8bd8 spec: %files: Move qemu-guest-agent and qemu-img earlier -- 353b632e37 spec: %install: Remove redundant bits -- 9d2015b752 spec: %install: Add %{modprobe_kvm_conf} macro -- 6d05134e8c spec: %install: Remove qemu-guest-agent /etc/qemu-kvm usage -- 985b226467 spec: %install: clean up qemu-ga section -- dfaf9c600d spec: %install: Use a single %{tools_only} section -- f6978ddb46 spec: Make tools_only not cross spec sections -- 071c211098 spec: %install: Limit time spent in %{qemu_kvm_build} -- 1b65c674be spec: misc syntactic merges with Fedora -- 4da16294cf spec: Use Fedora's pattern for specifying rc version -- d7ee259a79 spec: %files: don't use fine grained -docs file list -- 64cad0c60f spec: %files: Add licenses to qemu-common too -- c3de4f080a spec: %install: Drop python3 shebang fixup -- 46fc216115 Update local build to work with spec file improvements -- bab9531548 spec: Remove buildldflags -- c8360ab6a9 spec: Use %make_build macro -- f6966c66e9 spec: Drop make install sharedir and datadir usage -- 86982421bc spec: use %make_install macro -- 191c405d22 spec: parallelize `make check` -- 251a1fb958 spec: Drop explicit --build-id -- 44c7dda6c3 spec: use %{build_ldflags} -- 0009a34354 Move virtiofsd to separate package -- 34d1b200b3 Utilize --firmware configure option -- 2800e1dd03 spec: Switch toolchain to Clang/LLVM (except process-patches.sh) -- e8a70f500f spec: Use safe-stack for x86_64 -- e29445d50d spec: Reenable write support for VMDK etc. in tools -- a4fe2a3e16 redhat: Disable LTO on non-x86 architectures - -Merged patches (6.2.0): -- 333452440b remove sgabios dependency -- 7d3633f184 enable pulseaudio -- bd898709b0 spec: disable use of gcrypt for crypto backends in favour of gnutls -- e4f0c6dee6 spec: Remove block-curl and block-ssh dependency -- 4dc13bfe63 spec: Build the VDI block driver -- d2f2ff3c74 spec: Explicitly include compress filter -- a7d047f9c2 Move ksmtuned files to separate package - -With rebase new configure options are introducesed. We use two steps -configuration - first we disable all options and then enable supported -options. - -With 6.2.0, following changes are done: -- disabled all audiodev and enable only pa - - not use audio-drv-list anymore - - disabling oss driver removes oss module (added during rebase to 6.2.0) -- disable gettext -- disable l2tpv3 -- enable selinux -- enable spice-protocol - - added needed BuildRequire -- specify used capstone version -- specify used fdt version - -Signed-off-by: Miroslav Rezanina ---- - .distro/85-kvm.preset | 5 - - .distro/Makefile | 100 + - .distro/Makefile.common | 38 + - .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 | 3817 +++++++++++++++++++++++ - .distro/scripts/extract_build_cmd.py | 12 + - .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 +- - 24 files changed, 4066 insertions(+), 338 deletions(-) - delete mode 100644 .distro/85-kvm.preset - 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 - create mode 100644 scripts/systemtap/conf.d/qemu_kvm.conf - create mode 100644 scripts/systemtap/script.d/qemu_kvm.stp - -diff --git a/README.systemtap b/README.systemtap -new file mode 100644 -index 0000000000..ad913fc990 ---- /dev/null -+++ b/README.systemtap -@@ -0,0 +1,43 @@ -+QEMU tracing using systemtap-initscript -+--------------------------------------- -+ -+You can capture QEMU trace data all the time using systemtap-initscript. This -+uses SystemTap's flight recorder mode to trace all running guests to a -+fixed-size buffer on the host. Old trace entries are overwritten by new -+entries when the buffer size wraps. -+ -+1. Install the systemtap-initscript package: -+ # yum install systemtap-initscript -+ -+2. Install the systemtap scripts and the conf file: -+ # cp /usr/share/qemu-kvm/systemtap/script.d/qemu_kvm.stp /etc/systemtap/script.d/ -+ # cp /usr/share/qemu-kvm/systemtap/conf.d/qemu_kvm.conf /etc/systemtap/conf.d/ -+ -+The set of trace events to enable is given in qemu_kvm.stp. This SystemTap -+script can be customized to add or remove trace events provided in -+/usr/share/systemtap/tapset/qemu-kvm-simpletrace.stp. -+ -+SystemTap customizations can be made to qemu_kvm.conf to control the flight -+recorder buffer size and whether to store traces in memory only or disk too. -+See stap(1) for option documentation. -+ -+3. Start the systemtap service. -+　# service systemtap start qemu_kvm -+ -+4. Make the service start at boot time. -+　# chkconfig systemtap on -+ -+5. Confirm that the service works. -+ # service systemtap status qemu_kvm -+ qemu_kvm is running... -+ -+When you want to inspect the trace buffer, perform the following steps: -+ -+1. Dump the trace buffer. -+ # staprun -A qemu_kvm >/tmp/trace.log -+ -+2. Start the systemtap service because the preceding step stops the service. -+ # service systemtap start qemu_kvm -+ -+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 96de1a6ef9..5f6ba86dbb 100644 ---- a/meson.build -+++ b/meson.build -@@ -2108,7 +2108,9 @@ 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 -+++ b/scripts/qemu-guest-agent/fsfreeze-hook -@@ -8,7 +8,7 @@ - # request, it is issued with "thaw" argument after filesystem is thawed. - - LOGFILE=/var/log/qga-fsfreeze-hook.log --FSFREEZE_D=$(dirname -- "$0")/fsfreeze-hook.d -+FSFREEZE_D=$(dirname -- "$(realpath $0)")/fsfreeze-hook.d - - # Check whether file $1 is a backup or rpm-generated file and should be ignored - is_ignored_file() { -diff --git a/scripts/systemtap/conf.d/qemu_kvm.conf b/scripts/systemtap/conf.d/qemu_kvm.conf -new file mode 100644 -index 0000000000..372d8160a4 ---- /dev/null -+++ b/scripts/systemtap/conf.d/qemu_kvm.conf -@@ -0,0 +1,4 @@ -+# Force load uprobes (see BZ#1118352) -+stap -e 'probe process("/usr/libexec/qemu-kvm").function("main") { printf("") }' -c true -+ -+qemu_kvm_OPT="-s4" # per-CPU buffer size, in megabytes -diff --git a/scripts/systemtap/script.d/qemu_kvm.stp b/scripts/systemtap/script.d/qemu_kvm.stp -new file mode 100644 -index 0000000000..c04abf9449 ---- /dev/null -+++ b/scripts/systemtap/script.d/qemu_kvm.stp -@@ -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 f86cb863de..6d38340d49 100755 ---- a/tests/check-block.sh -+++ b/tests/check-block.sh -@@ -69,6 +69,8 @@ else - fi - fi - -+exit 0 -+ - cd tests/qemu-iotests - - # QEMU_CHECK_BLOCK_AUTO is used to disable some unstable sub-tests -diff --git a/ui/vnc-auth-sasl.c b/ui/vnc-auth-sasl.c -index 47fdae5b21..2a950caa2a 100644 ---- a/ui/vnc-auth-sasl.c -+++ b/ui/vnc-auth-sasl.c -@@ -42,7 +42,7 @@ - - bool vnc_sasl_server_init(Error **errp) - { -- int saslErr = sasl_server_init(NULL, "qemu"); -+ int saslErr = sasl_server_init(NULL, "qemu-kvm"); - - if (saslErr != SASL_OK) { - error_setg(errp, "Failed to initialize SASL auth: %s", --- -2.27.0 - diff --git a/SOURCES/0006-Enable-disable-devices-for-RHEL.patch b/SOURCES/0006-Enable-disable-devices-for-RHEL.patch deleted file mode 100644 index 345bd20..0000000 --- a/SOURCES/0006-Enable-disable-devices-for-RHEL.patch +++ /dev/null @@ -1,698 +0,0 @@ -From af4c83ed637bfda003ae86133413d53cefda3654 Mon Sep 17 00:00:00 2001 -From: Miroslav Rezanina -Date: Thu, 15 Jul 2021 03:22:36 -0400 -Subject: Enable/disable devices for RHEL - -This commit adds all changes related to changes in supported devices. - -Signed-off-by: Miroslav Rezanina --- -Rebase notes (6.1.0): -- Added CONFIG_TPM (except s390x) -- default-configs moved to configs -- Use --with-device- configure option to use rhel configs - -Rebase notes (6.2.0 RC0): -- Add CONFIG_ISA_FDC - -Rebase notes (6.2.0 RC3): -- Do not remove -no-hpet documentation - -Merged patches (6.1.0): -- c51bf45304 Remove SPICE and QXL from x86_64-rh-devices.mak -- 02fc745601 aarch64-rh-devices: add CONFIG_PVPANIC_PCI -- f2fe835153 aarch64-rh-devices: add CONFIG_PXB -- b5431733ad disable CONFIG_USB_STORAGE_BOT -- 478ba0cdf6 Disable TPM passthrough -- 2504d68a7c aarch64: Add USB storage devices -- 51c2a3253c disable ac97 audio - -Merged patches (6.2.0 RC0): -- 9f2f9fa2ba disable sga device ---- - .distro/qemu-kvm.spec.template | 9 +- - .../aarch64-softmmu/aarch64-rh-devices.mak | 33 ++++++ - .../ppc64-softmmu/ppc64-rh-devices.mak | 35 ++++++ - configs/devices/rh-virtio.mak | 10 ++ - .../s390x-softmmu/s390x-rh-devices.mak | 15 +++ - .../x86_64-softmmu/x86_64-rh-devices.mak | 102 ++++++++++++++++++ - .../x86_64-upstream-devices.mak | 4 + - hw/acpi/ich9.c | 4 +- - hw/arm/meson.build | 2 +- - hw/block/fdc.c | 10 ++ - hw/char/parallel.c | 9 ++ - hw/cpu/meson.build | 5 +- - hw/display/cirrus_vga.c | 3 + - hw/ide/piix.c | 5 +- - hw/input/pckbd.c | 2 + - hw/net/e1000.c | 2 + - hw/ppc/spapr_cpu_core.c | 2 + - hw/timer/hpet.c | 8 ++ - hw/usb/meson.build | 2 +- - target/arm/cpu_tcg.c | 10 ++ - target/ppc/cpu-models.c | 10 ++ - target/s390x/cpu_models_sysemu.c | 3 + - target/s390x/kvm/kvm.c | 8 ++ - 23 files changed, 283 insertions(+), 10 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 - create mode 100644 configs/devices/s390x-softmmu/s390x-rh-devices.mak - create mode 100644 configs/devices/x86_64-softmmu/x86_64-rh-devices.mak - create mode 100644 configs/devices/x86_64-softmmu/x86_64-upstream-devices.mak - -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..cd9c7c5127 ---- /dev/null -+++ b/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak -@@ -0,0 +1,33 @@ -+include ../rh-virtio.mak -+ -+CONFIG_ARM_GIC_KVM=y -+CONFIG_ARM_GIC=y -+CONFIG_ARM_SMMUV3=y -+CONFIG_ARM_V7M=y -+CONFIG_ARM_VIRT=y -+CONFIG_EDID=y -+CONFIG_PCIE_PORT=y -+CONFIG_PCI_DEVICES=y -+CONFIG_PCI_TESTDEV=y -+CONFIG_PFLASH_CFI01=y -+CONFIG_SCSI=y -+CONFIG_SEMIHOSTING=y -+CONFIG_USB=y -+CONFIG_USB_XHCI=y -+CONFIG_USB_XHCI_PCI=y -+CONFIG_USB_STORAGE_CORE=y -+CONFIG_USB_STORAGE_CLASSIC=y -+CONFIG_VFIO=y -+CONFIG_VFIO_PCI=y -+CONFIG_VIRTIO_MMIO=y -+CONFIG_VIRTIO_PCI=y -+CONFIG_XIO3130=y -+CONFIG_NVDIMM=y -+CONFIG_ACPI_APEI=y -+CONFIG_TPM=y -+CONFIG_TPM_EMULATOR=y -+CONFIG_TPM_TIS_SYSBUS=y -+CONFIG_PTIMER=y -+CONFIG_ARM_COMPATIBLE_SEMIHOSTING=y -+CONFIG_PVPANIC_PCI=y -+CONFIG_PXB=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 ---- /dev/null -+++ b/configs/devices/ppc64-softmmu/ppc64-rh-devices.mak -@@ -0,0 +1,35 @@ -+include ../rh-virtio.mak -+ -+CONFIG_DIMM=y -+CONFIG_MEM_DEVICE=y -+CONFIG_NVDIMM=y -+CONFIG_PCI=y -+CONFIG_PCI_DEVICES=y -+CONFIG_PCI_TESTDEV=y -+CONFIG_PCI_EXPRESS=y -+CONFIG_PSERIES=y -+CONFIG_SCSI=y -+CONFIG_SPAPR_VSCSI=y -+CONFIG_TEST_DEVICES=y -+CONFIG_USB=y -+CONFIG_USB_OHCI=y -+CONFIG_USB_OHCI_PCI=y -+CONFIG_USB_SMARTCARD=y -+CONFIG_USB_STORAGE_CORE=y -+CONFIG_USB_STORAGE_CLASSIC=y -+CONFIG_USB_XHCI=y -+CONFIG_USB_XHCI_NEC=y -+CONFIG_USB_XHCI_PCI=y -+CONFIG_VFIO=y -+CONFIG_VFIO_PCI=y -+CONFIG_VGA=y -+CONFIG_VGA_PCI=y -+CONFIG_VHOST_USER=y -+CONFIG_VIRTIO_PCI=y -+CONFIG_VIRTIO_VGA=y -+CONFIG_WDT_IB6300ESB=y -+CONFIG_XICS=y -+CONFIG_XIVE=y -+CONFIG_TPM=y -+CONFIG_TPM_SPAPR=y -+CONFIG_TPM_EMULATOR=y -diff --git a/configs/devices/rh-virtio.mak b/configs/devices/rh-virtio.mak -new file mode 100644 -index 0000000000..94ede1b5f6 ---- /dev/null -+++ b/configs/devices/rh-virtio.mak -@@ -0,0 +1,10 @@ -+CONFIG_VIRTIO=y -+CONFIG_VIRTIO_BALLOON=y -+CONFIG_VIRTIO_BLK=y -+CONFIG_VIRTIO_GPU=y -+CONFIG_VIRTIO_INPUT=y -+CONFIG_VIRTIO_INPUT_HOST=y -+CONFIG_VIRTIO_NET=y -+CONFIG_VIRTIO_RNG=y -+CONFIG_VIRTIO_SCSI=y -+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 ---- /dev/null -+++ b/configs/devices/s390x-softmmu/s390x-rh-devices.mak -@@ -0,0 +1,15 @@ -+include ../rh-virtio.mak -+ -+CONFIG_PCI=y -+CONFIG_S390_CCW_VIRTIO=y -+CONFIG_S390_FLIC=y -+CONFIG_S390_FLIC_KVM=y -+CONFIG_SCLPCONSOLE=y -+CONFIG_SCSI=y -+CONFIG_VFIO=y -+CONFIG_VFIO_AP=y -+CONFIG_VFIO_CCW=y -+CONFIG_VFIO_PCI=y -+CONFIG_VHOST_USER=y -+CONFIG_VIRTIO_CCW=y -+CONFIG_WDT_DIAG288=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..1f7a9ab024 ---- /dev/null -+++ b/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak -@@ -0,0 +1,102 @@ -+include ../rh-virtio.mak -+include x86_64-upstream-devices.mak -+ -+CONFIG_ACPI=y -+CONFIG_ACPI_PCI=y -+CONFIG_ACPI_CPU_HOTPLUG=y -+CONFIG_ACPI_MEMORY_HOTPLUG=y -+CONFIG_ACPI_NVDIMM=y -+CONFIG_ACPI_SMBUS=y -+CONFIG_ACPI_VMGENID=y -+CONFIG_ACPI_X86=y -+CONFIG_ACPI_X86_ICH=y -+CONFIG_AHCI=y -+CONFIG_APIC=y -+CONFIG_APM=y -+CONFIG_BOCHS_DISPLAY=y -+CONFIG_DIMM=y -+CONFIG_E1000E_PCI_EXPRESS=y -+CONFIG_E1000_PCI=y -+CONFIG_EDU=y -+CONFIG_FDC=y -+CONFIG_FDC_SYSBUS=y -+CONFIG_FDC_ISA=y -+CONFIG_FW_CFG_DMA=y -+CONFIG_HDA=y -+CONFIG_HYPERV=y -+CONFIG_HYPERV_TESTDEV=y -+CONFIG_I2C=y -+CONFIG_I440FX=y -+CONFIG_I8254=y -+CONFIG_I8257=y -+CONFIG_I8259=y -+CONFIG_I82801B11=y -+CONFIG_IDE_CORE=y -+CONFIG_IDE_PCI=y -+CONFIG_IDE_PIIX=y -+CONFIG_IDE_QDEV=y -+CONFIG_IOAPIC=y -+CONFIG_IOH3420=y -+CONFIG_ISA_BUS=y -+CONFIG_ISA_DEBUG=y -+CONFIG_ISA_TESTDEV=y -+CONFIG_LPC_ICH9=y -+CONFIG_MC146818RTC=y -+CONFIG_MEM_DEVICE=y -+CONFIG_NVDIMM=y -+CONFIG_OPENGL=y -+CONFIG_PAM=y -+CONFIG_PC=y -+CONFIG_PCI=y -+CONFIG_PCIE_PORT=y -+CONFIG_PCI_DEVICES=y -+CONFIG_PCI_EXPRESS=y -+CONFIG_PCI_EXPRESS_Q35=y -+CONFIG_PCI_I440FX=y -+CONFIG_PCI_TESTDEV=y -+CONFIG_PCKBD=y -+CONFIG_PCSPK=y -+CONFIG_PC_ACPI=y -+CONFIG_PC_PCI=y -+CONFIG_PFLASH_CFI01=y -+CONFIG_PVPANIC_ISA=y -+CONFIG_PXB=y -+CONFIG_Q35=y -+CONFIG_RTL8139_PCI=y -+CONFIG_SCSI=y -+CONFIG_SERIAL=y -+CONFIG_SERIAL_ISA=y -+CONFIG_SERIAL_PCI=y -+CONFIG_SEV=y -+CONFIG_SMBIOS=y -+CONFIG_SMBUS_EEPROM=y -+CONFIG_TEST_DEVICES=y -+CONFIG_USB=y -+CONFIG_USB_EHCI=y -+CONFIG_USB_EHCI_PCI=y -+CONFIG_USB_SMARTCARD=y -+CONFIG_USB_STORAGE_CORE=y -+CONFIG_USB_STORAGE_CLASSIC=y -+CONFIG_USB_UHCI=y -+CONFIG_USB_XHCI=y -+CONFIG_USB_XHCI_NEC=y -+CONFIG_USB_XHCI_PCI=y -+CONFIG_VFIO=y -+CONFIG_VFIO_PCI=y -+CONFIG_VGA=y -+CONFIG_VGA_CIRRUS=y -+CONFIG_VGA_PCI=y -+CONFIG_VHOST_USER=y -+CONFIG_VHOST_USER_BLK=y -+CONFIG_VIRTIO_PCI=y -+CONFIG_VIRTIO_VGA=y -+CONFIG_VMMOUSE=y -+CONFIG_VMPORT=y -+CONFIG_VTD=y -+CONFIG_WDT_IB6300ESB=y -+CONFIG_WDT_IB700=y -+CONFIG_XIO3130=y -+CONFIG_TPM=y -+CONFIG_TPM_CRB=y -+CONFIG_TPM_TIS_ISA=y -+CONFIG_TPM_EMULATOR=y -diff --git a/configs/devices/x86_64-softmmu/x86_64-upstream-devices.mak b/configs/devices/x86_64-softmmu/x86_64-upstream-devices.mak -new file mode 100644 -index 0000000000..2cd20f54d2 ---- /dev/null -+++ b/configs/devices/x86_64-softmmu/x86_64-upstream-devices.mak -@@ -0,0 +1,4 @@ -+# We need "isa-parallel" -+CONFIG_PARALLEL=y -+# We need "hpet" -+CONFIG_HPET=y -diff --git a/hw/acpi/ich9.c b/hw/acpi/ich9.c -index ebe08ed831..381ef2ddcf 100644 ---- a/hw/acpi/ich9.c -+++ b/hw/acpi/ich9.c -@@ -438,8 +438,8 @@ 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; -diff --git a/hw/arm/meson.build b/hw/arm/meson.build -index 721a8eb8be..87ed4dd914 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')) - arm_ss.add(when: 'CONFIG_ZYNQ', if_true: files('xilinx_zynq.c')) - arm_ss.add(when: 'CONFIG_SABRELITE', if_true: files('sabrelite.c')) - --arm_ss.add(when: 'CONFIG_ARM_V7M', if_true: files('armv7m.c')) -+#arm_ss.add(when: 'CONFIG_ARM_V7M', if_true: files('armv7m.c')) - arm_ss.add(when: 'CONFIG_EXYNOS4', if_true: files('exynos4210.c')) - 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 21d18ac2e3..97fa6de423 100644 ---- a/hw/block/fdc.c -+++ b/hw/block/fdc.c -@@ -48,6 +48,8 @@ - #include "qom/object.h" - #include "fdc-internal.h" - -+#include "hw/boards.h" -+ - /********************************************************/ - /* debug Floppy devices */ - -@@ -2337,6 +2339,14 @@ void fdctrl_realize_common(DeviceState *dev, FDCtrl *fdctrl, Error **errp) - FDrive *drive; - static int command_tables_inited = 0; - -+ /* Restricted for Red Hat Enterprise Linux: */ -+ MachineClass *mc = MACHINE_GET_CLASS(qdev_get_machine()); -+ if (!strstr(mc->name, "-rhel7.")) { -+ error_setg(errp, "Device %s is not supported with machine type %s", -+ object_get_typename(OBJECT(dev)), mc->name); -+ return; -+ } -+ - if (fdctrl->fallback == FLOPPY_DRIVE_TYPE_AUTO) { - error_setg(errp, "Cannot choose a fallback FDrive type of 'auto'"); - return; -diff --git a/hw/char/parallel.c b/hw/char/parallel.c -index b45e67bfbb..e5f108211b 100644 ---- a/hw/char/parallel.c -+++ b/hw/char/parallel.c -@@ -29,6 +29,7 @@ - #include "chardev/char-parallel.h" - #include "chardev/char-fe.h" - #include "hw/acpi/aml-build.h" -+#include "hw/boards.h" - #include "hw/irq.h" - #include "hw/isa/isa.h" - #include "hw/qdev-properties.h" -@@ -534,6 +535,14 @@ static void parallel_isa_realizefn(DeviceState *dev, Error **errp) - int base; - uint8_t dummy; - -+ /* Restricted for Red Hat Enterprise Linux */ -+ MachineClass *mc = MACHINE_GET_CLASS(qdev_get_machine()); -+ if (strstr(mc->name, "rhel")) { -+ error_setg(errp, "Device %s is not supported with machine type %s", -+ object_get_typename(OBJECT(dev)), mc->name); -+ return; -+ } -+ - if (!qemu_chr_fe_backend_connected(&s->chr)) { - error_setg(errp, "Can't create parallel device, empty char device"); - return; -diff --git a/hw/cpu/meson.build b/hw/cpu/meson.build -index 9e52fee9e7..bb71c9f3e7 100644 ---- a/hw/cpu/meson.build -+++ b/hw/cpu/meson.build -@@ -1,6 +1,7 @@ --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 fdca6ca659..fa1a7eee51 100644 ---- a/hw/display/cirrus_vga.c -+++ b/hw/display/cirrus_vga.c -@@ -2945,6 +2945,9 @@ static void pci_cirrus_vga_realize(PCIDevice *dev, Error **errp) - PCIDeviceClass *pc = PCI_DEVICE_GET_CLASS(dev); - int16_t device_id = pc->device_id; - -+ warn_report("'cirrus-vga' is deprecated, " -+ "please use a different VGA card instead"); -+ - /* follow real hardware, cirrus card emulated has 4 MB video memory. - Also accept 8 MB/16 MB for backward compatibility. */ - if (s->vga.vram_size_mb != 4 && s->vga.vram_size_mb != 8 && -diff --git a/hw/ide/piix.c b/hw/ide/piix.c -index ce89fd0aa3..fbcf802b13 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) - k->device_id = PCI_DEVICE_ID_INTEL_82371SB_1; - k->class_id = PCI_CLASS_STORAGE_IDE; - set_bit(DEVICE_CATEGORY_STORAGE, dc->categories); -- dc->hotpluggable = false; -+ /* Disabled for Red Hat Enterprise Linux: */ -+ dc->user_creatable = false; - } - - static const TypeInfo piix3_ide_info = { -@@ -261,6 +262,8 @@ 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; -+ /* Disabled for Red Hat Enterprise Linux: */ -+ dc->user_creatable = false; - } - - static const TypeInfo piix4_ide_info = { -diff --git a/hw/input/pckbd.c b/hw/input/pckbd.c -index baba62f357..bc360347ea 100644 ---- a/hw/input/pckbd.c -+++ b/hw/input/pckbd.c -@@ -796,6 +796,8 @@ static void i8042_class_initfn(ObjectClass *klass, void *data) - dc->vmsd = &vmstate_kbd_isa; - isa->build_aml = i8042_build_aml; - set_bit(DEVICE_CATEGORY_INPUT, dc->categories); -+ /* Disabled for Red Hat Enterprise Linux: */ -+ dc->user_creatable = false; - } - - static const TypeInfo i8042_info = { -diff --git a/hw/net/e1000.c b/hw/net/e1000.c -index f5bc81296d..282d01e374 100644 ---- a/hw/net/e1000.c -+++ b/hw/net/e1000.c -@@ -1821,6 +1821,7 @@ static const E1000Info e1000_devices[] = { - .revision = 0x03, - .phy_id2 = E1000_PHY_ID2_8254xx_DEFAULT, - }, -+#if 0 /* Disabled for Red Hat Enterprise Linux 7 */ - { - .name = "e1000-82544gc", - .device_id = E1000_DEV_ID_82544GC_COPPER, -@@ -1833,6 +1834,7 @@ static const E1000Info e1000_devices[] = { - .revision = 0x03, - .phy_id2 = E1000_PHY_ID2_8254xx_DEFAULT, - }, -+#endif - }; - - static void e1000_register_types(void) -diff --git a/hw/ppc/spapr_cpu_core.c b/hw/ppc/spapr_cpu_core.c -index 58e7341cb7..8ba34f6a1d 100644 ---- a/hw/ppc/spapr_cpu_core.c -+++ b/hw/ppc/spapr_cpu_core.c -@@ -370,10 +370,12 @@ static const TypeInfo spapr_cpu_core_type_infos[] = { - .instance_size = sizeof(SpaprCpuCore), - .class_size = sizeof(SpaprCpuCoreClass), - }, -+#if 0 /* Disabled for Red Hat Enterprise Linux */ - DEFINE_SPAPR_CPU_CORE_TYPE("970_v2.2"), - DEFINE_SPAPR_CPU_CORE_TYPE("970mp_v1.0"), - DEFINE_SPAPR_CPU_CORE_TYPE("970mp_v1.1"), - DEFINE_SPAPR_CPU_CORE_TYPE("power5+_v2.1"), -+#endif - DEFINE_SPAPR_CPU_CORE_TYPE("power7_v2.3"), - DEFINE_SPAPR_CPU_CORE_TYPE("power7+_v2.1"), - DEFINE_SPAPR_CPU_CORE_TYPE("power8_v2.0"), -diff --git a/hw/timer/hpet.c b/hw/timer/hpet.c -index 9520471be2..202e032524 100644 ---- a/hw/timer/hpet.c -+++ b/hw/timer/hpet.c -@@ -733,6 +733,14 @@ static void hpet_realize(DeviceState *dev, Error **errp) - int i; - HPETTimer *timer; - -+ /* Restricted for Red Hat Enterprise Linux */ -+ MachineClass *mc = MACHINE_GET_CLASS(qdev_get_machine()); -+ if (strstr(mc->name, "rhel")) { -+ error_setg(errp, "Device %s is not supported with machine type %s", -+ object_get_typename(OBJECT(dev)), mc->name); -+ return; -+ } -+ - if (!s->intcap) { - warn_report("Hpet's intcap not initialized"); - } -diff --git a/hw/usb/meson.build b/hw/usb/meson.build -index de853d780d..0776ae6a20 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 - if cacard.found() - usbsmartcard_ss = ss.source_set() - usbsmartcard_ss.add(when: 'CONFIG_USB_SMARTCARD', -- if_true: [cacard, files('ccid-card-emulated.c', 'ccid-card-passthru.c')]) -+ if_true: [cacard, files('ccid-card-passthru.c')]) - hw_usb_modules += {'smartcard': usbsmartcard_ss} - endif - -diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c -index 13d0e9b195..3826fa5122 100644 ---- a/target/arm/cpu_tcg.c -+++ b/target/arm/cpu_tcg.c -@@ -22,6 +22,7 @@ - /* 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) - { -@@ -375,6 +376,7 @@ 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) -@@ -400,6 +402,7 @@ 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); -@@ -445,6 +448,7 @@ 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) - { -@@ -488,6 +492,7 @@ 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); -@@ -928,6 +933,7 @@ 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 - /* -@@ -1007,6 +1013,7 @@ 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 }, -@@ -1022,7 +1029,9 @@ 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 }, -+#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, -@@ -1053,6 +1062,7 @@ static const ARMCPUInfo arm_tcg_cpus[] = { - { .name = "pxa270-b1", .initfn = pxa270b1_initfn }, - { .name = "pxa270-c0", .initfn = pxa270c0_initfn }, - { .name = "pxa270-c5", .initfn = pxa270c5_initfn }, -+#endif /* disabled for RHEL */ - #ifndef TARGET_AARCH64 - { .name = "max", .initfn = arm_max_initfn }, - #endif -diff --git a/target/ppc/cpu-models.c b/target/ppc/cpu-models.c -index 4baa111713..d779c4d1d5 100644 ---- a/target/ppc/cpu-models.c -+++ b/target/ppc/cpu-models.c -@@ -66,6 +66,7 @@ - #define POWERPC_DEF(_name, _pvr, _type, _desc) \ - POWERPC_DEF_SVR(_name, _desc, _pvr, POWERPC_SVR_NONE, _type) - -+#if 0 /* Embedded and 32-bit CPUs disabled for Red Hat Enterprise Linux */ - /* Embedded PowerPC */ - /* PowerPC 401 family */ - POWERPC_DEF("401", CPU_POWERPC_401, 401, -@@ -740,8 +741,10 @@ - "PowerPC 7447A v1.2 (G4)") - POWERPC_DEF("7457a_v1.2", CPU_POWERPC_74x7A_v12, 7455, - "PowerPC 7457A v1.2 (G4)") -+#endif - /* 64 bits PowerPC */ - #if defined(TARGET_PPC64) -+#if 0 /* Disabled for Red Hat Enterprise Linux */ - POWERPC_DEF("970_v2.2", CPU_POWERPC_970_v22, 970, - "PowerPC 970 v2.2") - POWERPC_DEF("970fx_v1.0", CPU_POWERPC_970FX_v10, 970, -@@ -760,6 +763,7 @@ - "PowerPC 970MP v1.1") - POWERPC_DEF("power5+_v2.1", CPU_POWERPC_POWER5P_v21, POWER5P, - "POWER5+ v2.1") -+#endif - POWERPC_DEF("power7_v2.3", CPU_POWERPC_POWER7_v23, POWER7, - "POWER7 v2.3") - POWERPC_DEF("power7+_v2.1", CPU_POWERPC_POWER7P_v21, POWER7, -@@ -784,6 +788,7 @@ - /* PowerPC CPU aliases */ - - PowerPCCPUAlias ppc_cpu_aliases[] = { -+#if 0 /* Embedded and 32-bit CPUs disabled for Red Hat Enterprise Linux */ - { "403", "403gc" }, - { "405", "405d4" }, - { "405cr", "405crc" }, -@@ -942,12 +947,15 @@ PowerPCCPUAlias ppc_cpu_aliases[] = { - { "7447a", "7447a_v1.2" }, - { "7457a", "7457a_v1.2" }, - { "apollo7pm", "7457a_v1.0" }, -+#endif - #if defined(TARGET_PPC64) -+#if 0 /* Disabled for Red Hat Enterprise Linux */ - { "970", "970_v2.2" }, - { "970fx", "970fx_v3.1" }, - { "970mp", "970mp_v1.1" }, - { "power5+", "power5+_v2.1" }, - { "power5gs", "power5+_v2.1" }, -+#endif - { "power7", "power7_v2.3" }, - { "power7+", "power7+_v2.1" }, - { "power8e", "power8e_v2.1" }, -@@ -957,6 +965,7 @@ PowerPCCPUAlias ppc_cpu_aliases[] = { - { "power10", "power10_v2.0" }, - #endif - -+#if 0 /* Disabled for Red Hat Enterprise Linux */ - /* Generic PowerPCs */ - #if defined(TARGET_PPC64) - { "ppc64", "970fx_v3.1" }, -@@ -964,5 +973,6 @@ PowerPCCPUAlias ppc_cpu_aliases[] = { - { "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 ---- 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, - (max_model->def->gen == model->def->gen && - max_model->def->ec_ga < model->def->ec_ga)) { - list_add_feat("type", unavailable); -+ } else if (model->def->gen < 11 && kvm_enabled()) { -+ /* Older CPU models are not supported on Red Hat Enterprise Linux */ -+ list_add_feat("type", unavailable); - } - - /* detect missing features if any to properly report them */ -diff --git a/target/s390x/kvm/kvm.c b/target/s390x/kvm/kvm.c -index 5b1fdb55c4..c52434985b 100644 ---- a/target/s390x/kvm/kvm.c -+++ b/target/s390x/kvm/kvm.c -@@ -2508,6 +2508,14 @@ void kvm_s390_apply_cpu_model(const S390CPUModel *model, Error **errp) - error_setg(errp, "KVM doesn't support CPU models"); - return; - } -+ -+ /* Older CPU models are not supported on Red Hat Enterprise Linux */ -+ if (model->def->gen < 11) { -+ error_setg(errp, "KVM: Unsupported CPU type specified: %s", -+ MACHINE(qdev_get_machine())->cpu_type); -+ return; -+ } -+ - prop.cpuid = s390_cpuid_from_cpu_model(model); - prop.ibc = s390_ibc_from_cpu_model(model); - /* configure cpu features indicated via STFL(e) */ --- -2.27.0 - diff --git a/SOURCES/0006-Machine-type-related-general-changes.patch b/SOURCES/0006-Machine-type-related-general-changes.patch new file mode 100644 index 0000000..c3b08a4 --- /dev/null +++ b/SOURCES/0006-Machine-type-related-general-changes.patch @@ -0,0 +1,619 @@ +From a525db3951dc68c469d1f51bdc69ab6e75e72c37 Mon Sep 17 00:00:00 2001 +From: Miroslav Rezanina +Date: Fri, 11 Jan 2019 09:54:45 +0100 +Subject: Machine type related general changes + +This patch is first part of original "Add RHEL machine types" patch we +split to allow easier review. It contains changes not related to any +architecture. + +Signed-off-by: Miroslav Rezanina +-- +Rebase notes (6.2.0): +- Do not duplicate minimal_version_id for piix4_pm +- Remove empty line chunks in serial.c +- Remove migration.h include in serial.c +- Update hw_compat_rhel_8_5 (from MR 66) + +Rebase notes (7.0.0): +- Remove downstream changes leftovers in hw/rtc/mc146818rtc.c +- Remove unnecessary change in hw/usb/hcd-uhci.c + +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 +- a3995e2eff Remove RHEL 7.0.0 machine type (only generic changes) +- ad3190a79b Remove RHEL 7.1.0 machine type (only generic changes) +- 84bbe15d4e Remove RHEL 7.2.0 machine type (only generic changes) +- 0215eb3356 Remove RHEL 7.3.0 machine types (only generic changes) +- af69d1ca6e Remove RHEL 7.4.0 machine types (only generic changes) +- 8f7a74ab78 Remove RHEL 7.5.0 machine types (only generic changes) + +Merged patches (6.2.0): +- d687ac13d2 redhat: Define hw_compat_rhel_8_5 + +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 +--- + hw/acpi/piix4.c | 6 +- + hw/arm/virt.c | 2 +- + hw/core/machine.c | 186 +++++++++++++++++++++++++++++++++++ + 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/timer/i8254_common.c | 2 +- + hw/usb/hcd-xhci-pci.c | 59 ++++++++--- + hw/usb/hcd-xhci-pci.h | 1 + + include/hw/boards.h | 21 ++++ + include/hw/firmware/smbios.h | 5 +- + include/hw/i386/pc.h | 3 + + 14 files changed, 316 insertions(+), 25 deletions(-) + +diff --git a/hw/acpi/piix4.c b/hw/acpi/piix4.c +index fe5625d07a..28544e78c3 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) + static const VMStateDescription vmstate_acpi = { + .name = "piix4_pm", + .version_id = 3, +- .minimum_version_id = 3, ++ .minimum_version_id = 2, + .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 +--- a/hw/arm/virt.c ++++ b/hw/arm/virt.c +@@ -1596,7 +1596,7 @@ static void virt_build_smbios(VirtMachineState *vms) + + smbios_set_defaults("QEMU", product, + vmc->smbios_old_sys_ver ? "1.0" : mc->name, false, +- true, SMBIOS_ENTRY_POINT_TYPE_64); ++ true, NULL, NULL, SMBIOS_ENTRY_POINT_TYPE_64); + + 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 +--- a/hw/core/machine.c ++++ b/hw/core/machine.c +@@ -37,6 +37,192 @@ + #include "hw/virtio/virtio.h" + #include "hw/virtio/virtio-pci.h" + ++/* ++ * Mostly the same as hw_compat_6_0 and hw_compat_6_1 ++ */ ++GlobalProperty hw_compat_rhel_8_5[] = { ++ /* hw_compat_rhel_8_5 from hw_compat_6_0 */ ++ { "gpex-pcihost", "allow-unmapped-accesses", "false" }, ++ /* hw_compat_rhel_8_5 from hw_compat_6_0 */ ++ { "i8042", "extended-state", "false"}, ++ /* hw_compat_rhel_8_5 from hw_compat_6_0 */ ++ { "nvme-ns", "eui64-default", "off"}, ++ /* hw_compat_rhel_8_5 from hw_compat_6_0 */ ++ { "e1000", "init-vet", "off" }, ++ /* hw_compat_rhel_8_5 from hw_compat_6_0 */ ++ { "e1000e", "init-vet", "off" }, ++ /* hw_compat_rhel_8_5 from hw_compat_6_0 */ ++ { "vhost-vsock-device", "seqpacket", "off" }, ++ /* hw_compat_rhel_8_5 from hw_compat_6_1 */ ++ { "vhost-user-vsock-device", "seqpacket", "off" }, ++ /* hw_compat_rhel_8_5 from hw_compat_6_1 */ ++ { "nvme-ns", "shared", "off" }, ++}; ++const size_t hw_compat_rhel_8_5_len = G_N_ELEMENTS(hw_compat_rhel_8_5); ++ ++/* ++ * Mostly the same as hw_compat_5_2 ++ */ ++GlobalProperty hw_compat_rhel_8_4[] = { ++ /* hw_compat_rhel_8_4 from hw_compat_5_2 */ ++ { "ICH9-LPC", "smm-compat", "on"}, ++ /* hw_compat_rhel_8_4 from hw_compat_5_2 */ ++ { "PIIX4_PM", "smm-compat", "on"}, ++ /* hw_compat_rhel_8_4 from hw_compat_5_2 */ ++ { "virtio-blk-device", "report-discard-granularity", "off" }, ++ /* hw_compat_rhel_8_4 from hw_compat_5_2 */ ++ /* ++ * Upstream incorrectly had "virtio-net-pci" instead of "virtio-net-pci-base", ++ * (https://bugzilla.redhat.com/show_bug.cgi?id=1999141) ++ */ ++ { "virtio-net-pci-base", "vectors", "3"}, ++}; ++const size_t hw_compat_rhel_8_4_len = G_N_ELEMENTS(hw_compat_rhel_8_4); ++ ++/* ++ * Mostly the same as hw_compat_5_1 ++ */ ++GlobalProperty hw_compat_rhel_8_3[] = { ++ /* hw_compat_rhel_8_3 from hw_compat_5_1 */ ++ { "vhost-scsi", "num_queues", "1"}, ++ /* hw_compat_rhel_8_3 from hw_compat_5_1 */ ++ { "vhost-user-blk", "num-queues", "1"}, ++ /* hw_compat_rhel_8_3 from hw_compat_5_1 */ ++ { "vhost-user-scsi", "num_queues", "1"}, ++ /* hw_compat_rhel_8_3 from hw_compat_5_1 */ ++ { "virtio-blk-device", "num-queues", "1"}, ++ /* hw_compat_rhel_8_3 from hw_compat_5_1 */ ++ { "virtio-scsi-device", "num_queues", "1"}, ++ /* hw_compat_rhel_8_3 from hw_compat_5_1 */ ++ { "nvme", "use-intel-id", "on"}, ++ /* hw_compat_rhel_8_3 from hw_compat_5_1 */ ++ { "pvpanic", "events", "1"}, /* PVPANIC_PANICKED */ ++ /* hw_compat_rhel_8_3 from hw_compat_5_1 */ ++ { "pl011", "migrate-clk", "off" }, ++ /* hw_compat_rhel_8_3 bz 1912846 */ ++ { "pci-xhci", "x-rh-late-msi-cap", "off" }, ++ /* hw_compat_rhel_8_3 from hw_compat_5_1 */ ++ { "virtio-pci", "x-ats-page-aligned", "off"}, ++}; ++const size_t hw_compat_rhel_8_3_len = G_N_ELEMENTS(hw_compat_rhel_8_3); ++ ++/* ++ * The same as hw_compat_4_2 + hw_compat_5_0 ++ */ ++GlobalProperty hw_compat_rhel_8_2[] = { ++ /* hw_compat_rhel_8_2 from hw_compat_4_2 */ ++ { "virtio-blk-device", "queue-size", "128"}, ++ /* hw_compat_rhel_8_2 from hw_compat_4_2 */ ++ { "virtio-scsi-device", "virtqueue_size", "128"}, ++ /* hw_compat_rhel_8_2 from hw_compat_4_2 */ ++ { "virtio-blk-device", "x-enable-wce-if-config-wce", "off" }, ++ /* hw_compat_rhel_8_2 from hw_compat_4_2 */ ++ { "virtio-blk-device", "seg-max-adjust", "off"}, ++ /* hw_compat_rhel_8_2 from hw_compat_4_2 */ ++ { "virtio-scsi-device", "seg_max_adjust", "off"}, ++ /* hw_compat_rhel_8_2 from hw_compat_4_2 */ ++ { "vhost-blk-device", "seg_max_adjust", "off"}, ++ /* hw_compat_rhel_8_2 from hw_compat_4_2 */ ++ { "usb-host", "suppress-remote-wake", "off" }, ++ /* hw_compat_rhel_8_2 from hw_compat_4_2 */ ++ { "usb-redir", "suppress-remote-wake", "off" }, ++ /* hw_compat_rhel_8_2 from hw_compat_4_2 */ ++ { "qxl", "revision", "4" }, ++ /* hw_compat_rhel_8_2 from hw_compat_4_2 */ ++ { "qxl-vga", "revision", "4" }, ++ /* hw_compat_rhel_8_2 from hw_compat_4_2 */ ++ { "fw_cfg", "acpi-mr-restore", "false" }, ++ /* hw_compat_rhel_8_2 from hw_compat_4_2 */ ++ { "virtio-device", "use-disabled-flag", "false" }, ++ /* hw_compat_rhel_8_2 from hw_compat_5_0 */ ++ { "pci-host-bridge", "x-config-reg-migration-enabled", "off" }, ++ /* hw_compat_rhel_8_2 from hw_compat_5_0 */ ++ { "virtio-balloon-device", "page-poison", "false" }, ++ /* hw_compat_rhel_8_2 from hw_compat_5_0 */ ++ { "vmport", "x-read-set-eax", "off" }, ++ /* hw_compat_rhel_8_2 from hw_compat_5_0 */ ++ { "vmport", "x-signal-unsupported-cmd", "off" }, ++ /* hw_compat_rhel_8_2 from hw_compat_5_0 */ ++ { "vmport", "x-report-vmx-type", "off" }, ++ /* hw_compat_rhel_8_2 from hw_compat_5_0 */ ++ { "vmport", "x-cmds-v2", "off" }, ++ /* hw_compat_rhel_8_2 from hw_compat_5_0 */ ++ { "virtio-device", "x-disable-legacy-check", "true" }, ++}; ++const size_t hw_compat_rhel_8_2_len = G_N_ELEMENTS(hw_compat_rhel_8_2); ++ ++/* ++ * The same as hw_compat_4_1 ++ */ ++GlobalProperty hw_compat_rhel_8_1[] = { ++ /* hw_compat_rhel_8_1 from hw_compat_4_1 */ ++ { "virtio-pci", "x-pcie-flr-init", "off" }, ++}; ++const size_t hw_compat_rhel_8_1_len = G_N_ELEMENTS(hw_compat_rhel_8_1); ++ ++/* The same as hw_compat_3_1 ++ * format of array has been changed by: ++ * 6c36bddf5340 ("machine: Use shorter format for GlobalProperty arrays") ++ */ ++GlobalProperty hw_compat_rhel_8_0[] = { ++ /* hw_compat_rhel_8_0 from hw_compat_3_1 */ ++ { "pcie-root-port", "x-speed", "2_5" }, ++ /* hw_compat_rhel_8_0 from hw_compat_3_1 */ ++ { "pcie-root-port", "x-width", "1" }, ++ /* hw_compat_rhel_8_0 from hw_compat_3_1 */ ++ { "memory-backend-file", "x-use-canonical-path-for-ramblock-id", "true" }, ++ /* hw_compat_rhel_8_0 from hw_compat_3_1 */ ++ { "memory-backend-memfd", "x-use-canonical-path-for-ramblock-id", "true" }, ++ /* hw_compat_rhel_8_0 from hw_compat_3_1 */ ++ { "tpm-crb", "ppi", "false" }, ++ /* hw_compat_rhel_8_0 from hw_compat_3_1 */ ++ { "tpm-tis", "ppi", "false" }, ++ /* hw_compat_rhel_8_0 from hw_compat_3_1 */ ++ { "usb-kbd", "serial", "42" }, ++ /* hw_compat_rhel_8_0 from hw_compat_3_1 */ ++ { "usb-mouse", "serial", "42" }, ++ /* hw_compat_rhel_8_0 from hw_compat_3_1 */ ++ { "usb-tablet", "serial", "42" }, ++ /* hw_compat_rhel_8_0 from hw_compat_3_1 */ ++ { "virtio-blk-device", "discard", "false" }, ++ /* hw_compat_rhel_8_0 from hw_compat_3_1 */ ++ { "virtio-blk-device", "write-zeroes", "false" }, ++ /* hw_compat_rhel_8_0 from hw_compat_4_0 */ ++ { "VGA", "edid", "false" }, ++ /* hw_compat_rhel_8_0 from hw_compat_4_0 */ ++ { "secondary-vga", "edid", "false" }, ++ /* hw_compat_rhel_8_0 from hw_compat_4_0 */ ++ { "bochs-display", "edid", "false" }, ++ /* hw_compat_rhel_8_0 from hw_compat_4_0 */ ++ { "virtio-vga", "edid", "false" }, ++ /* hw_compat_rhel_8_0 from hw_compat_4_0 */ ++ { "virtio-gpu-device", "edid", "false" }, ++ /* hw_compat_rhel_8_0 from hw_compat_4_0 */ ++ { "virtio-device", "use-started", "false" }, ++ /* hw_compat_rhel_8_0 from hw_compat_3_1 - that was added in 4.1 */ ++ { "pcie-root-port-base", "disable-acs", "true" }, ++}; ++const size_t hw_compat_rhel_8_0_len = G_N_ELEMENTS(hw_compat_rhel_8_0); ++ ++/* The same as hw_compat_3_0 + hw_compat_2_12 ++ * except that ++ * there's nothing in 3_0 ++ * migration.decompress-error-check=off was in 7.5 from bz 1584139 ++ */ ++GlobalProperty hw_compat_rhel_7_6[] = { ++ /* hw_compat_rhel_7_6 from hw_compat_2_12 */ ++ { "hda-audio", "use-timer", "false" }, ++ /* hw_compat_rhel_7_6 from hw_compat_2_12 */ ++ { "cirrus-vga", "global-vmstate", "true" }, ++ /* hw_compat_rhel_7_6 from hw_compat_2_12 */ ++ { "VGA", "global-vmstate", "true" }, ++ /* hw_compat_rhel_7_6 from hw_compat_2_12 */ ++ { "vmware-svga", "global-vmstate", "true" }, ++ /* hw_compat_rhel_7_6 from hw_compat_2_12 */ ++ { "qxl-vga", "global-vmstate", "true" }, ++}; ++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"}, + }; +diff --git a/hw/display/vga-isa.c b/hw/display/vga-isa.c +index 46abbc5653..505467059b 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) + } + + static Property vga_isa_properties[] = { +- DEFINE_PROP_UINT32("vgamem_mb", ISAVGAState, state.vram_size_mb, 8), ++ DEFINE_PROP_UINT32("vgamem_mb", ISAVGAState, state.vram_size_mb, 16), + DEFINE_PROP_END_OF_LIST(), + }; + +diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c +index b72c03d0a6..c797e98312 100644 +--- a/hw/i386/pc_piix.c ++++ b/hw/i386/pc_piix.c +@@ -177,6 +177,8 @@ 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, ++ pcmc->smbios_stream_product, ++ pcmc->smbios_stream_version, + pcms->smbios_entry_point_type); + } + +diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c +index 1780f79bc1..b695f88c45 100644 +--- a/hw/i386/pc_q35.c ++++ b/hw/i386/pc_q35.c +@@ -200,6 +200,8 @@ 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, ++ pcmc->smbios_stream_product, ++ pcmc->smbios_stream_version, + pcms->smbios_entry_point_type); + } + +diff --git a/hw/net/rtl8139.c b/hw/net/rtl8139.c +index 6b65823b4b..75dacabc43 100644 +--- a/hw/net/rtl8139.c ++++ b/hw/net/rtl8139.c +@@ -3179,7 +3179,7 @@ static int rtl8139_pre_save(void *opaque) + + static const VMStateDescription vmstate_rtl8139 = { + .name = "rtl8139", +- .version_id = 5, ++ .version_id = 4, + .minimum_version_id = 3, + .post_load = rtl8139_post_load, + .pre_save = rtl8139_pre_save, +@@ -3260,7 +3260,9 @@ static const VMStateDescription vmstate_rtl8139 = { + VMSTATE_UINT32(tally_counters.TxMCol, RTL8139State), + VMSTATE_UINT64(tally_counters.RxOkPhy, RTL8139State), + VMSTATE_UINT64(tally_counters.RxOkBrd, RTL8139State), ++#if 0 /* Disabled for Red Hat Enterprise Linux bz 1420195 */ + VMSTATE_UINT32_V(tally_counters.RxOkMul, RTL8139State, 5), ++#endif + VMSTATE_UINT16(tally_counters.TxAbt, RTL8139State), + VMSTATE_UINT16(tally_counters.TxUndrn, RTL8139State), + +diff --git a/hw/smbios/smbios.c b/hw/smbios/smbios.c +index 60349ee402..0edcc98434 100644 +--- a/hw/smbios/smbios.c ++++ b/hw/smbios/smbios.c +@@ -57,6 +57,9 @@ static bool smbios_legacy = true; + static bool smbios_uuid_encoded = true; + /* end: legacy structures & constants for <= 2.0 machines */ + ++/* Set to true for modern Windows 10 HardwareID-6 compat */ ++static bool smbios_type2_required; ++ + + uint8_t *smbios_tables; + size_t smbios_tables_len; +@@ -639,7 +642,7 @@ static void smbios_build_type_1_table(void) + + static void smbios_build_type_2_table(void) + { +- SMBIOS_BUILD_TABLE_PRE(2, T2_BASE, false); /* optional */ ++ SMBIOS_BUILD_TABLE_PRE(2, T2_BASE, smbios_type2_required); + + 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) + + void smbios_set_defaults(const char *manufacturer, const char *product, + const char *version, bool legacy_mode, +- bool uuid_encoded, SmbiosEntryPointType ep_type) ++ bool uuid_encoded, ++ const char *stream_product, ++ const char *stream_version, ++ SmbiosEntryPointType ep_type) + { + smbios_have_defaults = true; + smbios_legacy = legacy_mode; +@@ -935,11 +941,45 @@ void smbios_set_defaults(const char *manufacturer, const char *product, + g_free(smbios_entries); + } + ++ /* ++ * If @stream_product & @stream_version are non-NULL, then ++ * we're following rules for new Windows driver support. ++ * The data we have to report is defined in this doc: ++ * ++ * https://docs.microsoft.com/en-us/windows-hardware/drivers/install/specifying-hardware-ids-for-a-computer ++ * ++ * The Windows drivers are written to expect use of the ++ * scheme documented as "HardwareID-6" against Windows 10, ++ * which uses SMBIOS System (Type 1) and Base Board (Type 2) ++ * tables and will match on ++ * ++ * System Manufacturer = Red Hat (@manufacturer) ++ * System SKU Number = 8.2.0 (@stream_version) ++ * Baseboard Manufacturer = Red Hat (@manufacturer) ++ * Baseboard Product = RHEL-AV (@stream_product) ++ * ++ * NB, SKU must be changed with each RHEL-AV release ++ * ++ * Other fields can be freely used by applications using ++ * QEMU. For example apps can use the "System product" ++ * and "System version" to identify themselves. ++ * ++ * We get 'System Manufacturer' and 'Baseboard Manufacturer' ++ */ + SMBIOS_SET_DEFAULT(type1.manufacturer, manufacturer); + SMBIOS_SET_DEFAULT(type1.product, product); + SMBIOS_SET_DEFAULT(type1.version, version); ++ SMBIOS_SET_DEFAULT(type1.family, "Red Hat Enterprise Linux"); ++ if (stream_version != NULL) { ++ SMBIOS_SET_DEFAULT(type1.sku, stream_version); ++ } + SMBIOS_SET_DEFAULT(type2.manufacturer, manufacturer); +- SMBIOS_SET_DEFAULT(type2.product, product); ++ if (stream_product != NULL) { ++ SMBIOS_SET_DEFAULT(type2.product, stream_product); ++ smbios_type2_required = true; ++ } else { ++ SMBIOS_SET_DEFAULT(type2.product, product); ++ } + SMBIOS_SET_DEFAULT(type2.version, version); + SMBIOS_SET_DEFAULT(type3.manufacturer, manufacturer); + SMBIOS_SET_DEFAULT(type3.version, version); +diff --git a/hw/timer/i8254_common.c b/hw/timer/i8254_common.c +index 050875b497..32935da46c 100644 +--- a/hw/timer/i8254_common.c ++++ b/hw/timer/i8254_common.c +@@ -231,7 +231,7 @@ static const VMStateDescription vmstate_pit_common = { + .pre_save = pit_dispatch_pre_save, + .post_load = pit_dispatch_post_load, + .fields = (VMStateField[]) { +- VMSTATE_UINT32_V(channels[0].irq_disabled, PITCommonState, 3), ++ VMSTATE_UINT32(channels[0].irq_disabled, PITCommonState), /* qemu-kvm's v2 had 'flags' here */ + VMSTATE_STRUCT_ARRAY(channels, PITCommonState, 3, 2, + vmstate_pit_channel, PITChannelState), + VMSTATE_INT64(channels[0].next_transition_time, +diff --git a/hw/usb/hcd-xhci-pci.c b/hw/usb/hcd-xhci-pci.c +index e934b1a5b1..e18b05e528 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) + return 0; + } + ++/* RH bz 1912846 */ ++static bool usb_xhci_pci_add_msi(struct PCIDevice *dev, Error **errp) ++{ ++ int ret; ++ Error *err = NULL; ++ XHCIPciState *s = XHCI_PCI(dev); ++ ++ ret = msi_init(dev, 0x70, s->xhci.numintrs, true, false, &err); ++ /* ++ * Any error other than -ENOTSUP(board's MSI support is broken) ++ * is a programming error ++ */ ++ assert(!ret || ret == -ENOTSUP); ++ if (ret && s->msi == ON_OFF_AUTO_ON) { ++ /* Can't satisfy user's explicit msi=on request, fail */ ++ error_append_hint(&err, "You have to use msi=auto (default) or " ++ "msi=off with this machine type.\n"); ++ error_propagate(errp, err); ++ return true; ++ } ++ assert(!err || s->msi == ON_OFF_AUTO_AUTO); ++ /* With msi=auto, we fall back to MSI off silently */ ++ error_free(err); ++ ++ return false; ++} ++ + static void usb_xhci_pci_realize(struct PCIDevice *dev, Error **errp) + { + int ret; +@@ -125,23 +152,12 @@ static void usb_xhci_pci_realize(struct PCIDevice *dev, Error **errp) + s->xhci.nec_quirks = true; + } + +- if (s->msi != ON_OFF_AUTO_OFF) { +- ret = msi_init(dev, 0x70, s->xhci.numintrs, true, false, &err); +- /* +- * Any error other than -ENOTSUP(board's MSI support is broken) +- * is a programming error +- */ +- assert(!ret || ret == -ENOTSUP); +- if (ret && s->msi == ON_OFF_AUTO_ON) { +- /* Can't satisfy user's explicit msi=on request, fail */ +- error_append_hint(&err, "You have to use msi=auto (default) or " +- "msi=off with this machine type.\n"); ++ if (s->msi != ON_OFF_AUTO_OFF && s->rh_late_msi_cap) { ++ /* This gives the behaviour from 5.2.0 onwards, lspci shows 90,a0,70 */ ++ if (usb_xhci_pci_add_msi(dev, &err)) { + error_propagate(errp, err); + return; + } +- assert(!err || s->msi == ON_OFF_AUTO_AUTO); +- /* With msi=auto, we fall back to MSI off silently */ +- error_free(err); + } + pci_register_bar(dev, 0, + PCI_BASE_ADDRESS_SPACE_MEMORY | +@@ -154,6 +170,14 @@ static void usb_xhci_pci_realize(struct PCIDevice *dev, Error **errp) + assert(ret > 0); + } + ++ /* RH bz 1912846 */ ++ if (s->msi != ON_OFF_AUTO_OFF && !s->rh_late_msi_cap) { ++ /* This gives the older RH machine behaviour, lspci shows 90,70,a0 */ ++ if (usb_xhci_pci_add_msi(dev, &err)) { ++ error_propagate(errp, err); ++ return; ++ } ++ } + if (s->msix != ON_OFF_AUTO_OFF) { + /* TODO check for errors, and should fail when msix=on */ + msix_init(dev, s->xhci.numintrs, +@@ -198,11 +222,18 @@ static void xhci_instance_init(Object *obj) + qdev_alias_all_properties(DEVICE(&s->xhci), obj); + } + ++static Property xhci_pci_properties[] = { ++ /* RH bz 1912846 */ ++ DEFINE_PROP_BOOL("x-rh-late-msi-cap", XHCIPciState, rh_late_msi_cap, true), ++ DEFINE_PROP_END_OF_LIST() ++}; ++ + static void xhci_class_init(ObjectClass *klass, void *data) + { + PCIDeviceClass *k = PCI_DEVICE_CLASS(klass); + DeviceClass *dc = DEVICE_CLASS(klass); + ++ device_class_set_props(dc, xhci_pci_properties); + dc->reset = xhci_pci_reset; + dc->vmsd = &vmstate_xhci_pci; + set_bit(DEVICE_CATEGORY_USB, dc->categories); +diff --git a/hw/usb/hcd-xhci-pci.h b/hw/usb/hcd-xhci-pci.h +index c193f79443..086a1feb1e 100644 +--- a/hw/usb/hcd-xhci-pci.h ++++ b/hw/usb/hcd-xhci-pci.h +@@ -39,6 +39,7 @@ typedef struct XHCIPciState { + XHCIState xhci; + OnOffAuto msi; + OnOffAuto msix; ++ bool rh_late_msi_cap; /* bz 1912846 */ + } XHCIPciState; + + #endif +diff --git a/include/hw/boards.h b/include/hw/boards.h +index c92ac8815c..c90a19b4d1 100644 +--- a/include/hw/boards.h ++++ b/include/hw/boards.h +@@ -449,4 +449,25 @@ 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_5[]; ++extern const size_t hw_compat_rhel_8_5_len; ++ ++extern GlobalProperty hw_compat_rhel_8_4[]; ++extern const size_t hw_compat_rhel_8_4_len; ++ ++extern GlobalProperty hw_compat_rhel_8_3[]; ++extern const size_t hw_compat_rhel_8_3_len; ++ ++extern GlobalProperty hw_compat_rhel_8_2[]; ++extern const size_t hw_compat_rhel_8_2_len; ++ ++extern GlobalProperty hw_compat_rhel_8_1[]; ++extern const size_t hw_compat_rhel_8_1_len; ++ ++extern GlobalProperty hw_compat_rhel_8_0[]; ++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; ++ + #endif +diff --git a/include/hw/firmware/smbios.h b/include/hw/firmware/smbios.h +index 4b7ad77a44..9acff96a86 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); + void smbios_set_cpuid(uint32_t version, uint32_t features); + void smbios_set_defaults(const char *manufacturer, const char *product, + const char *version, bool legacy_mode, +- bool uuid_encoded, SmbiosEntryPointType ep_type); ++ bool uuid_encoded, ++ const char *stream_product, ++ const char *stream_version, ++ SmbiosEntryPointType ep_type); + uint8_t *smbios_get_table_legacy(MachineState *ms, size_t *length); + 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 +--- a/include/hw/i386/pc.h ++++ b/include/hw/i386/pc.h +@@ -113,6 +113,9 @@ struct PCMachineClass { + bool smbios_defaults; + bool smbios_legacy_mode; + bool smbios_uuid_encoded; ++ /* New fields needed for Windows HardwareID-6 matching */ ++ const char *smbios_stream_product; ++ const char *smbios_stream_version; + + /* RAM / address space compat: */ + bool gigabyte_align; +-- +2.31.1 + diff --git a/SOURCES/0007-Add-aarch64-machine-types.patch b/SOURCES/0007-Add-aarch64-machine-types.patch new file mode 100644 index 0000000..3c44b11 --- /dev/null +++ b/SOURCES/0007-Add-aarch64-machine-types.patch @@ -0,0 +1,352 @@ +From 697aaa43e3c0f20fc312f06be6c1093f1ba907e1 Mon Sep 17 00:00:00 2001 +From: Miroslav Rezanina +Date: Fri, 19 Oct 2018 12:53:31 +0200 +Subject: Add aarch64 machine types + +Adding changes to add RHEL machine types for aarch64 architecture. + +Signed-off-by: Miroslav Rezanina +--- +Rebase notes (6.1.0): +- Use CONFIG_TPM check when using TPM structures +- Add support for default_bus_bypass_iommu +- ea4c0b32d9 arm/virt: Register highmem and gic-version as class properties +- 895e1fa86a hw/arm/virt: Add 8.5 and 9.0 machine types and remove older ones + +Rebase notes (7.0.0): +- Added dtb-kaslr-seed option +- Set no_tcg_lpa2 to true + +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 + +Merged patches (7.0.0): +- 3b82be3dd3 redhat: virt-rhel8.5.0: Update machine type compatibility for QEMU 6.2.0 update +- c354a86c9b hw/arm/virt: Register "iommu" as a class property +- c1a2630dc9 hw/arm/virt: Register "its" as a class property +- 9d8c61dc93 hw/arm/virt: Rename default_bus_bypass_iommu +- 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 +--- + hw/arm/virt.c | 234 +++++++++++++++++++++++++++++++++++++++++- + include/hw/arm/virt.h | 8 ++ + 2 files changed, 241 insertions(+), 1 deletion(-) + +diff --git a/hw/arm/virt.c b/hw/arm/virt.c +index 6a84031fd7..e06862d22a 100644 +--- a/hw/arm/virt.c ++++ b/hw/arm/virt.c +@@ -80,6 +80,7 @@ + #include "hw/char/pl011.h" + #include "qemu/guest-random.h" + ++#if 0 /* Disabled for Red Hat Enterprise Linux */ + #define DEFINE_VIRT_MACHINE_LATEST(major, minor, latest) \ + static void virt_##major##_##minor##_class_init(ObjectClass *oc, \ + void *data) \ +@@ -106,7 +107,48 @@ + DEFINE_VIRT_MACHINE_LATEST(major, minor, true) + #define DEFINE_VIRT_MACHINE(major, minor) \ + DEFINE_VIRT_MACHINE_LATEST(major, minor, false) +- ++#endif /* disabled for RHEL */ ++ ++#define DEFINE_RHEL_MACHINE_LATEST(m, n, s, latest) \ ++ static void rhel##m##n##s##_virt_class_init(ObjectClass *oc, \ ++ void *data) \ ++ { \ ++ MachineClass *mc = MACHINE_CLASS(oc); \ ++ rhel##m##n##s##_virt_options(mc); \ ++ mc->desc = "RHEL " # m "." # n "." # s " ARM Virtual Machine"; \ ++ if (latest) { \ ++ mc->alias = "virt"; \ ++ mc->is_default = 1; \ ++ } \ ++ } \ ++ static const TypeInfo rhel##m##n##s##_machvirt_info = { \ ++ .name = MACHINE_TYPE_NAME("virt-rhel" # m "." # n "." # s), \ ++ .parent = TYPE_RHEL_MACHINE, \ ++ .class_init = rhel##m##n##s##_virt_class_init, \ ++ }; \ ++ static void rhel##m##n##s##_machvirt_init(void) \ ++ { \ ++ type_register_static(&rhel##m##n##s##_machvirt_info); \ ++ } \ ++ type_init(rhel##m##n##s##_machvirt_init); ++ ++#define DEFINE_RHEL_MACHINE_AS_LATEST(major, minor, subminor) \ ++ DEFINE_RHEL_MACHINE_LATEST(major, minor, subminor, true) ++#define DEFINE_RHEL_MACHINE(major, minor, subminor) \ ++ DEFINE_RHEL_MACHINE_LATEST(major, minor, subminor, false) ++ ++/* This variable is for changes to properties that are RHEL specific, ++ * different to the current upstream and to be applied to the latest ++ * machine type. ++ */ ++GlobalProperty arm_rhel_compat[] = { ++ { ++ .driver = "virtio-net-pci", ++ .property = "romfile", ++ .value = "", ++ }, ++}; ++const size_t arm_rhel_compat_len = G_N_ELEMENTS(arm_rhel_compat); + + /* Number of external interrupt lines to configure the GIC with */ + #define NUM_IRQS 256 +@@ -2250,6 +2292,7 @@ static void machvirt_init(MachineState *machine) + qemu_add_machine_init_done_notifier(&vms->machine_done); + } + ++#if 0 /* Disabled for Red Hat Enterprise Linux */ + 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) + + vms->virt = value; + } ++#endif /* disabled for RHEL */ + + static bool virt_get_highmem(Object *obj, Error **errp) + { +@@ -2402,6 +2446,7 @@ static void virt_set_ras(Object *obj, bool value, Error **errp) + vms->ras = value; + } + ++#if 0 /* Disabled for Red Hat Enterprise Linux */ + 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) + + vms->mte = value; + } ++#endif /* disabled for RHEL */ + + 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) + return fixed_ipa ? 0 : requested_pa_size; + } + ++#if 0 /* Disabled for Red Hat Enterprise Linux */ + 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) + vmc->no_pmu = true; + } + DEFINE_VIRT_MACHINE(2, 6) ++#endif /* disabled for RHEL */ ++ ++static void rhel_machine_class_init(ObjectClass *oc, void *data) ++{ ++ MachineClass *mc = MACHINE_CLASS(oc); ++ HotplugHandlerClass *hc = HOTPLUG_HANDLER_CLASS(oc); ++ ++ mc->family = "virt-rhel-Z"; ++ mc->init = machvirt_init; ++ /* Maximum supported VCPU count for all virt-rhel* machines */ ++ mc->max_cpus = 384; ++#ifdef CONFIG_TPM ++ machine_class_allow_dynamic_sysbus_dev(mc, TYPE_TPM_TIS_SYSBUS); ++#endif ++ mc->block_default_type = IF_VIRTIO; ++ mc->no_cdrom = 1; ++ mc->pci_allow_0_address = true; ++ /* We know we will never create a pre-ARMv7 CPU which needs 1K pages */ ++ mc->minimum_page_bits = 12; ++ mc->possible_cpu_arch_ids = virt_possible_cpu_arch_ids; ++ mc->cpu_index_to_instance_props = virt_cpu_index_to_props; ++ mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-a57"); ++ mc->get_default_cpu_node_id = virt_get_default_cpu_node_id; ++ mc->kvm_type = virt_kvm_type; ++ assert(!mc->get_hotplug_handler); ++ mc->get_hotplug_handler = virt_machine_get_hotplug_handler; ++ hc->pre_plug = virt_machine_device_pre_plug_cb; ++ hc->plug = virt_machine_device_plug_cb; ++ hc->unplug_request = virt_machine_device_unplug_request_cb; ++ hc->unplug = virt_machine_device_unplug_cb; ++ mc->nvdimm_supported = true; ++ mc->auto_enable_numa_with_memhp = true; ++ mc->auto_enable_numa_with_memdev = true; ++ mc->default_ram_id = "mach-virt.ram"; ++ ++ object_class_property_add(oc, "acpi", "OnOffAuto", ++ virt_get_acpi, virt_set_acpi, ++ NULL, NULL); ++ object_class_property_set_description(oc, "acpi", ++ "Enable ACPI"); ++ ++ object_class_property_add_bool(oc, "highmem", virt_get_highmem, ++ virt_set_highmem); ++ object_class_property_set_description(oc, "highmem", ++ "Set on/off to enable/disable using " ++ "physical address space above 32 bits"); ++ ++ object_class_property_add_str(oc, "gic-version", virt_get_gic_version, ++ virt_set_gic_version); ++ object_class_property_set_description(oc, "gic-version", ++ "Set GIC version. " ++ "Valid values are 2, 3, host and max"); ++ ++ object_class_property_add_str(oc, "iommu", virt_get_iommu, virt_set_iommu); ++ object_class_property_set_description(oc, "iommu", ++ "Set the IOMMU type. " ++ "Valid values are none and smmuv3"); ++ ++ object_class_property_add_bool(oc, "default-bus-bypass-iommu", ++ virt_get_default_bus_bypass_iommu, ++ virt_set_default_bus_bypass_iommu); ++ object_class_property_set_description(oc, "default-bus-bypass-iommu", ++ "Set on/off to enable/disable " ++ "bypass_iommu for default root bus"); ++ ++ object_class_property_add_bool(oc, "ras", virt_get_ras, ++ virt_set_ras); ++ object_class_property_set_description(oc, "ras", ++ "Set on/off to enable/disable reporting host memory errors " ++ "to a KVM guest using ACPI and guest external abort exceptions"); ++ ++ object_class_property_add_bool(oc, "its", virt_get_its, ++ virt_set_its); ++ object_class_property_set_description(oc, "its", ++ "Set on/off to enable/disable " ++ "ITS instantiation"); ++ ++ object_class_property_add_str(oc, "x-oem-id", ++ virt_get_oem_id, ++ virt_set_oem_id); ++ object_class_property_set_description(oc, "x-oem-id", ++ "Override the default value of field OEMID " ++ "in ACPI table header." ++ "The string may be up to 6 bytes in size"); ++ ++ ++ object_class_property_add_str(oc, "x-oem-table-id", ++ virt_get_oem_table_id, ++ virt_set_oem_table_id); ++ object_class_property_set_description(oc, "x-oem-table-id", ++ "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) ++{ ++ VirtMachineState *vms = VIRT_MACHINE(obj); ++ VirtMachineClass *vmc = VIRT_MACHINE_GET_CLASS(vms); ++ ++ /* EL3 is disabled by default and non-configurable for RHEL */ ++ vms->secure = false; ++ ++ /* EL2 is disabled by default and non-configurable for RHEL */ ++ vms->virt = false; ++ ++ /* High memory is enabled by default */ ++ vms->highmem = true; ++ vms->gic_version = VIRT_GIC_VERSION_NOSEL; ++ ++ vms->highmem_ecam = !vmc->no_highmem_ecam; ++ ++ if (vmc->no_its) { ++ vms->its = false; ++ } else { ++ /* Default allows ITS instantiation */ ++ vms->its = true; ++ ++ if (vmc->no_tcg_its) { ++ vms->tcg_its = false; ++ } else { ++ vms->tcg_its = true; ++ } ++ } ++ ++ /* Default disallows iommu instantiation */ ++ vms->iommu = VIRT_IOMMU_NONE; ++ ++ /* The default root bus is attached to iommu by default */ ++ vms->default_bus_bypass_iommu = false; ++ ++ /* Default disallows RAS instantiation and is non-configurable for RHEL */ ++ vms->ras = false; ++ ++ /* MTE is disabled by default and non-configurable for RHEL */ ++ vms->mte = false; ++ ++ /* Supply a kaslr-seed by default */ ++ vms->dtb_kaslr_seed = true; ++ ++ vms->irqmap = a15irqmap; ++ ++ virt_flash_create(vms); ++ ++ vms->oem_id = g_strndup(ACPI_BUILD_APPNAME6, 6); ++ vms->oem_table_id = g_strndup(ACPI_BUILD_APPNAME8, 8); ++} ++ ++static const TypeInfo rhel_machine_info = { ++ .name = TYPE_RHEL_MACHINE, ++ .parent = TYPE_MACHINE, ++ .abstract = true, ++ .instance_size = sizeof(VirtMachineState), ++ .class_size = sizeof(VirtMachineClass), ++ .class_init = rhel_machine_class_init, ++ .instance_init = rhel_virt_instance_init, ++ .interfaces = (InterfaceInfo[]) { ++ { TYPE_HOTPLUG_HANDLER }, ++ { } ++ }, ++}; ++ ++static void rhel_machine_init(void) ++{ ++ type_register_static(&rhel_machine_info); ++} ++type_init(rhel_machine_init); ++ ++static void rhel900_virt_options(MachineClass *mc) ++{ ++ VirtMachineClass *vmc = VIRT_MACHINE_CLASS(OBJECT_CLASS(mc)); ++ ++ compat_props_add(mc->compat_props, arm_rhel_compat, arm_rhel_compat_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 +--- a/include/hw/arm/virt.h ++++ b/include/hw/arm/virt.h +@@ -179,9 +179,17 @@ struct VirtMachineState { + + #define VIRT_ECAM_ID(high) (high ? VIRT_HIGH_PCIE_ECAM : VIRT_PCIE_ECAM) + ++#if 0 /* disabled for Red Hat Enterprise Linux */ + #define TYPE_VIRT_MACHINE MACHINE_TYPE_NAME("virt") + OBJECT_DECLARE_TYPE(VirtMachineState, VirtMachineClass, VIRT_MACHINE) + ++#else ++#define TYPE_RHEL_MACHINE MACHINE_TYPE_NAME("virt-rhel") ++typedef struct VirtMachineClass VirtMachineClass; ++typedef struct VirtMachineState VirtMachineState; ++DECLARE_OBJ_CHECKERS(VirtMachineState, VirtMachineClass, VIRT_MACHINE, TYPE_RHEL_MACHINE) ++#endif ++ + void virt_acpi_setup(VirtMachineState *vms); + bool virt_is_acpi_enabled(VirtMachineState *vms); + +-- +2.31.1 + diff --git a/SOURCES/0007-Machine-type-related-general-changes.patch b/SOURCES/0007-Machine-type-related-general-changes.patch deleted file mode 100644 index 9baf215..0000000 --- a/SOURCES/0007-Machine-type-related-general-changes.patch +++ /dev/null @@ -1,648 +0,0 @@ -From ef9b78c3f2810541eac453a3f8a8753763b1378d Mon Sep 17 00:00:00 2001 -From: Miroslav Rezanina -Date: Fri, 11 Jan 2019 09:54:45 +0100 -Subject: Machine type related general changes - -This patch is first part of original "Add RHEL machine types" patch we -split to allow easier review. It contains changes not related to any -architecture. - -Signed-off-by: Miroslav Rezanina --- -Rebase notes (6.2.0 RC0): -- Do not duplicate minimal_version_id for piix4_pm -- Remove empty line chunks in serial.c -- Remove migration.h include in serial.c - -Rebase notes (6.2.0 RC1): -- Update hw_compat_rhel_8_5 (from MR 66) - -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 -- a3995e2eff Remove RHEL 7.0.0 machine type (only generic changes) -- ad3190a79b Remove RHEL 7.1.0 machine type (only generic changes) -- 84bbe15d4e Remove RHEL 7.2.0 machine type (only generic changes) -- 0215eb3356 Remove RHEL 7.3.0 machine types (only generic changes) -- af69d1ca6e Remove RHEL 7.4.0 machine types (only generic changes) -- 8f7a74ab78 Remove RHEL 7.5.0 machine types (only generic changes) - -Merged patches (6.2.0 RC0): -- d687ac13d2 redhat: Define hw_compat_rhel_8_5 ---- - hw/acpi/piix4.c | 6 +- - hw/arm/virt.c | 2 +- - hw/core/machine.c | 180 +++++++++++++++++++++++++++++++++++ - hw/display/vga-isa.c | 2 +- - hw/i386/pc_piix.c | 2 + - hw/i386/pc_q35.c | 2 + - hw/net/rtl8139.c | 4 +- - hw/rtc/mc146818rtc.c | 2 + - hw/smbios/smbios.c | 46 ++++++++- - hw/timer/i8254_common.c | 2 +- - hw/usb/hcd-uhci.c | 4 +- - hw/usb/hcd-xhci-pci.c | 59 +++++++++--- - hw/usb/hcd-xhci-pci.h | 1 + - include/hw/boards.h | 21 ++++ - include/hw/firmware/smbios.h | 5 +- - include/hw/i386/pc.h | 3 + - 16 files changed, 315 insertions(+), 26 deletions(-) - -diff --git a/hw/acpi/piix4.c b/hw/acpi/piix4.c -index f0b5fac44a..8d6011c0a3 100644 ---- a/hw/acpi/piix4.c -+++ b/hw/acpi/piix4.c -@@ -278,7 +278,7 @@ static bool piix4_vmstate_need_smbus(void *opaque, int version_id) - static const VMStateDescription vmstate_acpi = { - .name = "piix4_pm", - .version_id = 3, -- .minimum_version_id = 3, -+ .minimum_version_id = 2, - .post_load = vmstate_acpi_post_load, - .fields = (VMStateField[]) { - VMSTATE_PCI_DEVICE(parent_obj, PIIX4PMState), -@@ -644,8 +644,8 @@ 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 30da05dfe0..5de4d9d73b 100644 ---- a/hw/arm/virt.c -+++ b/hw/arm/virt.c -@@ -1590,7 +1590,7 @@ static void virt_build_smbios(VirtMachineState *vms) - - smbios_set_defaults("QEMU", product, - vmc->smbios_old_sys_ver ? "1.0" : mc->name, false, -- true, SMBIOS_ENTRY_POINT_30); -+ true, NULL, NULL, SMBIOS_ENTRY_POINT_30); - - 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 53a99abc56..53a3caf4fb 100644 ---- a/hw/core/machine.c -+++ b/hw/core/machine.c -@@ -37,6 +37,186 @@ - #include "hw/virtio/virtio.h" - #include "hw/virtio/virtio-pci.h" - -+/* -+ * Mostly the same as hw_compat_6_0 and hw_compat_6_1 -+ */ -+GlobalProperty hw_compat_rhel_8_5[] = { -+ /* hw_compat_rhel_8_5 from hw_compat_6_0 */ -+ { "gpex-pcihost", "allow-unmapped-accesses", "false" }, -+ /* hw_compat_rhel_8_5 from hw_compat_6_0 */ -+ { "i8042", "extended-state", "false"}, -+ /* hw_compat_rhel_8_5 from hw_compat_6_0 */ -+ { "nvme-ns", "eui64-default", "off"}, -+ /* hw_compat_rhel_8_5 from hw_compat_6_0 */ -+ { "e1000", "init-vet", "off" }, -+ /* hw_compat_rhel_8_5 from hw_compat_6_0 */ -+ { "e1000e", "init-vet", "off" }, -+ /* hw_compat_rhel_8_5 from hw_compat_6_0 */ -+ { "vhost-vsock-device", "seqpacket", "off" }, -+ /* hw_compat_rhel_8_5 from hw_compat_6_1 */ -+ { "vhost-user-vsock-device", "seqpacket", "off" }, -+}; -+const size_t hw_compat_rhel_8_5_len = G_N_ELEMENTS(hw_compat_rhel_8_5); -+ -+/* -+ * Mostly the same as hw_compat_5_2 -+ */ -+GlobalProperty hw_compat_rhel_8_4[] = { -+ /* hw_compat_rhel_8_4 from hw_compat_5_2 */ -+ { "ICH9-LPC", "smm-compat", "on"}, -+ /* hw_compat_rhel_8_4 from hw_compat_5_2 */ -+ { "PIIX4_PM", "smm-compat", "on"}, -+ /* hw_compat_rhel_8_4 from hw_compat_5_2 */ -+ { "virtio-blk-device", "report-discard-granularity", "off" }, -+ /* hw_compat_rhel_8_4 from hw_compat_5_2 */ -+ { "virtio-net-pci", "vectors", "3"}, -+}; -+const size_t hw_compat_rhel_8_4_len = G_N_ELEMENTS(hw_compat_rhel_8_4); -+ -+/* -+ * Mostly the same as hw_compat_5_1 -+ */ -+GlobalProperty hw_compat_rhel_8_3[] = { -+ /* hw_compat_rhel_8_3 from hw_compat_5_1 */ -+ { "vhost-scsi", "num_queues", "1"}, -+ /* hw_compat_rhel_8_3 from hw_compat_5_1 */ -+ { "vhost-user-blk", "num-queues", "1"}, -+ /* hw_compat_rhel_8_3 from hw_compat_5_1 */ -+ { "vhost-user-scsi", "num_queues", "1"}, -+ /* hw_compat_rhel_8_3 from hw_compat_5_1 */ -+ { "virtio-blk-device", "num-queues", "1"}, -+ /* hw_compat_rhel_8_3 from hw_compat_5_1 */ -+ { "virtio-scsi-device", "num_queues", "1"}, -+ /* hw_compat_rhel_8_3 from hw_compat_5_1 */ -+ { "nvme", "use-intel-id", "on"}, -+ /* hw_compat_rhel_8_3 from hw_compat_5_1 */ -+ { "pvpanic", "events", "1"}, /* PVPANIC_PANICKED */ -+ /* hw_compat_rhel_8_3 from hw_compat_5_1 */ -+ { "pl011", "migrate-clk", "off" }, -+ /* hw_compat_rhel_8_3 bz 1912846 */ -+ { "pci-xhci", "x-rh-late-msi-cap", "off" }, -+ /* hw_compat_rhel_8_3 from hw_compat_5_1 */ -+ { "virtio-pci", "x-ats-page-aligned", "off"}, -+}; -+const size_t hw_compat_rhel_8_3_len = G_N_ELEMENTS(hw_compat_rhel_8_3); -+ -+/* -+ * The same as hw_compat_4_2 + hw_compat_5_0 -+ */ -+GlobalProperty hw_compat_rhel_8_2[] = { -+ /* hw_compat_rhel_8_2 from hw_compat_4_2 */ -+ { "virtio-blk-device", "queue-size", "128"}, -+ /* hw_compat_rhel_8_2 from hw_compat_4_2 */ -+ { "virtio-scsi-device", "virtqueue_size", "128"}, -+ /* hw_compat_rhel_8_2 from hw_compat_4_2 */ -+ { "virtio-blk-device", "x-enable-wce-if-config-wce", "off" }, -+ /* hw_compat_rhel_8_2 from hw_compat_4_2 */ -+ { "virtio-blk-device", "seg-max-adjust", "off"}, -+ /* hw_compat_rhel_8_2 from hw_compat_4_2 */ -+ { "virtio-scsi-device", "seg_max_adjust", "off"}, -+ /* hw_compat_rhel_8_2 from hw_compat_4_2 */ -+ { "vhost-blk-device", "seg_max_adjust", "off"}, -+ /* hw_compat_rhel_8_2 from hw_compat_4_2 */ -+ { "usb-host", "suppress-remote-wake", "off" }, -+ /* hw_compat_rhel_8_2 from hw_compat_4_2 */ -+ { "usb-redir", "suppress-remote-wake", "off" }, -+ /* hw_compat_rhel_8_2 from hw_compat_4_2 */ -+ { "qxl", "revision", "4" }, -+ /* hw_compat_rhel_8_2 from hw_compat_4_2 */ -+ { "qxl-vga", "revision", "4" }, -+ /* hw_compat_rhel_8_2 from hw_compat_4_2 */ -+ { "fw_cfg", "acpi-mr-restore", "false" }, -+ /* hw_compat_rhel_8_2 from hw_compat_4_2 */ -+ { "virtio-device", "use-disabled-flag", "false" }, -+ /* hw_compat_rhel_8_2 from hw_compat_5_0 */ -+ { "pci-host-bridge", "x-config-reg-migration-enabled", "off" }, -+ /* hw_compat_rhel_8_2 from hw_compat_5_0 */ -+ { "virtio-balloon-device", "page-poison", "false" }, -+ /* hw_compat_rhel_8_2 from hw_compat_5_0 */ -+ { "vmport", "x-read-set-eax", "off" }, -+ /* hw_compat_rhel_8_2 from hw_compat_5_0 */ -+ { "vmport", "x-signal-unsupported-cmd", "off" }, -+ /* hw_compat_rhel_8_2 from hw_compat_5_0 */ -+ { "vmport", "x-report-vmx-type", "off" }, -+ /* hw_compat_rhel_8_2 from hw_compat_5_0 */ -+ { "vmport", "x-cmds-v2", "off" }, -+ /* hw_compat_rhel_8_2 from hw_compat_5_0 */ -+ { "virtio-device", "x-disable-legacy-check", "true" }, -+}; -+const size_t hw_compat_rhel_8_2_len = G_N_ELEMENTS(hw_compat_rhel_8_2); -+ -+/* -+ * The same as hw_compat_4_1 -+ */ -+GlobalProperty hw_compat_rhel_8_1[] = { -+ /* hw_compat_rhel_8_1 from hw_compat_4_1 */ -+ { "virtio-pci", "x-pcie-flr-init", "off" }, -+}; -+const size_t hw_compat_rhel_8_1_len = G_N_ELEMENTS(hw_compat_rhel_8_1); -+ -+/* The same as hw_compat_3_1 -+ * format of array has been changed by: -+ * 6c36bddf5340 ("machine: Use shorter format for GlobalProperty arrays") -+ */ -+GlobalProperty hw_compat_rhel_8_0[] = { -+ /* hw_compat_rhel_8_0 from hw_compat_3_1 */ -+ { "pcie-root-port", "x-speed", "2_5" }, -+ /* hw_compat_rhel_8_0 from hw_compat_3_1 */ -+ { "pcie-root-port", "x-width", "1" }, -+ /* hw_compat_rhel_8_0 from hw_compat_3_1 */ -+ { "memory-backend-file", "x-use-canonical-path-for-ramblock-id", "true" }, -+ /* hw_compat_rhel_8_0 from hw_compat_3_1 */ -+ { "memory-backend-memfd", "x-use-canonical-path-for-ramblock-id", "true" }, -+ /* hw_compat_rhel_8_0 from hw_compat_3_1 */ -+ { "tpm-crb", "ppi", "false" }, -+ /* hw_compat_rhel_8_0 from hw_compat_3_1 */ -+ { "tpm-tis", "ppi", "false" }, -+ /* hw_compat_rhel_8_0 from hw_compat_3_1 */ -+ { "usb-kbd", "serial", "42" }, -+ /* hw_compat_rhel_8_0 from hw_compat_3_1 */ -+ { "usb-mouse", "serial", "42" }, -+ /* hw_compat_rhel_8_0 from hw_compat_3_1 */ -+ { "usb-tablet", "serial", "42" }, -+ /* hw_compat_rhel_8_0 from hw_compat_3_1 */ -+ { "virtio-blk-device", "discard", "false" }, -+ /* hw_compat_rhel_8_0 from hw_compat_3_1 */ -+ { "virtio-blk-device", "write-zeroes", "false" }, -+ /* hw_compat_rhel_8_0 from hw_compat_4_0 */ -+ { "VGA", "edid", "false" }, -+ /* hw_compat_rhel_8_0 from hw_compat_4_0 */ -+ { "secondary-vga", "edid", "false" }, -+ /* hw_compat_rhel_8_0 from hw_compat_4_0 */ -+ { "bochs-display", "edid", "false" }, -+ /* hw_compat_rhel_8_0 from hw_compat_4_0 */ -+ { "virtio-vga", "edid", "false" }, -+ /* hw_compat_rhel_8_0 from hw_compat_4_0 */ -+ { "virtio-gpu-device", "edid", "false" }, -+ /* hw_compat_rhel_8_0 from hw_compat_4_0 */ -+ { "virtio-device", "use-started", "false" }, -+ /* hw_compat_rhel_8_0 from hw_compat_3_1 - that was added in 4.1 */ -+ { "pcie-root-port-base", "disable-acs", "true" }, -+}; -+const size_t hw_compat_rhel_8_0_len = G_N_ELEMENTS(hw_compat_rhel_8_0); -+ -+/* The same as hw_compat_3_0 + hw_compat_2_12 -+ * except that -+ * there's nothing in 3_0 -+ * migration.decompress-error-check=off was in 7.5 from bz 1584139 -+ */ -+GlobalProperty hw_compat_rhel_7_6[] = { -+ /* hw_compat_rhel_7_6 from hw_compat_2_12 */ -+ { "hda-audio", "use-timer", "false" }, -+ /* hw_compat_rhel_7_6 from hw_compat_2_12 */ -+ { "cirrus-vga", "global-vmstate", "true" }, -+ /* hw_compat_rhel_7_6 from hw_compat_2_12 */ -+ { "VGA", "global-vmstate", "true" }, -+ /* hw_compat_rhel_7_6 from hw_compat_2_12 */ -+ { "vmware-svga", "global-vmstate", "true" }, -+ /* hw_compat_rhel_7_6 from hw_compat_2_12 */ -+ { "qxl-vga", "global-vmstate", "true" }, -+}; -+const size_t hw_compat_rhel_7_6_len = G_N_ELEMENTS(hw_compat_rhel_7_6); -+ - GlobalProperty hw_compat_6_1[] = { - { "vhost-user-vsock-device", "seqpacket", "off" }, - { "nvme-ns", "shared", "off" }, -diff --git a/hw/display/vga-isa.c b/hw/display/vga-isa.c -index 90851e730b..a91c5d7467 100644 ---- a/hw/display/vga-isa.c -+++ b/hw/display/vga-isa.c -@@ -85,7 +85,7 @@ static void vga_isa_realizefn(DeviceState *dev, Error **errp) - } - - static Property vga_isa_properties[] = { -- DEFINE_PROP_UINT32("vgamem_mb", ISAVGAState, state.vram_size_mb, 8), -+ DEFINE_PROP_UINT32("vgamem_mb", ISAVGAState, state.vram_size_mb, 16), - DEFINE_PROP_END_OF_LIST(), - }; - -diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c -index 223dd3e05d..dda3f64f19 100644 ---- a/hw/i386/pc_piix.c -+++ b/hw/i386/pc_piix.c -@@ -177,6 +177,8 @@ 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, -+ pcmc->smbios_stream_product, -+ pcmc->smbios_stream_version, - SMBIOS_ENTRY_POINT_21); - } - -diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c -index e1e100316d..235054a643 100644 ---- a/hw/i386/pc_q35.c -+++ b/hw/i386/pc_q35.c -@@ -200,6 +200,8 @@ 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, -+ pcmc->smbios_stream_product, -+ pcmc->smbios_stream_version, - SMBIOS_ENTRY_POINT_21); - } - -diff --git a/hw/net/rtl8139.c b/hw/net/rtl8139.c -index 90b4fc63ce..3ffb9dd22c 100644 ---- a/hw/net/rtl8139.c -+++ b/hw/net/rtl8139.c -@@ -3179,7 +3179,7 @@ static int rtl8139_pre_save(void *opaque) - - static const VMStateDescription vmstate_rtl8139 = { - .name = "rtl8139", -- .version_id = 5, -+ .version_id = 4, - .minimum_version_id = 3, - .post_load = rtl8139_post_load, - .pre_save = rtl8139_pre_save, -@@ -3260,7 +3260,9 @@ static const VMStateDescription vmstate_rtl8139 = { - VMSTATE_UINT32(tally_counters.TxMCol, RTL8139State), - VMSTATE_UINT64(tally_counters.RxOkPhy, RTL8139State), - VMSTATE_UINT64(tally_counters.RxOkBrd, RTL8139State), -+#if 0 /* Disabled for Red Hat Enterprise Linux bz 1420195 */ - VMSTATE_UINT32_V(tally_counters.RxOkMul, RTL8139State, 5), -+#endif - VMSTATE_UINT16(tally_counters.TxAbt, RTL8139State), - VMSTATE_UINT16(tally_counters.TxUndrn, RTL8139State), - -diff --git a/hw/rtc/mc146818rtc.c b/hw/rtc/mc146818rtc.c -index 4fbafddb22..6c42cc22cd 100644 ---- a/hw/rtc/mc146818rtc.c -+++ b/hw/rtc/mc146818rtc.c -@@ -43,6 +43,7 @@ - #include "qapi/qapi-events-misc-target.h" - #include "qapi/visitor.h" - #include "hw/rtc/mc146818rtc_regs.h" -+#include "migration/migration.h" - - #ifdef TARGET_I386 - #include "qapi/qapi-commands-misc-target.h" -@@ -821,6 +822,7 @@ static int rtc_post_load(void *opaque, int version_id) - static bool rtc_irq_reinject_on_ack_count_needed(void *opaque) - { - RTCState *s = (RTCState *)opaque; -+ - return s->irq_reinject_on_ack_count != 0; - } - -diff --git a/hw/smbios/smbios.c b/hw/smbios/smbios.c -index 7397e56737..3a4bb894ba 100644 ---- a/hw/smbios/smbios.c -+++ b/hw/smbios/smbios.c -@@ -57,6 +57,9 @@ static bool smbios_legacy = true; - static bool smbios_uuid_encoded = true; - /* end: legacy structures & constants for <= 2.0 machines */ - -+/* Set to true for modern Windows 10 HardwareID-6 compat */ -+static bool smbios_type2_required; -+ - - uint8_t *smbios_tables; - size_t smbios_tables_len; -@@ -619,7 +622,7 @@ static void smbios_build_type_1_table(void) - - static void smbios_build_type_2_table(void) - { -- SMBIOS_BUILD_TABLE_PRE(2, 0x200, false); /* optional */ -+ SMBIOS_BUILD_TABLE_PRE(2, 0x200, smbios_type2_required); - - SMBIOS_TABLE_SET_STR(2, manufacturer_str, type2.manufacturer); - SMBIOS_TABLE_SET_STR(2, product_str, type2.product); -@@ -888,7 +891,10 @@ 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, -- bool uuid_encoded, SmbiosEntryPointType ep_type) -+ bool uuid_encoded, -+ const char *stream_product, -+ const char *stream_version, -+ SmbiosEntryPointType ep_type) - { - smbios_have_defaults = true; - smbios_legacy = legacy_mode; -@@ -909,11 +915,45 @@ void smbios_set_defaults(const char *manufacturer, const char *product, - g_free(smbios_entries); - } - -+ /* -+ * If @stream_product & @stream_version are non-NULL, then -+ * we're following rules for new Windows driver support. -+ * The data we have to report is defined in this doc: -+ * -+ * https://docs.microsoft.com/en-us/windows-hardware/drivers/install/specifying-hardware-ids-for-a-computer -+ * -+ * The Windows drivers are written to expect use of the -+ * scheme documented as "HardwareID-6" against Windows 10, -+ * which uses SMBIOS System (Type 1) and Base Board (Type 2) -+ * tables and will match on -+ * -+ * System Manufacturer = Red Hat (@manufacturer) -+ * System SKU Number = 8.2.0 (@stream_version) -+ * Baseboard Manufacturer = Red Hat (@manufacturer) -+ * Baseboard Product = RHEL-AV (@stream_product) -+ * -+ * NB, SKU must be changed with each RHEL-AV release -+ * -+ * Other fields can be freely used by applications using -+ * QEMU. For example apps can use the "System product" -+ * and "System version" to identify themselves. -+ * -+ * We get 'System Manufacturer' and 'Baseboard Manufacturer' -+ */ - SMBIOS_SET_DEFAULT(type1.manufacturer, manufacturer); - SMBIOS_SET_DEFAULT(type1.product, product); - SMBIOS_SET_DEFAULT(type1.version, version); -+ SMBIOS_SET_DEFAULT(type1.family, "Red Hat Enterprise Linux"); -+ if (stream_version != NULL) { -+ SMBIOS_SET_DEFAULT(type1.sku, stream_version); -+ } - SMBIOS_SET_DEFAULT(type2.manufacturer, manufacturer); -- SMBIOS_SET_DEFAULT(type2.product, product); -+ if (stream_product != NULL) { -+ SMBIOS_SET_DEFAULT(type2.product, stream_product); -+ smbios_type2_required = true; -+ } else { -+ SMBIOS_SET_DEFAULT(type2.product, product); -+ } - SMBIOS_SET_DEFAULT(type2.version, version); - SMBIOS_SET_DEFAULT(type3.manufacturer, manufacturer); - SMBIOS_SET_DEFAULT(type3.version, version); -diff --git a/hw/timer/i8254_common.c b/hw/timer/i8254_common.c -index 050875b497..32935da46c 100644 ---- a/hw/timer/i8254_common.c -+++ b/hw/timer/i8254_common.c -@@ -231,7 +231,7 @@ static const VMStateDescription vmstate_pit_common = { - .pre_save = pit_dispatch_pre_save, - .post_load = pit_dispatch_post_load, - .fields = (VMStateField[]) { -- VMSTATE_UINT32_V(channels[0].irq_disabled, PITCommonState, 3), -+ VMSTATE_UINT32(channels[0].irq_disabled, PITCommonState), /* qemu-kvm's v2 had 'flags' here */ - VMSTATE_STRUCT_ARRAY(channels, PITCommonState, 3, 2, - vmstate_pit_channel, PITChannelState), - VMSTATE_INT64(channels[0].next_transition_time, -diff --git a/hw/usb/hcd-uhci.c b/hw/usb/hcd-uhci.c -index d1b5657d72..7930b868fa 100644 ---- a/hw/usb/hcd-uhci.c -+++ b/hw/usb/hcd-uhci.c -@@ -1166,11 +1166,13 @@ void usb_uhci_common_realize(PCIDevice *dev, Error **errp) - UHCIState *s = UHCI(dev); - uint8_t *pci_conf = s->dev.config; - int i; -+ int irq_pin; - - pci_conf[PCI_CLASS_PROG] = 0x00; - /* TODO: reset value should be 0. */ - pci_conf[USB_SBRN] = USB_RELEASE_1; /* release number */ -- pci_config_set_interrupt_pin(pci_conf, u->info.irq_pin + 1); -+ irq_pin = u->info.irq_pin; -+ pci_config_set_interrupt_pin(pci_conf, irq_pin + 1); - s->irq = pci_allocate_irq(dev); - - if (s->masterbus) { -diff --git a/hw/usb/hcd-xhci-pci.c b/hw/usb/hcd-xhci-pci.c -index e934b1a5b1..e18b05e528 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) - return 0; - } - -+/* RH bz 1912846 */ -+static bool usb_xhci_pci_add_msi(struct PCIDevice *dev, Error **errp) -+{ -+ int ret; -+ Error *err = NULL; -+ XHCIPciState *s = XHCI_PCI(dev); -+ -+ ret = msi_init(dev, 0x70, s->xhci.numintrs, true, false, &err); -+ /* -+ * Any error other than -ENOTSUP(board's MSI support is broken) -+ * is a programming error -+ */ -+ assert(!ret || ret == -ENOTSUP); -+ if (ret && s->msi == ON_OFF_AUTO_ON) { -+ /* Can't satisfy user's explicit msi=on request, fail */ -+ error_append_hint(&err, "You have to use msi=auto (default) or " -+ "msi=off with this machine type.\n"); -+ error_propagate(errp, err); -+ return true; -+ } -+ assert(!err || s->msi == ON_OFF_AUTO_AUTO); -+ /* With msi=auto, we fall back to MSI off silently */ -+ error_free(err); -+ -+ return false; -+} -+ - static void usb_xhci_pci_realize(struct PCIDevice *dev, Error **errp) - { - int ret; -@@ -125,23 +152,12 @@ static void usb_xhci_pci_realize(struct PCIDevice *dev, Error **errp) - s->xhci.nec_quirks = true; - } - -- if (s->msi != ON_OFF_AUTO_OFF) { -- ret = msi_init(dev, 0x70, s->xhci.numintrs, true, false, &err); -- /* -- * Any error other than -ENOTSUP(board's MSI support is broken) -- * is a programming error -- */ -- assert(!ret || ret == -ENOTSUP); -- if (ret && s->msi == ON_OFF_AUTO_ON) { -- /* Can't satisfy user's explicit msi=on request, fail */ -- error_append_hint(&err, "You have to use msi=auto (default) or " -- "msi=off with this machine type.\n"); -+ if (s->msi != ON_OFF_AUTO_OFF && s->rh_late_msi_cap) { -+ /* This gives the behaviour from 5.2.0 onwards, lspci shows 90,a0,70 */ -+ if (usb_xhci_pci_add_msi(dev, &err)) { - error_propagate(errp, err); - return; - } -- assert(!err || s->msi == ON_OFF_AUTO_AUTO); -- /* With msi=auto, we fall back to MSI off silently */ -- error_free(err); - } - pci_register_bar(dev, 0, - PCI_BASE_ADDRESS_SPACE_MEMORY | -@@ -154,6 +170,14 @@ static void usb_xhci_pci_realize(struct PCIDevice *dev, Error **errp) - assert(ret > 0); - } - -+ /* RH bz 1912846 */ -+ if (s->msi != ON_OFF_AUTO_OFF && !s->rh_late_msi_cap) { -+ /* This gives the older RH machine behaviour, lspci shows 90,70,a0 */ -+ if (usb_xhci_pci_add_msi(dev, &err)) { -+ error_propagate(errp, err); -+ return; -+ } -+ } - if (s->msix != ON_OFF_AUTO_OFF) { - /* TODO check for errors, and should fail when msix=on */ - msix_init(dev, s->xhci.numintrs, -@@ -198,11 +222,18 @@ static void xhci_instance_init(Object *obj) - qdev_alias_all_properties(DEVICE(&s->xhci), obj); - } - -+static Property xhci_pci_properties[] = { -+ /* RH bz 1912846 */ -+ DEFINE_PROP_BOOL("x-rh-late-msi-cap", XHCIPciState, rh_late_msi_cap, true), -+ DEFINE_PROP_END_OF_LIST() -+}; -+ - static void xhci_class_init(ObjectClass *klass, void *data) - { - PCIDeviceClass *k = PCI_DEVICE_CLASS(klass); - DeviceClass *dc = DEVICE_CLASS(klass); - -+ device_class_set_props(dc, xhci_pci_properties); - dc->reset = xhci_pci_reset; - dc->vmsd = &vmstate_xhci_pci; - set_bit(DEVICE_CATEGORY_USB, dc->categories); -diff --git a/hw/usb/hcd-xhci-pci.h b/hw/usb/hcd-xhci-pci.h -index c193f79443..086a1feb1e 100644 ---- a/hw/usb/hcd-xhci-pci.h -+++ b/hw/usb/hcd-xhci-pci.h -@@ -39,6 +39,7 @@ typedef struct XHCIPciState { - XHCIState xhci; - OnOffAuto msi; - OnOffAuto msix; -+ bool rh_late_msi_cap; /* bz 1912846 */ - } XHCIPciState; - - #endif -diff --git a/include/hw/boards.h b/include/hw/boards.h -index 9c1c190104..b0a6e05b48 100644 ---- a/include/hw/boards.h -+++ b/include/hw/boards.h -@@ -441,4 +441,25 @@ 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_5[]; -+extern const size_t hw_compat_rhel_8_5_len; -+ -+extern GlobalProperty hw_compat_rhel_8_4[]; -+extern const size_t hw_compat_rhel_8_4_len; -+ -+extern GlobalProperty hw_compat_rhel_8_3[]; -+extern const size_t hw_compat_rhel_8_3_len; -+ -+extern GlobalProperty hw_compat_rhel_8_2[]; -+extern const size_t hw_compat_rhel_8_2_len; -+ -+extern GlobalProperty hw_compat_rhel_8_1[]; -+extern const size_t hw_compat_rhel_8_1_len; -+ -+extern GlobalProperty hw_compat_rhel_8_0[]; -+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; -+ - #endif -diff --git a/include/hw/firmware/smbios.h b/include/hw/firmware/smbios.h -index 5a0dd0c8cf..2cb1ec2bab 100644 ---- a/include/hw/firmware/smbios.h -+++ b/include/hw/firmware/smbios.h -@@ -278,7 +278,10 @@ 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, -- bool uuid_encoded, SmbiosEntryPointType ep_type); -+ bool uuid_encoded, -+ const char *stream_product, -+ const char *stream_version, -+ SmbiosEntryPointType ep_type); - uint8_t *smbios_get_table_legacy(MachineState *ms, size_t *length); - 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 9ab39e428f..7ccc9a1a07 100644 ---- a/include/hw/i386/pc.h -+++ b/include/hw/i386/pc.h -@@ -107,6 +107,9 @@ struct PCMachineClass { - bool smbios_defaults; - bool smbios_legacy_mode; - bool smbios_uuid_encoded; -+ /* New fields needed for Windows HardwareID-6 matching */ -+ const char *smbios_stream_product; -+ const char *smbios_stream_version; - - /* RAM / address space compat: */ - bool gigabyte_align; --- -2.27.0 - diff --git a/SOURCES/0008-Add-aarch64-machine-types.patch b/SOURCES/0008-Add-aarch64-machine-types.patch deleted file mode 100644 index 07beb75..0000000 --- a/SOURCES/0008-Add-aarch64-machine-types.patch +++ /dev/null @@ -1,310 +0,0 @@ -From 19d36c4519a1a560cce60b212e3afdf7eb026e45 Mon Sep 17 00:00:00 2001 -From: Miroslav Rezanina -Date: Fri, 19 Oct 2018 12:53:31 +0200 -Subject: Add aarch64 machine types - -Adding changes to add RHEL machine types for aarch64 architecture. - -Signed-off-by: Miroslav Rezanina ---- -Rebase notes (6.1.0): -- Use CONFIG_TPM check when using TPM structures -- Add support for default_bus_bypass_iommu -- ea4c0b32d9 arm/virt: Register highmem and gic-version as class properties -- 895e1fa86a hw/arm/virt: Add 8.5 and 9.0 machine types and remove older ones - -Merged patches (6.2.0 RC0): -- 9a3d4fde0e hw/arm/virt: Remove 9.0 machine type -- f7d04d6695 hw: arm: virt: Add hw_compat_rhel_8_5 to 8.5 machine type ---- - hw/arm/virt.c | 205 +++++++++++++++++++++++++++++++++++++++++- - include/hw/arm/virt.h | 8 ++ - 2 files changed, 212 insertions(+), 1 deletion(-) - -diff --git a/hw/arm/virt.c b/hw/arm/virt.c -index 5de4d9d73b..7d51824263 100644 ---- a/hw/arm/virt.c -+++ b/hw/arm/virt.c -@@ -79,6 +79,7 @@ - #include "hw/char/pl011.h" - #include "qemu/guest-random.h" - -+#if 0 /* Disabled for Red Hat Enterprise Linux */ - #define DEFINE_VIRT_MACHINE_LATEST(major, minor, latest) \ - static void virt_##major##_##minor##_class_init(ObjectClass *oc, \ - void *data) \ -@@ -105,7 +106,48 @@ - DEFINE_VIRT_MACHINE_LATEST(major, minor, true) - #define DEFINE_VIRT_MACHINE(major, minor) \ - DEFINE_VIRT_MACHINE_LATEST(major, minor, false) -- -+#endif /* disabled for RHEL */ -+ -+#define DEFINE_RHEL_MACHINE_LATEST(m, n, s, latest) \ -+ static void rhel##m##n##s##_virt_class_init(ObjectClass *oc, \ -+ void *data) \ -+ { \ -+ MachineClass *mc = MACHINE_CLASS(oc); \ -+ rhel##m##n##s##_virt_options(mc); \ -+ mc->desc = "RHEL " # m "." # n "." # s " ARM Virtual Machine"; \ -+ if (latest) { \ -+ mc->alias = "virt"; \ -+ mc->is_default = 1; \ -+ } \ -+ } \ -+ static const TypeInfo rhel##m##n##s##_machvirt_info = { \ -+ .name = MACHINE_TYPE_NAME("virt-rhel" # m "." # n "." # s), \ -+ .parent = TYPE_RHEL_MACHINE, \ -+ .class_init = rhel##m##n##s##_virt_class_init, \ -+ }; \ -+ static void rhel##m##n##s##_machvirt_init(void) \ -+ { \ -+ type_register_static(&rhel##m##n##s##_machvirt_info); \ -+ } \ -+ type_init(rhel##m##n##s##_machvirt_init); -+ -+#define DEFINE_RHEL_MACHINE_AS_LATEST(major, minor, subminor) \ -+ DEFINE_RHEL_MACHINE_LATEST(major, minor, subminor, true) -+#define DEFINE_RHEL_MACHINE(major, minor, subminor) \ -+ DEFINE_RHEL_MACHINE_LATEST(major, minor, subminor, false) -+ -+/* This variable is for changes to properties that are RHEL specific, -+ * different to the current upstream and to be applied to the latest -+ * machine type. -+ */ -+GlobalProperty arm_rhel_compat[] = { -+ { -+ .driver = "virtio-net-pci", -+ .property = "romfile", -+ .value = "", -+ }, -+}; -+const size_t arm_rhel_compat_len = G_N_ELEMENTS(arm_rhel_compat); - - /* Number of external interrupt lines to configure the GIC with */ - #define NUM_IRQS 256 -@@ -2180,6 +2222,7 @@ static void machvirt_init(MachineState *machine) - qemu_add_machine_init_done_notifier(&vms->machine_done); - } - -+#if 0 /* Disabled for Red Hat Enterprise Linux */ - static bool virt_get_secure(Object *obj, Error **errp) - { - VirtMachineState *vms = VIRT_MACHINE(obj); -@@ -2207,6 +2250,7 @@ static void virt_set_virt(Object *obj, bool value, Error **errp) - - vms->virt = value; - } -+#endif /* disabled for RHEL */ - - static bool virt_get_highmem(Object *obj, Error **errp) - { -@@ -2304,6 +2348,7 @@ static void virt_set_acpi(Object *obj, Visitor *v, const char *name, - visit_type_OnOffAuto(v, name, &vms->acpi, errp); - } - -+#if 0 /* Disabled for Red Hat Enterprise Linux */ - static bool virt_get_ras(Object *obj, Error **errp) - { - VirtMachineState *vms = VIRT_MACHINE(obj); -@@ -2331,6 +2376,7 @@ static void virt_set_mte(Object *obj, bool value, Error **errp) - - vms->mte = value; - } -+#endif /* disabled for RHEL */ - - static char *virt_get_gic_version(Object *obj, Error **errp) - { -@@ -2666,6 +2712,7 @@ static int virt_kvm_type(MachineState *ms, const char *type_str) - return fixed_ipa ? 0 : requested_pa_size; - } - -+#if 0 /* Disabled for Red Hat Enterprise Linux */ - static void virt_machine_class_init(ObjectClass *oc, void *data) - { - MachineClass *mc = MACHINE_CLASS(oc); -@@ -3031,3 +3078,159 @@ static void virt_machine_2_6_options(MachineClass *mc) - vmc->no_pmu = true; - } - DEFINE_VIRT_MACHINE(2, 6) -+#endif /* disabled for RHEL */ -+ -+static void rhel_machine_class_init(ObjectClass *oc, void *data) -+{ -+ MachineClass *mc = MACHINE_CLASS(oc); -+ HotplugHandlerClass *hc = HOTPLUG_HANDLER_CLASS(oc); -+ -+ mc->family = "virt-rhel-Z"; -+ mc->init = machvirt_init; -+ /* Maximum supported VCPU count for all virt-rhel* machines */ -+ mc->max_cpus = 384; -+#ifdef CONFIG_TPM -+ machine_class_allow_dynamic_sysbus_dev(mc, TYPE_TPM_TIS_SYSBUS); -+#endif -+ mc->block_default_type = IF_VIRTIO; -+ mc->no_cdrom = 1; -+ mc->pci_allow_0_address = true; -+ /* We know we will never create a pre-ARMv7 CPU which needs 1K pages */ -+ mc->minimum_page_bits = 12; -+ mc->possible_cpu_arch_ids = virt_possible_cpu_arch_ids; -+ mc->cpu_index_to_instance_props = virt_cpu_index_to_props; -+ mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-a57"); -+ mc->get_default_cpu_node_id = virt_get_default_cpu_node_id; -+ mc->kvm_type = virt_kvm_type; -+ assert(!mc->get_hotplug_handler); -+ mc->get_hotplug_handler = virt_machine_get_hotplug_handler; -+ hc->pre_plug = virt_machine_device_pre_plug_cb; -+ hc->plug = virt_machine_device_plug_cb; -+ hc->unplug_request = virt_machine_device_unplug_request_cb; -+ hc->unplug = virt_machine_device_unplug_cb; -+ mc->nvdimm_supported = true; -+ mc->auto_enable_numa_with_memhp = true; -+ mc->auto_enable_numa_with_memdev = true; -+ mc->default_ram_id = "mach-virt.ram"; -+ -+ object_class_property_add(oc, "acpi", "OnOffAuto", -+ virt_get_acpi, virt_set_acpi, -+ NULL, NULL); -+ object_class_property_set_description(oc, "acpi", -+ "Enable ACPI"); -+ -+ object_class_property_add_bool(oc, "highmem", virt_get_highmem, -+ virt_set_highmem); -+ object_class_property_set_description(oc, "highmem", -+ "Set on/off to enable/disable using " -+ "physical address space above 32 bits"); -+ -+ object_class_property_add_str(oc, "gic-version", virt_get_gic_version, -+ virt_set_gic_version); -+ object_class_property_set_description(oc, "gic-version", -+ "Set GIC version. " -+ "Valid values are 2, 3, host and max"); -+ -+ object_class_property_add_str(oc, "x-oem-id", -+ virt_get_oem_id, -+ virt_set_oem_id); -+ object_class_property_set_description(oc, "x-oem-id", -+ "Override the default value of field OEMID " -+ "in ACPI table header." -+ "The string may be up to 6 bytes in size"); -+ -+ object_class_property_add_str(oc, "x-oem-table-id", -+ virt_get_oem_table_id, -+ virt_set_oem_table_id); -+ object_class_property_set_description(oc, "x-oem-table-id", -+ "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, "default_bus_bypass_iommu", -+ virt_get_default_bus_bypass_iommu, -+ virt_set_default_bus_bypass_iommu); -+ object_class_property_set_description(oc, "default_bus_bypass_iommu", -+ "Set on/off to enable/disable " -+ "bypass_iommu for default root bus"); -+ -+} -+ -+static void rhel_virt_instance_init(Object *obj) -+{ -+ VirtMachineState *vms = VIRT_MACHINE(obj); -+ VirtMachineClass *vmc = VIRT_MACHINE_GET_CLASS(vms); -+ -+ /* EL3 is disabled by default and non-configurable for RHEL */ -+ vms->secure = false; -+ -+ /* EL2 is disabled by default and non-configurable for RHEL */ -+ vms->virt = false; -+ -+ /* High memory is enabled by default */ -+ vms->highmem = true; -+ vms->gic_version = VIRT_GIC_VERSION_NOSEL; -+ -+ vms->highmem_ecam = !vmc->no_highmem_ecam; -+ -+ if (vmc->no_its) { -+ vms->its = false; -+ } else { -+ /* Default allows ITS instantiation */ -+ vms->its = true; -+ object_property_add_bool(obj, "its", virt_get_its, -+ virt_set_its); -+ object_property_set_description(obj, "its", -+ "Set on/off to enable/disable " -+ "ITS instantiation"); -+ } -+ -+ /* Default disallows iommu instantiation */ -+ vms->iommu = VIRT_IOMMU_NONE; -+ object_property_add_str(obj, "iommu", virt_get_iommu, virt_set_iommu); -+ object_property_set_description(obj, "iommu", -+ "Set the IOMMU type. " -+ "Valid values are none and smmuv3"); -+ -+ /* Default disallows RAS instantiation and is non-configurable for RHEL */ -+ vms->ras = false; -+ -+ /* MTE is disabled by default and non-configurable for RHEL */ -+ vms->mte = false; -+ -+ /* The default root bus is attached to iommu by default */ -+ vms->default_bus_bypass_iommu = false; -+ -+ vms->irqmap = a15irqmap; -+ -+ virt_flash_create(vms); -+ vms->oem_id = g_strndup(ACPI_BUILD_APPNAME6, 6); -+ vms->oem_table_id = g_strndup(ACPI_BUILD_APPNAME8, 8); -+ -+} -+ -+static const TypeInfo rhel_machine_info = { -+ .name = TYPE_RHEL_MACHINE, -+ .parent = TYPE_MACHINE, -+ .abstract = true, -+ .instance_size = sizeof(VirtMachineState), -+ .class_size = sizeof(VirtMachineClass), -+ .class_init = rhel_machine_class_init, -+ .instance_init = rhel_virt_instance_init, -+ .interfaces = (InterfaceInfo[]) { -+ { TYPE_HOTPLUG_HANDLER }, -+ { } -+ }, -+}; -+ -+static void rhel_machine_init(void) -+{ -+ type_register_static(&rhel_machine_info); -+} -+type_init(rhel_machine_init); -+ -+static void rhel850_virt_options(MachineClass *mc) -+{ -+ compat_props_add(mc->compat_props, arm_rhel_compat, arm_rhel_compat_len); -+ compat_props_add(mc->compat_props, hw_compat_rhel_8_5, hw_compat_rhel_8_5_len); -+} -+DEFINE_RHEL_MACHINE_AS_LATEST(8, 5, 0) -diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h -index dc6b66ffc8..9364628847 100644 ---- a/include/hw/arm/virt.h -+++ b/include/hw/arm/virt.h -@@ -175,9 +175,17 @@ struct VirtMachineState { - - #define VIRT_ECAM_ID(high) (high ? VIRT_HIGH_PCIE_ECAM : VIRT_PCIE_ECAM) - -+#if 0 /* disabled for Red Hat Enterprise Linux */ - #define TYPE_VIRT_MACHINE MACHINE_TYPE_NAME("virt") - OBJECT_DECLARE_TYPE(VirtMachineState, VirtMachineClass, VIRT_MACHINE) - -+#else -+#define TYPE_RHEL_MACHINE MACHINE_TYPE_NAME("virt-rhel") -+typedef struct VirtMachineClass VirtMachineClass; -+typedef struct VirtMachineState VirtMachineState; -+DECLARE_OBJ_CHECKERS(VirtMachineState, VirtMachineClass, VIRT_MACHINE, TYPE_RHEL_MACHINE) -+#endif -+ - void virt_acpi_setup(VirtMachineState *vms); - bool virt_is_acpi_enabled(VirtMachineState *vms); - --- -2.27.0 - diff --git a/SOURCES/0008-Add-ppc64-machine-types.patch b/SOURCES/0008-Add-ppc64-machine-types.patch new file mode 100644 index 0000000..860e803 --- /dev/null +++ b/SOURCES/0008-Add-ppc64-machine-types.patch @@ -0,0 +1,528 @@ +From f61b3d7dc000886e23943457ee9baf1d4cae43b4 Mon Sep 17 00:00:00 2001 +From: Miroslav Rezanina +Date: Fri, 19 Oct 2018 13:27:13 +0200 +Subject: Add ppc64 machine types + +Adding changes to add RHEL machine types for ppc64 architecture. + +Signed-off-by: Miroslav Rezanina + +Rebase notes (6.2.0): +- Fixed rebase conflict relicts +- Update machine type compat for 6.2 (from MR 66) + +Merged patches (6.1.0): +- c438c25ac3 redhat: Define pseries-rhel8.5.0 machine type +- a3995e2eff Remove RHEL 7.0.0 machine type (only ppc64 changes) +- ad3190a79b Remove RHEL 7.1.0 machine type (only ppc64 changes) +- 84bbe15d4e Remove RHEL 7.2.0 machine type (only ppc64 changes) +- 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) +--- + 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.h | 1 + + target/ppc/kvm.c | 27 +++++ + target/ppc/kvm_ppc.h | 13 +++ + 7 files changed, 313 insertions(+), 1 deletion(-) + +diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c +index a4372ba189..5fdf8b506d 100644 +--- a/hw/ppc/spapr.c ++++ b/hw/ppc/spapr.c +@@ -1622,6 +1622,9 @@ static void spapr_machine_reset(MachineState *machine) + + pef_kvm_reset(machine->cgs, &error_fatal); + spapr_caps_apply(spapr); ++ if (spapr->svm_allowed) { ++ kvmppc_svm_allow(&error_fatal); ++ } + + first_ppc_cpu = POWERPC_CPU(first_cpu); + if (kvm_enabled() && kvmppc_has_cap_mmu_radix() && +@@ -3317,6 +3320,20 @@ static void spapr_set_host_serial(Object *obj, const char *value, Error **errp) + spapr->host_serial = g_strdup(value); + } + ++static bool spapr_get_svm_allowed(Object *obj, Error **errp) ++{ ++ SpaprMachineState *spapr = SPAPR_MACHINE(obj); ++ ++ return spapr->svm_allowed; ++} ++ ++static void spapr_set_svm_allowed(Object *obj, bool value, Error **errp) ++{ ++ SpaprMachineState *spapr = SPAPR_MACHINE(obj); ++ ++ spapr->svm_allowed = value; ++} ++ + static void spapr_instance_init(Object *obj) + { + SpaprMachineState *spapr = SPAPR_MACHINE(obj); +@@ -3395,6 +3412,12 @@ 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"); ++ object_property_add_bool(obj, "x-svm-allowed", ++ spapr_get_svm_allowed, ++ spapr_set_svm_allowed); ++ object_property_set_description(obj, "x-svm-allowed", ++ "Allow the guest to become a Secure Guest" ++ " (experimental only)"); + } + + static void spapr_machine_finalizefn(Object *obj) +@@ -4652,6 +4675,7 @@ 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; ++ smc->has_power9_support = true; + } + + static const TypeInfo spapr_machine_info = { +@@ -4703,6 +4727,7 @@ 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 + */ +@@ -4830,6 +4855,7 @@ static void spapr_machine_4_1_class_options(MachineClass *mc) + } + + DEFINE_SPAPR_MACHINE(4_1, "4.1", false); ++#endif + + /* + * pseries-4.0 +@@ -4849,6 +4875,8 @@ static bool phb_placement_4_0(SpaprMachineState *spapr, uint32_t index, + *nv2atsd = 0; + return true; + } ++ ++#if 0 /* Disabled for Red Hat Enterprise Linux */ + 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) + compat_props_add(mc->compat_props, hw_compat_2_1, hw_compat_2_1_len); + } + DEFINE_SPAPR_MACHINE(2_1, "2.1", false); ++#endif ++ ++static void spapr_machine_rhel_default_class_options(MachineClass *mc) ++{ ++ /* ++ * Defaults for the latest behaviour inherited from the base class ++ * can be overriden here for all pseries-rhel* machines. ++ */ ++ ++ /* Maximum supported VCPU count */ ++ mc->max_cpus = 384; ++} ++ ++/* ++ * pseries-rhel8.5.0 ++ * like pseries-6.0 ++ */ ++ ++static void spapr_machine_rhel850_class_options(MachineClass *mc) ++{ ++ SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc); ++ ++ /* The default machine type must apply the RHEL specific defaults */ ++ spapr_machine_rhel_default_class_options(mc); ++ compat_props_add(mc->compat_props, hw_compat_rhel_8_5, ++ hw_compat_rhel_8_5_len); ++ smc->pre_6_2_numa_affinity = true; ++ mc->smp_props.prefer_sockets = true; ++} ++ ++DEFINE_SPAPR_MACHINE(rhel850, "rhel8.5.0", true); ++ ++/* ++ * pseries-rhel8.4.0 ++ * like pseries-5.2 ++ */ ++ ++static void spapr_machine_rhel840_class_options(MachineClass *mc) ++{ ++ spapr_machine_rhel850_class_options(mc); ++ compat_props_add(mc->compat_props, hw_compat_rhel_8_4, ++ hw_compat_rhel_8_4_len); ++} ++ ++DEFINE_SPAPR_MACHINE(rhel840, "rhel8.4.0", false); ++ ++/* ++ * pseries-rhel8.3.0 ++ * like pseries-5.1 ++ */ ++ ++static void spapr_machine_rhel830_class_options(MachineClass *mc) ++{ ++ SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc); ++ ++ spapr_machine_rhel840_class_options(mc); ++ compat_props_add(mc->compat_props, hw_compat_rhel_8_3, ++ hw_compat_rhel_8_3_len); ++ ++ /* from pseries-5.1 */ ++ smc->pre_5_2_numa_associativity = true; ++} ++ ++DEFINE_SPAPR_MACHINE(rhel830, "rhel8.3.0", false); ++ ++/* ++ * pseries-rhel8.2.0 ++ * like pseries-4.2 + pseries-5.0 ++ * except SPAPR_CAP_CCF_ASSIST that has been backported to pseries-rhel8.1.0 ++ */ ++ ++static void spapr_machine_rhel820_class_options(MachineClass *mc) ++{ ++ SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc); ++ /* from pseries-5.0 */ ++ static GlobalProperty compat[] = { ++ { TYPE_SPAPR_PCI_HOST_BRIDGE, "pre-5.1-associativity", "on" }, ++ }; ++ ++ spapr_machine_rhel830_class_options(mc); ++ compat_props_add(mc->compat_props, hw_compat_rhel_8_2, ++ hw_compat_rhel_8_2_len); ++ compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat)); ++ ++ /* from pseries-4.2 */ ++ smc->default_caps.caps[SPAPR_CAP_FWNMI] = SPAPR_CAP_OFF; ++ smc->rma_limit = 16 * GiB; ++ mc->nvdimm_supported = false; ++ ++ /* from pseries-5.0 */ ++ mc->numa_mem_supported = true; ++ smc->pre_5_1_assoc_refpoints = true; ++} ++ ++DEFINE_SPAPR_MACHINE(rhel820, "rhel8.2.0", false); ++ ++/* ++ * pseries-rhel8.1.0 ++ * like pseries-4.1 ++ */ ++ ++static void spapr_machine_rhel810_class_options(MachineClass *mc) ++{ ++ SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc); ++ static GlobalProperty compat[] = { ++ /* Only allow 4kiB and 64kiB IOMMU pagesizes */ ++ { TYPE_SPAPR_PCI_HOST_BRIDGE, "pgsz", "0x11000" }, ++ }; ++ ++ spapr_machine_rhel820_class_options(mc); ++ ++ /* from pseries-4.1 */ ++ smc->linux_pci_probe = false; ++ smc->smp_threads_vsmt = false; ++ compat_props_add(mc->compat_props, hw_compat_rhel_8_1, ++ hw_compat_rhel_8_1_len); ++ compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat)); ++ ++ /* from pseries-4.2 */ ++ smc->default_caps.caps[SPAPR_CAP_CCF_ASSIST] = SPAPR_CAP_OFF; ++} ++ ++DEFINE_SPAPR_MACHINE(rhel810, "rhel8.1.0", false); ++ ++/* ++ * pseries-rhel8.0.0 ++ * like pseries-3.1 and pseries-4.0 ++ * except SPAPR_CAP_CFPC, SPAPR_CAP_SBBC and SPAPR_CAP_IBS ++ * that have been backported to pseries-rhel8.0.0 ++ */ ++ ++static void spapr_machine_rhel800_class_options(MachineClass *mc) ++{ ++ SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc); ++ ++ spapr_machine_rhel810_class_options(mc); ++ compat_props_add(mc->compat_props, hw_compat_rhel_8_0, ++ hw_compat_rhel_8_0_len); ++ ++ /* pseries-4.0 */ ++ smc->phb_placement = phb_placement_4_0; ++ smc->irq = &spapr_irq_xics; ++ smc->pre_4_1_migration = true; ++ ++ /* pseries-3.1 */ ++ mc->default_cpu_type = POWERPC_CPU_TYPE_NAME("power8_v2.0"); ++ smc->update_dt_enabled = false; ++ smc->dr_phb_enabled = false; ++ smc->broken_host_serial_model = true; ++ smc->default_caps.caps[SPAPR_CAP_LARGE_DECREMENTER] = SPAPR_CAP_OFF; ++} ++ ++DEFINE_SPAPR_MACHINE(rhel800, "rhel8.0.0", false); ++ ++/* ++ * pseries-rhel7.6.0 ++ * like spapr_compat_2_12 and spapr_compat_3_0 ++ * spapr_compat_0 is empty ++ */ ++GlobalProperty spapr_compat_rhel7_6[] = { ++ { TYPE_POWERPC_CPU, "pre-3.0-migration", "on" }, ++ { TYPE_SPAPR_CPU_CORE, "pre-3.0-migration", "on" }, ++}; ++const size_t spapr_compat_rhel7_6_len = G_N_ELEMENTS(spapr_compat_rhel7_6); ++ ++ ++static void spapr_machine_rhel760_class_options(MachineClass *mc) ++{ ++ SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc); ++ ++ spapr_machine_rhel800_class_options(mc); ++ compat_props_add(mc->compat_props, hw_compat_rhel_7_6, hw_compat_rhel_7_6_len); ++ compat_props_add(mc->compat_props, spapr_compat_rhel7_6, spapr_compat_rhel7_6_len); ++ ++ /* from spapr_machine_3_0_class_options() */ ++ smc->legacy_irq_allocation = true; ++ smc->nr_xirqs = 0x400; ++ smc->irq = &spapr_irq_xics_legacy; ++ ++ /* from spapr_machine_2_12_class_options() */ ++ /* We depend on kvm_enabled() to choose a default value for the ++ * hpt-max-page-size capability. Of course we can't do it here ++ * because this is too early and the HW accelerator isn't initialzed ++ * yet. Postpone this to machine init (see default_caps_with_cpu()). ++ */ ++ smc->default_caps.caps[SPAPR_CAP_HPT_MAXPAGESIZE] = 0; ++ ++ /* SPAPR_CAP_WORKAROUND enabled in pseries-rhel800 by ++ * f21757edc554 ++ * "Enable mitigations by default for pseries-4.0 machine type") ++ */ ++ smc->default_caps.caps[SPAPR_CAP_CFPC] = SPAPR_CAP_BROKEN; ++ smc->default_caps.caps[SPAPR_CAP_SBBC] = SPAPR_CAP_BROKEN; ++ smc->default_caps.caps[SPAPR_CAP_IBS] = SPAPR_CAP_BROKEN; ++} ++ ++DEFINE_SPAPR_MACHINE(rhel760, "rhel7.6.0", false); ++ ++/* ++ * pseries-rhel7.6.0-sxxm ++ * ++ * pseries-rhel7.6.0 with speculative execution exploit mitigations enabled by default ++ */ ++ ++static void spapr_machine_rhel760sxxm_class_options(MachineClass *mc) ++{ ++ SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc); ++ ++ spapr_machine_rhel760_class_options(mc); ++ smc->default_caps.caps[SPAPR_CAP_CFPC] = SPAPR_CAP_WORKAROUND; ++ smc->default_caps.caps[SPAPR_CAP_SBBC] = SPAPR_CAP_WORKAROUND; ++ smc->default_caps.caps[SPAPR_CAP_IBS] = SPAPR_CAP_FIXED_CCD; ++} ++ ++DEFINE_SPAPR_MACHINE(rhel760sxxm, "rhel7.6.0-sxxm", false); + + static void spapr_machine_register_types(void) + { +diff --git a/hw/ppc/spapr_cpu_core.c b/hw/ppc/spapr_cpu_core.c +index fcb5dfe792..ab8fb5bf62 100644 +--- a/hw/ppc/spapr_cpu_core.c ++++ b/hw/ppc/spapr_cpu_core.c +@@ -25,6 +25,7 @@ + #include "sysemu/reset.h" + #include "sysemu/hw_accel.h" + #include "qemu/error-report.h" ++#include "cpu-models.h" + + static void spapr_reset_vcpu(PowerPCCPU *cpu) + { +@@ -259,6 +260,7 @@ static bool spapr_realize_vcpu(PowerPCCPU *cpu, SpaprMachineState *spapr, + { + CPUPPCState *env = &cpu->env; + CPUState *cs = CPU(cpu); ++ SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(spapr); + + if (!qdev_realize(DEVICE(cpu), NULL, errp)) { + return false; +@@ -270,6 +272,17 @@ static bool spapr_realize_vcpu(PowerPCCPU *cpu, SpaprMachineState *spapr, + /* Set time-base frequency to 512 MHz. vhyp must be set first. */ + cpu_ppc_tb_init(env, SPAPR_TIMEBASE_FREQ); + ++ if (!smc->has_power9_support && ++ (((spapr->max_compat_pvr && ++ ppc_compat_cmp(spapr->max_compat_pvr, ++ CPU_POWERPC_LOGICAL_3_00) >= 0)) || ++ (!spapr->max_compat_pvr && ++ ppc_check_compat(cpu, CPU_POWERPC_LOGICAL_3_00, 0, 0)))) { ++ error_set(errp, ERROR_CLASS_DEVICE_NOT_FOUND, ++ "POWER9 CPU is not supported by this machine class"); ++ return false; ++ } ++ + if (spapr_irq_cpu_intc_create(spapr, cpu, errp) < 0) { + qdev_unrealize(DEVICE(cpu)); + return false; +diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h +index f5c33dcc86..4a68e0a901 100644 +--- a/include/hw/ppc/spapr.h ++++ b/include/hw/ppc/spapr.h +@@ -154,6 +154,7 @@ struct SpaprMachineClass { + bool pre_5_2_numa_associativity; + bool pre_6_2_numa_affinity; + ++ bool has_power9_support; + bool (*phb_placement)(SpaprMachineState *spapr, uint32_t index, + uint64_t *buid, hwaddr *pio, + hwaddr *mmio32, hwaddr *mmio64, +@@ -241,6 +242,9 @@ struct SpaprMachineState { + /* Set by -boot */ + char *boot_device; + ++ /* Secure Guest support via x-svm-allowed */ ++ bool svm_allowed; ++ + /*< public >*/ + char *kvm_type; + char *host_model; +diff --git a/target/ppc/compat.c b/target/ppc/compat.c +index 7949a24f5a..f207a9ba01 100644 +--- a/target/ppc/compat.c ++++ b/target/ppc/compat.c +@@ -114,8 +114,19 @@ static const CompatInfo *compat_by_pvr(uint32_t pvr) + return NULL; + } + ++long ppc_compat_cmp(uint32_t pvr1, uint32_t pvr2) ++{ ++ const CompatInfo *compat1 = compat_by_pvr(pvr1); ++ const CompatInfo *compat2 = compat_by_pvr(pvr2); ++ ++ g_assert(compat1); ++ g_assert(compat2); ++ ++ return compat1 - compat2; ++} ++ + static bool pcc_compat(PowerPCCPUClass *pcc, uint32_t compat_pvr, +- uint32_t min_compat_pvr, uint32_t max_compat_pvr) ++ uint32_t min_compat_pvr, uint32_t max_compat_pvr) + { + const CompatInfo *compat = compat_by_pvr(compat_pvr); + const CompatInfo *min = compat_by_pvr(min_compat_pvr); +diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h +index 047b24ba50..79c5ac50b9 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) + + /* Compatibility modes */ + #if defined(TARGET_PPC64) ++long ppc_compat_cmp(uint32_t pvr1, uint32_t pvr2); + bool ppc_check_compat(PowerPCCPU *cpu, uint32_t compat_pvr, + 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 +--- a/target/ppc/kvm.c ++++ b/target/ppc/kvm.c +@@ -90,6 +90,7 @@ static int cap_ppc_nested_kvm_hv; + static int cap_large_decr; + static int cap_fwnmi; + static int cap_rpt_invalidate; ++static int cap_ppc_secure_guest; + + static uint32_t debug_inst_opcode; + +@@ -137,6 +138,7 @@ 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); ++ cap_ppc_secure_guest = kvm_vm_check_extension(s, KVM_CAP_PPC_SECURE_GUEST); + 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) + return cap_rpt_invalidate; + } + ++bool kvmppc_has_cap_secure_guest(void) ++{ ++ return !!cap_ppc_secure_guest; ++} ++ ++int kvmppc_enable_cap_secure_guest(void) ++{ ++ return kvm_vm_enable_cap(kvm_state, KVM_CAP_PPC_SECURE_GUEST, 0, 1); ++} ++ + 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) + { + return true; + } ++ ++void kvmppc_svm_allow(Error **errp) ++{ ++ if (!kvm_enabled()) { ++ error_setg(errp, "No PEF support in tcg, try x-svm-allowed=off"); ++ return; ++ } ++ ++ if (!kvmppc_has_cap_secure_guest()) { ++ error_setg(errp, "KVM implementation does not support secure guests, " ++ "try x-svm-allowed=off"); ++ } else if (kvmppc_enable_cap_secure_guest() < 0) { ++ error_setg(errp, "Error enabling x-svm-allowed, try x-svm-allowed=off"); ++ } ++} +diff --git a/target/ppc/kvm_ppc.h b/target/ppc/kvm_ppc.h +index ee9325bf9a..20dbb95989 100644 +--- a/target/ppc/kvm_ppc.h ++++ b/target/ppc/kvm_ppc.h +@@ -40,6 +40,7 @@ int kvmppc_booke_watchdog_enable(PowerPCCPU *cpu); + target_ulong kvmppc_configure_v3_mmu(PowerPCCPU *cpu, + bool radix, bool gtse, + uint64_t proc_tbl); ++void kvmppc_svm_allow(Error **errp); + #ifndef CONFIG_USER_ONLY + bool kvmppc_spapr_use_multitce(void); + int kvmppc_spapr_enable_inkernel_multitce(void); +@@ -74,6 +75,8 @@ int kvmppc_get_cap_large_decr(void); + int kvmppc_enable_cap_large_decr(PowerPCCPU *cpu, int enable); + int kvmppc_has_cap_rpt_invalidate(void); + int kvmppc_enable_hwrng(void); ++bool kvmppc_has_cap_secure_guest(void); ++int kvmppc_enable_cap_secure_guest(void); + int kvmppc_put_books_sregs(PowerPCCPU *cpu); + PowerPCCPUClass *kvm_ppc_get_host_cpu_class(void); + void kvmppc_check_papr_resize_hpt(Error **errp); +@@ -393,6 +396,16 @@ static inline int kvmppc_has_cap_rpt_invalidate(void) + return false; + } + ++static inline bool kvmppc_has_cap_secure_guest(void) ++{ ++ return false; ++} ++ ++static inline int kvmppc_enable_cap_secure_guest(void) ++{ ++ return -1; ++} ++ + static inline int kvmppc_enable_hwrng(void) + { + return -1; +-- +2.31.1 + diff --git a/SOURCES/0009-Add-ppc64-machine-types.patch b/SOURCES/0009-Add-ppc64-machine-types.patch deleted file mode 100644 index 90a6ff4..0000000 --- a/SOURCES/0009-Add-ppc64-machine-types.patch +++ /dev/null @@ -1,528 +0,0 @@ -From 2d595bc1744fc764ef506fd6ed6555f267d01ea4 Mon Sep 17 00:00:00 2001 -From: Miroslav Rezanina -Date: Fri, 19 Oct 2018 13:27:13 +0200 -Subject: Add ppc64 machine types - -Adding changes to add RHEL machine types for ppc64 architecture. - -Signed-off-by: Miroslav Rezanina - -Rebase notes (6.2.0 rc1): -- Fixed rebase conflict relicts -- Update machine type compat for 6.2 (from MR 66) - -Merged patches (6.1.0): -- c438c25ac3 redhat: Define pseries-rhel8.5.0 machine type -- a3995e2eff Remove RHEL 7.0.0 machine type (only ppc64 changes) -- ad3190a79b Remove RHEL 7.1.0 machine type (only ppc64 changes) -- 84bbe15d4e Remove RHEL 7.2.0 machine type (only ppc64 changes) -- 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) ---- - 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.h | 1 + - target/ppc/kvm.c | 27 +++++ - target/ppc/kvm_ppc.h | 13 +++ - 7 files changed, 313 insertions(+), 1 deletion(-) - -diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c -index 3b5fd749be..f4bb5f15f0 100644 ---- a/hw/ppc/spapr.c -+++ b/hw/ppc/spapr.c -@@ -1593,6 +1593,9 @@ static void spapr_machine_reset(MachineState *machine) - - pef_kvm_reset(machine->cgs, &error_fatal); - spapr_caps_apply(spapr); -+ if (spapr->svm_allowed) { -+ kvmppc_svm_allow(&error_fatal); -+ } - - first_ppc_cpu = POWERPC_CPU(first_cpu); - if (kvm_enabled() && kvmppc_has_cap_mmu_radix() && -@@ -3288,6 +3291,20 @@ static void spapr_set_host_serial(Object *obj, const char *value, Error **errp) - spapr->host_serial = g_strdup(value); - } - -+static bool spapr_get_svm_allowed(Object *obj, Error **errp) -+{ -+ SpaprMachineState *spapr = SPAPR_MACHINE(obj); -+ -+ return spapr->svm_allowed; -+} -+ -+static void spapr_set_svm_allowed(Object *obj, bool value, Error **errp) -+{ -+ SpaprMachineState *spapr = SPAPR_MACHINE(obj); -+ -+ spapr->svm_allowed = value; -+} -+ - static void spapr_instance_init(Object *obj) - { - SpaprMachineState *spapr = SPAPR_MACHINE(obj); -@@ -3366,6 +3383,12 @@ 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"); -+ object_property_add_bool(obj, "x-svm-allowed", -+ spapr_get_svm_allowed, -+ spapr_set_svm_allowed); -+ object_property_set_description(obj, "x-svm-allowed", -+ "Allow the guest to become a Secure Guest" -+ " (experimental only)"); - } - - static void spapr_machine_finalizefn(Object *obj) -@@ -4614,6 +4637,7 @@ 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; -+ smc->has_power9_support = true; - } - - static const TypeInfo spapr_machine_info = { -@@ -4665,6 +4689,7 @@ static void spapr_machine_latest_class_options(MachineClass *mc) - } \ - type_init(spapr_machine_register_##suffix) - -+#if 0 /* Disabled for Red Hat Enterprise Linux */ - /* - * pseries-6.2 - */ -@@ -4781,6 +4806,7 @@ static void spapr_machine_4_1_class_options(MachineClass *mc) - } - - DEFINE_SPAPR_MACHINE(4_1, "4.1", false); -+#endif - - /* - * pseries-4.0 -@@ -4800,6 +4826,8 @@ static bool phb_placement_4_0(SpaprMachineState *spapr, uint32_t index, - *nv2atsd = 0; - return true; - } -+ -+#if 0 /* Disabled for Red Hat Enterprise Linux */ - static void spapr_machine_4_0_class_options(MachineClass *mc) - { - SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc); -@@ -5127,6 +5155,221 @@ 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); -+#endif -+ -+static void spapr_machine_rhel_default_class_options(MachineClass *mc) -+{ -+ /* -+ * Defaults for the latest behaviour inherited from the base class -+ * can be overriden here for all pseries-rhel* machines. -+ */ -+ -+ /* Maximum supported VCPU count */ -+ mc->max_cpus = 384; -+} -+ -+/* -+ * pseries-rhel8.5.0 -+ * like pseries-6.0 -+ */ -+ -+static void spapr_machine_rhel850_class_options(MachineClass *mc) -+{ -+ SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc); -+ -+ /* The default machine type must apply the RHEL specific defaults */ -+ spapr_machine_rhel_default_class_options(mc); -+ compat_props_add(mc->compat_props, hw_compat_rhel_8_5, -+ hw_compat_rhel_8_5_len); -+ smc->pre_6_2_numa_affinity = true; -+ mc->smp_props.prefer_sockets = true; -+} -+ -+DEFINE_SPAPR_MACHINE(rhel850, "rhel8.5.0", true); -+ -+/* -+ * pseries-rhel8.4.0 -+ * like pseries-5.2 -+ */ -+ -+static void spapr_machine_rhel840_class_options(MachineClass *mc) -+{ -+ spapr_machine_rhel850_class_options(mc); -+ compat_props_add(mc->compat_props, hw_compat_rhel_8_4, -+ hw_compat_rhel_8_4_len); -+} -+ -+DEFINE_SPAPR_MACHINE(rhel840, "rhel8.4.0", false); -+ -+/* -+ * pseries-rhel8.3.0 -+ * like pseries-5.1 -+ */ -+ -+static void spapr_machine_rhel830_class_options(MachineClass *mc) -+{ -+ SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc); -+ -+ spapr_machine_rhel840_class_options(mc); -+ compat_props_add(mc->compat_props, hw_compat_rhel_8_3, -+ hw_compat_rhel_8_3_len); -+ -+ /* from pseries-5.1 */ -+ smc->pre_5_2_numa_associativity = true; -+} -+ -+DEFINE_SPAPR_MACHINE(rhel830, "rhel8.3.0", false); -+ -+/* -+ * pseries-rhel8.2.0 -+ * like pseries-4.2 + pseries-5.0 -+ * except SPAPR_CAP_CCF_ASSIST that has been backported to pseries-rhel8.1.0 -+ */ -+ -+static void spapr_machine_rhel820_class_options(MachineClass *mc) -+{ -+ SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc); -+ /* from pseries-5.0 */ -+ static GlobalProperty compat[] = { -+ { TYPE_SPAPR_PCI_HOST_BRIDGE, "pre-5.1-associativity", "on" }, -+ }; -+ -+ spapr_machine_rhel830_class_options(mc); -+ compat_props_add(mc->compat_props, hw_compat_rhel_8_2, -+ hw_compat_rhel_8_2_len); -+ compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat)); -+ -+ /* from pseries-4.2 */ -+ smc->default_caps.caps[SPAPR_CAP_FWNMI] = SPAPR_CAP_OFF; -+ smc->rma_limit = 16 * GiB; -+ mc->nvdimm_supported = false; -+ -+ /* from pseries-5.0 */ -+ mc->numa_mem_supported = true; -+ smc->pre_5_1_assoc_refpoints = true; -+} -+ -+DEFINE_SPAPR_MACHINE(rhel820, "rhel8.2.0", false); -+ -+/* -+ * pseries-rhel8.1.0 -+ * like pseries-4.1 -+ */ -+ -+static void spapr_machine_rhel810_class_options(MachineClass *mc) -+{ -+ SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc); -+ static GlobalProperty compat[] = { -+ /* Only allow 4kiB and 64kiB IOMMU pagesizes */ -+ { TYPE_SPAPR_PCI_HOST_BRIDGE, "pgsz", "0x11000" }, -+ }; -+ -+ spapr_machine_rhel820_class_options(mc); -+ -+ /* from pseries-4.1 */ -+ smc->linux_pci_probe = false; -+ smc->smp_threads_vsmt = false; -+ compat_props_add(mc->compat_props, hw_compat_rhel_8_1, -+ hw_compat_rhel_8_1_len); -+ compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat)); -+ -+ /* from pseries-4.2 */ -+ smc->default_caps.caps[SPAPR_CAP_CCF_ASSIST] = SPAPR_CAP_OFF; -+} -+ -+DEFINE_SPAPR_MACHINE(rhel810, "rhel8.1.0", false); -+ -+/* -+ * pseries-rhel8.0.0 -+ * like pseries-3.1 and pseries-4.0 -+ * except SPAPR_CAP_CFPC, SPAPR_CAP_SBBC and SPAPR_CAP_IBS -+ * that have been backported to pseries-rhel8.0.0 -+ */ -+ -+static void spapr_machine_rhel800_class_options(MachineClass *mc) -+{ -+ SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc); -+ -+ spapr_machine_rhel810_class_options(mc); -+ compat_props_add(mc->compat_props, hw_compat_rhel_8_0, -+ hw_compat_rhel_8_0_len); -+ -+ /* pseries-4.0 */ -+ smc->phb_placement = phb_placement_4_0; -+ smc->irq = &spapr_irq_xics; -+ smc->pre_4_1_migration = true; -+ -+ /* pseries-3.1 */ -+ mc->default_cpu_type = POWERPC_CPU_TYPE_NAME("power8_v2.0"); -+ smc->update_dt_enabled = false; -+ smc->dr_phb_enabled = false; -+ smc->broken_host_serial_model = true; -+ smc->default_caps.caps[SPAPR_CAP_LARGE_DECREMENTER] = SPAPR_CAP_OFF; -+} -+ -+DEFINE_SPAPR_MACHINE(rhel800, "rhel8.0.0", false); -+ -+/* -+ * pseries-rhel7.6.0 -+ * like spapr_compat_2_12 and spapr_compat_3_0 -+ * spapr_compat_0 is empty -+ */ -+GlobalProperty spapr_compat_rhel7_6[] = { -+ { TYPE_POWERPC_CPU, "pre-3.0-migration", "on" }, -+ { TYPE_SPAPR_CPU_CORE, "pre-3.0-migration", "on" }, -+}; -+const size_t spapr_compat_rhel7_6_len = G_N_ELEMENTS(spapr_compat_rhel7_6); -+ -+ -+static void spapr_machine_rhel760_class_options(MachineClass *mc) -+{ -+ SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc); -+ -+ spapr_machine_rhel800_class_options(mc); -+ compat_props_add(mc->compat_props, hw_compat_rhel_7_6, hw_compat_rhel_7_6_len); -+ compat_props_add(mc->compat_props, spapr_compat_rhel7_6, spapr_compat_rhel7_6_len); -+ -+ /* from spapr_machine_3_0_class_options() */ -+ smc->legacy_irq_allocation = true; -+ smc->nr_xirqs = 0x400; -+ smc->irq = &spapr_irq_xics_legacy; -+ -+ /* from spapr_machine_2_12_class_options() */ -+ /* We depend on kvm_enabled() to choose a default value for the -+ * hpt-max-page-size capability. Of course we can't do it here -+ * because this is too early and the HW accelerator isn't initialzed -+ * yet. Postpone this to machine init (see default_caps_with_cpu()). -+ */ -+ smc->default_caps.caps[SPAPR_CAP_HPT_MAXPAGESIZE] = 0; -+ -+ /* SPAPR_CAP_WORKAROUND enabled in pseries-rhel800 by -+ * f21757edc554 -+ * "Enable mitigations by default for pseries-4.0 machine type") -+ */ -+ smc->default_caps.caps[SPAPR_CAP_CFPC] = SPAPR_CAP_BROKEN; -+ smc->default_caps.caps[SPAPR_CAP_SBBC] = SPAPR_CAP_BROKEN; -+ smc->default_caps.caps[SPAPR_CAP_IBS] = SPAPR_CAP_BROKEN; -+} -+ -+DEFINE_SPAPR_MACHINE(rhel760, "rhel7.6.0", false); -+ -+/* -+ * pseries-rhel7.6.0-sxxm -+ * -+ * pseries-rhel7.6.0 with speculative execution exploit mitigations enabled by default -+ */ -+ -+static void spapr_machine_rhel760sxxm_class_options(MachineClass *mc) -+{ -+ SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc); -+ -+ spapr_machine_rhel760_class_options(mc); -+ smc->default_caps.caps[SPAPR_CAP_CFPC] = SPAPR_CAP_WORKAROUND; -+ smc->default_caps.caps[SPAPR_CAP_SBBC] = SPAPR_CAP_WORKAROUND; -+ smc->default_caps.caps[SPAPR_CAP_IBS] = SPAPR_CAP_FIXED_CCD; -+} -+ -+DEFINE_SPAPR_MACHINE(rhel760sxxm, "rhel7.6.0-sxxm", false); - - static void spapr_machine_register_types(void) - { -diff --git a/hw/ppc/spapr_cpu_core.c b/hw/ppc/spapr_cpu_core.c -index 8ba34f6a1d..78eca1c04a 100644 ---- a/hw/ppc/spapr_cpu_core.c -+++ b/hw/ppc/spapr_cpu_core.c -@@ -24,6 +24,7 @@ - #include "sysemu/reset.h" - #include "sysemu/hw_accel.h" - #include "qemu/error-report.h" -+#include "cpu-models.h" - - static void spapr_reset_vcpu(PowerPCCPU *cpu) - { -@@ -250,6 +251,7 @@ static bool spapr_realize_vcpu(PowerPCCPU *cpu, SpaprMachineState *spapr, - { - CPUPPCState *env = &cpu->env; - CPUState *cs = CPU(cpu); -+ SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(spapr); - - if (!qdev_realize(DEVICE(cpu), NULL, errp)) { - return false; -@@ -261,6 +263,17 @@ static bool spapr_realize_vcpu(PowerPCCPU *cpu, SpaprMachineState *spapr, - cpu_ppc_set_vhyp(cpu, PPC_VIRTUAL_HYPERVISOR(spapr)); - kvmppc_set_papr(cpu); - -+ if (!smc->has_power9_support && -+ (((spapr->max_compat_pvr && -+ ppc_compat_cmp(spapr->max_compat_pvr, -+ CPU_POWERPC_LOGICAL_3_00) >= 0)) || -+ (!spapr->max_compat_pvr && -+ ppc_check_compat(cpu, CPU_POWERPC_LOGICAL_3_00, 0, 0)))) { -+ error_set(errp, ERROR_CLASS_DEVICE_NOT_FOUND, -+ "POWER9 CPU is not supported by this machine class"); -+ return false; -+ } -+ - if (spapr_irq_cpu_intc_create(spapr, cpu, errp) < 0) { - qdev_unrealize(DEVICE(cpu)); - return false; -diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h -index ee7504b976..fcd5bf9302 100644 ---- a/include/hw/ppc/spapr.h -+++ b/include/hw/ppc/spapr.h -@@ -154,6 +154,7 @@ struct SpaprMachineClass { - bool pre_5_2_numa_associativity; - bool pre_6_2_numa_affinity; - -+ bool has_power9_support; - bool (*phb_placement)(SpaprMachineState *spapr, uint32_t index, - uint64_t *buid, hwaddr *pio, - hwaddr *mmio32, hwaddr *mmio64, -@@ -238,6 +239,9 @@ struct SpaprMachineState { - /* Set by -boot */ - char *boot_device; - -+ /* Secure Guest support via x-svm-allowed */ -+ bool svm_allowed; -+ - /*< public >*/ - char *kvm_type; - char *host_model; -diff --git a/target/ppc/compat.c b/target/ppc/compat.c -index 7949a24f5a..f207a9ba01 100644 ---- a/target/ppc/compat.c -+++ b/target/ppc/compat.c -@@ -114,8 +114,19 @@ static const CompatInfo *compat_by_pvr(uint32_t pvr) - return NULL; - } - -+long ppc_compat_cmp(uint32_t pvr1, uint32_t pvr2) -+{ -+ const CompatInfo *compat1 = compat_by_pvr(pvr1); -+ const CompatInfo *compat2 = compat_by_pvr(pvr2); -+ -+ g_assert(compat1); -+ g_assert(compat2); -+ -+ return compat1 - compat2; -+} -+ - static bool pcc_compat(PowerPCCPUClass *pcc, uint32_t compat_pvr, -- uint32_t min_compat_pvr, uint32_t max_compat_pvr) -+ uint32_t min_compat_pvr, uint32_t max_compat_pvr) - { - const CompatInfo *compat = compat_by_pvr(compat_pvr); - const CompatInfo *min = compat_by_pvr(min_compat_pvr); -diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h -index e946da5f3a..23e8b76c85 100644 ---- a/target/ppc/cpu.h -+++ b/target/ppc/cpu.h -@@ -1401,6 +1401,7 @@ static inline int cpu_mmu_index(CPUPPCState *env, bool ifetch) - - /* Compatibility modes */ - #if defined(TARGET_PPC64) -+long ppc_compat_cmp(uint32_t pvr1, uint32_t pvr2); - bool ppc_check_compat(PowerPCCPU *cpu, uint32_t compat_pvr, - 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 ---- a/target/ppc/kvm.c -+++ b/target/ppc/kvm.c -@@ -90,6 +90,7 @@ static int cap_ppc_nested_kvm_hv; - static int cap_large_decr; - static int cap_fwnmi; - static int cap_rpt_invalidate; -+static int cap_ppc_secure_guest; - - static uint32_t debug_inst_opcode; - -@@ -137,6 +138,7 @@ 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); -+ cap_ppc_secure_guest = kvm_vm_check_extension(s, KVM_CAP_PPC_SECURE_GUEST); - 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) - return cap_rpt_invalidate; - } - -+bool kvmppc_has_cap_secure_guest(void) -+{ -+ return !!cap_ppc_secure_guest; -+} -+ -+int kvmppc_enable_cap_secure_guest(void) -+{ -+ return kvm_vm_enable_cap(kvm_state, KVM_CAP_PPC_SECURE_GUEST, 0, 1); -+} -+ - 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) - { - return true; - } -+ -+void kvmppc_svm_allow(Error **errp) -+{ -+ if (!kvm_enabled()) { -+ error_setg(errp, "No PEF support in tcg, try x-svm-allowed=off"); -+ return; -+ } -+ -+ if (!kvmppc_has_cap_secure_guest()) { -+ error_setg(errp, "KVM implementation does not support secure guests, " -+ "try x-svm-allowed=off"); -+ } else if (kvmppc_enable_cap_secure_guest() < 0) { -+ error_setg(errp, "Error enabling x-svm-allowed, try x-svm-allowed=off"); -+ } -+} -diff --git a/target/ppc/kvm_ppc.h b/target/ppc/kvm_ppc.h -index ee9325bf9a..20dbb95989 100644 ---- a/target/ppc/kvm_ppc.h -+++ b/target/ppc/kvm_ppc.h -@@ -40,6 +40,7 @@ int kvmppc_booke_watchdog_enable(PowerPCCPU *cpu); - target_ulong kvmppc_configure_v3_mmu(PowerPCCPU *cpu, - bool radix, bool gtse, - uint64_t proc_tbl); -+void kvmppc_svm_allow(Error **errp); - #ifndef CONFIG_USER_ONLY - bool kvmppc_spapr_use_multitce(void); - int kvmppc_spapr_enable_inkernel_multitce(void); -@@ -74,6 +75,8 @@ int kvmppc_get_cap_large_decr(void); - int kvmppc_enable_cap_large_decr(PowerPCCPU *cpu, int enable); - int kvmppc_has_cap_rpt_invalidate(void); - int kvmppc_enable_hwrng(void); -+bool kvmppc_has_cap_secure_guest(void); -+int kvmppc_enable_cap_secure_guest(void); - int kvmppc_put_books_sregs(PowerPCCPU *cpu); - PowerPCCPUClass *kvm_ppc_get_host_cpu_class(void); - void kvmppc_check_papr_resize_hpt(Error **errp); -@@ -393,6 +396,16 @@ static inline int kvmppc_has_cap_rpt_invalidate(void) - return false; - } - -+static inline bool kvmppc_has_cap_secure_guest(void) -+{ -+ return false; -+} -+ -+static inline int kvmppc_enable_cap_secure_guest(void) -+{ -+ return -1; -+} -+ - static inline int kvmppc_enable_hwrng(void) - { - return -1; --- -2.27.0 - diff --git a/SOURCES/0009-Add-s390x-machine-types.patch b/SOURCES/0009-Add-s390x-machine-types.patch new file mode 100644 index 0000000..2d8b554 --- /dev/null +++ b/SOURCES/0009-Add-s390x-machine-types.patch @@ -0,0 +1,186 @@ +From 680f343e58a50a99d17bc7dedd3ee90980912023 Mon Sep 17 00:00:00 2001 +From: Miroslav Rezanina +Date: Fri, 19 Oct 2018 13:47:32 +0200 +Subject: Add s390x machine types + +Adding changes to add RHEL machine types for s390x architecture. + +Signed-off-by: Miroslav Rezanina +-- +Merged patches (6.1.0): +- 64a9a5c971 hw/s390x: Remove the RHEL7-only machine type +- 395516d62b redhat: s390x: add rhel-8.5.0 compat machine + +Merged patches (6.2.0): +- 3bf66f4520 redhat: Add s390x machine type compatibility update for 6.1 rebase + +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 + */ +diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c +index 90480e7cf9..ec4176a1e0 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) + } \ + type_init(ccw_machine_register_##suffix) + ++#if 0 /* Disabled for Red Hat Enterprise Linux */ + static void ccw_machine_7_0_instance_options(MachineState *machine) + { + } +@@ -1115,6 +1116,107 @@ 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 void ccw_machine_rhel900_class_options(MachineClass *mc) ++{ ++} ++DEFINE_CCW_MACHINE(rhel900, "rhel9.0.0", true); ++ ++static void ccw_machine_rhel860_instance_options(MachineState *machine) ++{ ++ /* Note: The -rhel8.6.0 and -rhel9.0.0 machines are technically identical */ ++ ccw_machine_rhel900_instance_options(machine); ++} ++ ++static void ccw_machine_rhel860_class_options(MachineClass *mc) ++{ ++ ccw_machine_rhel900_class_options(mc); ++ ++ /* All RHEL machines for prior major releases are deprecated */ ++ mc->deprecation_reason = rhel_old_machine_deprecation; ++} ++DEFINE_CCW_MACHINE(rhel860, "rhel8.6.0", false); ++ ++static void ccw_machine_rhel850_instance_options(MachineState *machine) ++{ ++ static const S390FeatInit qemu_cpu_feat = { S390_FEAT_LIST_QEMU_V6_0 }; ++ ++ ccw_machine_rhel860_instance_options(machine); ++ ++ s390_set_qemu_cpu_model(0x2964, 13, 2, qemu_cpu_feat); ++ ++ s390_cpudef_featoff_greater(16, 1, S390_FEAT_NNPA); ++ s390_cpudef_featoff_greater(16, 1, S390_FEAT_VECTOR_PACKED_DECIMAL_ENH2); ++ s390_cpudef_featoff_greater(16, 1, S390_FEAT_BEAR_ENH); ++ s390_cpudef_featoff_greater(16, 1, S390_FEAT_RDP); ++ s390_cpudef_featoff_greater(16, 1, S390_FEAT_PAI); ++} ++ ++static void ccw_machine_rhel850_class_options(MachineClass *mc) ++{ ++ ccw_machine_rhel860_class_options(mc); ++ compat_props_add(mc->compat_props, hw_compat_rhel_8_5, hw_compat_rhel_8_5_len); ++ mc->smp_props.prefer_sockets = true; ++} ++DEFINE_CCW_MACHINE(rhel850, "rhel8.5.0", false); ++ ++static void ccw_machine_rhel840_instance_options(MachineState *machine) ++{ ++ ccw_machine_rhel850_instance_options(machine); ++} ++ ++static void ccw_machine_rhel840_class_options(MachineClass *mc) ++{ ++ ccw_machine_rhel850_class_options(mc); ++ compat_props_add(mc->compat_props, hw_compat_rhel_8_4, hw_compat_rhel_8_4_len); ++} ++DEFINE_CCW_MACHINE(rhel840, "rhel8.4.0", false); ++ ++static void ccw_machine_rhel820_instance_options(MachineState *machine) ++{ ++ ccw_machine_rhel840_instance_options(machine); ++} ++ ++static void ccw_machine_rhel820_class_options(MachineClass *mc) ++{ ++ ccw_machine_rhel840_class_options(mc); ++ mc->fixup_ram_size = s390_fixup_ram_size; ++ /* we did not publish a rhel8.3.0 machine */ ++ compat_props_add(mc->compat_props, hw_compat_rhel_8_3, hw_compat_rhel_8_3_len); ++ compat_props_add(mc->compat_props, hw_compat_rhel_8_2, hw_compat_rhel_8_2_len); ++} ++DEFINE_CCW_MACHINE(rhel820, "rhel8.2.0", false); ++ ++static void ccw_machine_rhel760_instance_options(MachineState *machine) ++{ ++ static const S390FeatInit qemu_cpu_feat = { S390_FEAT_LIST_QEMU_V3_1 }; ++ ++ ccw_machine_rhel820_instance_options(machine); ++ ++ s390_set_qemu_cpu_model(0x2827, 12, 2, qemu_cpu_feat); ++ ++ /* The multiple-epoch facility was not available with rhel7.6.0 on z14GA1 */ ++ s390_cpudef_featoff(14, 1, S390_FEAT_MULTIPLE_EPOCH); ++ s390_cpudef_featoff(14, 1, S390_FEAT_PTFF_QSIE); ++ s390_cpudef_featoff(14, 1, S390_FEAT_PTFF_QTOUE); ++ s390_cpudef_featoff(14, 1, S390_FEAT_PTFF_STOE); ++ s390_cpudef_featoff(14, 1, S390_FEAT_PTFF_STOUE); ++} ++ ++static void ccw_machine_rhel760_class_options(MachineClass *mc) ++{ ++ ccw_machine_rhel820_class_options(mc); ++ /* We never published the s390x version of RHEL-AV 8.0 and 8.1, so add this here */ ++ compat_props_add(mc->compat_props, hw_compat_rhel_8_1, hw_compat_rhel_8_1_len); ++ compat_props_add(mc->compat_props, hw_compat_rhel_8_0, hw_compat_rhel_8_0_len); ++ compat_props_add(mc->compat_props, hw_compat_rhel_7_6, hw_compat_rhel_7_6_len); ++} ++DEFINE_CCW_MACHINE(rhel760, "rhel7.6.0", false); + + 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; ++ + #endif +-- +2.31.1 + diff --git a/SOURCES/0010-Add-s390x-machine-types.patch b/SOURCES/0010-Add-s390x-machine-types.patch deleted file mode 100644 index 1095f3a..0000000 --- a/SOURCES/0010-Add-s390x-machine-types.patch +++ /dev/null @@ -1,114 +0,0 @@ -From ea22b5ae0a89ef53f31f67bb6845fd6c45d4f412 Mon Sep 17 00:00:00 2001 -From: Miroslav Rezanina -Date: Fri, 19 Oct 2018 13:47:32 +0200 -Subject: Add s390x machine types - -Adding changes to add RHEL machine types for s390x architecture. - -Signed-off-by: Miroslav Rezanina --- -Merged patches (6.1.0): -- 64a9a5c971 hw/s390x: Remove the RHEL7-only machine type -- 395516d62b redhat: s390x: add rhel-8.5.0 compat machine - -Merged patches (6.2.0 RC0): -- 3bf66f4520 redhat: Add s390x machine type compatibility update for 6.1 rebase ---- - hw/s390x/s390-virtio-ccw.c | 67 +++++++++++++++++++++++++++++++++++++- - 1 file changed, 66 insertions(+), 1 deletion(-) - -diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c -index 653587ea62..4af14cb9ca 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) - } \ - type_init(ccw_machine_register_##suffix) - -+#if 0 /* Disabled for Red Hat Enterprise Linux */ - static void ccw_machine_6_2_instance_options(MachineState *machine) - { - } -@@ -1100,6 +1101,70 @@ 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_rhel850_instance_options(MachineState *machine) -+{ -+} -+ -+static void ccw_machine_rhel850_class_options(MachineClass *mc) -+{ -+ compat_props_add(mc->compat_props, hw_compat_rhel_8_5, hw_compat_rhel_8_5_len); -+} -+DEFINE_CCW_MACHINE(rhel850, "rhel8.5.0", true); -+ -+static void ccw_machine_rhel840_instance_options(MachineState *machine) -+{ -+ ccw_machine_rhel850_instance_options(machine); -+} -+ -+static void ccw_machine_rhel840_class_options(MachineClass *mc) -+{ -+ ccw_machine_rhel850_class_options(mc); -+ compat_props_add(mc->compat_props, hw_compat_rhel_8_4, hw_compat_rhel_8_4_len); -+} -+DEFINE_CCW_MACHINE(rhel840, "rhel8.4.0", false); -+ -+static void ccw_machine_rhel820_instance_options(MachineState *machine) -+{ -+ ccw_machine_rhel840_instance_options(machine); -+} -+ -+static void ccw_machine_rhel820_class_options(MachineClass *mc) -+{ -+ ccw_machine_rhel840_class_options(mc); -+ mc->fixup_ram_size = s390_fixup_ram_size; -+ /* we did not publish a rhel8.3.0 machine */ -+ compat_props_add(mc->compat_props, hw_compat_rhel_8_3, hw_compat_rhel_8_3_len); -+ compat_props_add(mc->compat_props, hw_compat_rhel_8_2, hw_compat_rhel_8_2_len); -+} -+DEFINE_CCW_MACHINE(rhel820, "rhel8.2.0", false); -+ -+static void ccw_machine_rhel760_instance_options(MachineState *machine) -+{ -+ static const S390FeatInit qemu_cpu_feat = { S390_FEAT_LIST_QEMU_V3_1 }; -+ -+ ccw_machine_rhel820_instance_options(machine); -+ -+ s390_set_qemu_cpu_model(0x2827, 12, 2, qemu_cpu_feat); -+ -+ /* The multiple-epoch facility was not available with rhel7.6.0 on z14GA1 */ -+ s390_cpudef_featoff(14, 1, S390_FEAT_MULTIPLE_EPOCH); -+ s390_cpudef_featoff(14, 1, S390_FEAT_PTFF_QSIE); -+ s390_cpudef_featoff(14, 1, S390_FEAT_PTFF_QTOUE); -+ s390_cpudef_featoff(14, 1, S390_FEAT_PTFF_STOE); -+ s390_cpudef_featoff(14, 1, S390_FEAT_PTFF_STOUE); -+} -+ -+static void ccw_machine_rhel760_class_options(MachineClass *mc) -+{ -+ ccw_machine_rhel820_class_options(mc); -+ /* We never published the s390x version of RHEL-AV 8.0 and 8.1, so add this here */ -+ compat_props_add(mc->compat_props, hw_compat_rhel_8_1, hw_compat_rhel_8_1_len); -+ compat_props_add(mc->compat_props, hw_compat_rhel_8_0, hw_compat_rhel_8_0_len); -+ compat_props_add(mc->compat_props, hw_compat_rhel_7_6, hw_compat_rhel_7_6_len); -+} -+DEFINE_CCW_MACHINE(rhel760, "rhel7.6.0", false); - - static void ccw_machine_register_types(void) - { --- -2.27.0 - diff --git a/SOURCES/0010-Add-x86_64-machine-types.patch b/SOURCES/0010-Add-x86_64-machine-types.patch new file mode 100644 index 0000000..7c48967 --- /dev/null +++ b/SOURCES/0010-Add-x86_64-machine-types.patch @@ -0,0 +1,714 @@ +From 427a575ca57966bc72e1ebf218081da530d435d7 Mon Sep 17 00:00:00 2001 +From: Miroslav Rezanina +Date: Fri, 19 Oct 2018 13:10:31 +0200 +Subject: Add x86_64 machine types + +Adding changes to add RHEL machine types for x86_64 architecture. + +Signed-off-by: Miroslav Rezanina + +Rebase notes (6.1.0): +- Update qemu64 cpu spec + +Rebase notes (7.0.0): +- Reset alias for all machine-types except latest one + +Merged patches (6.1.0): +- 59c284ad3b x86: Add x86 rhel8.5 machine types +- a8868b42fe redhat: x86: Enable 'kvm-asyncpf-int' by default +- a3995e2eff Remove RHEL 7.0.0 machine type (only x86_64 changes) +- ad3190a79b Remove RHEL 7.1.0 machine type (only x86_64 changes) +- 84bbe15d4e Remove RHEL 7.2.0 machine type (only x86_64 changes) +- 0215eb3356 Remove RHEL 7.3.0 machine types (only x86_64 changes) +- af69d1ca6e Remove RHEL 7.4.0 machine types (only x86_64 changes) +- 8f7a74ab78 Remove RHEL 7.5.0 machine types (only x86_64 changes) + +Merged patches (7.0.0): +- eae7d8dd3c x86/rhel machine types: Add pc_rhel_8_5_compat +- 6762f56469 x86/rhel machine types: Wire compat into q35 and i440fx +- 5762101438 rhel machine types/x86: set prefer_sockets +- 9ba9ddc632 x86: Add q35 RHEL 8.6.0 machine type +- 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 +--- + hw/core/machine.c | 10 ++ + hw/i386/pc.c | 135 +++++++++++++++++++++- + hw/i386/pc_piix.c | 79 ++++++++++++- + hw/i386/pc_q35.c | 227 ++++++++++++++++++++++++++++++++++++- + hw/s390x/s390-virtio-ccw.c | 1 + + include/hw/boards.h | 5 + + include/hw/i386/pc.h | 24 ++++ + 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(-) + +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 +--- a/hw/i386/pc.c ++++ b/hw/i386/pc.c +@@ -375,6 +375,137 @@ GlobalProperty pc_compat_1_4[] = { + }; + const size_t pc_compat_1_4_len = G_N_ELEMENTS(pc_compat_1_4); + ++/* This macro is for changes to properties that are RHEL specific, ++ * different to the current upstream and to be applied to the latest ++ * machine type. ++ */ ++GlobalProperty pc_rhel_compat[] = { ++ { 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" }, ++ { TYPE_X86_CPU, "vmx-exit-load-perf-global-ctrl", "off" }, ++ /* bz 1508330 */ ++ { "vfio-pci", "x-no-geforce-quirks", "on" }, ++ /* bz 1941397 */ ++ { TYPE_X86_CPU, "kvm-asyncpf-int", "on" }, ++}; ++const size_t pc_rhel_compat_len = G_N_ELEMENTS(pc_rhel_compat); ++ ++GlobalProperty pc_rhel_8_5_compat[] = { ++ /* pc_rhel_8_5_compat from pc_compat_6_0 */ ++ { "qemu64" "-" TYPE_X86_CPU, "family", "6" }, ++ /* pc_rhel_8_5_compat from pc_compat_6_0 */ ++ { "qemu64" "-" TYPE_X86_CPU, "model", "6" }, ++ /* pc_rhel_8_5_compat from pc_compat_6_0 */ ++ { "qemu64" "-" TYPE_X86_CPU, "stepping", "3" }, ++ /* pc_rhel_8_5_compat from pc_compat_6_0 */ ++ { TYPE_X86_CPU, "x-vendor-cpuid-only", "off" }, ++ /* pc_rhel_8_5_compat from pc_compat_6_0 */ ++ { "ICH9-LPC", ACPI_PM_PROP_ACPI_PCIHP_BRIDGE, "off" }, ++ ++ /* pc_rhel_8_5_compat from pc_compat_6_1 */ ++ { TYPE_X86_CPU, "hv-version-id-build", "0x1bbc" }, ++ /* pc_rhel_8_5_compat from pc_compat_6_1 */ ++ { TYPE_X86_CPU, "hv-version-id-major", "0x0006" }, ++ /* pc_rhel_8_5_compat from pc_compat_6_1 */ ++ { TYPE_X86_CPU, "hv-version-id-minor", "0x0001" }, ++}; ++const size_t pc_rhel_8_5_compat_len = G_N_ELEMENTS(pc_rhel_8_5_compat); ++ ++GlobalProperty pc_rhel_8_4_compat[] = { ++ /* pc_rhel_8_4_compat from pc_compat_5_2 */ ++ { "ICH9-LPC", "x-smi-cpu-hotunplug", "off" }, ++ { TYPE_X86_CPU, "kvm-asyncpf-int", "off" }, ++}; ++const size_t pc_rhel_8_4_compat_len = G_N_ELEMENTS(pc_rhel_8_4_compat); ++ ++GlobalProperty pc_rhel_8_3_compat[] = { ++ /* pc_rhel_8_3_compat from pc_compat_5_1 */ ++ { "ICH9-LPC", "x-smi-cpu-hotplug", "off" }, ++}; ++const size_t pc_rhel_8_3_compat_len = G_N_ELEMENTS(pc_rhel_8_3_compat); ++ ++GlobalProperty pc_rhel_8_2_compat[] = { ++ /* pc_rhel_8_2_compat from pc_compat_4_2 */ ++ { "mch", "smbase-smram", "off" }, ++}; ++const size_t pc_rhel_8_2_compat_len = G_N_ELEMENTS(pc_rhel_8_2_compat); ++ ++/* pc_rhel_8_1_compat is empty since pc_4_1_compat is */ ++GlobalProperty pc_rhel_8_1_compat[] = { }; ++const size_t pc_rhel_8_1_compat_len = G_N_ELEMENTS(pc_rhel_8_1_compat); ++ ++GlobalProperty pc_rhel_8_0_compat[] = { ++ /* pc_rhel_8_0_compat from pc_compat_3_1 */ ++ { "intel-iommu", "dma-drain", "off" }, ++ /* pc_rhel_8_0_compat from pc_compat_3_1 */ ++ { "Opteron_G3" "-" TYPE_X86_CPU, "rdtscp", "off" }, ++ /* pc_rhel_8_0_compat from pc_compat_3_1 */ ++ { "Opteron_G4" "-" TYPE_X86_CPU, "rdtscp", "off" }, ++ /* pc_rhel_8_0_compat from pc_compat_3_1 */ ++ { "Opteron_G4" "-" TYPE_X86_CPU, "npt", "off" }, ++ /* pc_rhel_8_0_compat from pc_compat_3_1 */ ++ { "Opteron_G4" "-" TYPE_X86_CPU, "nrip-save", "off" }, ++ /* pc_rhel_8_0_compat from pc_compat_3_1 */ ++ { "Opteron_G5" "-" TYPE_X86_CPU, "rdtscp", "off" }, ++ /* pc_rhel_8_0_compat from pc_compat_3_1 */ ++ { "Opteron_G5" "-" TYPE_X86_CPU, "npt", "off" }, ++ /* pc_rhel_8_0_compat from pc_compat_3_1 */ ++ { "Opteron_G5" "-" TYPE_X86_CPU, "nrip-save", "off" }, ++ /* pc_rhel_8_0_compat from pc_compat_3_1 */ ++ { "EPYC" "-" TYPE_X86_CPU, "npt", "off" }, ++ /* pc_rhel_8_0_compat from pc_compat_3_1 */ ++ { "EPYC" "-" TYPE_X86_CPU, "nrip-save", "off" }, ++ /* pc_rhel_8_0_compat from pc_compat_3_1 */ ++ { "EPYC-IBPB" "-" TYPE_X86_CPU, "npt", "off" }, ++ /* pc_rhel_8_0_compat from pc_compat_3_1 */ ++ { "EPYC-IBPB" "-" TYPE_X86_CPU, "nrip-save", "off" }, ++ /** The mpx=on entries from pc_compat_3_1 are in pc_rhel_7_6_compat **/ ++ /* pc_rhel_8_0_compat from pc_compat_3_1 */ ++ { "Cascadelake-Server" "-" TYPE_X86_CPU, "stepping", "5" }, ++ /* pc_rhel_8_0_compat from pc_compat_3_1 */ ++ { TYPE_X86_CPU, "x-intel-pt-auto-level", "off" }, ++}; ++const size_t pc_rhel_8_0_compat_len = G_N_ELEMENTS(pc_rhel_8_0_compat); ++ ++/* Similar to PC_COMPAT_3_0 + PC_COMPAT_2_12, but: ++ * all of the 2_12 stuff was already in 7.6 from bz 1481253 ++ * x-migrate-smi-count comes from PC_COMPAT_2_11 but ++ * is really tied to kernel version so keep it off on 7.x ++ * machine types irrespective of host. ++ */ ++GlobalProperty pc_rhel_7_6_compat[] = { ++ /* pc_rhel_7_6_compat from pc_compat_3_0 */ ++ { TYPE_X86_CPU, "x-hv-synic-kvm-only", "on" }, ++ /* pc_rhel_7_6_compat from pc_compat_3_0 */ ++ { "Skylake-Server" "-" TYPE_X86_CPU, "pku", "off" }, ++ /* pc_rhel_7_6_compat from pc_compat_3_0 */ ++ { "Skylake-Server-IBRS" "-" TYPE_X86_CPU, "pku", "off" }, ++ /* pc_rhel_7_6_compat from pc_compat_2_11 */ ++ { TYPE_X86_CPU, "x-migrate-smi-count", "off" }, ++ /* pc_rhel_7_6_compat from pc_compat_2_11 */ ++ { "Skylake-Client" "-" TYPE_X86_CPU, "mpx", "on" }, ++ /* pc_rhel_7_6_compat from pc_compat_2_11 */ ++ { "Skylake-Client-IBRS" "-" TYPE_X86_CPU, "mpx", "on" }, ++ /* pc_rhel_7_6_compat from pc_compat_2_11 */ ++ { "Skylake-Server" "-" TYPE_X86_CPU, "mpx", "on" }, ++ /* pc_rhel_7_6_compat from pc_compat_2_11 */ ++ { "Skylake-Server-IBRS" "-" TYPE_X86_CPU, "mpx", "on" }, ++ /* pc_rhel_7_6_compat from pc_compat_2_11 */ ++ { "Cascadelake-Server" "-" TYPE_X86_CPU, "mpx", "on" }, ++ /* pc_rhel_7_6_compat from pc_compat_2_11 */ ++ { "Icelake-Client" "-" TYPE_X86_CPU, "mpx", "on" }, ++ /* pc_rhel_7_6_compat from pc_compat_2_11 */ ++ { "Icelake-Server" "-" TYPE_X86_CPU, "mpx", "on" }, ++}; ++const size_t pc_rhel_7_6_compat_len = G_N_ELEMENTS(pc_rhel_7_6_compat); ++ ++/* ++ * The PC_RHEL_*_COMPAT serve the same purpose for RHEL-7 machine ++ * types as the PC_COMPAT_* do for upstream types. ++ * PC_RHEL_7_*_COMPAT apply both to i440fx and q35 types. ++ */ ++ + 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) + pcmc->pvh_enabled = true; + pcmc->kvmclock_create_always = true; + assert(!mc->get_hotplug_handler); ++ mc->async_pf_vmexit_disable = false; + mc->get_hotplug_handler = pc_get_hotplug_handler; + mc->hotplug_allowed = pc_hotplug_allowed; + mc->cpu_index_to_instance_props = x86_cpu_index_to_props; +@@ -1748,7 +1880,8 @@ 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; +- mc->max_cpus = 255; ++ /* 240: max CPU count for RHEL */ ++ mc->max_cpus = 240; + mc->reset = pc_machine_reset; + 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 +--- a/hw/i386/pc_piix.c ++++ b/hw/i386/pc_piix.c +@@ -50,6 +50,7 @@ + #include "qapi/error.h" + #include "qemu/error-report.h" + #include "sysemu/xen.h" ++#include "migration/migration.h" + #ifdef CONFIG_XEN + #include + #include "hw/xen/xen_pt.h" +@@ -174,8 +175,8 @@ static void pc_init1(MachineState *machine, + if (pcmc->smbios_defaults) { + MachineClass *mc = MACHINE_GET_CLASS(machine); + /* These values are guest ABI, do not change */ +- smbios_set_defaults("QEMU", "Standard PC (i440FX + PIIX, 1996)", +- mc->name, pcmc->smbios_legacy_mode, ++ smbios_set_defaults("Red Hat", "KVM", ++ mc->desc, pcmc->smbios_legacy_mode, + pcmc->smbios_uuid_encoded, + pcmc->smbios_stream_product, + pcmc->smbios_stream_version, +@@ -314,6 +315,7 @@ static void pc_init1(MachineState *machine, + * hw_compat_*, pc_compat_*, or * pc_*_machine_options(). + */ + ++#if 0 /* Disabled for Red Hat Enterprise Linux */ + 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) + DEFINE_PC_MACHINE(xenfv, "xenfv-3.1", pc_xen_hvm_init, + xenfv_3_1_machine_options); + #endif ++#endif /* Disabled for Red Hat Enterprise Linux */ ++ ++/* Red Hat Enterprise Linux machine types */ ++ ++/* Options for the latest rhel7 machine type */ ++static void pc_machine_rhel7_options(MachineClass *m) ++{ ++ PCMachineClass *pcmc = PC_MACHINE_CLASS(m); ++ m->family = "pc_piix_Y"; ++ m->default_machine_opts = "firmware=bios-256k.bin,hpet=off"; ++ pcmc->default_nic_model = "e1000"; ++ pcmc->pci_root_uid = 0; ++ m->default_display = "std"; ++ m->no_parallel = 1; ++ m->numa_mem_supported = true; ++ m->auto_enable_numa_with_memdev = false; ++ machine_class_allow_dynamic_sysbus_dev(m, TYPE_RAMFB_DEVICE); ++ compat_props_add(m->compat_props, pc_rhel_compat, pc_rhel_compat_len); ++ m->alias = "pc"; ++ m->is_default = 1; ++ m->smp_props.prefer_sockets = true; ++} ++ ++static void pc_init_rhel760(MachineState *machine) ++{ ++ pc_init1(machine, TYPE_I440FX_PCI_HOST_BRIDGE, \ ++ TYPE_I440FX_PCI_DEVICE); ++} ++ ++static void pc_machine_rhel760_options(MachineClass *m) ++{ ++ PCMachineClass *pcmc = PC_MACHINE_CLASS(m); ++ pc_machine_rhel7_options(m); ++ m->desc = "RHEL 7.6.0 PC (i440FX + PIIX, 1996)"; ++ m->async_pf_vmexit_disable = true; ++ m->smbus_no_migration_support = true; ++ ++ /* All RHEL machines for prior major releases are deprecated */ ++ m->deprecation_reason = rhel_old_machine_deprecation; ++ ++ pcmc->pvh_enabled = false; ++ pcmc->default_cpu_version = CPU_VERSION_LEGACY; ++ 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_8_6, ++ hw_compat_rhel_8_6_len); ++ compat_props_add(m->compat_props, hw_compat_rhel_8_5, ++ hw_compat_rhel_8_5_len); ++ compat_props_add(m->compat_props, pc_rhel_8_5_compat, ++ pc_rhel_8_5_compat_len); ++ compat_props_add(m->compat_props, hw_compat_rhel_8_4, ++ hw_compat_rhel_8_4_len); ++ compat_props_add(m->compat_props, pc_rhel_8_4_compat, ++ pc_rhel_8_4_compat_len); ++ compat_props_add(m->compat_props, hw_compat_rhel_8_3, ++ hw_compat_rhel_8_3_len); ++ compat_props_add(m->compat_props, pc_rhel_8_3_compat, ++ pc_rhel_8_3_compat_len); ++ compat_props_add(m->compat_props, hw_compat_rhel_8_2, ++ hw_compat_rhel_8_2_len); ++ compat_props_add(m->compat_props, pc_rhel_8_2_compat, ++ pc_rhel_8_2_compat_len); ++ compat_props_add(m->compat_props, hw_compat_rhel_8_1, hw_compat_rhel_8_1_len); ++ compat_props_add(m->compat_props, pc_rhel_8_1_compat, pc_rhel_8_1_compat_len); ++ compat_props_add(m->compat_props, hw_compat_rhel_8_0, hw_compat_rhel_8_0_len); ++ compat_props_add(m->compat_props, pc_rhel_8_0_compat, pc_rhel_8_0_compat_len); ++ compat_props_add(m->compat_props, hw_compat_rhel_7_6, hw_compat_rhel_7_6_len); ++ compat_props_add(m->compat_props, pc_rhel_7_6_compat, pc_rhel_7_6_compat_len); ++} ++ ++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 +--- a/hw/i386/pc_q35.c ++++ b/hw/i386/pc_q35.c +@@ -197,8 +197,8 @@ static void pc_q35_init(MachineState *machine) + + if (pcmc->smbios_defaults) { + /* These values are guest ABI, do not change */ +- smbios_set_defaults("QEMU", "Standard PC (Q35 + ICH9, 2009)", +- mc->name, pcmc->smbios_legacy_mode, ++ smbios_set_defaults("Red Hat", "KVM", ++ mc->desc, pcmc->smbios_legacy_mode, + pcmc->smbios_uuid_encoded, + pcmc->smbios_stream_product, + pcmc->smbios_stream_version, +@@ -342,6 +342,7 @@ static void pc_q35_init(MachineState *machine) + DEFINE_PC_MACHINE(suffix, name, pc_init_##suffix, optionfn) + + ++#if 0 /* Disabled for Red Hat Enterprise Linux */ + 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) + + DEFINE_Q35_MACHINE(v2_4, "pc-q35-2.4", NULL, + pc_q35_2_4_machine_options); ++#endif /* Disabled for Red Hat Enterprise Linux */ ++ ++/* Red Hat Enterprise Linux machine types */ ++ ++/* Options for the latest rhel q35 machine type */ ++static void pc_q35_machine_rhel_options(MachineClass *m) ++{ ++ PCMachineClass *pcmc = PC_MACHINE_CLASS(m); ++ pcmc->default_nic_model = "e1000e"; ++ pcmc->pci_root_uid = 0; ++ m->family = "pc_q35_Z"; ++ m->units_per_default_bus = 1; ++ m->default_machine_opts = "firmware=bios-256k.bin,hpet=off"; ++ m->default_display = "std"; ++ m->no_floppy = 1; ++ m->no_parallel = 1; ++ pcmc->default_cpu_version = 1; ++ machine_class_allow_dynamic_sysbus_dev(m, TYPE_AMD_IOMMU_DEVICE); ++ machine_class_allow_dynamic_sysbus_dev(m, TYPE_INTEL_IOMMU_DEVICE); ++ machine_class_allow_dynamic_sysbus_dev(m, TYPE_RAMFB_DEVICE); ++ m->alias = "q35"; ++ m->max_cpus = 710; ++ compat_props_add(m->compat_props, pc_rhel_compat, pc_rhel_compat_len); ++} ++ ++static void pc_q35_init_rhel900(MachineState *machine) ++{ ++ pc_q35_init(machine); ++} ++ ++static void pc_q35_machine_rhel900_options(MachineClass *m) ++{ ++ PCMachineClass *pcmc = PC_MACHINE_CLASS(m); ++ pc_q35_machine_rhel_options(m); ++ m->desc = "RHEL-9.0.0 PC (Q35 + ICH9, 2009)"; ++ pcmc->smbios_stream_product = "RHEL"; ++ pcmc->smbios_stream_version = "9.0.0"; ++} ++ ++DEFINE_PC_MACHINE(q35_rhel900, "pc-q35-rhel9.0.0", pc_q35_init_rhel900, ++ pc_q35_machine_rhel900_options); ++ ++static void pc_q35_init_rhel860(MachineState *machine) ++{ ++ pc_q35_init(machine); ++} ++ ++static void pc_q35_machine_rhel860_options(MachineClass *m) ++{ ++ PCMachineClass *pcmc = PC_MACHINE_CLASS(m); ++ pc_q35_machine_rhel900_options(m); ++ m->desc = "RHEL-8.6.0 PC (Q35 + ICH9, 2009)"; ++ m->alias = NULL; ++ ++ /* All RHEL machines for prior major releases are deprecated */ ++ m->deprecation_reason = rhel_old_machine_deprecation; ++ ++ pcmc->smbios_stream_product = "RHEL-AV"; ++ pcmc->smbios_stream_version = "8.6.0"; ++ compat_props_add(m->compat_props, hw_compat_rhel_8_6, ++ hw_compat_rhel_8_6_len); ++} ++ ++DEFINE_PC_MACHINE(q35_rhel860, "pc-q35-rhel8.6.0", pc_q35_init_rhel860, ++ pc_q35_machine_rhel860_options); ++ ++ ++static void pc_q35_init_rhel850(MachineState *machine) ++{ ++ pc_q35_init(machine); ++} ++ ++static void pc_q35_machine_rhel850_options(MachineClass *m) ++{ ++ PCMachineClass *pcmc = PC_MACHINE_CLASS(m); ++ pc_q35_machine_rhel860_options(m); ++ m->desc = "RHEL-8.5.0 PC (Q35 + ICH9, 2009)"; ++ m->alias = NULL; ++ pcmc->smbios_stream_product = "RHEL-AV"; ++ pcmc->smbios_stream_version = "8.5.0"; ++ compat_props_add(m->compat_props, hw_compat_rhel_8_5, ++ hw_compat_rhel_8_5_len); ++ compat_props_add(m->compat_props, pc_rhel_8_5_compat, ++ pc_rhel_8_5_compat_len); ++ m->smp_props.prefer_sockets = true; ++} ++ ++DEFINE_PC_MACHINE(q35_rhel850, "pc-q35-rhel8.5.0", pc_q35_init_rhel850, ++ pc_q35_machine_rhel850_options); ++ ++ ++static void pc_q35_init_rhel840(MachineState *machine) ++{ ++ pc_q35_init(machine); ++} ++ ++static void pc_q35_machine_rhel840_options(MachineClass *m) ++{ ++ PCMachineClass *pcmc = PC_MACHINE_CLASS(m); ++ pc_q35_machine_rhel850_options(m); ++ m->desc = "RHEL-8.4.0 PC (Q35 + ICH9, 2009)"; ++ m->alias = NULL; ++ pcmc->smbios_stream_product = "RHEL-AV"; ++ pcmc->smbios_stream_version = "8.4.0"; ++ compat_props_add(m->compat_props, hw_compat_rhel_8_4, ++ hw_compat_rhel_8_4_len); ++ compat_props_add(m->compat_props, pc_rhel_8_4_compat, ++ pc_rhel_8_4_compat_len); ++} ++ ++DEFINE_PC_MACHINE(q35_rhel840, "pc-q35-rhel8.4.0", pc_q35_init_rhel840, ++ pc_q35_machine_rhel840_options); ++ ++ ++static void pc_q35_init_rhel830(MachineState *machine) ++{ ++ pc_q35_init(machine); ++} ++ ++static void pc_q35_machine_rhel830_options(MachineClass *m) ++{ ++ PCMachineClass *pcmc = PC_MACHINE_CLASS(m); ++ pc_q35_machine_rhel840_options(m); ++ m->desc = "RHEL-8.3.0 PC (Q35 + ICH9, 2009)"; ++ m->alias = NULL; ++ pcmc->smbios_stream_product = "RHEL-AV"; ++ pcmc->smbios_stream_version = "8.3.0"; ++ compat_props_add(m->compat_props, hw_compat_rhel_8_3, ++ hw_compat_rhel_8_3_len); ++ compat_props_add(m->compat_props, pc_rhel_8_3_compat, ++ pc_rhel_8_3_compat_len); ++ /* From pc_q35_5_1_machine_options() */ ++ pcmc->kvmclock_create_always = false; ++ /* From pc_q35_5_1_machine_options() */ ++ pcmc->pci_root_uid = 1; ++} ++ ++DEFINE_PC_MACHINE(q35_rhel830, "pc-q35-rhel8.3.0", pc_q35_init_rhel830, ++ pc_q35_machine_rhel830_options); ++ ++static void pc_q35_init_rhel820(MachineState *machine) ++{ ++ pc_q35_init(machine); ++} ++ ++static void pc_q35_machine_rhel820_options(MachineClass *m) ++{ ++ PCMachineClass *pcmc = PC_MACHINE_CLASS(m); ++ pc_q35_machine_rhel830_options(m); ++ m->desc = "RHEL-8.2.0 PC (Q35 + ICH9, 2009)"; ++ m->alias = NULL; ++ m->numa_mem_supported = true; ++ m->auto_enable_numa_with_memdev = false; ++ pcmc->smbios_stream_product = "RHEL-AV"; ++ pcmc->smbios_stream_version = "8.2.0"; ++ compat_props_add(m->compat_props, hw_compat_rhel_8_2, ++ hw_compat_rhel_8_2_len); ++ compat_props_add(m->compat_props, pc_rhel_8_2_compat, ++ pc_rhel_8_2_compat_len); ++} ++ ++DEFINE_PC_MACHINE(q35_rhel820, "pc-q35-rhel8.2.0", pc_q35_init_rhel820, ++ pc_q35_machine_rhel820_options); ++ ++static void pc_q35_init_rhel810(MachineState *machine) ++{ ++ pc_q35_init(machine); ++} ++ ++static void pc_q35_machine_rhel810_options(MachineClass *m) ++{ ++ PCMachineClass *pcmc = PC_MACHINE_CLASS(m); ++ pc_q35_machine_rhel820_options(m); ++ m->desc = "RHEL-8.1.0 PC (Q35 + ICH9, 2009)"; ++ m->alias = NULL; ++ pcmc->smbios_stream_product = NULL; ++ pcmc->smbios_stream_version = NULL; ++ compat_props_add(m->compat_props, hw_compat_rhel_8_1, hw_compat_rhel_8_1_len); ++ compat_props_add(m->compat_props, pc_rhel_8_1_compat, pc_rhel_8_1_compat_len); ++} ++ ++DEFINE_PC_MACHINE(q35_rhel810, "pc-q35-rhel8.1.0", pc_q35_init_rhel810, ++ pc_q35_machine_rhel810_options); ++ ++static void pc_q35_init_rhel800(MachineState *machine) ++{ ++ pc_q35_init(machine); ++} ++ ++static void pc_q35_machine_rhel800_options(MachineClass *m) ++{ ++ PCMachineClass *pcmc = PC_MACHINE_CLASS(m); ++ pc_q35_machine_rhel810_options(m); ++ m->desc = "RHEL-8.0.0 PC (Q35 + ICH9, 2009)"; ++ m->smbus_no_migration_support = true; ++ m->alias = NULL; ++ pcmc->pvh_enabled = false; ++ pcmc->default_cpu_version = CPU_VERSION_LEGACY; ++ compat_props_add(m->compat_props, hw_compat_rhel_8_0, hw_compat_rhel_8_0_len); ++ compat_props_add(m->compat_props, pc_rhel_8_0_compat, pc_rhel_8_0_compat_len); ++} ++ ++DEFINE_PC_MACHINE(q35_rhel800, "pc-q35-rhel8.0.0", pc_q35_init_rhel800, ++ pc_q35_machine_rhel800_options); ++ ++static void pc_q35_init_rhel760(MachineState *machine) ++{ ++ pc_q35_init(machine); ++} ++ ++static void pc_q35_machine_rhel760_options(MachineClass *m) ++{ ++ pc_q35_machine_rhel800_options(m); ++ m->alias = NULL; ++ m->desc = "RHEL-7.6.0 PC (Q35 + ICH9, 2009)"; ++ m->async_pf_vmexit_disable = true; ++ compat_props_add(m->compat_props, hw_compat_rhel_7_6, hw_compat_rhel_7_6_len); ++ compat_props_add(m->compat_props, pc_rhel_7_6_compat, pc_rhel_7_6_compat_len); ++} ++ ++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 +--- 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) + static void ccw_machine_rhel860_class_options(MachineClass *mc) + { + ccw_machine_rhel900_class_options(mc); ++ compat_props_add(mc->compat_props, hw_compat_rhel_8_6, hw_compat_rhel_8_6_len); + + /* 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 +--- a/include/hw/boards.h ++++ b/include/hw/boards.h +@@ -266,6 +266,8 @@ struct MachineClass { + strList *allowed_dynamic_sysbus_devices; + bool auto_enable_numa_with_memhp; + bool auto_enable_numa_with_memdev; ++ /* RHEL only */ ++ bool async_pf_vmexit_disable; + 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 +--- 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; + 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_8_5_compat[]; ++extern const size_t pc_rhel_8_5_compat_len; ++ ++extern GlobalProperty pc_rhel_8_4_compat[]; ++extern const size_t pc_rhel_8_4_compat_len; ++ ++extern GlobalProperty pc_rhel_8_3_compat[]; ++extern const size_t pc_rhel_8_3_compat_len; ++ ++extern GlobalProperty pc_rhel_8_2_compat[]; ++extern const size_t pc_rhel_8_2_compat_len; ++ ++extern GlobalProperty pc_rhel_8_1_compat[]; ++extern const size_t pc_rhel_8_1_compat_len; ++ ++extern GlobalProperty pc_rhel_8_0_compat[]; ++extern const size_t pc_rhel_8_0_compat_len; ++ ++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. + */ +diff --git a/target/i386/kvm/kvm-cpu.c b/target/i386/kvm/kvm-cpu.c +index 5eb955ce9a..74c1396a93 100644 +--- a/target/i386/kvm/kvm-cpu.c ++++ b/target/i386/kvm/kvm-cpu.c +@@ -137,6 +137,7 @@ static PropValue kvm_default_props[] = { + { "acpi", "off" }, + { "monitor", "off" }, + { "svm", "off" }, ++ { "kvm-pv-unhalt", "on" }, + { NULL, NULL }, + }; + +diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c +index 9cf8e03669..6d1e009443 100644 +--- a/target/i386/kvm/kvm.c ++++ b/target/i386/kvm/kvm.c +@@ -3488,6 +3488,7 @@ 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; ++ MachineClass *mc = MACHINE_GET_CLASS(qdev_get_machine()); + + kvm_msr_buf_reset(cpu); + +@@ -3822,6 +3823,9 @@ static int kvm_get_msrs(X86CPU *cpu) + break; + case MSR_KVM_ASYNC_PF_EN: + env->async_pf_en_msr = msrs[i].data; ++ if (mc->async_pf_vmexit_disable) { ++ env->async_pf_en_msr &= ~(1ULL << 2); ++ } + break; + 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 +--- a/tests/qtest/pvpanic-test.c ++++ b/tests/qtest/pvpanic-test.c +@@ -17,7 +17,7 @@ static void test_panic_nopause(void) + QDict *response, *data; + QTestState *qts; + +- qts = qtest_init("-device pvpanic -action panic=none"); ++ qts = qtest_init("-M q35 -device pvpanic -action panic=none"); + + val = qtest_inb(qts, 0x505); + g_assert_cmpuint(val, ==, 3); +@@ -40,7 +40,8 @@ static void test_panic(void) + QDict *response, *data; + QTestState *qts; + +- qts = qtest_init("-device pvpanic -action panic=pause"); ++ /* RHEL: Use q35 */ ++ qts = qtest_init("-M q35 -device pvpanic -action panic=pause"); + + val = qtest_inb(qts, 0x505); + g_assert_cmpuint(val, ==, 3); +-- +2.31.1 + diff --git a/SOURCES/0011-Add-x86_64-machine-types.patch b/SOURCES/0011-Add-x86_64-machine-types.patch deleted file mode 100644 index aecc3fb..0000000 --- a/SOURCES/0011-Add-x86_64-machine-types.patch +++ /dev/null @@ -1,572 +0,0 @@ -From afe0cbc5cdb98998b37cf48e9a1c87a110d9fbb3 Mon Sep 17 00:00:00 2001 -From: Miroslav Rezanina -Date: Fri, 19 Oct 2018 13:10:31 +0200 -Subject: Add x86_64 machine types - -Adding changes to add RHEL machine types for x86_64 architecture. - -Signed-off-by: Miroslav Rezanina - -Rebase notes (6.1.0): -- Update qemu64 cpu spec - -Merged patches (6.1.0): -- 59c284ad3b x86: Add x86 rhel8.5 machine types -- a8868b42fe redhat: x86: Enable 'kvm-asyncpf-int' by default -- a3995e2eff Remove RHEL 7.0.0 machine type (only x86_64 changes) -- ad3190a79b Remove RHEL 7.1.0 machine type (only x86_64 changes) -- 84bbe15d4e Remove RHEL 7.2.0 machine type (only x86_64 changes) -- 0215eb3356 Remove RHEL 7.3.0 machine types (only x86_64 changes) -- af69d1ca6e Remove RHEL 7.4.0 machine types (only x86_64 changes) -- 8f7a74ab78 Remove RHEL 7.5.0 machine types (only x86_64 changes) ---- - hw/i386/pc.c | 114 +++++++++++++++++++++++- - hw/i386/pc_piix.c | 68 +++++++++++++- - hw/i386/pc_q35.c | 177 ++++++++++++++++++++++++++++++++++++- - include/hw/boards.h | 2 + - include/hw/i386/pc.h | 21 +++++ - target/i386/kvm/kvm-cpu.c | 1 + - target/i386/kvm/kvm.c | 4 + - tests/qtest/pvpanic-test.c | 5 +- - 8 files changed, 385 insertions(+), 7 deletions(-) - -diff --git a/hw/i386/pc.c b/hw/i386/pc.c -index a2ef40ecbc..b6d2db8d04 100644 ---- a/hw/i386/pc.c -+++ b/hw/i386/pc.c -@@ -371,6 +371,116 @@ GlobalProperty pc_compat_1_4[] = { - }; - const size_t pc_compat_1_4_len = G_N_ELEMENTS(pc_compat_1_4); - -+/* This macro is for changes to properties that are RHEL specific, -+ * different to the current upstream and to be applied to the latest -+ * machine type. -+ */ -+GlobalProperty pc_rhel_compat[] = { -+ { 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" }, -+ { TYPE_X86_CPU, "vmx-exit-load-perf-global-ctrl", "off" }, -+ /* bz 1508330 */ -+ { "vfio-pci", "x-no-geforce-quirks", "on" }, -+ /* bz 1941397 */ -+ { TYPE_X86_CPU, "kvm-asyncpf-int", "on" }, -+}; -+const size_t pc_rhel_compat_len = G_N_ELEMENTS(pc_rhel_compat); -+ -+GlobalProperty pc_rhel_8_4_compat[] = { -+ /* pc_rhel_8_4_compat from pc_compat_5_2 */ -+ { "ICH9-LPC", "x-smi-cpu-hotunplug", "off" }, -+ { TYPE_X86_CPU, "kvm-asyncpf-int", "off" }, -+}; -+const size_t pc_rhel_8_4_compat_len = G_N_ELEMENTS(pc_rhel_8_4_compat); -+ -+GlobalProperty pc_rhel_8_3_compat[] = { -+ /* pc_rhel_8_3_compat from pc_compat_5_1 */ -+ { "ICH9-LPC", "x-smi-cpu-hotplug", "off" }, -+}; -+const size_t pc_rhel_8_3_compat_len = G_N_ELEMENTS(pc_rhel_8_3_compat); -+ -+GlobalProperty pc_rhel_8_2_compat[] = { -+ /* pc_rhel_8_2_compat from pc_compat_4_2 */ -+ { "mch", "smbase-smram", "off" }, -+}; -+const size_t pc_rhel_8_2_compat_len = G_N_ELEMENTS(pc_rhel_8_2_compat); -+ -+/* pc_rhel_8_1_compat is empty since pc_4_1_compat is */ -+GlobalProperty pc_rhel_8_1_compat[] = { }; -+const size_t pc_rhel_8_1_compat_len = G_N_ELEMENTS(pc_rhel_8_1_compat); -+ -+GlobalProperty pc_rhel_8_0_compat[] = { -+ /* pc_rhel_8_0_compat from pc_compat_3_1 */ -+ { "intel-iommu", "dma-drain", "off" }, -+ /* pc_rhel_8_0_compat from pc_compat_3_1 */ -+ { "Opteron_G3" "-" TYPE_X86_CPU, "rdtscp", "off" }, -+ /* pc_rhel_8_0_compat from pc_compat_3_1 */ -+ { "Opteron_G4" "-" TYPE_X86_CPU, "rdtscp", "off" }, -+ /* pc_rhel_8_0_compat from pc_compat_3_1 */ -+ { "Opteron_G4" "-" TYPE_X86_CPU, "npt", "off" }, -+ /* pc_rhel_8_0_compat from pc_compat_3_1 */ -+ { "Opteron_G4" "-" TYPE_X86_CPU, "nrip-save", "off" }, -+ /* pc_rhel_8_0_compat from pc_compat_3_1 */ -+ { "Opteron_G5" "-" TYPE_X86_CPU, "rdtscp", "off" }, -+ /* pc_rhel_8_0_compat from pc_compat_3_1 */ -+ { "Opteron_G5" "-" TYPE_X86_CPU, "npt", "off" }, -+ /* pc_rhel_8_0_compat from pc_compat_3_1 */ -+ { "Opteron_G5" "-" TYPE_X86_CPU, "nrip-save", "off" }, -+ /* pc_rhel_8_0_compat from pc_compat_3_1 */ -+ { "EPYC" "-" TYPE_X86_CPU, "npt", "off" }, -+ /* pc_rhel_8_0_compat from pc_compat_3_1 */ -+ { "EPYC" "-" TYPE_X86_CPU, "nrip-save", "off" }, -+ /* pc_rhel_8_0_compat from pc_compat_3_1 */ -+ { "EPYC-IBPB" "-" TYPE_X86_CPU, "npt", "off" }, -+ /* pc_rhel_8_0_compat from pc_compat_3_1 */ -+ { "EPYC-IBPB" "-" TYPE_X86_CPU, "nrip-save", "off" }, -+ /** The mpx=on entries from pc_compat_3_1 are in pc_rhel_7_6_compat **/ -+ /* pc_rhel_8_0_compat from pc_compat_3_1 */ -+ { "Cascadelake-Server" "-" TYPE_X86_CPU, "stepping", "5" }, -+ /* pc_rhel_8_0_compat from pc_compat_3_1 */ -+ { TYPE_X86_CPU, "x-intel-pt-auto-level", "off" }, -+}; -+const size_t pc_rhel_8_0_compat_len = G_N_ELEMENTS(pc_rhel_8_0_compat); -+ -+/* Similar to PC_COMPAT_3_0 + PC_COMPAT_2_12, but: -+ * all of the 2_12 stuff was already in 7.6 from bz 1481253 -+ * x-migrate-smi-count comes from PC_COMPAT_2_11 but -+ * is really tied to kernel version so keep it off on 7.x -+ * machine types irrespective of host. -+ */ -+GlobalProperty pc_rhel_7_6_compat[] = { -+ /* pc_rhel_7_6_compat from pc_compat_3_0 */ -+ { TYPE_X86_CPU, "x-hv-synic-kvm-only", "on" }, -+ /* pc_rhel_7_6_compat from pc_compat_3_0 */ -+ { "Skylake-Server" "-" TYPE_X86_CPU, "pku", "off" }, -+ /* pc_rhel_7_6_compat from pc_compat_3_0 */ -+ { "Skylake-Server-IBRS" "-" TYPE_X86_CPU, "pku", "off" }, -+ /* pc_rhel_7_6_compat from pc_compat_2_11 */ -+ { TYPE_X86_CPU, "x-migrate-smi-count", "off" }, -+ /* pc_rhel_7_6_compat from pc_compat_2_11 */ -+ { "Skylake-Client" "-" TYPE_X86_CPU, "mpx", "on" }, -+ /* pc_rhel_7_6_compat from pc_compat_2_11 */ -+ { "Skylake-Client-IBRS" "-" TYPE_X86_CPU, "mpx", "on" }, -+ /* pc_rhel_7_6_compat from pc_compat_2_11 */ -+ { "Skylake-Server" "-" TYPE_X86_CPU, "mpx", "on" }, -+ /* pc_rhel_7_6_compat from pc_compat_2_11 */ -+ { "Skylake-Server-IBRS" "-" TYPE_X86_CPU, "mpx", "on" }, -+ /* pc_rhel_7_6_compat from pc_compat_2_11 */ -+ { "Cascadelake-Server" "-" TYPE_X86_CPU, "mpx", "on" }, -+ /* pc_rhel_7_6_compat from pc_compat_2_11 */ -+ { "Icelake-Client" "-" TYPE_X86_CPU, "mpx", "on" }, -+ /* pc_rhel_7_6_compat from pc_compat_2_11 */ -+ { "Icelake-Server" "-" TYPE_X86_CPU, "mpx", "on" }, -+}; -+const size_t pc_rhel_7_6_compat_len = G_N_ELEMENTS(pc_rhel_7_6_compat); -+ -+/* -+ * The PC_RHEL_*_COMPAT serve the same purpose for RHEL-7 machine -+ * types as the PC_COMPAT_* do for upstream types. -+ * PC_RHEL_7_*_COMPAT apply both to i440fx and q35 types. -+ */ -+ - GSIState *pc_gsi_create(qemu_irq **irqs, bool pci_enabled) - { - GSIState *s; -@@ -1694,6 +1804,7 @@ static void pc_machine_class_init(ObjectClass *oc, void *data) - pcmc->pvh_enabled = true; - pcmc->kvmclock_create_always = true; - assert(!mc->get_hotplug_handler); -+ mc->async_pf_vmexit_disable = false; - mc->get_hotplug_handler = pc_get_hotplug_handler; - mc->hotplug_allowed = pc_hotplug_allowed; - mc->cpu_index_to_instance_props = x86_cpu_index_to_props; -@@ -1704,7 +1815,8 @@ 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; -- mc->max_cpus = 255; -+ /* 240: max CPU count for RHEL */ -+ mc->max_cpus = 240; - mc->reset = pc_machine_reset; - 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 dda3f64f19..dabc6c1933 100644 ---- a/hw/i386/pc_piix.c -+++ b/hw/i386/pc_piix.c -@@ -50,6 +50,7 @@ - #include "qapi/error.h" - #include "qemu/error-report.h" - #include "sysemu/xen.h" -+#include "migration/migration.h" - #ifdef CONFIG_XEN - #include - #include "hw/xen/xen_pt.h" -@@ -174,8 +175,8 @@ static void pc_init1(MachineState *machine, - if (pcmc->smbios_defaults) { - MachineClass *mc = MACHINE_GET_CLASS(machine); - /* These values are guest ABI, do not change */ -- smbios_set_defaults("QEMU", "Standard PC (i440FX + PIIX, 1996)", -- mc->name, pcmc->smbios_legacy_mode, -+ smbios_set_defaults("Red Hat", "KVM", -+ mc->desc, pcmc->smbios_legacy_mode, - pcmc->smbios_uuid_encoded, - pcmc->smbios_stream_product, - pcmc->smbios_stream_version, -@@ -314,6 +315,7 @@ static void pc_init1(MachineState *machine, - * hw_compat_*, pc_compat_*, or * pc_*_machine_options(). - */ - -+#if 0 /* Disabled for Red Hat Enterprise Linux */ - static void pc_compat_2_3_fn(MachineState *machine) - { - X86MachineState *x86ms = X86_MACHINE(machine); -@@ -951,3 +953,65 @@ 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 -+#endif /* Disabled for Red Hat Enterprise Linux */ -+ -+/* Red Hat Enterprise Linux machine types */ -+ -+/* Options for the latest rhel7 machine type */ -+static void pc_machine_rhel7_options(MachineClass *m) -+{ -+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m); -+ m->family = "pc_piix_Y"; -+ m->default_machine_opts = "firmware=bios-256k.bin,hpet=off"; -+ pcmc->default_nic_model = "e1000"; -+ pcmc->pci_root_uid = 0; -+ m->default_display = "std"; -+ m->no_parallel = 1; -+ m->numa_mem_supported = true; -+ m->auto_enable_numa_with_memdev = false; -+ machine_class_allow_dynamic_sysbus_dev(m, TYPE_RAMFB_DEVICE); -+ compat_props_add(m->compat_props, pc_rhel_compat, pc_rhel_compat_len); -+ m->alias = "pc"; -+ m->is_default = 1; -+} -+ -+static void pc_init_rhel760(MachineState *machine) -+{ -+ pc_init1(machine, TYPE_I440FX_PCI_HOST_BRIDGE, \ -+ TYPE_I440FX_PCI_DEVICE); -+} -+ -+static void pc_machine_rhel760_options(MachineClass *m) -+{ -+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m); -+ pc_machine_rhel7_options(m); -+ m->desc = "RHEL 7.6.0 PC (i440FX + PIIX, 1996)"; -+ m->async_pf_vmexit_disable = true; -+ m->smbus_no_migration_support = true; -+ pcmc->pvh_enabled = false; -+ pcmc->default_cpu_version = CPU_VERSION_LEGACY; -+ 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_8_4, -+ hw_compat_rhel_8_4_len); -+ compat_props_add(m->compat_props, pc_rhel_8_4_compat, -+ pc_rhel_8_4_compat_len); -+ compat_props_add(m->compat_props, hw_compat_rhel_8_3, -+ hw_compat_rhel_8_3_len); -+ compat_props_add(m->compat_props, pc_rhel_8_3_compat, -+ pc_rhel_8_3_compat_len); -+ compat_props_add(m->compat_props, hw_compat_rhel_8_2, -+ hw_compat_rhel_8_2_len); -+ compat_props_add(m->compat_props, pc_rhel_8_2_compat, -+ pc_rhel_8_2_compat_len); -+ compat_props_add(m->compat_props, hw_compat_rhel_8_1, hw_compat_rhel_8_1_len); -+ compat_props_add(m->compat_props, pc_rhel_8_1_compat, pc_rhel_8_1_compat_len); -+ compat_props_add(m->compat_props, hw_compat_rhel_8_0, hw_compat_rhel_8_0_len); -+ compat_props_add(m->compat_props, pc_rhel_8_0_compat, pc_rhel_8_0_compat_len); -+ compat_props_add(m->compat_props, hw_compat_rhel_7_6, hw_compat_rhel_7_6_len); -+ compat_props_add(m->compat_props, pc_rhel_7_6_compat, pc_rhel_7_6_compat_len); -+} -+ -+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 235054a643..04c911da18 100644 ---- a/hw/i386/pc_q35.c -+++ b/hw/i386/pc_q35.c -@@ -197,8 +197,8 @@ static void pc_q35_init(MachineState *machine) - - if (pcmc->smbios_defaults) { - /* These values are guest ABI, do not change */ -- smbios_set_defaults("QEMU", "Standard PC (Q35 + ICH9, 2009)", -- mc->name, pcmc->smbios_legacy_mode, -+ smbios_set_defaults("Red Hat", "KVM", -+ mc->desc, pcmc->smbios_legacy_mode, - pcmc->smbios_uuid_encoded, - pcmc->smbios_stream_product, - pcmc->smbios_stream_version, -@@ -342,6 +342,7 @@ static void pc_q35_init(MachineState *machine) - DEFINE_PC_MACHINE(suffix, name, pc_init_##suffix, optionfn) - - -+#if 0 /* Disabled for Red Hat Enterprise Linux */ - static void pc_q35_machine_options(MachineClass *m) - { - PCMachineClass *pcmc = PC_MACHINE_CLASS(m); -@@ -620,3 +621,175 @@ 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); -+#endif /* Disabled for Red Hat Enterprise Linux */ -+ -+/* Red Hat Enterprise Linux machine types */ -+ -+/* Options for the latest rhel q35 machine type */ -+static void pc_q35_machine_rhel_options(MachineClass *m) -+{ -+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m); -+ pcmc->default_nic_model = "e1000e"; -+ pcmc->pci_root_uid = 0; -+ m->family = "pc_q35_Z"; -+ m->units_per_default_bus = 1; -+ m->default_machine_opts = "firmware=bios-256k.bin,hpet=off"; -+ m->default_display = "std"; -+ m->no_floppy = 1; -+ m->no_parallel = 1; -+ pcmc->default_cpu_version = 1; -+ machine_class_allow_dynamic_sysbus_dev(m, TYPE_AMD_IOMMU_DEVICE); -+ machine_class_allow_dynamic_sysbus_dev(m, TYPE_INTEL_IOMMU_DEVICE); -+ machine_class_allow_dynamic_sysbus_dev(m, TYPE_RAMFB_DEVICE); -+ m->alias = "q35"; -+ m->max_cpus = 710; -+ compat_props_add(m->compat_props, pc_rhel_compat, pc_rhel_compat_len); -+} -+ -+static void pc_q35_init_rhel850(MachineState *machine) -+{ -+ pc_q35_init(machine); -+} -+ -+static void pc_q35_machine_rhel850_options(MachineClass *m) -+{ -+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m); -+ pc_q35_machine_rhel_options(m); -+ m->desc = "RHEL-8.5.0 PC (Q35 + ICH9, 2009)"; -+ pcmc->smbios_stream_product = "RHEL-AV"; -+ pcmc->smbios_stream_version = "8.5.0"; -+} -+ -+DEFINE_PC_MACHINE(q35_rhel850, "pc-q35-rhel8.5.0", pc_q35_init_rhel850, -+ pc_q35_machine_rhel850_options); -+ -+ -+static void pc_q35_init_rhel840(MachineState *machine) -+{ -+ pc_q35_init(machine); -+} -+ -+static void pc_q35_machine_rhel840_options(MachineClass *m) -+{ -+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m); -+ pc_q35_machine_rhel850_options(m); -+ m->desc = "RHEL-8.4.0 PC (Q35 + ICH9, 2009)"; -+ m->alias = NULL; -+ pcmc->smbios_stream_product = "RHEL-AV"; -+ pcmc->smbios_stream_version = "8.4.0"; -+ compat_props_add(m->compat_props, hw_compat_rhel_8_4, -+ hw_compat_rhel_8_4_len); -+ compat_props_add(m->compat_props, pc_rhel_8_4_compat, -+ pc_rhel_8_4_compat_len); -+} -+ -+DEFINE_PC_MACHINE(q35_rhel840, "pc-q35-rhel8.4.0", pc_q35_init_rhel840, -+ pc_q35_machine_rhel840_options); -+ -+ -+static void pc_q35_init_rhel830(MachineState *machine) -+{ -+ pc_q35_init(machine); -+} -+ -+static void pc_q35_machine_rhel830_options(MachineClass *m) -+{ -+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m); -+ pc_q35_machine_rhel840_options(m); -+ m->desc = "RHEL-8.3.0 PC (Q35 + ICH9, 2009)"; -+ pcmc->smbios_stream_product = "RHEL-AV"; -+ pcmc->smbios_stream_version = "8.3.0"; -+ compat_props_add(m->compat_props, hw_compat_rhel_8_3, -+ hw_compat_rhel_8_3_len); -+ compat_props_add(m->compat_props, pc_rhel_8_3_compat, -+ pc_rhel_8_3_compat_len); -+ /* From pc_q35_5_1_machine_options() */ -+ pcmc->kvmclock_create_always = false; -+ /* From pc_q35_5_1_machine_options() */ -+ pcmc->pci_root_uid = 1; -+} -+ -+DEFINE_PC_MACHINE(q35_rhel830, "pc-q35-rhel8.3.0", pc_q35_init_rhel830, -+ pc_q35_machine_rhel830_options); -+ -+static void pc_q35_init_rhel820(MachineState *machine) -+{ -+ pc_q35_init(machine); -+} -+ -+static void pc_q35_machine_rhel820_options(MachineClass *m) -+{ -+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m); -+ pc_q35_machine_rhel830_options(m); -+ m->desc = "RHEL-8.2.0 PC (Q35 + ICH9, 2009)"; -+ m->numa_mem_supported = true; -+ m->auto_enable_numa_with_memdev = false; -+ pcmc->smbios_stream_product = "RHEL-AV"; -+ pcmc->smbios_stream_version = "8.2.0"; -+ compat_props_add(m->compat_props, hw_compat_rhel_8_2, -+ hw_compat_rhel_8_2_len); -+ compat_props_add(m->compat_props, pc_rhel_8_2_compat, -+ pc_rhel_8_2_compat_len); -+} -+ -+DEFINE_PC_MACHINE(q35_rhel820, "pc-q35-rhel8.2.0", pc_q35_init_rhel820, -+ pc_q35_machine_rhel820_options); -+ -+static void pc_q35_init_rhel810(MachineState *machine) -+{ -+ pc_q35_init(machine); -+} -+ -+static void pc_q35_machine_rhel810_options(MachineClass *m) -+{ -+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m); -+ pc_q35_machine_rhel820_options(m); -+ m->desc = "RHEL-8.1.0 PC (Q35 + ICH9, 2009)"; -+ m->alias = NULL; -+ pcmc->smbios_stream_product = NULL; -+ pcmc->smbios_stream_version = NULL; -+ compat_props_add(m->compat_props, hw_compat_rhel_8_1, hw_compat_rhel_8_1_len); -+ compat_props_add(m->compat_props, pc_rhel_8_1_compat, pc_rhel_8_1_compat_len); -+} -+ -+DEFINE_PC_MACHINE(q35_rhel810, "pc-q35-rhel8.1.0", pc_q35_init_rhel810, -+ pc_q35_machine_rhel810_options); -+ -+static void pc_q35_init_rhel800(MachineState *machine) -+{ -+ pc_q35_init(machine); -+} -+ -+static void pc_q35_machine_rhel800_options(MachineClass *m) -+{ -+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m); -+ pc_q35_machine_rhel810_options(m); -+ m->desc = "RHEL-8.0.0 PC (Q35 + ICH9, 2009)"; -+ m->smbus_no_migration_support = true; -+ m->alias = NULL; -+ pcmc->pvh_enabled = false; -+ pcmc->default_cpu_version = CPU_VERSION_LEGACY; -+ compat_props_add(m->compat_props, hw_compat_rhel_8_0, hw_compat_rhel_8_0_len); -+ compat_props_add(m->compat_props, pc_rhel_8_0_compat, pc_rhel_8_0_compat_len); -+} -+ -+DEFINE_PC_MACHINE(q35_rhel800, "pc-q35-rhel8.0.0", pc_q35_init_rhel800, -+ pc_q35_machine_rhel800_options); -+ -+static void pc_q35_init_rhel760(MachineState *machine) -+{ -+ pc_q35_init(machine); -+} -+ -+static void pc_q35_machine_rhel760_options(MachineClass *m) -+{ -+ pc_q35_machine_rhel800_options(m); -+ m->alias = NULL; -+ m->desc = "RHEL-7.6.0 PC (Q35 + ICH9, 2009)"; -+ m->async_pf_vmexit_disable = true; -+ compat_props_add(m->compat_props, hw_compat_rhel_7_6, hw_compat_rhel_7_6_len); -+ compat_props_add(m->compat_props, pc_rhel_7_6_compat, pc_rhel_7_6_compat_len); -+} -+ -+DEFINE_PC_MACHINE(q35_rhel760, "pc-q35-rhel7.6.0", pc_q35_init_rhel760, -+ pc_q35_machine_rhel760_options); -diff --git a/include/hw/boards.h b/include/hw/boards.h -index b0a6e05b48..3c3d2ad450 100644 ---- a/include/hw/boards.h -+++ b/include/hw/boards.h -@@ -263,6 +263,8 @@ struct MachineClass { - strList *allowed_dynamic_sysbus_devices; - bool auto_enable_numa_with_memhp; - bool auto_enable_numa_with_memdev; -+ /* RHEL only */ -+ bool async_pf_vmexit_disable; - bool ignore_boot_device_suffixes; - bool smbus_no_migration_support; - bool nvdimm_supported; -diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h -index 7ccc9a1a07..9689a58b14 100644 ---- a/include/hw/i386/pc.h -+++ b/include/hw/i386/pc.h -@@ -280,6 +280,27 @@ 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_8_4_compat[]; -+extern const size_t pc_rhel_8_4_compat_len; -+ -+extern GlobalProperty pc_rhel_8_3_compat[]; -+extern const size_t pc_rhel_8_3_compat_len; -+ -+extern GlobalProperty pc_rhel_8_2_compat[]; -+extern const size_t pc_rhel_8_2_compat_len; -+ -+extern GlobalProperty pc_rhel_8_1_compat[]; -+extern const size_t pc_rhel_8_1_compat_len; -+ -+extern GlobalProperty pc_rhel_8_0_compat[]; -+extern const size_t pc_rhel_8_0_compat_len; -+ -+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. - */ -diff --git a/target/i386/kvm/kvm-cpu.c b/target/i386/kvm/kvm-cpu.c -index d95028018e..7b004065ae 100644 ---- a/target/i386/kvm/kvm-cpu.c -+++ b/target/i386/kvm/kvm-cpu.c -@@ -131,6 +131,7 @@ static PropValue kvm_default_props[] = { - { "acpi", "off" }, - { "monitor", "off" }, - { "svm", "off" }, -+ { "kvm-pv-unhalt", "on" }, - { NULL, NULL }, - }; - -diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c -index 5a698bde19..a668f521ac 100644 ---- a/target/i386/kvm/kvm.c -+++ b/target/i386/kvm/kvm.c -@@ -3336,6 +3336,7 @@ 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; -+ MachineClass *mc = MACHINE_GET_CLASS(qdev_get_machine()); - - kvm_msr_buf_reset(cpu); - -@@ -3665,6 +3666,9 @@ static int kvm_get_msrs(X86CPU *cpu) - break; - case MSR_KVM_ASYNC_PF_EN: - env->async_pf_en_msr = msrs[i].data; -+ if (mc->async_pf_vmexit_disable) { -+ env->async_pf_en_msr &= ~(1ULL << 2); -+ } - break; - 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 ---- a/tests/qtest/pvpanic-test.c -+++ b/tests/qtest/pvpanic-test.c -@@ -17,7 +17,7 @@ static void test_panic_nopause(void) - QDict *response, *data; - QTestState *qts; - -- qts = qtest_init("-device pvpanic -action panic=none"); -+ qts = qtest_init("-M q35 -device pvpanic -action panic=none"); - - val = qtest_inb(qts, 0x505); - g_assert_cmpuint(val, ==, 3); -@@ -40,7 +40,8 @@ static void test_panic(void) - QDict *response, *data; - QTestState *qts; - -- qts = qtest_init("-device pvpanic -action panic=pause"); -+ /* RHEL: Use q35 */ -+ qts = qtest_init("-M q35 -device pvpanic -action panic=pause"); - - val = qtest_inb(qts, 0x505); - g_assert_cmpuint(val, ==, 3); --- -2.27.0 - diff --git a/SOURCES/0011-Enable-make-check.patch b/SOURCES/0011-Enable-make-check.patch new file mode 100644 index 0000000..832b38d --- /dev/null +++ b/SOURCES/0011-Enable-make-check.patch @@ -0,0 +1,186 @@ +From 5e419e5e0a721bdbbfa6d9b82c8be5c5b3d26a01 Mon Sep 17 00:00:00 2001 +From: Miroslav Rezanina +Date: Wed, 2 Sep 2020 09:39:41 +0200 +Subject: Enable make check + +Fixing tests after device disabling and machine types changes and enabling +make check run during build. + +Signed-off-by: Miroslav Rezanina +--- +Rebase changes (6.1.0): +- removed unnecessary test changes + +Rebase changes (6.2.0): +- new way of disabling bios-table-test + +Rebase changes (7.0.0): +- Disable testing virtio-iommu-pci +- Rename default_bus_bypass_iommu property to default-bus-bypass-iommu +- Disable qtest-bios-table for aarch64 +- Removed redhat chunks for boot-serial-test.c, cdrom-test.c and cpu-plug-test.c qtests +- Do not disable boot-order-test, prom-env-test and boot-serial-test qtests +- Use rhel machine type for new intel hda qtest +- Remove unnecessary changes in iotest 051 +- Remove changes in bios-tables-test.c and prom-env-test.c qtests + +Merged patches (6.1.0): +- 2f129df7d3 redhat: Enable the 'test-block-iothread' test again +--- + .distro/qemu-kvm.spec.template | 5 ++--- + 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/usb-hcd-xhci-test.c | 4 ++++ + tests/qtest/virtio-net-failover.c | 1 + + 9 files changed, 12 insertions(+), 12 deletions(-) + +diff --git a/tests/qtest/fuzz-e1000e-test.c b/tests/qtest/fuzz-e1000e-test.c +index 66229e6096..947fba73b7 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) + { + QTestState *s; + +- s = qtest_init("-nographic -monitor none -serial none -M pc-q35-5.0"); ++ s = qtest_init("-nographic -monitor none -serial none -M pc-q35-rhel8.4.0"); + + 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 +--- 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 " + "-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 +--- a/tests/qtest/intel-hda-test.c ++++ b/tests/qtest/intel-hda-test.c +@@ -38,7 +38,7 @@ static void test_issue542_ich6(void) + { + QTestState *s; + +- s = qtest_init("-nographic -nodefaults -M pc-q35-6.2 " ++ s = qtest_init("-nographic -nodefaults -M pc-q35-rhel9.0.0 " + "-device intel-hda,id=" HDA_ID CODEC_DEVICES); + + qtest_outl(s, 0xcf8, 0x80000804); +diff --git a/tests/qtest/libqos/meson.build b/tests/qtest/libqos/meson.build +index e988d15791..46f7dcb81a 100644 +--- a/tests/qtest/libqos/meson.build ++++ b/tests/qtest/libqos/meson.build +@@ -41,7 +41,7 @@ libqos_srcs = files('../libqtest.c', + 'virtio-rng.c', + 'virtio-scsi.c', + 'virtio-serial.c', +- 'virtio-iommu.c', ++# 'virtio-iommu.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 +--- 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) + { + QTestState *s; + +- s = qtest_init("-M pc-q35-5.0 " ++ s = qtest_init("-M pc-q35-rhel8.4.0 " + "-nographic -monitor none -serial none"); + + qtest_outl(s, 0xcf8, 0x8000f840); /* PMBASE */ +diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build +index d25f82bb5a..67cd32def1 100644 +--- a/tests/qtest/meson.build ++++ b/tests/qtest/meson.build +@@ -73,7 +73,6 @@ 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 + \ + ['fdc-test', + 'ide-test', +@@ -86,7 +85,6 @@ qtests_i386 = \ + 'drive_del-test', + 'tco-test', + 'cpu-plug-test', +- 'q35-test', + 'vmgenid-test', + 'migration-test', + 'test-x86-cpuid-compat', +@@ -216,7 +214,6 @@ qtests_arm = \ + + # TODO: once aarch64 TCG is fixed on ARM 32 bit host, make bios-tables-test unconditional + qtests_aarch64 = \ +- (cpu != 'arm' and unpack_edk2_blobs ? ['bios-tables-test'] : []) + \ + (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 = \ + (config_host.has_key('CONFIG_POSIX') ? ['test-filter-redirector'] : []) + \ + ['boot-serial-test', + 'drive_del-test', +- 'device-plug-test', + 'virtio-ccw-test', + 'cpu-plug-test', + 'migration-test'] +diff --git a/tests/qtest/usb-hcd-xhci-test.c b/tests/qtest/usb-hcd-xhci-test.c +index 10ef9d2a91..3855873050 100644 +--- a/tests/qtest/usb-hcd-xhci-test.c ++++ b/tests/qtest/usb-hcd-xhci-test.c +@@ -21,6 +21,7 @@ static void test_xhci_hotplug(void) + usb_test_hotplug(global_qtest, "xhci", "1", NULL); + } + ++#if 0 /* Disabled for Red Hat Enterprise Linux */ + static void test_usb_uas_hotplug(void) + { + QTestState *qts = global_qtest; +@@ -36,6 +37,7 @@ static void test_usb_uas_hotplug(void) + qtest_qmp_device_del(qts, "scsihd"); + qtest_qmp_device_del(qts, "uas"); + } ++#endif + + static void test_usb_ccid_hotplug(void) + { +@@ -56,7 +58,9 @@ int main(int argc, char **argv) + + qtest_add_func("/xhci/pci/init", test_xhci_init); + qtest_add_func("/xhci/pci/hotplug", test_xhci_hotplug); ++#if 0 /* Disabled for Red Hat Enterprise Linux */ + qtest_add_func("/xhci/pci/hotplug/usb-uas", test_usb_uas_hotplug); ++#endif + qtest_add_func("/xhci/pci/hotplug/usb-ccid", test_usb_ccid_hotplug); + + 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 +--- a/tests/qtest/virtio-net-failover.c ++++ b/tests/qtest/virtio-net-failover.c +@@ -25,6 +25,7 @@ + #define PCI_SEL_BASE 0x0010 + + #define BASE_MACHINE "-M q35 -nodefaults " \ ++ "-global ICH9-LPC.acpi-pci-hotplug-with-bridge-support=on " \ + "-device pcie-root-port,id=root0,addr=0x1,bus=pcie.0,chassis=1 " \ + "-device pcie-root-port,id=root1,addr=0x2,bus=pcie.0,chassis=2 " + +-- +2.31.1 + diff --git a/SOURCES/0012-Enable-make-check.patch b/SOURCES/0012-Enable-make-check.patch deleted file mode 100644 index 4cd1ecc..0000000 --- a/SOURCES/0012-Enable-make-check.patch +++ /dev/null @@ -1,376 +0,0 @@ -From b071f3eaa77dde1567d70b43d0b2975efe380da2 Mon Sep 17 00:00:00 2001 -From: Miroslav Rezanina -Date: Wed, 2 Sep 2020 09:39:41 +0200 -Subject: Enable make check - -Fixing tests after device disabling and machine types changes and enabling -make check run during build. - -Signed-off-by: Miroslav Rezanina ---- -Rebase changes (6.1.0): -- removed unnecessary test changes - -Rebase changes (6.2.0 RC0): -- new way of disabling bios-table-test - -Merged patches (6.1.0): -- 2f129df7d3 redhat: Enable the 'test-block-iothread' test again ---- - .distro/qemu-kvm.spec.template | 5 ++--- - tests/qemu-iotests/051 | 8 ++++---- - tests/qtest/bios-tables-test.c | 6 +++--- - tests/qtest/boot-serial-test.c | 6 +++++- - tests/qtest/cdrom-test.c | 4 ++++ - tests/qtest/cpu-plug-test.c | 4 ++-- - tests/qtest/fuzz-e1000e-test.c | 2 +- - tests/qtest/fuzz-virtio-scsi-test.c | 2 +- - tests/qtest/hd-geo-test.c | 4 ++++ - tests/qtest/lpc-ich9-test.c | 2 +- - tests/qtest/meson.build | 13 ++++--------- - tests/qtest/prom-env-test.c | 4 ++++ - tests/qtest/test-x86-cpuid-compat.c | 2 ++ - tests/qtest/usb-hcd-xhci-test.c | 4 ++++ - 14 files changed, 41 insertions(+), 25 deletions(-) - -diff --git a/tests/qemu-iotests/051 b/tests/qemu-iotests/051 -index 1d2fa93a11..c8a2815f54 100755 ---- a/tests/qemu-iotests/051 -+++ b/tests/qemu-iotests/051 -@@ -174,9 +174,9 @@ run_qemu -drive if=virtio - case "$QEMU_DEFAULT_MACHINE" in - pc) - run_qemu -drive if=none,id=disk -device ide-cd,drive=disk -- run_qemu -drive if=none,id=disk -device lsi53c895a -device scsi-cd,drive=disk -+# run_qemu -drive if=none,id=disk -device lsi53c895a -device scsi-cd,drive=disk - run_qemu -drive if=none,id=disk -device ide-hd,drive=disk -- run_qemu -drive if=none,id=disk -device lsi53c895a -device scsi-hd,drive=disk -+# run_qemu -drive if=none,id=disk -device lsi53c895a -device scsi-hd,drive=disk - ;; - *) - ;; -@@ -225,9 +225,9 @@ run_qemu -drive file="$TEST_IMG",if=virtio,readonly=on - case "$QEMU_DEFAULT_MACHINE" in - pc) - run_qemu -drive file="$TEST_IMG",if=none,id=disk,readonly=on -device ide-cd,drive=disk -- run_qemu -drive file="$TEST_IMG",if=none,id=disk,readonly=on -device lsi53c895a -device scsi-cd,drive=disk -+# run_qemu -drive file="$TEST_IMG",if=none,id=disk,readonly=on -device lsi53c895a -device scsi-cd,drive=disk - run_qemu -drive file="$TEST_IMG",if=none,id=disk,readonly=on -device ide-hd,drive=disk -- run_qemu -drive file="$TEST_IMG",if=none,id=disk,readonly=on -device lsi53c895a -device scsi-hd,drive=disk -+# run_qemu -drive file="$TEST_IMG",if=none,id=disk,readonly=on -device lsi53c895a -device scsi-hd,drive=disk - ;; - *) - ;; -diff --git a/tests/qtest/bios-tables-test.c b/tests/qtest/bios-tables-test.c -index 258874167e..62745181a8 100644 ---- a/tests/qtest/bios-tables-test.c -+++ b/tests/qtest/bios-tables-test.c -@@ -1371,7 +1371,7 @@ static void test_acpi_virt_tcg_numamem(void) - free_test_data(&data); - - } -- -+#if 0 /* Disabled for Red Hat Enterprise Linux */ - static void test_acpi_virt_tcg_pxb(void) - { - test_data data = { -@@ -1403,7 +1403,7 @@ static void test_acpi_virt_tcg_pxb(void) - - free_test_data(&data); - } -- -+#endif - static void test_acpi_tcg_acpi_hmat(const char *machine) - { - test_data data; -@@ -1644,7 +1644,7 @@ int main(int argc, char *argv[]) - qtest_add_func("acpi/virt", test_acpi_virt_tcg); - qtest_add_func("acpi/virt/numamem", test_acpi_virt_tcg_numamem); - qtest_add_func("acpi/virt/memhp", test_acpi_virt_tcg_memhp); -- qtest_add_func("acpi/virt/pxb", test_acpi_virt_tcg_pxb); -+/* qtest_add_func("acpi/virt/pxb", test_acpi_virt_tcg_pxb); */ - qtest_add_func("acpi/virt/oem-fields", test_acpi_oem_fields_virt); - } - } -diff --git a/tests/qtest/boot-serial-test.c b/tests/qtest/boot-serial-test.c -index 83828ba270..294476b959 100644 ---- a/tests/qtest/boot-serial-test.c -+++ b/tests/qtest/boot-serial-test.c -@@ -148,19 +148,23 @@ static testdef_t tests[] = { - { "ppc", "g3beige", "", "PowerPC,750" }, - { "ppc", "mac99", "", "PowerPC,G4" }, - { "ppc", "sam460ex", "-m 256", "DRAM: 256 MiB" }, -+#if 0 /* Disabled for Red Hat Enterprise Linux */ - { "ppc64", "ppce500", "", "U-Boot" }, - { "ppc64", "40p", "-m 192", "Memory: 192M" }, - { "ppc64", "mac99", "", "PowerPC,970FX" }, -+#endif - { "ppc64", "pseries", - "-machine " PSERIES_DEFAULT_CAPABILITIES, - "Open Firmware" }, -+#if 0 /* Disabled for Red Hat Enterprise Linux */ - { "ppc64", "powernv8", "", "OPAL" }, - { "ppc64", "powernv9", "", "OPAL" }, - { "ppc64", "sam460ex", "-device e1000", "8086 100e" }, -+#endif - { "i386", "isapc", "-cpu qemu32 -device sga", "SGABIOS" }, - { "i386", "pc", "-device sga", "SGABIOS" }, - { "i386", "q35", "-device sga", "SGABIOS" }, -- { "x86_64", "isapc", "-cpu qemu32 -device sga", "SGABIOS" }, -+ { "x86_64", "pc", "-cpu qemu32 -device sga", "SGABIOS" }, - { "x86_64", "q35", "-device sga", "SGABIOS" }, - { "sparc", "LX", "", "TMS390S10" }, - { "sparc", "SS-4", "", "MB86904" }, -diff --git a/tests/qtest/cdrom-test.c b/tests/qtest/cdrom-test.c -index 5af944a5fb..69d9bac38a 100644 ---- a/tests/qtest/cdrom-test.c -+++ b/tests/qtest/cdrom-test.c -@@ -140,6 +140,7 @@ static void add_x86_tests(void) - qtest_add_data_func("cdrom/boot/isapc", "-M isapc " - "-drive if=ide,media=cdrom,file=", test_cdboot); - } -+#if 0 /* Disabled for Red Hat Enterprise Linux */ - qtest_add_data_func("cdrom/boot/am53c974", - "-device am53c974 -device scsi-cd,drive=cd1 " - "-drive if=none,id=cd1,format=raw,file=", test_cdboot); -@@ -155,6 +156,7 @@ static void add_x86_tests(void) - qtest_add_data_func("cdrom/boot/megasas-gen2", "-M q35 " - "-device megasas-gen2 -device scsi-cd,drive=cd1 " - "-blockdev file,node-name=cd1,filename=", test_cdboot); -+#endif - } - - static void add_s390x_tests(void) -@@ -220,6 +222,7 @@ int main(int argc, char **argv) - "magnum", "malta", "pica61", NULL - }; - add_cdrom_param_tests(mips64machines); -+#if 0 /* Disabled for Red Hat Enterprise Linux */ - } else if (g_str_equal(arch, "arm") || g_str_equal(arch, "aarch64")) { - const char *armmachines[] = { - "realview-eb", "realview-eb-mpcore", "realview-pb-a8", -@@ -227,6 +230,7 @@ int main(int argc, char **argv) - "vexpress-a9", "virt", NULL - }; - add_cdrom_param_tests(armmachines); -+#endif - } else { - const char *nonemachine[] = { "none", NULL }; - add_cdrom_param_tests(nonemachine); -diff --git a/tests/qtest/cpu-plug-test.c b/tests/qtest/cpu-plug-test.c -index a1c689414b..a8f076711c 100644 ---- a/tests/qtest/cpu-plug-test.c -+++ b/tests/qtest/cpu-plug-test.c -@@ -110,8 +110,8 @@ static void add_pseries_test_case(const char *mname) - char *path; - PlugTestData *data; - -- if (!g_str_has_prefix(mname, "pseries-") || -- (g_str_has_prefix(mname, "pseries-2.") && atoi(&mname[10]) < 7)) { -+ if (!g_str_has_prefix(mname, "pseries-rhel") || -+ (g_str_has_prefix(mname, "pseries-rhel7.") && atoi(&mname[14]) < 4)) { - return; - } - data = g_new(PlugTestData, 1); -diff --git a/tests/qtest/fuzz-e1000e-test.c b/tests/qtest/fuzz-e1000e-test.c -index 66229e6096..947fba73b7 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) - { - QTestState *s; - -- s = qtest_init("-nographic -monitor none -serial none -M pc-q35-5.0"); -+ s = qtest_init("-nographic -monitor none -serial none -M pc-q35-rhel8.4.0"); - - 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 ---- 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 " - "-device virtio-scsi,num_queues=8,addr=03.0 "); - - qtest_outl(s, 0xcf8, 0x80001811); -diff --git a/tests/qtest/hd-geo-test.c b/tests/qtest/hd-geo-test.c -index 113126ae06..999ef2aace 100644 ---- a/tests/qtest/hd-geo-test.c -+++ b/tests/qtest/hd-geo-test.c -@@ -737,6 +737,7 @@ static void test_override_ide(void) - test_override(args, expected); - } - -+#if 0 /* Require lsi53c895a - not supported on RHEL */ - static void test_override_scsi(void) - { - TestArgs *args = create_args(); -@@ -781,6 +782,7 @@ static void test_override_scsi_2_controllers(void) - add_scsi_disk(args, 3, 1, 0, 1, 2, 0, 1, 0); - test_override(args, expected); - } -+#endif - - static void test_override_virtio_blk(void) - { -@@ -960,9 +962,11 @@ int main(int argc, char **argv) - qtest_add_func("hd-geo/ide/device/user/chst", test_ide_device_user_chst); - if (have_qemu_img()) { - qtest_add_func("hd-geo/override/ide", test_override_ide); -+#if 0 /* Require lsi53c895a - not supported on RHEL */ - qtest_add_func("hd-geo/override/scsi", test_override_scsi); - qtest_add_func("hd-geo/override/scsi_2_controllers", - test_override_scsi_2_controllers); -+#endif - qtest_add_func("hd-geo/override/virtio_blk", test_override_virtio_blk); - qtest_add_func("hd-geo/override/zero_chs", test_override_zero_chs); - qtest_add_func("hd-geo/override/scsi_hot_unplug", -diff --git a/tests/qtest/lpc-ich9-test.c b/tests/qtest/lpc-ich9-test.c -index fe0bef9980..7a9d51579b 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) - { - QTestState *s; - -- s = qtest_init("-M pc-q35-5.0 " -+ s = qtest_init("-M pc-q35-rhel8.4.0 " - "-nographic -monitor none -serial none"); - - qtest_outl(s, 0xcf8, 0x8000f840); /* PMBASE */ -diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build -index c9d8458062..049e06c057 100644 ---- a/tests/qtest/meson.build -+++ b/tests/qtest/meson.build -@@ -68,7 +68,6 @@ qtests_i386 = \ - (config_all_devices.has_key('CONFIG_RTL8139_PCI') ? ['rtl8139-test'] : []) + \ - (config_all_devices.has_key('CONFIG_E1000E_PCI_EXPRESS') ? ['fuzz-e1000e-test'] : []) + \ - (config_all_devices.has_key('CONFIG_ESP_PCI') ? ['am53c974-test'] : []) + \ -- (unpack_edk2_blobs ? ['bios-tables-test'] : []) + \ - qtests_pci + \ - ['fdc-test', - 'ide-test', -@@ -81,7 +80,6 @@ qtests_i386 = \ - 'drive_del-test', - 'tco-test', - 'cpu-plug-test', -- 'q35-test', - 'vmgenid-test', - 'migration-test', - 'test-x86-cpuid-compat', -@@ -130,17 +128,15 @@ qtests_mips64el = \ - - qtests_ppc = \ - (config_all_devices.has_key('CONFIG_ISA_TESTDEV') ? ['endianness-test'] : []) + \ -- (config_all_devices.has_key('CONFIG_M48T59') ? ['m48t59-test'] : []) + \ -- ['boot-order-test', 'prom-env-test', 'boot-serial-test'] \ -+ (config_all_devices.has_key('CONFIG_M48T59') ? ['m48t59-test'] : []) - - qtests_ppc64 = \ - (config_all_devices.has_key('CONFIG_PSERIES') ? ['device-plug-test'] : []) + \ - (config_all_devices.has_key('CONFIG_POWERNV') ? ['pnv-xscom-test'] : []) + \ - (config_all_devices.has_key('CONFIG_PSERIES') ? ['rtas-test'] : []) + \ -- (slirp.found() ? ['pxe-test', 'test-netfilter'] : []) + \ -+ (slirp.found() ? ['pxe-test'] : []) + \ - (config_all_devices.has_key('CONFIG_USB_UHCI') ? ['usb-hcd-uhci-test'] : []) + \ - (config_all_devices.has_key('CONFIG_USB_XHCI_NEC') ? ['usb-hcd-xhci-test'] : []) + \ -- (config_host.has_key('CONFIG_POSIX') ? ['test-filter-mirror'] : []) + \ - qtests_pci + ['migration-test', 'numa-test', 'cpu-plug-test', 'drive_del-test'] - - qtests_sh4 = (config_all_devices.has_key('CONFIG_ISA_TESTDEV') ? ['endianness-test'] : []) -@@ -186,8 +182,8 @@ qtests_aarch64 = \ - ['arm-cpu-features', - 'numa-test', - 'boot-serial-test', -- 'xlnx-can-test', -- 'fuzz-xlnx-dp-test', -+# 'xlnx-can-test', -+# 'fuzz-xlnx-dp-test', - 'migration-test'] - - qtests_s390x = \ -@@ -196,7 +192,6 @@ qtests_s390x = \ - (config_host.has_key('CONFIG_POSIX') ? ['test-filter-redirector'] : []) + \ - ['boot-serial-test', - 'drive_del-test', -- 'device-plug-test', - 'virtio-ccw-test', - 'cpu-plug-test', - 'migration-test'] -diff --git a/tests/qtest/prom-env-test.c b/tests/qtest/prom-env-test.c -index f41d80154a..f8dc478ce8 100644 ---- a/tests/qtest/prom-env-test.c -+++ b/tests/qtest/prom-env-test.c -@@ -89,10 +89,14 @@ int main(int argc, char *argv[]) - if (!strcmp(arch, "ppc")) { - add_tests(ppc_machines); - } else if (!strcmp(arch, "ppc64")) { -+#if 0 /* Disabled for Red Hat Enterprise Linux */ - add_tests(ppc_machines); - if (g_test_slow()) { -+#endif - qtest_add_data_func("prom-env/pseries", "pseries", test_machine); -+#if 0 /* Disabled for Red Hat Enterprise Linux */ - } -+#endif - } else if (!strcmp(arch, "sparc")) { - add_tests(sparc_machines); - } else if (!strcmp(arch, "sparc64")) { -diff --git a/tests/qtest/test-x86-cpuid-compat.c b/tests/qtest/test-x86-cpuid-compat.c -index f28848e06e..6b2fd398a2 100644 ---- a/tests/qtest/test-x86-cpuid-compat.c -+++ b/tests/qtest/test-x86-cpuid-compat.c -@@ -300,6 +300,7 @@ int main(int argc, char **argv) - "-cpu 486,xlevel2=0xC0000002,xstore=on", - "xlevel2", 0xC0000002); - -+#if 0 /* Disabled in Red Hat Enterprise Linux */ - /* Check compatibility of old machine-types that didn't - * auto-increase level/xlevel/xlevel2: */ - -@@ -350,6 +351,7 @@ int main(int argc, char **argv) - add_cpuid_test("x86/cpuid/xlevel-compat/pc-i440fx-2.4/npt-on", - "-machine pc-i440fx-2.4 -cpu SandyBridge,svm=on,npt=on", - "xlevel", 0x80000008); -+#endif - - /* Test feature parsing */ - add_feature_test("x86/cpuid/features/plus", -diff --git a/tests/qtest/usb-hcd-xhci-test.c b/tests/qtest/usb-hcd-xhci-test.c -index 10ef9d2a91..3855873050 100644 ---- a/tests/qtest/usb-hcd-xhci-test.c -+++ b/tests/qtest/usb-hcd-xhci-test.c -@@ -21,6 +21,7 @@ static void test_xhci_hotplug(void) - usb_test_hotplug(global_qtest, "xhci", "1", NULL); - } - -+#if 0 /* Disabled for Red Hat Enterprise Linux */ - static void test_usb_uas_hotplug(void) - { - QTestState *qts = global_qtest; -@@ -36,6 +37,7 @@ static void test_usb_uas_hotplug(void) - qtest_qmp_device_del(qts, "scsihd"); - qtest_qmp_device_del(qts, "uas"); - } -+#endif - - static void test_usb_ccid_hotplug(void) - { -@@ -56,7 +58,9 @@ int main(int argc, char **argv) - - qtest_add_func("/xhci/pci/init", test_xhci_init); - qtest_add_func("/xhci/pci/hotplug", test_xhci_hotplug); -+#if 0 /* Disabled for Red Hat Enterprise Linux */ - qtest_add_func("/xhci/pci/hotplug/usb-uas", test_usb_uas_hotplug); -+#endif - qtest_add_func("/xhci/pci/hotplug/usb-ccid", test_usb_ccid_hotplug); - - qtest_start("-device nec-usb-xhci,id=xhci" --- -2.27.0 - diff --git a/SOURCES/0012-vfio-cap-number-of-devices-that-can-be-assigned.patch b/SOURCES/0012-vfio-cap-number-of-devices-that-can-be-assigned.patch new file mode 100644 index 0000000..c9e42b2 --- /dev/null +++ b/SOURCES/0012-vfio-cap-number-of-devices-that-can-be-assigned.patch @@ -0,0 +1,104 @@ +From c358fd4c224a9c3f64b4a8fff34cc6b1dc201fa0 Mon Sep 17 00:00:00 2001 +From: Bandan Das +Date: Tue, 3 Dec 2013 20:05:13 +0100 +Subject: vfio: cap number of devices that can be assigned + +RH-Author: Bandan Das +Message-id: <1386101113-31560-3-git-send-email-bsd@redhat.com> +Patchwork-id: 55984 +O-Subject: [PATCH RHEL7 qemu-kvm v2 2/2] vfio: cap number of devices that can be assigned +Bugzilla: 678368 +RH-Acked-by: Alex Williamson +RH-Acked-by: Marcelo Tosatti +RH-Acked-by: Michael S. Tsirkin + +Go through all groups to get count of total number of devices +active to enforce limit + +Reasoning from Alex for the limit(32) - Assuming 3 slots per +device, with 125 slots (number of memory slots for RHEL 7), +we can support almost 40 devices and still have few slots left +for other uses. Stepping down a bit, the number 32 arbitrarily +matches the number of slots on a PCI bus and is also a nice power +of two. + +Count of slots increased to 509 later so we could increase limit +to 64 as some usecases require more than 32 devices. + +Signed-off-by: Bandan Das +--- + hw/vfio/pci.c | 29 ++++++++++++++++++++++++++++- + hw/vfio/pci.h | 1 + + 2 files changed, 29 insertions(+), 1 deletion(-) + +diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c +index 67a183f17b..1e20f9fd59 100644 +--- a/hw/vfio/pci.c ++++ b/hw/vfio/pci.c +@@ -45,6 +45,9 @@ + + #define TYPE_VFIO_PCI_NOHOTPLUG "vfio-pci-nohotplug" + ++/* 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) + ssize_t len; + struct stat st; + int groupid; +- int i, ret; ++ int ret, i = 0; + bool is_mdev; + ++ if (device_limit && device_limit != vdev->assigned_device_limit) { ++ error_setg(errp, "Assigned device limit has been redefined. " ++ "Old:%d, New:%d", ++ device_limit, vdev->assigned_device_limit); ++ return; ++ } else { ++ device_limit = vdev->assigned_device_limit; ++ } ++ ++ QLIST_FOREACH(group, &vfio_group_list, next) { ++ QLIST_FOREACH(vbasedev_iter, &group->device_list, next) { ++ i++; ++ } ++ } ++ ++ if (i >= vdev->assigned_device_limit) { ++ error_setg(errp, "Maximum supported vfio devices (%d) " ++ "already attached", vdev->assigned_device_limit); ++ return; ++ } ++ + if (!vdev->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[] = { + DEFINE_PROP_BOOL("x-no-kvm-msix", VFIOPCIDevice, no_kvm_msix, false), + DEFINE_PROP_BOOL("x-no-geforce-quirks", VFIOPCIDevice, + no_geforce_quirks, false), ++ /* RHEL only */ ++ DEFINE_PROP_UINT16("x-assigned-device-limit", VFIOPCIDevice, ++ assigned_device_limit, 64), + DEFINE_PROP_BOOL("x-no-kvm-ioeventfd", VFIOPCIDevice, no_kvm_ioeventfd, + 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 +--- a/hw/vfio/pci.h ++++ b/hw/vfio/pci.h +@@ -139,6 +139,7 @@ struct VFIOPCIDevice { + EventNotifier err_notifier; + EventNotifier req_notifier; + int (*resetfn)(struct VFIOPCIDevice *); ++ uint16_t assigned_device_limit; + uint32_t vendor_id; + uint32_t device_id; + uint32_t sub_vendor_id; +-- +2.31.1 + diff --git a/SOURCES/0013-Add-support-statement-to-help-output.patch b/SOURCES/0013-Add-support-statement-to-help-output.patch new file mode 100644 index 0000000..4826ea4 --- /dev/null +++ b/SOURCES/0013-Add-support-statement-to-help-output.patch @@ -0,0 +1,55 @@ +From ba0c7a5f6b9a1f75666db6b3b795ddf03695dc26 Mon Sep 17 00:00:00 2001 +From: Eduardo Habkost +Date: Wed, 4 Dec 2013 18:53:17 +0100 +Subject: Add support statement to -help output + +RH-Author: Eduardo Habkost +Message-id: <1386183197-27761-1-git-send-email-ehabkost@redhat.com> +Patchwork-id: 55994 +O-Subject: [qemu-kvm RHEL7 PATCH] Add support statement to -help output +Bugzilla: 972773 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: knoel@redhat.com +RH-Acked-by: Paolo Bonzini + +Add support statement to -help output, reporting direct qemu-kvm usage +as unsupported by Red Hat, and advising users to use libvirt instead. + +Signed-off-by: Eduardo Habkost +--- + softmmu/vl.c | 9 +++++++++ + 1 file changed, 9 insertions(+) + +diff --git a/softmmu/vl.c b/softmmu/vl.c +index 6f646531a0..9d5dab43d2 100644 +--- a/softmmu/vl.c ++++ b/softmmu/vl.c +@@ -831,9 +831,17 @@ static void version(void) + QEMU_COPYRIGHT "\n"); + } + ++static void print_rh_warning(void) ++{ ++ printf("\nWARNING: Direct use of qemu-kvm from the command line is not supported by Red Hat.\n" ++ "WARNING: Use libvirt as the stable management interface.\n" ++ "WARNING: Some command line options listed here may not be available in future releases.\n\n"); ++} ++ + static void help(int exitcode) + { + version(); ++ print_rh_warning(); + 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) + "\n" + QEMU_HELP_BOTTOM "\n"); + ++ print_rh_warning(); + exit(exitcode); + } + +-- +2.31.1 + diff --git a/SOURCES/0013-vfio-cap-number-of-devices-that-can-be-assigned.patch b/SOURCES/0013-vfio-cap-number-of-devices-that-can-be-assigned.patch deleted file mode 100644 index 44db7e1..0000000 --- a/SOURCES/0013-vfio-cap-number-of-devices-that-can-be-assigned.patch +++ /dev/null @@ -1,104 +0,0 @@ -From 55dcef9d806aa530f10e3ca42eb24d52f850d674 Mon Sep 17 00:00:00 2001 -From: Bandan Das -Date: Tue, 3 Dec 2013 20:05:13 +0100 -Subject: vfio: cap number of devices that can be assigned - -RH-Author: Bandan Das -Message-id: <1386101113-31560-3-git-send-email-bsd@redhat.com> -Patchwork-id: 55984 -O-Subject: [PATCH RHEL7 qemu-kvm v2 2/2] vfio: cap number of devices that can be assigned -Bugzilla: 678368 -RH-Acked-by: Alex Williamson -RH-Acked-by: Marcelo Tosatti -RH-Acked-by: Michael S. Tsirkin - -Go through all groups to get count of total number of devices -active to enforce limit - -Reasoning from Alex for the limit(32) - Assuming 3 slots per -device, with 125 slots (number of memory slots for RHEL 7), -we can support almost 40 devices and still have few slots left -for other uses. Stepping down a bit, the number 32 arbitrarily -matches the number of slots on a PCI bus and is also a nice power -of two. - -Count of slots increased to 509 later so we could increase limit -to 64 as some usecases require more than 32 devices. - -Signed-off-by: Bandan Das ---- - hw/vfio/pci.c | 29 ++++++++++++++++++++++++++++- - hw/vfio/pci.h | 1 + - 2 files changed, 29 insertions(+), 1 deletion(-) - -diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c -index 7b45353ce2..eb725a3aee 100644 ---- a/hw/vfio/pci.c -+++ b/hw/vfio/pci.c -@@ -45,6 +45,9 @@ - - #define TYPE_VFIO_PCI_NOHOTPLUG "vfio-pci-nohotplug" - -+/* 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); - -@@ -2807,9 +2810,30 @@ static void vfio_realize(PCIDevice *pdev, Error **errp) - ssize_t len; - struct stat st; - int groupid; -- int i, ret; -+ int ret, i = 0; - bool is_mdev; - -+ if (device_limit && device_limit != vdev->assigned_device_limit) { -+ error_setg(errp, "Assigned device limit has been redefined. " -+ "Old:%d, New:%d", -+ device_limit, vdev->assigned_device_limit); -+ return; -+ } else { -+ device_limit = vdev->assigned_device_limit; -+ } -+ -+ QLIST_FOREACH(group, &vfio_group_list, next) { -+ QLIST_FOREACH(vbasedev_iter, &group->device_list, next) { -+ i++; -+ } -+ } -+ -+ if (i >= vdev->assigned_device_limit) { -+ error_setg(errp, "Maximum supported vfio devices (%d) " -+ "already attached", vdev->assigned_device_limit); -+ return; -+ } -+ - if (!vdev->vbasedev.sysfsdev) { - if (!(~vdev->host.domain || ~vdev->host.bus || - ~vdev->host.slot || ~vdev->host.function)) { -@@ -3246,6 +3270,9 @@ 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), -+ /* RHEL only */ -+ DEFINE_PROP_UINT16("x-assigned-device-limit", VFIOPCIDevice, -+ assigned_device_limit, 64), - DEFINE_PROP_BOOL("x-no-kvm-ioeventfd", VFIOPCIDevice, no_kvm_ioeventfd, - 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 ---- a/hw/vfio/pci.h -+++ b/hw/vfio/pci.h -@@ -139,6 +139,7 @@ struct VFIOPCIDevice { - EventNotifier err_notifier; - EventNotifier req_notifier; - int (*resetfn)(struct VFIOPCIDevice *); -+ uint16_t assigned_device_limit; - uint32_t vendor_id; - uint32_t device_id; - uint32_t sub_vendor_id; --- -2.27.0 - diff --git a/SOURCES/0014-Add-support-statement-to-help-output.patch b/SOURCES/0014-Add-support-statement-to-help-output.patch deleted file mode 100644 index 095b9db..0000000 --- a/SOURCES/0014-Add-support-statement-to-help-output.patch +++ /dev/null @@ -1,55 +0,0 @@ -From fcccb5c061b8bbae29de59637c5ad4cf4416281b Mon Sep 17 00:00:00 2001 -From: Eduardo Habkost -Date: Wed, 4 Dec 2013 18:53:17 +0100 -Subject: Add support statement to -help output - -RH-Author: Eduardo Habkost -Message-id: <1386183197-27761-1-git-send-email-ehabkost@redhat.com> -Patchwork-id: 55994 -O-Subject: [qemu-kvm RHEL7 PATCH] Add support statement to -help output -Bugzilla: 972773 -RH-Acked-by: Miroslav Rezanina -RH-Acked-by: knoel@redhat.com -RH-Acked-by: Paolo Bonzini - -Add support statement to -help output, reporting direct qemu-kvm usage -as unsupported by Red Hat, and advising users to use libvirt instead. - -Signed-off-by: Eduardo Habkost ---- - softmmu/vl.c | 9 +++++++++ - 1 file changed, 9 insertions(+) - -diff --git a/softmmu/vl.c b/softmmu/vl.c -index 620a1f1367..d46b8fb4ab 100644 ---- a/softmmu/vl.c -+++ b/softmmu/vl.c -@@ -827,9 +827,17 @@ static void version(void) - QEMU_COPYRIGHT "\n"); - } - -+static void print_rh_warning(void) -+{ -+ printf("\nWARNING: Direct use of qemu-kvm from the command line is not supported by Red Hat.\n" -+ "WARNING: Use libvirt as the stable management interface.\n" -+ "WARNING: Some command line options listed here may not be available in future releases.\n\n"); -+} -+ - static void help(int exitcode) - { - version(); -+ print_rh_warning(); - printf("usage: %s [options] [disk_image]\n\n" - "'disk_image' is a raw hard disk image for IDE hard disk 0\n\n", - error_get_progname()); -@@ -855,6 +863,7 @@ static void help(int exitcode) - "\n" - QEMU_HELP_BOTTOM "\n"); - -+ print_rh_warning(); - exit(exitcode); - } - --- -2.27.0 - diff --git a/SOURCES/0014-globally-limit-the-maximum-number-of-CPUs.patch b/SOURCES/0014-globally-limit-the-maximum-number-of-CPUs.patch new file mode 100644 index 0000000..6764a84 --- /dev/null +++ b/SOURCES/0014-globally-limit-the-maximum-number-of-CPUs.patch @@ -0,0 +1,45 @@ +From 9ebfd2f6cfa8e79c92e58fd169f90cc768fb865a Mon Sep 17 00:00:00 2001 +From: Andrew Jones +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 +Signed-off-by: Miroslav Rezanina +Signed-off-by: Danilo Cesar Lemes de Paula +--- + 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 + diff --git a/SOURCES/0015-Use-qemu-kvm-in-documentation-instead-of-qemu-system.patch b/SOURCES/0015-Use-qemu-kvm-in-documentation-instead-of-qemu-system.patch new file mode 100644 index 0000000..722484d --- /dev/null +++ b/SOURCES/0015-Use-qemu-kvm-in-documentation-instead-of-qemu-system.patch @@ -0,0 +1,61 @@ +From 4b6c8cdc52fdf94d4098d278defb3833dce1d189 Mon Sep 17 00:00:00 2001 +From: Miroslav Rezanina +Date: Wed, 8 Jul 2020 08:35:50 +0200 +Subject: Use qemu-kvm in documentation instead of qemu-system- + +Patchwork-id: 62380 +O-Subject: [RHEV-7.1 qemu-kvm-rhev PATCHv4] Use qemu-kvm in documentation instead of qemu-system-i386 +Bugzilla: 1140620 +RH-Acked-by: Laszlo Ersek +RH-Acked-by: Markus Armbruster +RH-Acked-by: Stefan Hajnoczi + +From: Miroslav Rezanina + +We change the name and location of qemu-kvm binaries. Update documentation +to reflect this change. Only architectures available in RHEL are updated. + +Signed-off-by: Miroslav Rezanina +--- + docs/defs.rst.inc | 4 ++-- + qemu-options.hx | 10 +++++----- + 2 files changed, 7 insertions(+), 7 deletions(-) + +diff --git a/docs/defs.rst.inc b/docs/defs.rst.inc +index 52d6454b93..d74dbdeca9 100644 +--- a/docs/defs.rst.inc ++++ b/docs/defs.rst.inc +@@ -9,7 +9,7 @@ + but the manpages will end up misrendered with following normal text + incorrectly in boldface. + +-.. |qemu_system| replace:: qemu-system-x86_64 +-.. |qemu_system_x86| replace:: qemu-system-x86_64 ++.. |qemu_system| replace:: qemu-kvm ++.. |qemu_system_x86| replace:: qemu-kvm + .. |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 +--- a/qemu-options.hx ++++ b/qemu-options.hx +@@ -3233,11 +3233,11 @@ SRST + + :: + +- qemu -m 512 -object memory-backend-file,id=mem,size=512M,mem-path=/hugetlbfs,share=on \ +- -numa node,memdev=mem \ +- -chardev socket,id=chr0,path=/path/to/socket \ +- -netdev type=vhost-user,id=net0,chardev=chr0 \ +- -device virtio-net-pci,netdev=net0 ++ qemu-kvm -m 512 -object memory-backend-file,id=mem,size=512M,mem-path=/hugetlbfs,share=on \ ++ -numa node,memdev=mem \ ++ -chardev socket,id=chr0,path=/path/to/socket \ ++ -netdev type=vhost-user,id=net0,chardev=chr0 \ ++ -device virtio-net-pci,netdev=net0 + + ``-netdev vhost-vdpa,vhostdev=/path/to/dev`` + Establish a vhost-vdpa netdev. +-- +2.31.1 + diff --git a/SOURCES/0015-globally-limit-the-maximum-number-of-CPUs.patch b/SOURCES/0015-globally-limit-the-maximum-number-of-CPUs.patch deleted file mode 100644 index 50c1e79..0000000 --- a/SOURCES/0015-globally-limit-the-maximum-number-of-CPUs.patch +++ /dev/null @@ -1,45 +0,0 @@ -From 354c9ce982e566ddb3c724a57252986dcb7c36db Mon Sep 17 00:00:00 2001 -From: Andrew Jones -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 -Signed-off-by: Miroslav Rezanina -Signed-off-by: Danilo Cesar Lemes de Paula ---- - 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 eecd8031cf..8f2a53438f 100644 ---- a/accel/kvm/kvm-all.c -+++ b/accel/kvm/kvm-all.c -@@ -2423,6 +2423,18 @@ 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 " --- -2.27.0 - diff --git a/SOURCES/0016-Use-qemu-kvm-in-documentation-instead-of-qemu-system.patch b/SOURCES/0016-Use-qemu-kvm-in-documentation-instead-of-qemu-system.patch deleted file mode 100644 index 415bcc2..0000000 --- a/SOURCES/0016-Use-qemu-kvm-in-documentation-instead-of-qemu-system.patch +++ /dev/null @@ -1,120 +0,0 @@ -From b057b4ebec0f87f21ba4a15adbb2a1bde7240ed5 Mon Sep 17 00:00:00 2001 -From: Miroslav Rezanina -Date: Wed, 8 Jul 2020 08:35:50 +0200 -Subject: Use qemu-kvm in documentation instead of qemu-system- - -Patchwork-id: 62380 -O-Subject: [RHEV-7.1 qemu-kvm-rhev PATCHv4] Use qemu-kvm in documentation instead of qemu-system-i386 -Bugzilla: 1140620 -RH-Acked-by: Laszlo Ersek -RH-Acked-by: Markus Armbruster -RH-Acked-by: Stefan Hajnoczi - -From: Miroslav Rezanina - -We change the name and location of qemu-kvm binaries. Update documentation -to reflect this change. Only architectures available in RHEL are updated. - -Signed-off-by: Miroslav Rezanina ---- - docs/defs.rst.inc | 4 ++-- - docs/tools/qemu-trace-stap.rst | 14 +++++++------- - qemu-options.hx | 10 +++++----- - 3 files changed, 14 insertions(+), 14 deletions(-) - -diff --git a/docs/defs.rst.inc b/docs/defs.rst.inc -index 52d6454b93..d74dbdeca9 100644 ---- a/docs/defs.rst.inc -+++ b/docs/defs.rst.inc -@@ -9,7 +9,7 @@ - but the manpages will end up misrendered with following normal text - incorrectly in boldface. - --.. |qemu_system| replace:: qemu-system-x86_64 --.. |qemu_system_x86| replace:: qemu-system-x86_64 -+.. |qemu_system| replace:: qemu-kvm -+.. |qemu_system_x86| replace:: qemu-kvm - .. |I2C| replace:: I\ :sup:`2`\ C - .. |I2S| replace:: I\ :sup:`2`\ S -diff --git a/docs/tools/qemu-trace-stap.rst b/docs/tools/qemu-trace-stap.rst -index d53073b52b..9e93df084f 100644 ---- a/docs/tools/qemu-trace-stap.rst -+++ b/docs/tools/qemu-trace-stap.rst -@@ -46,19 +46,19 @@ The following commands are valid: - any of the listed names. If no *PATTERN* is given, the all possible - probes will be listed. - -- For example, to list all probes available in the ``qemu-system-x86_64`` -+ For example, to list all probes available in the ``qemu-kvm`` - binary: - - :: - -- $ qemu-trace-stap list qemu-system-x86_64 -+ $ qemu-trace-stap list qemu-kvm - - To filter the list to only cover probes related to QEMU's cryptographic - subsystem, in a binary outside ``$PATH`` - - :: - -- $ qemu-trace-stap list /opt/qemu/4.0.0/bin/qemu-system-x86_64 'qcrypto*' -+ $ qemu-trace-stap list /opt/qemu/4.0.0/bin/qemu-kvm 'qcrypto*' - - .. option:: run OPTIONS BINARY PATTERN... - -@@ -90,18 +90,18 @@ The following commands are valid: - Restrict the tracing session so that it only triggers for the process - identified by *PID*. - -- For example, to monitor all processes executing ``qemu-system-x86_64`` -+ For example, to monitor all processes executing ``qemu-kvm`` - as found on ``$PATH``, displaying all I/O related probes: - - :: - -- $ qemu-trace-stap run qemu-system-x86_64 'qio*' -+ $ qemu-trace-stap run qemu-kvm 'qio*' - - To monitor only the QEMU process with PID 1732 - - :: - -- $ qemu-trace-stap run --pid=1732 qemu-system-x86_64 'qio*' -+ $ qemu-trace-stap run --pid=1732 qemu-kvm 'qio*' - - To monitor QEMU processes running an alternative binary outside of - ``$PATH``, displaying verbose information about setup of the -@@ -109,7 +109,7 @@ The following commands are valid: - - :: - -- $ qemu-trace-stap -v run /opt/qemu/4.0.0/qemu-system-x86_64 'qio*' -+ $ qemu-trace-stap -v run /opt/qemu/4.0.0/qemu-kvm 'qio*' - - See also - -------- -diff --git a/qemu-options.hx b/qemu-options.hx -index ae2c6dbbfc..94c4a8dbaf 100644 ---- a/qemu-options.hx -+++ b/qemu-options.hx -@@ -3150,11 +3150,11 @@ SRST - - :: - -- qemu -m 512 -object memory-backend-file,id=mem,size=512M,mem-path=/hugetlbfs,share=on \ -- -numa node,memdev=mem \ -- -chardev socket,id=chr0,path=/path/to/socket \ -- -netdev type=vhost-user,id=net0,chardev=chr0 \ -- -device virtio-net-pci,netdev=net0 -+ qemu-kvm -m 512 -object memory-backend-file,id=mem,size=512M,mem-path=/hugetlbfs,share=on \ -+ -numa node,memdev=mem \ -+ -chardev socket,id=chr0,path=/path/to/socket \ -+ -netdev type=vhost-user,id=net0,chardev=chr0 \ -+ -device virtio-net-pci,netdev=net0 - - ``-netdev vhost-vdpa,vhostdev=/path/to/dev`` - Establish a vhost-vdpa netdev. --- -2.27.0 - diff --git a/SOURCES/0016-virtio-scsi-Reject-scsi-cd-if-data-plane-enabled-RHE.patch b/SOURCES/0016-virtio-scsi-Reject-scsi-cd-if-data-plane-enabled-RHE.patch new file mode 100644 index 0000000..9f08024 --- /dev/null +++ b/SOURCES/0016-virtio-scsi-Reject-scsi-cd-if-data-plane-enabled-RHE.patch @@ -0,0 +1,66 @@ +From b72e04cb7e417d9e1c973223747ab3a27abda8b4 Mon Sep 17 00:00:00 2001 +From: Fam Zheng +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 +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 +RH-Acked-by: Stefan Hajnoczi +RH-Acked-by: Max Reitz + +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 +Signed-off-by: Miroslav Rezanina +Signed-off-by: Danilo C. L. de Paula +--- + 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 + diff --git a/SOURCES/0017-BZ1653590-Require-at-least-64kiB-pages-for-downstrea.patch b/SOURCES/0017-BZ1653590-Require-at-least-64kiB-pages-for-downstrea.patch new file mode 100644 index 0000000..2bc687c --- /dev/null +++ b/SOURCES/0017-BZ1653590-Require-at-least-64kiB-pages-for-downstrea.patch @@ -0,0 +1,60 @@ +From 64a06662cdea0ff62efb122be4eab506b2a842d9 Mon Sep 17 00:00:00 2001 +From: David Gibson +Date: Wed, 6 Feb 2019 03:58:56 +0000 +Subject: BZ1653590: Require at least 64kiB pages for downstream guests & hosts + +RH-Author: David Gibson +Message-id: <20190206035856.19058-1-dgibson@redhat.com> +Patchwork-id: 84246 +O-Subject: [RHELAV-8.0/rhel qemu-kvm PATCH] BZ1653590: Require at least 64kiB pages for downstream guests & hosts +Bugzilla: 1653590 +RH-Acked-by: Laurent Vivier +RH-Acked-by: Serhii Popovych +RH-Acked-by: Thomas Huth + +Most current POWER guests require 64kiB page support, so that's the default +for the cap-hpt-max-pagesize option in qemu which limits available guest +page sizes. We warn if the value is set smaller than that, but don't +outright fail upstream, because we need to allow for the possibility of +guest (and/or host) kernels configured for 4kiB page sizes. + +Downstream, however, we simply don't support 4kiB pagesize configured +kernels in guest or host, so we can have qemu simply error out in this +situation. + +Testing: Attempted to start a guest with cap-hpt-max-page-size=4k and verified + it failed immediately with a qemu error + +Signed-off-by: David Gibson +Signed-off-by: Danilo C. L. de Paula +--- + hw/ppc/spapr_caps.c | 7 +++++++ + 1 file changed, 7 insertions(+) + +diff --git a/hw/ppc/spapr_caps.c b/hw/ppc/spapr_caps.c +index 655ab856a0..6aa7f93df9 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, + static void cap_hpt_maxpagesize_apply(SpaprMachineState *spapr, + uint8_t val, Error **errp) + { ++#if 0 /* disabled for RHEL */ + if (val < 12) { + error_setg(errp, "Require at least 4kiB hpt-max-page-size"); + return; + } else if (val < 16) { + warn_report("Many guests require at least 64kiB hpt-max-page-size"); + } ++#else /* Only page sizes >=64kiB supported for RHEL */ ++ if (val < 16) { ++ error_setg(errp, "Require at least 64kiB hpt-max-page-size"); ++ return; ++ } ++#endif + + spapr_check_pagesize(spapr, qemu_minrampagesize(), errp); + } +-- +2.31.1 + diff --git a/SOURCES/0017-virtio-scsi-Reject-scsi-cd-if-data-plane-enabled-RHE.patch b/SOURCES/0017-virtio-scsi-Reject-scsi-cd-if-data-plane-enabled-RHE.patch deleted file mode 100644 index 031b551..0000000 --- a/SOURCES/0017-virtio-scsi-Reject-scsi-cd-if-data-plane-enabled-RHE.patch +++ /dev/null @@ -1,66 +0,0 @@ -From 41fe05330d095f69f12973b0540466439e030047 Mon Sep 17 00:00:00 2001 -From: Fam Zheng -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 -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 -RH-Acked-by: Stefan Hajnoczi -RH-Acked-by: Max Reitz - -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 -Signed-off-by: Miroslav Rezanina -Signed-off-by: Danilo C. L. de Paula ---- - 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 51fd09522a..a35257c35a 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; --- -2.27.0 - diff --git a/SOURCES/0018-BZ1653590-Require-at-least-64kiB-pages-for-downstrea.patch b/SOURCES/0018-BZ1653590-Require-at-least-64kiB-pages-for-downstrea.patch deleted file mode 100644 index 7f161e8..0000000 --- a/SOURCES/0018-BZ1653590-Require-at-least-64kiB-pages-for-downstrea.patch +++ /dev/null @@ -1,60 +0,0 @@ -From 295ee942608d48ab167aa76adabf3697c28e6910 Mon Sep 17 00:00:00 2001 -From: David Gibson -Date: Wed, 6 Feb 2019 03:58:56 +0000 -Subject: BZ1653590: Require at least 64kiB pages for downstream guests & hosts - -RH-Author: David Gibson -Message-id: <20190206035856.19058-1-dgibson@redhat.com> -Patchwork-id: 84246 -O-Subject: [RHELAV-8.0/rhel qemu-kvm PATCH] BZ1653590: Require at least 64kiB pages for downstream guests & hosts -Bugzilla: 1653590 -RH-Acked-by: Laurent Vivier -RH-Acked-by: Serhii Popovych -RH-Acked-by: Thomas Huth - -Most current POWER guests require 64kiB page support, so that's the default -for the cap-hpt-max-pagesize option in qemu which limits available guest -page sizes. We warn if the value is set smaller than that, but don't -outright fail upstream, because we need to allow for the possibility of -guest (and/or host) kernels configured for 4kiB page sizes. - -Downstream, however, we simply don't support 4kiB pagesize configured -kernels in guest or host, so we can have qemu simply error out in this -situation. - -Testing: Attempted to start a guest with cap-hpt-max-page-size=4k and verified - it failed immediately with a qemu error - -Signed-off-by: David Gibson -Signed-off-by: Danilo C. L. de Paula ---- - hw/ppc/spapr_caps.c | 7 +++++++ - 1 file changed, 7 insertions(+) - -diff --git a/hw/ppc/spapr_caps.c b/hw/ppc/spapr_caps.c -index ed7c077a0d..48a8efe678 100644 ---- a/hw/ppc/spapr_caps.c -+++ b/hw/ppc/spapr_caps.c -@@ -332,12 +332,19 @@ bool spapr_check_pagesize(SpaprMachineState *spapr, hwaddr pagesize, - static void cap_hpt_maxpagesize_apply(SpaprMachineState *spapr, - uint8_t val, Error **errp) - { -+#if 0 /* disabled for RHEL */ - if (val < 12) { - error_setg(errp, "Require at least 4kiB hpt-max-page-size"); - return; - } else if (val < 16) { - warn_report("Many guests require at least 64kiB hpt-max-page-size"); - } -+#else /* Only page sizes >=64kiB supported for RHEL */ -+ if (val < 16) { -+ error_setg(errp, "Require at least 64kiB hpt-max-page-size"); -+ return; -+ } -+#endif - - spapr_check_pagesize(spapr, qemu_minrampagesize(), errp); - } --- -2.27.0 - diff --git a/SOURCES/0018-qcow2-Deprecation-warning-when-opening-v2-images-rw.patch b/SOURCES/0018-qcow2-Deprecation-warning-when-opening-v2-images-rw.patch new file mode 100644 index 0000000..d7401d5 --- /dev/null +++ b/SOURCES/0018-qcow2-Deprecation-warning-when-opening-v2-images-rw.patch @@ -0,0 +1,77 @@ +From 54f9157a918e1404f2f17ce89a9c8b9088c1bc06 Mon Sep 17 00:00:00 2001 +From: Kevin Wolf +Date: Fri, 20 Aug 2021 18:25:12 +0200 +Subject: qcow2: Deprecation warning when opening v2 images rw +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Kevin Wolf +RH-MergeRequest: 37: qcow2: Deprecation warning when opening v2 images rw +RH-Commit: [1/1] f450d0ae32d35063b28c72c4f2d2ebb9e6d8db3e (kmwolf/centos-qemu-kvm) +RH-Bugzilla: 1951814 +RH-Acked-by: Stefan Hajnoczi +RH-Acked-by: Hanna Reitz +RH-Acked-by: Thomas Huth +RH-Acked-by: Philippe Mathieu-Daudé + +qcow2 v3 has been around for a long time (since QEMU 1.1/RHEL 7), so +there is no real reason any more to use it. People still using it might +do so unintentionally. Warn about it and suggest upgrading during the +RHEL 9 timeframe so that the code can possibly be disabled in RHEL 10. + +The warning is restricted to read-write mode and the system emulator. +The primary motivation for not having it in qemu-img is that 'qemu-img +amend' for upgrades would warn otherwise. It also avoids having to make +too many changes to the test suite. + +bdrv_uses_whitelist() is used as a proxy for deciding whether we are +running in a tool or the system emulator. This is not entirely clean, +but it's what is available and the same function qcow2_do_open() already +uses it this way for another warning. + +Signed-off-by: Kevin Wolf + +patch_name: kvm-qcow2-Deprecation-warning-when-opening-v2-images-rw.patch +present_in_specfile: true +location_in_specfile: 116 +--- +Rebase notes (6.1.0): +- Replace bs->read_only with bdrv_is_read_only +--- + block/qcow2.c | 6 ++++++ + tests/qemu-iotests/common.filter | 1 + + 2 files changed, 7 insertions(+) + +diff --git a/block/qcow2.c b/block/qcow2.c +index b5c47931ef..a795e457ac 100644 +--- a/block/qcow2.c ++++ b/block/qcow2.c +@@ -1337,6 +1337,12 @@ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options, + ret = -ENOTSUP; + goto fail; + } ++ if (header.version < 3 && !bdrv_is_read_only(bs) && bdrv_uses_whitelist()) { ++ warn_report_once("qcow2 v2 images are deprecated and may not be " ++ "supported in future versions. Please consider " ++ "upgrading the image with 'qemu-img amend " ++ "-o compat=v3'."); ++ } + + s->qcow_version = header.version; + +diff --git a/tests/qemu-iotests/common.filter b/tests/qemu-iotests/common.filter +index cc9f1a5891..6a13757177 100644 +--- a/tests/qemu-iotests/common.filter ++++ b/tests/qemu-iotests/common.filter +@@ -83,6 +83,7 @@ _filter_qemu() + { + gsed -e "s#\\(^\\|(qemu) \\)$(basename $QEMU_PROG):#\1QEMU_PROG:#" \ + -e 's#^QEMU [0-9]\+\.[0-9]\+\.[0-9]\+ monitor#QEMU X.Y.Z monitor#' \ ++ -e "/qcow2 v2 images are deprecated/d" \ + -e $'s#\r##' # QEMU monitor uses \r\n line endings + } + +-- +2.31.1 + diff --git a/SOURCES/0019-WRB-Introduce-RHEL-9.0.0-hw-compat-structure.patch b/SOURCES/0019-WRB-Introduce-RHEL-9.0.0-hw-compat-structure.patch new file mode 100644 index 0000000..285cd6b --- /dev/null +++ b/SOURCES/0019-WRB-Introduce-RHEL-9.0.0-hw-compat-structure.patch @@ -0,0 +1,135 @@ +From 1d6439527aa6ccabb58208c94417778ccc19de39 Mon Sep 17 00:00:00 2001 +From: Miroslav Rezanina +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 +--- + 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 + diff --git a/SOURCES/0019-qcow2-Deprecation-warning-when-opening-v2-images-rw.patch b/SOURCES/0019-qcow2-Deprecation-warning-when-opening-v2-images-rw.patch deleted file mode 100644 index 7ff46fd..0000000 --- a/SOURCES/0019-qcow2-Deprecation-warning-when-opening-v2-images-rw.patch +++ /dev/null @@ -1,77 +0,0 @@ -From a3bb2330bbf68faabc57b768cdf3ae2f4f4d86f3 Mon Sep 17 00:00:00 2001 -From: Kevin Wolf -Date: Fri, 20 Aug 2021 18:25:12 +0200 -Subject: qcow2: Deprecation warning when opening v2 images rw -MIME-Version: 1.0 -Content-Type: text/plain; charset=UTF-8 -Content-Transfer-Encoding: 8bit - -RH-Author: Kevin Wolf -RH-MergeRequest: 37: qcow2: Deprecation warning when opening v2 images rw -RH-Commit: [1/1] f450d0ae32d35063b28c72c4f2d2ebb9e6d8db3e (kmwolf/centos-qemu-kvm) -RH-Bugzilla: 1951814 -RH-Acked-by: Stefan Hajnoczi -RH-Acked-by: Hanna Reitz -RH-Acked-by: Thomas Huth -RH-Acked-by: Philippe Mathieu-Daudé - -qcow2 v3 has been around for a long time (since QEMU 1.1/RHEL 7), so -there is no real reason any more to use it. People still using it might -do so unintentionally. Warn about it and suggest upgrading during the -RHEL 9 timeframe so that the code can possibly be disabled in RHEL 10. - -The warning is restricted to read-write mode and the system emulator. -The primary motivation for not having it in qemu-img is that 'qemu-img -amend' for upgrades would warn otherwise. It also avoids having to make -too many changes to the test suite. - -bdrv_uses_whitelist() is used as a proxy for deciding whether we are -running in a tool or the system emulator. This is not entirely clean, -but it's what is available and the same function qcow2_do_open() already -uses it this way for another warning. - -Signed-off-by: Kevin Wolf - -patch_name: kvm-qcow2-Deprecation-warning-when-opening-v2-images-rw.patch -present_in_specfile: true -location_in_specfile: 116 ---- -Rebase notes (6.1.0): -- Replace bs->read_only with bdrv_is_read_only ---- - block/qcow2.c | 6 ++++++ - tests/qemu-iotests/common.filter | 1 + - 2 files changed, 7 insertions(+) - -diff --git a/block/qcow2.c b/block/qcow2.c -index d509016756..37d1c26a71 100644 ---- a/block/qcow2.c -+++ b/block/qcow2.c -@@ -1336,6 +1336,12 @@ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options, - ret = -ENOTSUP; - goto fail; - } -+ if (header.version < 3 && !bdrv_is_read_only(bs) && bdrv_uses_whitelist()) { -+ warn_report_once("qcow2 v2 images are deprecated and may not be " -+ "supported in future versions. Please consider " -+ "upgrading the image with 'qemu-img amend " -+ "-o compat=v3'."); -+ } - - s->qcow_version = header.version; - -diff --git a/tests/qemu-iotests/common.filter b/tests/qemu-iotests/common.filter -index 2b2b53946c..c5c2dc39bd 100644 ---- a/tests/qemu-iotests/common.filter -+++ b/tests/qemu-iotests/common.filter -@@ -82,6 +82,7 @@ _filter_qemu() - { - $SED -e "s#\\(^\\|(qemu) \\)$(basename $QEMU_PROG):#\1QEMU_PROG:#" \ - -e 's#^QEMU [0-9]\+\.[0-9]\+\.[0-9]\+ monitor#QEMU X.Y.Z monitor#' \ -+ -e "/qcow2 v2 images are deprecated/d" \ - -e $'s#\r##' # QEMU monitor uses \r\n line endings - } - --- -2.27.0 - diff --git a/SOURCES/0020-Fix-virtio-net-pci-vectors-compat.patch b/SOURCES/0020-Fix-virtio-net-pci-vectors-compat.patch deleted file mode 100644 index 6caad1d..0000000 --- a/SOURCES/0020-Fix-virtio-net-pci-vectors-compat.patch +++ /dev/null @@ -1,46 +0,0 @@ -From ef5afcc86dc44d1c9d3030a8ceca2018df86c6ec Mon Sep 17 00:00:00 2001 -From: Eduardo Habkost -Date: Tue, 19 Oct 2021 13:17:06 -0400 -Subject: Fix virtio-net-pci* "vectors" compat - -RH-Author: Dr. David Alan Gilbert -RH-MergeRequest: 76: 9.0/6.2.0-rc1 x86 machine type fixes -RH-Commit: [20/22] ebb570f053f96d3558bac49962dc7dc88296c207 -RH-Bugzilla: 2025468 -RH-Acked-by: quintela1 -RH-Acked-by: Vitaly Kuznetsov -RH-Acked-by: Cornelia Huck - -hw_compat_rhel_8_4 has an issue: it affects only "virtio-net-pci" -but not "virtio-net-pci-transitional" and -"virtio-net-pci-non-transitional". The solution is to use the -"virtio-net-pci-base" type in compat_props. - -An equivalent fix will be submitted for hw_compat_5_2 upstream. - -Signed-off-by: Eduardo Habkost -(cherry picked from commit d45823ab0d0138b2fbaf2ed1e1896d2052f3ccb3) ---- - hw/core/machine.c | 6 +++++- - 1 file changed, 5 insertions(+), 1 deletion(-) - -diff --git a/hw/core/machine.c b/hw/core/machine.c -index 53a3caf4fb..448a8dd127 100644 ---- a/hw/core/machine.c -+++ b/hw/core/machine.c -@@ -69,7 +69,11 @@ GlobalProperty hw_compat_rhel_8_4[] = { - /* hw_compat_rhel_8_4 from hw_compat_5_2 */ - { "virtio-blk-device", "report-discard-granularity", "off" }, - /* hw_compat_rhel_8_4 from hw_compat_5_2 */ -- { "virtio-net-pci", "vectors", "3"}, -+ /* -+ * Upstream incorrectly had "virtio-net-pci" instead of "virtio-net-pci-base", -+ * (https://bugzilla.redhat.com/show_bug.cgi?id=1999141) -+ */ -+ { "virtio-net-pci-base", "vectors", "3"}, - }; - const size_t hw_compat_rhel_8_4_len = G_N_ELEMENTS(hw_compat_rhel_8_4); - --- -2.27.0 - diff --git a/SOURCES/0020-redhat-Update-s390x-machine-type-compatibility-for-r.patch b/SOURCES/0020-redhat-Update-s390x-machine-type-compatibility-for-r.patch new file mode 100644 index 0000000..d3b91d0 --- /dev/null +++ b/SOURCES/0020-redhat-Update-s390x-machine-type-compatibility-for-r.patch @@ -0,0 +1,38 @@ +From c8ad21ca31892f8798cf82508c2b2c61bf3b9895 Mon Sep 17 00:00:00 2001 +From: Thomas Huth +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 +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 +RH-Acked-by: David Hildenbrand + +No s390x-specific machine class property updates required this time, +only an update to the default qemu cpu model. + +Signed-off-by: Thomas Huth +--- + 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 + diff --git a/SOURCES/0021-pc-Move-s3-s4-suspend-disabling-to-compat.patch b/SOURCES/0021-pc-Move-s3-s4-suspend-disabling-to-compat.patch new file mode 100644 index 0000000..f9535a8 --- /dev/null +++ b/SOURCES/0021-pc-Move-s3-s4-suspend-disabling-to-compat.patch @@ -0,0 +1,70 @@ +From 38b89dc24551258b630f09d1c654b6c72b265c79 Mon Sep 17 00:00:00 2001 +From: "Dr. David Alan Gilbert" +Date: Thu, 14 Apr 2022 14:58:43 +0100 +Subject: pc: Move s3/s4 suspend disabling to compat + +RH-Author: Dr. David Alan Gilbert +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 +--- + 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 + diff --git a/SOURCES/0021-x86-rhel-machine-types-Add-pc_rhel_8_5_compat.patch b/SOURCES/0021-x86-rhel-machine-types-Add-pc_rhel_8_5_compat.patch deleted file mode 100644 index 8ef276d..0000000 --- a/SOURCES/0021-x86-rhel-machine-types-Add-pc_rhel_8_5_compat.patch +++ /dev/null @@ -1,75 +0,0 @@ -From eae7d8dd3c3b9aa859a619933f52a4759a42bf66 Mon Sep 17 00:00:00 2001 -From: "Dr. David Alan Gilbert" -Date: Tue, 23 Nov 2021 17:57:42 +0000 -Subject: x86/rhel machine types: Add pc_rhel_8_5_compat - -RH-Author: Dr. David Alan Gilbert -RH-MergeRequest: 76: 9.0/6.2.0-rc1 x86 machine type fixes -RH-Commit: [21/22] dd23060695bc0ad892bbfa51d93afe31f5d745c7 -RH-Bugzilla: 2025468 -RH-Acked-by: quintela1 -RH-Acked-by: Vitaly Kuznetsov -RH-Acked-by: Cornelia Huck - -Add pc_rhel_8_5_compat as the merge of pc_compat_6_1 and pc_compat_6_0 -(since 8.5 was based on 6.0). - -Note, x-keep-pci-slot-hpc flipped back and forward, leaving it out -looks like it leaves us with the original. - -Signed-off-by: Dr. David Alan Gilbert -Signed-off-by: Miroslav Rezanina ---- - hw/i386/pc.c | 21 +++++++++++++++++++++ - include/hw/i386/pc.h | 3 +++ - 2 files changed, 24 insertions(+) - -diff --git a/hw/i386/pc.c b/hw/i386/pc.c -index b6d2db8d04..4661473d2a 100644 ---- a/hw/i386/pc.c -+++ b/hw/i386/pc.c -@@ -387,6 +387,27 @@ GlobalProperty pc_rhel_compat[] = { - }; - const size_t pc_rhel_compat_len = G_N_ELEMENTS(pc_rhel_compat); - -+GlobalProperty pc_rhel_8_5_compat[] = { -+ /* pc_rhel_8_5_compat from pc_compat_6_0 */ -+ { "qemu64" "-" TYPE_X86_CPU, "family", "6" }, -+ /* pc_rhel_8_5_compat from pc_compat_6_0 */ -+ { "qemu64" "-" TYPE_X86_CPU, "model", "6" }, -+ /* pc_rhel_8_5_compat from pc_compat_6_0 */ -+ { "qemu64" "-" TYPE_X86_CPU, "stepping", "3" }, -+ /* pc_rhel_8_5_compat from pc_compat_6_0 */ -+ { TYPE_X86_CPU, "x-vendor-cpuid-only", "off" }, -+ /* pc_rhel_8_5_compat from pc_compat_6_0 */ -+ { "ICH9-LPC", ACPI_PM_PROP_ACPI_PCIHP_BRIDGE, "off" }, -+ -+ /* pc_rhel_8_5_compat from pc_compat_6_1 */ -+ { TYPE_X86_CPU, "hv-version-id-build", "0x1bbc" }, -+ /* pc_rhel_8_5_compat from pc_compat_6_1 */ -+ { TYPE_X86_CPU, "hv-version-id-major", "0x0006" }, -+ /* pc_rhel_8_5_compat from pc_compat_6_1 */ -+ { TYPE_X86_CPU, "hv-version-id-minor", "0x0001" }, -+}; -+const size_t pc_rhel_8_5_compat_len = G_N_ELEMENTS(pc_rhel_8_5_compat); -+ - GlobalProperty pc_rhel_8_4_compat[] = { - /* pc_rhel_8_4_compat from pc_compat_5_2 */ - { "ICH9-LPC", "x-smi-cpu-hotunplug", "off" }, -diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h -index 9689a58b14..afb570ba14 100644 ---- a/include/hw/i386/pc.h -+++ b/include/hw/i386/pc.h -@@ -283,6 +283,9 @@ 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_8_5_compat[]; -+extern const size_t pc_rhel_8_5_compat_len; -+ - extern GlobalProperty pc_rhel_8_4_compat[]; - extern const size_t pc_rhel_8_4_compat_len; - --- -2.27.0 - diff --git a/SOURCES/0022-x86-rhel-machine-types-Wire-compat-into-q35-and-i440.patch b/SOURCES/0022-x86-rhel-machine-types-Wire-compat-into-q35-and-i440.patch deleted file mode 100644 index 85c6b26..0000000 --- a/SOURCES/0022-x86-rhel-machine-types-Wire-compat-into-q35-and-i440.patch +++ /dev/null @@ -1,55 +0,0 @@ -From 6762f5646943c759ece5972f08eb88364cf0a8ad Mon Sep 17 00:00:00 2001 -From: "Dr. David Alan Gilbert" -Date: Tue, 23 Nov 2021 18:07:49 +0000 -Subject: x86/rhel machine types: Wire compat into q35 and i440fx - -RH-Author: Dr. David Alan Gilbert -RH-MergeRequest: 76: 9.0/6.2.0-rc1 x86 machine type fixes -RH-Commit: [22/22] e2767df0d920773057cb52d346e0106a76cb0a28 -RH-Bugzilla: 2025468 -RH-Acked-by: quintela1 -RH-Acked-by: Vitaly Kuznetsov -RH-Acked-by: Cornelia Huck -Wire the pc_rhel_8_5 compat data into both piix and q35 -to keep the existing machine types compatible. - -Signed-off-by: Dr. David Alan Gilbert -Signed-off-by: Miroslav Rezanina ---- - hw/i386/pc_piix.c | 4 ++++ - hw/i386/pc_q35.c | 4 ++++ - 2 files changed, 8 insertions(+) - -diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c -index dabc6c1933..183b5d5464 100644 ---- a/hw/i386/pc_piix.c -+++ b/hw/i386/pc_piix.c -@@ -993,6 +993,10 @@ 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_8_5, -+ hw_compat_rhel_8_5_len); -+ compat_props_add(m->compat_props, pc_rhel_8_5_compat, -+ pc_rhel_8_5_compat_len); - compat_props_add(m->compat_props, hw_compat_rhel_8_4, - hw_compat_rhel_8_4_len); - compat_props_add(m->compat_props, pc_rhel_8_4_compat, -diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c -index 04c911da18..0e7e885e78 100644 ---- a/hw/i386/pc_q35.c -+++ b/hw/i386/pc_q35.c -@@ -658,6 +658,10 @@ static void pc_q35_machine_rhel850_options(MachineClass *m) - m->desc = "RHEL-8.5.0 PC (Q35 + ICH9, 2009)"; - pcmc->smbios_stream_product = "RHEL-AV"; - pcmc->smbios_stream_version = "8.5.0"; -+ compat_props_add(m->compat_props, hw_compat_rhel_8_5, -+ hw_compat_rhel_8_5_len); -+ compat_props_add(m->compat_props, pc_rhel_8_5_compat, -+ pc_rhel_8_5_compat_len); - } - - DEFINE_PC_MACHINE(q35_rhel850, "pc-q35-rhel8.5.0", pc_q35_init_rhel850, --- -2.27.0 - diff --git a/SOURCES/0023-redhat-virt-rhel8.5.0-Update-machine-type-compatibil.patch b/SOURCES/0023-redhat-virt-rhel8.5.0-Update-machine-type-compatibil.patch deleted file mode 100644 index 293854f..0000000 --- a/SOURCES/0023-redhat-virt-rhel8.5.0-Update-machine-type-compatibil.patch +++ /dev/null @@ -1,50 +0,0 @@ -From 3b82be3dd3d5254baedf82ba2a6cf0412e84a991 Mon Sep 17 00:00:00 2001 -From: Eric Auger -Date: Tue, 16 Nov 2021 17:03:07 +0100 -Subject: redhat: virt-rhel8.5.0: Update machine type compatibility for QEMU - 6.2.0 update - -RH-Author: Eric Auger -RH-MergeRequest: 75: redhat: virt-rhel8.5.0: Update machine type compatibility for QEMU 6.2.0 update -RH-Commit: [21/21] f027d13654944e3d34e3356affe7af952eec2bed -RH-Bugzilla: 2022607 -RH-Acked-by: Gavin Shan -RH-Acked-by: Miroslav Rezanina -RH-Acked-by: Andrew Jones -RH-Acked-by: Cornelia Huck -RH-Acked-by: Laurent Vivier - -To keep compatibility with 8.5-AV machine type we need to -turn few new options on by default: -smp_props.prefer_sockets, no_cpu_topology, no_tcg_its - -TESTED: migrate from rhel-av-8.5.0 to rhel-8.6.0 and vice-versa -with upstream fix: 33a0c404fb hw/intc/arm_gicv3_its: Revert version -increments in vmstate_its - -Signed-off-by: Eric Auger -Signed-off-by: Miroslav Rezanina ---- - hw/arm/virt.c | 5 +++++ - 1 file changed, 5 insertions(+) - -diff --git a/hw/arm/virt.c b/hw/arm/virt.c -index 7d51824263..6ba9a2c2e1 100644 ---- a/hw/arm/virt.c -+++ b/hw/arm/virt.c -@@ -3230,7 +3230,12 @@ type_init(rhel_machine_init); - - static void rhel850_virt_options(MachineClass *mc) - { -+ 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_8_5, hw_compat_rhel_8_5_len); -+ mc->smp_props.prefer_sockets = true; -+ vmc->no_cpu_topology = true; -+ vmc->no_tcg_its = true; - } - DEFINE_RHEL_MACHINE_AS_LATEST(8, 5, 0) --- -2.27.0 - diff --git a/SOURCES/0024-redhat-Add-s390x-machine-type-compatibility-handling.patch b/SOURCES/0024-redhat-Add-s390x-machine-type-compatibility-handling.patch deleted file mode 100644 index 9762048..0000000 --- a/SOURCES/0024-redhat-Add-s390x-machine-type-compatibility-handling.patch +++ /dev/null @@ -1,58 +0,0 @@ -From e6ff4de4f7036f88ee63adad6de5ee5dd74f1d99 Mon Sep 17 00:00:00 2001 -From: Thomas Huth -Date: Fri, 26 Nov 2021 09:37:11 +0100 -Subject: redhat: Add s390x machine type compatibility handling for the rebase - to v6.2 - -RH-Author: Thomas Huth -RH-MergeRequest: 80: Add s390x machine type compatibility handling for the rebase to v6.2 -RH-Commit: [26/26] c45cf594604f6dd23954696b9c84d2025e328d11 -RH-Bugzilla: 2022602 -RH-Acked-by: David Hildenbrand -RH-Acked-by: Laurent Vivier -RH-Acked-by: Cornelia Huck - -Add compatibility handling for the rhel8.5.0 machine type (and -recursively older, of course). - -Based on the following upstream commits: - - 463e50da8b - s390x/cpumodel: Bump up QEMU model to a stripped-down IBM z14 GA2 - 30e398f796 - s390x/cpumodel: Add more feature to gen16 default model - 4a0af2930a - machine: Prefer cores over sockets in smp parsing since 6.2 - 2b52619994 - machine: Move smp_prefer_sockets to struct SMPCompatProps - -Signed-off-by: Thomas Huth ---- - hw/s390x/s390-virtio-ccw.c | 10 ++++++++++ - 1 file changed, 10 insertions(+) - -diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c -index 4af14cb9ca..c654045964 100644 ---- a/hw/s390x/s390-virtio-ccw.c -+++ b/hw/s390x/s390-virtio-ccw.c -@@ -1105,11 +1105,21 @@ DEFINE_CCW_MACHINE(2_4, "2.4", false); - - static void ccw_machine_rhel850_instance_options(MachineState *machine) - { -+ static const S390FeatInit qemu_cpu_feat = { S390_FEAT_LIST_QEMU_V6_0 }; -+ -+ s390_set_qemu_cpu_model(0x2964, 13, 2, qemu_cpu_feat); -+ -+ s390_cpudef_featoff_greater(16, 1, S390_FEAT_NNPA); -+ s390_cpudef_featoff_greater(16, 1, S390_FEAT_VECTOR_PACKED_DECIMAL_ENH2); -+ s390_cpudef_featoff_greater(16, 1, S390_FEAT_BEAR_ENH); -+ s390_cpudef_featoff_greater(16, 1, S390_FEAT_RDP); -+ s390_cpudef_featoff_greater(16, 1, S390_FEAT_PAI); - } - - static void ccw_machine_rhel850_class_options(MachineClass *mc) - { - compat_props_add(mc->compat_props, hw_compat_rhel_8_5, hw_compat_rhel_8_5_len); -+ mc->smp_props.prefer_sockets = true; - } - DEFINE_CCW_MACHINE(rhel850, "rhel8.5.0", true); - --- -2.27.0 - diff --git a/SOURCES/0025-compat-Update-hw_compat_rhel_8_5-with-6.2.0-RC2-chan.patch b/SOURCES/0025-compat-Update-hw_compat_rhel_8_5-with-6.2.0-RC2-chan.patch deleted file mode 100644 index 1fdd794..0000000 --- a/SOURCES/0025-compat-Update-hw_compat_rhel_8_5-with-6.2.0-RC2-chan.patch +++ /dev/null @@ -1,31 +0,0 @@ -From 168f0d56e3a37a7d5fcc59483e2b1181824a23d2 Mon Sep 17 00:00:00 2001 -From: Miroslav Rezanina -Date: Wed, 24 Nov 2021 23:51:52 -0500 -Subject: compat: Update hw_compat_rhel_8_5 with 6.2.0 RC2 changes - -In RC2 nvme-ns 'shared' default was changed (commit 916b0f0b52). - -Adding compat record for RHEL 8.5.0 so we keep it off for downstream -machinetypes. - -Signed-off-by: Miroslav Rezanina ---- - hw/core/machine.c | 2 ++ - 1 file changed, 2 insertions(+) - -diff --git a/hw/core/machine.c b/hw/core/machine.c -index 448a8dd127..669d3d8b91 100644 ---- a/hw/core/machine.c -+++ b/hw/core/machine.c -@@ -55,6 +55,8 @@ GlobalProperty hw_compat_rhel_8_5[] = { - { "vhost-vsock-device", "seqpacket", "off" }, - /* hw_compat_rhel_8_5 from hw_compat_6_1 */ - { "vhost-user-vsock-device", "seqpacket", "off" }, -+ /* hw_compat_rhel_8_5 from hw_compat_6_1 */ -+ { "nvme-ns", "shared", "off" }, - }; - const size_t hw_compat_rhel_8_5_len = G_N_ELEMENTS(hw_compat_rhel_8_5); - --- -2.27.0 - diff --git a/SOURCES/kvm-Add-dirty-sync-missed-zero-copy-migration-stat.patch b/SOURCES/kvm-Add-dirty-sync-missed-zero-copy-migration-stat.patch new file mode 100644 index 0000000..30c28f7 --- /dev/null +++ b/SOURCES/kvm-Add-dirty-sync-missed-zero-copy-migration-stat.patch @@ -0,0 +1,87 @@ +From ac346634c5731407baa9de709dbd4d5cc6f45301 Mon Sep 17 00:00:00 2001 +From: Leonardo Bras +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 +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 +RH-Acked-by: Thomas Huth +RH-Acked-by: Dr. David Alan Gilbert + +Signed-off-by: Leonardo Bras +Acked-by: Markus Armbruster +Acked-by: Peter Xu +Reviewed-by: Daniel P. Berrangé +Message-Id: <20220711211112.18951-3-leobras@redhat.com> +Signed-off-by: Dr. David Alan Gilbert +(cherry picked from commit cf20c897338067ab4b70a4596fdccaf90c7e29a1) +Signed-off-by: Leonardo Bras +--- + 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 + diff --git a/SOURCES/kvm-Enable-SGX-RH-Only.patch b/SOURCES/kvm-Enable-SGX-RH-Only.patch deleted file mode 100644 index 63f335b..0000000 --- a/SOURCES/kvm-Enable-SGX-RH-Only.patch +++ /dev/null @@ -1,28 +0,0 @@ -From f4f7c62a4658a570d3ad694b64463665fa4b80a7 Mon Sep 17 00:00:00 2001 -From: Paul Lai -Date: Fri, 21 Jan 2022 13:14:42 -0500 -Subject: [PATCH 04/12] Enable SGX -- RH Only - -RH-Author: Paul Lai -RH-MergeRequest: 65: Enable SGX and add SGX Numa support -RH-Commit: [4/5] 2cd4ee4a429f5e7b1c32e83a10bf488503603795 -RH-Bugzilla: 2033708 -RH-Acked-by: Paolo Bonzini -RH-Acked-by: Bandan Das -RH-Acked-by: Cornelia Huck ---- - 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 dc03fbb671..327b1bee62 100644 ---- a/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak -+++ b/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak -@@ -101,3 +101,4 @@ CONFIG_TPM=y - CONFIG_TPM_CRB=y - CONFIG_TPM_TIS_ISA=y - CONFIG_TPM_EMULATOR=y -+CONFIG_SGX=y --- -2.27.0 - diff --git a/SOURCES/kvm-Enable-virtio-iommu-pci-on-aarch64.patch b/SOURCES/kvm-Enable-virtio-iommu-pci-on-aarch64.patch new file mode 100644 index 0000000..3aafd3c --- /dev/null +++ b/SOURCES/kvm-Enable-virtio-iommu-pci-on-aarch64.patch @@ -0,0 +1,41 @@ +From 85781b8745fa1581a66f64011d61a4f0c4e103dc Mon Sep 17 00:00:00 2001 +From: Eric Auger +Date: Fri, 6 May 2022 17:03:11 +0200 +Subject: [PATCH 3/5] Enable virtio-iommu-pci on aarch64 + +RH-Author: Eric Auger +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 +RH-Acked-by: Andrew Jones +RH-Acked-by: Cornelia Huck + +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 +--- + 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 + diff --git a/SOURCES/kvm-Enable-virtio-iommu-pci-on-x86_64.patch b/SOURCES/kvm-Enable-virtio-iommu-pci-on-x86_64.patch new file mode 100644 index 0000000..2eb24df --- /dev/null +++ b/SOURCES/kvm-Enable-virtio-iommu-pci-on-x86_64.patch @@ -0,0 +1,41 @@ +From c531a39171201f8a1d063e6af752e5d629c1b4bf Mon Sep 17 00:00:00 2001 +From: Eric Auger +Date: Thu, 9 Jun 2022 11:35:18 +0200 +Subject: [PATCH 4/6] Enable virtio-iommu-pci on x86_64 + +RH-Author: Eric Auger +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 +RH-Acked-by: MST +RH-Acked-by: Cornelia Huck + +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 +--- + 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 + diff --git a/SOURCES/kvm-Introduce-event-loop-base-abstract-class.patch b/SOURCES/kvm-Introduce-event-loop-base-abstract-class.patch new file mode 100644 index 0000000..9f987ea --- /dev/null +++ b/SOURCES/kvm-Introduce-event-loop-base-abstract-class.patch @@ -0,0 +1,503 @@ +From 1163da281c178359dd7e1cf1ced5c98caa600f8e Mon Sep 17 00:00:00 2001 +From: Nicolas Saenz Julienne +Date: Mon, 25 Apr 2022 09:57:21 +0200 +Subject: [PATCH 01/16] Introduce event-loop-base abstract class + +RH-Author: Nicolas Saenz Julienne +RH-MergeRequest: 93: util/thread-pool: Expose minimum and maximum size +RH-Commit: [1/3] 5817205d8f56cc4aa98bd5963ecac54a59bad990 +RH-Bugzilla: 2031024 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Stefan Hajnoczi + +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 +Reviewed-by: Stefan Hajnoczi +Acked-by: Markus Armbruster +Message-id: 20220425075723.20019-2-nsaenzju@redhat.com +Signed-off-by: Stefan Hajnoczi +(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 ++ * Nicolas Saenz Julienne ++ * ++ * 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 ++ * ++ * 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 + diff --git a/SOURCES/kvm-QIOChannel-Add-flags-on-io_writev-and-introduce-io_f.patch b/SOURCES/kvm-QIOChannel-Add-flags-on-io_writev-and-introduce-io_f.patch new file mode 100644 index 0000000..c7b8898 --- /dev/null +++ b/SOURCES/kvm-QIOChannel-Add-flags-on-io_writev-and-introduce-io_f.patch @@ -0,0 +1,420 @@ +From cda3fcf14f2883fea633e25256f6c14a71271adf Mon Sep 17 00:00:00 2001 +From: Leonardo Bras +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 +RH-MergeRequest: 95: MSG_ZEROCOPY + Multifd +RH-Commit: [2/11] 06acfb6b0cb2c25733c2eb198011f7623b5a7024 (LeoBras/centos-qemu-kvm) +RH-Bugzilla: 1968509 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Dr. David Alan Gilbert +RH-Acked-by: Peter Xu + +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 +Reviewed-by: Daniel P. Berrangé +Reviewed-by: Peter Xu +Reviewed-by: Juan Quintela +Message-Id: <20220513062836.965425-3-leobras@redhat.com> +Signed-off-by: Dr. David Alan Gilbert +(cherry picked from commit b88651cb4d4fa416fdbb6afaf5b26ec8c035eaad) +Signed-off-by: Leonardo Bras +--- + 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 + diff --git a/SOURCES/kvm-QIOChannelSocket-Add-support-for-MSG_ZEROCOPY-IPV6.patch b/SOURCES/kvm-QIOChannelSocket-Add-support-for-MSG_ZEROCOPY-IPV6.patch new file mode 100644 index 0000000..0fd4b6c --- /dev/null +++ b/SOURCES/kvm-QIOChannelSocket-Add-support-for-MSG_ZEROCOPY-IPV6.patch @@ -0,0 +1,56 @@ +From cb6dc39a5e5d2d981b4b1e983042b3fbb529d5d1 Mon Sep 17 00:00:00 2001 +From: Leonardo Bras +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 +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 +RH-Acked-by: Thomas Huth +RH-Acked-by: Dr. David Alan Gilbert + +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 +Signed-off-by: Daniel P. Berrangé +(cherry picked from commit 5258a7e2c0677d16e9e1d06845f60171adf0b290) +Signed-off-by: Leonardo Bras +--- + 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 + diff --git a/SOURCES/kvm-QIOChannelSocket-Fix-zero-copy-flush-returning-code-.patch b/SOURCES/kvm-QIOChannelSocket-Fix-zero-copy-flush-returning-code-.patch new file mode 100644 index 0000000..b382a59 --- /dev/null +++ b/SOURCES/kvm-QIOChannelSocket-Fix-zero-copy-flush-returning-code-.patch @@ -0,0 +1,65 @@ +From 678981c6bb7c964e1591f6f8aba49e9602f64852 Mon Sep 17 00:00:00 2001 +From: Leonardo Bras +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 +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 +RH-Acked-by: Thomas Huth +RH-Acked-by: Dr. David Alan Gilbert + +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 +Reviewed-by: Daniel P. Berrangé +Acked-by: Daniel P. Berrangé +Reviewed-by: Juan Quintela +Reviewed-by: Peter Xu +Message-Id: <20220711211112.18951-2-leobras@redhat.com> +Signed-off-by: Dr. David Alan Gilbert +(cherry picked from commit 927f93e099c4f9184e60a1bc61624ac2d04d0223) +Signed-off-by: Leonardo Bras +--- + 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 + diff --git a/SOURCES/kvm-QIOChannelSocket-Fix-zero-copy-send-so-socket-flush-.patch b/SOURCES/kvm-QIOChannelSocket-Fix-zero-copy-send-so-socket-flush-.patch new file mode 100644 index 0000000..9d134e6 --- /dev/null +++ b/SOURCES/kvm-QIOChannelSocket-Fix-zero-copy-send-so-socket-flush-.patch @@ -0,0 +1,58 @@ +From e70f01749addd7d0b7aa7fa4fdedb664f98e6b9b Mon Sep 17 00:00:00 2001 +From: Leonardo Bras +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 +RH-MergeRequest: 95: MSG_ZEROCOPY + Multifd +RH-Commit: [10/11] a2dfac987e24026b1a78e90b86234ca206b6401f (LeoBras/centos-qemu-kvm) +RH-Bugzilla: 1968509 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Dr. David Alan Gilbert +RH-Acked-by: Peter Xu + +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 +Signed-off-by: Leonardo Bras +Reviewed-by: Daniel P. Berrangé +Reviewed-by: Peter Xu +Reviewed-by: Juan Quintela +Signed-off-by: Juan Quintela +Signed-off-by: Dr. David Alan Gilbert +(cherry picked from commit 4f5a09714c983a3471fd12e3c7f3196e95c650c1) +Signed-off-by: Leonardo Bras +--- + 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 + diff --git a/SOURCES/kvm-QIOChannelSocket-Implement-io_writev-zero-copy-flag-.patch b/SOURCES/kvm-QIOChannelSocket-Implement-io_writev-zero-copy-flag-.patch new file mode 100644 index 0000000..89aa806 --- /dev/null +++ b/SOURCES/kvm-QIOChannelSocket-Implement-io_writev-zero-copy-flag-.patch @@ -0,0 +1,249 @@ +From 4aeba0365d30dabe2e70dc172683f0878a4a9621 Mon Sep 17 00:00:00 2001 +From: Leonardo Bras +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 +RH-MergeRequest: 95: MSG_ZEROCOPY + Multifd +RH-Commit: [3/11] 9afeac1f5ac7675624660a0281726c09c8321180 (LeoBras/centos-qemu-kvm) +RH-Bugzilla: 1968509 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Dr. David Alan Gilbert +RH-Acked-by: Peter Xu + +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 +Reviewed-by: Peter Xu +Reviewed-by: Daniel P. Berrangé +Reviewed-by: Juan Quintela +Message-Id: <20220513062836.965425-4-leobras@redhat.com> +Signed-off-by: Dr. David Alan Gilbert +(cherry picked from commit 2bc58ffc2926a4efdd03edfb5909861fefc68c3d) +Signed-off-by: Leonardo Bras +--- + 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 ++#include ++ ++#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 + diff --git a/SOURCES/kvm-QIOChannelSocket-Introduce-assert-and-reduce-ifdefs-.patch b/SOURCES/kvm-QIOChannelSocket-Introduce-assert-and-reduce-ifdefs-.patch new file mode 100644 index 0000000..6fc0c76 --- /dev/null +++ b/SOURCES/kvm-QIOChannelSocket-Introduce-assert-and-reduce-ifdefs-.patch @@ -0,0 +1,82 @@ +From 60bf942a58db12c821f2a6a49e2e0b04b99bec30 Mon Sep 17 00:00:00 2001 +From: Leonardo Bras +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 +RH-MergeRequest: 95: MSG_ZEROCOPY + Multifd +RH-Commit: [9/11] eaa02d68301852ccc98bdacc7387d8d03be1cb05 (LeoBras/centos-qemu-kvm) +RH-Bugzilla: 1968509 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Dr. David Alan Gilbert +RH-Acked-by: Peter Xu + +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 +Reviewed-by: Daniel P. Berrangé +Reviewed-by: Juan Quintela +Reviewed-by: Peter Xu +Signed-off-by: Juan Quintela +Signed-off-by: Dr. David Alan Gilbert + dgilbert: Fixed up thinko'd g_assert_unreachable->g_assert_not_reached +(cherry picked from commit 803ca43e4c7fcf32f9f68c118301ccd0c83ece3f) +Signed-off-by: Leonardo Bras +--- + 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 + diff --git a/SOURCES/kvm-RHEL-disable-seqpacket-for-vhost-vsock-device-in-rhe.patch b/SOURCES/kvm-RHEL-disable-seqpacket-for-vhost-vsock-device-in-rhe.patch deleted file mode 100644 index fa17617..0000000 --- a/SOURCES/kvm-RHEL-disable-seqpacket-for-vhost-vsock-device-in-rhe.patch +++ /dev/null @@ -1,107 +0,0 @@ -From 5688fdb9a3ed192b85dca84c47a7ddfd325778d9 Mon Sep 17 00:00:00 2001 -From: Stefano Garzarella -Date: Thu, 24 Mar 2022 16:04:57 +0100 -Subject: [PATCH 1/3] RHEL: disable "seqpacket" for "vhost-vsock-device" in - rhel8.6.0 -MIME-Version: 1.0 -Content-Type: text/plain; charset=UTF-8 -Content-Transfer-Encoding: 8bit - -RH-Author: Stefano Garzarella -RH-MergeRequest: 135: RHEL: disable "seqpacket" for "vhost-vsock-device" in rhel8.6.0 [rhel-9.0.0.z] -RH-Commit: [1/1] 5ee0de3110deaa0222c9783c00168b536b0c8934 -RH-Bugzilla: 2071102 -RH-Acked-by: Jason Wang -RH-Acked-by: Eugenio Pérez -RH-Acked-by: Dr. David Alan Gilbert -RH-Acked-by: Stefan Hajnoczi - -vhost-vsock device in RHEL 8 kernels doesn't support seqpacket. -To avoid problems when migrating a VM from RHEL 9 host, we need to -disable it in rhel8-* machine types. - -Signed-off-by: Stefano Garzarella ---- - hw/core/machine.c | 10 ++++++++++ - hw/i386/pc_piix.c | 2 ++ - hw/i386/pc_q35.c | 2 ++ - hw/s390x/s390-virtio-ccw.c | 1 + - include/hw/boards.h | 3 +++ - 5 files changed, 18 insertions(+) - -diff --git a/hw/core/machine.c b/hw/core/machine.c -index 5fae55d6cd..7dcceb904a 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_piix.c b/hw/i386/pc_piix.c -index cf68d7498c..08579366b6 100644 ---- a/hw/i386/pc_piix.c -+++ b/hw/i386/pc_piix.c -@@ -998,6 +998,8 @@ 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_8_6, -+ hw_compat_rhel_8_6_len); - compat_props_add(m->compat_props, hw_compat_rhel_8_5, - hw_compat_rhel_8_5_len); - compat_props_add(m->compat_props, pc_rhel_8_5_compat, -diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c -index c8e06da084..23dacdd923 100644 ---- a/hw/i386/pc_q35.c -+++ b/hw/i386/pc_q35.c -@@ -680,6 +680,8 @@ static void pc_q35_machine_rhel860_options(MachineClass *m) - - pcmc->smbios_stream_product = "RHEL-AV"; - pcmc->smbios_stream_version = "8.6.0"; -+ compat_props_add(m->compat_props, hw_compat_rhel_8_6, -+ hw_compat_rhel_8_6_len); - } - - DEFINE_PC_MACHINE(q35_rhel860, "pc-q35-rhel8.6.0", pc_q35_init_rhel860, -diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c -index cc78a315e3..13bfa4253e 100644 ---- a/hw/s390x/s390-virtio-ccw.c -+++ b/hw/s390x/s390-virtio-ccw.c -@@ -1121,6 +1121,7 @@ static void ccw_machine_rhel860_instance_options(MachineState *machine) - static void ccw_machine_rhel860_class_options(MachineClass *mc) - { - ccw_machine_rhel900_class_options(mc); -+ compat_props_add(mc->compat_props, hw_compat_rhel_8_6, hw_compat_rhel_8_6_len); - - /* 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 21d8d5528e..b9c12c4bf2 100644 ---- a/include/hw/boards.h -+++ b/include/hw/boards.h -@@ -443,6 +443,9 @@ 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; - --- -2.31.1 - diff --git a/SOURCES/kvm-RHEL-mark-old-machine-types-as-deprecated.patch b/SOURCES/kvm-RHEL-mark-old-machine-types-as-deprecated.patch deleted file mode 100644 index b6d4003..0000000 --- a/SOURCES/kvm-RHEL-mark-old-machine-types-as-deprecated.patch +++ /dev/null @@ -1,110 +0,0 @@ -From dcc64971bf25e5c2303d551fb2fef448a5e8f4fd Mon Sep 17 00:00:00 2001 -From: Cornelia Huck -Date: Thu, 3 Mar 2022 10:57:37 +0100 -Subject: [PATCH 1/5] RHEL: mark old machine types as deprecated -MIME-Version: 1.0 -Content-Type: text/plain; charset=UTF-8 -Content-Transfer-Encoding: 8bit - -RH-Author: Cornelia Huck -RH-MergeRequest: 119: RHEL: mark old machine types as deprecated -RH-Commit: [1/1] 5d7531d23fac5dd67c3cc202f538b25f26393600 (cohuck/qemu-kvm) -RH-Bugzilla: 2052050 -RH-Acked-by: Thomas Huth -RH-Acked-by: Dr. David Alan Gilbert -RH-Acked-by: Daniel P. Berrangé - -We want to make it obvious that we consider machine types for older -RHEL major releases to be deprecated; we only carry them for -compatibility purposes. - -Let's mark all rhel-7.x and rhel-8.x machine type as deprecated via -QEMU's existing deprecation mechanism; those machine types will -continue to work as expected, but commands like 'virsh capabilities', -'virsh dominfo', or the libvirt log will tag the machine as -deprecated. - -Signed-off-by: Cornelia Huck ---- - hw/core/machine.c | 6 ++++++ - hw/i386/pc_piix.c | 4 ++++ - hw/i386/pc_q35.c | 4 ++++ - hw/s390x/s390-virtio-ccw.c | 3 +++ - include/hw/boards.h | 2 ++ - 5 files changed, 19 insertions(+) - -diff --git a/hw/core/machine.c b/hw/core/machine.c -index 669d3d8b91..5fae55d6cd 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 - */ -diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c -index fccb7f5fc9..cf68d7498c 100644 ---- a/hw/i386/pc_piix.c -+++ b/hw/i386/pc_piix.c -@@ -989,6 +989,10 @@ static void pc_machine_rhel760_options(MachineClass *m) - m->desc = "RHEL 7.6.0 PC (i440FX + PIIX, 1996)"; - m->async_pf_vmexit_disable = true; - m->smbus_no_migration_support = true; -+ -+ /* All RHEL machines for prior major releases are deprecated */ -+ m->deprecation_reason = rhel_old_machine_deprecation; -+ - pcmc->pvh_enabled = false; - pcmc->default_cpu_version = CPU_VERSION_LEGACY; - pcmc->kvmclock_create_always = false; -diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c -index bf9ad32f0e..c8e06da084 100644 ---- a/hw/i386/pc_q35.c -+++ b/hw/i386/pc_q35.c -@@ -674,6 +674,10 @@ static void pc_q35_machine_rhel860_options(MachineClass *m) - pc_q35_machine_rhel900_options(m); - m->desc = "RHEL-8.6.0 PC (Q35 + ICH9, 2009)"; - m->alias = NULL; -+ -+ /* All RHEL machines for prior major releases are deprecated */ -+ m->deprecation_reason = rhel_old_machine_deprecation; -+ - pcmc->smbios_stream_product = "RHEL-AV"; - pcmc->smbios_stream_version = "8.6.0"; - } -diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c -index 9da6e9b1d4..cc78a315e3 100644 ---- a/hw/s390x/s390-virtio-ccw.c -+++ b/hw/s390x/s390-virtio-ccw.c -@@ -1121,6 +1121,9 @@ static void ccw_machine_rhel860_instance_options(MachineState *machine) - static void ccw_machine_rhel860_class_options(MachineClass *mc) - { - ccw_machine_rhel900_class_options(mc); -+ -+ /* All RHEL machines for prior major releases are deprecated */ -+ mc->deprecation_reason = rhel_old_machine_deprecation; - } - DEFINE_CCW_MACHINE(rhel860, "rhel8.6.0", false); - -diff --git a/include/hw/boards.h b/include/hw/boards.h -index 3c3d2ad450..21d8d5528e 100644 ---- a/include/hw/boards.h -+++ b/include/hw/boards.h -@@ -464,4 +464,6 @@ 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; -+ - #endif --- -2.31.1 - diff --git a/SOURCES/kvm-RHEL-only-AArch64-Drop-unsupported-CPU-types.patch b/SOURCES/kvm-RHEL-only-AArch64-Drop-unsupported-CPU-types.patch new file mode 100644 index 0000000..8a0aeb0 --- /dev/null +++ b/SOURCES/kvm-RHEL-only-AArch64-Drop-unsupported-CPU-types.patch @@ -0,0 +1,237 @@ +From 055edf068196622a3e1868c9e4c991d410272a6d Mon Sep 17 00:00:00 2001 +From: Andrew Jones +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 +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 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Cornelia Huck + +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 +--- + 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 + diff --git a/SOURCES/kvm-RHEL-only-tests-avocado-Switch-aarch64-tests-from-a5.patch b/SOURCES/kvm-RHEL-only-tests-avocado-Switch-aarch64-tests-from-a5.patch new file mode 100644 index 0000000..a1cc4c7 --- /dev/null +++ b/SOURCES/kvm-RHEL-only-tests-avocado-Switch-aarch64-tests-from-a5.patch @@ -0,0 +1,95 @@ +From d710394f68eb0b6116dd8ac76f619c192e0d5972 Mon Sep 17 00:00:00 2001 +From: Andrew Jones +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 +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 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Cornelia Huck + +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 +--- + 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 + diff --git a/SOURCES/kvm-Revert-globally-limit-the-maximum-number-of-CPUs.patch b/SOURCES/kvm-Revert-globally-limit-the-maximum-number-of-CPUs.patch new file mode 100644 index 0000000..7740d0b --- /dev/null +++ b/SOURCES/kvm-Revert-globally-limit-the-maximum-number-of-CPUs.patch @@ -0,0 +1,58 @@ +From 5ab8613582fd56b847fe75750acb5b7255900b35 Mon Sep 17 00:00:00 2001 +From: Vitaly Kuznetsov +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 +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 +RH-Acked-by: Cornelia Huck +RH-Acked-by: Thomas Huth + +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 +--- + 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 + diff --git a/SOURCES/kvm-Revert-migration-Simplify-unqueue_page.patch b/SOURCES/kvm-Revert-migration-Simplify-unqueue_page.patch new file mode 100644 index 0000000..f5c97f6 --- /dev/null +++ b/SOURCES/kvm-Revert-migration-Simplify-unqueue_page.patch @@ -0,0 +1,134 @@ +From 5ea59b17866add54e5ae8c76d3cb472c67e1fa91 Mon Sep 17 00:00:00 2001 +From: Thomas Huth +Date: Tue, 2 Aug 2022 08:19:49 +0200 +Subject: [PATCH 32/32] Revert "migration: Simplify unqueue_page()" + +RH-Author: Thomas Huth +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 +RH-Acked-by: Cornelia Huck +RH-Acked-by: David Hildenbrand +RH-Acked-by: Peter Xu + +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 +Message-Id: <20220802061949.331576-1-thuth@redhat.com> +Reviewed-by: Dr. David Alan Gilbert +Signed-off-by: Dr. David Alan Gilbert +(cherry picked from commit 777f53c75983dd10756f5dbfc8af50fe11da81c1) +Conflicts: + migration/trace-events + (trivial contextual conflict) +Signed-off-by: Thomas Huth +--- + 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 + diff --git a/SOURCES/kvm-Revert-ui-clipboard-Don-t-use-g_autoptr-just-to-free.patch b/SOURCES/kvm-Revert-ui-clipboard-Don-t-use-g_autoptr-just-to-free.patch deleted file mode 100644 index d9d5145..0000000 --- a/SOURCES/kvm-Revert-ui-clipboard-Don-t-use-g_autoptr-just-to-free.patch +++ /dev/null @@ -1,45 +0,0 @@ -From 213d2c6d3138f3570bca36edaacfd1ee86b18967 Mon Sep 17 00:00:00 2001 -From: Gerd Hoffmann -Date: Fri, 4 Feb 2022 06:45:51 +0100 -Subject: [PATCH 1/6] Revert "ui/clipboard: Don't use g_autoptr just to free a - variable" -MIME-Version: 1.0 -Content-Type: text/plain; charset=UTF-8 -Content-Transfer-Encoding: 8bit - -RH-Author: Gerd Hoffmann -RH-MergeRequest: 75: fix vnc cut+paste crash -RH-Commit: [1/4] 0937d15054ad6e902bc22d1872231504f442ddcc (kraxel/centos-qemu-kvm) -RH-Bugzilla: 2042820 -RH-Acked-by: Marc-André Lureau -RH-Acked-by: Daniel P. Berrangé -RH-Acked-by: Miroslav Rezanina - -This reverts commit 8df1ea81ee6c674522967d056daa8d3748fa3883. ---- - ui/clipboard.c | 3 +-- - 1 file changed, 1 insertion(+), 2 deletions(-) - -diff --git a/ui/clipboard.c b/ui/clipboard.c -index d53576b0f6..d7b008d62a 100644 ---- a/ui/clipboard.c -+++ b/ui/clipboard.c -@@ -44,14 +44,13 @@ void qemu_clipboard_peer_release(QemuClipboardPeer *peer, - - void qemu_clipboard_update(QemuClipboardInfo *info) - { -- QemuClipboardInfo *old = NULL; -+ g_autoptr(QemuClipboardInfo) old = NULL; - assert(info->selection < QEMU_CLIPBOARD_SELECTION__COUNT); - - notifier_list_notify(&clipboard_notifiers, info); - - old = cbinfo[info->selection]; - cbinfo[info->selection] = qemu_clipboard_info_ref(info); -- g_free(old); - } - - QemuClipboardInfo *qemu_clipboard_info(QemuClipboardSelection selection) --- -2.27.0 - diff --git a/SOURCES/kvm-Revert-virtio-scsi-Reject-scsi-cd-if-data-plane-enab.patch b/SOURCES/kvm-Revert-virtio-scsi-Reject-scsi-cd-if-data-plane-enab.patch new file mode 100644 index 0000000..e8eb35d --- /dev/null +++ b/SOURCES/kvm-Revert-virtio-scsi-Reject-scsi-cd-if-data-plane-enab.patch @@ -0,0 +1,51 @@ +From 733acef2caea0758edd74fb634b095ce09bf5914 Mon Sep 17 00:00:00 2001 +From: Emanuele Giuseppe Esposito +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 +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 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Stefan Hajnoczi + +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 +--- + 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 + diff --git a/SOURCES/kvm-acpi-fix-OEM-ID-OEM-Table-ID-padding.patch b/SOURCES/kvm-acpi-fix-OEM-ID-OEM-Table-ID-padding.patch deleted file mode 100644 index 1e620ff..0000000 --- a/SOURCES/kvm-acpi-fix-OEM-ID-OEM-Table-ID-padding.patch +++ /dev/null @@ -1,70 +0,0 @@ -From 473b05bbdad50dc3877ab6da4ac52b5a4fc7d5e1 Mon Sep 17 00:00:00 2001 -From: Igor Mammedov -Date: Wed, 12 Jan 2022 08:03:31 -0500 -Subject: [PATCH 11/14] acpi: fix OEM ID/OEM Table ID padding - -RH-Author: Igor Mammedov -RH-MergeRequest: 130: acpi: fix QEMU crash when started with SLIC table -RH-Commit: [7/10] 276af1aa7650e79f146c75ef4ec19f792e7e163c -RH-Bugzilla: 2043531 -RH-Acked-by: Gerd Hoffmann -RH-Acked-by: Miroslav Rezanina -RH-Acked-by: MST - -Commit [2] broke original '\0' padding of OEM ID and OEM Table ID -fields in headers of ACPI tables. While it doesn't have impact on -default values since QEMU uses 6 and 8 characters long values -respectively, it broke usecase where IDs are provided on QEMU CLI. -It shouldn't affect guest (but may cause licensing verification -issues in guest OS). -One of the broken usecases is user supplied SLIC table with IDs -shorter than max possible length, where [2] mangles IDs with extra -spaces in RSDT and FADT tables whereas guest OS expects those to -mirror the respective values of the used SLIC table. - -Fix it by replacing whitespace padding with '\0' padding in -accordance with [1] and expectations of guest OS - -1) ACPI spec, v2.0b - 17.2 AML Grammar Definition - ... - //OEM ID of up to 6 characters. If the OEM ID is - //shorter than 6 characters, it can be terminated - //with a NULL character. - -2) -Fixes: 602b458201 ("acpi: Permit OEM ID and OEM table ID fields to be changed") -Resolves: https://gitlab.com/qemu-project/qemu/-/issues/707 -Reported-by: Dmitry V. Orekhov -Signed-off-by: Igor Mammedov -Cc: qemu-stable@nongnu.org -Message-Id: <20220112130332.1648664-4-imammedo@redhat.com> -Reviewed-by: Michael S. Tsirkin -Signed-off-by: Michael S. Tsirkin -Reviewed-by: Ani Sinha -Tested-by: Dmitry V. Orekhov dima.orekhov@gmail.com -(cherry picked from commit 748c030f360a940fe0c9382c8ca1649096c3a80d) -Signed-off-by: Igor Mammedov ---- - hw/acpi/aml-build.c | 4 ++-- - 1 file changed, 2 insertions(+), 2 deletions(-) - -diff --git a/hw/acpi/aml-build.c b/hw/acpi/aml-build.c -index b3b3310df3..65148d5b9d 100644 ---- a/hw/acpi/aml-build.c -+++ b/hw/acpi/aml-build.c -@@ -1724,9 +1724,9 @@ void acpi_table_begin(AcpiTable *desc, GArray *array) - build_append_int_noprefix(array, 0, 4); /* Length */ - build_append_int_noprefix(array, desc->rev, 1); /* Revision */ - build_append_int_noprefix(array, 0, 1); /* Checksum */ -- build_append_padded_str(array, desc->oem_id, 6, ' '); /* OEMID */ -+ build_append_padded_str(array, desc->oem_id, 6, '\0'); /* OEMID */ - /* OEM Table ID */ -- build_append_padded_str(array, desc->oem_table_id, 8, ' '); -+ build_append_padded_str(array, desc->oem_table_id, 8, '\0'); - build_append_int_noprefix(array, 1, 4); /* OEM Revision */ - g_array_append_vals(array, ACPI_BUILD_APPNAME8, 4); /* Creator ID */ - build_append_int_noprefix(array, 1, 4); /* Creator Revision */ --- -2.31.1 - diff --git a/SOURCES/kvm-acpi-fix-QEMU-crash-when-started-with-SLIC-table.patch b/SOURCES/kvm-acpi-fix-QEMU-crash-when-started-with-SLIC-table.patch deleted file mode 100644 index 763a621..0000000 --- a/SOURCES/kvm-acpi-fix-QEMU-crash-when-started-with-SLIC-table.patch +++ /dev/null @@ -1,100 +0,0 @@ -From 636a09dbe361517ac2b8d810166676b5006a6ca2 Mon Sep 17 00:00:00 2001 -From: Igor Mammedov -Date: Mon, 27 Dec 2021 14:31:17 -0500 -Subject: [PATCH 05/14] acpi: fix QEMU crash when started with SLIC table -MIME-Version: 1.0 -Content-Type: text/plain; charset=UTF-8 -Content-Transfer-Encoding: 8bit - -RH-Author: Igor Mammedov -RH-MergeRequest: 130: acpi: fix QEMU crash when started with SLIC table -RH-Commit: [1/10] 67c1d1d2358d0ba746f260dfc3c1cfc165357fd1 -RH-Bugzilla: 2043531 -RH-Acked-by: Gerd Hoffmann -RH-Acked-by: Miroslav Rezanina -RH-Acked-by: MST - -if QEMU is started with used provided SLIC table blob, - - -acpitable sig=SLIC,oem_id='CRASH ',oem_table_id="ME",oem_rev=00002210,asl_compiler_id="",asl_compiler_rev=00000000,data=/dev/null -it will assert with: - - hw/acpi/aml-build.c:61:build_append_padded_str: assertion failed: (len <= maxlen) - -and following backtrace: - - ... - build_append_padded_str (array=0x555556afe320, str=0x555556afdb2e "CRASH ME", maxlen=0x6, pad=0x20) at hw/acpi/aml-build.c:61 - acpi_table_begin (desc=0x7fffffffd1b0, array=0x555556afe320) at hw/acpi/aml-build.c:1727 - build_fadt (tbl=0x555556afe320, linker=0x555557ca3830, f=0x7fffffffd318, oem_id=0x555556afdb2e "CRASH ME", oem_table_id=0x555556afdb34 "ME") at hw/acpi/aml-build.c:2064 - ... - -which happens due to acpi_table_begin() expecting NULL terminated -oem_id and oem_table_id strings, which is normally the case, but -in case of user provided SLIC table, oem_id points to table's blob -directly and as result oem_id became longer than expected. - -Fix issue by handling oem_id consistently and make acpi_get_slic_oem() -return NULL terminated strings. - -PS: -After [1] refactoring, oem_id semantics became inconsistent, where -NULL terminated string was coming from machine and old way pointer -into byte array coming from -acpitable option. That used to work -since build_header() wasn't expecting NULL terminated string and -blindly copied the 1st 6 bytes only. - -However commit [2] broke that by replacing build_header() with -acpi_table_begin(), which was expecting NULL terminated string -and was checking oem_id size. - -1) 602b45820 ("acpi: Permit OEM ID and OEM table ID fields to be changed") -2) -Fixes: 4b56e1e4eb08 ("acpi: build_fadt: use acpi_table_begin()/acpi_table_end() instead of build_header()") -Resolves: https://gitlab.com/qemu-project/qemu/-/issues/786 -Signed-off-by: Igor Mammedov -Message-Id: <20211227193120.1084176-2-imammedo@redhat.com> -Reviewed-by: Philippe Mathieu-Daudé -Tested-by: Denis Lisov -Tested-by: Alexander Tsoy -Cc: qemu-stable@nongnu.org -Reviewed-by: Michael S. Tsirkin -Signed-off-by: Michael S. Tsirkin -(cherry picked from commit 8cdb99af45365727ac17f45239a9b8c1d5155c6d) -Signed-off-by: Igor Mammedov ---- - hw/acpi/core.c | 4 ++-- - hw/i386/acpi-build.c | 2 ++ - 2 files changed, 4 insertions(+), 2 deletions(-) - -diff --git a/hw/acpi/core.c b/hw/acpi/core.c -index 1e004d0078..3e811bf03c 100644 ---- a/hw/acpi/core.c -+++ b/hw/acpi/core.c -@@ -345,8 +345,8 @@ int acpi_get_slic_oem(AcpiSlicOem *oem) - struct acpi_table_header *hdr = (void *)(u - sizeof(hdr->_length)); - - if (memcmp(hdr->sig, "SLIC", 4) == 0) { -- oem->id = hdr->oem_id; -- oem->table_id = hdr->oem_table_id; -+ oem->id = g_strndup(hdr->oem_id, 6); -+ oem->table_id = g_strndup(hdr->oem_table_id, 8); - return 0; - } - } -diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c -index 8383b83ee3..0234fe7588 100644 ---- a/hw/i386/acpi-build.c -+++ b/hw/i386/acpi-build.c -@@ -2723,6 +2723,8 @@ void acpi_build(AcpiBuildTables *tables, MachineState *machine) - - /* Cleanup memory that's no longer used. */ - g_array_free(table_offsets, true); -+ g_free(slic_oem.id); -+ g_free(slic_oem.table_id); - } - - static void acpi_ram_update(MemoryRegion *mr, GArray *data) --- -2.31.1 - diff --git a/SOURCES/kvm-acpi-pcihp-pcie-set-power-on-cap-on-parent-slot.patch b/SOURCES/kvm-acpi-pcihp-pcie-set-power-on-cap-on-parent-slot.patch deleted file mode 100644 index 02bcda3..0000000 --- a/SOURCES/kvm-acpi-pcihp-pcie-set-power-on-cap-on-parent-slot.patch +++ /dev/null @@ -1,130 +0,0 @@ -From a3a4fd1733e71d029e38136366e73ace8e78298b Mon Sep 17 00:00:00 2001 -From: Igor Mammedov -Date: Tue, 1 Mar 2022 10:11:59 -0500 -Subject: [PATCH 02/14] acpi: pcihp: pcie: set power on cap on parent slot - -RH-Author: Igor Mammedov -RH-MergeRequest: 124: RHEL-9.0 Fix broken PCIe device after migration -RH-Commit: [2/2] 135602421e5fed803f7d71121380306633d490d8 -RH-Bugzilla: 2053584 -RH-Acked-by: Vitaly Kuznetsov -RH-Acked-by: MST -RH-Acked-by: Gerd Hoffmann - -on creation a PCIDevice has power turned on at the end of pci_qdev_realize() -however later on if PCIe slot isn't populated with any children -it's power is turned off. It's fine if native hotplug is used -as plug callback will power slot on among other things. -However when ACPI hotplug is enabled it replaces native PCIe plug -callbacks with ACPI specific ones (acpi_pcihp_device_*plug_cb) and -as result slot stays powered off. It works fine as ACPI hotplug -on guest side takes care of enumerating/initializing hotplugged -device. But when later guest is migrated, call chain introduced by] -commit d5daff7d312 (pcie: implement slot power control for pcie root ports) - - pcie_cap_slot_post_load() - -> pcie_cap_update_power() - -> pcie_set_power_device() - -> pci_set_power() - -> pci_update_mappings() - -will disable earlier initialized BARs for the hotplugged device -in powered off slot due to commit 23786d13441 (pci: implement power state) -which disables BARs if power is off. - -Fix it by setting PCI_EXP_SLTCTL_PCC to PCI_EXP_SLTCTL_PWR_ON -on slot (root port/downstream port) at the time a device -hotplugged into it. As result PCI_EXP_SLTCTL_PWR_ON is migrated -to target and above call chain keeps device plugged into it -powered on. - -Fixes: d5daff7d312 ("pcie: implement slot power control for pcie root ports") -Fixes: 23786d13441 ("pci: implement power state") -Fixes: https://bugzilla.redhat.com/show_bug.cgi?id=2053584 -Suggested-by: "Michael S. Tsirkin" -Signed-off-by: Igor Mammedov -Message-Id: <20220301151200.3507298-3-imammedo@redhat.com> -Reviewed-by: Michael S. Tsirkin -Signed-off-by: Michael S. Tsirkin -(cherry picked from commit 6b0969f1ec825984cd74619f0730be421b0c46fb) -Signed-off-by: Igor Mammedov ---- - hw/acpi/pcihp.c | 12 +++++++++++- - hw/pci/pcie.c | 11 +++++++++++ - include/hw/pci/pcie.h | 1 + - 3 files changed, 23 insertions(+), 1 deletion(-) - -diff --git a/hw/acpi/pcihp.c b/hw/acpi/pcihp.c -index 30405b5113..3d5610e02d 100644 ---- a/hw/acpi/pcihp.c -+++ b/hw/acpi/pcihp.c -@@ -32,6 +32,7 @@ - #include "hw/pci/pci_bridge.h" - #include "hw/pci/pci_host.h" - #include "hw/pci/pcie_port.h" -+#include "hw/pci-bridge/xio3130_downstream.h" - #include "hw/i386/acpi-build.h" - #include "hw/acpi/acpi.h" - #include "hw/pci/pci_bus.h" -@@ -341,6 +342,8 @@ void acpi_pcihp_device_plug_cb(HotplugHandler *hotplug_dev, AcpiPciHpState *s, - { - PCIDevice *pdev = PCI_DEVICE(dev); - int slot = PCI_SLOT(pdev->devfn); -+ PCIDevice *bridge; -+ PCIBus *bus; - int bsel; - - /* Don't send event when device is enabled during qemu machine creation: -@@ -370,7 +373,14 @@ void acpi_pcihp_device_plug_cb(HotplugHandler *hotplug_dev, AcpiPciHpState *s, - return; - } - -- bsel = acpi_pcihp_get_bsel(pci_get_bus(pdev)); -+ bus = pci_get_bus(pdev); -+ bridge = pci_bridge_get_device(bus); -+ if (object_dynamic_cast(OBJECT(bridge), TYPE_PCIE_ROOT_PORT) || -+ object_dynamic_cast(OBJECT(bridge), TYPE_XIO3130_DOWNSTREAM)) { -+ pcie_cap_slot_enable_power(bridge); -+ } -+ -+ bsel = acpi_pcihp_get_bsel(bus); - g_assert(bsel >= 0); - s->acpi_pcihp_pci_status[bsel].up |= (1U << slot); - acpi_send_event(DEVICE(hotplug_dev), ACPI_PCI_HOTPLUG_STATUS); -diff --git a/hw/pci/pcie.c b/hw/pci/pcie.c -index d7d73a31e4..996f0e24fe 100644 ---- a/hw/pci/pcie.c -+++ b/hw/pci/pcie.c -@@ -366,6 +366,17 @@ static void hotplug_event_clear(PCIDevice *dev) - } - } - -+void pcie_cap_slot_enable_power(PCIDevice *dev) -+{ -+ uint8_t *exp_cap = dev->config + dev->exp.exp_cap; -+ uint32_t sltcap = pci_get_long(exp_cap + PCI_EXP_SLTCAP); -+ -+ if (sltcap & PCI_EXP_SLTCAP_PCP) { -+ pci_set_word_by_mask(exp_cap + PCI_EXP_SLTCTL, -+ PCI_EXP_SLTCTL_PCC, PCI_EXP_SLTCTL_PWR_ON); -+ } -+} -+ - static void pcie_set_power_device(PCIBus *bus, PCIDevice *dev, void *opaque) - { - bool *power = opaque; -diff --git a/include/hw/pci/pcie.h b/include/hw/pci/pcie.h -index 6063bee0ec..c27368d077 100644 ---- a/include/hw/pci/pcie.h -+++ b/include/hw/pci/pcie.h -@@ -112,6 +112,7 @@ void pcie_cap_slot_write_config(PCIDevice *dev, - uint32_t addr, uint32_t val, int len); - int pcie_cap_slot_post_load(void *opaque, int version_id); - void pcie_cap_slot_push_attention_button(PCIDevice *dev); -+void pcie_cap_slot_enable_power(PCIDevice *dev); - - void pcie_cap_root_init(PCIDevice *dev); - void pcie_cap_root_reset(PCIDevice *dev); --- -2.31.1 - diff --git a/SOURCES/kvm-block-Lock-AioContext-for-drain_end-in-blockdev-reop.patch b/SOURCES/kvm-block-Lock-AioContext-for-drain_end-in-blockdev-reop.patch deleted file mode 100644 index 6fc7f38..0000000 --- a/SOURCES/kvm-block-Lock-AioContext-for-drain_end-in-blockdev-reop.patch +++ /dev/null @@ -1,63 +0,0 @@ -From 7b973b9cb7b890eaf9a31c99f5c272b513322ac1 Mon Sep 17 00:00:00 2001 -From: Kevin Wolf -Date: Thu, 3 Feb 2022 15:05:33 +0100 -Subject: [PATCH 1/8] block: Lock AioContext for drain_end in blockdev-reopen - -RH-Author: Kevin Wolf -RH-MergeRequest: 73: block: Lock AioContext for drain_end in blockdev-reopen -RH-Commit: [1/2] db25e999152b0e4f09decade1ac76b9f56cd9706 (kmwolf/centos-qemu-kvm) -RH-Bugzilla: 2046659 -RH-Acked-by: Sergio Lopez -RH-Acked-by: Stefan Hajnoczi -RH-Acked-by: Hanna Reitz - -bdrv_subtree_drained_end() requires the caller to hold the AioContext -lock for the drained node. Not doing this for nodes outside of the main -AioContext leads to crashes when AIO_WAIT_WHILE() needs to wait and -tries to temporarily release the lock. - -Fixes: 3908b7a8994fa5ef7a89aa58cd5a02fc58141592 -Resolves: https://bugzilla.redhat.com/show_bug.cgi?id=2046659 -Reported-by: Qing Wang -Signed-off-by: Kevin Wolf -Message-Id: <20220203140534.36522-2-kwolf@redhat.com> -Reviewed-by: Hanna Reitz -Signed-off-by: Kevin Wolf -(cherry picked from commit aba8205be0707b9d108e32254e186ba88107a869) -Signed-off-by: Kevin Wolf ---- - blockdev.c | 11 ++++++++++- - 1 file changed, 10 insertions(+), 1 deletion(-) - -diff --git a/blockdev.c b/blockdev.c -index b35072644e..565f6a81fd 100644 ---- a/blockdev.c -+++ b/blockdev.c -@@ -3562,6 +3562,7 @@ 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) { -@@ -3611,7 +3612,15 @@ void qmp_blockdev_reopen(BlockdevOptionsList *reopen_list, Error **errp) - - fail: - bdrv_reopen_queue_free(queue); -- g_slist_free_full(drained, (GDestroyNotify) bdrv_subtree_drained_end); -+ 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) --- -2.27.0 - diff --git a/SOURCES/kvm-block-backend-prevent-dangling-BDS-pointers-across-a.patch b/SOURCES/kvm-block-backend-prevent-dangling-BDS-pointers-across-a.patch deleted file mode 100644 index 8dbf30f..0000000 --- a/SOURCES/kvm-block-backend-prevent-dangling-BDS-pointers-across-a.patch +++ /dev/null @@ -1,129 +0,0 @@ -From 87f3b10dc600ac12272ee6cdc67571910ea722f6 Mon Sep 17 00:00:00 2001 -From: Stefan Hajnoczi -Date: Tue, 11 Jan 2022 15:36:12 +0000 -Subject: [PATCH 10/12] block-backend: prevent dangling BDS pointers across - aio_poll() - -RH-Author: Hanna Reitz -RH-MergeRequest: 71: block-backend: prevent dangling BDS pointers across aio_poll() -RH-Commit: [1/2] 1b4cab39bf8c933ab910293a29bfceaa9e821068 (hreitz/qemu-kvm-c-9-s) -RH-Bugzilla: 2040123 -RH-Acked-by: Kevin Wolf -RH-Acked-by: Stefan Hajnoczi -RH-Acked-by: Emanuele Giuseppe Esposito - -The BlockBackend root child can change when aio_poll() is invoked. This -happens when a temporary filter node is removed upon blockjob -completion, for example. - -Functions in block/block-backend.c must be aware of this when using a -blk_bs() pointer across aio_poll() because the BlockDriverState refcnt -may reach 0, resulting in a stale pointer. - -One example is scsi_device_purge_requests(), which calls blk_drain() to -wait for in-flight requests to cancel. If the backup blockjob is active, -then the BlockBackend root child is a temporary filter BDS owned by the -blockjob. The blockjob can complete during bdrv_drained_begin() and the -last reference to the BDS is released when the temporary filter node is -removed. This results in a use-after-free when blk_drain() calls -bdrv_drained_end(bs) on the dangling pointer. - -Explicitly hold a reference to bs across block APIs that invoke -aio_poll(). - -Buglink: https://bugzilla.redhat.com/show_bug.cgi?id=2021778 -Buglink: https://bugzilla.redhat.com/show_bug.cgi?id=2036178 -Signed-off-by: Stefan Hajnoczi -Message-Id: <20220111153613.25453-2-stefanha@redhat.com> -Signed-off-by: Kevin Wolf -(cherry picked from commit 1e3552dbd28359d35967b7c28dc86cde1bc29205) -Signed-off-by: Hanna Reitz ---- - block/block-backend.c | 19 +++++++++++++++++-- - 1 file changed, 17 insertions(+), 2 deletions(-) - -diff --git a/block/block-backend.c b/block/block-backend.c -index 12ef80ea17..23e727199b 100644 ---- a/block/block-backend.c -+++ b/block/block-backend.c -@@ -822,16 +822,22 @@ BlockBackend *blk_by_public(BlockBackendPublic *public) - void blk_remove_bs(BlockBackend *blk) - { - ThrottleGroupMember *tgm = &blk->public.throttle_group_member; -- BlockDriverState *bs; - BdrvChild *root; - - notifier_list_notify(&blk->remove_bs_notifiers, blk); - if (tgm->throttle_state) { -- bs = blk_bs(blk); -+ BlockDriverState *bs = blk_bs(blk); -+ -+ /* -+ * Take a ref in case blk_bs() changes across bdrv_drained_begin(), for -+ * example, if a temporary filter node is removed by a blockjob. -+ */ -+ bdrv_ref(bs); - bdrv_drained_begin(bs); - throttle_group_detach_aio_context(tgm); - throttle_group_attach_aio_context(tgm, qemu_get_aio_context()); - bdrv_drained_end(bs); -+ bdrv_unref(bs); - } - - blk_update_root_state(blk); -@@ -1705,6 +1711,7 @@ void blk_drain(BlockBackend *blk) - BlockDriverState *bs = blk_bs(blk); - - if (bs) { -+ bdrv_ref(bs); - bdrv_drained_begin(bs); - } - -@@ -1714,6 +1721,7 @@ void blk_drain(BlockBackend *blk) - - if (bs) { - bdrv_drained_end(bs); -+ bdrv_unref(bs); - } - } - -@@ -2044,10 +2052,13 @@ static int blk_do_set_aio_context(BlockBackend *blk, AioContext *new_context, - int ret; - - if (bs) { -+ bdrv_ref(bs); -+ - if (update_root_node) { - ret = bdrv_child_try_set_aio_context(bs, new_context, blk->root, - errp); - if (ret < 0) { -+ bdrv_unref(bs); - return ret; - } - } -@@ -2057,6 +2068,8 @@ static int blk_do_set_aio_context(BlockBackend *blk, AioContext *new_context, - throttle_group_attach_aio_context(tgm, new_context); - bdrv_drained_end(bs); - } -+ -+ bdrv_unref(bs); - } - - blk->ctx = new_context; -@@ -2326,11 +2339,13 @@ void blk_io_limits_disable(BlockBackend *blk) - ThrottleGroupMember *tgm = &blk->public.throttle_group_member; - assert(tgm->throttle_state); - if (bs) { -+ bdrv_ref(bs); - bdrv_drained_begin(bs); - } - throttle_group_unregister_tgm(tgm); - if (bs) { - bdrv_drained_end(bs); -+ bdrv_unref(bs); - } - } - --- -2.27.0 - diff --git a/SOURCES/kvm-block-io-Update-BSC-only-if-want_zero-is-true.patch b/SOURCES/kvm-block-io-Update-BSC-only-if-want_zero-is-true.patch deleted file mode 100644 index 5fff268..0000000 --- a/SOURCES/kvm-block-io-Update-BSC-only-if-want_zero-is-true.patch +++ /dev/null @@ -1,56 +0,0 @@ -From a6b472de71f6ebbe44025e1348c90e6f1f2b2326 Mon Sep 17 00:00:00 2001 -From: Hanna Reitz -Date: Tue, 18 Jan 2022 17:59:59 +0100 -Subject: [PATCH 06/12] block/io: Update BSC only if want_zero is true - -RH-Author: Hanna Reitz -RH-MergeRequest: 69: block/io: Update BSC only if want_zero is true -RH-Commit: [1/2] ad19ff86c3420cafe5a9e785ee210e482fbc8cd7 (hreitz/qemu-kvm-c-9-s) -RH-Bugzilla: 2041461 -RH-Acked-by: Eric Blake -RH-Acked-by: Stefan Hajnoczi -RH-Acked-by: Kevin Wolf - -We update the block-status cache whenever we get new information from a -bdrv_co_block_status() call to the block driver. However, if we have -passed want_zero=false to that call, it may flag areas containing zeroes -as data, and so we would update the block-status cache with wrong -information. - -Therefore, we should not update the cache with want_zero=false. - -Reported-by: Nir Soffer -Fixes: 0bc329fbb00 ("block: block-status cache for data regions") -Reviewed-by: Nir Soffer -Cc: qemu-stable@nongnu.org -Signed-off-by: Hanna Reitz -Message-Id: <20220118170000.49423-2-hreitz@redhat.com> -Reviewed-by: Eric Blake -Signed-off-by: Eric Blake -(cherry picked from commit 113b727ce788335cf76f65355d670c9bc130fd75) -Signed-off-by: Hanna Reitz ---- - block/io.c | 6 +++++- - 1 file changed, 5 insertions(+), 1 deletion(-) - -diff --git a/block/io.c b/block/io.c -index bb0a254def..4e4cb556c5 100644 ---- a/block/io.c -+++ b/block/io.c -@@ -2497,8 +2497,12 @@ static int coroutine_fn bdrv_co_block_status(BlockDriverState *bs, - * non-protocol nodes, and then it is never used. However, filling - * the cache requires an RCU update, so double check here to avoid - * such an update if possible. -+ * -+ * Check want_zero, because we only want to update the cache when we -+ * have accurate information about what is zero and what is data. - */ -- if (ret == (BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID) && -+ if (want_zero && -+ ret == (BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID) && - QLIST_EMPTY(&bs->children)) - { - /* --- -2.27.0 - diff --git a/SOURCES/kvm-block-nbd-Assert-there-are-no-timers-when-closed.patch b/SOURCES/kvm-block-nbd-Assert-there-are-no-timers-when-closed.patch deleted file mode 100644 index 24c5b8a..0000000 --- a/SOURCES/kvm-block-nbd-Assert-there-are-no-timers-when-closed.patch +++ /dev/null @@ -1,52 +0,0 @@ -From 76b03619435d0b2f0125ee7aa5c94f2b889247de Mon Sep 17 00:00:00 2001 -From: Hanna Reitz -Date: Fri, 4 Feb 2022 12:10:08 +0100 -Subject: [PATCH 4/8] block/nbd: Assert there are no timers when closed - -RH-Author: Hanna Reitz -RH-MergeRequest: 74: block/nbd: Handle AioContext changes -RH-Commit: [2/6] 56903457ca35d9c596aeb6827a48f80e8eabd66a (hreitz/qemu-kvm-c-9-s) -RH-Bugzilla: 2033626 -RH-Acked-by: Miroslav Rezanina -RH-Acked-by: Eric Blake -RH-Acked-by: Stefan Hajnoczi - -Our two timers must not remain armed beyond nbd_clear_bdrvstate(), or -they will access freed data when they fire. - -This patch is separate from the patches that actually fix the issue -(HEAD^^ and HEAD^) so that you can run the associated regression iotest -(281) on a configuration that reproducibly exposes the bug. - -Reviewed-by: Vladimir Sementsov-Ogievskiy -Signed-off-by: Hanna Reitz -Signed-off-by: Vladimir Sementsov-Ogievskiy -(cherry picked from commit 8a39c381e5e407d2fe5500324323f90a8540fa90) - -Conflict: -- block/nbd.c: open_timer was introduced after the 6.2 release (for - nbd's @open-timeout parameter), and has not been backported, so drop - the assertion that it is NULL - -Signed-off-by: Hanna Reitz ---- - block/nbd.c | 3 +++ - 1 file changed, 3 insertions(+) - -diff --git a/block/nbd.c b/block/nbd.c -index b8e5a9b4cc..aab20125d8 100644 ---- a/block/nbd.c -+++ b/block/nbd.c -@@ -108,6 +108,9 @@ static void nbd_clear_bdrvstate(BlockDriverState *bs) - - yank_unregister_instance(BLOCKDEV_YANK_INSTANCE(bs->node_name)); - -+ /* Must not leave timers behind that would access freed data */ -+ assert(!s->reconnect_delay_timer); -+ - object_unref(OBJECT(s->tlscreds)); - qapi_free_SocketAddress(s->saddr); - s->saddr = NULL; --- -2.27.0 - diff --git a/SOURCES/kvm-block-nbd-Delete-reconnect-delay-timer-when-done.patch b/SOURCES/kvm-block-nbd-Delete-reconnect-delay-timer-when-done.patch deleted file mode 100644 index 0cdf622..0000000 --- a/SOURCES/kvm-block-nbd-Delete-reconnect-delay-timer-when-done.patch +++ /dev/null @@ -1,54 +0,0 @@ -From eeb4683ad8c40a03a4e91463ec1d1b651974b744 Mon Sep 17 00:00:00 2001 -From: Hanna Reitz -Date: Fri, 4 Feb 2022 12:10:06 +0100 -Subject: [PATCH 3/8] block/nbd: Delete reconnect delay timer when done - -RH-Author: Hanna Reitz -RH-MergeRequest: 74: block/nbd: Handle AioContext changes -RH-Commit: [1/6] 34f92910b6ffd256d781109a2b39737fc6ab449c (hreitz/qemu-kvm-c-9-s) -RH-Bugzilla: 2033626 -RH-Acked-by: Miroslav Rezanina -RH-Acked-by: Eric Blake -RH-Acked-by: Stefan Hajnoczi - -We start the reconnect delay timer to cancel the reconnection attempt -after a while. Once nbd_co_do_establish_connection() has returned, this -attempt is over, and we no longer need the timer. - -Delete it before returning from nbd_reconnect_attempt(), so that it does -not persist beyond the I/O request that was paused for reconnecting; we -do not want it to fire in a drained section, because all sort of things -can happen in such a section (e.g. the AioContext might be changed, and -we do not want the timer to fire in the wrong context; or the BDS might -even be deleted, and so the timer CB would access already-freed data). - -Reviewed-by: Vladimir Sementsov-Ogievskiy -Signed-off-by: Hanna Reitz -Signed-off-by: Vladimir Sementsov-Ogievskiy -(cherry picked from commit 3ce1fc16bad9c3f8b7b10b451a224d6d76e5c551) -Signed-off-by: Hanna Reitz ---- - block/nbd.c | 7 +++++++ - 1 file changed, 7 insertions(+) - -diff --git a/block/nbd.c b/block/nbd.c -index 5ef462db1b..b8e5a9b4cc 100644 ---- a/block/nbd.c -+++ b/block/nbd.c -@@ -353,6 +353,13 @@ static coroutine_fn void nbd_reconnect_attempt(BDRVNBDState *s) - } - - nbd_co_do_establish_connection(s->bs, NULL); -+ -+ /* -+ * The reconnect attempt is done (maybe successfully, maybe not), so -+ * we no longer need this timer. Delete it so it will not outlive -+ * this I/O request (so draining removes all timers). -+ */ -+ reconnect_delay_timer_del(s); - } - - static coroutine_fn int nbd_receive_replies(BDRVNBDState *s, uint64_t handle) --- -2.27.0 - diff --git a/SOURCES/kvm-block-nbd-Move-s-ioc-on-AioContext-change.patch b/SOURCES/kvm-block-nbd-Move-s-ioc-on-AioContext-change.patch deleted file mode 100644 index 1cb29e9..0000000 --- a/SOURCES/kvm-block-nbd-Move-s-ioc-on-AioContext-change.patch +++ /dev/null @@ -1,107 +0,0 @@ -From 6d9d86cc4e6149d4c0793e8ceb65dab7535a4561 Mon Sep 17 00:00:00 2001 -From: Hanna Reitz -Date: Fri, 4 Feb 2022 12:10:11 +0100 -Subject: [PATCH 7/8] block/nbd: Move s->ioc on AioContext change - -RH-Author: Hanna Reitz -RH-MergeRequest: 74: block/nbd: Handle AioContext changes -RH-Commit: [5/6] b3c1eb21ac70d64fdac6094468a72cfbe50a30a9 (hreitz/qemu-kvm-c-9-s) -RH-Bugzilla: 2033626 -RH-Acked-by: Miroslav Rezanina -RH-Acked-by: Eric Blake -RH-Acked-by: Stefan Hajnoczi - -s->ioc must always be attached to the NBD node's AioContext. If that -context changes, s->ioc must be attached to the new context. - -Buglink: https://bugzilla.redhat.com/show_bug.cgi?id=2033626 -Reviewed-by: Vladimir Sementsov-Ogievskiy -Signed-off-by: Hanna Reitz -Signed-off-by: Vladimir Sementsov-Ogievskiy -(cherry picked from commit e15f3a66c830e3fce99c9d56c493c2f7078a1225) - -Conflict: -- block/nbd.c: open_timer was added after the 6.2 release, so we need - not (and cannot) assert it is NULL here. - -Signed-off-by: Hanna Reitz ---- - block/nbd.c | 41 +++++++++++++++++++++++++++++++++++++++++ - 1 file changed, 41 insertions(+) - -diff --git a/block/nbd.c b/block/nbd.c -index aab20125d8..a3896c7f5f 100644 ---- a/block/nbd.c -+++ b/block/nbd.c -@@ -2003,6 +2003,38 @@ static void nbd_cancel_in_flight(BlockDriverState *bs) - nbd_co_establish_connection_cancel(s->conn); - } - -+static void nbd_attach_aio_context(BlockDriverState *bs, -+ AioContext *new_context) -+{ -+ BDRVNBDState *s = bs->opaque; -+ -+ /* -+ * The reconnect_delay_timer is scheduled in I/O paths when the -+ * connection is lost, to cancel the reconnection attempt after a -+ * given time. Once this attempt is done (successfully or not), -+ * nbd_reconnect_attempt() ensures the timer is deleted before the -+ * respective I/O request is resumed. -+ * Since the AioContext can only be changed when a node is drained, -+ * the reconnect_delay_timer cannot be active here. -+ */ -+ assert(!s->reconnect_delay_timer); -+ -+ if (s->ioc) { -+ qio_channel_attach_aio_context(s->ioc, new_context); -+ } -+} -+ -+static void nbd_detach_aio_context(BlockDriverState *bs) -+{ -+ BDRVNBDState *s = bs->opaque; -+ -+ assert(!s->reconnect_delay_timer); -+ -+ if (s->ioc) { -+ qio_channel_detach_aio_context(s->ioc); -+ } -+} -+ - static BlockDriver bdrv_nbd = { - .format_name = "nbd", - .protocol_name = "nbd", -@@ -2026,6 +2058,9 @@ static BlockDriver bdrv_nbd = { - .bdrv_dirname = nbd_dirname, - .strong_runtime_opts = nbd_strong_runtime_opts, - .bdrv_cancel_in_flight = nbd_cancel_in_flight, -+ -+ .bdrv_attach_aio_context = nbd_attach_aio_context, -+ .bdrv_detach_aio_context = nbd_detach_aio_context, - }; - - static BlockDriver bdrv_nbd_tcp = { -@@ -2051,6 +2086,9 @@ static BlockDriver bdrv_nbd_tcp = { - .bdrv_dirname = nbd_dirname, - .strong_runtime_opts = nbd_strong_runtime_opts, - .bdrv_cancel_in_flight = nbd_cancel_in_flight, -+ -+ .bdrv_attach_aio_context = nbd_attach_aio_context, -+ .bdrv_detach_aio_context = nbd_detach_aio_context, - }; - - static BlockDriver bdrv_nbd_unix = { -@@ -2076,6 +2114,9 @@ static BlockDriver bdrv_nbd_unix = { - .bdrv_dirname = nbd_dirname, - .strong_runtime_opts = nbd_strong_runtime_opts, - .bdrv_cancel_in_flight = nbd_cancel_in_flight, -+ -+ .bdrv_attach_aio_context = nbd_attach_aio_context, -+ .bdrv_detach_aio_context = nbd_detach_aio_context, - }; - - static void bdrv_nbd_init(void) --- -2.27.0 - diff --git a/SOURCES/kvm-block-nvme-fix-infinite-loop-in-nvme_free_req_queue_.patch b/SOURCES/kvm-block-nvme-fix-infinite-loop-in-nvme_free_req_queue_.patch deleted file mode 100644 index bdebdc3..0000000 --- a/SOURCES/kvm-block-nvme-fix-infinite-loop-in-nvme_free_req_queue_.patch +++ /dev/null @@ -1,71 +0,0 @@ -From 6989be9d0aa08470f8b287c243dc4bf027d5fbcf Mon Sep 17 00:00:00 2001 -From: Stefan Hajnoczi -Date: Wed, 8 Dec 2021 15:22:46 +0000 -Subject: [PATCH 1/2] block/nvme: fix infinite loop in nvme_free_req_queue_cb() -MIME-Version: 1.0 -Content-Type: text/plain; charset=UTF-8 -Content-Transfer-Encoding: 8bit - -RH-Author: Stefan Hajnoczi -RH-MergeRequest: 58: block/nvme: fix infinite loop in nvme_free_req_queue_cb() -RH-Commit: [1/1] 544b3f310d791a20c63b51947de0c6cbb60b0d5b (stefanha/centos-stream-qemu-kvm) -RH-Bugzilla: 2024544 -RH-Acked-by: Kevin Wolf -RH-Acked-by: Stefano Garzarella -RH-Acked-by: Hanna Reitz - -When the request free list is exhausted the coroutine waits on -q->free_req_queue for the next free request. Whenever a request is -completed a BH is scheduled to invoke nvme_free_req_queue_cb() and wake -up waiting coroutines. - -1. nvme_get_free_req() waits for a free request: - - while (q->free_req_head == -1) { - ... - trace_nvme_free_req_queue_wait(q->s, q->index); - qemu_co_queue_wait(&q->free_req_queue, &q->lock); - ... - } - -2. nvme_free_req_queue_cb() wakes up the coroutine: - - while (qemu_co_enter_next(&q->free_req_queue, &q->lock)) { - ^--- infinite loop when free_req_head == -1 - } - -nvme_free_req_queue_cb() and the coroutine form an infinite loop when -q->free_req_head == -1. Fix this by checking q->free_req_head in -nvme_free_req_queue_cb(). If the free request list is exhausted, don't -wake waiting coroutines. Eventually an in-flight request will complete -and the BH will be scheduled again, guaranteeing forward progress. - -Signed-off-by: Stefan Hajnoczi -Reviewed-by: Philippe Mathieu-Daudé -Message-id: 20211208152246.244585-1-stefanha@redhat.com -Signed-off-by: Stefan Hajnoczi -(cherry picked from commit cf4fbc3030c974fff726756a7ceef8386cdf500b) -Signed-off-by: Stefan Hajnoczi ---- - block/nvme.c | 5 +++-- - 1 file changed, 3 insertions(+), 2 deletions(-) - -diff --git a/block/nvme.c b/block/nvme.c -index e4f336d79c..fa360b9b3c 100644 ---- a/block/nvme.c -+++ b/block/nvme.c -@@ -206,8 +206,9 @@ static void nvme_free_req_queue_cb(void *opaque) - NVMeQueuePair *q = opaque; - - qemu_mutex_lock(&q->lock); -- while (qemu_co_enter_next(&q->free_req_queue, &q->lock)) { -- /* Retry all pending requests */ -+ while (q->free_req_head != -1 && -+ qemu_co_enter_next(&q->free_req_queue, &q->lock)) { -+ /* Retry waiting requests */ - } - qemu_mutex_unlock(&q->lock); - } --- -2.27.0 - diff --git a/SOURCES/kvm-block-rbd-fix-handling-of-holes-in-.bdrv_co_block_st.patch b/SOURCES/kvm-block-rbd-fix-handling-of-holes-in-.bdrv_co_block_st.patch deleted file mode 100644 index 39aa96c..0000000 --- a/SOURCES/kvm-block-rbd-fix-handling-of-holes-in-.bdrv_co_block_st.patch +++ /dev/null @@ -1,59 +0,0 @@ -From d374d5aa4485a0c62d6b48eec64491cae2fd0873 Mon Sep 17 00:00:00 2001 -From: Peter Lieven -Date: Thu, 13 Jan 2022 15:44:25 +0100 -Subject: [PATCH 4/5] block/rbd: fix handling of holes in .bdrv_co_block_status - -RH-Author: Stefano Garzarella -RH-MergeRequest: 68: block/rbd: fix handling of holes in .bdrv_co_block_status -RH-Commit: [1/2] 8ef178b01885e3c292f7844ccff865b1a8d4faf0 (sgarzarella/qemu-kvm-c-9-s) -RH-Bugzilla: 2034791 -RH-Acked-by: Miroslav Rezanina -RH-Acked-by: Kevin Wolf -RH-Acked-by: Hanna Reitz - -the assumption that we can't hit a hole if we do not diff against a snapshot was wrong. - -We can see a hole in an image if we diff against base if there exists an older snapshot -of the image and we have discarded blocks in the image where the snapshot has data. - -Fix this by simply handling a hole like an unallocated area. There are no callbacks -for unallocated areas so just bail out if we hit a hole. - -Fixes: 0347a8fd4c3faaedf119be04c197804be40a384b -Suggested-by: Ilya Dryomov -Cc: qemu-stable@nongnu.org -Signed-off-by: Peter Lieven -Message-Id: <20220113144426.4036493-2-pl@kamp.de> -Reviewed-by: Ilya Dryomov -Reviewed-by: Stefano Garzarella -Signed-off-by: Kevin Wolf -(cherry picked from commit 9e302f64bb407a9bb097b626da97228c2654cfee) -Signed-off-by: Stefano Garzarella ---- - block/rbd.c | 10 +++++----- - 1 file changed, 5 insertions(+), 5 deletions(-) - -diff --git a/block/rbd.c b/block/rbd.c -index def96292e0..20bb896c4a 100644 ---- a/block/rbd.c -+++ b/block/rbd.c -@@ -1279,11 +1279,11 @@ static int qemu_rbd_diff_iterate_cb(uint64_t offs, size_t len, - RBDDiffIterateReq *req = opaque; - - assert(req->offs + req->bytes <= offs); -- /* -- * we do not diff against a snapshot so we should never receive a callback -- * for a hole. -- */ -- assert(exists); -+ -+ /* treat a hole like an unallocated area and bail out */ -+ if (!exists) { -+ return 0; -+ } - - if (!req->exists && offs > req->offs) { - /* --- -2.27.0 - diff --git a/SOURCES/kvm-block-rbd-workaround-for-ceph-issue-53784.patch b/SOURCES/kvm-block-rbd-workaround-for-ceph-issue-53784.patch deleted file mode 100644 index dd3876e..0000000 --- a/SOURCES/kvm-block-rbd-workaround-for-ceph-issue-53784.patch +++ /dev/null @@ -1,103 +0,0 @@ -From f035b5250529eed8d12e0b93b1b6d6f2c50003f6 Mon Sep 17 00:00:00 2001 -From: Peter Lieven -Date: Thu, 13 Jan 2022 15:44:26 +0100 -Subject: [PATCH 5/5] block/rbd: workaround for ceph issue #53784 - -RH-Author: Stefano Garzarella -RH-MergeRequest: 68: block/rbd: fix handling of holes in .bdrv_co_block_status -RH-Commit: [2/2] 5feaa2e20a77886cc1a84cdf212ade3dcda28289 (sgarzarella/qemu-kvm-c-9-s) -RH-Bugzilla: 2034791 -RH-Acked-by: Miroslav Rezanina -RH-Acked-by: Kevin Wolf -RH-Acked-by: Hanna Reitz - -librbd had a bug until early 2022 that affected all versions of ceph that -supported fast-diff. This bug results in reporting of incorrect offsets -if the offset parameter to rbd_diff_iterate2 is not object aligned. - -This patch works around this bug for pre Quincy versions of librbd. - -Fixes: 0347a8fd4c3faaedf119be04c197804be40a384b -Cc: qemu-stable@nongnu.org -Signed-off-by: Peter Lieven -Message-Id: <20220113144426.4036493-3-pl@kamp.de> -Reviewed-by: Ilya Dryomov -Reviewed-by: Stefano Garzarella -Tested-by: Stefano Garzarella -Signed-off-by: Kevin Wolf -(cherry picked from commit fc176116cdea816ceb8dd969080b2b95f58edbc0) -Signed-off-by: Stefano Garzarella ---- - block/rbd.c | 42 ++++++++++++++++++++++++++++++++++++++++-- - 1 file changed, 40 insertions(+), 2 deletions(-) - -diff --git a/block/rbd.c b/block/rbd.c -index 20bb896c4a..8f183eba2a 100644 ---- a/block/rbd.c -+++ b/block/rbd.c -@@ -1320,6 +1320,7 @@ static int coroutine_fn qemu_rbd_co_block_status(BlockDriverState *bs, - int status, r; - RBDDiffIterateReq req = { .offs = offset }; - uint64_t features, flags; -+ uint64_t head = 0; - - assert(offset + bytes <= s->image_size); - -@@ -1347,7 +1348,43 @@ static int coroutine_fn qemu_rbd_co_block_status(BlockDriverState *bs, - return status; - } - -- r = rbd_diff_iterate2(s->image, NULL, offset, bytes, true, true, -+#if LIBRBD_VERSION_CODE < LIBRBD_VERSION(1, 17, 0) -+ /* -+ * librbd had a bug until early 2022 that affected all versions of ceph that -+ * supported fast-diff. This bug results in reporting of incorrect offsets -+ * if the offset parameter to rbd_diff_iterate2 is not object aligned. -+ * Work around this bug by rounding down the offset to object boundaries. -+ * This is OK because we call rbd_diff_iterate2 with whole_object = true. -+ * However, this workaround only works for non cloned images with default -+ * striping. -+ * -+ * See: https://tracker.ceph.com/issues/53784 -+ */ -+ -+ /* check if RBD image has non-default striping enabled */ -+ if (features & RBD_FEATURE_STRIPINGV2) { -+ return status; -+ } -+ -+#pragma GCC diagnostic push -+#pragma GCC diagnostic ignored "-Wdeprecated-declarations" -+ /* -+ * check if RBD image is a clone (= has a parent). -+ * -+ * rbd_get_parent_info is deprecated from Nautilus onwards, but the -+ * replacement rbd_get_parent is not present in Luminous and Mimic. -+ */ -+ if (rbd_get_parent_info(s->image, NULL, 0, NULL, 0, NULL, 0) != -ENOENT) { -+ return status; -+ } -+#pragma GCC diagnostic pop -+ -+ head = req.offs & (s->object_size - 1); -+ req.offs -= head; -+ bytes += head; -+#endif -+ -+ r = rbd_diff_iterate2(s->image, NULL, req.offs, bytes, true, true, - qemu_rbd_diff_iterate_cb, &req); - if (r < 0 && r != QEMU_RBD_EXIT_DIFF_ITERATE2) { - return status; -@@ -1366,7 +1403,8 @@ static int coroutine_fn qemu_rbd_co_block_status(BlockDriverState *bs, - status = BDRV_BLOCK_ZERO | BDRV_BLOCK_OFFSET_VALID; - } - -- *pnum = req.bytes; -+ assert(req.bytes > head); -+ *pnum = req.bytes - head; - return status; - } - --- -2.27.0 - diff --git a/SOURCES/kvm-configs-devices-aarch64-softmmu-Enable-CONFIG_VIRTIO.patch b/SOURCES/kvm-configs-devices-aarch64-softmmu-Enable-CONFIG_VIRTIO.patch new file mode 100644 index 0000000..a948e57 --- /dev/null +++ b/SOURCES/kvm-configs-devices-aarch64-softmmu-Enable-CONFIG_VIRTIO.patch @@ -0,0 +1,41 @@ +From 3a0e9bb88e82cc76ca5efc0595ce94b5dc34749e Mon Sep 17 00:00:00 2001 +From: Gavin Shan +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 +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 +RH-Acked-by: Eric Auger +RH-Acked-by: David Hildenbrand + +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 +--- + 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 + diff --git a/SOURCES/kvm-coroutine-Rename-qemu_coroutine_inc-dec_pool_size.patch b/SOURCES/kvm-coroutine-Rename-qemu_coroutine_inc-dec_pool_size.patch new file mode 100644 index 0000000..c1f3683 --- /dev/null +++ b/SOURCES/kvm-coroutine-Rename-qemu_coroutine_inc-dec_pool_size.patch @@ -0,0 +1,101 @@ +From e3cb8849862a9f0dd20f2913d540336a037d43c7 Mon Sep 17 00:00:00 2001 +From: Kevin Wolf +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 +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 +RH-Acked-by: Stefan Hajnoczi +RH-Acked-by: Stefano Garzarella + +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 +Message-Id: <20220510151020.105528-2-kwolf@redhat.com> +Signed-off-by: Kevin Wolf +(cherry picked from commit 98e3ab35054b946f7c2aba5408822532b0920b53) +Signed-off-by: Kevin Wolf +--- + 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 + diff --git a/SOURCES/kvm-coroutine-Revert-to-constant-batch-size.patch b/SOURCES/kvm-coroutine-Revert-to-constant-batch-size.patch new file mode 100644 index 0000000..2973510 --- /dev/null +++ b/SOURCES/kvm-coroutine-Revert-to-constant-batch-size.patch @@ -0,0 +1,138 @@ +From 345107bfd5537b51f34aaeb97d6161858bb6feee Mon Sep 17 00:00:00 2001 +From: Kevin Wolf +Date: Tue, 10 May 2022 17:10:20 +0200 +Subject: [PATCH 08/16] coroutine: Revert to constant batch size + +RH-Author: Kevin Wolf +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 +RH-Acked-by: Stefan Hajnoczi +RH-Acked-by: Stefano Garzarella + +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 +Message-Id: <20220510151020.105528-3-kwolf@redhat.com> +Tested-by: Hiroki Narukawa +Signed-off-by: Kevin Wolf +(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 +--- + 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 + diff --git a/SOURCES/kvm-coroutine-ucontext-use-QEMU_DEFINE_STATIC_CO_TLS.patch b/SOURCES/kvm-coroutine-ucontext-use-QEMU_DEFINE_STATIC_CO_TLS.patch new file mode 100644 index 0000000..963cf04 --- /dev/null +++ b/SOURCES/kvm-coroutine-ucontext-use-QEMU_DEFINE_STATIC_CO_TLS.patch @@ -0,0 +1,132 @@ +From ffbd90e5f4eba620c7cd631b04f0ed31beb22ffa Mon Sep 17 00:00:00 2001 +From: Stefan Hajnoczi +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 +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 +RH-Acked-by: Eric Blake +RH-Acked-by: Kevin Wolf + +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 +Message-Id: <20220307153853.602859-2-stefanha@redhat.com> +Reviewed-by: Philippe Mathieu-Daudé +Signed-off-by: Kevin Wolf +(cherry picked from commit 34145a307d849d0b6734d0222a7aa0bb9eef7407) +Signed-off-by: Stefan Hajnoczi +--- + 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 + #include "qemu/coroutine_int.h" ++#include "qemu/coroutine-tls.h" + + #ifdef CONFIG_VALGRIND_H + #include +@@ -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 + diff --git a/SOURCES/kvm-coroutine-use-QEMU_DEFINE_STATIC_CO_TLS.patch b/SOURCES/kvm-coroutine-use-QEMU_DEFINE_STATIC_CO_TLS.patch new file mode 100644 index 0000000..9d0f811 --- /dev/null +++ b/SOURCES/kvm-coroutine-use-QEMU_DEFINE_STATIC_CO_TLS.patch @@ -0,0 +1,139 @@ +From 9c2e55d25fec6ffb21e344513b7dbeed7e21f641 Mon Sep 17 00:00:00 2001 +From: Stefan Hajnoczi +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 +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 +RH-Acked-by: Eric Blake +RH-Acked-by: Kevin Wolf + +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 +Message-Id: <20220307153853.602859-3-stefanha@redhat.com> +Reviewed-by: Philippe Mathieu-Daudé +Signed-off-by: Kevin Wolf +(cherry picked from commit ac387a08a9c9f6b36757da912f0339c25f421f90) + +Conflicts: +- Context conflicts due to commit 5411171c3ef4 ("coroutine: Revert to + constant batch size"). + +Signed-off-by: Stefan Hajnoczi +--- + 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 + diff --git a/SOURCES/kvm-coroutine-win32-use-QEMU_DEFINE_STATIC_CO_TLS.patch b/SOURCES/kvm-coroutine-win32-use-QEMU_DEFINE_STATIC_CO_TLS.patch new file mode 100644 index 0000000..1665319 --- /dev/null +++ b/SOURCES/kvm-coroutine-win32-use-QEMU_DEFINE_STATIC_CO_TLS.patch @@ -0,0 +1,99 @@ +From 336581e6e9ace3f1ddd24ad0a258db9785f9b0ed Mon Sep 17 00:00:00 2001 +From: Stefan Hajnoczi +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 +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 +RH-Acked-by: Eric Blake +RH-Acked-by: Kevin Wolf + +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 +Message-Id: <20220307153853.602859-4-stefanha@redhat.com> +Reviewed-by: Philippe Mathieu-Daudé +Signed-off-by: Kevin Wolf +(cherry picked from commit c1fe694357a328c807ae3cc6961c19e923448fcc) +Signed-off-by: Stefan Hajnoczi +--- + 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 + diff --git a/SOURCES/kvm-doc-Add-the-SGX-numa-description.patch b/SOURCES/kvm-doc-Add-the-SGX-numa-description.patch deleted file mode 100644 index 8eac5fa..0000000 --- a/SOURCES/kvm-doc-Add-the-SGX-numa-description.patch +++ /dev/null @@ -1,77 +0,0 @@ -From eb88a12ab1ecfe77bcc0d0067c96fce27a3bde01 Mon Sep 17 00:00:00 2001 -From: Yang Zhong -Date: Mon, 1 Nov 2021 12:20:08 -0400 -Subject: [PATCH 03/12] doc: Add the SGX numa description - -RH-Author: Paul Lai -RH-MergeRequest: 65: Enable SGX and add SGX Numa support -RH-Commit: [3/5] c27b3f6976cbe92cc3c0e1dab0191cdd25de596a -RH-Bugzilla: 2033708 -RH-Acked-by: Paolo Bonzini -RH-Acked-by: Bandan Das -RH-Acked-by: Cornelia Huck - -Add the SGX numa reference command and how to check if -SGX numa is support or not with multiple EPC sections. - -Signed-off-by: Yang Zhong -Message-Id: <20211101162009.62161-5-yang.zhong@intel.com> -Signed-off-by: Paolo Bonzini -(cherry picked from commit d1889b36098c79e2e6ac90faf3d0dc5ec0057677) -Signed-off-by: Paul Lai ---- - docs/system/i386/sgx.rst | 31 +++++++++++++++++++++++++++---- - 1 file changed, 27 insertions(+), 4 deletions(-) - -diff --git a/docs/system/i386/sgx.rst b/docs/system/i386/sgx.rst -index f8fade5ac2..0f0a73f758 100644 ---- a/docs/system/i386/sgx.rst -+++ b/docs/system/i386/sgx.rst -@@ -141,8 +141,7 @@ To launch a SGX guest: - |qemu_system_x86| \\ - -cpu host,+sgx-provisionkey \\ - -object memory-backend-epc,id=mem1,size=64M,prealloc=on \\ -- -object memory-backend-epc,id=mem2,size=28M \\ -- -M sgx-epc.0.memdev=mem1,sgx-epc.1.memdev=mem2 -+ -M sgx-epc.0.memdev=mem1,sgx-epc.0.node=0 - - Utilizing SGX in the guest requires a kernel/OS with SGX support. - The support can be determined in guest by:: -@@ -152,8 +151,32 @@ The support can be determined in guest by:: - and SGX epc info by:: - - $ dmesg | grep sgx -- [ 1.242142] sgx: EPC section 0x180000000-0x181bfffff -- [ 1.242319] sgx: EPC section 0x181c00000-0x1837fffff -+ [ 0.182807] sgx: EPC section 0x140000000-0x143ffffff -+ [ 0.183695] sgx: [Firmware Bug]: Unable to map EPC section to online node. Fallback to the NUMA node 0. -+ -+To launch a SGX numa guest: -+ -+.. parsed-literal:: -+ -+ |qemu_system_x86| \\ -+ -cpu host,+sgx-provisionkey \\ -+ -object memory-backend-ram,size=2G,host-nodes=0,policy=bind,id=node0 \\ -+ -object memory-backend-epc,id=mem0,size=64M,prealloc=on,host-nodes=0,policy=bind \\ -+ -numa node,nodeid=0,cpus=0-1,memdev=node0 \\ -+ -object memory-backend-ram,size=2G,host-nodes=1,policy=bind,id=node1 \\ -+ -object memory-backend-epc,id=mem1,size=28M,prealloc=on,host-nodes=1,policy=bind \\ -+ -numa node,nodeid=1,cpus=2-3,memdev=node1 \\ -+ -M sgx-epc.0.memdev=mem0,sgx-epc.0.node=0,sgx-epc.1.memdev=mem1,sgx-epc.1.node=1 -+ -+and SGX epc numa info by:: -+ -+ $ dmesg | grep sgx -+ [ 0.369937] sgx: EPC section 0x180000000-0x183ffffff -+ [ 0.370259] sgx: EPC section 0x184000000-0x185bfffff -+ -+ $ dmesg | grep SRAT -+ [ 0.009981] ACPI: SRAT: Node 0 PXM 0 [mem 0x180000000-0x183ffffff] -+ [ 0.009982] ACPI: SRAT: Node 1 PXM 1 [mem 0x184000000-0x185bfffff] - - References - ---------- --- -2.27.0 - diff --git a/SOURCES/kvm-hw-acpi-aml-build-Use-existing-CPU-topology-to-build.patch b/SOURCES/kvm-hw-acpi-aml-build-Use-existing-CPU-topology-to-build.patch new file mode 100644 index 0000000..2795dcd --- /dev/null +++ b/SOURCES/kvm-hw-acpi-aml-build-Use-existing-CPU-topology-to-build.patch @@ -0,0 +1,179 @@ +From 8a12049e97149056f61f7748d9869606d282d16e Mon Sep 17 00:00:00 2001 +From: Gavin Shan +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 +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 +RH-Acked-by: Cornelia Huck +RH-Acked-by: Andrew Jones + +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 +Tested-by: Yanan Wang +Reviewed-by: Yanan Wang +Acked-by: Igor Mammedov +Acked-by: Michael S. Tsirkin +Message-id: 20220503140304.855514-7-gshan@redhat.com +Signed-off-by: Peter Maydell +(cherry picked from commit ae9141d4a3265553503bf07d3574b40f84615a34) +Signed-off-by: Gavin Shan +--- + 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 + diff --git a/SOURCES/kvm-hw-arm-smmuv3-Fix-device-reset.patch b/SOURCES/kvm-hw-arm-smmuv3-Fix-device-reset.patch deleted file mode 100644 index 3b8f307..0000000 --- a/SOURCES/kvm-hw-arm-smmuv3-Fix-device-reset.patch +++ /dev/null @@ -1,61 +0,0 @@ -From c08c3fbb2bb8494738fd34ec8fc9dc434ce82f4b Mon Sep 17 00:00:00 2001 -From: Eric Auger -Date: Wed, 2 Feb 2022 12:16:02 +0100 -Subject: [PATCH 12/12] hw/arm/smmuv3: Fix device reset - -RH-Author: Eric Auger -RH-MergeRequest: 72: hw/arm/smmuv3: Fix device reset -RH-Commit: [1/1] 2cfee2f7a03692681224fed96bb4f28406bf460a (eauger1/centos-qemu-kvm) -RH-Bugzilla: 2042481 -RH-Acked-by: Miroslav Rezanina -RH-Acked-by: Peter Xu -RH-Acked-by: Andrew Jones - -branch: c9s -Brew: 42958737 -Upstream: yes - -We currently miss a bunch of register resets in the device reset -function. This sometimes prevents the guest from rebooting after -a system_reset (with virtio-blk-pci). For instance, we may get -the following errors: - -invalid STE -smmuv3-iommu-memory-region-0-0 translation failed for iova=0x13a9d2000(SMMU_EVT_C_BAD_STE) -Invalid read at addr 0x13A9D2000, size 2, region '(null)', reason: rejected -invalid STE -smmuv3-iommu-memory-region-0-0 translation failed for iova=0x13a9d2000(SMMU_EVT_C_BAD_STE) -Invalid write at addr 0x13A9D2000, size 2, region '(null)', reason: rejected -invalid STE - -Signed-off-by: Eric Auger -Message-id: 20220202111602.627429-1-eric.auger@redhat.com -Fixes: 10a83cb988 ("hw/arm/smmuv3: Skeleton") -Reviewed-by: Peter Maydell -Signed-off-by: Peter Maydell -(cherry picked from commit 43530095e18fd16dcd51a4b385ad2a22c36f5698) -Signed-off-by: Eric Auger ---- - hw/arm/smmuv3.c | 6 ++++++ - 1 file changed, 6 insertions(+) - -diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c -index 01b60bee49..1b5640bb98 100644 ---- a/hw/arm/smmuv3.c -+++ b/hw/arm/smmuv3.c -@@ -276,6 +276,12 @@ static void smmuv3_init_regs(SMMUv3State *s) - s->features = 0; - s->sid_split = 0; - s->aidr = 0x1; -+ s->cr[0] = 0; -+ s->cr0ack = 0; -+ s->irq_ctrl = 0; -+ s->gerror = 0; -+ s->gerrorn = 0; -+ s->statusr = 0; - } - - static int smmu_get_ste(SMMUv3State *s, dma_addr_t addr, STE *buf, --- -2.27.0 - diff --git a/SOURCES/kvm-hw-arm-virt-Add-9.0-machine-type-and-remove-8.5-one.patch b/SOURCES/kvm-hw-arm-virt-Add-9.0-machine-type-and-remove-8.5-one.patch deleted file mode 100644 index 390a91c..0000000 --- a/SOURCES/kvm-hw-arm-virt-Add-9.0-machine-type-and-remove-8.5-one.patch +++ /dev/null @@ -1,48 +0,0 @@ -From 6b0e129f0758ccd076d1ecbf85c8f1e863788981 Mon Sep 17 00:00:00 2001 -From: Eric Auger -Date: Mon, 20 Dec 2021 10:11:47 +0100 -Subject: [PATCH 5/6] hw/arm/virt: Add 9.0 machine type and remove 8.5 one - -RH-Author: Eric Auger -RH-MergeRequest: 57: hw/arm/virt: Add 9.0 machine type and remove 8.5 one -RH-Commit: [5/6] f573a2fb44882a010e2c6bf5f561f29d54e6e9b5 (eauger1/centos-qemu-kvm) -RH-Bugzilla: 2031044 -RH-Acked-by: Gavin Shan -RH-Acked-by: Andrew Jones -RH-Acked-by: Miroslav Rezanina - -branch: c9s -Brew: 42213566 -Upstream: no - -Add 9.0 machine type and remove 8.5 one. - -Signed-off-by: Eric Auger ---- - hw/arm/virt.c | 10 ++-------- - 1 file changed, 2 insertions(+), 8 deletions(-) - -diff --git a/hw/arm/virt.c b/hw/arm/virt.c -index d433139479..d537706a86 100644 ---- a/hw/arm/virt.c -+++ b/hw/arm/virt.c -@@ -3236,14 +3236,8 @@ static void rhel_machine_init(void) - } - type_init(rhel_machine_init); - --static void rhel850_virt_options(MachineClass *mc) -+static void rhel900_virt_options(MachineClass *mc) - { -- 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_8_5, hw_compat_rhel_8_5_len); -- mc->smp_props.prefer_sockets = true; -- vmc->no_cpu_topology = true; -- vmc->no_tcg_its = true; - } --DEFINE_RHEL_MACHINE_AS_LATEST(8, 5, 0) -+DEFINE_RHEL_MACHINE_AS_LATEST(9, 0, 0) --- -2.27.0 - diff --git a/SOURCES/kvm-hw-arm-virt-Check-no_tcg_its-and-minor-style-changes.patch b/SOURCES/kvm-hw-arm-virt-Check-no_tcg_its-and-minor-style-changes.patch deleted file mode 100644 index 0e4acf4..0000000 --- a/SOURCES/kvm-hw-arm-virt-Check-no_tcg_its-and-minor-style-changes.patch +++ /dev/null @@ -1,88 +0,0 @@ -From 4098f7b5aea8871a655bab43d5114d067662e6c5 Mon Sep 17 00:00:00 2001 -From: Eric Auger -Date: Wed, 5 Jan 2022 16:17:10 +0100 -Subject: [PATCH 6/6] hw/arm/virt: Check no_tcg_its and minor style changes - -RH-Author: Eric Auger -RH-MergeRequest: 57: hw/arm/virt: Add 9.0 machine type and remove 8.5 one -RH-Commit: [6/6] 4480d569463fd3f637404539d3bd06b59cafbc88 (eauger1/centos-qemu-kvm) -RH-Bugzilla: 2031044 -RH-Acked-by: Gavin Shan -RH-Acked-by: Andrew Jones -RH-Acked-by: Miroslav Rezanina - -branch: c9s -Brew: 42213566 -Upstream: no - -Truly allow TCG ITS instantiation according to the no_tcg_its -class flag. Otherwise it is always set to false. - -We also take benefit of this patch to do some minor non -functional style changes to be closer to the upstream code. - -Signed-off-by: Eric Auger ---- - hw/arm/virt.c | 16 ++++++++++++---- - 1 file changed, 12 insertions(+), 4 deletions(-) - -diff --git a/hw/arm/virt.c b/hw/arm/virt.c -index d537706a86..0e691cbe81 100644 ---- a/hw/arm/virt.c -+++ b/hw/arm/virt.c -@@ -3163,6 +3163,7 @@ static void rhel_machine_class_init(ObjectClass *oc, void *data) - "in ACPI table header." - "The string may be up to 6 bytes in size"); - -+ - object_class_property_add_str(oc, "x-oem-table-id", - virt_get_oem_table_id, - virt_set_oem_table_id); -@@ -3170,6 +3171,7 @@ 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"); -+ - } - - static void rhel_virt_instance_init(Object *obj) -@@ -3194,26 +3196,32 @@ static void rhel_virt_instance_init(Object *obj) - } else { - /* Default allows ITS instantiation */ - vms->its = true; -+ -+ if (vmc->no_tcg_its) { -+ vms->tcg_its = false; -+ } else { -+ vms->tcg_its = true; -+ } - } - - /* Default disallows iommu instantiation */ - vms->iommu = VIRT_IOMMU_NONE; - -+ /* The default root bus is attached to iommu by default */ -+ vms->default_bus_bypass_iommu = false; -+ - /* Default disallows RAS instantiation and is non-configurable for RHEL */ - vms->ras = false; - - /* MTE is disabled by default and non-configurable for RHEL */ - vms->mte = false; - -- /* The default root bus is attached to iommu by default */ -- vms->default_bus_bypass_iommu = false; -- - vms->irqmap = a15irqmap; - - virt_flash_create(vms); -+ - vms->oem_id = g_strndup(ACPI_BUILD_APPNAME6, 6); - vms->oem_table_id = g_strndup(ACPI_BUILD_APPNAME8, 8); -- - } - - static const TypeInfo rhel_machine_info = { --- -2.27.0 - diff --git a/SOURCES/kvm-hw-arm-virt-Consider-SMP-configuration-in-CPU-topolo.patch b/SOURCES/kvm-hw-arm-virt-Consider-SMP-configuration-in-CPU-topolo.patch new file mode 100644 index 0000000..240aead --- /dev/null +++ b/SOURCES/kvm-hw-arm-virt-Consider-SMP-configuration-in-CPU-topolo.patch @@ -0,0 +1,74 @@ +From 3b05d3464945295112b5d02d142422f524a52054 Mon Sep 17 00:00:00 2001 +From: Gavin Shan +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 +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 +RH-Acked-by: Cornelia Huck +RH-Acked-by: Andrew Jones + +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 +Reviewed-by: Yanan Wang +Acked-by: Igor Mammedov +Message-id: 20220503140304.855514-4-gshan@redhat.com +Signed-off-by: Peter Maydell +(cherry picked from commit c9ec4cb5e4936f980889e717524e73896b0200ed) +Signed-off-by: Gavin Shan +--- + 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 + diff --git a/SOURCES/kvm-hw-arm-virt-Expose-the-RAS-option.patch b/SOURCES/kvm-hw-arm-virt-Expose-the-RAS-option.patch deleted file mode 100644 index e0365c9..0000000 --- a/SOURCES/kvm-hw-arm-virt-Expose-the-RAS-option.patch +++ /dev/null @@ -1,60 +0,0 @@ -From 914d9f9eea5d0a944aa93682b03d3189ad37ec9b Mon Sep 17 00:00:00 2001 -From: Eric Auger -Date: Mon, 20 Dec 2021 15:34:22 +0100 -Subject: [PATCH 4/6] hw/arm/virt: Expose the 'RAS' option - -RH-Author: Eric Auger -RH-MergeRequest: 57: hw/arm/virt: Add 9.0 machine type and remove 8.5 one -RH-Commit: [4/6] c8704564d31b23a0f08a6ced946c9a81e2e72c11 (eauger1/centos-qemu-kvm) -RH-Bugzilla: 2031044 -RH-Acked-by: Gavin Shan -RH-Acked-by: Andrew Jones -RH-Acked-by: Miroslav Rezanina - -branch: c9s -Brew: 42213566 -Upstream: no - -In RHEL9.0 we want to expose the 'RAS' option. - -Signed-off-by: Eric Auger ---- - hw/arm/virt.c | 8 +++++++- - 1 file changed, 7 insertions(+), 1 deletion(-) - -diff --git a/hw/arm/virt.c b/hw/arm/virt.c -index c99ca93e75..d433139479 100644 ---- a/hw/arm/virt.c -+++ b/hw/arm/virt.c -@@ -2348,7 +2348,6 @@ static void virt_set_acpi(Object *obj, Visitor *v, const char *name, - visit_type_OnOffAuto(v, name, &vms->acpi, errp); - } - --#if 0 /* Disabled for Red Hat Enterprise Linux */ - static bool virt_get_ras(Object *obj, Error **errp) - { - VirtMachineState *vms = VIRT_MACHINE(obj); -@@ -2363,6 +2362,7 @@ static void virt_set_ras(Object *obj, bool value, Error **errp) - vms->ras = value; - } - -+#if 0 /* Disabled for Red Hat Enterprise Linux */ - static bool virt_get_mte(Object *obj, Error **errp) - { - VirtMachineState *vms = VIRT_MACHINE(obj); -@@ -3143,6 +3143,12 @@ static void rhel_machine_class_init(ObjectClass *oc, void *data) - "Set on/off to enable/disable " - "bypass_iommu for default root bus"); - -+ object_class_property_add_bool(oc, "ras", virt_get_ras, -+ virt_set_ras); -+ object_class_property_set_description(oc, "ras", -+ "Set on/off to enable/disable reporting host memory errors " -+ "to a KVM guest using ACPI and guest external abort exceptions"); -+ - object_class_property_add_bool(oc, "its", virt_get_its, - virt_set_its); - object_class_property_set_description(oc, "its", --- -2.27.0 - diff --git a/SOURCES/kvm-hw-arm-virt-Fix-CPU-s-default-NUMA-node-ID.patch b/SOURCES/kvm-hw-arm-virt-Fix-CPU-s-default-NUMA-node-ID.patch new file mode 100644 index 0000000..6b60b70 --- /dev/null +++ b/SOURCES/kvm-hw-arm-virt-Fix-CPU-s-default-NUMA-node-ID.patch @@ -0,0 +1,88 @@ +From 14e49ad3b98f01c1ad6fe456469d40a96a43dc3c Mon Sep 17 00:00:00 2001 +From: Gavin Shan +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 +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 +RH-Acked-by: Cornelia Huck +RH-Acked-by: Andrew Jones + +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 + +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 +Reviewed-by: Igor Mammedov +Reviewed-by: Yanan Wang +Message-id: 20220503140304.855514-6-gshan@redhat.com +Signed-off-by: Peter Maydell +(cherry picked from commit 4c18bc192386dfbca530e7f550e0992df657818a) +Signed-off-by: Gavin Shan +--- + 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 + diff --git a/SOURCES/kvm-hw-arm-virt-Fix-missing-initialization-in-instance-c.patch b/SOURCES/kvm-hw-arm-virt-Fix-missing-initialization-in-instance-c.patch new file mode 100644 index 0000000..78b9ee0 --- /dev/null +++ b/SOURCES/kvm-hw-arm-virt-Fix-missing-initialization-in-instance-c.patch @@ -0,0 +1,56 @@ +From e25c40735d2f022c07481b548d20476222006657 Mon Sep 17 00:00:00 2001 +From: Eric Auger +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 +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 +RH-Acked-by: Andrew Jones +RH-Acked-by: Cornelia Huck + +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 +--- + 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 + diff --git a/SOURCES/kvm-hw-arm-virt-Register-iommu-as-a-class-property.patch b/SOURCES/kvm-hw-arm-virt-Register-iommu-as-a-class-property.patch deleted file mode 100644 index 6c21c9a..0000000 --- a/SOURCES/kvm-hw-arm-virt-Register-iommu-as-a-class-property.patch +++ /dev/null @@ -1,81 +0,0 @@ -From 545076d67ef27203e08538123d8bc3798caf9505 Mon Sep 17 00:00:00 2001 -From: Eric Auger -Date: Mon, 20 Dec 2021 15:50:44 +0100 -Subject: [PATCH 1/6] hw/arm/virt: Register "iommu" as a class property - -RH-Author: Eric Auger -RH-MergeRequest: 57: hw/arm/virt: Add 9.0 machine type and remove 8.5 one -RH-Commit: [1/6] 2b6a22ebddd2da7505961ff4ffe90424f7489300 (eauger1/centos-qemu-kvm) -RH-Bugzilla: 2031044 -RH-Acked-by: Gavin Shan -RH-Acked-by: Andrew Jones -RH-Acked-by: Miroslav Rezanina - -branch: c9s -Brew: 42213566 -Upstream: no - -Register the "iommu" option as a class property. This mirrors what -was done in upstream commit b91def7b ("arm/virt: Register -most properties as class properties"). - -While we are at it we also move the "x-oem-id" and "x-oem-table-id" -registrations at the very end of the rhel_machine_class_init() -function. This makes our life easier when comparing with upstream. - -Signed-off-by: Eric Auger ---- - hw/arm/virt.c | 23 ++++++++++++----------- - 1 file changed, 12 insertions(+), 11 deletions(-) - -diff --git a/hw/arm/virt.c b/hw/arm/virt.c -index 6ba9a2c2e1..7e227b1fa4 100644 ---- a/hw/arm/virt.c -+++ b/hw/arm/virt.c -@@ -3131,6 +3131,18 @@ static void rhel_machine_class_init(ObjectClass *oc, void *data) - "Set GIC version. " - "Valid values are 2, 3, host and max"); - -+ object_class_property_add_str(oc, "iommu", virt_get_iommu, virt_set_iommu); -+ object_class_property_set_description(oc, "iommu", -+ "Set the IOMMU type. " -+ "Valid values are none and smmuv3"); -+ -+ object_class_property_add_bool(oc, "default_bus_bypass_iommu", -+ virt_get_default_bus_bypass_iommu, -+ virt_set_default_bus_bypass_iommu); -+ object_class_property_set_description(oc, "default_bus_bypass_iommu", -+ "Set on/off to enable/disable " -+ "bypass_iommu for default root bus"); -+ - object_class_property_add_str(oc, "x-oem-id", - virt_get_oem_id, - virt_set_oem_id); -@@ -3146,13 +3158,6 @@ 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, "default_bus_bypass_iommu", -- virt_get_default_bus_bypass_iommu, -- virt_set_default_bus_bypass_iommu); -- object_class_property_set_description(oc, "default_bus_bypass_iommu", -- "Set on/off to enable/disable " -- "bypass_iommu for default root bus"); -- - } - - static void rhel_virt_instance_init(Object *obj) -@@ -3186,10 +3191,6 @@ static void rhel_virt_instance_init(Object *obj) - - /* Default disallows iommu instantiation */ - vms->iommu = VIRT_IOMMU_NONE; -- object_property_add_str(obj, "iommu", virt_get_iommu, virt_set_iommu); -- object_property_set_description(obj, "iommu", -- "Set the IOMMU type. " -- "Valid values are none and smmuv3"); - - /* Default disallows RAS instantiation and is non-configurable for RHEL */ - vms->ras = false; --- -2.27.0 - diff --git a/SOURCES/kvm-hw-arm-virt-Register-its-as-a-class-property.patch b/SOURCES/kvm-hw-arm-virt-Register-its-as-a-class-property.patch deleted file mode 100644 index 95f58a4..0000000 --- a/SOURCES/kvm-hw-arm-virt-Register-its-as-a-class-property.patch +++ /dev/null @@ -1,57 +0,0 @@ -From 789933e2598f9a525c2a638feca974ca1730a859 Mon Sep 17 00:00:00 2001 -From: Eric Auger -Date: Mon, 20 Dec 2021 16:04:59 +0100 -Subject: [PATCH 2/6] hw/arm/virt: Register "its" as a class property - -RH-Author: Eric Auger -RH-MergeRequest: 57: hw/arm/virt: Add 9.0 machine type and remove 8.5 one -RH-Commit: [2/6] dbd3e994553f00cd19842824f6bd763863a4e484 (eauger1/centos-qemu-kvm) -RH-Bugzilla: 2031044 -RH-Acked-by: Gavin Shan -RH-Acked-by: Andrew Jones -RH-Acked-by: Miroslav Rezanina - -branch: c9s -Brew: 42213566 -Upstream: no - -Register "its" as a class property. This mirrors what was done -in commit 27edeeaafe43 ("virt: Register "its" as class property"). - -Signed-off-by: Eric Auger ---- - hw/arm/virt.c | 11 ++++++----- - 1 file changed, 6 insertions(+), 5 deletions(-) - -diff --git a/hw/arm/virt.c b/hw/arm/virt.c -index 7e227b1fa4..984151b7dd 100644 ---- a/hw/arm/virt.c -+++ b/hw/arm/virt.c -@@ -3143,6 +3143,12 @@ static void rhel_machine_class_init(ObjectClass *oc, void *data) - "Set on/off to enable/disable " - "bypass_iommu for default root bus"); - -+ object_class_property_add_bool(oc, "its", virt_get_its, -+ virt_set_its); -+ object_class_property_set_description(oc, "its", -+ "Set on/off to enable/disable " -+ "ITS instantiation"); -+ - object_class_property_add_str(oc, "x-oem-id", - virt_get_oem_id, - virt_set_oem_id); -@@ -3182,11 +3188,6 @@ static void rhel_virt_instance_init(Object *obj) - } else { - /* Default allows ITS instantiation */ - vms->its = true; -- object_property_add_bool(obj, "its", virt_get_its, -- virt_set_its); -- object_property_set_description(obj, "its", -- "Set on/off to enable/disable " -- "ITS instantiation"); - } - - /* Default disallows iommu instantiation */ --- -2.27.0 - diff --git a/SOURCES/kvm-hw-arm-virt-Remove-the-dtb-kaslr-seed-machine-option.patch b/SOURCES/kvm-hw-arm-virt-Remove-the-dtb-kaslr-seed-machine-option.patch new file mode 100644 index 0000000..10af6c0 --- /dev/null +++ b/SOURCES/kvm-hw-arm-virt-Remove-the-dtb-kaslr-seed-machine-option.patch @@ -0,0 +1,76 @@ +From 69f771c3dc641431f3e98497cbd3832edb69284f Mon Sep 17 00:00:00 2001 +From: Eric Auger +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 +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 +RH-Acked-by: Andrew Jones +RH-Acked-by: Cornelia Huck + +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 + +--- +--- + 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 + diff --git a/SOURCES/kvm-hw-arm-virt-Rename-default_bus_bypass_iommu.patch b/SOURCES/kvm-hw-arm-virt-Rename-default_bus_bypass_iommu.patch deleted file mode 100644 index eab69d2..0000000 --- a/SOURCES/kvm-hw-arm-virt-Rename-default_bus_bypass_iommu.patch +++ /dev/null @@ -1,46 +0,0 @@ -From 94987c271c3bdc37216c5baa4c5766b9b7f053a1 Mon Sep 17 00:00:00 2001 -From: Eric Auger -Date: Mon, 20 Dec 2021 15:58:38 +0100 -Subject: [PATCH 3/6] hw/arm/virt: Rename default_bus_bypass_iommu - -RH-Author: Eric Auger -RH-MergeRequest: 57: hw/arm/virt: Add 9.0 machine type and remove 8.5 one -RH-Commit: [3/6] 6b66844ae4629d8c879f7c6abbc5e5017a162e16 (eauger1/centos-qemu-kvm) -RH-Bugzilla: 2031044 -RH-Acked-by: Gavin Shan -RH-Acked-by: Andrew Jones -RH-Acked-by: Miroslav Rezanina - -branch: c9s -Brew: 42213566 -Upstream: no - -Rename "default_bus_bypass_iommu" into "default-bus-bypass-iommu". -This mirrors what was done in upstream commit: -9dad363a223 ("hw/arm/virt: Rename default_bus_bypass_iommu") - -Signed-off-by: Eric Auger ---- - hw/arm/virt.c | 4 ++-- - 1 file changed, 2 insertions(+), 2 deletions(-) - -diff --git a/hw/arm/virt.c b/hw/arm/virt.c -index 984151b7dd..c99ca93e75 100644 ---- a/hw/arm/virt.c -+++ b/hw/arm/virt.c -@@ -3136,10 +3136,10 @@ static void rhel_machine_class_init(ObjectClass *oc, void *data) - "Set the IOMMU type. " - "Valid values are none and smmuv3"); - -- object_class_property_add_bool(oc, "default_bus_bypass_iommu", -+ object_class_property_add_bool(oc, "default-bus-bypass-iommu", - virt_get_default_bus_bypass_iommu, - virt_set_default_bus_bypass_iommu); -- object_class_property_set_description(oc, "default_bus_bypass_iommu", -+ object_class_property_set_description(oc, "default-bus-bypass-iommu", - "Set on/off to enable/disable " - "bypass_iommu for default root bus"); - --- -2.27.0 - diff --git a/SOURCES/kvm-hw-block-fdc-Prevent-end-of-track-overrun-CVE-2021-3.patch b/SOURCES/kvm-hw-block-fdc-Prevent-end-of-track-overrun-CVE-2021-3.patch new file mode 100644 index 0000000..1bdad27 --- /dev/null +++ b/SOURCES/kvm-hw-block-fdc-Prevent-end-of-track-overrun-CVE-2021-3.patch @@ -0,0 +1,96 @@ +From 6ee4a8718dcce2d6da43ee200534b75baf1d7bbe Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Philippe=20Mathieu-Daud=C3=A9?= +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 +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 +RH-Acked-by: Miroslav Rezanina + +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 +Fixes: baca51faff0 ("floppy driver: disk geometry auto detect") +Reported-by: Alexander Bulekov +Resolves: https://gitlab.com/qemu-project/qemu/-/issues/339 +Signed-off-by: Philippe Mathieu-Daudé +Message-Id: <20211118115733.4038610-2-philmd@redhat.com> +Reviewed-by: Hanna Reitz +Signed-off-by: Kevin Wolf +(cherry picked from commit defac5e2fbddf8423a354ff0454283a2115e1367) +Signed-off-by: Jon Maloy +--- + 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 + diff --git a/SOURCES/kvm-hw-virtio-Replace-g_memdup-by-g_memdup2.patch b/SOURCES/kvm-hw-virtio-Replace-g_memdup-by-g_memdup2.patch new file mode 100644 index 0000000..44897ac --- /dev/null +++ b/SOURCES/kvm-hw-virtio-Replace-g_memdup-by-g_memdup2.patch @@ -0,0 +1,95 @@ +From 4dad0e9abbc843fba4e5fee6e7aa1b0db13f5898 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +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 +RH-MergeRequest: 108: Net Control Virtqueue shadow Support +RH-Commit: [3/27] ae196903eb1a7aebbf999100e997cf82e5024cb6 (eperezmartin/qemu-kvm) +RH-Bugzilla: 1939363 +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Cindy Lu +RH-Acked-by: Laurent Vivier + +Bugzilla: https://bugzilla.redhat.com/1939363 + +Upstream Status: git://git.qemu.org/qemu.git + +commit d792199de55ca5cb5334016884039c740290b5c7 +Author: Philippe Mathieu-Daudé +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 + Acked-by: Eugenio Pérez + Signed-off-by: Philippe Mathieu-Daudé + Message-Id: <20220512175747.142058-6-eperezma@redhat.com> + Reviewed-by: Michael S. Tsirkin + Signed-off-by: Michael S. Tsirkin + +Signed-off-by: Eugenio Pérez +--- + 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 + diff --git a/SOURCES/kvm-hw-virtio-vdpa-Fix-leak-of-host-notifier-memory-regi.patch b/SOURCES/kvm-hw-virtio-vdpa-Fix-leak-of-host-notifier-memory-regi.patch deleted file mode 100644 index 20401ff..0000000 --- a/SOURCES/kvm-hw-virtio-vdpa-Fix-leak-of-host-notifier-memory-regi.patch +++ /dev/null @@ -1,60 +0,0 @@ -From 2005e3bb97fba4889829b58331a057b9cb35a65d Mon Sep 17 00:00:00 2001 -From: Laurent Vivier -Date: Fri, 11 Feb 2022 18:02:59 +0100 -Subject: [PATCH 2/5] hw/virtio: vdpa: Fix leak of host-notifier memory-region - -RH-Author: Laurent Vivier -RH-MergeRequest: 123: hw/virtio: vdpa: Fix leak of host-notifier memory-region -RH-Commit: [1/1] ddd64cac5c29786edf652f5fa97767b261ccfcdd -RH-Bugzilla: 2059786 -RH-Acked-by: Jason Wang -RH-Acked-by: Cindy Lu -RH-Acked-by: MST -RH-Acked-by: Stefano Garzarella - -BZ: https://bugzilla.redhat.com/2059786 -BRANCH: rhel-9.0.0 -BREW: https://brewweb.engineering.redhat.com/brew/taskinfo?taskID=43688388 -UPTREAM: Merged - -If call virtio_queue_set_host_notifier_mr fails, should free -host-notifier memory-region. - -This problem can trigger a coredump with some vDPA drivers (mlx5, -but not with the vdpasim), if we unplug the virtio-net card from -the guest after a stop/start. - -The same fix has been done for vhost-user: - 1f89d3b91e3e ("hw/virtio: Fix leak of host-notifier memory-region") - -Fixes: d0416d487bd5 ("vhost-vdpa: map virtqueue notification area if possible") -Cc: jasowang@redhat.com -Resolves: https://bugzilla.redhat.com/2027208 -Signed-off-by: Laurent Vivier -Message-Id: <20220211170259.1388734-1-lvivier@redhat.com> -Cc: qemu-stable@nongnu.org -Acked-by: Jason Wang -Reviewed-by: Stefano Garzarella -Reviewed-by: Michael S. Tsirkin -Signed-off-by: Michael S. Tsirkin -(cherry picked from commit 98f7607ecda00dea3cbb2ed7b4427c96846efb83) -Signed-off-by: Laurent Vivier ---- - hw/virtio/vhost-vdpa.c | 1 + - 1 file changed, 1 insertion(+) - -diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c -index bcaf00e09f..78da48a333 100644 ---- a/hw/virtio/vhost-vdpa.c -+++ b/hw/virtio/vhost-vdpa.c -@@ -415,6 +415,7 @@ static int vhost_vdpa_host_notifier_init(struct vhost_dev *dev, int queue_index) - g_free(name); - - if (virtio_queue_set_host_notifier_mr(vdev, queue_index, &n->mr, true)) { -+ object_unparent(OBJECT(&n->mr)); - munmap(addr, page_size); - goto err; - } --- -2.31.1 - diff --git a/SOURCES/kvm-i386-Add-Icelake-Server-v6-CPU-model-with-5-level-EP.patch b/SOURCES/kvm-i386-Add-Icelake-Server-v6-CPU-model-with-5-level-EP.patch deleted file mode 100644 index 2a67791..0000000 --- a/SOURCES/kvm-i386-Add-Icelake-Server-v6-CPU-model-with-5-level-EP.patch +++ /dev/null @@ -1,60 +0,0 @@ -From 575ca409fa21db088c76e57f7285021dd8da1569 Mon Sep 17 00:00:00 2001 -From: Vitaly Kuznetsov -Date: Wed, 16 Mar 2022 09:36:19 +0100 -Subject: [PATCH 04/14] i386: Add Icelake-Server-v6 CPU model with 5-level EPT - support - -RH-Author: Vitaly Kuznetsov -RH-MergeRequest: 126: i386: Add Icelake-Server-v6 CPU model with 5-level EPT support -RH-Commit: [2/2] a047caa01fafd8ca6a5fa0704b379edab91d4ccc -RH-Bugzilla: 2038051 -RH-Acked-by: Igor Mammedov -RH-Acked-by: Cornelia Huck -RH-Acked-by: Paolo Bonzini - -Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2038051 -Brew: https://brewweb.engineering.redhat.com/brew/taskinfo?taskID=43862630 - -commit 12cab535db6440af41ed8dfefe908a594321b6ce -Author: Vitaly Kuznetsov -Date: Mon Feb 21 15:53:15 2022 +0100 - - i386: Add Icelake-Server-v6 CPU model with 5-level EPT support - - Windows 11 with WSL2 enabled (Hyper-V) fails to boot with Icelake-Server - {-v5} CPU model but boots well with '-cpu host'. Apparently, it expects - 5-level paging and 5-level EPT support to come in pair but QEMU's - Icelake-Server CPU model lacks the later. Introduce 'Icelake-Server-v6' - CPU model with 'vmx-page-walk-5' enabled by default. - - Signed-off-by: Vitaly Kuznetsov - Message-Id: <20220221145316.576138-1-vkuznets@redhat.com> - Signed-off-by: Paolo Bonzini - -Signed-off-by: Vitaly Kuznetsov ---- - target/i386/cpu.c | 8 ++++++++ - 1 file changed, 8 insertions(+) - -diff --git a/target/i386/cpu.c b/target/i386/cpu.c -index aa9e636800..6e25d13339 100644 ---- a/target/i386/cpu.c -+++ b/target/i386/cpu.c -@@ -3505,6 +3505,14 @@ static const X86CPUDefinition builtin_x86_defs[] = { - { /* end of list */ } - }, - }, -+ { -+ .version = 6, -+ .note = "5-level EPT", -+ .props = (PropValue[]) { -+ { "vmx-page-walk-5", "on" }, -+ { /* end of list */ } -+ }, -+ }, - { /* end of list */ } - } - }, --- -2.31.1 - diff --git a/SOURCES/kvm-i386-do-kvm_put_msr_feature_control-first-thing-when.patch b/SOURCES/kvm-i386-do-kvm_put_msr_feature_control-first-thing-when.patch new file mode 100644 index 0000000..a1d4496 --- /dev/null +++ b/SOURCES/kvm-i386-do-kvm_put_msr_feature_control-first-thing-when.patch @@ -0,0 +1,68 @@ +From 8452a7925e18d6d57e2ac787b192097d4136b104 Mon Sep 17 00:00:00 2001 +From: Vitaly Kuznetsov +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 +RH-MergeRequest: 217: i386: fix 'system_reset' when the VM is in VMX root operation +RH-Bugzilla: 2117546 +RH-Acked-by: Emanuele Giuseppe Esposito +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Peter Xu +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 +Message-Id: <20220818150113.479917-3-vkuznets@redhat.com> +Signed-off-by: Paolo Bonzini +(cherry picked from commit 45ed68a1a3a19754ade954d75a3c9d13ff560e5c) +Signed-off-by: Vitaly Kuznetsov +--- + 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 + diff --git a/SOURCES/kvm-i386-reset-KVM-nested-state-upon-CPU-reset.patch b/SOURCES/kvm-i386-reset-KVM-nested-state-upon-CPU-reset.patch new file mode 100644 index 0000000..7fe9b99 --- /dev/null +++ b/SOURCES/kvm-i386-reset-KVM-nested-state-upon-CPU-reset.patch @@ -0,0 +1,95 @@ +From b84bb71165c97b475548edc1c07decccca53cf16 Mon Sep 17 00:00:00 2001 +From: Vitaly Kuznetsov +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 +RH-MergeRequest: 217: i386: fix 'system_reset' when the VM is in VMX root operation +RH-Bugzilla: 2117546 +RH-Acked-by: Emanuele Giuseppe Esposito +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Peter Xu +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 +Signed-off-by: Vitaly Kuznetsov +Message-Id: <20220818150113.479917-2-vkuznets@redhat.com> +Signed-off-by: Paolo Bonzini +(cherry picked from commit 3cafdb67504a34a0305260f0c86a73d5a3fb000b) +Signed-off-by: Vitaly Kuznetsov +--- + 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 + diff --git a/SOURCES/kvm-iotests-108-Fix-when-missing-user_allow_other.patch b/SOURCES/kvm-iotests-108-Fix-when-missing-user_allow_other.patch new file mode 100644 index 0000000..a37ea6f --- /dev/null +++ b/SOURCES/kvm-iotests-108-Fix-when-missing-user_allow_other.patch @@ -0,0 +1,52 @@ +From 447bca651c9156d7aba6b7495c75f19b5e4ed53f Mon Sep 17 00:00:00 2001 +From: Hanna Reitz +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 +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 +RH-Acked-by: Eric Blake +RH-Acked-by: Stefan Hajnoczi + +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 +Signed-off-by: Hanna Reitz +Message-Id: <20220421142435.569600-1-hreitz@redhat.com> +Tested-by: Markus Armbruster +Tested-by: Eric Blake +(cherry picked from commit 348a0740afc5b313599533eb69bbb2b95d2f1bba) +Signed-off-by: Hanna Reitz +--- + 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 + diff --git a/SOURCES/kvm-iotests-108-Test-new-refcount-rebuild-algorithm.patch b/SOURCES/kvm-iotests-108-Test-new-refcount-rebuild-algorithm.patch new file mode 100644 index 0000000..7a968f6 --- /dev/null +++ b/SOURCES/kvm-iotests-108-Test-new-refcount-rebuild-algorithm.patch @@ -0,0 +1,445 @@ +From ed69e01352b5e9a06173daab53bfa373c8535732 Mon Sep 17 00:00:00 2001 +From: Hanna Reitz +Date: Tue, 5 Apr 2022 15:46:51 +0200 +Subject: [PATCH 05/16] iotests/108: Test new refcount rebuild algorithm + +RH-Author: Hanna Reitz +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 +RH-Acked-by: Eric Blake +RH-Acked-by: Stefan Hajnoczi + +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 +Signed-off-by: Hanna Reitz +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 +--- + 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 + diff --git a/SOURCES/kvm-iotests-281-Let-NBD-connection-yield-in-iothread.patch b/SOURCES/kvm-iotests-281-Let-NBD-connection-yield-in-iothread.patch deleted file mode 100644 index 20bc3a5..0000000 --- a/SOURCES/kvm-iotests-281-Let-NBD-connection-yield-in-iothread.patch +++ /dev/null @@ -1,108 +0,0 @@ -From 06583ce33fab2976157461ac4503d6f8eeb59e75 Mon Sep 17 00:00:00 2001 -From: Hanna Reitz -Date: Fri, 4 Feb 2022 12:10:12 +0100 -Subject: [PATCH 8/8] iotests/281: Let NBD connection yield in iothread - -RH-Author: Hanna Reitz -RH-MergeRequest: 74: block/nbd: Handle AioContext changes -RH-Commit: [6/6] 632b9ef5177a80d1c0c00121e1acc37272076d3e (hreitz/qemu-kvm-c-9-s) -RH-Bugzilla: 2033626 -RH-Acked-by: Miroslav Rezanina -RH-Acked-by: Eric Blake -RH-Acked-by: Stefan Hajnoczi - -Put an NBD block device into an I/O thread, and then read data from it, -hoping that the NBD connection will yield during that read. When it -does, the coroutine must be reentered in the block device's I/O thread, -which will only happen if the NBD block driver attaches the connection's -QIOChannel to the new AioContext. It did not do that after 4ddb5d2fde -("block/nbd: drop connection_co") and prior to "block/nbd: Move s->ioc -on AioContext change", which would cause an assertion failure. - -To improve our chances of yielding, the NBD server is throttled to -reading 64 kB/s, and the NBD client reads 128 kB, so it should yield at -some point. - -Reviewed-by: Vladimir Sementsov-Ogievskiy -Signed-off-by: Hanna Reitz -Signed-off-by: Vladimir Sementsov-Ogievskiy -(cherry picked from commit 8cfbe929e8c26050f0a4580a1606a370a947d4ce) -Signed-off-by: Hanna Reitz ---- - tests/qemu-iotests/281 | 28 +++++++++++++++++++++++++--- - tests/qemu-iotests/281.out | 4 ++-- - 2 files changed, 27 insertions(+), 5 deletions(-) - -diff --git a/tests/qemu-iotests/281 b/tests/qemu-iotests/281 -index 13c588be75..b2ead7f388 100755 ---- a/tests/qemu-iotests/281 -+++ b/tests/qemu-iotests/281 -@@ -253,8 +253,9 @@ class TestYieldingAndTimers(iotests.QMPTestCase): - self.create_nbd_export() - - # Simple VM with an NBD block device connected to the NBD export -- # provided by the QSD -+ # provided by the QSD, and an (initially unused) iothread - self.vm = iotests.VM() -+ self.vm.add_object('iothread,id=iothr') - self.vm.add_blockdev('nbd,node-name=nbd,server.type=unix,' + - f'server.path={self.sock},export=exp,' + - 'reconnect-delay=1') -@@ -293,19 +294,40 @@ class TestYieldingAndTimers(iotests.QMPTestCase): - # thus not see the error, and so the test will pass.) - time.sleep(2) - -+ def test_yield_in_iothread(self): -+ # Move the NBD node to the I/O thread; the NBD block driver should -+ # attach the connection's QIOChannel to that thread's AioContext, too -+ result = self.vm.qmp('x-blockdev-set-iothread', -+ node_name='nbd', iothread='iothr') -+ self.assert_qmp(result, 'return', {}) -+ -+ # Do some I/O that will be throttled by the QSD, so that the network -+ # connection hopefully will yield here. When it is resumed, it must -+ # then be resumed in the I/O thread's AioContext. -+ result = self.vm.qmp('human-monitor-command', -+ command_line='qemu-io nbd "read 0 128K"') -+ self.assert_qmp(result, 'return', '') -+ - def create_nbd_export(self): - assert self.qsd is None - -- # Simple NBD export of a null-co BDS -+ # Export a throttled null-co BDS: Reads are throttled (max 64 kB/s), -+ # writes are not. - self.qsd = QemuStorageDaemon( -+ '--object', -+ 'throttle-group,id=thrgr,x-bps-read=65536,x-bps-read-max=65536', -+ - '--blockdev', - 'null-co,node-name=null,read-zeroes=true', - -+ '--blockdev', -+ 'throttle,node-name=thr,file=null,throttle-group=thrgr', -+ - '--nbd-server', - f'addr.type=unix,addr.path={self.sock}', - - '--export', -- 'nbd,id=exp,node-name=null,name=exp,writable=true' -+ 'nbd,id=exp,node-name=thr,name=exp,writable=true' - ) - - def stop_nbd_export(self): -diff --git a/tests/qemu-iotests/281.out b/tests/qemu-iotests/281.out -index 914e3737bd..3f8a935a08 100644 ---- a/tests/qemu-iotests/281.out -+++ b/tests/qemu-iotests/281.out -@@ -1,5 +1,5 @@ --..... -+...... - ---------------------------------------------------------------------- --Ran 5 tests -+Ran 6 tests - - OK --- -2.27.0 - diff --git a/SOURCES/kvm-iotests-281-Test-lingering-timers.patch b/SOURCES/kvm-iotests-281-Test-lingering-timers.patch deleted file mode 100644 index 7175a31..0000000 --- a/SOURCES/kvm-iotests-281-Test-lingering-timers.patch +++ /dev/null @@ -1,174 +0,0 @@ -From 3d2d7a46713d362d2ff5137841e689593da976a3 Mon Sep 17 00:00:00 2001 -From: Hanna Reitz -Date: Fri, 4 Feb 2022 12:10:10 +0100 -Subject: [PATCH 6/8] iotests/281: Test lingering timers - -RH-Author: Hanna Reitz -RH-MergeRequest: 74: block/nbd: Handle AioContext changes -RH-Commit: [4/6] d228ba3fcdfaab2d54dd5b023688a1c055cce2c2 (hreitz/qemu-kvm-c-9-s) -RH-Bugzilla: 2033626 -RH-Acked-by: Miroslav Rezanina -RH-Acked-by: Eric Blake -RH-Acked-by: Stefan Hajnoczi - -Prior to "block/nbd: Delete reconnect delay timer when done" and -"block/nbd: Delete open timer when done", both of those timers would -remain scheduled even after successfully (re-)connecting to the server, -and they would not even be deleted when the BDS is deleted. - -This test constructs exactly this situation: -(1) Configure an @open-timeout, so the open timer is armed, and -(2) Configure a @reconnect-delay and trigger a reconnect situation - (which succeeds immediately), so the reconnect delay timer is armed. -Then we immediately delete the BDS, and sleep for longer than the -@open-timeout and @reconnect-delay. Prior to said patches, this caused -one (or both) of the timer CBs to access already-freed data. - -Accessing freed data may or may not crash, so this test can produce -false successes, but I do not know how to show the problem in a better -or more reliable way. If you run this test on "block/nbd: Assert there -are no timers when closed" and without the fix patches mentioned above, -you should reliably see an assertion failure. -(But all other tests that use the reconnect delay timer (264 and 277) -will fail in that configuration, too; as will nbd-reconnect-on-open, -which uses the open timer.) - -Remove this test from the quick group because of the two second sleep -this patch introduces. - -(I decided to put this test case into 281, because the main bug this -series addresses is in the interaction of the NBD block driver and I/O -threads, which is precisely the scope of 281. The test case for that -other bug will also be put into the test class added here. - -Also, excuse the test class's name, I couldn't come up with anything -better. The "yield" part will make sense two patches from now.) - -Reviewed-by: Vladimir Sementsov-Ogievskiy -Signed-off-by: Hanna Reitz -Signed-off-by: Vladimir Sementsov-Ogievskiy -(cherry picked from commit eaf1e85d4ddefdbd197f393fa9c5acc7ba8133b0) - -Conflict: -- @open-timeout was introduced after the 6.2 release, and has not been - backported. Consequently, there is no open_timer, and we can (and - must) drop the respective parts of the test here. - -Signed-off-by: Hanna Reitz ---- - tests/qemu-iotests/281 | 73 ++++++++++++++++++++++++++++++++++++-- - tests/qemu-iotests/281.out | 4 +-- - 2 files changed, 73 insertions(+), 4 deletions(-) - -diff --git a/tests/qemu-iotests/281 b/tests/qemu-iotests/281 -index 956698083f..13c588be75 100755 ---- a/tests/qemu-iotests/281 -+++ b/tests/qemu-iotests/281 -@@ -1,5 +1,5 @@ - #!/usr/bin/env python3 --# group: rw quick -+# group: rw - # - # Test cases for blockdev + IOThread interactions - # -@@ -20,8 +20,9 @@ - # - - import os -+import time - import iotests --from iotests import qemu_img -+from iotests import qemu_img, QemuStorageDaemon - - image_len = 64 * 1024 * 1024 - -@@ -243,6 +244,74 @@ class TestBlockdevBackupAbort(iotests.QMPTestCase): - # Hangs on failure, we expect this error. - self.assert_qmp(result, 'error/class', 'GenericError') - -+# Test for RHBZ#2033626 -+class TestYieldingAndTimers(iotests.QMPTestCase): -+ sock = os.path.join(iotests.sock_dir, 'nbd.sock') -+ qsd = None -+ -+ def setUp(self): -+ self.create_nbd_export() -+ -+ # Simple VM with an NBD block device connected to the NBD export -+ # provided by the QSD -+ self.vm = iotests.VM() -+ self.vm.add_blockdev('nbd,node-name=nbd,server.type=unix,' + -+ f'server.path={self.sock},export=exp,' + -+ 'reconnect-delay=1') -+ -+ self.vm.launch() -+ -+ def tearDown(self): -+ self.stop_nbd_export() -+ self.vm.shutdown() -+ -+ def test_timers_with_blockdev_del(self): -+ # Stop and restart the NBD server, and do some I/O on the client to -+ # trigger a reconnect and start the reconnect delay timer -+ self.stop_nbd_export() -+ self.create_nbd_export() -+ -+ result = self.vm.qmp('human-monitor-command', -+ command_line='qemu-io nbd "write 0 512"') -+ self.assert_qmp(result, 'return', '') -+ -+ # Reconnect is done, so the reconnect delay timer should be gone. -+ # (But there used to be a bug where it remained active, for which this -+ # is a regression test.) -+ -+ # Delete the BDS to see whether the timer is gone. If it is not, -+ # it will remain active, fire later, and then access freed data. -+ # (Or, with "block/nbd: Assert there are no timers when closed" -+ # applied, the assertion added in that patch will fail.) -+ result = self.vm.qmp('blockdev-del', node_name='nbd') -+ self.assert_qmp(result, 'return', {}) -+ -+ # Give the timer some time to fire (it has a timeout of 1 s). -+ # (Sleeping in an iotest may ring some alarm bells, but note that if -+ # the timing is off here, the test will just always pass. If we kill -+ # the VM too early, then we just kill the timer before it can fire, -+ # thus not see the error, and so the test will pass.) -+ time.sleep(2) -+ -+ def create_nbd_export(self): -+ assert self.qsd is None -+ -+ # Simple NBD export of a null-co BDS -+ self.qsd = QemuStorageDaemon( -+ '--blockdev', -+ 'null-co,node-name=null,read-zeroes=true', -+ -+ '--nbd-server', -+ f'addr.type=unix,addr.path={self.sock}', -+ -+ '--export', -+ 'nbd,id=exp,node-name=null,name=exp,writable=true' -+ ) -+ -+ def stop_nbd_export(self): -+ self.qsd.stop() -+ self.qsd = None -+ - if __name__ == '__main__': - iotests.main(supported_fmts=['qcow2'], - supported_protocols=['file']) -diff --git a/tests/qemu-iotests/281.out b/tests/qemu-iotests/281.out -index 89968f35d7..914e3737bd 100644 ---- a/tests/qemu-iotests/281.out -+++ b/tests/qemu-iotests/281.out -@@ -1,5 +1,5 @@ --.... -+..... - ---------------------------------------------------------------------- --Ran 4 tests -+Ran 5 tests - - OK --- -2.27.0 - diff --git a/SOURCES/kvm-iotests-Test-blockdev-reopen-with-iothreads-and-thro.patch b/SOURCES/kvm-iotests-Test-blockdev-reopen-with-iothreads-and-thro.patch deleted file mode 100644 index 8616f1c..0000000 --- a/SOURCES/kvm-iotests-Test-blockdev-reopen-with-iothreads-and-thro.patch +++ /dev/null @@ -1,106 +0,0 @@ -From 37593348e7d95580fb2b0009dcb026c07367f1f8 Mon Sep 17 00:00:00 2001 -From: Kevin Wolf -Date: Thu, 3 Feb 2022 15:05:34 +0100 -Subject: [PATCH 2/8] iotests: Test blockdev-reopen with iothreads and - throttling - -RH-Author: Kevin Wolf -RH-MergeRequest: 73: block: Lock AioContext for drain_end in blockdev-reopen -RH-Commit: [2/2] d19d5fa9efa4813ece75708436891041754ab910 (kmwolf/centos-qemu-kvm) -RH-Bugzilla: 2046659 -RH-Acked-by: Sergio Lopez -RH-Acked-by: Stefan Hajnoczi -RH-Acked-by: Hanna Reitz - -The 'throttle' block driver implements .bdrv_co_drain_end, so -blockdev-reopen will have to wait for it to complete in the polling -loop at the end of qmp_blockdev_reopen(). This makes AIO_WAIT_WHILE() -release the AioContext lock, which causes a crash if the lock hasn't -correctly been taken. - -Signed-off-by: Kevin Wolf -Message-Id: <20220203140534.36522-3-kwolf@redhat.com> -Reviewed-by: Hanna Reitz -Signed-off-by: Kevin Wolf -(cherry picked from commit ee810602376125ca0e0afd6b7c715e13740978ea) -Signed-off-by: Kevin Wolf ---- - tests/qemu-iotests/245 | 36 +++++++++++++++++++++++++++++++++--- - tests/qemu-iotests/245.out | 4 ++-- - 2 files changed, 35 insertions(+), 5 deletions(-) - -diff --git a/tests/qemu-iotests/245 b/tests/qemu-iotests/245 -index 24ac43f70e..8cbed7821b 100755 ---- a/tests/qemu-iotests/245 -+++ b/tests/qemu-iotests/245 -@@ -1138,12 +1138,13 @@ class TestBlockdevReopen(iotests.QMPTestCase): - self.assertEqual(self.get_node('hd1'), None) - self.assert_qmp(self.get_node('hd2'), 'ro', True) - -- def run_test_iothreads(self, iothread_a, iothread_b, errmsg = None): -- opts = hd_opts(0) -+ def run_test_iothreads(self, iothread_a, iothread_b, errmsg = None, -+ opts_a = None, opts_b = None): -+ opts = opts_a or hd_opts(0) - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) - -- opts2 = hd_opts(2) -+ opts2 = opts_b or hd_opts(2) - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts2) - self.assert_qmp(result, 'return', {}) - -@@ -1194,6 +1195,35 @@ class TestBlockdevReopen(iotests.QMPTestCase): - def test_iothreads_switch_overlay(self): - self.run_test_iothreads('', 'iothread0') - -+ def test_iothreads_with_throttling(self): -+ # Create a throttle-group object -+ opts = { 'qom-type': 'throttle-group', 'id': 'group0', -+ 'limits': { 'iops-total': 1000 } } -+ result = self.vm.qmp('object-add', conv_keys = False, **opts) -+ self.assert_qmp(result, 'return', {}) -+ -+ # Options with a throttle filter between format and protocol -+ opts = [ -+ { -+ 'driver': iotests.imgfmt, -+ 'node-name': f'hd{idx}', -+ 'file' : { -+ 'node-name': f'hd{idx}-throttle', -+ 'driver': 'throttle', -+ 'throttle-group': 'group0', -+ 'file': { -+ 'driver': 'file', -+ 'node-name': f'hd{idx}-file', -+ 'filename': hd_path[idx], -+ }, -+ }, -+ } -+ for idx in (0, 2) -+ ] -+ -+ self.run_test_iothreads('iothread0', 'iothread0', None, -+ opts[0], opts[1]) -+ - if __name__ == '__main__': - iotests.activate_logging() - iotests.main(supported_fmts=["qcow2"], -diff --git a/tests/qemu-iotests/245.out b/tests/qemu-iotests/245.out -index 4eced19294..a4e04a3266 100644 ---- a/tests/qemu-iotests/245.out -+++ b/tests/qemu-iotests/245.out -@@ -17,8 +17,8 @@ read 1/1 bytes at offset 262152 - read 1/1 bytes at offset 262160 - 1 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) - --............... -+................ - ---------------------------------------------------------------------- --Ran 25 tests -+Ran 26 tests - - OK --- -2.27.0 - diff --git a/SOURCES/kvm-iotests-Test-qemu-img-convert-of-zeroed-data-cluster.patch b/SOURCES/kvm-iotests-Test-qemu-img-convert-of-zeroed-data-cluster.patch deleted file mode 100644 index 0ab3bcc..0000000 --- a/SOURCES/kvm-iotests-Test-qemu-img-convert-of-zeroed-data-cluster.patch +++ /dev/null @@ -1,81 +0,0 @@ -From 51f691acd8042351d005873996d7bf4c7b045508 Mon Sep 17 00:00:00 2001 -From: Kevin Wolf -Date: Fri, 17 Dec 2021 17:46:53 +0100 -Subject: [PATCH 08/12] iotests: Test qemu-img convert of zeroed data cluster - -RH-Author: Kevin Wolf -RH-MergeRequest: 70: qemu-img convert: Fix sparseness of output image -RH-Commit: [1/2] 0770582c553ac6b0f18c035f9a0238599d4763cc (kmwolf/centos-qemu-kvm) -RH-Bugzilla: 1882917 -RH-Acked-by: Eric Blake -RH-Acked-by: Stefan Hajnoczi -RH-Acked-by: Hanna Reitz - -This demonstrates what happens when the block status changes in -sub-min_sparse granularity, but all of the parts are zeroed out. The -alignment logic in is_allocated_sectors() prevents that the target image -remains fully sparse as expected, but turns it into a data cluster of -explicit zeros. - -Signed-off-by: Kevin Wolf -Signed-off-by: Vladimir Sementsov-Ogievskiy -Message-Id: <20211217164654.1184218-2-vsementsov@virtuozzo.com> -Tested-by: Peter Lieven -Signed-off-by: Kevin Wolf -(cherry picked from commit 51cd8bddd63540514d44808f7920811439baa253) -Signed-off-by: Kevin Wolf ---- - tests/qemu-iotests/122 | 1 + - tests/qemu-iotests/122.out | 10 ++++++++-- - 2 files changed, 9 insertions(+), 2 deletions(-) - -diff --git a/tests/qemu-iotests/122 b/tests/qemu-iotests/122 -index efb260d822..be0f6b79e5 100755 ---- a/tests/qemu-iotests/122 -+++ b/tests/qemu-iotests/122 -@@ -251,6 +251,7 @@ $QEMU_IO -c "write -P 0 0 64k" "$TEST_IMG" 2>&1 | _filter_qemu_io | _filter_test - $QEMU_IO -c "write 0 1k" "$TEST_IMG" 2>&1 | _filter_qemu_io | _filter_testdir - $QEMU_IO -c "write 8k 1k" "$TEST_IMG" 2>&1 | _filter_qemu_io | _filter_testdir - $QEMU_IO -c "write 17k 1k" "$TEST_IMG" 2>&1 | _filter_qemu_io | _filter_testdir -+$QEMU_IO -c "write -P 0 65k 1k" "$TEST_IMG" 2>&1 | _filter_qemu_io | _filter_testdir - - for min_sparse in 4k 8k; do - echo -diff --git a/tests/qemu-iotests/122.out b/tests/qemu-iotests/122.out -index 8fbdac2b39..69b8e8b803 100644 ---- a/tests/qemu-iotests/122.out -+++ b/tests/qemu-iotests/122.out -@@ -192,6 +192,8 @@ wrote 1024/1024 bytes at offset 8192 - 1 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) - wrote 1024/1024 bytes at offset 17408 - 1 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) -+wrote 1024/1024 bytes at offset 66560 -+1 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) - - convert -S 4k - [{ "start": 0, "length": 4096, "depth": 0, "present": true, "zero": false, "data": true, "offset": OFFSET}, -@@ -199,7 +201,9 @@ convert -S 4k - { "start": 8192, "length": 4096, "depth": 0, "present": true, "zero": false, "data": true, "offset": OFFSET}, - { "start": 12288, "length": 4096, "depth": 0, "present": false, "zero": true, "data": false}, - { "start": 16384, "length": 4096, "depth": 0, "present": true, "zero": false, "data": true, "offset": OFFSET}, --{ "start": 20480, "length": 67088384, "depth": 0, "present": false, "zero": true, "data": false}] -+{ "start": 20480, "length": 46080, "depth": 0, "present": false, "zero": true, "data": false}, -+{ "start": 66560, "length": 1024, "depth": 0, "present": true, "zero": false, "data": true, "offset": OFFSET}, -+{ "start": 67584, "length": 67041280, "depth": 0, "present": false, "zero": true, "data": false}] - - convert -c -S 4k - [{ "start": 0, "length": 1024, "depth": 0, "present": true, "zero": false, "data": true}, -@@ -211,7 +215,9 @@ convert -c -S 4k - - convert -S 8k - [{ "start": 0, "length": 24576, "depth": 0, "present": true, "zero": false, "data": true, "offset": OFFSET}, --{ "start": 24576, "length": 67084288, "depth": 0, "present": false, "zero": true, "data": false}] -+{ "start": 24576, "length": 41984, "depth": 0, "present": false, "zero": true, "data": false}, -+{ "start": 66560, "length": 1024, "depth": 0, "present": true, "zero": false, "data": true, "offset": OFFSET}, -+{ "start": 67584, "length": 67041280, "depth": 0, "present": false, "zero": true, "data": false}] - - convert -c -S 8k - [{ "start": 0, "length": 1024, "depth": 0, "present": true, "zero": false, "data": true}, --- -2.27.0 - diff --git a/SOURCES/kvm-iotests-block-status-cache-New-test.patch b/SOURCES/kvm-iotests-block-status-cache-New-test.patch deleted file mode 100644 index cd9a198..0000000 --- a/SOURCES/kvm-iotests-block-status-cache-New-test.patch +++ /dev/null @@ -1,197 +0,0 @@ -From 89fe89491f89a7526ba864a9d94d3de930261d69 Mon Sep 17 00:00:00 2001 -From: Hanna Reitz -Date: Tue, 18 Jan 2022 18:00:00 +0100 -Subject: [PATCH 07/12] iotests/block-status-cache: New test - -RH-Author: Hanna Reitz -RH-MergeRequest: 69: block/io: Update BSC only if want_zero is true -RH-Commit: [2/2] 3c5a55aca1ac7a71c175a124d63bcf7a4430a022 (hreitz/qemu-kvm-c-9-s) -RH-Bugzilla: 2041461 -RH-Acked-by: Eric Blake -RH-Acked-by: Stefan Hajnoczi -RH-Acked-by: Kevin Wolf - -Add a new test to verify that want_zero=false block-status calls do not -pollute the block-status cache for want_zero=true calls. - -We check want_zero=true calls and their results using `qemu-img map` -(over NBD), and want_zero=false calls also using `qemu-img map` over -NBD, but using the qemu:allocation-depth context. - -(This test case cannot be integrated into nbd-qemu-allocation, because -that is a qcow2 test, and this is a raw test.) - -Signed-off-by: Hanna Reitz -Message-Id: <20220118170000.49423-3-hreitz@redhat.com> -Reviewed-by: Nir Soffer -Reviewed-by: Eric Blake -Tested-by: Eric Blake -Signed-off-by: Eric Blake -(cherry picked from commit 6384dd534d742123d26c008d9794b20bc41359d5) -Signed-off-by: Hanna Reitz ---- - tests/qemu-iotests/tests/block-status-cache | 139 ++++++++++++++++++ - .../qemu-iotests/tests/block-status-cache.out | 5 + - 2 files changed, 144 insertions(+) - create mode 100755 tests/qemu-iotests/tests/block-status-cache - create mode 100644 tests/qemu-iotests/tests/block-status-cache.out - -diff --git a/tests/qemu-iotests/tests/block-status-cache b/tests/qemu-iotests/tests/block-status-cache -new file mode 100755 -index 0000000000..6fa10bb8f8 ---- /dev/null -+++ b/tests/qemu-iotests/tests/block-status-cache -@@ -0,0 +1,139 @@ -+#!/usr/bin/env python3 -+# group: rw quick -+# -+# Test cases for the block-status cache. -+# -+# Copyright (C) 2022 Red Hat, Inc. -+# -+# This program is free software; you can redistribute it and/or modify -+# it under the terms of the GNU General Public License as published by -+# the Free Software Foundation; either version 2 of the License, or -+# (at your option) any later version. -+# -+# This program is distributed in the hope that it will be useful, -+# but WITHOUT ANY WARRANTY; without even the implied warranty of -+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -+# GNU General Public License for more details. -+# -+# You should have received a copy of the GNU General Public License -+# along with this program. If not, see . -+# -+ -+import os -+import signal -+import iotests -+from iotests import qemu_img_create, qemu_img_pipe, qemu_nbd -+ -+ -+image_size = 1 * 1024 * 1024 -+test_img = os.path.join(iotests.test_dir, 'test.img') -+ -+nbd_pidfile = os.path.join(iotests.test_dir, 'nbd.pid') -+nbd_sock = os.path.join(iotests.sock_dir, 'nbd.sock') -+ -+ -+class TestBscWithNbd(iotests.QMPTestCase): -+ def setUp(self) -> None: -+ """Just create an empty image with a read-only NBD server on it""" -+ assert qemu_img_create('-f', iotests.imgfmt, test_img, -+ str(image_size)) == 0 -+ -+ # Pass --allocation-depth to enable the qemu:allocation-depth context, -+ # which we are going to query to provoke a block-status inquiry with -+ # want_zero=false. -+ assert qemu_nbd(f'--socket={nbd_sock}', -+ f'--format={iotests.imgfmt}', -+ '--persistent', -+ '--allocation-depth', -+ '--read-only', -+ f'--pid-file={nbd_pidfile}', -+ test_img) \ -+ == 0 -+ -+ def tearDown(self) -> None: -+ with open(nbd_pidfile, encoding='utf-8') as f: -+ pid = int(f.read()) -+ os.kill(pid, signal.SIGTERM) -+ os.remove(nbd_pidfile) -+ os.remove(test_img) -+ -+ def test_with_zero_bug(self) -> None: -+ """ -+ Verify that the block-status cache is not corrupted by a -+ want_zero=false call. -+ We can provoke a want_zero=false call with `qemu-img map` over NBD with -+ x-dirty-bitmap=qemu:allocation-depth, so we first run a normal `map` -+ (which results in want_zero=true), then using said -+ qemu:allocation-depth context, and finally another normal `map` to -+ verify that the cache has not been corrupted. -+ """ -+ -+ nbd_img_opts = f'driver=nbd,server.type=unix,server.path={nbd_sock}' -+ nbd_img_opts_alloc_depth = nbd_img_opts + \ -+ ',x-dirty-bitmap=qemu:allocation-depth' -+ -+ # Normal map, results in want_zero=true. -+ # This will probably detect an allocated data sector first (qemu likes -+ # to allocate the first sector to facilitate alignment probing), and -+ # then the rest to be zero. The BSC will thus contain (if anything) -+ # one range covering the first sector. -+ map_pre = qemu_img_pipe('map', '--output=json', '--image-opts', -+ nbd_img_opts) -+ -+ # qemu:allocation-depth maps for want_zero=false. -+ # want_zero=false should (with the file driver, which the server is -+ # using) report everything as data. While this is sufficient for -+ # want_zero=false, this is nothing that should end up in the -+ # block-status cache. -+ # Due to a bug, this information did end up in the cache, though, and -+ # this would lead to wrong information being returned on subsequent -+ # want_zero=true calls. -+ # -+ # We need to run this map twice: On the first call, we probably still -+ # have the first sector in the cache, and so this will be served from -+ # the cache; and only the subsequent range will be queried from the -+ # block driver. This subsequent range will then be entered into the -+ # cache. -+ # If we did a want_zero=true call at this point, we would thus get -+ # correct information: The first sector is not covered by the cache, so -+ # we would get fresh block-status information from the driver, which -+ # would return a data range, and this would then go into the cache, -+ # evicting the wrong range from the want_zero=false call before. -+ # -+ # Therefore, we need a second want_zero=false map to reproduce: -+ # Since the first sector is not in the cache, the query for its status -+ # will go to the driver, which will return a result that reports the -+ # whole image to be a single data area. This result will then go into -+ # the cache, and so the cache will then report the whole image to -+ # contain data. -+ # -+ # Note that once the cache reports the whole image to contain data, any -+ # subsequent map operation will be served from the cache, and so we can -+ # never loop too many times here. -+ for _ in range(2): -+ # (Ignore the result, this is just to contaminate the cache) -+ qemu_img_pipe('map', '--output=json', '--image-opts', -+ nbd_img_opts_alloc_depth) -+ -+ # Now let's see whether the cache reports everything as data, or -+ # whether we get correct information (i.e. the same as we got on our -+ # first attempt). -+ map_post = qemu_img_pipe('map', '--output=json', '--image-opts', -+ nbd_img_opts) -+ -+ if map_pre != map_post: -+ print('ERROR: Map information differs before and after querying ' + -+ 'qemu:allocation-depth') -+ print('Before:') -+ print(map_pre) -+ print('After:') -+ print(map_post) -+ -+ self.fail("Map information differs") -+ -+ -+if __name__ == '__main__': -+ # The block-status cache only works on the protocol layer, so to test it, -+ # we can only use the raw format -+ iotests.main(supported_fmts=['raw'], -+ supported_protocols=['file']) -diff --git a/tests/qemu-iotests/tests/block-status-cache.out b/tests/qemu-iotests/tests/block-status-cache.out -new file mode 100644 -index 0000000000..ae1213e6f8 ---- /dev/null -+++ b/tests/qemu-iotests/tests/block-status-cache.out -@@ -0,0 +1,5 @@ -+. -+---------------------------------------------------------------------- -+Ran 1 tests -+ -+OK --- -2.27.0 - diff --git a/SOURCES/kvm-iotests-stream-error-on-reset-New-test.patch b/SOURCES/kvm-iotests-stream-error-on-reset-New-test.patch deleted file mode 100644 index cf69e38..0000000 --- a/SOURCES/kvm-iotests-stream-error-on-reset-New-test.patch +++ /dev/null @@ -1,196 +0,0 @@ -From 300f912d4a5afe4ecca9c68a71429fbc9966ec34 Mon Sep 17 00:00:00 2001 -From: Hanna Reitz -Date: Tue, 11 Jan 2022 15:36:13 +0000 -Subject: [PATCH 11/12] iotests/stream-error-on-reset: New test - -RH-Author: Hanna Reitz -RH-MergeRequest: 71: block-backend: prevent dangling BDS pointers across aio_poll() -RH-Commit: [2/2] 3167f31b91eb433f338564201f4ef336e39f7f7d (hreitz/qemu-kvm-c-9-s) -RH-Bugzilla: 2040123 -RH-Acked-by: Kevin Wolf -RH-Acked-by: Stefan Hajnoczi -RH-Acked-by: Emanuele Giuseppe Esposito - -Test the following scenario: -- Simple stream block in two-layer backing chain (base and top) -- The job is drained via blk_drain(), then an error occurs while the job - settles the ongoing request -- And so the job completes while in blk_drain() - -This was reported as a segfault, but is fixed by "block-backend: prevent -dangling BDS pointers across aio_poll()". - -Buglink: https://bugzilla.redhat.com/show_bug.cgi?id=2036178 -Signed-off-by: Hanna Reitz -Signed-off-by: Stefan Hajnoczi -Message-Id: <20220111153613.25453-3-stefanha@redhat.com> -Signed-off-by: Kevin Wolf -(cherry picked from commit 2ca1d5d6b91f8a52a5c651f660b2f58c94bf97ba) -Signed-off-by: Hanna Reitz ---- - .../qemu-iotests/tests/stream-error-on-reset | 140 ++++++++++++++++++ - .../tests/stream-error-on-reset.out | 5 + - 2 files changed, 145 insertions(+) - create mode 100755 tests/qemu-iotests/tests/stream-error-on-reset - create mode 100644 tests/qemu-iotests/tests/stream-error-on-reset.out - -diff --git a/tests/qemu-iotests/tests/stream-error-on-reset b/tests/qemu-iotests/tests/stream-error-on-reset -new file mode 100755 -index 0000000000..7eaedb24d7 ---- /dev/null -+++ b/tests/qemu-iotests/tests/stream-error-on-reset -@@ -0,0 +1,140 @@ -+#!/usr/bin/env python3 -+# group: rw quick -+# -+# Test what happens when a stream job completes in a blk_drain(). -+# -+# Copyright (C) 2022 Red Hat, Inc. -+# -+# This program is free software; you can redistribute it and/or modify -+# it under the terms of the GNU General Public License as published by -+# the Free Software Foundation; either version 2 of the License, or -+# (at your option) any later version. -+# -+# This program is distributed in the hope that it will be useful, -+# but WITHOUT ANY WARRANTY; without even the implied warranty of -+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -+# GNU General Public License for more details. -+# -+# You should have received a copy of the GNU General Public License -+# along with this program. If not, see . -+# -+ -+import os -+import iotests -+from iotests import imgfmt, qemu_img_create, qemu_io_silent, QMPTestCase -+ -+ -+image_size = 1 * 1024 * 1024 -+data_size = 64 * 1024 -+base = os.path.join(iotests.test_dir, 'base.img') -+top = os.path.join(iotests.test_dir, 'top.img') -+ -+ -+# We want to test completing a stream job in a blk_drain(). -+# -+# The blk_drain() we are going to use is a virtio-scsi device resetting, -+# which we can trigger by resetting the system. -+# -+# In order to have the block job complete on drain, we (1) throttle its -+# base image so we can start the drain after it has begun, but before it -+# completes, and (2) make it encounter an I/O error on the ensuing write. -+# (If it completes regularly, the completion happens after the drain for -+# some reason.) -+ -+class TestStreamErrorOnReset(QMPTestCase): -+ def setUp(self) -> None: -+ """ -+ Create two images: -+ - base image {base} with {data_size} bytes allocated -+ - top image {top} without any data allocated -+ -+ And the following VM configuration: -+ - base image throttled to {data_size} -+ - top image with a blkdebug configuration so the first write access -+ to it will result in an error -+ - top image is attached to a virtio-scsi device -+ """ -+ assert qemu_img_create('-f', imgfmt, base, str(image_size)) == 0 -+ assert qemu_io_silent('-c', f'write 0 {data_size}', base) == 0 -+ assert qemu_img_create('-f', imgfmt, top, str(image_size)) == 0 -+ -+ self.vm = iotests.VM() -+ self.vm.add_args('-accel', 'tcg') # Make throttling work properly -+ self.vm.add_object(self.vm.qmp_to_opts({ -+ 'qom-type': 'throttle-group', -+ 'id': 'thrgr', -+ 'x-bps-total': str(data_size) -+ })) -+ self.vm.add_blockdev(self.vm.qmp_to_opts({ -+ 'driver': imgfmt, -+ 'node-name': 'base', -+ 'file': { -+ 'driver': 'throttle', -+ 'throttle-group': 'thrgr', -+ 'file': { -+ 'driver': 'file', -+ 'filename': base -+ } -+ } -+ })) -+ self.vm.add_blockdev(self.vm.qmp_to_opts({ -+ 'driver': imgfmt, -+ 'node-name': 'top', -+ 'file': { -+ 'driver': 'blkdebug', -+ 'node-name': 'top-blkdebug', -+ 'inject-error': [{ -+ 'event': 'pwritev', -+ 'immediately': 'true', -+ 'once': 'true' -+ }], -+ 'image': { -+ 'driver': 'file', -+ 'filename': top -+ } -+ }, -+ 'backing': 'base' -+ })) -+ self.vm.add_device(self.vm.qmp_to_opts({ -+ 'driver': 'virtio-scsi', -+ 'id': 'vscsi' -+ })) -+ self.vm.add_device(self.vm.qmp_to_opts({ -+ 'driver': 'scsi-hd', -+ 'bus': 'vscsi.0', -+ 'drive': 'top' -+ })) -+ self.vm.launch() -+ -+ def tearDown(self) -> None: -+ self.vm.shutdown() -+ os.remove(top) -+ os.remove(base) -+ -+ def test_stream_error_on_reset(self) -> None: -+ # Launch a stream job, which will take at least a second to -+ # complete, because the base image is throttled (so we can -+ # get in between it having started and it having completed) -+ res = self.vm.qmp('block-stream', job_id='stream', device='top') -+ self.assert_qmp(res, 'return', {}) -+ -+ while True: -+ ev = self.vm.event_wait('JOB_STATUS_CHANGE') -+ if ev['data']['status'] == 'running': -+ # Once the stream job is running, reset the system, which -+ # forces the virtio-scsi device to be reset, thus draining -+ # the stream job, and making it complete. Completing -+ # inside of that drain should not result in a segfault. -+ res = self.vm.qmp('system_reset') -+ self.assert_qmp(res, 'return', {}) -+ elif ev['data']['status'] == 'null': -+ # The test is done once the job is gone -+ break -+ -+ -+if __name__ == '__main__': -+ # Passes with any format with backing file support, but qed and -+ # qcow1 do not seem to exercise the used-to-be problematic code -+ # path, so there is no point in having them in this list -+ iotests.main(supported_fmts=['qcow2', 'vmdk'], -+ supported_protocols=['file']) -diff --git a/tests/qemu-iotests/tests/stream-error-on-reset.out b/tests/qemu-iotests/tests/stream-error-on-reset.out -new file mode 100644 -index 0000000000..ae1213e6f8 ---- /dev/null -+++ b/tests/qemu-iotests/tests/stream-error-on-reset.out -@@ -0,0 +1,5 @@ -+. -+---------------------------------------------------------------------- -+Ran 1 tests -+ -+OK --- -2.27.0 - diff --git a/SOURCES/kvm-iotests.py-Add-QemuStorageDaemon-class.patch b/SOURCES/kvm-iotests.py-Add-QemuStorageDaemon-class.patch deleted file mode 100644 index b215d23..0000000 --- a/SOURCES/kvm-iotests.py-Add-QemuStorageDaemon-class.patch +++ /dev/null @@ -1,92 +0,0 @@ -From c21502a220d107261c9a8627158f357489d86543 Mon Sep 17 00:00:00 2001 -From: Hanna Reitz -Date: Fri, 4 Feb 2022 12:10:09 +0100 -Subject: [PATCH 5/8] iotests.py: Add QemuStorageDaemon class - -RH-Author: Hanna Reitz -RH-MergeRequest: 74: block/nbd: Handle AioContext changes -RH-Commit: [3/6] 5da1cda4d025c1bd7029ed8071b4ccf25459a878 (hreitz/qemu-kvm-c-9-s) -RH-Bugzilla: 2033626 -RH-Acked-by: Miroslav Rezanina -RH-Acked-by: Eric Blake -RH-Acked-by: Stefan Hajnoczi - -This is a rather simple class that allows creating a QSD instance -running in the background and stopping it when no longer needed. - -The __del__ handler is a safety net for when something goes so wrong in -a test that e.g. the tearDown() method is not called (e.g. setUp() -launches the QSD, but then launching a VM fails). We do not want the -QSD to continue running after the test has failed, so __del__() will -take care to kill it. - -Reviewed-by: Vladimir Sementsov-Ogievskiy -Signed-off-by: Hanna Reitz -Signed-off-by: Vladimir Sementsov-Ogievskiy -(cherry picked from commit 091dc7b2b5553a529bff9a7bf9ad3bc85bc5bdcd) -Signed-off-by: Hanna Reitz ---- - tests/qemu-iotests/iotests.py | 40 +++++++++++++++++++++++++++++++++++ - 1 file changed, 40 insertions(+) - -diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py -index 83bfedb902..a51b5ce8cd 100644 ---- a/tests/qemu-iotests/iotests.py -+++ b/tests/qemu-iotests/iotests.py -@@ -72,6 +72,8 @@ - qemu_prog = os.environ.get('QEMU_PROG', 'qemu') - qemu_opts = os.environ.get('QEMU_OPTIONS', '').strip().split(' ') - -+qsd_prog = os.environ.get('QSD_PROG', 'qemu-storage-daemon') -+ - gdb_qemu_env = os.environ.get('GDB_OPTIONS') - qemu_gdb = [] - if gdb_qemu_env: -@@ -312,6 +314,44 @@ def cmd(self, cmd): - return self._read_output() - - -+class QemuStorageDaemon: -+ def __init__(self, *args: str, instance_id: str = 'a'): -+ assert '--pidfile' not in args -+ self.pidfile = os.path.join(test_dir, f'qsd-{instance_id}-pid') -+ all_args = [qsd_prog] + list(args) + ['--pidfile', self.pidfile] -+ -+ # Cannot use with here, we want the subprocess to stay around -+ # pylint: disable=consider-using-with -+ self._p = subprocess.Popen(all_args) -+ while not os.path.exists(self.pidfile): -+ if self._p.poll() is not None: -+ cmd = ' '.join(all_args) -+ raise RuntimeError( -+ 'qemu-storage-daemon terminated with exit code ' + -+ f'{self._p.returncode}: {cmd}') -+ -+ time.sleep(0.01) -+ -+ with open(self.pidfile, encoding='utf-8') as f: -+ self._pid = int(f.read().strip()) -+ -+ assert self._pid == self._p.pid -+ -+ def stop(self, kill_signal=15): -+ self._p.send_signal(kill_signal) -+ self._p.wait() -+ self._p = None -+ -+ try: -+ os.remove(self.pidfile) -+ except OSError: -+ pass -+ -+ def __del__(self): -+ if self._p is not None: -+ self.stop(kill_signal=9) -+ -+ - def qemu_nbd(*args): - '''Run qemu-nbd in daemon mode and return the parent's exit code''' - return subprocess.call(qemu_nbd_args + ['--fork'] + list(args)) --- -2.27.0 - diff --git a/SOURCES/kvm-kvm-don-t-use-perror-without-useful-errno.patch b/SOURCES/kvm-kvm-don-t-use-perror-without-useful-errno.patch new file mode 100644 index 0000000..a78c089 --- /dev/null +++ b/SOURCES/kvm-kvm-don-t-use-perror-without-useful-errno.patch @@ -0,0 +1,62 @@ +From 9ddefaedf423ec03eadaf17496c14e0d7b2381c8 Mon Sep 17 00:00:00 2001 +From: Cornelia Huck +Date: Thu, 28 Jul 2022 16:24:46 +0200 +Subject: [PATCH 30/32] kvm: don't use perror() without useful errno + +RH-Author: Cornelia Huck +RH-MergeRequest: 110: kvm: don't use perror() without useful errno +RH-Commit: [1/1] 20e51aac6767c1f89f74c7d692d1fb7689eff5f0 (cohuck/qemu-kvm-c9s) +RH-Bugzilla: 2095608 +RH-Acked-by: Eric Auger +RH-Acked-by: Thomas Huth +RH-Acked-by: Gavin Shan + +perror() is designed to append the decoded errno value to a +string. This, however, only makes sense if we called something that +actually sets errno prior to that. + +For the callers that check for split irqchip support that is not the +case, and we end up with confusing error messages that end in +"success". Use error_report() instead. + +Signed-off-by: Cornelia Huck +Message-Id: <20220728142446.438177-1-cohuck@redhat.com> +Signed-off-by: Paolo Bonzini + +https://bugzilla.redhat.com/show_bug.cgi?id=2095608 +(cherry picked from commit 47c182fe8b03c0c40059fb95840923e65c9bdb4f) +Signed-off-by: Cornelia Huck +--- + accel/kvm/kvm-all.c | 2 +- + target/arm/kvm.c | 2 +- + 2 files changed, 2 insertions(+), 2 deletions(-) + +diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c +index 5f1377ca04..e9c7947640 100644 +--- a/accel/kvm/kvm-all.c ++++ b/accel/kvm/kvm-all.c +@@ -2254,7 +2254,7 @@ static void kvm_irqchip_create(KVMState *s) + ret = kvm_arch_irqchip_create(s); + if (ret == 0) { + if (s->kernel_irqchip_split == ON_OFF_AUTO_ON) { +- perror("Split IRQ chip mode not supported."); ++ error_report("Split IRQ chip mode not supported."); + exit(1); + } else { + ret = kvm_vm_ioctl(s, KVM_CREATE_IRQCHIP); +diff --git a/target/arm/kvm.c b/target/arm/kvm.c +index bbf1ce7ba3..0a2ba1f8e3 100644 +--- a/target/arm/kvm.c ++++ b/target/arm/kvm.c +@@ -960,7 +960,7 @@ void kvm_arch_init_irq_routing(KVMState *s) + int kvm_arch_irqchip_create(KVMState *s) + { + if (kvm_kernel_irqchip_split()) { +- perror("-machine kernel_irqchip=split is not supported on ARM."); ++ error_report("-machine kernel_irqchip=split is not supported on ARM."); + exit(1); + } + +-- +2.31.1 + diff --git a/SOURCES/kvm-linux-aio-explain-why-max-batch-is-checked-in-laio_i.patch b/SOURCES/kvm-linux-aio-explain-why-max-batch-is-checked-in-laio_i.patch index cc90e17..f12b8ec 100644 --- a/SOURCES/kvm-linux-aio-explain-why-max-batch-is-checked-in-laio_i.patch +++ b/SOURCES/kvm-linux-aio-explain-why-max-batch-is-checked-in-laio_i.patch @@ -1,17 +1,16 @@ -From 0cd0c916715c43f71cf249bafa2829b42aa67267 Mon Sep 17 00:00:00 2001 +From 49d9c9dced7278517105e9cfec34ea4af716432d Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Thu, 9 Jun 2022 17:47:12 +0100 -Subject: [PATCH 2/2] linux-aio: explain why max batch is checked in +Subject: [PATCH 6/6] linux-aio: explain why max batch is checked in laio_io_unplug() RH-Author: Stefan Hajnoczi -RH-MergeRequest: 210: linux-aio: fix unbalanced plugged counter in laio_io_unplug() -RH-Bugzilla: 2109569 -RH-Acked-by: Hanna Reitz +RH-MergeRequest: 102: linux-aio: fix unbalanced plugged counter in laio_io_unplug() +RH-Commit: [2/2] b3d6421086bde50d4baad2343b2df89c5f66950e (stefanha/centos-stream-qemu-kvm) +RH-Bugzilla: 2092788 +RH-Acked-by: Miroslav Rezanina RH-Acked-by: Kevin Wolf RH-Acked-by: Stefano Garzarella -RH-Acked-by: Alberto Faria -RH-Commit: [2/2] caed03e006e8004d3c0670b24e4454a94274d7d9 It may not be obvious why laio_io_unplug() checks max batch. I discussed this with Stefano and have added a comment summarizing the reason. @@ -29,10 +28,10 @@ Signed-off-by: Stefan Hajnoczi 1 file changed, 6 insertions(+) diff --git a/block/linux-aio.c b/block/linux-aio.c -index 77f17ad596..85650c4222 100644 +index 6078da7e42..9c2393a2f7 100644 --- a/block/linux-aio.c +++ b/block/linux-aio.c -@@ -362,6 +362,12 @@ void laio_io_unplug(BlockDriverState *bs, LinuxAioState *s, +@@ -365,6 +365,12 @@ void laio_io_unplug(BlockDriverState *bs, LinuxAioState *s, assert(s->io_q.plugged); s->io_q.plugged--; diff --git a/SOURCES/kvm-linux-aio-fix-unbalanced-plugged-counter-in-laio_io_.patch b/SOURCES/kvm-linux-aio-fix-unbalanced-plugged-counter-in-laio_io_.patch index f583f3e..ed9b5ee 100644 --- a/SOURCES/kvm-linux-aio-fix-unbalanced-plugged-counter-in-laio_io_.patch +++ b/SOURCES/kvm-linux-aio-fix-unbalanced-plugged-counter-in-laio_io_.patch @@ -1,17 +1,16 @@ -From 9c5a68878b3c6ec16c94dfcfe388a830df8deb2f Mon Sep 17 00:00:00 2001 +From e7326c3a7e0fc022aa5c0ae07bc1e19ad1b6f2ed Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Thu, 9 Jun 2022 17:47:11 +0100 -Subject: [PATCH 1/2] linux-aio: fix unbalanced plugged counter in +Subject: [PATCH 5/6] linux-aio: fix unbalanced plugged counter in laio_io_unplug() RH-Author: Stefan Hajnoczi -RH-MergeRequest: 210: linux-aio: fix unbalanced plugged counter in laio_io_unplug() -RH-Bugzilla: 2109569 -RH-Acked-by: Hanna Reitz +RH-MergeRequest: 102: linux-aio: fix unbalanced plugged counter in laio_io_unplug() +RH-Commit: [1/2] 8a71da371c72521f1d70b8767ee564575e0d522b (stefanha/centos-stream-qemu-kvm) +RH-Bugzilla: 2092788 +RH-Acked-by: Miroslav Rezanina RH-Acked-by: Kevin Wolf RH-Acked-by: Stefano Garzarella -RH-Acked-by: Alberto Faria -RH-Commit: [1/2] bc1fa9b401cffb712f09935aba861d1a0bf74421 Every laio_io_plug() call has a matching laio_io_unplug() call. There is a plugged counter that tracks the number of levels of plugging and @@ -37,10 +36,10 @@ Signed-off-by: Stefan Hajnoczi 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/block/linux-aio.c b/block/linux-aio.c -index f53ae72e21..77f17ad596 100644 +index 4c423fcccf..6078da7e42 100644 --- a/block/linux-aio.c +++ b/block/linux-aio.c -@@ -360,8 +360,10 @@ void laio_io_unplug(BlockDriverState *bs, LinuxAioState *s, +@@ -363,8 +363,10 @@ void laio_io_unplug(BlockDriverState *bs, LinuxAioState *s, uint64_t dev_max_batch) { assert(s->io_q.plugged); diff --git a/SOURCES/kvm-memory-Fix-incorrect-calls-of-log_global_start-stop.patch b/SOURCES/kvm-memory-Fix-incorrect-calls-of-log_global_start-stop.patch deleted file mode 100644 index 5ff2734..0000000 --- a/SOURCES/kvm-memory-Fix-incorrect-calls-of-log_global_start-stop.patch +++ /dev/null @@ -1,97 +0,0 @@ -From b169059c8fbf15c3ffeec0f68b938cb9febd8db7 Mon Sep 17 00:00:00 2001 -From: Peter Xu -Date: Tue, 30 Nov 2021 16:00:28 +0800 -Subject: [PATCH 5/6] memory: Fix incorrect calls of log_global_start/stop -MIME-Version: 1.0 -Content-Type: text/plain; charset=UTF-8 -Content-Transfer-Encoding: 8bit - -RH-Author: Peter Xu -RH-MergeRequest: 77: memory: Fix qemu crash on continuous migrations of stopped VM -RH-Commit: [1/2] 6271ee689266b24d29d4c87f60e5b096ef5f5d63 (peterx/qemu-kvm) -RH-Bugzilla: 2044818 -RH-Acked-by: Paolo Bonzini -RH-Acked-by: David Hildenbrand -RH-Acked-by: quintela1 - -We should only call the log_global_start/stop when the global dirty track -bitmask changes from zero<->non-zero. - -No real issue reported for this yet probably because no immediate user to -enable both dirty rate measurement and migration at the same time. However -it'll be good to be prepared for it. - -Fixes: 63b41db4bc ("memory: make global_dirty_tracking a bitmask") -Cc: qemu-stable@nongnu.org -Cc: Hyman Huang -Cc: Paolo Bonzini -Cc: Dr. David Alan Gilbert -Cc: Juan Quintela -Cc: David Hildenbrand -Signed-off-by: Peter Xu -Reviewed-by: David Hildenbrand -Message-Id: <20211130080028.6474-1-peterx@redhat.com> -Signed-off-by: Philippe Mathieu-Daudé -(cherry picked from commit 7b0538ed3a22ce30817f818449d10701fb0821f9) -Signed-off-by: Peter Xu ---- - softmmu/memory.c | 27 ++++++++++++++------------- - 1 file changed, 14 insertions(+), 13 deletions(-) - -diff --git a/softmmu/memory.c b/softmmu/memory.c -index 7340e19ff5..81d4bf1454 100644 ---- a/softmmu/memory.c -+++ b/softmmu/memory.c -@@ -2773,6 +2773,8 @@ static VMChangeStateEntry *vmstate_change; - - void memory_global_dirty_log_start(unsigned int flags) - { -+ unsigned int old_flags = global_dirty_tracking; -+ - if (vmstate_change) { - qemu_del_vm_change_state_handler(vmstate_change); - vmstate_change = NULL; -@@ -2781,15 +2783,14 @@ void memory_global_dirty_log_start(unsigned int flags) - assert(flags && !(flags & (~GLOBAL_DIRTY_MASK))); - assert(!(global_dirty_tracking & flags)); - global_dirty_tracking |= flags; -- - trace_global_dirty_changed(global_dirty_tracking); - -- MEMORY_LISTENER_CALL_GLOBAL(log_global_start, Forward); -- -- /* Refresh DIRTY_MEMORY_MIGRATION bit. */ -- memory_region_transaction_begin(); -- memory_region_update_pending = true; -- memory_region_transaction_commit(); -+ if (!old_flags) { -+ MEMORY_LISTENER_CALL_GLOBAL(log_global_start, Forward); -+ memory_region_transaction_begin(); -+ memory_region_update_pending = true; -+ memory_region_transaction_commit(); -+ } - } - - static void memory_global_dirty_log_do_stop(unsigned int flags) -@@ -2800,12 +2801,12 @@ static void memory_global_dirty_log_do_stop(unsigned int flags) - - trace_global_dirty_changed(global_dirty_tracking); - -- /* Refresh DIRTY_MEMORY_MIGRATION bit. */ -- memory_region_transaction_begin(); -- memory_region_update_pending = true; -- memory_region_transaction_commit(); -- -- MEMORY_LISTENER_CALL_GLOBAL(log_global_stop, Reverse); -+ if (!global_dirty_tracking) { -+ memory_region_transaction_begin(); -+ memory_region_update_pending = true; -+ memory_region_transaction_commit(); -+ MEMORY_LISTENER_CALL_GLOBAL(log_global_stop, Reverse); -+ } - } - - static void memory_vm_change_state_handler(void *opaque, bool running, --- -2.27.0 - diff --git a/SOURCES/kvm-memory-Fix-qemu-crash-on-starting-dirty-log-twice-wi.patch b/SOURCES/kvm-memory-Fix-qemu-crash-on-starting-dirty-log-twice-wi.patch deleted file mode 100644 index 5ea0007..0000000 --- a/SOURCES/kvm-memory-Fix-qemu-crash-on-starting-dirty-log-twice-wi.patch +++ /dev/null @@ -1,156 +0,0 @@ -From b3ed8e344c733bc8c2223c1b9e424a9fbcea56d4 Mon Sep 17 00:00:00 2001 -From: Peter Xu -Date: Mon, 7 Feb 2022 20:30:19 +0800 -Subject: [PATCH 6/6] memory: Fix qemu crash on starting dirty log twice with - stopped VM - -RH-Author: Peter Xu -RH-MergeRequest: 77: memory: Fix qemu crash on continuous migrations of stopped VM -RH-Commit: [2/2] 98ed2ef6226ec80a1896ebb554015aded0dc0c18 (peterx/qemu-kvm) -RH-Bugzilla: 2044818 -RH-Acked-by: Paolo Bonzini -RH-Acked-by: David Hildenbrand -RH-Acked-by: quintela1 - -QEMU can now easily crash with two continuous migration carried out: - -(qemu) migrate -d exec:cat>out -(qemu) migrate_cancel -(qemu) migrate -d exec:cat>out -[crash] ../softmmu/memory.c:2782: memory_global_dirty_log_start: Assertion -`!(global_dirty_tracking & flags)' failed. - -It's because memory API provides a way to postpone dirty log stop if the VM is -stopped, and that'll be re-done until the next VM start. It was added in 2017 -with commit 1931076077 ("migration: optimize the downtime", 2017-08-01). - -However the recent work on allowing dirty tracking to be bitmask broke it, -which is commit 63b41db4bc ("memory: make global_dirty_tracking a bitmask", -2021-11-01). - -The fix proposed in this patch contains two things: - - (1) Instead of passing over the flags to postpone stop dirty track, we add a - global variable (along with current vmstate_change variable) to record - what flags to stop dirty tracking. - - (2) When start dirty tracking, instead if remove the vmstate hook directly, - we also execute the postponed stop process so that we make sure all the - starts and stops will be paired. - -This procedure is overlooked in the bitmask-ify work in 2021. - -Cc: Hyman Huang -Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2044818 -Fixes: 63b41db4bc ("memory: make global_dirty_tracking a bitmask") -Signed-off-by: Peter Xu -Message-Id: <20220207123019.27223-1-peterx@redhat.com> -Signed-off-by: Paolo Bonzini -(cherry picked from commit a5c90c61a118027b86155cffdf4fe4e2e9de1020) -Signed-off-by: Peter Xu ---- - softmmu/memory.c | 61 +++++++++++++++++++++++++++++++++++------------- - 1 file changed, 45 insertions(+), 16 deletions(-) - -diff --git a/softmmu/memory.c b/softmmu/memory.c -index 81d4bf1454..0311e362ee 100644 ---- a/softmmu/memory.c -+++ b/softmmu/memory.c -@@ -2769,19 +2769,32 @@ void memory_global_after_dirty_log_sync(void) - MEMORY_LISTENER_CALL_GLOBAL(log_global_after_sync, Forward); - } - -+/* -+ * Dirty track stop flags that are postponed due to VM being stopped. Should -+ * only be used within vmstate_change hook. -+ */ -+static unsigned int postponed_stop_flags; - static VMChangeStateEntry *vmstate_change; -+static void memory_global_dirty_log_stop_postponed_run(void); - - void memory_global_dirty_log_start(unsigned int flags) - { -- unsigned int old_flags = global_dirty_tracking; -+ unsigned int old_flags; -+ -+ assert(flags && !(flags & (~GLOBAL_DIRTY_MASK))); - - if (vmstate_change) { -- qemu_del_vm_change_state_handler(vmstate_change); -- vmstate_change = NULL; -+ /* If there is postponed stop(), operate on it first */ -+ postponed_stop_flags &= ~flags; -+ memory_global_dirty_log_stop_postponed_run(); - } - -- assert(flags && !(flags & (~GLOBAL_DIRTY_MASK))); -- assert(!(global_dirty_tracking & flags)); -+ flags &= ~global_dirty_tracking; -+ if (!flags) { -+ return; -+ } -+ -+ old_flags = global_dirty_tracking; - global_dirty_tracking |= flags; - trace_global_dirty_changed(global_dirty_tracking); - -@@ -2809,29 +2822,45 @@ static void memory_global_dirty_log_do_stop(unsigned int flags) - } - } - -+/* -+ * Execute the postponed dirty log stop operations if there is, then reset -+ * everything (including the flags and the vmstate change hook). -+ */ -+static void memory_global_dirty_log_stop_postponed_run(void) -+{ -+ /* This must be called with the vmstate handler registered */ -+ assert(vmstate_change); -+ -+ /* Note: postponed_stop_flags can be cleared in log start routine */ -+ if (postponed_stop_flags) { -+ memory_global_dirty_log_do_stop(postponed_stop_flags); -+ postponed_stop_flags = 0; -+ } -+ -+ qemu_del_vm_change_state_handler(vmstate_change); -+ vmstate_change = NULL; -+} -+ - static void memory_vm_change_state_handler(void *opaque, bool running, - RunState state) - { -- unsigned int flags = (unsigned int)(uintptr_t)opaque; - if (running) { -- memory_global_dirty_log_do_stop(flags); -- -- if (vmstate_change) { -- qemu_del_vm_change_state_handler(vmstate_change); -- vmstate_change = NULL; -- } -+ memory_global_dirty_log_stop_postponed_run(); - } - } - - void memory_global_dirty_log_stop(unsigned int flags) - { - if (!runstate_is_running()) { -+ /* Postpone the dirty log stop, e.g., to when VM starts again */ - if (vmstate_change) { -- return; -+ /* Batch with previous postponed flags */ -+ postponed_stop_flags |= flags; -+ } else { -+ postponed_stop_flags = flags; -+ vmstate_change = qemu_add_vm_change_state_handler( -+ memory_vm_change_state_handler, NULL); - } -- vmstate_change = qemu_add_vm_change_state_handler( -- memory_vm_change_state_handler, -- (void *)(uintptr_t)flags); - return; - } - --- -2.27.0 - diff --git a/SOURCES/kvm-meson-create-have_vhost_-variables.patch b/SOURCES/kvm-meson-create-have_vhost_-variables.patch new file mode 100644 index 0000000..fcae620 --- /dev/null +++ b/SOURCES/kvm-meson-create-have_vhost_-variables.patch @@ -0,0 +1,154 @@ +From 51c310097832724bafac26aed81399da40128400 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Thu, 21 Jul 2022 15:50:43 +0200 +Subject: [PATCH 05/32] meson: create have_vhost_* variables +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 108: Net Control Virtqueue shadow Support +RH-Commit: [5/27] 3b30f89e6d639923dc9d9a92a4261bb4509e5c83 (eperezmartin/qemu-kvm) +RH-Bugzilla: 1939363 +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Cindy Lu +RH-Acked-by: Laurent Vivier + +Bugzilla: https://bugzilla.redhat.com/1939363 + +Upstream Status: git://git.qemu.org/qemu.git + +commit 2a3129a37652e5e81d12f6e16dd3c447f09831f9 +Author: Paolo Bonzini +Date: Wed Apr 20 17:34:05 2022 +0200 + + meson: create have_vhost_* variables + + When using Meson options rather than config-host.h, the "when" clauses + have to be changed to if statements (which is not necessarily great, + though at least it highlights which parts of the build are per-target + and which are not). + + Do that before moving vhost logic to meson.build, though for now + the variables are just based on config-host.mak data. + + Reviewed-by: Marc-André Lureau + Signed-off-by: Paolo Bonzini + +Signed-off-by: Eugenio Pérez +--- + meson.build | 30 ++++++++++++++++++++---------- + tests/meson.build | 2 +- + tools/meson.build | 2 +- + 3 files changed, 22 insertions(+), 12 deletions(-) + +diff --git a/meson.build b/meson.build +index 13e3323380..735f538497 100644 +--- a/meson.build ++++ b/meson.build +@@ -298,6 +298,15 @@ have_tpm = get_option('tpm') \ + .require(targetos != 'windows', error_message: 'TPM emulation only available on POSIX systems') \ + .allowed() + ++# vhost ++have_vhost_user = 'CONFIG_VHOST_USER' in config_host ++have_vhost_vdpa = 'CONFIG_VHOST_VDPA' in config_host ++have_vhost_kernel = 'CONFIG_VHOST_KERNEL' in config_host ++have_vhost_net_user = 'CONFIG_VHOST_NET_USER' in config_host ++have_vhost_net_vdpa = 'CONFIG_VHOST_NET_VDPA' in config_host ++have_vhost_net = 'CONFIG_VHOST_NET' in config_host ++have_vhost_user_crypto = 'CONFIG_VHOST_CRYPTO' in config_host ++ + # Target-specific libraries and flags + libm = cc.find_library('m', required: false) + threads = dependency('threads') +@@ -1335,7 +1344,7 @@ has_statx_mnt_id = cc.links(statx_mnt_id_test) + have_vhost_user_blk_server = get_option('vhost_user_blk_server') \ + .require(targetos == 'linux', + error_message: 'vhost_user_blk_server requires linux') \ +- .require('CONFIG_VHOST_USER' in config_host, ++ .require(have_vhost_user, + error_message: 'vhost_user_blk_server requires vhost-user support') \ + .disable_auto_if(not have_system) \ + .allowed() +@@ -2116,9 +2125,9 @@ host_kconfig = \ + (have_ivshmem ? ['CONFIG_IVSHMEM=y'] : []) + \ + ('CONFIG_OPENGL' in config_host ? ['CONFIG_OPENGL=y'] : []) + \ + (x11.found() ? ['CONFIG_X11=y'] : []) + \ +- ('CONFIG_VHOST_USER' in config_host ? ['CONFIG_VHOST_USER=y'] : []) + \ +- ('CONFIG_VHOST_VDPA' in config_host ? ['CONFIG_VHOST_VDPA=y'] : []) + \ +- ('CONFIG_VHOST_KERNEL' in config_host ? ['CONFIG_VHOST_KERNEL=y'] : []) + \ ++ (have_vhost_user ? ['CONFIG_VHOST_USER=y'] : []) + \ ++ (have_vhost_vdpa ? ['CONFIG_VHOST_VDPA=y'] : []) + \ ++ (have_vhost_kernel ? ['CONFIG_VHOST_KERNEL=y'] : []) + \ + (have_virtfs ? ['CONFIG_VIRTFS=y'] : []) + \ + ('CONFIG_LINUX' in config_host ? ['CONFIG_LINUX=y'] : []) + \ + ('CONFIG_PVRDMA' in config_host ? ['CONFIG_PVRDMA=y'] : []) + \ +@@ -2799,7 +2808,7 @@ if have_system or have_user + endif + + vhost_user = not_found +-if targetos == 'linux' and 'CONFIG_VHOST_USER' in config_host ++if targetos == 'linux' and have_vhost_user + libvhost_user = subproject('libvhost-user') + vhost_user = libvhost_user.get_variable('vhost_user_dep') + endif +@@ -3386,7 +3395,7 @@ if have_tools + dependencies: qemuutil, + install: true) + +- if 'CONFIG_VHOST_USER' in config_host ++ if have_vhost_user + subdir('contrib/vhost-user-blk') + subdir('contrib/vhost-user-gpu') + subdir('contrib/vhost-user-input') +@@ -3516,15 +3525,16 @@ if 'simple' in get_option('trace_backends') + endif + summary_info += {'D-Bus display': dbus_display} + summary_info += {'QOM debugging': get_option('qom_cast_debug')} +-summary_info += {'vhost-kernel support': config_host.has_key('CONFIG_VHOST_KERNEL')} +-summary_info += {'vhost-net support': config_host.has_key('CONFIG_VHOST_NET')} +-summary_info += {'vhost-crypto support': config_host.has_key('CONFIG_VHOST_CRYPTO')} ++summary_info += {'vhost-kernel support': have_vhost_kernel} ++summary_info += {'vhost-net support': have_vhost_net} ++summary_info += {'vhost-user support': have_vhost_user} ++summary_info += {'vhost-user-crypto support': have_vhost_user_crypto} + summary_info += {'vhost-scsi support': config_host.has_key('CONFIG_VHOST_SCSI')} + summary_info += {'vhost-vsock support': config_host.has_key('CONFIG_VHOST_VSOCK')} +-summary_info += {'vhost-user support': config_host.has_key('CONFIG_VHOST_USER')} + summary_info += {'vhost-user-blk server support': have_vhost_user_blk_server} + summary_info += {'vhost-user-fs support': config_host.has_key('CONFIG_VHOST_USER_FS')} + summary_info += {'vhost-vdpa support': config_host.has_key('CONFIG_VHOST_VDPA')} ++summary_info += {'vhost-vdpa support': have_vhost_vdpa} + summary_info += {'build guest agent': have_ga} + summary(summary_info, bool_yn: true, section: 'Configurable features') + +diff --git a/tests/meson.build b/tests/meson.build +index 1d05109eb4..bbe41c8559 100644 +--- a/tests/meson.build ++++ b/tests/meson.build +@@ -70,7 +70,7 @@ test_deps = { + 'test-qht-par': qht_bench, + } + +-if have_tools and 'CONFIG_VHOST_USER' in config_host and 'CONFIG_LINUX' in config_host ++if have_tools and have_vhost_user and 'CONFIG_LINUX' in config_host + executable('vhost-user-bridge', + sources: files('vhost-user-bridge.c'), + dependencies: [qemuutil, vhost_user]) +diff --git a/tools/meson.build b/tools/meson.build +index 46977af84f..10eb3a043f 100644 +--- a/tools/meson.build ++++ b/tools/meson.build +@@ -3,7 +3,7 @@ have_virtiofsd = get_option('virtiofsd') \ + error_message: 'virtiofsd requires Linux') \ + .require(seccomp.found() and libcap_ng.found(), + error_message: 'virtiofsd requires libcap-ng-devel and seccomp-devel') \ +- .require('CONFIG_VHOST_USER' in config_host, ++ .require(have_vhost_user, + error_message: 'virtiofsd needs vhost-user-support') \ + .disable_auto_if(not have_tools and not have_system) \ + .allowed() +-- +2.31.1 + diff --git a/SOURCES/kvm-meson-use-have_vhost_-variables-to-pick-sources.patch b/SOURCES/kvm-meson-use-have_vhost_-variables-to-pick-sources.patch new file mode 100644 index 0000000..99d86c1 --- /dev/null +++ b/SOURCES/kvm-meson-use-have_vhost_-variables-to-pick-sources.patch @@ -0,0 +1,213 @@ +From a7d57a09e33275d5e6649273b5c9da1bc3c92491 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Thu, 21 Jul 2022 15:51:53 +0200 +Subject: [PATCH 06/32] meson: use have_vhost_* variables to pick sources +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 108: Net Control Virtqueue shadow Support +RH-Commit: [6/27] bc3db1efb759c0bc97fde2f4fbb3d6dc404c8d3d (eperezmartin/qemu-kvm) +RH-Bugzilla: 1939363 +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Cindy Lu +RH-Acked-by: Laurent Vivier + +Bugzilla: https://bugzilla.redhat.com/1939363 + +Upstream Status: git://git.qemu.org/qemu.git + +commit 43b6d7ee1fbc5b5fb7c85d8131fdac1863214ad6 +Author: Paolo Bonzini +Date: Wed Apr 20 17:34:06 2022 +0200 + + meson: use have_vhost_* variables to pick sources + + Reviewed-by: Marc-André Lureau + Signed-off-by: Paolo Bonzini + +Signed-off-by: Eugenio Pérez +--- + Kconfig.host | 3 --- + backends/meson.build | 8 ++++++-- + hw/net/meson.build | 8 ++++++-- + hw/virtio/Kconfig | 3 --- + hw/virtio/meson.build | 25 ++++++++++++++++--------- + meson.build | 1 + + net/meson.build | 12 +++++++----- + tests/qtest/meson.build | 4 +++- + 8 files changed, 39 insertions(+), 25 deletions(-) + +diff --git a/Kconfig.host b/Kconfig.host +index 60b9c07b5e..1165c4eacd 100644 +--- a/Kconfig.host ++++ b/Kconfig.host +@@ -22,15 +22,12 @@ config TPM + + config VHOST_USER + bool +- select VHOST + + config VHOST_VDPA + bool +- select VHOST + + config VHOST_KERNEL + bool +- select VHOST + + config VIRTFS + bool +diff --git a/backends/meson.build b/backends/meson.build +index 6e68945528..cb92f639ca 100644 +--- a/backends/meson.build ++++ b/backends/meson.build +@@ -12,9 +12,13 @@ softmmu_ss.add([files( + softmmu_ss.add(when: 'CONFIG_POSIX', if_true: files('rng-random.c')) + softmmu_ss.add(when: 'CONFIG_POSIX', if_true: files('hostmem-file.c')) + softmmu_ss.add(when: 'CONFIG_LINUX', if_true: files('hostmem-memfd.c')) +-softmmu_ss.add(when: ['CONFIG_VHOST_USER', 'CONFIG_VIRTIO'], if_true: files('vhost-user.c')) ++if have_vhost_user ++ softmmu_ss.add(when: 'CONFIG_VIRTIO', if_true: files('vhost-user.c')) ++endif + softmmu_ss.add(when: 'CONFIG_VIRTIO_CRYPTO', if_true: files('cryptodev-vhost.c')) +-softmmu_ss.add(when: ['CONFIG_VIRTIO_CRYPTO', 'CONFIG_VHOST_CRYPTO'], if_true: files('cryptodev-vhost-user.c')) ++if have_vhost_user_crypto ++ softmmu_ss.add(when: 'CONFIG_VIRTIO_CRYPTO', if_true: files('cryptodev-vhost-user.c')) ++endif + softmmu_ss.add(when: 'CONFIG_GIO', if_true: [files('dbus-vmstate.c'), gio]) + softmmu_ss.add(when: 'CONFIG_SGX', if_true: files('hostmem-epc.c')) + +diff --git a/hw/net/meson.build b/hw/net/meson.build +index 685b75badb..ebac261542 100644 +--- a/hw/net/meson.build ++++ b/hw/net/meson.build +@@ -46,8 +46,12 @@ specific_ss.add(when: 'CONFIG_XILINX_ETHLITE', if_true: files('xilinx_ethlite.c' + softmmu_ss.add(when: 'CONFIG_VIRTIO_NET', if_true: files('net_rx_pkt.c')) + specific_ss.add(when: 'CONFIG_VIRTIO_NET', if_true: files('virtio-net.c')) + +-softmmu_ss.add(when: ['CONFIG_VIRTIO_NET', 'CONFIG_VHOST_NET'], if_true: files('vhost_net.c'), if_false: files('vhost_net-stub.c')) +-softmmu_ss.add(when: 'CONFIG_ALL', if_true: files('vhost_net-stub.c')) ++if have_vhost_net ++ softmmu_ss.add(when: 'CONFIG_VIRTIO_NET', if_true: files('vhost_net.c'), if_false: files('vhost_net-stub.c')) ++ softmmu_ss.add(when: 'CONFIG_ALL', if_true: files('vhost_net-stub.c')) ++else ++ softmmu_ss.add(files('vhost_net-stub.c')) ++endif + + softmmu_ss.add(when: 'CONFIG_ETSEC', if_true: files( + 'fsl_etsec/etsec.c', +diff --git a/hw/virtio/Kconfig b/hw/virtio/Kconfig +index c144d42f9b..8ca7b3d9d6 100644 +--- a/hw/virtio/Kconfig ++++ b/hw/virtio/Kconfig +@@ -1,6 +1,3 @@ +-config VHOST +- bool +- + config VIRTIO + bool + +diff --git a/hw/virtio/meson.build b/hw/virtio/meson.build +index 67dc77e00f..30a832eb4a 100644 +--- a/hw/virtio/meson.build ++++ b/hw/virtio/meson.build +@@ -2,18 +2,22 @@ softmmu_virtio_ss = ss.source_set() + softmmu_virtio_ss.add(files('virtio-bus.c')) + softmmu_virtio_ss.add(when: 'CONFIG_VIRTIO_PCI', if_true: files('virtio-pci.c')) + softmmu_virtio_ss.add(when: 'CONFIG_VIRTIO_MMIO', if_true: files('virtio-mmio.c')) +-softmmu_virtio_ss.add(when: 'CONFIG_VHOST', if_false: files('vhost-stub.c')) +- +-softmmu_ss.add_all(when: 'CONFIG_VIRTIO', if_true: softmmu_virtio_ss) +-softmmu_ss.add(when: 'CONFIG_VIRTIO', if_false: files('vhost-stub.c')) +- +-softmmu_ss.add(when: 'CONFIG_ALL', if_true: files('vhost-stub.c')) + + virtio_ss = ss.source_set() + virtio_ss.add(files('virtio.c')) +-virtio_ss.add(when: 'CONFIG_VHOST', if_true: files('vhost.c', 'vhost-backend.c', 'vhost-iova-tree.c')) +-virtio_ss.add(when: 'CONFIG_VHOST_USER', if_true: files('vhost-user.c')) +-virtio_ss.add(when: 'CONFIG_VHOST_VDPA', if_true: files('vhost-shadow-virtqueue.c', 'vhost-vdpa.c')) ++ ++if have_vhost ++ virtio_ss.add(files('vhost.c', 'vhost-backend.c', 'vhost-iova-tree.c')) ++ if have_vhost_user ++ virtio_ss.add(files('vhost-user.c')) ++ endif ++ if have_vhost_vdpa ++ virtio_ss.add(files('vhost-vdpa.c', 'vhost-shadow-virtqueue.c')) ++ endif ++else ++ softmmu_virtio_ss.add(files('vhost-stub.c')) ++endif ++ + virtio_ss.add(when: 'CONFIG_VIRTIO_BALLOON', if_true: files('virtio-balloon.c')) + virtio_ss.add(when: 'CONFIG_VIRTIO_CRYPTO', if_true: files('virtio-crypto.c')) + virtio_ss.add(when: ['CONFIG_VIRTIO_CRYPTO', 'CONFIG_VIRTIO_PCI'], if_true: files('virtio-crypto-pci.c')) +@@ -53,3 +57,6 @@ virtio_pci_ss.add(when: 'CONFIG_VIRTIO_MEM', if_true: files('virtio-mem-pci.c')) + virtio_ss.add_all(when: 'CONFIG_VIRTIO_PCI', if_true: virtio_pci_ss) + + specific_ss.add_all(when: 'CONFIG_VIRTIO', if_true: virtio_ss) ++softmmu_ss.add_all(when: 'CONFIG_VIRTIO', if_true: softmmu_virtio_ss) ++softmmu_ss.add(when: 'CONFIG_VIRTIO', if_false: files('vhost-stub.c')) ++softmmu_ss.add(when: 'CONFIG_ALL', if_true: files('vhost-stub.c')) +diff --git a/meson.build b/meson.build +index 735f538497..9ba675f098 100644 +--- a/meson.build ++++ b/meson.build +@@ -305,6 +305,7 @@ have_vhost_kernel = 'CONFIG_VHOST_KERNEL' in config_host + have_vhost_net_user = 'CONFIG_VHOST_NET_USER' in config_host + have_vhost_net_vdpa = 'CONFIG_VHOST_NET_VDPA' in config_host + have_vhost_net = 'CONFIG_VHOST_NET' in config_host ++have_vhost = have_vhost_user or have_vhost_vdpa or have_vhost_kernel + have_vhost_user_crypto = 'CONFIG_VHOST_CRYPTO' in config_host + + # Target-specific libraries and flags +diff --git a/net/meson.build b/net/meson.build +index 847bc2ac85..c965e83b26 100644 +--- a/net/meson.build ++++ b/net/meson.build +@@ -26,10 +26,10 @@ softmmu_ss.add(when: vde, if_true: files('vde.c')) + if have_netmap + softmmu_ss.add(files('netmap.c')) + endif +-vhost_user_ss = ss.source_set() +-vhost_user_ss.add(when: 'CONFIG_VIRTIO_NET', if_true: files('vhost-user.c'), if_false: files('vhost-user-stub.c')) +-softmmu_ss.add_all(when: 'CONFIG_VHOST_NET_USER', if_true: vhost_user_ss) +-softmmu_ss.add(when: 'CONFIG_ALL', if_true: files('vhost-user-stub.c')) ++if have_vhost_net_user ++ softmmu_ss.add(when: 'CONFIG_VIRTIO_NET', if_true: files('vhost-user.c'), if_false: files('vhost-user-stub.c')) ++ softmmu_ss.add(when: 'CONFIG_ALL', if_true: files('vhost-user-stub.c')) ++endif + + softmmu_ss.add(when: 'CONFIG_LINUX', if_true: files('tap-linux.c')) + softmmu_ss.add(when: 'CONFIG_BSD', if_true: files('tap-bsd.c')) +@@ -40,6 +40,8 @@ if not config_host.has_key('CONFIG_LINUX') and not config_host.has_key('CONFIG_B + endif + softmmu_ss.add(when: 'CONFIG_POSIX', if_true: files(tap_posix)) + softmmu_ss.add(when: 'CONFIG_WIN32', if_true: files('tap-win32.c')) +-softmmu_ss.add(when: 'CONFIG_VHOST_NET_VDPA', if_true: files('vhost-vdpa.c')) ++if have_vhost_net_vdpa ++ softmmu_ss.add(files('vhost-vdpa.c')) ++endif + + subdir('can') +diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build +index 67cd32def1..9f550df900 100644 +--- a/tests/qtest/meson.build ++++ b/tests/qtest/meson.build +@@ -269,7 +269,9 @@ qos_test_ss.add( + if have_virtfs + qos_test_ss.add(files('virtio-9p-test.c')) + endif +-qos_test_ss.add(when: 'CONFIG_VHOST_USER', if_true: files('vhost-user-test.c')) ++if have_vhost_user ++ qos_test_ss.add(files('vhost-user-test.c')) ++endif + if have_tools and have_vhost_user_blk_server + qos_test_ss.add(files('vhost-user-blk-test.c')) + endif +-- +2.31.1 + diff --git a/SOURCES/kvm-meson.build-Fix-docker-test-build-alpine-when-includ.patch b/SOURCES/kvm-meson.build-Fix-docker-test-build-alpine-when-includ.patch new file mode 100644 index 0000000..0da63bf --- /dev/null +++ b/SOURCES/kvm-meson.build-Fix-docker-test-build-alpine-when-includ.patch @@ -0,0 +1,87 @@ +From 7c489b54b0bb33445113fbf16e88feb23be68013 Mon Sep 17 00:00:00 2001 +From: Leonardo Bras +Date: Fri, 13 May 2022 03:28:30 -0300 +Subject: [PATCH 07/18] meson.build: Fix docker-test-build@alpine when + including linux/errqueue.h +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Leonardo Brás +RH-MergeRequest: 95: MSG_ZEROCOPY + Multifd +RH-Commit: [1/11] f058eb846fcf611d527a1dd3b0cc399cdc17e3ee (LeoBras/centos-qemu-kvm) +RH-Bugzilla: 1968509 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Dr. David Alan Gilbert +RH-Acked-by: Peter Xu + +A build error happens in alpine CI when linux/errqueue.h is included +in io/channel-socket.c, due to redefining of 'struct __kernel_timespec': + +=== +ninja: job failed: [...] +In file included from /usr/include/linux/errqueue.h:6, + from ../io/channel-socket.c:29: +/usr/include/linux/time_types.h:7:8: error: redefinition of 'struct __kernel_timespec' + 7 | struct __kernel_timespec { + | ^~~~~~~~~~~~~~~~~ +In file included from /usr/include/liburing.h:19, + from /builds/user/qemu/include/block/aio.h:18, + from /builds/user/qemu/include/io/channel.h:26, + from /builds/user/qemu/include/io/channel-socket.h:24, + from ../io/channel-socket.c:24: +/usr/include/liburing/compat.h:9:8: note: originally defined here + 9 | struct __kernel_timespec { + | ^~~~~~~~~~~~~~~~~ +ninja: subcommand failed +=== + +As above error message suggests, 'struct __kernel_timespec' was already +defined by liburing/compat.h. + +Fix alpine CI by adding test to disable liburing in configure step if a +redefinition happens between linux/errqueue.h and liburing/compat.h. + +[dgilbert: This has been fixed in Alpine issue 13813 and liburing] + +Signed-off-by: Leonardo Bras +Message-Id: <20220513062836.965425-2-leobras@redhat.com> +Reviewed-by: Dr. David Alan Gilbert +Signed-off-by: Dr. David Alan Gilbert +(cherry picked from commit 354081d43de44ebd3497fe08f7f0121a5517d528) +Signed-off-by: Leonardo Bras +--- + meson.build | 11 +++++++++++ + 1 file changed, 11 insertions(+) + +diff --git a/meson.build b/meson.build +index 5a7c10e639..13e3323380 100644 +--- a/meson.build ++++ b/meson.build +@@ -471,12 +471,23 @@ if not get_option('linux_aio').auto() or have_block + required: get_option('linux_aio'), + kwargs: static_kwargs) + endif ++ ++linux_io_uring_test = ''' ++ #include ++ #include ++ ++ int main(void) { return 0; }''' ++ + linux_io_uring = not_found + if not get_option('linux_io_uring').auto() or have_block + linux_io_uring = dependency('liburing', version: '>=0.3', + required: get_option('linux_io_uring'), + method: 'pkg-config', kwargs: static_kwargs) ++ if not cc.links(linux_io_uring_test) ++ linux_io_uring = not_found ++ endif + endif ++ + libnfs = not_found + if not get_option('libnfs').auto() or have_block + libnfs = dependency('libnfs', version: '>=1.9.3', +-- +2.35.3 + diff --git a/SOURCES/kvm-migration-Add-migrate_use_tls-helper.patch b/SOURCES/kvm-migration-Add-migrate_use_tls-helper.patch new file mode 100644 index 0000000..0fe0d91 --- /dev/null +++ b/SOURCES/kvm-migration-Add-migrate_use_tls-helper.patch @@ -0,0 +1,106 @@ +From 828f6c106eedcb7a48e551ffda15af56ff92a899 Mon Sep 17 00:00:00 2001 +From: Leonardo Bras +Date: Fri, 13 May 2022 03:28:34 -0300 +Subject: [PATCH 11/18] migration: Add migrate_use_tls() helper +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Leonardo Brás +RH-MergeRequest: 95: MSG_ZEROCOPY + Multifd +RH-Commit: [5/11] 06e945297c3b9c0ce5864885aafcdba1e5746bc2 (LeoBras/centos-qemu-kvm) +RH-Bugzilla: 1968509 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Dr. David Alan Gilbert +RH-Acked-by: Peter Xu + +A lot of places check parameters.tls_creds in order to evaluate if TLS is +in use, and sometimes call migrate_get_current() just for that test. + +Add new helper function migrate_use_tls() in order to simplify testing +for TLS usage. + +Signed-off-by: Leonardo Bras +Reviewed-by: Juan Quintela +Reviewed-by: Peter Xu +Reviewed-by: Daniel P. Berrangé +Message-Id: <20220513062836.965425-6-leobras@redhat.com> +Signed-off-by: Dr. David Alan Gilbert +(cherry picked from commit d2fafb6a6814a8998607d0baf691265032996a0f) +Signed-off-by: Leonardo Bras +--- + migration/channel.c | 3 +-- + migration/migration.c | 9 +++++++++ + migration/migration.h | 1 + + migration/multifd.c | 5 +---- + 4 files changed, 12 insertions(+), 6 deletions(-) + +diff --git a/migration/channel.c b/migration/channel.c +index c4fc000a1a..086b5c0d8b 100644 +--- a/migration/channel.c ++++ b/migration/channel.c +@@ -38,8 +38,7 @@ void migration_channel_process_incoming(QIOChannel *ioc) + trace_migration_set_incoming_channel( + ioc, object_get_typename(OBJECT(ioc))); + +- if (s->parameters.tls_creds && +- *s->parameters.tls_creds && ++ if (migrate_use_tls() && + !object_dynamic_cast(OBJECT(ioc), + TYPE_QIO_CHANNEL_TLS)) { + migration_tls_channel_process_incoming(s, ioc, &local_err); +diff --git a/migration/migration.c b/migration/migration.c +index 0a6b3b9f4d..d91efb66fe 100644 +--- a/migration/migration.c ++++ b/migration/migration.c +@@ -2582,6 +2582,15 @@ bool migrate_use_zero_copy_send(void) + } + #endif + ++int migrate_use_tls(void) ++{ ++ MigrationState *s; ++ ++ s = migrate_get_current(); ++ ++ return s->parameters.tls_creds && *s->parameters.tls_creds; ++} ++ + int migrate_use_xbzrle(void) + { + MigrationState *s; +diff --git a/migration/migration.h b/migration/migration.h +index 5bcb7628ef..c2cabb8a14 100644 +--- a/migration/migration.h ++++ b/migration/migration.h +@@ -381,6 +381,7 @@ bool migrate_use_zero_copy_send(void); + #else + #define migrate_use_zero_copy_send() (false) + #endif ++int migrate_use_tls(void); + int migrate_use_xbzrle(void); + uint64_t migrate_xbzrle_cache_size(void); + bool migrate_colo_enabled(void); +diff --git a/migration/multifd.c b/migration/multifd.c +index 76b57a7177..43998ad117 100644 +--- a/migration/multifd.c ++++ b/migration/multifd.c +@@ -784,14 +784,11 @@ static bool multifd_channel_connect(MultiFDSendParams *p, + QIOChannel *ioc, + Error *error) + { +- MigrationState *s = migrate_get_current(); +- + trace_multifd_set_outgoing_channel( + ioc, object_get_typename(OBJECT(ioc)), p->tls_hostname, error); + + if (!error) { +- if (s->parameters.tls_creds && +- *s->parameters.tls_creds && ++ if (migrate_use_tls() && + !object_dynamic_cast(OBJECT(ioc), + TYPE_QIO_CHANNEL_TLS)) { + multifd_tls_channel_connect(p, ioc, &error); +-- +2.35.3 + diff --git a/SOURCES/kvm-migration-Add-zero-copy-send-parameter-for-QMP-HMP-f.patch b/SOURCES/kvm-migration-Add-zero-copy-send-parameter-for-QMP-HMP-f.patch new file mode 100644 index 0000000..206ac3d --- /dev/null +++ b/SOURCES/kvm-migration-Add-zero-copy-send-parameter-for-QMP-HMP-f.patch @@ -0,0 +1,250 @@ +From d6500340dc3c1152b5efe04ef3daa50c17a55e30 Mon Sep 17 00:00:00 2001 +From: Leonardo Bras +Date: Fri, 13 May 2022 03:28:33 -0300 +Subject: [PATCH 10/18] migration: Add zero-copy-send parameter for QMP/HMP for + Linux +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Leonardo Brás +RH-MergeRequest: 95: MSG_ZEROCOPY + Multifd +RH-Commit: [4/11] 514d98d595992c53ff98de750035e080ded8972e (LeoBras/centos-qemu-kvm) +RH-Bugzilla: 1968509 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Dr. David Alan Gilbert +RH-Acked-by: Peter Xu + +Add property that allows zero-copy migration of memory pages +on the sending side, and also includes a helper function +migrate_use_zero_copy_send() to check if it's enabled. + +No code is introduced to actually do the migration, but it allow +future implementations to enable/disable this feature. + +On non-Linux builds this parameter is compiled-out. + +Signed-off-by: Leonardo Bras +Reviewed-by: Peter Xu +Reviewed-by: Daniel P. Berrangé +Reviewed-by: Juan Quintela +Acked-by: Markus Armbruster +Message-Id: <20220513062836.965425-5-leobras@redhat.com> +Signed-off-by: Dr. David Alan Gilbert +(cherry picked from commit abb6295b3ace5d17c3a65936913fc346616dbf14) +Signed-off-by: Leonardo Bras +--- + migration/migration.c | 32 ++++++++++++++++++++++++++++++++ + migration/migration.h | 5 +++++ + migration/socket.c | 11 +++++++++-- + monitor/hmp-cmds.c | 6 ++++++ + qapi/migration.json | 24 ++++++++++++++++++++++++ + 5 files changed, 76 insertions(+), 2 deletions(-) + +diff --git a/migration/migration.c b/migration/migration.c +index 695f0f2900..0a6b3b9f4d 100644 +--- a/migration/migration.c ++++ b/migration/migration.c +@@ -899,6 +899,10 @@ MigrationParameters *qmp_query_migrate_parameters(Error **errp) + params->multifd_zlib_level = s->parameters.multifd_zlib_level; + params->has_multifd_zstd_level = true; + params->multifd_zstd_level = s->parameters.multifd_zstd_level; ++#ifdef CONFIG_LINUX ++ params->has_zero_copy_send = true; ++ params->zero_copy_send = s->parameters.zero_copy_send; ++#endif + params->has_xbzrle_cache_size = true; + params->xbzrle_cache_size = s->parameters.xbzrle_cache_size; + params->has_max_postcopy_bandwidth = true; +@@ -1555,6 +1559,11 @@ static void migrate_params_test_apply(MigrateSetParameters *params, + if (params->has_multifd_compression) { + dest->multifd_compression = params->multifd_compression; + } ++#ifdef CONFIG_LINUX ++ if (params->has_zero_copy_send) { ++ dest->zero_copy_send = params->zero_copy_send; ++ } ++#endif + if (params->has_xbzrle_cache_size) { + dest->xbzrle_cache_size = params->xbzrle_cache_size; + } +@@ -1667,6 +1676,11 @@ static void migrate_params_apply(MigrateSetParameters *params, Error **errp) + if (params->has_multifd_compression) { + s->parameters.multifd_compression = params->multifd_compression; + } ++#ifdef CONFIG_LINUX ++ if (params->has_zero_copy_send) { ++ s->parameters.zero_copy_send = params->zero_copy_send; ++ } ++#endif + if (params->has_xbzrle_cache_size) { + s->parameters.xbzrle_cache_size = params->xbzrle_cache_size; + xbzrle_cache_resize(params->xbzrle_cache_size, errp); +@@ -2557,6 +2571,17 @@ int migrate_multifd_zstd_level(void) + return s->parameters.multifd_zstd_level; + } + ++#ifdef CONFIG_LINUX ++bool migrate_use_zero_copy_send(void) ++{ ++ MigrationState *s; ++ ++ s = migrate_get_current(); ++ ++ return s->parameters.zero_copy_send; ++} ++#endif ++ + int migrate_use_xbzrle(void) + { + MigrationState *s; +@@ -4200,6 +4225,10 @@ static Property migration_properties[] = { + DEFINE_PROP_UINT8("multifd-zstd-level", MigrationState, + parameters.multifd_zstd_level, + DEFAULT_MIGRATE_MULTIFD_ZSTD_LEVEL), ++#ifdef CONFIG_LINUX ++ DEFINE_PROP_BOOL("zero_copy_send", MigrationState, ++ parameters.zero_copy_send, false), ++#endif + DEFINE_PROP_SIZE("xbzrle-cache-size", MigrationState, + parameters.xbzrle_cache_size, + DEFAULT_MIGRATE_XBZRLE_CACHE_SIZE), +@@ -4297,6 +4326,9 @@ static void migration_instance_init(Object *obj) + params->has_multifd_compression = true; + params->has_multifd_zlib_level = true; + params->has_multifd_zstd_level = true; ++#ifdef CONFIG_LINUX ++ params->has_zero_copy_send = true; ++#endif + params->has_xbzrle_cache_size = true; + params->has_max_postcopy_bandwidth = true; + params->has_max_cpu_throttle = true; +diff --git a/migration/migration.h b/migration/migration.h +index 2de861df01..5bcb7628ef 100644 +--- a/migration/migration.h ++++ b/migration/migration.h +@@ -376,6 +376,11 @@ MultiFDCompression migrate_multifd_compression(void); + int migrate_multifd_zlib_level(void); + int migrate_multifd_zstd_level(void); + ++#ifdef CONFIG_LINUX ++bool migrate_use_zero_copy_send(void); ++#else ++#define migrate_use_zero_copy_send() (false) ++#endif + int migrate_use_xbzrle(void); + uint64_t migrate_xbzrle_cache_size(void); + bool migrate_colo_enabled(void); +diff --git a/migration/socket.c b/migration/socket.c +index 05705a32d8..3754d8f72c 100644 +--- a/migration/socket.c ++++ b/migration/socket.c +@@ -74,9 +74,16 @@ static void socket_outgoing_migration(QIOTask *task, + + if (qio_task_propagate_error(task, &err)) { + trace_migration_socket_outgoing_error(error_get_pretty(err)); +- } else { +- trace_migration_socket_outgoing_connected(data->hostname); ++ goto out; + } ++ ++ trace_migration_socket_outgoing_connected(data->hostname); ++ ++ if (migrate_use_zero_copy_send()) { ++ error_setg(&err, "Zero copy send not available in migration"); ++ } ++ ++out: + migration_channel_connect(data->s, sioc, data->hostname, err); + object_unref(OBJECT(sioc)); + } +diff --git a/monitor/hmp-cmds.c b/monitor/hmp-cmds.c +index 634968498b..55b48d3733 100644 +--- a/monitor/hmp-cmds.c ++++ b/monitor/hmp-cmds.c +@@ -1309,6 +1309,12 @@ void hmp_migrate_set_parameter(Monitor *mon, const QDict *qdict) + p->has_multifd_zstd_level = true; + visit_type_uint8(v, param, &p->multifd_zstd_level, &err); + break; ++#ifdef CONFIG_LINUX ++ case MIGRATION_PARAMETER_ZERO_COPY_SEND: ++ p->has_zero_copy_send = true; ++ visit_type_bool(v, param, &p->zero_copy_send, &err); ++ break; ++#endif + case MIGRATION_PARAMETER_XBZRLE_CACHE_SIZE: + p->has_xbzrle_cache_size = true; + if (!visit_type_size(v, param, &cache_size, &err)) { +diff --git a/qapi/migration.json b/qapi/migration.json +index 27d7b28158..4d833ecdd6 100644 +--- a/qapi/migration.json ++++ b/qapi/migration.json +@@ -741,6 +741,13 @@ + # will consume more CPU. + # Defaults to 1. (Since 5.0) + # ++# @zero-copy-send: Controls behavior on sending memory pages on migration. ++# When true, enables a zero-copy mechanism for sending ++# memory pages, if host supports it. ++# Requires that QEMU be permitted to use locked memory ++# for guest RAM pages. ++# Defaults to false. (Since 7.1) ++# + # @block-bitmap-mapping: Maps block nodes and bitmaps on them to + # aliases for the purpose of dirty bitmap migration. Such + # aliases may for example be the corresponding names on the +@@ -780,6 +787,7 @@ + 'xbzrle-cache-size', 'max-postcopy-bandwidth', + 'max-cpu-throttle', 'multifd-compression', + 'multifd-zlib-level' ,'multifd-zstd-level', ++ { 'name': 'zero-copy-send', 'if' : 'CONFIG_LINUX'}, + 'block-bitmap-mapping' ] } + + ## +@@ -906,6 +914,13 @@ + # will consume more CPU. + # Defaults to 1. (Since 5.0) + # ++# @zero-copy-send: Controls behavior on sending memory pages on migration. ++# When true, enables a zero-copy mechanism for sending ++# memory pages, if host supports it. ++# Requires that QEMU be permitted to use locked memory ++# for guest RAM pages. ++# Defaults to false. (Since 7.1) ++# + # @block-bitmap-mapping: Maps block nodes and bitmaps on them to + # aliases for the purpose of dirty bitmap migration. Such + # aliases may for example be the corresponding names on the +@@ -960,6 +975,7 @@ + '*multifd-compression': 'MultiFDCompression', + '*multifd-zlib-level': 'uint8', + '*multifd-zstd-level': 'uint8', ++ '*zero-copy-send': { 'type': 'bool', 'if': 'CONFIG_LINUX' }, + '*block-bitmap-mapping': [ 'BitmapMigrationNodeAlias' ] } } + + ## +@@ -1106,6 +1122,13 @@ + # will consume more CPU. + # Defaults to 1. (Since 5.0) + # ++# @zero-copy-send: Controls behavior on sending memory pages on migration. ++# When true, enables a zero-copy mechanism for sending ++# memory pages, if host supports it. ++# Requires that QEMU be permitted to use locked memory ++# for guest RAM pages. ++# Defaults to false. (Since 7.1) ++# + # @block-bitmap-mapping: Maps block nodes and bitmaps on them to + # aliases for the purpose of dirty bitmap migration. Such + # aliases may for example be the corresponding names on the +@@ -1158,6 +1181,7 @@ + '*multifd-compression': 'MultiFDCompression', + '*multifd-zlib-level': 'uint8', + '*multifd-zstd-level': 'uint8', ++ '*zero-copy-send': { 'type': 'bool', 'if': 'CONFIG_LINUX' }, + '*block-bitmap-mapping': [ 'BitmapMigrationNodeAlias' ] } } + + ## +-- +2.35.3 + diff --git a/SOURCES/kvm-migration-Allow-migrate-recover-to-run-multiple-time.patch b/SOURCES/kvm-migration-Allow-migrate-recover-to-run-multiple-time.patch new file mode 100644 index 0000000..29dc0ea --- /dev/null +++ b/SOURCES/kvm-migration-Allow-migrate-recover-to-run-multiple-time.patch @@ -0,0 +1,98 @@ +From fd6f516a94e635bc42e58448f314db575814a834 Mon Sep 17 00:00:00 2001 +From: Peter Xu +Date: Thu, 31 Mar 2022 11:08:45 -0400 +Subject: [PATCH 18/18] migration: Allow migrate-recover to run multiple times +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Peter Xu +RH-MergeRequest: 104: migration: Allow migrate-recover to run multiple times +RH-Commit: [1/1] afd726e54c069ae800e2d01f34e768d6bac7dcb9 (peterx/qemu-kvm) +RH-Bugzilla: 2096143 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Hanna Reitz +RH-Acked-by: Dr. David Alan Gilbert + +Previously migration didn't have an easy way to cleanup the listening +transport, migrate recovery only allows to execute once. That's done with a +trick flag in postcopy_recover_triggered. + +Now the facility is already there. + +Drop postcopy_recover_triggered and instead allows a new migrate-recover to +release the previous listener transport. + +Reviewed-by: Dr. David Alan Gilbert +Signed-off-by: Peter Xu +Message-Id: <20220331150857.74406-8-peterx@redhat.com> +Reviewed-by: Daniel P. Berrangé +Signed-off-by: Dr. David Alan Gilbert +(cherry picked from commit 08401c0426bc1a5ce4609afd1cda5dd39abbf9fa) +Signed-off-by: Peter Xu +--- + migration/migration.c | 13 ++----------- + migration/migration.h | 1 - + migration/savevm.c | 3 --- + 3 files changed, 2 insertions(+), 15 deletions(-) + +diff --git a/migration/migration.c b/migration/migration.c +index 2a141bfaf3..8fb3eae910 100644 +--- a/migration/migration.c ++++ b/migration/migration.c +@@ -2166,11 +2166,8 @@ void qmp_migrate_recover(const char *uri, Error **errp) + return; + } + +- if (qatomic_cmpxchg(&mis->postcopy_recover_triggered, +- false, true) == true) { +- error_setg(errp, "Migrate recovery is triggered already"); +- return; +- } ++ /* If there's an existing transport, release it */ ++ migration_incoming_transport_cleanup(mis); + + /* + * Note that this call will never start a real migration; it will +@@ -2178,12 +2175,6 @@ void qmp_migrate_recover(const char *uri, Error **errp) + * to continue using that newly established channel. + */ + qemu_start_incoming_migration(uri, errp); +- +- /* Safe to dereference with the assert above */ +- if (*errp) { +- /* Reset the flag so user could still retry */ +- qatomic_set(&mis->postcopy_recover_triggered, false); +- } + } + + void qmp_migrate_pause(Error **errp) +diff --git a/migration/migration.h b/migration/migration.h +index c2cabb8a14..fbc8690ec8 100644 +--- a/migration/migration.h ++++ b/migration/migration.h +@@ -139,7 +139,6 @@ struct MigrationIncomingState { + struct PostcopyBlocktimeContext *blocktime_ctx; + + /* notify PAUSED postcopy incoming migrations to try to continue */ +- bool postcopy_recover_triggered; + QemuSemaphore postcopy_pause_sem_dst; + QemuSemaphore postcopy_pause_sem_fault; + +diff --git a/migration/savevm.c b/migration/savevm.c +index 02ed94c180..d9076897b8 100644 +--- a/migration/savevm.c ++++ b/migration/savevm.c +@@ -2589,9 +2589,6 @@ static bool postcopy_pause_incoming(MigrationIncomingState *mis) + + assert(migrate_postcopy_ram()); + +- /* Clear the triggered bit to allow one recovery */ +- mis->postcopy_recover_triggered = false; +- + /* + * Unregister yank with either from/to src would work, since ioc behind it + * is the same +-- +2.35.3 + diff --git a/SOURCES/kvm-migration-Avoid-false-positive-on-non-supported-scen.patch b/SOURCES/kvm-migration-Avoid-false-positive-on-non-supported-scen.patch new file mode 100644 index 0000000..9f440eb --- /dev/null +++ b/SOURCES/kvm-migration-Avoid-false-positive-on-non-supported-scen.patch @@ -0,0 +1,93 @@ +From 0753565af588dfa78b3529e359b1590e15fcbdb3 Mon Sep 17 00:00:00 2001 +From: Leonardo Bras +Date: Tue, 19 Jul 2022 09:23:45 -0300 +Subject: [PATCH 04/11] migration: Avoid false-positive on non-supported + scenarios for zero-copy-send +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Leonardo Brás +RH-MergeRequest: 111: zero-copy-send fixes & improvements +RH-Commit: [4/6] f5c7ed6710d92668acb81d0118a71fab0b4e3d43 (LeoBras/centos-qemu-kvm) +RH-Bugzilla: 2107466 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Thomas Huth +RH-Acked-by: Dr. David Alan Gilbert + +Migration with zero-copy-send currently has it's limitations, as it can't +be used with TLS nor any kind of compression. In such scenarios, it should +output errors during parameter / capability setting. + +But currently there are some ways of setting this not-supported scenarios +without printing the error message: + +!) For 'compression' capability, it works by enabling it together with +zero-copy-send. This happens because the validity test for zero-copy uses +the helper unction migrate_use_compression(), which check for compression +presence in s->enabled_capabilities[MIGRATION_CAPABILITY_COMPRESS]. + +The point here is: the validity test happens before the capability gets +enabled. If all of them get enabled together, this test will not return +error. + +In order to fix that, replace migrate_use_compression() by directly testing +the cap_list parameter migrate_caps_check(). + +2) For features enabled by parameters such as TLS & 'multifd_compression', +there was also a possibility of setting non-supported scenarios: setting +zero-copy-send first, then setting the unsupported parameter. + +In order to fix that, also add a check for parameters conflicting with +zero-copy-send on migrate_params_check(). + +3) XBZRLE is also a compression capability, so it makes sense to also add +it to the list of capabilities which are not supported with zero-copy-send. + +Fixes: 1abaec9a1b2c ("migration: Change zero_copy_send from migration parameter to migration capability") +Signed-off-by: Leonardo Bras +Message-Id: <20220719122345.253713-1-leobras@redhat.com> +Reviewed-by: Dr. David Alan Gilbert +Signed-off-by: Dr. David Alan Gilbert +(cherry picked from commit 90eb69e4f1a16b388d0483543bf6bfc69a9966e4) +Signed-off-by: Leonardo Bras +--- + migration/migration.c | 15 ++++++++++++++- + 1 file changed, 14 insertions(+), 1 deletion(-) + +diff --git a/migration/migration.c b/migration/migration.c +index 3a3a7a4a50..343629d59c 100644 +--- a/migration/migration.c ++++ b/migration/migration.c +@@ -1265,7 +1265,9 @@ static bool migrate_caps_check(bool *cap_list, + #ifdef CONFIG_LINUX + if (cap_list[MIGRATION_CAPABILITY_ZERO_COPY_SEND] && + (!cap_list[MIGRATION_CAPABILITY_MULTIFD] || +- migrate_use_compression() || ++ cap_list[MIGRATION_CAPABILITY_COMPRESS] || ++ cap_list[MIGRATION_CAPABILITY_XBZRLE] || ++ migrate_multifd_compression() || + migrate_use_tls())) { + error_setg(errp, + "Zero copy only available for non-compressed non-TLS multifd migration"); +@@ -1502,6 +1504,17 @@ static bool migrate_params_check(MigrationParameters *params, Error **errp) + error_prepend(errp, "Invalid mapping given for block-bitmap-mapping: "); + return false; + } ++ ++#ifdef CONFIG_LINUX ++ if (migrate_use_zero_copy_send() && ++ ((params->has_multifd_compression && params->multifd_compression) || ++ (params->has_tls_creds && params->tls_creds && *params->tls_creds))) { ++ error_setg(errp, ++ "Zero copy only available for non-compressed non-TLS multifd migration"); ++ return false; ++ } ++#endif ++ + return true; + } + +-- +2.31.1 + diff --git a/SOURCES/kvm-migration-Change-zero_copy_send-from-migration-param.patch b/SOURCES/kvm-migration-Change-zero_copy_send-from-migration-param.patch new file mode 100644 index 0000000..abeeeb6 --- /dev/null +++ b/SOURCES/kvm-migration-Change-zero_copy_send-from-migration-param.patch @@ -0,0 +1,289 @@ +From 7e2a037f3f349c21201152cecce32d8c8ff0bea0 Mon Sep 17 00:00:00 2001 +From: Leonardo Bras +Date: Mon, 20 Jun 2022 02:39:45 -0300 +Subject: [PATCH 17/18] migration: Change zero_copy_send from migration + parameter to migration capability +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Leonardo Brás +RH-MergeRequest: 95: MSG_ZEROCOPY + Multifd +RH-Commit: [11/11] e4a955607947896a49398ac8400241a0adac51a1 (LeoBras/centos-qemu-kvm) +RH-Bugzilla: 1968509 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Dr. David Alan Gilbert +RH-Acked-by: Peter Xu + +When originally implemented, zero_copy_send was designed as a Migration +paramenter. + +But taking into account how is that supposed to work, and how +the difference between a capability and a parameter, it only makes sense +that zero-copy-send would work better as a capability. + +Taking into account how recently the change got merged, it was decided +that it's still time to make it right, and convert zero_copy_send into +a Migration capability. + +Signed-off-by: Leonardo Bras +Reviewed-by: Juan Quintela +Acked-by: Markus Armbruster +Acked-by: Peter Xu +Signed-off-by: Juan Quintela +Signed-off-by: Dr. David Alan Gilbert + dgilbert: always define the capability, even on non-Linux but error if +set; avoids build problems with the capability +(cherry picked from commit 1abaec9a1b2c23f7aa94709a422128d9e42c3e0b) +Signed-off-by: Leonardo Bras +--- + migration/migration.c | 58 +++++++++++++++++++------------------------ + monitor/hmp-cmds.c | 6 ----- + qapi/migration.json | 33 +++++++----------------- + 3 files changed, 34 insertions(+), 63 deletions(-) + +diff --git a/migration/migration.c b/migration/migration.c +index 102236fba0..2a141bfaf3 100644 +--- a/migration/migration.c ++++ b/migration/migration.c +@@ -163,7 +163,8 @@ INITIALIZE_MIGRATE_CAPS_SET(check_caps_background_snapshot, + MIGRATION_CAPABILITY_COMPRESS, + MIGRATION_CAPABILITY_XBZRLE, + MIGRATION_CAPABILITY_X_COLO, +- MIGRATION_CAPABILITY_VALIDATE_UUID); ++ MIGRATION_CAPABILITY_VALIDATE_UUID, ++ MIGRATION_CAPABILITY_ZERO_COPY_SEND); + + /* When we add fault tolerance, we could have several + migrations at once. For now we don't need to add +@@ -899,10 +900,6 @@ MigrationParameters *qmp_query_migrate_parameters(Error **errp) + params->multifd_zlib_level = s->parameters.multifd_zlib_level; + params->has_multifd_zstd_level = true; + params->multifd_zstd_level = s->parameters.multifd_zstd_level; +-#ifdef CONFIG_LINUX +- params->has_zero_copy_send = true; +- params->zero_copy_send = s->parameters.zero_copy_send; +-#endif + params->has_xbzrle_cache_size = true; + params->xbzrle_cache_size = s->parameters.xbzrle_cache_size; + params->has_max_postcopy_bandwidth = true; +@@ -1263,6 +1260,24 @@ static bool migrate_caps_check(bool *cap_list, + } + } + ++#ifdef CONFIG_LINUX ++ if (cap_list[MIGRATION_CAPABILITY_ZERO_COPY_SEND] && ++ (!cap_list[MIGRATION_CAPABILITY_MULTIFD] || ++ migrate_use_compression() || ++ migrate_use_tls())) { ++ error_setg(errp, ++ "Zero copy only available for non-compressed non-TLS multifd migration"); ++ return false; ++ } ++#else ++ if (cap_list[MIGRATION_CAPABILITY_ZERO_COPY_SEND]) { ++ error_setg(errp, ++ "Zero copy currently only available on Linux"); ++ return false; ++ } ++#endif ++ ++ + /* incoming side only */ + if (runstate_check(RUN_STATE_INMIGRATE) && + !migrate_multifd_is_allowed() && +@@ -1485,16 +1500,6 @@ static bool migrate_params_check(MigrationParameters *params, Error **errp) + error_prepend(errp, "Invalid mapping given for block-bitmap-mapping: "); + return false; + } +-#ifdef CONFIG_LINUX +- if (params->zero_copy_send && +- (!migrate_use_multifd() || +- params->multifd_compression != MULTIFD_COMPRESSION_NONE || +- (params->tls_creds && *params->tls_creds))) { +- error_setg(errp, +- "Zero copy only available for non-compressed non-TLS multifd migration"); +- return false; +- } +-#endif + return true; + } + +@@ -1568,11 +1573,6 @@ static void migrate_params_test_apply(MigrateSetParameters *params, + if (params->has_multifd_compression) { + dest->multifd_compression = params->multifd_compression; + } +-#ifdef CONFIG_LINUX +- if (params->has_zero_copy_send) { +- dest->zero_copy_send = params->zero_copy_send; +- } +-#endif + if (params->has_xbzrle_cache_size) { + dest->xbzrle_cache_size = params->xbzrle_cache_size; + } +@@ -1685,11 +1685,6 @@ static void migrate_params_apply(MigrateSetParameters *params, Error **errp) + if (params->has_multifd_compression) { + s->parameters.multifd_compression = params->multifd_compression; + } +-#ifdef CONFIG_LINUX +- if (params->has_zero_copy_send) { +- s->parameters.zero_copy_send = params->zero_copy_send; +- } +-#endif + if (params->has_xbzrle_cache_size) { + s->parameters.xbzrle_cache_size = params->xbzrle_cache_size; + xbzrle_cache_resize(params->xbzrle_cache_size, errp); +@@ -2587,7 +2582,7 @@ bool migrate_use_zero_copy_send(void) + + s = migrate_get_current(); + +- return s->parameters.zero_copy_send; ++ return s->enabled_capabilities[MIGRATION_CAPABILITY_ZERO_COPY_SEND]; + } + #endif + +@@ -4243,10 +4238,6 @@ static Property migration_properties[] = { + DEFINE_PROP_UINT8("multifd-zstd-level", MigrationState, + parameters.multifd_zstd_level, + DEFAULT_MIGRATE_MULTIFD_ZSTD_LEVEL), +-#ifdef CONFIG_LINUX +- DEFINE_PROP_BOOL("zero_copy_send", MigrationState, +- parameters.zero_copy_send, false), +-#endif + DEFINE_PROP_SIZE("xbzrle-cache-size", MigrationState, + parameters.xbzrle_cache_size, + DEFAULT_MIGRATE_XBZRLE_CACHE_SIZE), +@@ -4284,6 +4275,10 @@ static Property migration_properties[] = { + DEFINE_PROP_MIG_CAP("x-multifd", MIGRATION_CAPABILITY_MULTIFD), + DEFINE_PROP_MIG_CAP("x-background-snapshot", + MIGRATION_CAPABILITY_BACKGROUND_SNAPSHOT), ++#ifdef CONFIG_LINUX ++ DEFINE_PROP_MIG_CAP("x-zero-copy-send", ++ MIGRATION_CAPABILITY_ZERO_COPY_SEND), ++#endif + + DEFINE_PROP_END_OF_LIST(), + }; +@@ -4344,9 +4339,6 @@ static void migration_instance_init(Object *obj) + params->has_multifd_compression = true; + params->has_multifd_zlib_level = true; + params->has_multifd_zstd_level = true; +-#ifdef CONFIG_LINUX +- params->has_zero_copy_send = true; +-#endif + params->has_xbzrle_cache_size = true; + params->has_max_postcopy_bandwidth = true; + params->has_max_cpu_throttle = true; +diff --git a/monitor/hmp-cmds.c b/monitor/hmp-cmds.c +index 55b48d3733..634968498b 100644 +--- a/monitor/hmp-cmds.c ++++ b/monitor/hmp-cmds.c +@@ -1309,12 +1309,6 @@ void hmp_migrate_set_parameter(Monitor *mon, const QDict *qdict) + p->has_multifd_zstd_level = true; + visit_type_uint8(v, param, &p->multifd_zstd_level, &err); + break; +-#ifdef CONFIG_LINUX +- case MIGRATION_PARAMETER_ZERO_COPY_SEND: +- p->has_zero_copy_send = true; +- visit_type_bool(v, param, &p->zero_copy_send, &err); +- break; +-#endif + case MIGRATION_PARAMETER_XBZRLE_CACHE_SIZE: + p->has_xbzrle_cache_size = true; + if (!visit_type_size(v, param, &cache_size, &err)) { +diff --git a/qapi/migration.json b/qapi/migration.json +index 4d833ecdd6..5105790cd0 100644 +--- a/qapi/migration.json ++++ b/qapi/migration.json +@@ -463,6 +463,13 @@ + # procedure starts. The VM RAM is saved with running VM. + # (since 6.0) + # ++# @zero-copy-send: Controls behavior on sending memory pages on migration. ++# When true, enables a zero-copy mechanism for sending ++# memory pages, if host supports it. ++# Requires that QEMU be permitted to use locked memory ++# for guest RAM pages. ++# (since 7.1) ++# + # Features: + # @unstable: Members @x-colo and @x-ignore-shared are experimental. + # +@@ -476,7 +483,8 @@ + 'block', 'return-path', 'pause-before-switchover', 'multifd', + 'dirty-bitmaps', 'postcopy-blocktime', 'late-block-activate', + { 'name': 'x-ignore-shared', 'features': [ 'unstable' ] }, +- 'validate-uuid', 'background-snapshot'] } ++ 'validate-uuid', 'background-snapshot', ++ 'zero-copy-send'] } + + ## + # @MigrationCapabilityStatus: +@@ -741,12 +749,6 @@ + # will consume more CPU. + # Defaults to 1. (Since 5.0) + # +-# @zero-copy-send: Controls behavior on sending memory pages on migration. +-# When true, enables a zero-copy mechanism for sending +-# memory pages, if host supports it. +-# Requires that QEMU be permitted to use locked memory +-# for guest RAM pages. +-# Defaults to false. (Since 7.1) + # + # @block-bitmap-mapping: Maps block nodes and bitmaps on them to + # aliases for the purpose of dirty bitmap migration. Such +@@ -787,7 +789,6 @@ + 'xbzrle-cache-size', 'max-postcopy-bandwidth', + 'max-cpu-throttle', 'multifd-compression', + 'multifd-zlib-level' ,'multifd-zstd-level', +- { 'name': 'zero-copy-send', 'if' : 'CONFIG_LINUX'}, + 'block-bitmap-mapping' ] } + + ## +@@ -914,13 +915,6 @@ + # will consume more CPU. + # Defaults to 1. (Since 5.0) + # +-# @zero-copy-send: Controls behavior on sending memory pages on migration. +-# When true, enables a zero-copy mechanism for sending +-# memory pages, if host supports it. +-# Requires that QEMU be permitted to use locked memory +-# for guest RAM pages. +-# Defaults to false. (Since 7.1) +-# + # @block-bitmap-mapping: Maps block nodes and bitmaps on them to + # aliases for the purpose of dirty bitmap migration. Such + # aliases may for example be the corresponding names on the +@@ -975,7 +969,6 @@ + '*multifd-compression': 'MultiFDCompression', + '*multifd-zlib-level': 'uint8', + '*multifd-zstd-level': 'uint8', +- '*zero-copy-send': { 'type': 'bool', 'if': 'CONFIG_LINUX' }, + '*block-bitmap-mapping': [ 'BitmapMigrationNodeAlias' ] } } + + ## +@@ -1122,13 +1115,6 @@ + # will consume more CPU. + # Defaults to 1. (Since 5.0) + # +-# @zero-copy-send: Controls behavior on sending memory pages on migration. +-# When true, enables a zero-copy mechanism for sending +-# memory pages, if host supports it. +-# Requires that QEMU be permitted to use locked memory +-# for guest RAM pages. +-# Defaults to false. (Since 7.1) +-# + # @block-bitmap-mapping: Maps block nodes and bitmaps on them to + # aliases for the purpose of dirty bitmap migration. Such + # aliases may for example be the corresponding names on the +@@ -1181,7 +1167,6 @@ + '*multifd-compression': 'MultiFDCompression', + '*multifd-zlib-level': 'uint8', + '*multifd-zstd-level': 'uint8', +- '*zero-copy-send': { 'type': 'bool', 'if': 'CONFIG_LINUX' }, + '*block-bitmap-mapping': [ 'BitmapMigrationNodeAlias' ] } } + + ## +-- +2.35.3 + diff --git a/SOURCES/kvm-migration-Fix-operator-type.patch b/SOURCES/kvm-migration-Fix-operator-type.patch new file mode 100644 index 0000000..f6a462a --- /dev/null +++ b/SOURCES/kvm-migration-Fix-operator-type.patch @@ -0,0 +1,47 @@ +From 4bd48e784ae0c38c89f1a944b06c997fd28c4d37 Mon Sep 17 00:00:00 2001 +From: Miroslav Rezanina +Date: Thu, 19 May 2022 04:15:33 -0400 +Subject: [PATCH 16/16] migration: Fix operator type +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Miroslav Rezanina +RH-MergeRequest: 92: Fix build using clang 14 +RH-Commit: [1/1] ad9980e64cf2e39085d68f1ff601444bf2afe228 (mrezanin/centos-src-qemu-kvm) +RH-Bugzilla: 2064530 +RH-Acked-by: Daniel P. Berrangé +RH-Acked-by: Dr. David Alan Gilbert + +Clang spotted an & that should have been an &&; fix it. + +Reported by: David Binderman / https://gitlab.com/dcb +Fixes: 65dacaa04fa ("migration: introduce save_normal_page()") +Resolves: https://gitlab.com/qemu-project/qemu/-/issues/963 +Signed-off-by: Dr. David Alan Gilbert +Message-Id: <20220406102515.96320-1-dgilbert@redhat.com> +Reviewed-by: Peter Maydell +Reviewed-by: Peter Xu +Signed-off-by: Dr. David Alan Gilbert +(cherry picked from commit f912ec5b2d65644116ff496b58d7c9145c19e4c0) +Signed-off-by: Miroslav Rezanina +--- + migration/ram.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/migration/ram.c b/migration/ram.c +index 3532f64ecb..0ef4bd63eb 100644 +--- a/migration/ram.c ++++ b/migration/ram.c +@@ -1289,7 +1289,7 @@ static int save_normal_page(RAMState *rs, RAMBlock *block, ram_addr_t offset, + offset | RAM_SAVE_FLAG_PAGE)); + if (async) { + qemu_put_buffer_async(rs->f, buf, TARGET_PAGE_SIZE, +- migrate_release_ram() & ++ migrate_release_ram() && + migration_in_postcopy()); + } else { + qemu_put_buffer(rs->f, buf, TARGET_PAGE_SIZE); +-- +2.31.1 + diff --git a/SOURCES/kvm-migration-add-remaining-params-has_-true-in-migratio.patch b/SOURCES/kvm-migration-add-remaining-params-has_-true-in-migratio.patch new file mode 100644 index 0000000..bcaff3b --- /dev/null +++ b/SOURCES/kvm-migration-add-remaining-params-has_-true-in-migratio.patch @@ -0,0 +1,62 @@ +From 9698c0e8dd9b4f5dbc237a3f98ac46297dac85fb Mon Sep 17 00:00:00 2001 +From: Leonardo Bras +Date: Mon, 25 Jul 2022 22:02:35 -0300 +Subject: [PATCH 05/11] migration: add remaining params->has_* = true in + migration_instance_init() +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Leonardo Brás +RH-MergeRequest: 111: zero-copy-send fixes & improvements +RH-Commit: [5/6] 50bbad254e2356b3ae16f6e00a3db8fd0b22dde9 (LeoBras/centos-qemu-kvm) +RH-Bugzilla: 2107466 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Thomas Huth +RH-Acked-by: Dr. David Alan Gilbert + +Some of params->has_* = true are missing in migration_instance_init, this +causes migrate_params_check() to skip some tests, allowing some +unsupported scenarios. + +Fix this by adding all missing params->has_* = true in +migration_instance_init(). + +Fixes: 69ef1f36b0 ("migration: define 'tls-creds' and 'tls-hostname' migration parameters") +Fixes: 1d58872a91 ("migration: do not wait for free thread") +Fixes: d2f1d29b95 ("migration: add support for a "tls-authz" migration parameter") +Signed-off-by: Leonardo Bras +Message-Id: <20220726010235.342927-1-leobras@redhat.com> +Reviewed-by: Peter Xu +Signed-off-by: Dr. David Alan Gilbert +(cherry picked from commit df67aa3e61e2c83459da7d815962d9706f1528fc) +Signed-off-by: Leonardo Bras +--- + migration/migration.c | 4 ++++ + 1 file changed, 4 insertions(+) + +diff --git a/migration/migration.c b/migration/migration.c +index 343629d59c..5e78028df4 100644 +--- a/migration/migration.c ++++ b/migration/migration.c +@@ -4332,6 +4332,7 @@ static void migration_instance_init(Object *obj) + /* Set has_* up only for parameter checks */ + params->has_compress_level = true; + params->has_compress_threads = true; ++ params->has_compress_wait_thread = true; + params->has_decompress_threads = true; + params->has_throttle_trigger_threshold = true; + params->has_cpu_throttle_initial = true; +@@ -4352,6 +4353,9 @@ static void migration_instance_init(Object *obj) + params->has_announce_max = true; + params->has_announce_rounds = true; + params->has_announce_step = true; ++ params->has_tls_creds = true; ++ params->has_tls_hostname = true; ++ params->has_tls_authz = true; + + qemu_sem_init(&ms->postcopy_pause_sem, 0); + qemu_sem_init(&ms->postcopy_pause_rp_sem, 0); +-- +2.31.1 + diff --git a/SOURCES/kvm-migration-multifd-Report-to-user-when-zerocopy-not-w.patch b/SOURCES/kvm-migration-multifd-Report-to-user-when-zerocopy-not-w.patch new file mode 100644 index 0000000..d7b1ab3 --- /dev/null +++ b/SOURCES/kvm-migration-multifd-Report-to-user-when-zerocopy-not-w.patch @@ -0,0 +1,83 @@ +From 78bbe28d5f5691330239041448cccfb339eed779 Mon Sep 17 00:00:00 2001 +From: Leonardo Bras +Date: Mon, 11 Jul 2022 18:11:13 -0300 +Subject: [PATCH 03/11] migration/multifd: Report to user when zerocopy not + working +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Leonardo Brás +RH-MergeRequest: 111: zero-copy-send fixes & improvements +RH-Commit: [3/6] 4f9165325b3cb8ff16d8b3b7649ff780fae0e2ad (LeoBras/centos-qemu-kvm) +RH-Bugzilla: 2107466 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Thomas Huth +RH-Acked-by: Dr. David Alan Gilbert + +Some errors, like the lack of Scatter-Gather support by the network +interface(NETIF_F_SG) may cause sendmsg(...,MSG_ZEROCOPY) to fail on using +zero-copy, which causes it to fall back to the default copying mechanism. + +After each full dirty-bitmap scan there should be a zero-copy flush +happening, which checks for errors each of the previous calls to +sendmsg(...,MSG_ZEROCOPY). If all of them failed to use zero-copy, then +increment dirty_sync_missed_zero_copy migration stat to let the user know +about it. + +Signed-off-by: Leonardo Bras +Reviewed-by: Daniel P. Berrangé +Acked-by: Peter Xu +Message-Id: <20220711211112.18951-4-leobras@redhat.com> +Signed-off-by: Dr. David Alan Gilbert +(cherry picked from commit d59c40cc483729f2e67c80e58df769ad19976fe9) +Signed-off-by: Leonardo Bras +--- + migration/multifd.c | 2 ++ + migration/ram.c | 5 +++++ + migration/ram.h | 2 ++ + 3 files changed, 9 insertions(+) + +diff --git a/migration/multifd.c b/migration/multifd.c +index 0b5b41c53f..96e5f0a058 100644 +--- a/migration/multifd.c ++++ b/migration/multifd.c +@@ -626,6 +626,8 @@ int multifd_send_sync_main(QEMUFile *f) + if (ret < 0) { + error_report_err(err); + return -1; ++ } else if (ret == 1) { ++ dirty_sync_missed_zero_copy(); + } + } + } +diff --git a/migration/ram.c b/migration/ram.c +index ee40e4a718..c437ff1b1f 100644 +--- a/migration/ram.c ++++ b/migration/ram.c +@@ -406,6 +406,11 @@ static void ram_transferred_add(uint64_t bytes) + ram_counters.transferred += bytes; + } + ++void dirty_sync_missed_zero_copy(void) ++{ ++ ram_counters.dirty_sync_missed_zero_copy++; ++} ++ + /* used by the search for pages to send */ + struct PageSearchStatus { + /* Current block being searched */ +diff --git a/migration/ram.h b/migration/ram.h +index 2c6dc3675d..34adf5cb92 100644 +--- a/migration/ram.h ++++ b/migration/ram.h +@@ -86,4 +86,6 @@ void ram_write_tracking_prepare(void); + int ram_write_tracking_start(void); + void ram_write_tracking_stop(void); + ++void dirty_sync_missed_zero_copy(void); ++ + #endif +-- +2.31.1 + diff --git a/SOURCES/kvm-multifd-Copy-pages-before-compressing-them-with-zlib.patch b/SOURCES/kvm-multifd-Copy-pages-before-compressing-them-with-zlib.patch new file mode 100644 index 0000000..ea89a9f --- /dev/null +++ b/SOURCES/kvm-multifd-Copy-pages-before-compressing-them-with-zlib.patch @@ -0,0 +1,142 @@ +From 1d280070748b604c60a7be4d4c3c3a28e3964f37 Mon Sep 17 00:00:00 2001 +From: Thomas Huth +Date: Tue, 2 Aug 2022 10:11:21 +0200 +Subject: [PATCH 31/32] multifd: Copy pages before compressing them with zlib + +RH-Author: Thomas Huth +RH-MergeRequest: 112: Fix postcopy migration on s390x +RH-Commit: [1/2] fd5a0221e22b4563bd1cb7f8a8b95f0bfe8f5fc9 (thuth/qemu-kvm-cs9) +RH-Bugzilla: 2099934 +RH-Acked-by: Dr. David Alan Gilbert +RH-Acked-by: Cornelia Huck +RH-Acked-by: David Hildenbrand +RH-Acked-by: Peter Xu + +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2099934 + +zlib_send_prepare() compresses pages of a running VM. zlib does not +make any thread-safety guarantees with respect to changing deflate() +input concurrently with deflate() [1]. + +One can observe problems due to this with the IBM zEnterprise Data +Compression accelerator capable zlib [2]. When the hardware +acceleration is enabled, migration/multifd/tcp/plain/zlib test fails +intermittently [3] due to sliding window corruption. The accelerator's +architecture explicitly discourages concurrent accesses [4]: + + Page 26-57, "Other Conditions": + + As observed by this CPU, other CPUs, and channel + programs, references to the parameter block, first, + second, and third operands may be multiple-access + references, accesses to these storage locations are + not necessarily block-concurrent, and the sequence + of these accesses or references is undefined. + +Mark Adler pointed out that vanilla zlib performs double fetches under +certain circumstances as well [5], therefore we need to copy data +before passing it to deflate(). + +[1] https://zlib.net/manual.html +[2] https://github.com/madler/zlib/pull/410 +[3] https://lists.nongnu.org/archive/html/qemu-devel/2022-03/msg03988.html +[4] http://publibfp.dhe.ibm.com/epubs/pdf/a227832c.pdf +[5] https://lists.gnu.org/archive/html/qemu-devel/2022-07/msg00889.html + +Signed-off-by: Ilya Leoshkevich +Message-Id: <20220705203559.2960949-1-iii@linux.ibm.com> +Reviewed-by: Dr. David Alan Gilbert +Signed-off-by: Dr. David Alan Gilbert +(cherry picked from commit 007e179ef0e97eafda4c9ff2a9d665a1947c7c6d) +Signed-off-by: Thomas Huth +--- + migration/multifd-zlib.c | 38 ++++++++++++++++++++++++++++++-------- + 1 file changed, 30 insertions(+), 8 deletions(-) + +diff --git a/migration/multifd-zlib.c b/migration/multifd-zlib.c +index 3a7ae44485..18213a9513 100644 +--- a/migration/multifd-zlib.c ++++ b/migration/multifd-zlib.c +@@ -27,6 +27,8 @@ struct zlib_data { + uint8_t *zbuff; + /* size of compressed buffer */ + uint32_t zbuff_len; ++ /* uncompressed buffer of size qemu_target_page_size() */ ++ uint8_t *buf; + }; + + /* Multifd zlib compression */ +@@ -45,26 +47,38 @@ static int zlib_send_setup(MultiFDSendParams *p, Error **errp) + { + struct zlib_data *z = g_new0(struct zlib_data, 1); + z_stream *zs = &z->zs; ++ const char *err_msg; + + zs->zalloc = Z_NULL; + zs->zfree = Z_NULL; + zs->opaque = Z_NULL; + if (deflateInit(zs, migrate_multifd_zlib_level()) != Z_OK) { +- g_free(z); +- error_setg(errp, "multifd %u: deflate init failed", p->id); +- return -1; ++ err_msg = "deflate init failed"; ++ goto err_free_z; + } + /* This is the maxium size of the compressed buffer */ + z->zbuff_len = compressBound(MULTIFD_PACKET_SIZE); + z->zbuff = g_try_malloc(z->zbuff_len); + if (!z->zbuff) { +- deflateEnd(&z->zs); +- g_free(z); +- error_setg(errp, "multifd %u: out of memory for zbuff", p->id); +- return -1; ++ err_msg = "out of memory for zbuff"; ++ goto err_deflate_end; ++ } ++ z->buf = g_try_malloc(qemu_target_page_size()); ++ if (!z->buf) { ++ err_msg = "out of memory for buf"; ++ goto err_free_zbuff; + } + p->data = z; + return 0; ++ ++err_free_zbuff: ++ g_free(z->zbuff); ++err_deflate_end: ++ deflateEnd(&z->zs); ++err_free_z: ++ g_free(z); ++ error_setg(errp, "multifd %u: %s", p->id, err_msg); ++ return -1; + } + + /** +@@ -82,6 +96,8 @@ static void zlib_send_cleanup(MultiFDSendParams *p, Error **errp) + deflateEnd(&z->zs); + g_free(z->zbuff); + z->zbuff = NULL; ++ g_free(z->buf); ++ z->buf = NULL; + g_free(p->data); + p->data = NULL; + } +@@ -114,8 +130,14 @@ static int zlib_send_prepare(MultiFDSendParams *p, Error **errp) + flush = Z_SYNC_FLUSH; + } + ++ /* ++ * Since the VM might be running, the page may be changing concurrently ++ * with compression. zlib does not guarantee that this is safe, ++ * therefore copy the page before calling deflate(). ++ */ ++ memcpy(z->buf, p->pages->block->host + p->normal[i], page_size); + zs->avail_in = page_size; +- zs->next_in = p->pages->block->host + p->normal[i]; ++ zs->next_in = z->buf; + + zs->avail_out = available; + zs->next_out = z->zbuff + out_size; +-- +2.31.1 + diff --git a/SOURCES/kvm-multifd-Implement-zero-copy-write-in-multifd-migrati.patch b/SOURCES/kvm-multifd-Implement-zero-copy-write-in-multifd-migrati.patch new file mode 100644 index 0000000..c7159e1 --- /dev/null +++ b/SOURCES/kvm-multifd-Implement-zero-copy-write-in-multifd-migrati.patch @@ -0,0 +1,182 @@ +From c1a2866d158ac67179fa0d17f1710302eb9a3866 Mon Sep 17 00:00:00 2001 +From: Leonardo Bras +Date: Fri, 13 May 2022 03:28:37 -0300 +Subject: [PATCH 14/18] multifd: Implement zero copy write in multifd migration + (multifd-zero-copy) +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Leonardo Brás +RH-MergeRequest: 95: MSG_ZEROCOPY + Multifd +RH-Commit: [8/11] b93009cc94b2cc4b464b4f68ebfb37b870dd6f7d (LeoBras/centos-qemu-kvm) +RH-Bugzilla: 1968509 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Dr. David Alan Gilbert +RH-Acked-by: Peter Xu + +Implement zero copy send on nocomp_send_write(), by making use of QIOChannel +writev + flags & flush interface. + +Change multifd_send_sync_main() so flush_zero_copy() can be called +after each iteration in order to make sure all dirty pages are sent before +a new iteration is started. It will also flush at the beginning and at the +end of migration. + +Also make it return -1 if flush_zero_copy() fails, in order to cancel +the migration process, and avoid resuming the guest in the target host +without receiving all current RAM. + +This will work fine on RAM migration because the RAM pages are not usually freed, +and there is no problem on changing the pages content between writev_zero_copy() and +the actual sending of the buffer, because this change will dirty the page and +cause it to be re-sent on a next iteration anyway. + +A lot of locked memory may be needed in order to use multifd migration +with zero-copy enabled, so disabling the feature should be necessary for +low-privileged users trying to perform multifd migrations. + +Signed-off-by: Leonardo Bras +Reviewed-by: Peter Xu +Reviewed-by: Daniel P. Berrangé +Message-Id: <20220513062836.965425-9-leobras@redhat.com> +Signed-off-by: Dr. David Alan Gilbert +(cherry picked from commit 5b1d9bab2da4fca3a3caee97c430e5709cb32b7b) +Signed-off-by: Leonardo Bras +--- + migration/migration.c | 11 ++++++++++- + migration/multifd.c | 37 +++++++++++++++++++++++++++++++++++-- + migration/multifd.h | 2 ++ + migration/socket.c | 5 +++-- + 4 files changed, 50 insertions(+), 5 deletions(-) + +diff --git a/migration/migration.c b/migration/migration.c +index d91efb66fe..102236fba0 100644 +--- a/migration/migration.c ++++ b/migration/migration.c +@@ -1485,7 +1485,16 @@ static bool migrate_params_check(MigrationParameters *params, Error **errp) + error_prepend(errp, "Invalid mapping given for block-bitmap-mapping: "); + return false; + } +- ++#ifdef CONFIG_LINUX ++ if (params->zero_copy_send && ++ (!migrate_use_multifd() || ++ params->multifd_compression != MULTIFD_COMPRESSION_NONE || ++ (params->tls_creds && *params->tls_creds))) { ++ error_setg(errp, ++ "Zero copy only available for non-compressed non-TLS multifd migration"); ++ return false; ++ } ++#endif + return true; + } + +diff --git a/migration/multifd.c b/migration/multifd.c +index 8fca6c970e..0b5b41c53f 100644 +--- a/migration/multifd.c ++++ b/migration/multifd.c +@@ -571,6 +571,7 @@ void multifd_save_cleanup(void) + int multifd_send_sync_main(QEMUFile *f) + { + int i; ++ bool flush_zero_copy; + + if (!migrate_use_multifd()) { + return 0; +@@ -581,6 +582,20 @@ int multifd_send_sync_main(QEMUFile *f) + return -1; + } + } ++ ++ /* ++ * When using zero-copy, it's necessary to flush the pages before any of ++ * the pages can be sent again, so we'll make sure the new version of the ++ * pages will always arrive _later_ than the old pages. ++ * ++ * Currently we achieve this by flushing the zero-page requested writes ++ * per ram iteration, but in the future we could potentially optimize it ++ * to be less frequent, e.g. only after we finished one whole scanning of ++ * all the dirty bitmaps. ++ */ ++ ++ flush_zero_copy = migrate_use_zero_copy_send(); ++ + for (i = 0; i < migrate_multifd_channels(); i++) { + MultiFDSendParams *p = &multifd_send_state->params[i]; + +@@ -602,6 +617,17 @@ int multifd_send_sync_main(QEMUFile *f) + ram_counters.transferred += p->packet_len; + qemu_mutex_unlock(&p->mutex); + qemu_sem_post(&p->sem); ++ ++ if (flush_zero_copy && p->c) { ++ int ret; ++ Error *err = NULL; ++ ++ ret = qio_channel_flush(p->c, &err); ++ if (ret < 0) { ++ error_report_err(err); ++ return -1; ++ } ++ } + } + for (i = 0; i < migrate_multifd_channels(); i++) { + MultiFDSendParams *p = &multifd_send_state->params[i]; +@@ -686,8 +712,8 @@ static void *multifd_send_thread(void *opaque) + p->iov[0].iov_base = p->packet; + } + +- ret = qio_channel_writev_all(p->c, p->iov, p->iovs_num, +- &local_err); ++ ret = qio_channel_writev_full_all(p->c, p->iov, p->iovs_num, NULL, ++ 0, p->write_flags, &local_err); + if (ret != 0) { + break; + } +@@ -928,6 +954,13 @@ int multifd_save_setup(Error **errp) + /* We need one extra place for the packet header */ + p->iov = g_new0(struct iovec, page_count + 1); + p->normal = g_new0(ram_addr_t, page_count); ++ ++ if (migrate_use_zero_copy_send()) { ++ p->write_flags = QIO_CHANNEL_WRITE_FLAG_ZERO_COPY; ++ } else { ++ p->write_flags = 0; ++ } ++ + socket_send_channel_create(multifd_new_send_channel_async, p); + } + +diff --git a/migration/multifd.h b/migration/multifd.h +index cd495195ce..7ec688fb4f 100644 +--- a/migration/multifd.h ++++ b/migration/multifd.h +@@ -96,6 +96,8 @@ typedef struct { + uint32_t packet_len; + /* pointer to the packet */ + MultiFDPacket_t *packet; ++ /* multifd flags for sending ram */ ++ int write_flags; + /* multifd flags for each packet */ + uint32_t flags; + /* size of the next packet that contains pages */ +diff --git a/migration/socket.c b/migration/socket.c +index 3754d8f72c..4fd5e85f50 100644 +--- a/migration/socket.c ++++ b/migration/socket.c +@@ -79,8 +79,9 @@ static void socket_outgoing_migration(QIOTask *task, + + trace_migration_socket_outgoing_connected(data->hostname); + +- if (migrate_use_zero_copy_send()) { +- error_setg(&err, "Zero copy send not available in migration"); ++ if (migrate_use_zero_copy_send() && ++ !qio_channel_has_feature(sioc, QIO_CHANNEL_FEATURE_WRITE_ZERO_COPY)) { ++ error_setg(&err, "Zero copy send feature not detected in host kernel"); + } + + out: +-- +2.35.3 + diff --git a/SOURCES/kvm-multifd-Send-header-packet-without-flags-if-zero-cop.patch b/SOURCES/kvm-multifd-Send-header-packet-without-flags-if-zero-cop.patch new file mode 100644 index 0000000..415e3a9 --- /dev/null +++ b/SOURCES/kvm-multifd-Send-header-packet-without-flags-if-zero-cop.patch @@ -0,0 +1,102 @@ +From 63255c13492f42a3236d96e706e5f8e70bb4e219 Mon Sep 17 00:00:00 2001 +From: Leonardo Bras +Date: Fri, 13 May 2022 03:28:36 -0300 +Subject: [PATCH 13/18] multifd: Send header packet without flags if + zero-copy-send is enabled +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Leonardo Brás +RH-MergeRequest: 95: MSG_ZEROCOPY + Multifd +RH-Commit: [7/11] 137eea685e387d3d6aff187ec3fcac05bc16b6e3 (LeoBras/centos-qemu-kvm) +RH-Bugzilla: 1968509 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Dr. David Alan Gilbert +RH-Acked-by: Peter Xu + +Since d48c3a0445 ("multifd: Use a single writev on the send side"), +sending the header packet and the memory pages happens in the same +writev, which can potentially make the migration faster. + +Using channel-socket as example, this works well with the default copying +mechanism of sendmsg(), but with zero-copy-send=true, it will cause +the migration to often break. + +This happens because the header packet buffer gets reused quite often, +and there is a high chance that by the time the MSG_ZEROCOPY mechanism get +to send the buffer, it has already changed, sending the wrong data and +causing the migration to abort. + +It means that, as it is, the buffer for the header packet is not suitable +for sending with MSG_ZEROCOPY. + +In order to enable zero copy for multifd, send the header packet on an +individual write(), without any flags, and the remanining pages with a +writev(), as it was happening before. This only changes how a migration +with zero-copy-send=true works, not changing any current behavior for +migrations with zero-copy-send=false. + +Signed-off-by: Leonardo Bras +Reviewed-by: Peter Xu +Reviewed-by: Daniel P. Berrangé +Message-Id: <20220513062836.965425-8-leobras@redhat.com> +Signed-off-by: Dr. David Alan Gilbert +(cherry picked from commit b7dbdd8e76cd03453c234dbb9578d20969859d74) +Signed-off-by: Leonardo Bras +--- + migration/multifd.c | 22 +++++++++++++++++++--- + 1 file changed, 19 insertions(+), 3 deletions(-) + +diff --git a/migration/multifd.c b/migration/multifd.c +index cdb57439a7..8fca6c970e 100644 +--- a/migration/multifd.c ++++ b/migration/multifd.c +@@ -619,6 +619,7 @@ static void *multifd_send_thread(void *opaque) + MultiFDSendParams *p = opaque; + Error *local_err = NULL; + int ret = 0; ++ bool use_zero_copy_send = migrate_use_zero_copy_send(); + + trace_multifd_send_thread_start(p->id); + rcu_register_thread(); +@@ -641,9 +642,14 @@ static void *multifd_send_thread(void *opaque) + if (p->pending_job) { + uint64_t packet_num = p->packet_num; + uint32_t flags = p->flags; +- p->iovs_num = 1; + p->normal_num = 0; + ++ if (use_zero_copy_send) { ++ p->iovs_num = 0; ++ } else { ++ p->iovs_num = 1; ++ } ++ + for (int i = 0; i < p->pages->num; i++) { + p->normal[p->normal_num] = p->pages->offset[i]; + p->normal_num++; +@@ -667,8 +673,18 @@ static void *multifd_send_thread(void *opaque) + trace_multifd_send(p->id, packet_num, p->normal_num, flags, + p->next_packet_size); + +- p->iov[0].iov_len = p->packet_len; +- p->iov[0].iov_base = p->packet; ++ if (use_zero_copy_send) { ++ /* Send header first, without zerocopy */ ++ ret = qio_channel_write_all(p->c, (void *)p->packet, ++ p->packet_len, &local_err); ++ if (ret != 0) { ++ break; ++ } ++ } else { ++ /* Send header using the same writev call */ ++ p->iov[0].iov_len = p->packet_len; ++ p->iov[0].iov_base = p->packet; ++ } + + ret = qio_channel_writev_all(p->c, p->iov, p->iovs_num, + &local_err); +-- +2.35.3 + diff --git a/SOURCES/kvm-multifd-multifd_send_sync_main-now-returns-negative-.patch b/SOURCES/kvm-multifd-multifd_send_sync_main-now-returns-negative-.patch new file mode 100644 index 0000000..e6d726a --- /dev/null +++ b/SOURCES/kvm-multifd-multifd_send_sync_main-now-returns-negative-.patch @@ -0,0 +1,163 @@ +From 4ca5375a936bc87829c6e2b4620f56c73a5efc70 Mon Sep 17 00:00:00 2001 +From: Leonardo Bras +Date: Fri, 13 May 2022 03:28:35 -0300 +Subject: [PATCH 12/18] multifd: multifd_send_sync_main now returns negative on + error +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Leonardo Brás +RH-MergeRequest: 95: MSG_ZEROCOPY + Multifd +RH-Commit: [6/11] c8ebdee4327d463c74f4b2eeb42d3c964f314c94 (LeoBras/centos-qemu-kvm) +RH-Bugzilla: 1968509 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Dr. David Alan Gilbert +RH-Acked-by: Peter Xu + +Even though multifd_send_sync_main() currently emits error_reports, it's +callers don't really check it before continuing. + +Change multifd_send_sync_main() to return -1 on error and 0 on success. +Also change all it's callers to make use of this change and possibly fail +earlier. + +(This change is important to next patch on multifd zero copy +implementation, to make it sure an error in zero-copy flush does not go +unnoticed. + +Signed-off-by: Leonardo Bras +Reviewed-by: Daniel P. Berrangé +Reviewed-by: Peter Xu +Message-Id: <20220513062836.965425-7-leobras@redhat.com> +Signed-off-by: Dr. David Alan Gilbert +(cherry picked from commit 33d70973a3a6e8c6b62bcbc64d9e488961981007) +Signed-off-by: Leonardo Bras +--- + migration/multifd.c | 10 ++++++---- + migration/multifd.h | 2 +- + migration/ram.c | 29 ++++++++++++++++++++++------- + 3 files changed, 29 insertions(+), 12 deletions(-) + +diff --git a/migration/multifd.c b/migration/multifd.c +index 43998ad117..cdb57439a7 100644 +--- a/migration/multifd.c ++++ b/migration/multifd.c +@@ -568,17 +568,17 @@ void multifd_save_cleanup(void) + multifd_send_state = NULL; + } + +-void multifd_send_sync_main(QEMUFile *f) ++int multifd_send_sync_main(QEMUFile *f) + { + int i; + + if (!migrate_use_multifd()) { +- return; ++ return 0; + } + if (multifd_send_state->pages->num) { + if (multifd_send_pages(f) < 0) { + error_report("%s: multifd_send_pages fail", __func__); +- return; ++ return -1; + } + } + for (i = 0; i < migrate_multifd_channels(); i++) { +@@ -591,7 +591,7 @@ void multifd_send_sync_main(QEMUFile *f) + if (p->quit) { + error_report("%s: channel %d has already quit", __func__, i); + qemu_mutex_unlock(&p->mutex); +- return; ++ return -1; + } + + p->packet_num = multifd_send_state->packet_num++; +@@ -610,6 +610,8 @@ void multifd_send_sync_main(QEMUFile *f) + qemu_sem_wait(&p->sem_sync); + } + trace_multifd_send_sync_main(multifd_send_state->packet_num); ++ ++ return 0; + } + + static void *multifd_send_thread(void *opaque) +diff --git a/migration/multifd.h b/migration/multifd.h +index 4dda900a0b..cd495195ce 100644 +--- a/migration/multifd.h ++++ b/migration/multifd.h +@@ -22,7 +22,7 @@ int multifd_load_cleanup(Error **errp); + bool multifd_recv_all_channels_created(void); + bool multifd_recv_new_channel(QIOChannel *ioc, Error **errp); + void multifd_recv_sync_main(void); +-void multifd_send_sync_main(QEMUFile *f); ++int multifd_send_sync_main(QEMUFile *f); + int multifd_queue_page(QEMUFile *f, RAMBlock *block, ram_addr_t offset); + + /* Multifd Compression flags */ +diff --git a/migration/ram.c b/migration/ram.c +index 0ef4bd63eb..fb6db54642 100644 +--- a/migration/ram.c ++++ b/migration/ram.c +@@ -2903,6 +2903,7 @@ static int ram_save_setup(QEMUFile *f, void *opaque) + { + RAMState **rsp = opaque; + RAMBlock *block; ++ int ret; + + if (compress_threads_save_setup()) { + return -1; +@@ -2937,7 +2938,11 @@ static int ram_save_setup(QEMUFile *f, void *opaque) + ram_control_before_iterate(f, RAM_CONTROL_SETUP); + ram_control_after_iterate(f, RAM_CONTROL_SETUP); + +- multifd_send_sync_main(f); ++ ret = multifd_send_sync_main(f); ++ if (ret < 0) { ++ return ret; ++ } ++ + qemu_put_be64(f, RAM_SAVE_FLAG_EOS); + qemu_fflush(f); + +@@ -3046,7 +3051,11 @@ static int ram_save_iterate(QEMUFile *f, void *opaque) + out: + if (ret >= 0 + && migration_is_setup_or_active(migrate_get_current()->state)) { +- multifd_send_sync_main(rs->f); ++ ret = multifd_send_sync_main(rs->f); ++ if (ret < 0) { ++ return ret; ++ } ++ + qemu_put_be64(f, RAM_SAVE_FLAG_EOS); + qemu_fflush(f); + ram_transferred_add(8); +@@ -3106,13 +3115,19 @@ static int ram_save_complete(QEMUFile *f, void *opaque) + ram_control_after_iterate(f, RAM_CONTROL_FINISH); + } + +- if (ret >= 0) { +- multifd_send_sync_main(rs->f); +- qemu_put_be64(f, RAM_SAVE_FLAG_EOS); +- qemu_fflush(f); ++ if (ret < 0) { ++ return ret; + } + +- return ret; ++ ret = multifd_send_sync_main(rs->f); ++ if (ret < 0) { ++ return ret; ++ } ++ ++ qemu_put_be64(f, RAM_SAVE_FLAG_EOS); ++ qemu_fflush(f); ++ ++ return 0; + } + + static void ram_save_pending(QEMUFile *f, void *opaque, uint64_t max_size, +-- +2.35.3 + diff --git a/SOURCES/kvm-nbd-server-Allow-MULTI_CONN-for-shared-writable-expo.patch b/SOURCES/kvm-nbd-server-Allow-MULTI_CONN-for-shared-writable-expo.patch new file mode 100644 index 0000000..56abcb1 --- /dev/null +++ b/SOURCES/kvm-nbd-server-Allow-MULTI_CONN-for-shared-writable-expo.patch @@ -0,0 +1,381 @@ +From 4a9ddf42788d3f924bdad7746f7aca615f03d7c1 Mon Sep 17 00:00:00 2001 +From: Eric Blake +Date: Wed, 11 May 2022 19:49:24 -0500 +Subject: [PATCH 2/2] nbd/server: Allow MULTI_CONN for shared writable exports +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eric Blake +RH-MergeRequest: 90: Advertise MULTI_CONN on writeable NBD servers +RH-Commit: [2/2] 53f0e885a5ed7f6e4bb14e74fe8e7957e6afe90f (ebblake/centos-qemu-kvm) +RH-Bugzilla: 1708300 +RH-Acked-by: Nir Soffer +RH-Acked-by: Kevin Wolf +RH-Acked-by: Daniel P. Berrangé + +According to the NBD spec, a server that advertises +NBD_FLAG_CAN_MULTI_CONN promises that multiple client connections will +not see any cache inconsistencies: when properly separated by a single +flush, actions performed by one client will be visible to another +client, regardless of which client did the flush. + +We always satisfy these conditions in qemu - even when we support +multiple clients, ALL clients go through a single point of reference +into the block layer, with no local caching. The effect of one client +is instantly visible to the next client. Even if our backend were a +network device, we argue that any multi-path caching effects that +would cause inconsistencies in back-to-back actions not seeing the +effect of previous actions would be a bug in that backend, and not the +fault of caching in qemu. As such, it is safe to unconditionally +advertise CAN_MULTI_CONN for any qemu NBD server situation that +supports parallel clients. + +Note, however, that we don't want to advertise CAN_MULTI_CONN when we +know that a second client cannot connect (for historical reasons, +qemu-nbd defaults to a single connection while nbd-server-add and QMP +commands default to unlimited connections; but we already have +existing means to let either style of NBD server creation alter those +defaults). This is visible by no longer advertising MULTI_CONN for +'qemu-nbd -r' without -e, as in the iotest nbd-qemu-allocation. + +The harder part of this patch is setting up an iotest to demonstrate +behavior of multiple NBD clients to a single server. It might be +possible with parallel qemu-io processes, but I found it easier to do +in python with the help of libnbd, and help from Nir and Vladimir in +writing the test. + +Signed-off-by: Eric Blake +Suggested-by: Nir Soffer +Suggested-by: Vladimir Sementsov-Ogievskiy +Message-Id: <20220512004924.417153-3-eblake@redhat.com> +Signed-off-by: Kevin Wolf + +(cherry picked from commit 58a6fdcc9efb2a7c1ef4893dca4aa5e8020ca3dc) +Conflicts: + nbd/server.c - context, e5fb29d5 not backported +Signed-off-by: Eric Blake +--- + MAINTAINERS | 1 + + blockdev-nbd.c | 5 + + docs/interop/nbd.txt | 1 + + docs/tools/qemu-nbd.rst | 3 +- + include/block/nbd.h | 3 +- + nbd/server.c | 10 +- + qapi/block-export.json | 8 +- + tests/qemu-iotests/tests/nbd-multiconn | 145 ++++++++++++++++++ + tests/qemu-iotests/tests/nbd-multiconn.out | 5 + + .../tests/nbd-qemu-allocation.out | 2 +- + 10 files changed, 172 insertions(+), 11 deletions(-) + create mode 100755 tests/qemu-iotests/tests/nbd-multiconn + create mode 100644 tests/qemu-iotests/tests/nbd-multiconn.out + +diff --git a/MAINTAINERS b/MAINTAINERS +index 4ad2451e03..2fe20a49ab 100644 +--- a/MAINTAINERS ++++ b/MAINTAINERS +@@ -3370,6 +3370,7 @@ F: qemu-nbd.* + F: blockdev-nbd.c + F: docs/interop/nbd.txt + F: docs/tools/qemu-nbd.rst ++F: tests/qemu-iotests/tests/*nbd* + T: git https://repo.or.cz/qemu/ericb.git nbd + T: git https://src.openvz.org/scm/~vsementsov/qemu.git nbd + +diff --git a/blockdev-nbd.c b/blockdev-nbd.c +index add41a23af..c6d9b0324c 100644 +--- a/blockdev-nbd.c ++++ b/blockdev-nbd.c +@@ -44,6 +44,11 @@ bool nbd_server_is_running(void) + return nbd_server || qemu_nbd_connections >= 0; + } + ++int nbd_server_max_connections(void) ++{ ++ return nbd_server ? nbd_server->max_connections : qemu_nbd_connections; ++} ++ + static void nbd_blockdev_client_closed(NBDClient *client, bool ignored) + { + nbd_client_put(client); +diff --git a/docs/interop/nbd.txt b/docs/interop/nbd.txt +index bdb0f2a41a..f5ca25174a 100644 +--- a/docs/interop/nbd.txt ++++ b/docs/interop/nbd.txt +@@ -68,3 +68,4 @@ NBD_CMD_BLOCK_STATUS for "qemu:dirty-bitmap:", NBD_CMD_CACHE + * 4.2: NBD_FLAG_CAN_MULTI_CONN for shareable read-only exports, + NBD_CMD_FLAG_FAST_ZERO + * 5.2: NBD_CMD_BLOCK_STATUS for "qemu:allocation-depth" ++* 7.1: NBD_FLAG_CAN_MULTI_CONN for shareable writable exports +diff --git a/docs/tools/qemu-nbd.rst b/docs/tools/qemu-nbd.rst +index 4c950f6199..8e08a29e89 100644 +--- a/docs/tools/qemu-nbd.rst ++++ b/docs/tools/qemu-nbd.rst +@@ -139,8 +139,7 @@ driver options if :option:`--image-opts` is specified. + .. option:: -e, --shared=NUM + + Allow up to *NUM* clients to share the device (default +- ``1``), 0 for unlimited. Safe for readers, but for now, +- consistency is not guaranteed between multiple writers. ++ ``1``), 0 for unlimited. + + .. option:: -t, --persistent + +diff --git a/include/block/nbd.h b/include/block/nbd.h +index c5a29ce1c6..c74b7a9d2e 100644 +--- a/include/block/nbd.h ++++ b/include/block/nbd.h +@@ -1,5 +1,5 @@ + /* +- * Copyright (C) 2016-2020 Red Hat, Inc. ++ * Copyright (C) 2016-2022 Red Hat, Inc. + * Copyright (C) 2005 Anthony Liguori + * + * Network Block Device +@@ -346,6 +346,7 @@ void nbd_client_put(NBDClient *client); + + void nbd_server_is_qemu_nbd(int max_connections); + bool nbd_server_is_running(void); ++int nbd_server_max_connections(void); + void nbd_server_start(SocketAddress *addr, const char *tls_creds, + const char *tls_authz, uint32_t max_connections, + Error **errp); +diff --git a/nbd/server.c b/nbd/server.c +index c5644fd3f6..6e2157acfa 100644 +--- a/nbd/server.c ++++ b/nbd/server.c +@@ -1,5 +1,5 @@ + /* +- * Copyright (C) 2016-2021 Red Hat, Inc. ++ * Copyright (C) 2016-2022 Red Hat, Inc. + * Copyright (C) 2005 Anthony Liguori + * + * Network Block Device Server Side +@@ -1642,7 +1642,6 @@ static int nbd_export_create(BlockExport *blk_exp, BlockExportOptions *exp_args, + int64_t size; + uint64_t perm, shared_perm; + bool readonly = !exp_args->writable; +- bool shared = !exp_args->writable; + strList *bitmaps; + size_t i; + int ret; +@@ -1693,11 +1692,12 @@ static int nbd_export_create(BlockExport *blk_exp, BlockExportOptions *exp_args, + exp->description = g_strdup(arg->description); + exp->nbdflags = (NBD_FLAG_HAS_FLAGS | NBD_FLAG_SEND_FLUSH | + NBD_FLAG_SEND_FUA | NBD_FLAG_SEND_CACHE); ++ ++ if (nbd_server_max_connections() != 1) { ++ exp->nbdflags |= NBD_FLAG_CAN_MULTI_CONN; ++ } + if (readonly) { + exp->nbdflags |= NBD_FLAG_READ_ONLY; +- if (shared) { +- exp->nbdflags |= NBD_FLAG_CAN_MULTI_CONN; +- } + } else { + exp->nbdflags |= (NBD_FLAG_SEND_TRIM | NBD_FLAG_SEND_WRITE_ZEROES | + NBD_FLAG_SEND_FAST_ZERO); +diff --git a/qapi/block-export.json b/qapi/block-export.json +index 1e34927f85..755ccc89b1 100644 +--- a/qapi/block-export.json ++++ b/qapi/block-export.json +@@ -21,7 +21,9 @@ + # recreated on the fly while the NBD server is active. + # If missing, it will default to denying access (since 4.0). + # @max-connections: The maximum number of connections to allow at the same +-# time, 0 for unlimited. (since 5.2; default: 0) ++# time, 0 for unlimited. Setting this to 1 also stops ++# the server from advertising multiple client support ++# (since 5.2; default: 0) + # + # Since: 4.2 + ## +@@ -50,7 +52,9 @@ + # recreated on the fly while the NBD server is active. + # If missing, it will default to denying access (since 4.0). + # @max-connections: The maximum number of connections to allow at the same +-# time, 0 for unlimited. (since 5.2; default: 0) ++# time, 0 for unlimited. Setting this to 1 also stops ++# the server from advertising multiple client support ++# (since 5.2; default: 0). + # + # Returns: error if the server is already running. + # +diff --git a/tests/qemu-iotests/tests/nbd-multiconn b/tests/qemu-iotests/tests/nbd-multiconn +new file mode 100755 +index 0000000000..b121f2e363 +--- /dev/null ++++ b/tests/qemu-iotests/tests/nbd-multiconn +@@ -0,0 +1,145 @@ ++#!/usr/bin/env python3 ++# group: rw auto quick ++# ++# Test cases for NBD multi-conn advertisement ++# ++# Copyright (C) 2022 Red Hat, Inc. ++# ++# This program is free software; you can redistribute it and/or modify ++# it under the terms of the GNU General Public License as published by ++# the Free Software Foundation; either version 2 of the License, or ++# (at your option) any later version. ++# ++# This program is distributed in the hope that it will be useful, ++# but WITHOUT ANY WARRANTY; without even the implied warranty of ++# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++# GNU General Public License for more details. ++# ++# You should have received a copy of the GNU General Public License ++# along with this program. If not, see . ++ ++import os ++from contextlib import contextmanager ++import iotests ++from iotests import qemu_img_create, qemu_io ++ ++ ++disk = os.path.join(iotests.test_dir, 'disk') ++size = '4M' ++nbd_sock = os.path.join(iotests.sock_dir, 'nbd_sock') ++nbd_uri = 'nbd+unix:///{}?socket=' + nbd_sock ++ ++ ++@contextmanager ++def open_nbd(export_name): ++ h = nbd.NBD() ++ try: ++ h.connect_uri(nbd_uri.format(export_name)) ++ yield h ++ finally: ++ h.shutdown() ++ ++class TestNbdMulticonn(iotests.QMPTestCase): ++ def setUp(self): ++ qemu_img_create('-f', iotests.imgfmt, disk, size) ++ qemu_io('-c', 'w -P 1 0 2M', '-c', 'w -P 2 2M 2M', disk) ++ ++ self.vm = iotests.VM() ++ self.vm.launch() ++ result = self.vm.qmp('blockdev-add', { ++ 'driver': 'qcow2', ++ 'node-name': 'n', ++ 'file': {'driver': 'file', 'filename': disk} ++ }) ++ self.assert_qmp(result, 'return', {}) ++ ++ def tearDown(self): ++ self.vm.shutdown() ++ os.remove(disk) ++ try: ++ os.remove(nbd_sock) ++ except OSError: ++ pass ++ ++ @contextmanager ++ def run_server(self, max_connections=None): ++ args = { ++ 'addr': { ++ 'type': 'unix', ++ 'data': {'path': nbd_sock} ++ } ++ } ++ if max_connections is not None: ++ args['max-connections'] = max_connections ++ ++ result = self.vm.qmp('nbd-server-start', args) ++ self.assert_qmp(result, 'return', {}) ++ yield ++ ++ result = self.vm.qmp('nbd-server-stop') ++ self.assert_qmp(result, 'return', {}) ++ ++ def add_export(self, name, writable=None): ++ args = { ++ 'type': 'nbd', ++ 'id': name, ++ 'node-name': 'n', ++ 'name': name, ++ } ++ if writable is not None: ++ args['writable'] = writable ++ ++ result = self.vm.qmp('block-export-add', args) ++ self.assert_qmp(result, 'return', {}) ++ ++ def test_default_settings(self): ++ with self.run_server(): ++ self.add_export('r') ++ self.add_export('w', writable=True) ++ with open_nbd('r') as h: ++ self.assertTrue(h.can_multi_conn()) ++ with open_nbd('w') as h: ++ self.assertTrue(h.can_multi_conn()) ++ ++ def test_limited_connections(self): ++ with self.run_server(max_connections=1): ++ self.add_export('r') ++ self.add_export('w', writable=True) ++ with open_nbd('r') as h: ++ self.assertFalse(h.can_multi_conn()) ++ with open_nbd('w') as h: ++ self.assertFalse(h.can_multi_conn()) ++ ++ def test_parallel_writes(self): ++ with self.run_server(): ++ self.add_export('w', writable=True) ++ ++ clients = [nbd.NBD() for _ in range(3)] ++ for c in clients: ++ c.connect_uri(nbd_uri.format('w')) ++ self.assertTrue(c.can_multi_conn()) ++ ++ initial_data = clients[0].pread(1024 * 1024, 0) ++ self.assertEqual(initial_data, b'\x01' * 1024 * 1024) ++ ++ updated_data = b'\x03' * 1024 * 1024 ++ clients[1].pwrite(updated_data, 0) ++ clients[2].flush() ++ current_data = clients[0].pread(1024 * 1024, 0) ++ ++ self.assertEqual(updated_data, current_data) ++ ++ for i in range(3): ++ clients[i].shutdown() ++ ++ ++if __name__ == '__main__': ++ try: ++ # Easier to use libnbd than to try and set up parallel ++ # 'qemu-nbd --list' or 'qemu-io' processes, but not all systems ++ # have libnbd installed. ++ import nbd # type: ignore ++ ++ iotests.main(supported_fmts=['qcow2']) ++ except ImportError: ++ iotests.notrun('libnbd not installed') +diff --git a/tests/qemu-iotests/tests/nbd-multiconn.out b/tests/qemu-iotests/tests/nbd-multiconn.out +new file mode 100644 +index 0000000000..8d7e996700 +--- /dev/null ++++ b/tests/qemu-iotests/tests/nbd-multiconn.out +@@ -0,0 +1,5 @@ ++... ++---------------------------------------------------------------------- ++Ran 3 tests ++ ++OK +diff --git a/tests/qemu-iotests/tests/nbd-qemu-allocation.out b/tests/qemu-iotests/tests/nbd-qemu-allocation.out +index 0bf1abb063..9d938db24e 100644 +--- a/tests/qemu-iotests/tests/nbd-qemu-allocation.out ++++ b/tests/qemu-iotests/tests/nbd-qemu-allocation.out +@@ -17,7 +17,7 @@ wrote 2097152/2097152 bytes at offset 1048576 + exports available: 1 + export: '' + size: 4194304 +- flags: 0x58f ( readonly flush fua df multi cache ) ++ flags: 0x48f ( readonly flush fua df cache ) + min block: 1 + opt block: 4096 + max block: 33554432 +-- +2.31.1 + diff --git a/SOURCES/kvm-numa-Enable-numa-for-SGX-EPC-sections.patch b/SOURCES/kvm-numa-Enable-numa-for-SGX-EPC-sections.patch deleted file mode 100644 index e26bfcf..0000000 --- a/SOURCES/kvm-numa-Enable-numa-for-SGX-EPC-sections.patch +++ /dev/null @@ -1,287 +0,0 @@ -From 6274a2a09a8931188889467b104bf2e2fc39cb54 Mon Sep 17 00:00:00 2001 -From: Yang Zhong -Date: Mon, 1 Nov 2021 12:20:05 -0400 -Subject: [PATCH 01/12] numa: Enable numa for SGX EPC sections - -RH-Author: Paul Lai -RH-MergeRequest: 65: Enable SGX and add SGX Numa support -RH-Commit: [1/5] ff69d138c3f5903096388ec7ccf8dc5e6c6c6ffb -RH-Bugzilla: 2033708 -RH-Acked-by: Paolo Bonzini -RH-Acked-by: Bandan Das -RH-Acked-by: Cornelia Huck - -The basic SGX did not enable numa for SGX EPC sections, which -result in all EPC sections located in numa node 0. This patch -enable SGX numa function in the guest and the EPC section can -work with RAM as one numa node. - -The Guest kernel related log: -[ 0.009981] ACPI: SRAT: Node 0 PXM 0 [mem 0x180000000-0x183ffffff] -[ 0.009982] ACPI: SRAT: Node 1 PXM 1 [mem 0x184000000-0x185bfffff] -The SRAT table can normally show SGX EPC sections menory info in different -numa nodes. - -The SGX EPC numa related command: - ...... - -m 4G,maxmem=20G \ - -smp sockets=2,cores=2 \ - -cpu host,+sgx-provisionkey \ - -object memory-backend-ram,size=2G,host-nodes=0,policy=bind,id=node0 \ - -object memory-backend-epc,id=mem0,size=64M,prealloc=on,host-nodes=0,policy=bind \ - -numa node,nodeid=0,cpus=0-1,memdev=node0 \ - -object memory-backend-ram,size=2G,host-nodes=1,policy=bind,id=node1 \ - -object memory-backend-epc,id=mem1,size=28M,prealloc=on,host-nodes=1,policy=bind \ - -numa node,nodeid=1,cpus=2-3,memdev=node1 \ - -M sgx-epc.0.memdev=mem0,sgx-epc.0.node=0,sgx-epc.1.memdev=mem1,sgx-epc.1.node=1 \ - ...... - -Signed-off-by: Yang Zhong -Message-Id: <20211101162009.62161-2-yang.zhong@intel.com> -Signed-off-by: Paolo Bonzini -(cherry picked from commit 1105812382e1126d86dddc16b3700f8c79dc93d1) -Signed-off-by: Paul Lai ---- - hw/core/numa.c | 5 ++--- - hw/i386/acpi-build.c | 2 ++ - hw/i386/sgx-epc.c | 3 +++ - hw/i386/sgx-stub.c | 4 ++++ - hw/i386/sgx.c | 44 +++++++++++++++++++++++++++++++++++++++ - include/hw/i386/sgx-epc.h | 3 +++ - monitor/hmp-cmds.c | 1 + - qapi/machine.json | 10 ++++++++- - qemu-options.hx | 4 ++-- - 9 files changed, 70 insertions(+), 6 deletions(-) - -diff --git a/hw/core/numa.c b/hw/core/numa.c -index e6050b2273..1aa05dcf42 100644 ---- a/hw/core/numa.c -+++ b/hw/core/numa.c -@@ -784,9 +784,8 @@ static void numa_stat_memory_devices(NumaNodeMem node_mem[]) - break; - case MEMORY_DEVICE_INFO_KIND_SGX_EPC: - se = value->u.sgx_epc.data; -- /* TODO: once we support numa, assign to right node */ -- node_mem[0].node_mem += se->size; -- node_mem[0].node_plugged_mem += se->size; -+ node_mem[se->node].node_mem += se->size; -+ node_mem[se->node].node_plugged_mem = 0; - break; - default: - g_assert_not_reached(); -diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c -index a99c6e4fe3..8383b83ee3 100644 ---- a/hw/i386/acpi-build.c -+++ b/hw/i386/acpi-build.c -@@ -2068,6 +2068,8 @@ build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine) - nvdimm_build_srat(table_data); - } - -+ sgx_epc_build_srat(table_data); -+ - /* - * TODO: this part is not in ACPI spec and current linux kernel boots fine - * without these entries. But I recall there were issues the last time I -diff --git a/hw/i386/sgx-epc.c b/hw/i386/sgx-epc.c -index e508827e78..96b2940d75 100644 ---- a/hw/i386/sgx-epc.c -+++ b/hw/i386/sgx-epc.c -@@ -21,6 +21,7 @@ - - static Property sgx_epc_properties[] = { - DEFINE_PROP_UINT64(SGX_EPC_ADDR_PROP, SGXEPCDevice, addr, 0), -+ DEFINE_PROP_UINT32(SGX_EPC_NUMA_NODE_PROP, SGXEPCDevice, node, 0), - DEFINE_PROP_LINK(SGX_EPC_MEMDEV_PROP, SGXEPCDevice, hostmem, - TYPE_MEMORY_BACKEND_EPC, HostMemoryBackendEpc *), - DEFINE_PROP_END_OF_LIST(), -@@ -139,6 +140,8 @@ static void sgx_epc_md_fill_device_info(const MemoryDeviceState *md, - se->memaddr = epc->addr; - se->size = object_property_get_uint(OBJECT(epc), SGX_EPC_SIZE_PROP, - NULL); -+ se->node = object_property_get_uint(OBJECT(epc), SGX_EPC_NUMA_NODE_PROP, -+ NULL); - se->memdev = object_get_canonical_path(OBJECT(epc->hostmem)); - - info->u.sgx_epc.data = se; -diff --git a/hw/i386/sgx-stub.c b/hw/i386/sgx-stub.c -index c9b379e665..26833eb233 100644 ---- a/hw/i386/sgx-stub.c -+++ b/hw/i386/sgx-stub.c -@@ -6,6 +6,10 @@ - #include "qapi/error.h" - #include "qapi/qapi-commands-misc-target.h" - -+void sgx_epc_build_srat(GArray *table_data) -+{ -+} -+ - SGXInfo *qmp_query_sgx(Error **errp) - { - error_setg(errp, "SGX support is not compiled in"); -diff --git a/hw/i386/sgx.c b/hw/i386/sgx.c -index 8fef3dd8fa..d04299904a 100644 ---- a/hw/i386/sgx.c -+++ b/hw/i386/sgx.c -@@ -23,6 +23,7 @@ - #include "sysemu/hw_accel.h" - #include "sysemu/reset.h" - #include -+#include "hw/acpi/aml-build.h" - - #define SGX_MAX_EPC_SECTIONS 8 - #define SGX_CPUID_EPC_INVALID 0x0 -@@ -36,6 +37,46 @@ - - #define RETRY_NUM 2 - -+static int sgx_epc_device_list(Object *obj, void *opaque) -+{ -+ GSList **list = opaque; -+ -+ if (object_dynamic_cast(obj, TYPE_SGX_EPC)) { -+ *list = g_slist_append(*list, DEVICE(obj)); -+ } -+ -+ object_child_foreach(obj, sgx_epc_device_list, opaque); -+ return 0; -+} -+ -+static GSList *sgx_epc_get_device_list(void) -+{ -+ GSList *list = NULL; -+ -+ object_child_foreach(qdev_get_machine(), sgx_epc_device_list, &list); -+ return list; -+} -+ -+void sgx_epc_build_srat(GArray *table_data) -+{ -+ GSList *device_list = sgx_epc_get_device_list(); -+ -+ for (; device_list; device_list = device_list->next) { -+ DeviceState *dev = device_list->data; -+ Object *obj = OBJECT(dev); -+ uint64_t addr, size; -+ int node; -+ -+ node = object_property_get_uint(obj, SGX_EPC_NUMA_NODE_PROP, -+ &error_abort); -+ addr = object_property_get_uint(obj, SGX_EPC_ADDR_PROP, &error_abort); -+ size = object_property_get_uint(obj, SGX_EPC_SIZE_PROP, &error_abort); -+ -+ build_srat_memory(table_data, addr, size, node, MEM_AFFINITY_ENABLED); -+ } -+ g_slist_free(device_list); -+} -+ - static uint64_t sgx_calc_section_metric(uint64_t low, uint64_t high) - { - return (low & MAKE_64BIT_MASK(12, 20)) + -@@ -226,6 +267,9 @@ void pc_machine_init_sgx_epc(PCMachineState *pcms) - /* set the memdev link with memory backend */ - object_property_parse(obj, SGX_EPC_MEMDEV_PROP, list->value->memdev, - &error_fatal); -+ /* set the numa node property for sgx epc object */ -+ object_property_set_uint(obj, SGX_EPC_NUMA_NODE_PROP, list->value->node, -+ &error_fatal); - object_property_set_bool(obj, "realized", true, &error_fatal); - object_unref(obj); - } -diff --git a/include/hw/i386/sgx-epc.h b/include/hw/i386/sgx-epc.h -index a6a65be854..581fac389a 100644 ---- a/include/hw/i386/sgx-epc.h -+++ b/include/hw/i386/sgx-epc.h -@@ -25,6 +25,7 @@ - #define SGX_EPC_ADDR_PROP "addr" - #define SGX_EPC_SIZE_PROP "size" - #define SGX_EPC_MEMDEV_PROP "memdev" -+#define SGX_EPC_NUMA_NODE_PROP "node" - - /** - * SGXEPCDevice: -@@ -38,6 +39,7 @@ typedef struct SGXEPCDevice { - - /* public */ - uint64_t addr; -+ uint32_t node; - HostMemoryBackendEpc *hostmem; - } SGXEPCDevice; - -@@ -56,6 +58,7 @@ typedef struct SGXEPCState { - } SGXEPCState; - - bool sgx_epc_get_section(int section_nr, uint64_t *addr, uint64_t *size); -+void sgx_epc_build_srat(GArray *table_data); - - static inline uint64_t sgx_epc_above_4g_end(SGXEPCState *sgx_epc) - { -diff --git a/monitor/hmp-cmds.c b/monitor/hmp-cmds.c -index 9c91bf93e9..2669156b28 100644 ---- a/monitor/hmp-cmds.c -+++ b/monitor/hmp-cmds.c -@@ -1810,6 +1810,7 @@ void hmp_info_memory_devices(Monitor *mon, const QDict *qdict) - se->id ? se->id : ""); - monitor_printf(mon, " memaddr: 0x%" PRIx64 "\n", se->memaddr); - monitor_printf(mon, " size: %" PRIu64 "\n", se->size); -+ monitor_printf(mon, " node: %" PRId64 "\n", se->node); - monitor_printf(mon, " memdev: %s\n", se->memdev); - break; - default: -diff --git a/qapi/machine.json b/qapi/machine.json -index 067e3f5378..16e771affc 100644 ---- a/qapi/machine.json -+++ b/qapi/machine.json -@@ -1207,12 +1207,15 @@ - # - # @memdev: memory backend linked with device - # -+# @node: the numa node -+# - # Since: 6.2 - ## - { 'struct': 'SgxEPCDeviceInfo', - 'data': { '*id': 'str', - 'memaddr': 'size', - 'size': 'size', -+ 'node': 'int', - 'memdev': 'str' - } - } -@@ -1285,10 +1288,15 @@ - # - # @memdev: memory backend linked with device - # -+# @node: the numa node -+# - # Since: 6.2 - ## - { 'struct': 'SgxEPC', -- 'data': { 'memdev': 'str' } } -+ 'data': { 'memdev': 'str', -+ 'node': 'int' -+ } -+} - - ## - # @SgxEPCProperties: -diff --git a/qemu-options.hx b/qemu-options.hx -index 94c4a8dbaf..4b7798088b 100644 ---- a/qemu-options.hx -+++ b/qemu-options.hx -@@ -127,11 +127,11 @@ SRST - ERST - - DEF("M", HAS_ARG, QEMU_OPTION_M, -- " sgx-epc.0.memdev=memid\n", -+ " sgx-epc.0.memdev=memid,sgx-epc.0.node=numaid\n", - QEMU_ARCH_ALL) - - SRST --``sgx-epc.0.memdev=@var{memid}`` -+``sgx-epc.0.memdev=@var{memid},sgx-epc.0.node=@var{numaid}`` - Define an SGX EPC section. - ERST - --- -2.27.0 - diff --git a/SOURCES/kvm-numa-Support-SGX-numa-in-the-monitor-and-Libvirt-int.patch b/SOURCES/kvm-numa-Support-SGX-numa-in-the-monitor-and-Libvirt-int.patch deleted file mode 100644 index de4c4b1..0000000 --- a/SOURCES/kvm-numa-Support-SGX-numa-in-the-monitor-and-Libvirt-int.patch +++ /dev/null @@ -1,210 +0,0 @@ -From 0f75501ba348dc9fb3ce0198ceafc8093149457d Mon Sep 17 00:00:00 2001 -From: Yang Zhong -Date: Mon, 1 Nov 2021 12:20:07 -0400 -Subject: [PATCH 02/12] numa: Support SGX numa in the monitor and Libvirt - interfaces - -RH-Author: Paul Lai -RH-MergeRequest: 65: Enable SGX and add SGX Numa support -RH-Commit: [2/5] 8c19cfb1a139fd4dbac771e695a133f16a68437f -RH-Bugzilla: 2033708 -RH-Acked-by: Paolo Bonzini -RH-Acked-by: Bandan Das -RH-Acked-by: Cornelia Huck - -Add the SGXEPCSection list into SGXInfo to show the multiple -SGX EPC sections detailed info, not the total size like before. -This patch can enable numa support for 'info sgx' command and -QMP interfaces. The new interfaces show each EPC section info -in one numa node. Libvirt can use QMP interface to get the -detailed host SGX EPC capabilities to decide how to allocate -host EPC sections to guest. - -(qemu) info sgx - SGX support: enabled - SGX1 support: enabled - SGX2 support: enabled - FLC support: enabled - NUMA node #0: size=67108864 - NUMA node #1: size=29360128 - -The QMP interface show: -(QEMU) query-sgx -{"return": {"sgx": true, "sgx2": true, "sgx1": true, "sections": \ -[{"node": 0, "size": 67108864}, {"node": 1, "size": 29360128}], "flc": true}} - -(QEMU) query-sgx-capabilities -{"return": {"sgx": true, "sgx2": true, "sgx1": true, "sections": \ -[{"node": 0, "size": 17070817280}, {"node": 1, "size": 17079205888}], "flc": true}} - -Signed-off-by: Yang Zhong -Message-Id: <20211101162009.62161-4-yang.zhong@intel.com> -Signed-off-by: Paolo Bonzini -(cherry picked from commit 4755927ae12547c2e7cb22c5fa1b39038c6c11b1) -Signed-off-by: Paul Lai ---- - hw/i386/sgx.c | 51 +++++++++++++++++++++++++++++++++++-------- - qapi/misc-target.json | 19 ++++++++++++++-- - 2 files changed, 59 insertions(+), 11 deletions(-) - -diff --git a/hw/i386/sgx.c b/hw/i386/sgx.c -index d04299904a..5de5dd0893 100644 ---- a/hw/i386/sgx.c -+++ b/hw/i386/sgx.c -@@ -83,11 +83,13 @@ static uint64_t sgx_calc_section_metric(uint64_t low, uint64_t high) - ((high & MAKE_64BIT_MASK(0, 20)) << 32); - } - --static uint64_t sgx_calc_host_epc_section_size(void) -+static SGXEPCSectionList *sgx_calc_host_epc_sections(void) - { -+ SGXEPCSectionList *head = NULL, **tail = &head; -+ SGXEPCSection *section; - uint32_t i, type; - uint32_t eax, ebx, ecx, edx; -- uint64_t size = 0; -+ uint32_t j = 0; - - for (i = 0; i < SGX_MAX_EPC_SECTIONS; i++) { - host_cpuid(0x12, i + 2, &eax, &ebx, &ecx, &edx); -@@ -101,10 +103,13 @@ static uint64_t sgx_calc_host_epc_section_size(void) - break; - } - -- size += sgx_calc_section_metric(ecx, edx); -+ section = g_new0(SGXEPCSection, 1); -+ section->node = j++; -+ section->size = sgx_calc_section_metric(ecx, edx); -+ QAPI_LIST_APPEND(tail, section); - } - -- return size; -+ return head; - } - - static void sgx_epc_reset(void *opaque) -@@ -168,13 +173,35 @@ SGXInfo *qmp_query_sgx_capabilities(Error **errp) - info->sgx1 = eax & (1U << 0) ? true : false; - info->sgx2 = eax & (1U << 1) ? true : false; - -- info->section_size = sgx_calc_host_epc_section_size(); -+ info->sections = sgx_calc_host_epc_sections(); - - close(fd); - - return info; - } - -+static SGXEPCSectionList *sgx_get_epc_sections_list(void) -+{ -+ GSList *device_list = sgx_epc_get_device_list(); -+ SGXEPCSectionList *head = NULL, **tail = &head; -+ SGXEPCSection *section; -+ -+ for (; device_list; device_list = device_list->next) { -+ DeviceState *dev = device_list->data; -+ Object *obj = OBJECT(dev); -+ -+ section = g_new0(SGXEPCSection, 1); -+ section->node = object_property_get_uint(obj, SGX_EPC_NUMA_NODE_PROP, -+ &error_abort); -+ section->size = object_property_get_uint(obj, SGX_EPC_SIZE_PROP, -+ &error_abort); -+ QAPI_LIST_APPEND(tail, section); -+ } -+ g_slist_free(device_list); -+ -+ return head; -+} -+ - SGXInfo *qmp_query_sgx(Error **errp) - { - SGXInfo *info = NULL; -@@ -193,14 +220,13 @@ SGXInfo *qmp_query_sgx(Error **errp) - return NULL; - } - -- SGXEPCState *sgx_epc = &pcms->sgx_epc; - info = g_new0(SGXInfo, 1); - - info->sgx = true; - info->sgx1 = true; - info->sgx2 = true; - info->flc = true; -- info->section_size = sgx_epc->size; -+ info->sections = sgx_get_epc_sections_list(); - - return info; - } -@@ -208,6 +234,7 @@ SGXInfo *qmp_query_sgx(Error **errp) - void hmp_info_sgx(Monitor *mon, const QDict *qdict) - { - Error *err = NULL; -+ SGXEPCSectionList *section_list, *section; - g_autoptr(SGXInfo) info = qmp_query_sgx(&err); - - if (err) { -@@ -222,8 +249,14 @@ void hmp_info_sgx(Monitor *mon, const QDict *qdict) - info->sgx2 ? "enabled" : "disabled"); - monitor_printf(mon, "FLC support: %s\n", - info->flc ? "enabled" : "disabled"); -- monitor_printf(mon, "size: %" PRIu64 "\n", -- info->section_size); -+ -+ section_list = info->sections; -+ for (section = section_list; section; section = section->next) { -+ monitor_printf(mon, "NUMA node #%" PRId64 ": ", -+ section->value->node); -+ monitor_printf(mon, "size=%" PRIu64 "\n", -+ section->value->size); -+ } - } - - bool sgx_epc_get_section(int section_nr, uint64_t *addr, uint64_t *size) -diff --git a/qapi/misc-target.json b/qapi/misc-target.json -index 5aa2b95b7d..1022aa0184 100644 ---- a/qapi/misc-target.json -+++ b/qapi/misc-target.json -@@ -337,6 +337,21 @@ - 'if': 'TARGET_ARM' } - - -+## -+# @SGXEPCSection: -+# -+# Information about intel SGX EPC section info -+# -+# @node: the numa node -+# -+# @size: the size of epc section -+# -+# Since: 6.2 -+## -+{ 'struct': 'SGXEPCSection', -+ 'data': { 'node': 'int', -+ 'size': 'uint64'}} -+ - ## - # @SGXInfo: - # -@@ -350,7 +365,7 @@ - # - # @flc: true if FLC is supported - # --# @section-size: The EPC section size for guest -+# @sections: The EPC sections info for guest - # - # Since: 6.2 - ## -@@ -359,7 +374,7 @@ - 'sgx1': 'bool', - 'sgx2': 'bool', - 'flc': 'bool', -- 'section-size': 'uint64'}, -+ 'sections': ['SGXEPCSection']}, - 'if': 'TARGET_I386' } - - ## --- -2.27.0 - diff --git a/SOURCES/kvm-pc-bios-s390-ccw-Fix-booting-with-logical-block-size.patch b/SOURCES/kvm-pc-bios-s390-ccw-Fix-booting-with-logical-block-size.patch new file mode 100644 index 0000000..1bb8ea5 --- /dev/null +++ b/SOURCES/kvm-pc-bios-s390-ccw-Fix-booting-with-logical-block-size.patch @@ -0,0 +1,63 @@ +From 03996a8a826c9186e4a16e1b4757f1ef5947a503 Mon Sep 17 00:00:00 2001 +From: Thomas Huth +Date: Fri, 5 Aug 2022 11:42:14 +0200 +Subject: [PATCH 07/11] pc-bios/s390-ccw: Fix booting with logical block size < + physical block size + +RH-Author: Thomas Huth +RH-MergeRequest: 113: pc-bios/s390-ccw: Fix booting with logical block size < physical block size +RH-Commit: [1/1] a45ff477bc7d7011ea6c4d42a1aade213d1e4690 (thuth/qemu-kvm-cs9) +RH-Bugzilla: 2112303 +RH-Acked-by: Cornelia Huck +RH-Acked-by: David Hildenbrand +RH-Acked-by: Claudio Imbrenda + +For accessing single blocks during boot, it's the logical block size that +matters. (Physical block sizes are rather interesting e.g. for creating +file systems with the correct alignment for speed reasons etc.). +So the s390-ccw bios has to use the logical block size for calculating +sector numbers during the boot phase, the "physical_block_exp" shift +value must not be taken into account. This change fixes the boot process +when the guest hast been installed on a disk where the logical block size +differs from the physical one, e.g. if the guest has been installed +like this: + + qemu-system-s390x -nographic -accel kvm -m 2G \ + -drive if=none,id=d1,file=fedora.iso,format=raw,media=cdrom \ + -device virtio-scsi -device scsi-cd,drive=d1 \ + -drive if=none,id=d2,file=test.qcow2,format=qcow2 + -device virtio-blk,drive=d2,physical_block_size=4096,logical_block_size=512 + +Linux correctly uses the logical block size of 512 for the installation, +but the s390-ccw bios tries to boot from a disk with 4096 block size so +far, as long as this patch has not been applied yet (well, it used to work +by accident in the past due to the virtio_assume_scsi() hack that used to +enforce 512 byte sectors on all virtio-block disks, but that hack has been +well removed in commit 5447de2619050a0a4d to fix other scenarios). + +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2112303 +Message-Id: <20220805094214.285223-1-thuth@redhat.com> +Reviewed-by: Cornelia Huck +Reviewed-by: Eric Farman +Signed-off-by: Thomas Huth +(cherry picked from commit 393296de19650e1400ca265914cfdeb313725363) +--- + pc-bios/s390-ccw/virtio-blkdev.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/pc-bios/s390-ccw/virtio-blkdev.c b/pc-bios/s390-ccw/virtio-blkdev.c +index 8271c47296..794f99b42c 100644 +--- a/pc-bios/s390-ccw/virtio-blkdev.c ++++ b/pc-bios/s390-ccw/virtio-blkdev.c +@@ -173,7 +173,7 @@ int virtio_get_block_size(void) + + switch (vdev->senseid.cu_model) { + case VIRTIO_ID_BLOCK: +- return vdev->config.blk.blk_size << vdev->config.blk.physical_block_exp; ++ return vdev->config.blk.blk_size; + case VIRTIO_ID_SCSI: + return vdev->scsi_block_size; + } +-- +2.31.1 + diff --git a/SOURCES/kvm-pc-bios-s390-ccw-Split-virtio-scsi-code-from-virtio_.patch b/SOURCES/kvm-pc-bios-s390-ccw-Split-virtio-scsi-code-from-virtio_.patch new file mode 100644 index 0000000..b212194 --- /dev/null +++ b/SOURCES/kvm-pc-bios-s390-ccw-Split-virtio-scsi-code-from-virtio_.patch @@ -0,0 +1,180 @@ +From 2e38b4ec5c53b2b98539a70105d3046e1c452ab8 Mon Sep 17 00:00:00 2001 +From: Thomas Huth +Date: Fri, 8 Jul 2022 20:49:01 +0200 +Subject: [PATCH 13/17] pc-bios/s390-ccw: Split virtio-scsi code from + virtio_blk_setup_device() + +RH-Author: Thomas Huth +RH-MergeRequest: 106: pc-bios/s390-ccw: Fix boot from disks with 4k sectors that do not have the typical DASD geometry +RH-Commit: [8/10] f49c5fb77e05c9dc09ed9f037e37f6a461e4bba6 (thuth/qemu-kvm-cs9) +RH-Bugzilla: 2098077 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: David Hildenbrand +RH-Acked-by: Cornelia Huck + +Bugzilla: http://bugzilla.redhat.com/2098077 + +commit cf30b7c4a9b2c64518be8037c2e6670aacdb00b9 +Author: Thomas Huth +Date: Mon Jul 4 13:19:00 2022 +0200 + + pc-bios/s390-ccw: Split virtio-scsi code from virtio_blk_setup_device() + + The next patch is going to add more virtio-block specific code to + virtio_blk_setup_device(), and if the virtio-scsi code is also in + there, this is more cumbersome. And the calling function virtio_setup() + in main.c looks at the device type already anyway, so it's more + logical to separate the virtio-scsi stuff into a new function in + virtio-scsi.c instead. + + Message-Id: <20220704111903.62400-10-thuth@redhat.com> + Reviewed-by: Eric Farman + Signed-off-by: Thomas Huth + +Signed-off-by: Thomas Huth +--- + pc-bios/s390-ccw/main.c | 24 +++++++++++++++++------- + pc-bios/s390-ccw/virtio-blkdev.c | 20 ++------------------ + pc-bios/s390-ccw/virtio-scsi.c | 19 ++++++++++++++++++- + pc-bios/s390-ccw/virtio-scsi.h | 2 +- + 4 files changed, 38 insertions(+), 27 deletions(-) + +diff --git a/pc-bios/s390-ccw/main.c b/pc-bios/s390-ccw/main.c +index 5d2b7ba94d..13e1d8fdf7 100644 +--- a/pc-bios/s390-ccw/main.c ++++ b/pc-bios/s390-ccw/main.c +@@ -14,6 +14,7 @@ + #include "s390-ccw.h" + #include "cio.h" + #include "virtio.h" ++#include "virtio-scsi.h" + #include "dasd-ipl.h" + + char stack[PAGE_SIZE * 8] __attribute__((__aligned__(PAGE_SIZE))); +@@ -218,6 +219,7 @@ static int virtio_setup(void) + { + VDev *vdev = virtio_get_device(); + QemuIplParameters *early_qipl = (QemuIplParameters *)QIPL_ADDRESS; ++ int ret; + + memcpy(&qipl, early_qipl, sizeof(QemuIplParameters)); + +@@ -225,18 +227,26 @@ static int virtio_setup(void) + menu_setup(); + } + +- if (virtio_get_device_type() == VIRTIO_ID_NET) { ++ switch (vdev->senseid.cu_model) { ++ case VIRTIO_ID_NET: + sclp_print("Network boot device detected\n"); + vdev->netboot_start_addr = qipl.netboot_start_addr; +- } else { +- int ret = virtio_blk_setup_device(blk_schid); +- if (ret) { +- return ret; +- } ++ return 0; ++ case VIRTIO_ID_BLOCK: ++ ret = virtio_blk_setup_device(blk_schid); ++ break; ++ case VIRTIO_ID_SCSI: ++ ret = virtio_scsi_setup_device(blk_schid); ++ break; ++ default: ++ panic("\n! No IPL device available !\n"); ++ } ++ ++ if (!ret) { + IPL_assert(virtio_ipl_disk_is_valid(), "No valid IPL device detected"); + } + +- return 0; ++ return ret; + } + + static void ipl_boot_device(void) +diff --git a/pc-bios/s390-ccw/virtio-blkdev.c b/pc-bios/s390-ccw/virtio-blkdev.c +index db1f7f44aa..c175b66a47 100644 +--- a/pc-bios/s390-ccw/virtio-blkdev.c ++++ b/pc-bios/s390-ccw/virtio-blkdev.c +@@ -222,27 +222,11 @@ uint64_t virtio_get_blocks(void) + int virtio_blk_setup_device(SubChannelId schid) + { + VDev *vdev = virtio_get_device(); +- int ret = 0; + + vdev->schid = schid; + virtio_setup_ccw(vdev); + +- switch (vdev->senseid.cu_model) { +- case VIRTIO_ID_BLOCK: +- sclp_print("Using virtio-blk.\n"); +- break; +- case VIRTIO_ID_SCSI: +- IPL_assert(vdev->config.scsi.sense_size == VIRTIO_SCSI_SENSE_SIZE, +- "Config: sense size mismatch"); +- IPL_assert(vdev->config.scsi.cdb_size == VIRTIO_SCSI_CDB_SIZE, +- "Config: CDB size mismatch"); ++ sclp_print("Using virtio-blk.\n"); + +- sclp_print("Using virtio-scsi.\n"); +- ret = virtio_scsi_setup(vdev); +- break; +- default: +- panic("\n! No IPL device available !\n"); +- } +- +- return ret; ++ return 0; + } +diff --git a/pc-bios/s390-ccw/virtio-scsi.c b/pc-bios/s390-ccw/virtio-scsi.c +index 2c8d0f3097..3b7069270c 100644 +--- a/pc-bios/s390-ccw/virtio-scsi.c ++++ b/pc-bios/s390-ccw/virtio-scsi.c +@@ -329,7 +329,7 @@ static void scsi_parse_capacity_report(void *data, + } + } + +-int virtio_scsi_setup(VDev *vdev) ++static int virtio_scsi_setup(VDev *vdev) + { + int retry_test_unit_ready = 3; + uint8_t data[256]; +@@ -430,3 +430,20 @@ int virtio_scsi_setup(VDev *vdev) + + return 0; + } ++ ++int virtio_scsi_setup_device(SubChannelId schid) ++{ ++ VDev *vdev = virtio_get_device(); ++ ++ vdev->schid = schid; ++ virtio_setup_ccw(vdev); ++ ++ IPL_assert(vdev->config.scsi.sense_size == VIRTIO_SCSI_SENSE_SIZE, ++ "Config: sense size mismatch"); ++ IPL_assert(vdev->config.scsi.cdb_size == VIRTIO_SCSI_CDB_SIZE, ++ "Config: CDB size mismatch"); ++ ++ sclp_print("Using virtio-scsi.\n"); ++ ++ return virtio_scsi_setup(vdev); ++} +diff --git a/pc-bios/s390-ccw/virtio-scsi.h b/pc-bios/s390-ccw/virtio-scsi.h +index 4b14c2c2f9..e6b6cd4815 100644 +--- a/pc-bios/s390-ccw/virtio-scsi.h ++++ b/pc-bios/s390-ccw/virtio-scsi.h +@@ -67,8 +67,8 @@ static inline bool virtio_scsi_response_ok(const VirtioScsiCmdResp *r) + return r->response == VIRTIO_SCSI_S_OK && r->status == CDB_STATUS_GOOD; + } + +-int virtio_scsi_setup(VDev *vdev); + int virtio_scsi_read_many(VDev *vdev, + ulong sector, void *load_addr, int sec_num); ++int virtio_scsi_setup_device(SubChannelId schid); + + #endif /* VIRTIO_SCSI_H */ +-- +2.31.1 + diff --git a/SOURCES/kvm-pc-bios-s390-ccw-bootmap-Improve-the-guessing-logic-.patch b/SOURCES/kvm-pc-bios-s390-ccw-bootmap-Improve-the-guessing-logic-.patch new file mode 100644 index 0000000..231a8a0 --- /dev/null +++ b/SOURCES/kvm-pc-bios-s390-ccw-bootmap-Improve-the-guessing-logic-.patch @@ -0,0 +1,102 @@ +From 64fa56e0520215e3909e442f09d8073c1870648a Mon Sep 17 00:00:00 2001 +From: Thomas Huth +Date: Fri, 8 Jul 2022 20:49:01 +0200 +Subject: [PATCH 07/17] pc-bios/s390-ccw/bootmap: Improve the guessing logic in + zipl_load_vblk() + +RH-Author: Thomas Huth +RH-MergeRequest: 106: pc-bios/s390-ccw: Fix boot from disks with 4k sectors that do not have the typical DASD geometry +RH-Commit: [2/10] ca8f5e847617cf4ac2fd6c38edb2982f32fa3eba (thuth/qemu-kvm-cs9) +RH-Bugzilla: 2098077 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: David Hildenbrand +RH-Acked-by: Cornelia Huck + +Bugzilla: http://bugzilla.redhat.com/2098077 + +commit 422865f6672ee1482b98d18321b55c1ecfb06c82 +Author: Thomas Huth +Date: Mon Jul 4 13:18:54 2022 +0200 + + pc-bios/s390-ccw/bootmap: Improve the guessing logic in zipl_load_vblk() + + The logic of trying an final ISO or ECKD boot on virtio-block devices is + very weird: Since the geometry hardly ever matches in virtio_disk_is_scsi(), + virtio_blk_setup_device() always sets a "guessed" disk geometry via + virtio_assume_scsi() (which is certainly also wrong in a lot of cases). + + zipl_load_vblk() then sees that there's been a "virtio_guessed_disk_nature" + and tries to fix up the geometry again via virtio_assume_iso9660() before + always trying to do ipl_iso_el_torito(). That's a very brain-twisting + way of attempting to boot from ISO images, which won't work anymore after + the following patches that will clean up the virtio_assume_scsi() mess + (and thus get rid of the "virtio_guessed_disk_nature" here). + + Let's try a better approach instead: ISO files always have a magic + string "CD001" at offset 0x8001 (see e.g. the ECMA-119 specification) + which we can use to decide whether we should try to boot in ISO 9660 + mode (which we should also try if we see a sector size of 2048). + + And if we were not able to boot in ISO mode here, the final boot attempt + before panicking is to boot in ECKD mode. Since this is our last boot + attempt anyway, simply always assume the ECKD geometry here (if the sector + size was not 4096 yet), so that we also do not depend on the guessed disk + geometry from virtio_blk_setup_device() here anymore. + + Message-Id: <20220704111903.62400-4-thuth@redhat.com> + Signed-off-by: Thomas Huth + +Signed-off-by: Thomas Huth +--- + pc-bios/s390-ccw/bootmap.c | 27 +++++++++++++++++++++++---- + 1 file changed, 23 insertions(+), 4 deletions(-) + +diff --git a/pc-bios/s390-ccw/bootmap.c b/pc-bios/s390-ccw/bootmap.c +index 56411ab3b6..994e59c0b0 100644 +--- a/pc-bios/s390-ccw/bootmap.c ++++ b/pc-bios/s390-ccw/bootmap.c +@@ -780,18 +780,37 @@ static void ipl_iso_el_torito(void) + } + } + ++/** ++ * Detect whether we're trying to boot from an .ISO image. ++ * These always have a signature string "CD001" at offset 0x8001. ++ */ ++static bool has_iso_signature(void) ++{ ++ int blksize = virtio_get_block_size(); ++ ++ if (!blksize || virtio_read(0x8000 / blksize, sec)) { ++ return false; ++ } ++ ++ return !memcmp("CD001", &sec[1], 5); ++} ++ + /*********************************************************************** + * Bus specific IPL sequences + */ + + static void zipl_load_vblk(void) + { +- if (virtio_guessed_disk_nature()) { +- virtio_assume_iso9660(); ++ int blksize = virtio_get_block_size(); ++ ++ if (blksize == VIRTIO_ISO_BLOCK_SIZE || has_iso_signature()) { ++ if (blksize != VIRTIO_ISO_BLOCK_SIZE) { ++ virtio_assume_iso9660(); ++ } ++ ipl_iso_el_torito(); + } +- ipl_iso_el_torito(); + +- if (virtio_guessed_disk_nature()) { ++ if (blksize != VIRTIO_DASD_DEFAULT_BLOCK_SIZE) { + sclp_print("Using guessed DASD geometry.\n"); + virtio_assume_eckd(); + } +-- +2.31.1 + diff --git a/SOURCES/kvm-pc-bios-s390-ccw-netboot.mak-Ignore-Clang-s-warnings.patch b/SOURCES/kvm-pc-bios-s390-ccw-netboot.mak-Ignore-Clang-s-warnings.patch new file mode 100644 index 0000000..00601aa --- /dev/null +++ b/SOURCES/kvm-pc-bios-s390-ccw-netboot.mak-Ignore-Clang-s-warnings.patch @@ -0,0 +1,78 @@ +From 56674ee1f25f12978a6a8a1390e11b55b3e0fabe Mon Sep 17 00:00:00 2001 +From: Thomas Huth +Date: Fri, 8 Jul 2022 20:49:01 +0200 +Subject: [PATCH 15/17] pc-bios/s390-ccw/netboot.mak: Ignore Clang's warnings + about GNU extensions + +RH-Author: Thomas Huth +RH-MergeRequest: 106: pc-bios/s390-ccw: Fix boot from disks with 4k sectors that do not have the typical DASD geometry +RH-Commit: [10/10] 037dab4df23ebb2b42871bca8c842a53a7204b50 (thuth/qemu-kvm-cs9) +RH-Bugzilla: 2098077 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: David Hildenbrand +RH-Acked-by: Cornelia Huck + +Bugzilla: http://bugzilla.redhat.com/2098077 + +commit e2269220acb03e6c6a460c3090d804835e202239 +Author: Thomas Huth +Date: Mon Jul 4 13:19:03 2022 +0200 + + pc-bios/s390-ccw/netboot.mak: Ignore Clang's warnings about GNU extensions + + When compiling the s390-ccw bios with Clang (v14.0), there is currently + an unuseful warning like this: + + CC pc-bios/s390-ccw/ipv6.o + ../../roms/SLOF/lib/libnet/ipv6.c:447:18: warning: variable length array + folded to constant array as an extension [-Wgnu-folding-constant] + unsigned short raw[ip6size]; + ^ + + SLOF is currently GCC-only and cannot be compiled with Clang yet, so + it is expected that such extensions sneak in there - and as long as + we don't want to compile the code with a compiler that is neither GCC + or Clang, it is also not necessary to avoid such extensions. + + Thus these GNU-extension related warnings are completely useless in + the s390-ccw bios, especially in the code that is coming from SLOF, + so we should simply disable the related warnings here now. + + Message-Id: <20220704111903.62400-13-thuth@redhat.com> + Signed-off-by: Thomas Huth + +Signed-off-by: Thomas Huth +--- + pc-bios/s390-ccw/netboot.mak | 7 +++++-- + 1 file changed, 5 insertions(+), 2 deletions(-) + +diff --git a/pc-bios/s390-ccw/netboot.mak b/pc-bios/s390-ccw/netboot.mak +index 68b4d7edcb..ad41898cb6 100644 +--- a/pc-bios/s390-ccw/netboot.mak ++++ b/pc-bios/s390-ccw/netboot.mak +@@ -16,9 +16,12 @@ s390-netboot.elf: $(NETOBJS) libnet.a libc.a + s390-netboot.img: s390-netboot.elf + $(call quiet-command,$(STRIP) --strip-unneeded $< -o $@,"STRIP","$(TARGET_DIR)$@") + ++# SLOF is GCC-only, so ignore warnings about GNU extensions with Clang here ++NO_GNU_WARN := $(call cc-option,-Werror $(QEMU_CFLAGS),-Wno-gnu) ++ + # libc files: + +-LIBC_CFLAGS = $(QEMU_CFLAGS) $(CFLAGS) $(LIBC_INC) $(LIBNET_INC) \ ++LIBC_CFLAGS = $(QEMU_CFLAGS) $(CFLAGS) $(NO_GNU_WARN) $(LIBC_INC) $(LIBNET_INC) \ + -MMD -MP -MT $@ -MF $(@:%.o=%.d) + + CTYPE_OBJS = isdigit.o isxdigit.o toupper.o +@@ -52,7 +55,7 @@ libc.a: $(LIBCOBJS) + + LIBNETOBJS := args.o dhcp.o dns.o icmpv6.o ipv6.o tcp.o udp.o bootp.o \ + dhcpv6.o ethernet.o ipv4.o ndp.o tftp.o pxelinux.o +-LIBNETCFLAGS = $(QEMU_CFLAGS) $(CFLAGS) $(LIBC_INC) $(LIBNET_INC) \ ++LIBNETCFLAGS = $(QEMU_CFLAGS) $(CFLAGS) $(NO_GNU_WARN) $(LIBC_INC) $(LIBNET_INC) \ + -DDHCPARCH=0x1F -MMD -MP -MT $@ -MF $(@:%.o=%.d) + + %.o : $(SLOF_DIR)/lib/libnet/%.c +-- +2.31.1 + diff --git a/SOURCES/kvm-pc-bios-s390-ccw-virtio-Beautify-the-code-for-readin.patch b/SOURCES/kvm-pc-bios-s390-ccw-virtio-Beautify-the-code-for-readin.patch new file mode 100644 index 0000000..5e4b689 --- /dev/null +++ b/SOURCES/kvm-pc-bios-s390-ccw-virtio-Beautify-the-code-for-readin.patch @@ -0,0 +1,56 @@ +From 430e76fd964390db86c8486f76b916a1cf7f74c2 Mon Sep 17 00:00:00 2001 +From: Thomas Huth +Date: Fri, 8 Jul 2022 20:49:01 +0200 +Subject: [PATCH 12/17] pc-bios/s390-ccw/virtio: Beautify the code for reading + virtqueue configuration + +RH-Author: Thomas Huth +RH-MergeRequest: 106: pc-bios/s390-ccw: Fix boot from disks with 4k sectors that do not have the typical DASD geometry +RH-Commit: [7/10] b15c06b4c5431837672b6cb5d57d09da20718441 (thuth/qemu-kvm-cs9) +RH-Bugzilla: 2098077 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: David Hildenbrand +RH-Acked-by: Cornelia Huck + +Bugzilla: http://bugzilla.redhat.com/2098077 + +commit 070824885741f5d2a66626d3c4ecb2773c8e0552 +Author: Thomas Huth +Date: Mon Jul 4 13:18:59 2022 +0200 + + pc-bios/s390-ccw/virtio: Beautify the code for reading virtqueue configuration + + It looks nicer if we separate the run_ccw() from the IPL_assert() + statement, and the error message should talk about "virtio device" + instead of "block device", since this code is nowadays used for + non-block (i.e. network) devices, too. + + Message-Id: <20220704111903.62400-9-thuth@redhat.com> + Reviewed-by: Cornelia Huck + Reviewed-by: Eric Farman + Signed-off-by: Thomas Huth + +Signed-off-by: Thomas Huth +--- + pc-bios/s390-ccw/virtio.c | 5 ++--- + 1 file changed, 2 insertions(+), 3 deletions(-) + +diff --git a/pc-bios/s390-ccw/virtio.c b/pc-bios/s390-ccw/virtio.c +index d8c2b52710..f37510f312 100644 +--- a/pc-bios/s390-ccw/virtio.c ++++ b/pc-bios/s390-ccw/virtio.c +@@ -289,9 +289,8 @@ void virtio_setup_ccw(VDev *vdev) + .num = 0, + }; + +- IPL_assert( +- run_ccw(vdev, CCW_CMD_READ_VQ_CONF, &config, sizeof(config), false) == 0, +- "Could not get block device VQ configuration"); ++ rc = run_ccw(vdev, CCW_CMD_READ_VQ_CONF, &config, sizeof(config), false); ++ IPL_assert(rc == 0, "Could not get virtio device VQ configuration"); + info.num = config.num; + vring_init(&vdev->vrings[i], &info); + vdev->vrings[i].schid = vdev->schid; +-- +2.31.1 + diff --git a/SOURCES/kvm-pc-bios-s390-ccw-virtio-Introduce-a-macro-for-the-DA.patch b/SOURCES/kvm-pc-bios-s390-ccw-virtio-Introduce-a-macro-for-the-DA.patch new file mode 100644 index 0000000..04ab605 --- /dev/null +++ b/SOURCES/kvm-pc-bios-s390-ccw-virtio-Introduce-a-macro-for-the-DA.patch @@ -0,0 +1,63 @@ +From 7d4f2454f95bfc087ad3f2fe3bc4625dcea3568e Mon Sep 17 00:00:00 2001 +From: Thomas Huth +Date: Fri, 8 Jul 2022 20:49:01 +0200 +Subject: [PATCH 06/17] pc-bios/s390-ccw/virtio: Introduce a macro for the DASD + block size + +RH-Author: Thomas Huth +RH-MergeRequest: 106: pc-bios/s390-ccw: Fix boot from disks with 4k sectors that do not have the typical DASD geometry +RH-Commit: [1/10] 71033934e1e9988bcf71362e02665ceb7449009d (thuth/qemu-kvm-cs9) +RH-Bugzilla: 2098077 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: David Hildenbrand +RH-Acked-by: Cornelia Huck + +Bugzilla: http://bugzilla.redhat.com/2098077 + +commit 1f2c2ee48e87ea743f8e23cc7569dd26c4cf9623 +Author: Thomas Huth +Date: Mon Jul 4 13:18:53 2022 +0200 + + pc-bios/s390-ccw/virtio: Introduce a macro for the DASD block size + + Use VIRTIO_DASD_DEFAULT_BLOCK_SIZE instead of the magic value 4096. + + Message-Id: <20220704111903.62400-3-thuth@redhat.com> + Reviewed-by: Eric Farman + Reviewed-by: Cornelia Huck + Signed-off-by: Thomas Huth + +Signed-off-by: Thomas Huth +--- + pc-bios/s390-ccw/virtio-blkdev.c | 2 +- + pc-bios/s390-ccw/virtio.h | 1 + + 2 files changed, 2 insertions(+), 1 deletion(-) + +diff --git a/pc-bios/s390-ccw/virtio-blkdev.c b/pc-bios/s390-ccw/virtio-blkdev.c +index 7d35050292..6483307630 100644 +--- a/pc-bios/s390-ccw/virtio-blkdev.c ++++ b/pc-bios/s390-ccw/virtio-blkdev.c +@@ -155,7 +155,7 @@ void virtio_assume_eckd(void) + vdev->config.blk.physical_block_exp = 0; + switch (vdev->senseid.cu_model) { + case VIRTIO_ID_BLOCK: +- vdev->config.blk.blk_size = 4096; ++ vdev->config.blk.blk_size = VIRTIO_DASD_DEFAULT_BLOCK_SIZE; + break; + case VIRTIO_ID_SCSI: + vdev->config.blk.blk_size = vdev->scsi_block_size; +diff --git a/pc-bios/s390-ccw/virtio.h b/pc-bios/s390-ccw/virtio.h +index 19fceb6495..9e410bde6f 100644 +--- a/pc-bios/s390-ccw/virtio.h ++++ b/pc-bios/s390-ccw/virtio.h +@@ -198,6 +198,7 @@ extern int virtio_read_many(ulong sector, void *load_addr, int sec_num); + #define VIRTIO_SECTOR_SIZE 512 + #define VIRTIO_ISO_BLOCK_SIZE 2048 + #define VIRTIO_SCSI_BLOCK_SIZE 512 ++#define VIRTIO_DASD_DEFAULT_BLOCK_SIZE 4096 + + static inline ulong virtio_sector_adjust(ulong sector) + { +-- +2.31.1 + diff --git a/SOURCES/kvm-pc-bios-s390-ccw-virtio-Read-device-config-after-fea.patch b/SOURCES/kvm-pc-bios-s390-ccw-virtio-Read-device-config-after-fea.patch new file mode 100644 index 0000000..41ae538 --- /dev/null +++ b/SOURCES/kvm-pc-bios-s390-ccw-virtio-Read-device-config-after-fea.patch @@ -0,0 +1,67 @@ +From 20f8724d0837acbe642c8c7698a4b256f34c1209 Mon Sep 17 00:00:00 2001 +From: Thomas Huth +Date: Fri, 8 Jul 2022 20:49:01 +0200 +Subject: [PATCH 11/17] pc-bios/s390-ccw/virtio: Read device config after + feature negotiation + +RH-Author: Thomas Huth +RH-MergeRequest: 106: pc-bios/s390-ccw: Fix boot from disks with 4k sectors that do not have the typical DASD geometry +RH-Commit: [6/10] 54d21e430b2dfba9e0a0823d6bb8ec7e7f8ff2ff (thuth/qemu-kvm-cs9) +RH-Bugzilla: 2098077 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: David Hildenbrand +RH-Acked-by: Cornelia Huck + +Bugzilla: http://bugzilla.redhat.com/2098077 + +commit aa5c69ce99411c4886bcd051f288afc02b6d968d +Author: Thomas Huth +Date: Mon Jul 4 13:18:58 2022 +0200 + + pc-bios/s390-ccw/virtio: Read device config after feature negotiation + + Feature negotiation should be done first, since some fields in the + config area can depend on the negotiated features and thus should + rather be read afterwards. + + While we're at it, also adjust the error message here a little bit + (the code is nowadays used for non-block virtio devices, too). + + Message-Id: <20220704111903.62400-8-thuth@redhat.com> + Reviewed-by: Eric Farman + Reviewed-by: Cornelia Huck + Signed-off-by: Thomas Huth + +Signed-off-by: Thomas Huth +--- + pc-bios/s390-ccw/virtio.c | 7 +++---- + 1 file changed, 3 insertions(+), 4 deletions(-) + +diff --git a/pc-bios/s390-ccw/virtio.c b/pc-bios/s390-ccw/virtio.c +index 4e85a2eb82..d8c2b52710 100644 +--- a/pc-bios/s390-ccw/virtio.c ++++ b/pc-bios/s390-ccw/virtio.c +@@ -262,10 +262,6 @@ void virtio_setup_ccw(VDev *vdev) + rc = run_ccw(vdev, CCW_CMD_WRITE_STATUS, &status, sizeof(status), false); + IPL_assert(rc == 0, "Could not write DRIVER status to host"); + +- IPL_assert( +- run_ccw(vdev, CCW_CMD_READ_CONF, &vdev->config, cfg_size, false) == 0, +- "Could not get block device configuration"); +- + /* Feature negotiation */ + for (i = 0; i < ARRAY_SIZE(vdev->guest_features); i++) { + feats.features = 0; +@@ -278,6 +274,9 @@ void virtio_setup_ccw(VDev *vdev) + IPL_assert(rc == 0, "Could not set features bits"); + } + ++ rc = run_ccw(vdev, CCW_CMD_READ_CONF, &vdev->config, cfg_size, false); ++ IPL_assert(rc == 0, "Could not get virtio device configuration"); ++ + for (i = 0; i < vdev->nr_vqs; i++) { + VqInfo info = { + .queue = (unsigned long long) ring_area + (i * VIRTIO_RING_SIZE), +-- +2.31.1 + diff --git a/SOURCES/kvm-pc-bios-s390-ccw-virtio-Set-missing-status-bits-whil.patch b/SOURCES/kvm-pc-bios-s390-ccw-virtio-Set-missing-status-bits-whil.patch new file mode 100644 index 0000000..e976047 --- /dev/null +++ b/SOURCES/kvm-pc-bios-s390-ccw-virtio-Set-missing-status-bits-whil.patch @@ -0,0 +1,93 @@ +From 303fb3ddcdbbd1373c5b1aa28e03f90507e217f3 Mon Sep 17 00:00:00 2001 +From: Thomas Huth +Date: Fri, 8 Jul 2022 20:49:01 +0200 +Subject: [PATCH 10/17] pc-bios/s390-ccw/virtio: Set missing status bits while + initializing + +RH-Author: Thomas Huth +RH-MergeRequest: 106: pc-bios/s390-ccw: Fix boot from disks with 4k sectors that do not have the typical DASD geometry +RH-Commit: [5/10] 4bc44d9adae055fb60b79d04a2f08535b4d38d2b (thuth/qemu-kvm-cs9) +RH-Bugzilla: 2098077 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: David Hildenbrand +RH-Acked-by: Cornelia Huck + +Bugzilla: http://bugzilla.redhat.com/2098077 + +commit 175aa06a152ef6b58ba9b2e47a1296b024dea70c +Author: Thomas Huth +Date: Mon Jul 4 13:18:57 2022 +0200 + + pc-bios/s390-ccw/virtio: Set missing status bits while initializing + + According chapter "3.1.1 Driver Requirements: Device Initialization" + of the Virtio specification (v1.1), a driver for a device has to set + the ACKNOWLEDGE and DRIVER bits in the status field after resetting + the device. The s390-ccw bios skipped these steps so far and seems + like QEMU never cared. Anyway, it's better to follow the spec, so + let's set these bits now in the right spots, too. + + Message-Id: <20220704111903.62400-7-thuth@redhat.com> + Acked-by: Christian Borntraeger + Reviewed-by: Cornelia Huck + Reviewed-by: Eric Farman + Signed-off-by: Thomas Huth + +Signed-off-by: Thomas Huth +--- + pc-bios/s390-ccw/virtio.c | 18 ++++++++++++++---- + 1 file changed, 14 insertions(+), 4 deletions(-) + +diff --git a/pc-bios/s390-ccw/virtio.c b/pc-bios/s390-ccw/virtio.c +index 5d2c6e3381..4e85a2eb82 100644 +--- a/pc-bios/s390-ccw/virtio.c ++++ b/pc-bios/s390-ccw/virtio.c +@@ -220,7 +220,7 @@ int virtio_run(VDev *vdev, int vqid, VirtioCmd *cmd) + void virtio_setup_ccw(VDev *vdev) + { + int i, rc, cfg_size = 0; +- unsigned char status = VIRTIO_CONFIG_S_DRIVER_OK; ++ uint8_t status; + struct VirtioFeatureDesc { + uint32_t features; + uint8_t index; +@@ -234,6 +234,10 @@ void virtio_setup_ccw(VDev *vdev) + + run_ccw(vdev, CCW_CMD_VDEV_RESET, NULL, 0, false); + ++ status = VIRTIO_CONFIG_S_ACKNOWLEDGE; ++ rc = run_ccw(vdev, CCW_CMD_WRITE_STATUS, &status, sizeof(status), false); ++ IPL_assert(rc == 0, "Could not write ACKNOWLEDGE status to host"); ++ + switch (vdev->senseid.cu_model) { + case VIRTIO_ID_NET: + vdev->nr_vqs = 2; +@@ -253,6 +257,11 @@ void virtio_setup_ccw(VDev *vdev) + default: + panic("Unsupported virtio device\n"); + } ++ ++ status |= VIRTIO_CONFIG_S_DRIVER; ++ rc = run_ccw(vdev, CCW_CMD_WRITE_STATUS, &status, sizeof(status), false); ++ IPL_assert(rc == 0, "Could not write DRIVER status to host"); ++ + IPL_assert( + run_ccw(vdev, CCW_CMD_READ_CONF, &vdev->config, cfg_size, false) == 0, + "Could not get block device configuration"); +@@ -291,9 +300,10 @@ void virtio_setup_ccw(VDev *vdev) + run_ccw(vdev, CCW_CMD_SET_VQ, &info, sizeof(info), false) == 0, + "Cannot set VQ info"); + } +- IPL_assert( +- run_ccw(vdev, CCW_CMD_WRITE_STATUS, &status, sizeof(status), false) == 0, +- "Could not write status to host"); ++ ++ status |= VIRTIO_CONFIG_S_DRIVER_OK; ++ rc = run_ccw(vdev, CCW_CMD_WRITE_STATUS, &status, sizeof(status), false); ++ IPL_assert(rc == 0, "Could not write DRIVER_OK status to host"); + } + + bool virtio_is_supported(SubChannelId schid) +-- +2.31.1 + diff --git a/SOURCES/kvm-pc-bios-s390-ccw-virtio-blkdev-Remove-virtio_assume_.patch b/SOURCES/kvm-pc-bios-s390-ccw-virtio-blkdev-Remove-virtio_assume_.patch new file mode 100644 index 0000000..109b98e --- /dev/null +++ b/SOURCES/kvm-pc-bios-s390-ccw-virtio-blkdev-Remove-virtio_assume_.patch @@ -0,0 +1,101 @@ +From d3335a98a7b6e084aadf4907968536a67cf8e64c Mon Sep 17 00:00:00 2001 +From: Thomas Huth +Date: Fri, 8 Jul 2022 20:49:01 +0200 +Subject: [PATCH 09/17] pc-bios/s390-ccw/virtio-blkdev: Remove + virtio_assume_scsi() + +RH-Author: Thomas Huth +RH-MergeRequest: 106: pc-bios/s390-ccw: Fix boot from disks with 4k sectors that do not have the typical DASD geometry +RH-Commit: [4/10] bf27f75344f220a03475a2918ed49ec9cd5ba317 (thuth/qemu-kvm-cs9) +RH-Bugzilla: 2098077 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: David Hildenbrand +RH-Acked-by: Cornelia Huck + +Bugzilla: http://bugzilla.redhat.com/2098077 + +commit 5447de2619050a0a4dd480b97f88a9b58da360d1 +Author: Thomas Huth +Date: Mon Jul 4 13:18:56 2022 +0200 + + pc-bios/s390-ccw/virtio-blkdev: Remove virtio_assume_scsi() + + The virtio_assume_scsi() function is very questionable: First, it + is only called for virtio-blk, and not for virtio-scsi, so the naming + is already quite confusing. Second, it is called if we detected a + "invalid" IPL disk, trying to fix it by blindly setting a sector + size of 512. This of course won't work in most cases since disks + might have a different sector size for a reason. + + Thus let's remove this strange function now. The calling code can + also be removed completely, since there is another spot in main.c + that does "IPL_assert(virtio_ipl_disk_is_valid(), ...)" to make + sure that we do not try to IPL from an invalid device. + + Message-Id: <20220704111903.62400-6-thuth@redhat.com> + Reviewed-by: Eric Farman + Signed-off-by: Thomas Huth + +Signed-off-by: Thomas Huth +--- + pc-bios/s390-ccw/virtio-blkdev.c | 24 ------------------------ + pc-bios/s390-ccw/virtio.h | 1 - + 2 files changed, 25 deletions(-) + +diff --git a/pc-bios/s390-ccw/virtio-blkdev.c b/pc-bios/s390-ccw/virtio-blkdev.c +index 7e13155589..db1f7f44aa 100644 +--- a/pc-bios/s390-ccw/virtio-blkdev.c ++++ b/pc-bios/s390-ccw/virtio-blkdev.c +@@ -112,23 +112,6 @@ VirtioGDN virtio_guessed_disk_nature(void) + return virtio_get_device()->guessed_disk_nature; + } + +-void virtio_assume_scsi(void) +-{ +- VDev *vdev = virtio_get_device(); +- +- switch (vdev->senseid.cu_model) { +- case VIRTIO_ID_BLOCK: +- vdev->guessed_disk_nature = VIRTIO_GDN_SCSI; +- vdev->config.blk.blk_size = VIRTIO_SCSI_BLOCK_SIZE; +- vdev->config.blk.physical_block_exp = 0; +- vdev->blk_factor = 1; +- break; +- case VIRTIO_ID_SCSI: +- vdev->scsi_block_size = VIRTIO_SCSI_BLOCK_SIZE; +- break; +- } +-} +- + void virtio_assume_iso9660(void) + { + VDev *vdev = virtio_get_device(); +@@ -247,13 +230,6 @@ int virtio_blk_setup_device(SubChannelId schid) + switch (vdev->senseid.cu_model) { + case VIRTIO_ID_BLOCK: + sclp_print("Using virtio-blk.\n"); +- if (!virtio_ipl_disk_is_valid()) { +- /* make sure all getters but blocksize return 0 for +- * invalid IPL disk +- */ +- memset(&vdev->config.blk, 0, sizeof(vdev->config.blk)); +- virtio_assume_scsi(); +- } + break; + case VIRTIO_ID_SCSI: + IPL_assert(vdev->config.scsi.sense_size == VIRTIO_SCSI_SENSE_SIZE, +diff --git a/pc-bios/s390-ccw/virtio.h b/pc-bios/s390-ccw/virtio.h +index 241730effe..600ba5052b 100644 +--- a/pc-bios/s390-ccw/virtio.h ++++ b/pc-bios/s390-ccw/virtio.h +@@ -182,7 +182,6 @@ enum guessed_disk_nature_type { + typedef enum guessed_disk_nature_type VirtioGDN; + + VirtioGDN virtio_guessed_disk_nature(void); +-void virtio_assume_scsi(void); + void virtio_assume_eckd(void); + void virtio_assume_iso9660(void); + +-- +2.31.1 + diff --git a/SOURCES/kvm-pc-bios-s390-ccw-virtio-blkdev-Request-the-right-fea.patch b/SOURCES/kvm-pc-bios-s390-ccw-virtio-blkdev-Request-the-right-fea.patch new file mode 100644 index 0000000..8bc7a11 --- /dev/null +++ b/SOURCES/kvm-pc-bios-s390-ccw-virtio-blkdev-Request-the-right-fea.patch @@ -0,0 +1,63 @@ +From db58915fcaf3d24b64fe2c34cc15b5596b9a81bb Mon Sep 17 00:00:00 2001 +From: Thomas Huth +Date: Fri, 8 Jul 2022 20:49:01 +0200 +Subject: [PATCH 14/17] pc-bios/s390-ccw/virtio-blkdev: Request the right + feature bits + +RH-Author: Thomas Huth +RH-MergeRequest: 106: pc-bios/s390-ccw: Fix boot from disks with 4k sectors that do not have the typical DASD geometry +RH-Commit: [9/10] 9dcd8c2f659f366f9487ab6473d1f0d7778b40a7 (thuth/qemu-kvm-cs9) +RH-Bugzilla: 2098077 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: David Hildenbrand +RH-Acked-by: Cornelia Huck + +Bugzilla: http://bugzilla.redhat.com/2098077 + +commit 9125a314cca4a1838b09305a87d8efb98f80ab67 +Author: Thomas Huth +Date: Mon Jul 4 13:19:01 2022 +0200 + + pc-bios/s390-ccw/virtio-blkdev: Request the right feature bits + + The virtio-blk code uses the block size and geometry fields in the + config area. According to the virtio-spec, these have to be negotiated + with the right feature bits during initialization, otherwise they + might not be available. QEMU is so far very forgiving and always + provides them, but we should not rely on this behavior, so let's + better request them properly via the VIRTIO_BLK_F_GEOMETRY and + VIRTIO_BLK_F_BLK_SIZE feature bits. + + Message-Id: <20220704111903.62400-11-thuth@redhat.com> + Signed-off-by: Thomas Huth + +Signed-off-by: Thomas Huth +--- + pc-bios/s390-ccw/virtio-blkdev.c | 4 ++++ + 1 file changed, 4 insertions(+) + +diff --git a/pc-bios/s390-ccw/virtio-blkdev.c b/pc-bios/s390-ccw/virtio-blkdev.c +index c175b66a47..8271c47296 100644 +--- a/pc-bios/s390-ccw/virtio-blkdev.c ++++ b/pc-bios/s390-ccw/virtio-blkdev.c +@@ -13,6 +13,9 @@ + #include "virtio.h" + #include "virtio-scsi.h" + ++#define VIRTIO_BLK_F_GEOMETRY (1 << 4) ++#define VIRTIO_BLK_F_BLK_SIZE (1 << 6) ++ + static int virtio_blk_read_many(VDev *vdev, ulong sector, void *load_addr, + int sec_num) + { +@@ -223,6 +226,7 @@ int virtio_blk_setup_device(SubChannelId schid) + { + VDev *vdev = virtio_get_device(); + ++ vdev->guest_features[0] = VIRTIO_BLK_F_GEOMETRY | VIRTIO_BLK_F_BLK_SIZE; + vdev->schid = schid; + virtio_setup_ccw(vdev); + +-- +2.31.1 + diff --git a/SOURCES/kvm-pc-bios-s390-ccw-virtio-blkdev-Simplify-fix-virtio_i.patch b/SOURCES/kvm-pc-bios-s390-ccw-virtio-blkdev-Simplify-fix-virtio_i.patch new file mode 100644 index 0000000..818e515 --- /dev/null +++ b/SOURCES/kvm-pc-bios-s390-ccw-virtio-blkdev-Simplify-fix-virtio_i.patch @@ -0,0 +1,124 @@ +From f07e4629a7c58407f903810a038660c88c6a6315 Mon Sep 17 00:00:00 2001 +From: Thomas Huth +Date: Fri, 8 Jul 2022 20:49:01 +0200 +Subject: [PATCH 08/17] pc-bios/s390-ccw/virtio-blkdev: Simplify/fix + virtio_ipl_disk_is_valid() + +RH-Author: Thomas Huth +RH-MergeRequest: 106: pc-bios/s390-ccw: Fix boot from disks with 4k sectors that do not have the typical DASD geometry +RH-Commit: [3/10] fb06830a3e50d9da3d84913b50bb227865cc44b3 (thuth/qemu-kvm-cs9) +RH-Bugzilla: 2098077 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: David Hildenbrand +RH-Acked-by: Cornelia Huck + +Bugzilla: http://bugzilla.redhat.com/2098077 + +commit bbf615f7b707f009ef8e757d170902ad33b90644 +Author: Thomas Huth +Date: Mon Jul 4 13:18:55 2022 +0200 + + pc-bios/s390-ccw/virtio-blkdev: Simplify/fix virtio_ipl_disk_is_valid() + + The s390-ccw bios fails to boot if the boot disk is a virtio-blk + disk with a sector size of 4096. For example: + + dasdfmt -b 4096 -d cdl -y -p -M quick /dev/dasdX + fdasd -a /dev/dasdX + install a guest onto /dev/dasdX1 using virtio-blk + qemu-system-s390x -nographic -hda /dev/dasdX1 + + The bios then bails out with: + + ! Cannot read block 0 ! + + Looking at virtio_ipl_disk_is_valid() and especially the function + virtio_disk_is_scsi(), it does not really make sense that we expect + only such a limited disk geometry (like a block size of 512) for + our boot disks. Let's relax the check and allow everything that + remotely looks like a sane disk. + + Message-Id: <20220704111903.62400-5-thuth@redhat.com> + Reviewed-by: Eric Farman + Signed-off-by: Thomas Huth + +Signed-off-by: Thomas Huth +--- + pc-bios/s390-ccw/virtio-blkdev.c | 41 ++++++-------------------------- + pc-bios/s390-ccw/virtio.h | 2 -- + 2 files changed, 7 insertions(+), 36 deletions(-) + +diff --git a/pc-bios/s390-ccw/virtio-blkdev.c b/pc-bios/s390-ccw/virtio-blkdev.c +index 6483307630..7e13155589 100644 +--- a/pc-bios/s390-ccw/virtio-blkdev.c ++++ b/pc-bios/s390-ccw/virtio-blkdev.c +@@ -166,46 +166,19 @@ void virtio_assume_eckd(void) + virtio_eckd_sectors_for_block_size(vdev->config.blk.blk_size); + } + +-bool virtio_disk_is_scsi(void) +-{ +- VDev *vdev = virtio_get_device(); +- +- if (vdev->guessed_disk_nature == VIRTIO_GDN_SCSI) { +- return true; +- } +- switch (vdev->senseid.cu_model) { +- case VIRTIO_ID_BLOCK: +- return (vdev->config.blk.geometry.heads == 255) +- && (vdev->config.blk.geometry.sectors == 63) +- && (virtio_get_block_size() == VIRTIO_SCSI_BLOCK_SIZE); +- case VIRTIO_ID_SCSI: +- return true; +- } +- return false; +-} +- +-bool virtio_disk_is_eckd(void) ++bool virtio_ipl_disk_is_valid(void) + { ++ int blksize = virtio_get_block_size(); + VDev *vdev = virtio_get_device(); +- const int block_size = virtio_get_block_size(); + +- if (vdev->guessed_disk_nature == VIRTIO_GDN_DASD) { ++ if (vdev->guessed_disk_nature == VIRTIO_GDN_SCSI || ++ vdev->guessed_disk_nature == VIRTIO_GDN_DASD) { + return true; + } +- switch (vdev->senseid.cu_model) { +- case VIRTIO_ID_BLOCK: +- return (vdev->config.blk.geometry.heads == 15) +- && (vdev->config.blk.geometry.sectors == +- virtio_eckd_sectors_for_block_size(block_size)); +- case VIRTIO_ID_SCSI: +- return false; +- } +- return false; +-} + +-bool virtio_ipl_disk_is_valid(void) +-{ +- return virtio_disk_is_scsi() || virtio_disk_is_eckd(); ++ return (vdev->senseid.cu_model == VIRTIO_ID_BLOCK || ++ vdev->senseid.cu_model == VIRTIO_ID_SCSI) && ++ blksize >= 512 && blksize <= 4096; + } + + int virtio_get_block_size(void) +diff --git a/pc-bios/s390-ccw/virtio.h b/pc-bios/s390-ccw/virtio.h +index 9e410bde6f..241730effe 100644 +--- a/pc-bios/s390-ccw/virtio.h ++++ b/pc-bios/s390-ccw/virtio.h +@@ -186,8 +186,6 @@ void virtio_assume_scsi(void); + void virtio_assume_eckd(void); + void virtio_assume_iso9660(void); + +-extern bool virtio_disk_is_scsi(void); +-extern bool virtio_disk_is_eckd(void); + extern bool virtio_ipl_disk_is_valid(void); + extern int virtio_get_block_size(void); + extern uint8_t virtio_get_heads(void); +-- +2.31.1 + diff --git a/SOURCES/kvm-pci-expose-TYPE_XIO3130_DOWNSTREAM-name.patch b/SOURCES/kvm-pci-expose-TYPE_XIO3130_DOWNSTREAM-name.patch deleted file mode 100644 index 435d3f2..0000000 --- a/SOURCES/kvm-pci-expose-TYPE_XIO3130_DOWNSTREAM-name.patch +++ /dev/null @@ -1,73 +0,0 @@ -From 0a200d937e63554c38db577961ef4f09c836cb2f Mon Sep 17 00:00:00 2001 -From: Igor Mammedov -Date: Tue, 1 Mar 2022 10:11:58 -0500 -Subject: [PATCH 01/14] pci: expose TYPE_XIO3130_DOWNSTREAM name - -RH-Author: Igor Mammedov -RH-MergeRequest: 124: RHEL-9.0 Fix broken PCIe device after migration -RH-Commit: [1/2] 38a5fef15d0b6c231b5ac268aad7d541e5303a7e -RH-Bugzilla: 2053584 -RH-Acked-by: Vitaly Kuznetsov -RH-Acked-by: MST -RH-Acked-by: Gerd Hoffmann - -Type name will be used in followup patch for cast check -in pcihp code. - -Signed-off-by: Igor Mammedov -Message-Id: <20220301151200.3507298-2-imammedo@redhat.com> -Reviewed-by: Michael S. Tsirkin -Signed-off-by: Michael S. Tsirkin -(cherry picked from commit c41481af9a5d0d463607cc45b45c510875570817) -Signed-off-by: Igor Mammedov ---- - hw/pci-bridge/xio3130_downstream.c | 3 ++- - include/hw/pci-bridge/xio3130_downstream.h | 15 +++++++++++++++ - 2 files changed, 17 insertions(+), 1 deletion(-) - create mode 100644 include/hw/pci-bridge/xio3130_downstream.h - -diff --git a/hw/pci-bridge/xio3130_downstream.c b/hw/pci-bridge/xio3130_downstream.c -index 04aae72cd6..b17cafd359 100644 ---- a/hw/pci-bridge/xio3130_downstream.c -+++ b/hw/pci-bridge/xio3130_downstream.c -@@ -28,6 +28,7 @@ - #include "migration/vmstate.h" - #include "qapi/error.h" - #include "qemu/module.h" -+#include "hw/pci-bridge/xio3130_downstream.h" - - #define PCI_DEVICE_ID_TI_XIO3130D 0x8233 /* downstream port */ - #define XIO3130_REVISION 0x1 -@@ -173,7 +174,7 @@ static void xio3130_downstream_class_init(ObjectClass *klass, void *data) - } - - static const TypeInfo xio3130_downstream_info = { -- .name = "xio3130-downstream", -+ .name = TYPE_XIO3130_DOWNSTREAM, - .parent = TYPE_PCIE_SLOT, - .class_init = xio3130_downstream_class_init, - .interfaces = (InterfaceInfo[]) { -diff --git a/include/hw/pci-bridge/xio3130_downstream.h b/include/hw/pci-bridge/xio3130_downstream.h -new file mode 100644 -index 0000000000..1d10139aea ---- /dev/null -+++ b/include/hw/pci-bridge/xio3130_downstream.h -@@ -0,0 +1,15 @@ -+/* -+ * TI X3130 pci express downstream port switch -+ * -+ * Copyright (C) 2022 Igor Mammedov -+ * -+ * SPDX-License-Identifier: GPL-2.0-or-later -+ */ -+ -+#ifndef HW_PCI_BRIDGE_XIO3130_DOWNSTREAM_H -+#define HW_PCI_BRIDGE_XIO3130_DOWNSTREAM_H -+ -+#define TYPE_XIO3130_DOWNSTREAM "xio3130-downstream" -+ -+#endif -+ --- -2.31.1 - diff --git a/SOURCES/kvm-qapi-Cleanup-SGX-related-comments-and-restore-sectio.patch b/SOURCES/kvm-qapi-Cleanup-SGX-related-comments-and-restore-sectio.patch deleted file mode 100644 index 9e58f6c..0000000 --- a/SOURCES/kvm-qapi-Cleanup-SGX-related-comments-and-restore-sectio.patch +++ /dev/null @@ -1,213 +0,0 @@ -From a6a327ae392c02b8e8c75b5d702d929ff8fe408d Mon Sep 17 00:00:00 2001 -From: Yang Zhong -Date: Thu, 20 Jan 2022 17:31:04 -0500 -Subject: [PATCH 05/12] qapi: Cleanup SGX related comments and restore - @section-size -MIME-Version: 1.0 -Content-Type: text/plain; charset=UTF-8 -Content-Transfer-Encoding: 8bit - -RH-Author: Paul Lai -RH-MergeRequest: 65: Enable SGX and add SGX Numa support -RH-Commit: [5/5] 0d3b9f37cd3cce202050ba3bd51eef4410ef3d38 -RH-Bugzilla: 2033708 -RH-Acked-by: Paolo Bonzini -RH-Acked-by: Bandan Das -RH-Acked-by: Cornelia Huck - -The SGX NUMA patches were merged into Qemu 7.0 release, we need -clarify detailed version history information and also change -some related comments, which make SGX related comments clearer. - -The QMP command schema promises backwards compatibility as standard. -We temporarily restore "@section-size", which can avoid incompatible -API breakage. The "@section-size" will be deprecated in 7.2 version. - -Suggested-by: Daniel P. Berrangé -Signed-off-by: Yang Zhong -Reviewed-by: Daniel P. Berrangé -Reviewed-by: Philippe Mathieu-Daudé -Message-Id: <20220120223104.437161-1-yang.zhong@intel.com> -Signed-off-by: Paolo Bonzini -Signed-off-by: Paul Lai ---- - docs/about/deprecated.rst | 13 +++++++++++++ - hw/i386/sgx.c | 11 +++++++++-- - qapi/machine.json | 4 ++-- - qapi/misc-target.json | 22 +++++++++++++++++----- - 4 files changed, 41 insertions(+), 9 deletions(-) - -diff --git a/docs/about/deprecated.rst b/docs/about/deprecated.rst -index ff7488cb63..33925edf45 100644 ---- a/docs/about/deprecated.rst -+++ b/docs/about/deprecated.rst -@@ -270,6 +270,19 @@ accepted incorrect commands will return an error. Users should make sure that - all arguments passed to ``device_add`` are consistent with the documented - property types. - -+``query-sgx`` return value member ``section-size`` (since 7.0) -+'''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''' -+ -+Member ``section-size`` in return value elements with meta-type ``uint64`` is -+deprecated. Use ``sections`` instead. -+ -+ -+``query-sgx-capabilities`` return value member ``section-size`` (since 7.0) -+''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''' -+ -+Member ``section-size`` in return value elements with meta-type ``uint64`` is -+deprecated. Use ``sections`` instead. -+ - System accelerators - ------------------- - -diff --git a/hw/i386/sgx.c b/hw/i386/sgx.c -index 5de5dd0893..a2b318dd93 100644 ---- a/hw/i386/sgx.c -+++ b/hw/i386/sgx.c -@@ -83,7 +83,7 @@ static uint64_t sgx_calc_section_metric(uint64_t low, uint64_t high) - ((high & MAKE_64BIT_MASK(0, 20)) << 32); - } - --static SGXEPCSectionList *sgx_calc_host_epc_sections(void) -+static SGXEPCSectionList *sgx_calc_host_epc_sections(uint64_t *size) - { - SGXEPCSectionList *head = NULL, **tail = &head; - SGXEPCSection *section; -@@ -106,6 +106,7 @@ static SGXEPCSectionList *sgx_calc_host_epc_sections(void) - section = g_new0(SGXEPCSection, 1); - section->node = j++; - section->size = sgx_calc_section_metric(ecx, edx); -+ *size += section->size; - QAPI_LIST_APPEND(tail, section); - } - -@@ -156,6 +157,7 @@ SGXInfo *qmp_query_sgx_capabilities(Error **errp) - { - SGXInfo *info = NULL; - uint32_t eax, ebx, ecx, edx; -+ uint64_t size = 0; - - int fd = qemu_open_old("/dev/sgx_vepc", O_RDWR); - if (fd < 0) { -@@ -173,7 +175,8 @@ SGXInfo *qmp_query_sgx_capabilities(Error **errp) - info->sgx1 = eax & (1U << 0) ? true : false; - info->sgx2 = eax & (1U << 1) ? true : false; - -- info->sections = sgx_calc_host_epc_sections(); -+ info->sections = sgx_calc_host_epc_sections(&size); -+ info->section_size = size; - - close(fd); - -@@ -220,12 +223,14 @@ SGXInfo *qmp_query_sgx(Error **errp) - return NULL; - } - -+ SGXEPCState *sgx_epc = &pcms->sgx_epc; - info = g_new0(SGXInfo, 1); - - info->sgx = true; - info->sgx1 = true; - info->sgx2 = true; - info->flc = true; -+ info->section_size = sgx_epc->size; - info->sections = sgx_get_epc_sections_list(); - - return info; -@@ -249,6 +254,8 @@ void hmp_info_sgx(Monitor *mon, const QDict *qdict) - info->sgx2 ? "enabled" : "disabled"); - monitor_printf(mon, "FLC support: %s\n", - info->flc ? "enabled" : "disabled"); -+ monitor_printf(mon, "size: %" PRIu64 "\n", -+ info->section_size); - - section_list = info->sections; - for (section = section_list; section; section = section->next) { -diff --git a/qapi/machine.json b/qapi/machine.json -index 16e771affc..a9f33d0f27 100644 ---- a/qapi/machine.json -+++ b/qapi/machine.json -@@ -1207,7 +1207,7 @@ - # - # @memdev: memory backend linked with device - # --# @node: the numa node -+# @node: the numa node (Since: 7.0) - # - # Since: 6.2 - ## -@@ -1288,7 +1288,7 @@ - # - # @memdev: memory backend linked with device - # --# @node: the numa node -+# @node: the numa node (Since: 7.0) - # - # Since: 6.2 - ## -diff --git a/qapi/misc-target.json b/qapi/misc-target.json -index 1022aa0184..4bc45d2474 100644 ---- a/qapi/misc-target.json -+++ b/qapi/misc-target.json -@@ -344,9 +344,9 @@ - # - # @node: the numa node - # --# @size: the size of epc section -+# @size: the size of EPC section - # --# Since: 6.2 -+# Since: 7.0 - ## - { 'struct': 'SGXEPCSection', - 'data': { 'node': 'int', -@@ -365,7 +365,13 @@ - # - # @flc: true if FLC is supported - # --# @sections: The EPC sections info for guest -+# @section-size: The EPC section size for guest -+# Redundant with @sections. Just for backward compatibility. -+# -+# @sections: The EPC sections info for guest (Since: 7.0) -+# -+# Features: -+# @deprecated: Member @section-size is deprecated. Use @sections instead. - # - # Since: 6.2 - ## -@@ -374,6 +380,8 @@ - 'sgx1': 'bool', - 'sgx2': 'bool', - 'flc': 'bool', -+ 'section-size': { 'type': 'uint64', -+ 'features': [ 'deprecated' ] }, - 'sections': ['SGXEPCSection']}, - 'if': 'TARGET_I386' } - -@@ -390,7 +398,9 @@ - # - # -> { "execute": "query-sgx" } - # <- { "return": { "sgx": true, "sgx1" : true, "sgx2" : true, --# "flc": true, "section-size" : 0 } } -+# "flc": true, "section-size" : 96468992, -+# "sections": [{"node": 0, "size": 67108864}, -+# {"node": 1, "size": 29360128}]} } - # - ## - { 'command': 'query-sgx', 'returns': 'SGXInfo', 'if': 'TARGET_I386' } -@@ -408,7 +418,9 @@ - # - # -> { "execute": "query-sgx-capabilities" } - # <- { "return": { "sgx": true, "sgx1" : true, "sgx2" : true, --# "flc": true, "section-size" : 0 } } -+# "flc": true, "section-size" : 96468992, -+# "section" : [{"node": 0, "size": 67108864}, -+# {"node": 1, "size": 29360128}]} } - # - ## - { 'command': 'query-sgx-capabilities', 'returns': 'SGXInfo', 'if': 'TARGET_I386' } --- -2.27.0 - diff --git a/SOURCES/kvm-qapi-machine.json-Add-cluster-id.patch b/SOURCES/kvm-qapi-machine.json-Add-cluster-id.patch new file mode 100644 index 0000000..2b2a22a --- /dev/null +++ b/SOURCES/kvm-qapi-machine.json-Add-cluster-id.patch @@ -0,0 +1,126 @@ +From e97c563f7146098119839aa146a6f25070eb7148 Mon Sep 17 00:00:00 2001 +From: Gavin Shan +Date: Wed, 11 May 2022 18:01:02 +0800 +Subject: [PATCH 01/16] qapi/machine.json: Add cluster-id + +RH-Author: Gavin Shan +RH-MergeRequest: 86: hw/arm/virt: Fix the default CPU topology +RH-Commit: [1/6] 44d7d83008c6d28485ae44f7cced792f4987b919 (gwshan/qemu-rhel-9) +RH-Bugzilla: 2041823 +RH-Acked-by: Eric Auger +RH-Acked-by: Cornelia Huck +RH-Acked-by: Andrew Jones + +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2041823 + +This adds cluster-id in CPU instance properties, which will be used +by arm/virt machine. Besides, the cluster-id is also verified or +dumped in various spots: + + * hw/core/machine.c::machine_set_cpu_numa_node() to associate + CPU with its NUMA node. + + * hw/core/machine.c::machine_numa_finish_cpu_init() to record + CPU slots with no NUMA mapping set. + + * hw/core/machine-hmp-cmds.c::hmp_hotpluggable_cpus() to dump + cluster-id. + +Signed-off-by: Gavin Shan +Reviewed-by: Yanan Wang +Acked-by: Igor Mammedov +Message-id: 20220503140304.855514-2-gshan@redhat.com +Signed-off-by: Peter Maydell +(cherry picked from commit 1dcf7001d4bae651129d46d5628b29e93a411d0b) +Signed-off-by: Gavin Shan +--- + hw/core/machine-hmp-cmds.c | 4 ++++ + hw/core/machine.c | 16 ++++++++++++++++ + qapi/machine.json | 6 ++++-- + 3 files changed, 24 insertions(+), 2 deletions(-) + +diff --git a/hw/core/machine-hmp-cmds.c b/hw/core/machine-hmp-cmds.c +index 4e2f319aeb..5cb5eecbfc 100644 +--- a/hw/core/machine-hmp-cmds.c ++++ b/hw/core/machine-hmp-cmds.c +@@ -77,6 +77,10 @@ void hmp_hotpluggable_cpus(Monitor *mon, const QDict *qdict) + if (c->has_die_id) { + monitor_printf(mon, " die-id: \"%" PRIu64 "\"\n", c->die_id); + } ++ if (c->has_cluster_id) { ++ monitor_printf(mon, " cluster-id: \"%" PRIu64 "\"\n", ++ c->cluster_id); ++ } + if (c->has_core_id) { + monitor_printf(mon, " core-id: \"%" PRIu64 "\"\n", c->core_id); + } +diff --git a/hw/core/machine.c b/hw/core/machine.c +index dffc3ef4ab..168f4de910 100644 +--- a/hw/core/machine.c ++++ b/hw/core/machine.c +@@ -890,6 +890,11 @@ void machine_set_cpu_numa_node(MachineState *machine, + return; + } + ++ if (props->has_cluster_id && !slot->props.has_cluster_id) { ++ error_setg(errp, "cluster-id is not supported"); ++ return; ++ } ++ + if (props->has_socket_id && !slot->props.has_socket_id) { + error_setg(errp, "socket-id is not supported"); + return; +@@ -909,6 +914,11 @@ void machine_set_cpu_numa_node(MachineState *machine, + continue; + } + ++ if (props->has_cluster_id && ++ props->cluster_id != slot->props.cluster_id) { ++ continue; ++ } ++ + if (props->has_die_id && props->die_id != slot->props.die_id) { + continue; + } +@@ -1203,6 +1213,12 @@ static char *cpu_slot_to_string(const CPUArchId *cpu) + } + g_string_append_printf(s, "die-id: %"PRId64, cpu->props.die_id); + } ++ if (cpu->props.has_cluster_id) { ++ if (s->len) { ++ g_string_append_printf(s, ", "); ++ } ++ g_string_append_printf(s, "cluster-id: %"PRId64, cpu->props.cluster_id); ++ } + if (cpu->props.has_core_id) { + if (s->len) { + g_string_append_printf(s, ", "); +diff --git a/qapi/machine.json b/qapi/machine.json +index d25a481ce4..4c417e32a5 100644 +--- a/qapi/machine.json ++++ b/qapi/machine.json +@@ -868,10 +868,11 @@ + # @node-id: NUMA node ID the CPU belongs to + # @socket-id: socket number within node/board the CPU belongs to + # @die-id: die number within socket the CPU belongs to (since 4.1) +-# @core-id: core number within die the CPU belongs to ++# @cluster-id: cluster number within die the CPU belongs to (since 7.1) ++# @core-id: core number within cluster the CPU belongs to + # @thread-id: thread number within core the CPU belongs to + # +-# Note: currently there are 5 properties that could be present ++# Note: currently there are 6 properties that could be present + # but management should be prepared to pass through other + # properties with device_add command to allow for future + # interface extension. This also requires the filed names to be kept in +@@ -883,6 +884,7 @@ + 'data': { '*node-id': 'int', + '*socket-id': 'int', + '*die-id': 'int', ++ '*cluster-id': 'int', + '*core-id': 'int', + '*thread-id': 'int' + } +-- +2.31.1 + diff --git a/SOURCES/kvm-qcow2-Add-errp-to-rebuild_refcount_structure.patch b/SOURCES/kvm-qcow2-Add-errp-to-rebuild_refcount_structure.patch new file mode 100644 index 0000000..9010d3d --- /dev/null +++ b/SOURCES/kvm-qcow2-Add-errp-to-rebuild_refcount_structure.patch @@ -0,0 +1,162 @@ +From 5e385a0e49a520550a83299632be175857b63f19 Mon Sep 17 00:00:00 2001 +From: Hanna Reitz +Date: Tue, 5 Apr 2022 15:46:52 +0200 +Subject: [PATCH 06/16] qcow2: Add errp to rebuild_refcount_structure() + +RH-Author: Hanna Reitz +RH-MergeRequest: 96: qcow2: Improve refcount structure rebuilding +RH-Commit: [3/4] 937b89a7eab6ec6b18618d59bc1526976ad03290 (hreitz/qemu-kvm-c-9-s) +RH-Bugzilla: 2072379 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Eric Blake +RH-Acked-by: Stefan Hajnoczi + +Instead of fprint()-ing error messages in rebuild_refcount_structure() +and its rebuild_refcounts_write_refblocks() helper, pass them through an +Error object to qcow2_check_refcounts() (which will then print it). + +Suggested-by: Eric Blake +Signed-off-by: Hanna Reitz +Message-Id: <20220405134652.19278-4-hreitz@redhat.com> +Reviewed-by: Eric Blake +(cherry picked from commit 0423f75351ab83b844a31349218b0eadd830e07a) +Signed-off-by: Hanna Reitz +--- + block/qcow2-refcount.c | 33 +++++++++++++++++++-------------- + 1 file changed, 19 insertions(+), 14 deletions(-) + +diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c +index c5669eaa51..ed0ecfaa89 100644 +--- a/block/qcow2-refcount.c ++++ b/block/qcow2-refcount.c +@@ -2465,7 +2465,8 @@ static int64_t alloc_clusters_imrt(BlockDriverState *bs, + static int rebuild_refcounts_write_refblocks( + BlockDriverState *bs, void **refcount_table, int64_t *nb_clusters, + int64_t first_cluster, int64_t end_cluster, +- uint64_t **on_disk_reftable_ptr, uint32_t *on_disk_reftable_entries_ptr ++ uint64_t **on_disk_reftable_ptr, uint32_t *on_disk_reftable_entries_ptr, ++ Error **errp + ) + { + BDRVQcow2State *s = bs->opaque; +@@ -2516,8 +2517,8 @@ static int rebuild_refcounts_write_refblocks( + nb_clusters, + &first_free_cluster); + if (refblock_offset < 0) { +- fprintf(stderr, "ERROR allocating refblock: %s\n", +- strerror(-refblock_offset)); ++ error_setg_errno(errp, -refblock_offset, ++ "ERROR allocating refblock"); + return refblock_offset; + } + +@@ -2539,6 +2540,7 @@ static int rebuild_refcounts_write_refblocks( + on_disk_reftable_entries * + REFTABLE_ENTRY_SIZE); + if (!on_disk_reftable) { ++ error_setg(errp, "ERROR allocating reftable memory"); + return -ENOMEM; + } + +@@ -2562,7 +2564,7 @@ static int rebuild_refcounts_write_refblocks( + ret = qcow2_pre_write_overlap_check(bs, 0, refblock_offset, + s->cluster_size, false); + if (ret < 0) { +- fprintf(stderr, "ERROR writing refblock: %s\n", strerror(-ret)); ++ error_setg_errno(errp, -ret, "ERROR writing refblock"); + return ret; + } + +@@ -2578,7 +2580,7 @@ static int rebuild_refcounts_write_refblocks( + ret = bdrv_pwrite(bs->file, refblock_offset, on_disk_refblock, + s->cluster_size); + if (ret < 0) { +- fprintf(stderr, "ERROR writing refblock: %s\n", strerror(-ret)); ++ error_setg_errno(errp, -ret, "ERROR writing refblock"); + return ret; + } + +@@ -2601,7 +2603,8 @@ static int rebuild_refcounts_write_refblocks( + static int rebuild_refcount_structure(BlockDriverState *bs, + BdrvCheckResult *res, + void **refcount_table, +- int64_t *nb_clusters) ++ int64_t *nb_clusters, ++ Error **errp) + { + BDRVQcow2State *s = bs->opaque; + int64_t reftable_offset = -1; +@@ -2652,7 +2655,7 @@ static int rebuild_refcount_structure(BlockDriverState *bs, + rebuild_refcounts_write_refblocks(bs, refcount_table, nb_clusters, + 0, *nb_clusters, + &on_disk_reftable, +- &on_disk_reftable_entries); ++ &on_disk_reftable_entries, errp); + if (reftable_size_changed < 0) { + res->check_errors++; + ret = reftable_size_changed; +@@ -2676,8 +2679,8 @@ static int rebuild_refcount_structure(BlockDriverState *bs, + refcount_table, nb_clusters, + &first_free_cluster); + if (reftable_offset < 0) { +- fprintf(stderr, "ERROR allocating reftable: %s\n", +- strerror(-reftable_offset)); ++ error_setg_errno(errp, -reftable_offset, ++ "ERROR allocating reftable"); + res->check_errors++; + ret = reftable_offset; + goto fail; +@@ -2695,7 +2698,7 @@ static int rebuild_refcount_structure(BlockDriverState *bs, + reftable_start_cluster, + reftable_end_cluster, + &on_disk_reftable, +- &on_disk_reftable_entries); ++ &on_disk_reftable_entries, errp); + if (reftable_size_changed < 0) { + res->check_errors++; + ret = reftable_size_changed; +@@ -2725,7 +2728,7 @@ static int rebuild_refcount_structure(BlockDriverState *bs, + ret = qcow2_pre_write_overlap_check(bs, 0, reftable_offset, reftable_length, + false); + if (ret < 0) { +- fprintf(stderr, "ERROR writing reftable: %s\n", strerror(-ret)); ++ error_setg_errno(errp, -ret, "ERROR writing reftable"); + goto fail; + } + +@@ -2733,7 +2736,7 @@ static int rebuild_refcount_structure(BlockDriverState *bs, + ret = bdrv_pwrite(bs->file, reftable_offset, on_disk_reftable, + reftable_length); + if (ret < 0) { +- fprintf(stderr, "ERROR writing reftable: %s\n", strerror(-ret)); ++ error_setg_errno(errp, -ret, "ERROR writing reftable"); + goto fail; + } + +@@ -2746,7 +2749,7 @@ static int rebuild_refcount_structure(BlockDriverState *bs, + &reftable_offset_and_clusters, + sizeof(reftable_offset_and_clusters)); + if (ret < 0) { +- fprintf(stderr, "ERROR setting reftable: %s\n", strerror(-ret)); ++ error_setg_errno(errp, -ret, "ERROR setting reftable"); + goto fail; + } + +@@ -2814,11 +2817,13 @@ int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res, + if (rebuild && (fix & BDRV_FIX_ERRORS)) { + BdrvCheckResult old_res = *res; + int fresh_leaks = 0; ++ Error *local_err = NULL; + + fprintf(stderr, "Rebuilding refcount structure\n"); + ret = rebuild_refcount_structure(bs, res, &refcount_table, +- &nb_clusters); ++ &nb_clusters, &local_err); + if (ret < 0) { ++ error_report_err(local_err); + goto fail; + } + +-- +2.31.1 + diff --git a/SOURCES/kvm-qcow2-Improve-refcount-structure-rebuilding.patch b/SOURCES/kvm-qcow2-Improve-refcount-structure-rebuilding.patch new file mode 100644 index 0000000..cdc92b8 --- /dev/null +++ b/SOURCES/kvm-qcow2-Improve-refcount-structure-rebuilding.patch @@ -0,0 +1,465 @@ +From b453cf6be8429f4438d51eb24fcf49e7d9f14db6 Mon Sep 17 00:00:00 2001 +From: Hanna Reitz +Date: Tue, 5 Apr 2022 15:46:50 +0200 +Subject: [PATCH 04/16] qcow2: Improve refcount structure rebuilding + +RH-Author: Hanna Reitz +RH-MergeRequest: 96: qcow2: Improve refcount structure rebuilding +RH-Commit: [1/4] a3606b7abcaebb4930b566e95b1090aead62dfae (hreitz/qemu-kvm-c-9-s) +RH-Bugzilla: 2072379 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Eric Blake +RH-Acked-by: Stefan Hajnoczi + +When rebuilding the refcount structures (when qemu-img check -r found +errors with refcount = 0, but reference count > 0), the new refcount +table defaults to being put at the image file end[1]. There is no good +reason for that except that it means we will not have to rewrite any +refblocks we already wrote to disk. + +Changing the code to rewrite those refblocks is not too difficult, +though, so let us do that. That is beneficial for images on block +devices, where we cannot really write beyond the end of the image file. + +Use this opportunity to add extensive comments to the code, and refactor +it a bit, getting rid of the backwards-jumping goto. + +[1] Unless there is something allocated in the area pointed to by the + last refblock, so we have to write that refblock. In that case, we + try to put the reftable in there. + +Buglink: https://bugzilla.redhat.com/show_bug.cgi?id=1519071 +Closes: https://gitlab.com/qemu-project/qemu/-/issues/941 +Reviewed-by: Eric Blake +Signed-off-by: Hanna Reitz +Message-Id: <20220405134652.19278-2-hreitz@redhat.com> +(cherry picked from commit a8c07ec287554dcefd33733f0e5888a281ddc95e) +Signed-off-by: Hanna Reitz +--- + block/qcow2-refcount.c | 332 +++++++++++++++++++++++++++++------------ + 1 file changed, 235 insertions(+), 97 deletions(-) + +diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c +index b91499410c..c5669eaa51 100644 +--- a/block/qcow2-refcount.c ++++ b/block/qcow2-refcount.c +@@ -2438,111 +2438,140 @@ static int64_t alloc_clusters_imrt(BlockDriverState *bs, + } + + /* +- * Creates a new refcount structure based solely on the in-memory information +- * given through *refcount_table. All necessary allocations will be reflected +- * in that array. ++ * Helper function for rebuild_refcount_structure(). + * +- * On success, the old refcount structure is leaked (it will be covered by the +- * new refcount structure). ++ * Scan the range of clusters [first_cluster, end_cluster) for allocated ++ * clusters and write all corresponding refblocks to disk. The refblock ++ * and allocation data is taken from the in-memory refcount table ++ * *refcount_table[] (of size *nb_clusters), which is basically one big ++ * (unlimited size) refblock for the whole image. ++ * ++ * For these refblocks, clusters are allocated using said in-memory ++ * refcount table. Care is taken that these allocations are reflected ++ * in the refblocks written to disk. ++ * ++ * The refblocks' offsets are written into a reftable, which is ++ * *on_disk_reftable_ptr[] (of size *on_disk_reftable_entries_ptr). If ++ * that reftable is of insufficient size, it will be resized to fit. ++ * This reftable is not written to disk. ++ * ++ * (If *on_disk_reftable_ptr is not NULL, the entries within are assumed ++ * to point to existing valid refblocks that do not need to be allocated ++ * again.) ++ * ++ * Return whether the on-disk reftable array was resized (true/false), ++ * or -errno on error. + */ +-static int rebuild_refcount_structure(BlockDriverState *bs, +- BdrvCheckResult *res, +- void **refcount_table, +- int64_t *nb_clusters) ++static int rebuild_refcounts_write_refblocks( ++ BlockDriverState *bs, void **refcount_table, int64_t *nb_clusters, ++ int64_t first_cluster, int64_t end_cluster, ++ uint64_t **on_disk_reftable_ptr, uint32_t *on_disk_reftable_entries_ptr ++ ) + { + BDRVQcow2State *s = bs->opaque; +- int64_t first_free_cluster = 0, reftable_offset = -1, cluster = 0; ++ int64_t cluster; + int64_t refblock_offset, refblock_start, refblock_index; +- uint32_t reftable_size = 0; +- uint64_t *on_disk_reftable = NULL; ++ int64_t first_free_cluster = 0; ++ uint64_t *on_disk_reftable = *on_disk_reftable_ptr; ++ uint32_t on_disk_reftable_entries = *on_disk_reftable_entries_ptr; + void *on_disk_refblock; +- int ret = 0; +- struct { +- uint64_t reftable_offset; +- uint32_t reftable_clusters; +- } QEMU_PACKED reftable_offset_and_clusters; +- +- qcow2_cache_empty(bs, s->refcount_block_cache); ++ bool reftable_grown = false; ++ int ret; + +-write_refblocks: +- for (; cluster < *nb_clusters; cluster++) { ++ for (cluster = first_cluster; cluster < end_cluster; cluster++) { ++ /* Check all clusters to find refblocks that contain non-zero entries */ + if (!s->get_refcount(*refcount_table, cluster)) { + continue; + } + ++ /* ++ * This cluster is allocated, so we need to create a refblock ++ * for it. The data we will write to disk is just the ++ * respective slice from *refcount_table, so it will contain ++ * accurate refcounts for all clusters belonging to this ++ * refblock. After we have written it, we will therefore skip ++ * all remaining clusters in this refblock. ++ */ ++ + refblock_index = cluster >> s->refcount_block_bits; + refblock_start = refblock_index << s->refcount_block_bits; + +- /* Don't allocate a cluster in a refblock already written to disk */ +- if (first_free_cluster < refblock_start) { +- first_free_cluster = refblock_start; +- } +- refblock_offset = alloc_clusters_imrt(bs, 1, refcount_table, +- nb_clusters, &first_free_cluster); +- if (refblock_offset < 0) { +- fprintf(stderr, "ERROR allocating refblock: %s\n", +- strerror(-refblock_offset)); +- res->check_errors++; +- ret = refblock_offset; +- goto fail; +- } ++ if (on_disk_reftable_entries > refblock_index && ++ on_disk_reftable[refblock_index]) ++ { ++ /* ++ * We can get here after a `goto write_refblocks`: We have a ++ * reftable from a previous run, and the refblock is already ++ * allocated. No need to allocate it again. ++ */ ++ refblock_offset = on_disk_reftable[refblock_index]; ++ } else { ++ int64_t refblock_cluster_index; + +- if (reftable_size <= refblock_index) { +- uint32_t old_reftable_size = reftable_size; +- uint64_t *new_on_disk_reftable; ++ /* Don't allocate a cluster in a refblock already written to disk */ ++ if (first_free_cluster < refblock_start) { ++ first_free_cluster = refblock_start; ++ } ++ refblock_offset = alloc_clusters_imrt(bs, 1, refcount_table, ++ nb_clusters, ++ &first_free_cluster); ++ if (refblock_offset < 0) { ++ fprintf(stderr, "ERROR allocating refblock: %s\n", ++ strerror(-refblock_offset)); ++ return refblock_offset; ++ } + +- reftable_size = ROUND_UP((refblock_index + 1) * REFTABLE_ENTRY_SIZE, +- s->cluster_size) / REFTABLE_ENTRY_SIZE; +- new_on_disk_reftable = g_try_realloc(on_disk_reftable, +- reftable_size * +- REFTABLE_ENTRY_SIZE); +- if (!new_on_disk_reftable) { +- res->check_errors++; +- ret = -ENOMEM; +- goto fail; ++ refblock_cluster_index = refblock_offset / s->cluster_size; ++ if (refblock_cluster_index >= end_cluster) { ++ /* ++ * We must write the refblock that holds this refblock's ++ * refcount ++ */ ++ end_cluster = refblock_cluster_index + 1; + } +- on_disk_reftable = new_on_disk_reftable; + +- memset(on_disk_reftable + old_reftable_size, 0, +- (reftable_size - old_reftable_size) * REFTABLE_ENTRY_SIZE); ++ if (on_disk_reftable_entries <= refblock_index) { ++ on_disk_reftable_entries = ++ ROUND_UP((refblock_index + 1) * REFTABLE_ENTRY_SIZE, ++ s->cluster_size) / REFTABLE_ENTRY_SIZE; ++ on_disk_reftable = ++ g_try_realloc(on_disk_reftable, ++ on_disk_reftable_entries * ++ REFTABLE_ENTRY_SIZE); ++ if (!on_disk_reftable) { ++ return -ENOMEM; ++ } + +- /* The offset we have for the reftable is now no longer valid; +- * this will leak that range, but we can easily fix that by running +- * a leak-fixing check after this rebuild operation */ +- reftable_offset = -1; +- } else { +- assert(on_disk_reftable); +- } +- on_disk_reftable[refblock_index] = refblock_offset; ++ memset(on_disk_reftable + *on_disk_reftable_entries_ptr, 0, ++ (on_disk_reftable_entries - ++ *on_disk_reftable_entries_ptr) * ++ REFTABLE_ENTRY_SIZE); + +- /* If this is apparently the last refblock (for now), try to squeeze the +- * reftable in */ +- if (refblock_index == (*nb_clusters - 1) >> s->refcount_block_bits && +- reftable_offset < 0) +- { +- uint64_t reftable_clusters = size_to_clusters(s, reftable_size * +- REFTABLE_ENTRY_SIZE); +- reftable_offset = alloc_clusters_imrt(bs, reftable_clusters, +- refcount_table, nb_clusters, +- &first_free_cluster); +- if (reftable_offset < 0) { +- fprintf(stderr, "ERROR allocating reftable: %s\n", +- strerror(-reftable_offset)); +- res->check_errors++; +- ret = reftable_offset; +- goto fail; ++ *on_disk_reftable_ptr = on_disk_reftable; ++ *on_disk_reftable_entries_ptr = on_disk_reftable_entries; ++ ++ reftable_grown = true; ++ } else { ++ assert(on_disk_reftable); + } ++ on_disk_reftable[refblock_index] = refblock_offset; + } + ++ /* Refblock is allocated, write it to disk */ ++ + ret = qcow2_pre_write_overlap_check(bs, 0, refblock_offset, + s->cluster_size, false); + if (ret < 0) { + fprintf(stderr, "ERROR writing refblock: %s\n", strerror(-ret)); +- goto fail; ++ return ret; + } + +- /* The size of *refcount_table is always cluster-aligned, therefore the +- * write operation will not overflow */ ++ /* ++ * The refblock is simply a slice of *refcount_table. ++ * Note that the size of *refcount_table is always aligned to ++ * whole clusters, so the write operation will not result in ++ * out-of-bounds accesses. ++ */ + on_disk_refblock = (void *)((char *) *refcount_table + + refblock_index * s->cluster_size); + +@@ -2550,23 +2579,99 @@ write_refblocks: + s->cluster_size); + if (ret < 0) { + fprintf(stderr, "ERROR writing refblock: %s\n", strerror(-ret)); +- goto fail; ++ return ret; + } + +- /* Go to the end of this refblock */ ++ /* This refblock is done, skip to its end */ + cluster = refblock_start + s->refcount_block_size - 1; + } + +- if (reftable_offset < 0) { +- uint64_t post_refblock_start, reftable_clusters; ++ return reftable_grown; ++} ++ ++/* ++ * Creates a new refcount structure based solely on the in-memory information ++ * given through *refcount_table (this in-memory information is basically just ++ * the concatenation of all refblocks). All necessary allocations will be ++ * reflected in that array. ++ * ++ * On success, the old refcount structure is leaked (it will be covered by the ++ * new refcount structure). ++ */ ++static int rebuild_refcount_structure(BlockDriverState *bs, ++ BdrvCheckResult *res, ++ void **refcount_table, ++ int64_t *nb_clusters) ++{ ++ BDRVQcow2State *s = bs->opaque; ++ int64_t reftable_offset = -1; ++ int64_t reftable_length = 0; ++ int64_t reftable_clusters; ++ int64_t refblock_index; ++ uint32_t on_disk_reftable_entries = 0; ++ uint64_t *on_disk_reftable = NULL; ++ int ret = 0; ++ int reftable_size_changed = 0; ++ struct { ++ uint64_t reftable_offset; ++ uint32_t reftable_clusters; ++ } QEMU_PACKED reftable_offset_and_clusters; ++ ++ qcow2_cache_empty(bs, s->refcount_block_cache); ++ ++ /* ++ * For each refblock containing entries, we try to allocate a ++ * cluster (in the in-memory refcount table) and write its offset ++ * into on_disk_reftable[]. We then write the whole refblock to ++ * disk (as a slice of the in-memory refcount table). ++ * This is done by rebuild_refcounts_write_refblocks(). ++ * ++ * Once we have scanned all clusters, we try to find space for the ++ * reftable. This will dirty the in-memory refcount table (i.e. ++ * make it differ from the refblocks we have already written), so we ++ * need to run rebuild_refcounts_write_refblocks() again for the ++ * range of clusters where the reftable has been allocated. ++ * ++ * This second run might make the reftable grow again, in which case ++ * we will need to allocate another space for it, which is why we ++ * repeat all this until the reftable stops growing. ++ * ++ * (This loop will terminate, because with every cluster the ++ * reftable grows, it can accomodate a multitude of more refcounts, ++ * so that at some point this must be able to cover the reftable ++ * and all refblocks describing it.) ++ * ++ * We then convert the reftable to big-endian and write it to disk. ++ * ++ * Note that we never free any reftable allocations. Doing so would ++ * needlessly complicate the algorithm: The eventual second check ++ * run we do will clean up all leaks we have caused. ++ */ ++ ++ reftable_size_changed = ++ rebuild_refcounts_write_refblocks(bs, refcount_table, nb_clusters, ++ 0, *nb_clusters, ++ &on_disk_reftable, ++ &on_disk_reftable_entries); ++ if (reftable_size_changed < 0) { ++ res->check_errors++; ++ ret = reftable_size_changed; ++ goto fail; ++ } ++ ++ /* ++ * There was no reftable before, so rebuild_refcounts_write_refblocks() ++ * must have increased its size (from 0 to something). ++ */ ++ assert(reftable_size_changed); ++ ++ do { ++ int64_t reftable_start_cluster, reftable_end_cluster; ++ int64_t first_free_cluster = 0; ++ ++ reftable_length = on_disk_reftable_entries * REFTABLE_ENTRY_SIZE; ++ reftable_clusters = size_to_clusters(s, reftable_length); + +- post_refblock_start = ROUND_UP(*nb_clusters, s->refcount_block_size); +- reftable_clusters = +- size_to_clusters(s, reftable_size * REFTABLE_ENTRY_SIZE); +- /* Not pretty but simple */ +- if (first_free_cluster < post_refblock_start) { +- first_free_cluster = post_refblock_start; +- } + reftable_offset = alloc_clusters_imrt(bs, reftable_clusters, + refcount_table, nb_clusters, + &first_free_cluster); +@@ -2578,24 +2683,55 @@ write_refblocks: + goto fail; + } + +- goto write_refblocks; +- } ++ /* ++ * We need to update the affected refblocks, so re-run the ++ * write_refblocks loop for the reftable's range of clusters. ++ */ ++ assert(offset_into_cluster(s, reftable_offset) == 0); ++ reftable_start_cluster = reftable_offset / s->cluster_size; ++ reftable_end_cluster = reftable_start_cluster + reftable_clusters; ++ reftable_size_changed = ++ rebuild_refcounts_write_refblocks(bs, refcount_table, nb_clusters, ++ reftable_start_cluster, ++ reftable_end_cluster, ++ &on_disk_reftable, ++ &on_disk_reftable_entries); ++ if (reftable_size_changed < 0) { ++ res->check_errors++; ++ ret = reftable_size_changed; ++ goto fail; ++ } ++ ++ /* ++ * If the reftable size has changed, we will need to find a new ++ * allocation, repeating the loop. ++ */ ++ } while (reftable_size_changed); + +- for (refblock_index = 0; refblock_index < reftable_size; refblock_index++) { ++ /* The above loop must have run at least once */ ++ assert(reftable_offset >= 0); ++ ++ /* ++ * All allocations are done, all refblocks are written, convert the ++ * reftable to big-endian and write it to disk. ++ */ ++ ++ for (refblock_index = 0; refblock_index < on_disk_reftable_entries; ++ refblock_index++) ++ { + cpu_to_be64s(&on_disk_reftable[refblock_index]); + } + +- ret = qcow2_pre_write_overlap_check(bs, 0, reftable_offset, +- reftable_size * REFTABLE_ENTRY_SIZE, ++ ret = qcow2_pre_write_overlap_check(bs, 0, reftable_offset, reftable_length, + false); + if (ret < 0) { + fprintf(stderr, "ERROR writing reftable: %s\n", strerror(-ret)); + goto fail; + } + +- assert(reftable_size < INT_MAX / REFTABLE_ENTRY_SIZE); ++ assert(reftable_length < INT_MAX); + ret = bdrv_pwrite(bs->file, reftable_offset, on_disk_reftable, +- reftable_size * REFTABLE_ENTRY_SIZE); ++ reftable_length); + if (ret < 0) { + fprintf(stderr, "ERROR writing reftable: %s\n", strerror(-ret)); + goto fail; +@@ -2604,7 +2740,7 @@ write_refblocks: + /* Enter new reftable into the image header */ + reftable_offset_and_clusters.reftable_offset = cpu_to_be64(reftable_offset); + reftable_offset_and_clusters.reftable_clusters = +- cpu_to_be32(size_to_clusters(s, reftable_size * REFTABLE_ENTRY_SIZE)); ++ cpu_to_be32(reftable_clusters); + ret = bdrv_pwrite_sync(bs->file, + offsetof(QCowHeader, refcount_table_offset), + &reftable_offset_and_clusters, +@@ -2614,12 +2750,14 @@ write_refblocks: + goto fail; + } + +- for (refblock_index = 0; refblock_index < reftable_size; refblock_index++) { ++ for (refblock_index = 0; refblock_index < on_disk_reftable_entries; ++ refblock_index++) ++ { + be64_to_cpus(&on_disk_reftable[refblock_index]); + } + s->refcount_table = on_disk_reftable; + s->refcount_table_offset = reftable_offset; +- s->refcount_table_size = reftable_size; ++ s->refcount_table_size = on_disk_reftable_entries; + update_max_refcount_table_index(s); + + return 0; +-- +2.31.1 + diff --git a/SOURCES/kvm-qemu-img-make-is_allocated_sectors-more-efficient.patch b/SOURCES/kvm-qemu-img-make-is_allocated_sectors-more-efficient.patch deleted file mode 100644 index 2d67070..0000000 --- a/SOURCES/kvm-qemu-img-make-is_allocated_sectors-more-efficient.patch +++ /dev/null @@ -1,108 +0,0 @@ -From a221f5a8ed02690687e6709c49ae0e1e01c5f466 Mon Sep 17 00:00:00 2001 -From: Vladimir Sementsov-Ogievskiy -Date: Fri, 17 Dec 2021 17:46:54 +0100 -Subject: [PATCH 09/12] qemu-img: make is_allocated_sectors() more efficient - -RH-Author: Kevin Wolf -RH-MergeRequest: 70: qemu-img convert: Fix sparseness of output image -RH-Commit: [2/2] cc05aa4ac506b57ff9b430c007618cdf1485a03f (kmwolf/centos-qemu-kvm) -RH-Bugzilla: 1882917 -RH-Acked-by: Eric Blake -RH-Acked-by: Stefan Hajnoczi -RH-Acked-by: Hanna Reitz - -Consider the case when the whole buffer is zero and end is unaligned. - -If i <= tail, we return 1 and do one unaligned WRITE, RMW happens. - -If i > tail, we do on aligned WRITE_ZERO (or skip if target is zeroed) -and again one unaligned WRITE, RMW happens. - -Let's do better: don't fragment the whole-zero buffer and report it as -ZERO: in case of zeroed target we just do nothing and avoid RMW. If -target is not zeroes, one unaligned WRITE_ZERO should not be much worse -than one unaligned WRITE. - -Signed-off-by: Vladimir Sementsov-Ogievskiy -Message-Id: <20211217164654.1184218-3-vsementsov@virtuozzo.com> -Tested-by: Peter Lieven -Signed-off-by: Kevin Wolf -(cherry picked from commit 96054c76ff2db74165385a69f234c57a6bbc941e) -Signed-off-by: Kevin Wolf ---- - qemu-img.c | 23 +++++++++++++++++++---- - tests/qemu-iotests/122.out | 8 ++------ - 2 files changed, 21 insertions(+), 10 deletions(-) - -diff --git a/qemu-img.c b/qemu-img.c -index f036a1d428..d7ddfcc528 100644 ---- a/qemu-img.c -+++ b/qemu-img.c -@@ -1171,19 +1171,34 @@ static int is_allocated_sectors(const uint8_t *buf, int n, int *pnum, - } - } - -+ if (i == n) { -+ /* -+ * The whole buf is the same. -+ * No reason to split it into chunks, so return now. -+ */ -+ *pnum = i; -+ return !is_zero; -+ } -+ - tail = (sector_num + i) & (alignment - 1); - if (tail) { - if (is_zero && i <= tail) { -- /* treat unallocated areas which only consist -- * of a small tail as allocated. */ -+ /* -+ * For sure next sector after i is data, and it will rewrite this -+ * tail anyway due to RMW. So, let's just write data now. -+ */ - is_zero = false; - } - if (!is_zero) { -- /* align up end offset of allocated areas. */ -+ /* If possible, align up end offset of allocated areas. */ - i += alignment - tail; - i = MIN(i, n); - } else { -- /* align down end offset of zero areas. */ -+ /* -+ * For sure next sector after i is data, and it will rewrite this -+ * tail anyway due to RMW. Better is avoid RMW and write zeroes up -+ * to aligned bound. -+ */ - i -= tail; - } - } -diff --git a/tests/qemu-iotests/122.out b/tests/qemu-iotests/122.out -index 69b8e8b803..e18766e167 100644 ---- a/tests/qemu-iotests/122.out -+++ b/tests/qemu-iotests/122.out -@@ -201,9 +201,7 @@ convert -S 4k - { "start": 8192, "length": 4096, "depth": 0, "present": true, "zero": false, "data": true, "offset": OFFSET}, - { "start": 12288, "length": 4096, "depth": 0, "present": false, "zero": true, "data": false}, - { "start": 16384, "length": 4096, "depth": 0, "present": true, "zero": false, "data": true, "offset": OFFSET}, --{ "start": 20480, "length": 46080, "depth": 0, "present": false, "zero": true, "data": false}, --{ "start": 66560, "length": 1024, "depth": 0, "present": true, "zero": false, "data": true, "offset": OFFSET}, --{ "start": 67584, "length": 67041280, "depth": 0, "present": false, "zero": true, "data": false}] -+{ "start": 20480, "length": 67088384, "depth": 0, "present": false, "zero": true, "data": false}] - - convert -c -S 4k - [{ "start": 0, "length": 1024, "depth": 0, "present": true, "zero": false, "data": true}, -@@ -215,9 +213,7 @@ convert -c -S 4k - - convert -S 8k - [{ "start": 0, "length": 24576, "depth": 0, "present": true, "zero": false, "data": true, "offset": OFFSET}, --{ "start": 24576, "length": 41984, "depth": 0, "present": false, "zero": true, "data": false}, --{ "start": 66560, "length": 1024, "depth": 0, "present": true, "zero": false, "data": true, "offset": OFFSET}, --{ "start": 67584, "length": 67041280, "depth": 0, "present": false, "zero": true, "data": false}] -+{ "start": 24576, "length": 67084288, "depth": 0, "present": false, "zero": true, "data": false}] - - convert -c -S 8k - [{ "start": 0, "length": 1024, "depth": 0, "present": true, "zero": false, "data": true}, --- -2.27.0 - diff --git a/SOURCES/kvm-qemu-nbd-Pass-max-connections-to-blockdev-layer.patch b/SOURCES/kvm-qemu-nbd-Pass-max-connections-to-blockdev-layer.patch new file mode 100644 index 0000000..9acff58 --- /dev/null +++ b/SOURCES/kvm-qemu-nbd-Pass-max-connections-to-blockdev-layer.patch @@ -0,0 +1,92 @@ +From e6aae1d0368a152924c38775e517f4e83c1d898b Mon Sep 17 00:00:00 2001 +From: Eric Blake +Date: Wed, 11 May 2022 19:49:23 -0500 +Subject: [PATCH 1/2] qemu-nbd: Pass max connections to blockdev layer +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eric Blake +RH-MergeRequest: 90: Advertise MULTI_CONN on writeable NBD servers +RH-Commit: [1/2] b0e33fd125bf3523b8b9a4dead3c8bb2342bfd4e (ebblake/centos-qemu-kvm) +RH-Bugzilla: 1708300 +RH-Acked-by: Nir Soffer +RH-Acked-by: Kevin Wolf +RH-Acked-by: Daniel P. Berrangé + +The next patch wants to adjust whether the NBD server code advertises +MULTI_CONN based on whether it is known if the server limits to +exactly one client. For a server started by QMP, this information is +obtained through nbd_server_start (which can support more than one +export); but for qemu-nbd (which supports exactly one export), it is +controlled only by the command-line option -e/--shared. Since we +already have a hook function used by qemu-nbd, it's easiest to just +alter its signature to fit our needs. + +Signed-off-by: Eric Blake +Message-Id: <20220512004924.417153-2-eblake@redhat.com> +Signed-off-by: Kevin Wolf +(cherry picked from commit a5fced40212ed73c715ca298a2929dd4d99c9999) +Signed-off-by: Eric Blake +--- + blockdev-nbd.c | 8 ++++---- + include/block/nbd.h | 2 +- + qemu-nbd.c | 2 +- + 3 files changed, 6 insertions(+), 6 deletions(-) + +diff --git a/blockdev-nbd.c b/blockdev-nbd.c +index 9840d25a82..add41a23af 100644 +--- a/blockdev-nbd.c ++++ b/blockdev-nbd.c +@@ -30,18 +30,18 @@ typedef struct NBDServerData { + } NBDServerData; + + static NBDServerData *nbd_server; +-static bool is_qemu_nbd; ++static int qemu_nbd_connections = -1; /* Non-negative if this is qemu-nbd */ + + static void nbd_update_server_watch(NBDServerData *s); + +-void nbd_server_is_qemu_nbd(bool value) ++void nbd_server_is_qemu_nbd(int max_connections) + { +- is_qemu_nbd = value; ++ qemu_nbd_connections = max_connections; + } + + bool nbd_server_is_running(void) + { +- return nbd_server || is_qemu_nbd; ++ return nbd_server || qemu_nbd_connections >= 0; + } + + static void nbd_blockdev_client_closed(NBDClient *client, bool ignored) +diff --git a/include/block/nbd.h b/include/block/nbd.h +index a98eb665da..c5a29ce1c6 100644 +--- a/include/block/nbd.h ++++ b/include/block/nbd.h +@@ -344,7 +344,7 @@ void nbd_client_new(QIOChannelSocket *sioc, + void nbd_client_get(NBDClient *client); + void nbd_client_put(NBDClient *client); + +-void nbd_server_is_qemu_nbd(bool value); ++void nbd_server_is_qemu_nbd(int max_connections); + bool nbd_server_is_running(void); + void nbd_server_start(SocketAddress *addr, const char *tls_creds, + const char *tls_authz, uint32_t max_connections, +diff --git a/qemu-nbd.c b/qemu-nbd.c +index 713e7557a9..8c25ae93df 100644 +--- a/qemu-nbd.c ++++ b/qemu-nbd.c +@@ -1087,7 +1087,7 @@ int main(int argc, char **argv) + + bs->detect_zeroes = detect_zeroes; + +- nbd_server_is_qemu_nbd(true); ++ nbd_server_is_qemu_nbd(shared); + + export_opts = g_new(BlockExportOptions, 1); + *export_opts = (BlockExportOptions) { +-- +2.31.1 + diff --git a/SOURCES/kvm-qemu-storage-daemon-Add-vhost-user-blk-help.patch b/SOURCES/kvm-qemu-storage-daemon-Add-vhost-user-blk-help.patch deleted file mode 100644 index bc36f5c..0000000 --- a/SOURCES/kvm-qemu-storage-daemon-Add-vhost-user-blk-help.patch +++ /dev/null @@ -1,72 +0,0 @@ -From 0f4592f79f8c24f84db18a8c39c6056b2a0be524 Mon Sep 17 00:00:00 2001 -From: =?UTF-8?q?Philippe=20Mathieu-Daud=C3=A9?= -Date: Fri, 7 Jan 2022 11:54:19 +0100 -Subject: [PATCH 1/5] qemu-storage-daemon: Add vhost-user-blk help -MIME-Version: 1.0 -Content-Type: text/plain; charset=UTF-8 -Content-Transfer-Encoding: 8bit - -RH-Author: Kevin Wolf -RH-MergeRequest: 63: qemu-storage-daemon: Add vhost-user-blk help -RH-Commit: [1/2] 6b08fec5d6ceea9f8f3810321099310069e08b53 (kmwolf/centos-qemu-kvm) -RH-Bugzilla: 1962088 -RH-Acked-by: Miroslav Rezanina -RH-Acked-by: Stefano Garzarella -RH-Acked-by: Hanna Reitz - -Add missing vhost-user-blk help: - - $ qemu-storage-daemon -h - ... - --export [type=]vhost-user-blk,id=,node-name=, - addr.type=unix,addr.path=[,writable=on|off] - [,logical-block-size=][,num-queues=] - export the specified block node as a - vhosts-user-blk device over UNIX domain socket - --export [type=]vhost-user-blk,id=,node-name=, - fd,addr.str=[,writable=on|off] - [,logical-block-size=][,num-queues=] - export the specified block node as a - vhosts-user-blk device over file descriptor - ... - -Fixes: 90fc91d50b7 ("convert vhost-user-blk server to block export API") -Reported-by: Qing Wang -Reviewed-by: Eric Blake -Signed-off-by: Philippe Mathieu-Daudé -Signed-off-by: Philippe Mathieu-Daudé -Message-Id: <20220107105420.395011-3-f4bug@amsat.org> -Signed-off-by: Kevin Wolf -(cherry picked from commit c8cbc9524269d9583749aaaea8aa244add7e1900) -Signed-off-by: Kevin Wolf ---- - storage-daemon/qemu-storage-daemon.c | 13 +++++++++++++ - 1 file changed, 13 insertions(+) - -diff --git a/storage-daemon/qemu-storage-daemon.c b/storage-daemon/qemu-storage-daemon.c -index 52cf17e8ac..9d76d1114d 100644 ---- a/storage-daemon/qemu-storage-daemon.c -+++ b/storage-daemon/qemu-storage-daemon.c -@@ -104,6 +104,19 @@ static void help(void) - " export the specified block node over FUSE\n" - "\n" - #endif /* CONFIG_FUSE */ -+#ifdef CONFIG_VHOST_USER_BLK_SERVER -+" --export [type=]vhost-user-blk,id=,node-name=,\n" -+" addr.type=unix,addr.path=[,writable=on|off]\n" -+" [,logical-block-size=][,num-queues=]\n" -+" export the specified block node as a\n" -+" vhost-user-blk device over UNIX domain socket\n" -+" --export [type=]vhost-user-blk,id=,node-name=,\n" -+" fd,addr.str=[,writable=on|off]\n" -+" [,logical-block-size=][,num-queues=]\n" -+" export the specified block node as a\n" -+" vhost-user-blk device over file descriptor\n" -+"\n" -+#endif /* CONFIG_VHOST_USER_BLK_SERVER */ - " --monitor [chardev=]name[,mode=control][,pretty[=on|off]]\n" - " configure a QMP monitor\n" - "\n" --- -2.27.0 - diff --git a/SOURCES/kvm-qemu-storage-daemon-Fix-typo-in-vhost-user-blk-help.patch b/SOURCES/kvm-qemu-storage-daemon-Fix-typo-in-vhost-user-blk-help.patch deleted file mode 100644 index 798a27e..0000000 --- a/SOURCES/kvm-qemu-storage-daemon-Fix-typo-in-vhost-user-blk-help.patch +++ /dev/null @@ -1,41 +0,0 @@ -From 20edf203c8cb314e27409918399aa7cbdc6fdb02 Mon Sep 17 00:00:00 2001 -From: Kevin Wolf -Date: Tue, 25 Jan 2022 16:15:14 +0100 -Subject: [PATCH 2/5] qemu-storage-daemon: Fix typo in vhost-user-blk help - -RH-Author: Kevin Wolf -RH-MergeRequest: 63: qemu-storage-daemon: Add vhost-user-blk help -RH-Commit: [2/2] b7afb670c398799b6e49b926e296771453a55fba (kmwolf/centos-qemu-kvm) -RH-Bugzilla: 1962088 -RH-Acked-by: Miroslav Rezanina -RH-Acked-by: Stefano Garzarella -RH-Acked-by: Hanna Reitz - -The syntax of the fd passing case misses the "addr.type=" key. Add it. - -Signed-off-by: Kevin Wolf -Message-Id: <20220125151514.49035-1-kwolf@redhat.com> -Reviewed-by: Hanna Reitz -Signed-off-by: Kevin Wolf -(cherry picked from commit e66e665f15736f5ee1fbd8087926cb0f1e52f61a) -Signed-off-by: Kevin Wolf ---- - storage-daemon/qemu-storage-daemon.c | 2 +- - 1 file changed, 1 insertion(+), 1 deletion(-) - -diff --git a/storage-daemon/qemu-storage-daemon.c b/storage-daemon/qemu-storage-daemon.c -index 9d76d1114d..ec9aa79b55 100644 ---- a/storage-daemon/qemu-storage-daemon.c -+++ b/storage-daemon/qemu-storage-daemon.c -@@ -111,7 +111,7 @@ static void help(void) - " export the specified block node as a\n" - " vhost-user-blk device over UNIX domain socket\n" - " --export [type=]vhost-user-blk,id=,node-name=,\n" --" fd,addr.str=[,writable=on|off]\n" -+" addr.type=fd,addr.str=[,writable=on|off]\n" - " [,logical-block-size=][,num-queues=]\n" - " export the specified block node as a\n" - " vhost-user-blk device over file descriptor\n" --- -2.27.0 - diff --git a/SOURCES/kvm-qtest-numa-test-Correct-CPU-and-NUMA-association-in-.patch b/SOURCES/kvm-qtest-numa-test-Correct-CPU-and-NUMA-association-in-.patch new file mode 100644 index 0000000..9c2ac99 --- /dev/null +++ b/SOURCES/kvm-qtest-numa-test-Correct-CPU-and-NUMA-association-in-.patch @@ -0,0 +1,100 @@ +From a039ed652e6d2f5edcef9d5d1d3baec17ce7f929 Mon Sep 17 00:00:00 2001 +From: Gavin Shan +Date: Wed, 11 May 2022 18:01:35 +0800 +Subject: [PATCH 04/16] qtest/numa-test: Correct CPU and NUMA association in + aarch64_numa_cpu() + +RH-Author: Gavin Shan +RH-MergeRequest: 86: hw/arm/virt: Fix the default CPU topology +RH-Commit: [4/6] 64e9908a179eb4fb586d662f70f275a81808e50c (gwshan/qemu-rhel-9) +RH-Bugzilla: 2041823 +RH-Acked-by: Eric Auger +RH-Acked-by: Cornelia Huck +RH-Acked-by: Andrew Jones + +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2041823 + +In aarch64_numa_cpu(), the CPU and NUMA association is something +like below. Two threads in the same core/cluster/socket are +associated with two individual NUMA nodes, which is unreal as +Igor Mammedov mentioned. We don't expect the association to break +NUMA-to-socket boundary, which matches with the real world. + +NUMA-node socket cluster core thread +------------------------------------------ +0 0 0 0 0 +1 0 0 0 1 + +This corrects the topology for CPUs and their association with +NUMA nodes. After this patch is applied, the CPU and NUMA +association becomes something like below, which looks real. +Besides, socket/cluster/core/thread IDs are all checked when +the NUMA node IDs are verified. It helps to check if the CPU +topology is properly populated or not. + +NUMA-node socket cluster core thread +------------------------------------------ +0 1 0 0 0 +1 0 0 0 0 + +Suggested-by: Igor Mammedov +Signed-off-by: Gavin Shan +Acked-by: Igor Mammedov +Message-id: 20220503140304.855514-5-gshan@redhat.com +Signed-off-by: Peter Maydell +(cherry picked from commit e280ecb39bc1629f74ea5479d464fd1608dc8f76) +Signed-off-by: Gavin Shan +--- + tests/qtest/numa-test.c | 18 ++++++++++++------ + 1 file changed, 12 insertions(+), 6 deletions(-) + +diff --git a/tests/qtest/numa-test.c b/tests/qtest/numa-test.c +index aeda8c774c..32e35daaae 100644 +--- a/tests/qtest/numa-test.c ++++ b/tests/qtest/numa-test.c +@@ -224,17 +224,17 @@ static void aarch64_numa_cpu(const void *data) + g_autofree char *cli = NULL; + + cli = make_cli(data, "-machine " +- "smp.cpus=2,smp.sockets=1,smp.clusters=1,smp.cores=1,smp.threads=2 " ++ "smp.cpus=2,smp.sockets=2,smp.clusters=1,smp.cores=1,smp.threads=1 " + "-numa node,nodeid=0,memdev=ram -numa node,nodeid=1 " +- "-numa cpu,node-id=1,thread-id=0 " +- "-numa cpu,node-id=0,thread-id=1"); ++ "-numa cpu,node-id=0,socket-id=1,cluster-id=0,core-id=0,thread-id=0 " ++ "-numa cpu,node-id=1,socket-id=0,cluster-id=0,core-id=0,thread-id=0"); + qts = qtest_init(cli); + cpus = get_cpus(qts, &resp); + g_assert(cpus); + + while ((e = qlist_pop(cpus))) { + QDict *cpu, *props; +- int64_t thread, node; ++ int64_t socket, cluster, core, thread, node; + + cpu = qobject_to(QDict, e); + g_assert(qdict_haskey(cpu, "props")); +@@ -242,12 +242,18 @@ static void aarch64_numa_cpu(const void *data) + + g_assert(qdict_haskey(props, "node-id")); + node = qdict_get_int(props, "node-id"); ++ g_assert(qdict_haskey(props, "socket-id")); ++ socket = qdict_get_int(props, "socket-id"); ++ g_assert(qdict_haskey(props, "cluster-id")); ++ cluster = qdict_get_int(props, "cluster-id"); ++ g_assert(qdict_haskey(props, "core-id")); ++ core = qdict_get_int(props, "core-id"); + g_assert(qdict_haskey(props, "thread-id")); + thread = qdict_get_int(props, "thread-id"); + +- if (thread == 0) { ++ if (socket == 0 && cluster == 0 && core == 0 && thread == 0) { + g_assert_cmpint(node, ==, 1); +- } else if (thread == 1) { ++ } else if (socket == 1 && cluster == 0 && core == 0 && thread == 0) { + g_assert_cmpint(node, ==, 0); + } else { + g_assert(false); +-- +2.31.1 + diff --git a/SOURCES/kvm-qtest-numa-test-Specify-CPU-topology-in-aarch64_numa.patch b/SOURCES/kvm-qtest-numa-test-Specify-CPU-topology-in-aarch64_numa.patch new file mode 100644 index 0000000..a87abc0 --- /dev/null +++ b/SOURCES/kvm-qtest-numa-test-Specify-CPU-topology-in-aarch64_numa.patch @@ -0,0 +1,68 @@ +From 66f3928b40991d8467a3da086688f73d061886c8 Mon Sep 17 00:00:00 2001 +From: Gavin Shan +Date: Wed, 11 May 2022 18:01:35 +0800 +Subject: [PATCH 02/16] qtest/numa-test: Specify CPU topology in + aarch64_numa_cpu() +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Gavin Shan +RH-MergeRequest: 86: hw/arm/virt: Fix the default CPU topology +RH-Commit: [2/6] b851e7ad59e057825392ddf75e9040cc102a0385 (gwshan/qemu-rhel-9) +RH-Bugzilla: 2041823 +RH-Acked-by: Eric Auger +RH-Acked-by: Cornelia Huck +RH-Acked-by: Andrew Jones + +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2041823 + +The CPU topology isn't enabled on arm/virt machine yet, but we're +going to do it in next patch. After the CPU topology is enabled by +next patch, "thread-id=1" becomes invalid because the CPU core is +preferred on arm/virt machine. It means these two CPUs have 0/1 +as their core IDs, but their thread IDs are all 0. It will trigger +test failure as the following message indicates: + +[14/21 qemu:qtest+qtest-aarch64 / qtest-aarch64/numa-test ERROR +1.48s killed by signal 6 SIGABRT +>>> G_TEST_DBUS_DAEMON=/home/gavin/sandbox/qemu.main/tests/dbus-vmstate-daemon.sh \ +QTEST_QEMU_STORAGE_DAEMON_BINARY=./storage-daemon/qemu-storage-daemon \ +QTEST_QEMU_BINARY=./qemu-system-aarch64 \ +QTEST_QEMU_IMG=./qemu-img MALLOC_PERTURB_=83 \ +/home/gavin/sandbox/qemu.main/build/tests/qtest/numa-test --tap -k +―――――――――――――――――――――――――――――――――――――――――――――― +stderr: +qemu-system-aarch64: -numa cpu,node-id=0,thread-id=1: no match found + +This fixes the issue by providing comprehensive SMP configurations +in aarch64_numa_cpu(). The SMP configurations aren't used before +the CPU topology is enabled in next patch. + +Signed-off-by: Gavin Shan +Reviewed-by: Yanan Wang +Message-id: 20220503140304.855514-3-gshan@redhat.com +Signed-off-by: Peter Maydell +(cherry picked from commit ac7199a2523ce2ccf8e685087a5d177eeca89b09) +Signed-off-by: Gavin Shan +--- + tests/qtest/numa-test.c | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +diff --git a/tests/qtest/numa-test.c b/tests/qtest/numa-test.c +index 90bf68a5b3..aeda8c774c 100644 +--- a/tests/qtest/numa-test.c ++++ b/tests/qtest/numa-test.c +@@ -223,7 +223,8 @@ static void aarch64_numa_cpu(const void *data) + QTestState *qts; + g_autofree char *cli = NULL; + +- cli = make_cli(data, "-machine smp.cpus=2 " ++ cli = make_cli(data, "-machine " ++ "smp.cpus=2,smp.sockets=1,smp.clusters=1,smp.cores=1,smp.threads=2 " + "-numa node,nodeid=0,memdev=ram -numa node,nodeid=1 " + "-numa cpu,node-id=1,thread-id=0 " + "-numa cpu,node-id=0,thread-id=1"); +-- +2.31.1 + diff --git a/SOURCES/kvm-redhat-Add-rhel8.6.0-and-rhel9.0.0-machine-types-for.patch b/SOURCES/kvm-redhat-Add-rhel8.6.0-and-rhel9.0.0-machine-types-for.patch deleted file mode 100644 index 407aa1e..0000000 --- a/SOURCES/kvm-redhat-Add-rhel8.6.0-and-rhel9.0.0-machine-types-for.patch +++ /dev/null @@ -1,82 +0,0 @@ -From 0e85c10b73c36f386723c842a797d5e2155e758f Mon Sep 17 00:00:00 2001 -From: Thomas Huth -Date: Fri, 10 Dec 2021 10:07:40 +0100 -Subject: [PATCH 1/2] redhat: Add rhel8.6.0 and rhel9.0.0 machine types for - s390x -MIME-Version: 1.0 -Content-Type: text/plain; charset=UTF-8 -Content-Transfer-Encoding: 8bit - -RH-Author: Thomas Huth -RH-MergeRequest: 55: redhat: Add rhel8.6.0 and rhel9.0.0 machine types for s390x -RH-Commit: [1/1] ad8fd5c825ae52a8fbb3a28f700a514509c59978 (thuth/qemu-kvm-cs9) -RH-Bugzilla: 2008060 -RH-Acked-by: Philippe Mathieu-Daudé -RH-Acked-by: Laurent Vivier -RH-Acked-by: David Hildenbrand -RH-Acked-by: Cornelia Huck - -Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2008060 - -The new machine types have better default values for the upcoming -"generation 16" mainframe. - -Signed-off-by: Thomas Huth ---- - hw/s390x/s390-virtio-ccw.c | 26 +++++++++++++++++++++++++- - 1 file changed, 25 insertions(+), 1 deletion(-) - -diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c -index c654045964..9da6e9b1d4 100644 ---- a/hw/s390x/s390-virtio-ccw.c -+++ b/hw/s390x/s390-virtio-ccw.c -@@ -1103,10 +1103,33 @@ 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) -+{ -+} -+DEFINE_CCW_MACHINE(rhel900, "rhel9.0.0", true); -+ -+static void ccw_machine_rhel860_instance_options(MachineState *machine) -+{ -+ /* Note: The -rhel8.6.0 and -rhel9.0.0 machines are technically identical */ -+ ccw_machine_rhel900_instance_options(machine); -+} -+ -+static void ccw_machine_rhel860_class_options(MachineClass *mc) -+{ -+ ccw_machine_rhel900_class_options(mc); -+} -+DEFINE_CCW_MACHINE(rhel860, "rhel8.6.0", false); -+ - static void ccw_machine_rhel850_instance_options(MachineState *machine) - { - static const S390FeatInit qemu_cpu_feat = { S390_FEAT_LIST_QEMU_V6_0 }; - -+ ccw_machine_rhel860_instance_options(machine); -+ - s390_set_qemu_cpu_model(0x2964, 13, 2, qemu_cpu_feat); - - s390_cpudef_featoff_greater(16, 1, S390_FEAT_NNPA); -@@ -1118,10 +1141,11 @@ static void ccw_machine_rhel850_instance_options(MachineState *machine) - - static void ccw_machine_rhel850_class_options(MachineClass *mc) - { -+ ccw_machine_rhel860_class_options(mc); - compat_props_add(mc->compat_props, hw_compat_rhel_8_5, hw_compat_rhel_8_5_len); - mc->smp_props.prefer_sockets = true; - } --DEFINE_CCW_MACHINE(rhel850, "rhel8.5.0", true); -+DEFINE_CCW_MACHINE(rhel850, "rhel8.5.0", false); - - static void ccw_machine_rhel840_instance_options(MachineState *machine) - { --- -2.27.0 - diff --git a/SOURCES/kvm-redhat-Enable-virtio-mem-as-tech-preview-on-x86-64.patch b/SOURCES/kvm-redhat-Enable-virtio-mem-as-tech-preview-on-x86-64.patch deleted file mode 100644 index d3b2ba0..0000000 --- a/SOURCES/kvm-redhat-Enable-virtio-mem-as-tech-preview-on-x86-64.patch +++ /dev/null @@ -1,43 +0,0 @@ -From 24b44713de4b2a47c42dfeea813c8911694367a0 Mon Sep 17 00:00:00 2001 -From: David Hildenbrand -Date: Fri, 17 Dec 2021 10:00:53 +0100 -Subject: [PATCH 2/2] redhat: Enable virtio-mem as tech-preview on x86-64 -MIME-Version: 1.0 -Content-Type: text/plain; charset=UTF-8 -Content-Transfer-Encoding: 8bit - -RH-Author: David Hildenbrand -RH-MergeRequest: 56: redhat: Enable virtio-mem as tech-preview on x86-64 -RH-Commit: [1/1] 255749cd877b91ce1978b67a088f7c0e181fd85e -RH-Bugzilla: 2014484 -RH-Acked-by: Philippe Mathieu-Daudé -RH-Acked-by: Thomas Huth -RH-Acked-by: Gavin Shan - -Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2014484 -Upstream-status: RHEL-only - -Everything necesssary for tech-preview of virtio-mem in RHEL9 is -included in QEMU v6.2. Let's enable it via the config option -CONFIG_VIRTIO_MEM on x86-64. - -Signed-off-by: David Hildenbrand ---- - 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 1f7a9ab024..dc03fbb671 100644 ---- a/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak -+++ b/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak -@@ -88,6 +88,7 @@ CONFIG_VGA_CIRRUS=y - CONFIG_VGA_PCI=y - CONFIG_VHOST_USER=y - CONFIG_VHOST_USER_BLK=y -+CONFIG_VIRTIO_MEM=y - CONFIG_VIRTIO_PCI=y - CONFIG_VIRTIO_VGA=y - CONFIG_VMMOUSE=y --- -2.27.0 - diff --git a/SOURCES/kvm-redhat-Update-linux-headers-linux-kvm.h-to-v5.18-rc6.patch b/SOURCES/kvm-redhat-Update-linux-headers-linux-kvm.h-to-v5.18-rc6.patch new file mode 100644 index 0000000..f027c45 --- /dev/null +++ b/SOURCES/kvm-redhat-Update-linux-headers-linux-kvm.h-to-v5.18-rc6.patch @@ -0,0 +1,106 @@ +From 236f216309261bc924e49014267998fdc2ef7f46 Mon Sep 17 00:00:00 2001 +From: Thomas Huth +Date: Fri, 29 Jul 2022 16:55:34 +0200 +Subject: [PATCH 28/32] redhat: Update linux-headers/linux/kvm.h to v5.18-rc6 + +RH-Author: Thomas Huth +RH-MergeRequest: 109: Honor storage keys during emulation of I/O instructions +RH-Commit: [1/2] f306d7ff8efa64b14158388b95815ac556a25d8a (thuth/qemu-kvm-cs9) +RH-Bugzilla: 2111994 +RH-Acked-by: Cornelia Huck +RH-Acked-by: David Hildenbrand +RH-Acked-by: Claudio Imbrenda + +Upstream Status: RHEL-only +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2111994 + +Based on upstream commit e4082063e47e9731dbeb1c26174c17f6038f577f +("linux-headers: Update to v5.18-rc6"), but this is focusing on +the file linux-headers/linux/kvm.h only (since the other changes +related to the VFIO renaming might break some stuff). + +Signed-off-by: Thomas Huth +--- + linux-headers/linux/kvm.h | 27 +++++++++++++++++++++------ + 1 file changed, 21 insertions(+), 6 deletions(-) + +diff --git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h +index d232feaae9..0d05d02ee4 100644 +--- a/linux-headers/linux/kvm.h ++++ b/linux-headers/linux/kvm.h +@@ -445,7 +445,11 @@ struct kvm_run { + #define KVM_SYSTEM_EVENT_RESET 2 + #define KVM_SYSTEM_EVENT_CRASH 3 + __u32 type; +- __u64 flags; ++ __u32 ndata; ++ union { ++ __u64 flags; ++ __u64 data[16]; ++ }; + } system_event; + /* KVM_EXIT_S390_STSI */ + struct { +@@ -562,9 +566,12 @@ struct kvm_s390_mem_op { + __u32 op; /* type of operation */ + __u64 buf; /* buffer in userspace */ + union { +- __u8 ar; /* the access register number */ ++ struct { ++ __u8 ar; /* the access register number */ ++ __u8 key; /* access key, ignored if flag unset */ ++ }; + __u32 sida_offset; /* offset into the sida */ +- __u8 reserved[32]; /* should be set to 0 */ ++ __u8 reserved[32]; /* ignored */ + }; + }; + /* types for kvm_s390_mem_op->op */ +@@ -572,9 +579,12 @@ struct kvm_s390_mem_op { + #define KVM_S390_MEMOP_LOGICAL_WRITE 1 + #define KVM_S390_MEMOP_SIDA_READ 2 + #define KVM_S390_MEMOP_SIDA_WRITE 3 ++#define KVM_S390_MEMOP_ABSOLUTE_READ 4 ++#define KVM_S390_MEMOP_ABSOLUTE_WRITE 5 + /* flags for kvm_s390_mem_op->flags */ + #define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0) + #define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1) ++#define KVM_S390_MEMOP_F_SKEY_PROTECTION (1ULL << 2) + + /* for KVM_INTERRUPT */ + struct kvm_interrupt { +@@ -1134,6 +1144,12 @@ struct kvm_ppc_resize_hpt { + #define KVM_CAP_VM_GPA_BITS 207 + #define KVM_CAP_XSAVE2 208 + #define KVM_CAP_SYS_ATTRIBUTES 209 ++#define KVM_CAP_PPC_AIL_MODE_3 210 ++#define KVM_CAP_S390_MEM_OP_EXTENSION 211 ++#define KVM_CAP_PMU_CAPABILITY 212 ++#define KVM_CAP_DISABLE_QUIRKS2 213 ++/* #define KVM_CAP_VM_TSC_CONTROL 214 */ ++#define KVM_CAP_SYSTEM_EVENT_DATA 215 + + #ifdef KVM_CAP_IRQ_ROUTING + +@@ -1624,9 +1640,6 @@ struct kvm_enc_region { + #define KVM_S390_NORMAL_RESET _IO(KVMIO, 0xc3) + #define KVM_S390_CLEAR_RESET _IO(KVMIO, 0xc4) + +-/* Available with KVM_CAP_XSAVE2 */ +-#define KVM_GET_XSAVE2 _IOR(KVMIO, 0xcf, struct kvm_xsave) +- + struct kvm_s390_pv_sec_parm { + __u64 origin; + __u64 length; +@@ -1973,6 +1986,8 @@ struct kvm_dirty_gfn { + #define KVM_BUS_LOCK_DETECTION_OFF (1 << 0) + #define KVM_BUS_LOCK_DETECTION_EXIT (1 << 1) + ++#define KVM_PMU_CAP_DISABLE (1 << 0) ++ + /** + * struct kvm_stats_header - Header of per vm/vcpu binary statistics data. + * @flags: Some extra information for header, always 0 for now. +-- +2.31.1 + diff --git a/SOURCES/kvm-rhel-machine-types-x86-set-prefer_sockets.patch b/SOURCES/kvm-rhel-machine-types-x86-set-prefer_sockets.patch deleted file mode 100644 index 83c912d..0000000 --- a/SOURCES/kvm-rhel-machine-types-x86-set-prefer_sockets.patch +++ /dev/null @@ -1,52 +0,0 @@ -From ecadfaec992fda7f485522c9ee6e7c9b05614a22 Mon Sep 17 00:00:00 2001 -From: "Dr. David Alan Gilbert" -Date: Tue, 7 Dec 2021 18:39:47 +0000 -Subject: [PATCH 2/2] rhel machine types/x86: set prefer_sockets - -RH-Author: Dr. David Alan Gilbert -RH-MergeRequest: 59: rhel machine types/x86: set prefer_sockets -RH-Commit: [1/1] 9bcd9e2c95154e39ef30a8a342ad6c713fa4f1fb (dagrh/c-9-s-qemu-kvm) -RH-Bugzilla: 2028623 -RH-Acked-by: Miroslav Rezanina -RH-Acked-by: quintela1 -RH-Acked-by: Cornelia Huck - -When I fixed up the machine types for 8.5 I missed the - prefer_sockets = true - -add them in; it looks like Power, ARM already have them, and I see them -in thuth's s390 patch. - -Signed-off-by: Dr. David Alan Gilbert ---- - hw/i386/pc_piix.c | 1 + - hw/i386/pc_q35.c | 1 + - 2 files changed, 2 insertions(+) - -diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c -index 183b5d5464..fccb7f5fc9 100644 ---- a/hw/i386/pc_piix.c -+++ b/hw/i386/pc_piix.c -@@ -973,6 +973,7 @@ static void pc_machine_rhel7_options(MachineClass *m) - compat_props_add(m->compat_props, pc_rhel_compat, pc_rhel_compat_len); - m->alias = "pc"; - m->is_default = 1; -+ m->smp_props.prefer_sockets = true; - } - - static void pc_init_rhel760(MachineState *machine) -diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c -index 0e7e885e78..3b748ddd7b 100644 ---- a/hw/i386/pc_q35.c -+++ b/hw/i386/pc_q35.c -@@ -662,6 +662,7 @@ static void pc_q35_machine_rhel850_options(MachineClass *m) - hw_compat_rhel_8_5_len); - compat_props_add(m->compat_props, pc_rhel_8_5_compat, - pc_rhel_8_5_compat_len); -+ m->smp_props.prefer_sockets = true; - } - - DEFINE_PC_MACHINE(q35_rhel850, "pc-q35-rhel8.5.0", pc_q35_init_rhel850, --- -2.27.0 - diff --git a/SOURCES/kvm-scsi-generic-Fix-emulated-block-limits-VPD-page.patch b/SOURCES/kvm-scsi-generic-Fix-emulated-block-limits-VPD-page.patch new file mode 100644 index 0000000..cee10e7 --- /dev/null +++ b/SOURCES/kvm-scsi-generic-Fix-emulated-block-limits-VPD-page.patch @@ -0,0 +1,96 @@ +From e5360c1e76fee8b8dcbcba7efbb1e36f0b48ac40 Mon Sep 17 00:00:00 2001 +From: Kevin Wolf +Date: Mon, 22 Aug 2022 14:53:20 +0200 +Subject: [PATCH 01/23] scsi-generic: Fix emulated block limits VPD page + +RH-Author: Kevin Wolf +RH-MergeRequest: 115: scsi-generic: Fix emulated block limits VPD page +RH-Bugzilla: 2120275 +RH-Acked-by: Emanuele Giuseppe Esposito +RH-Acked-by: Hanna Reitz +RH-Acked-by: Paolo Bonzini +RH-Acked-by: Stefan Hajnoczi +RH-Commit: [1/1] 336ba583311a80beeadd1900336056404f63211a (kmwolf/centos-qemu-kvm) +Commits 01ef8185b80 amd 24b36e9813e updated the way that the maximum +transfer length is calculated for patching block limits VPD page in an +INQUIRY response. + +The same updates also need to be made for the case where the host device +does not support the block limits VPD page at all and we emulate the +whole page. + +Without this fix, on host block devices a maximum transfer length of +(INT_MAX - sector_size) bytes is advertised to the guest, resulting in +I/O errors when a request that exceeds the host limits is made by the +guest. (Prior to commit 24b36e9813e, this code path would use the +max_transfer value from the host instead of INT_MAX, but still miss the +fix from 01ef8185b80 where max_transfer is also capped to max_iov +host pages, so it would be less wrong, but still wrong.) + +Cc: qemu-stable@nongnu.org +Buglink: https://bugzilla.redhat.com/show_bug.cgi?id=2096251 +Fixes: 01ef8185b809af9d287e1a03a3f9d8ea8231118a +Fixes: 24b36e9813ec15da7db62e3b3621730710c5f020 +Signed-off-by: Kevin Wolf +Message-Id: <20220822125320.48257-1-kwolf@redhat.com> +Reviewed-by: Stefan Hajnoczi +Signed-off-by: Kevin Wolf +(cherry picked from commit 51e15194b0a091e5c40aab2eb234a1d36c5c58ee) + +Resolved conflict: qemu_real_host_page_size() is a getter function in +current upstream, but still just a public global variable downstream. + +Signed-off-by: Kevin Wolf +--- + hw/scsi/scsi-generic.c | 21 ++++++++++++++------- + 1 file changed, 14 insertions(+), 7 deletions(-) + +diff --git a/hw/scsi/scsi-generic.c b/hw/scsi/scsi-generic.c +index 0306ccc7b1..3742899839 100644 +--- a/hw/scsi/scsi-generic.c ++++ b/hw/scsi/scsi-generic.c +@@ -147,6 +147,18 @@ static int execute_command(BlockBackend *blk, + return 0; + } + ++static uint64_t calculate_max_transfer(SCSIDevice *s) ++{ ++ uint64_t max_transfer = blk_get_max_hw_transfer(s->conf.blk); ++ uint32_t max_iov = blk_get_max_hw_iov(s->conf.blk); ++ ++ assert(max_transfer); ++ max_transfer = MIN_NON_ZERO(max_transfer, ++ max_iov * qemu_real_host_page_size); ++ ++ return max_transfer / s->blocksize; ++} ++ + static int scsi_handle_inquiry_reply(SCSIGenericReq *r, SCSIDevice *s, int len) + { + uint8_t page, page_idx; +@@ -179,12 +191,7 @@ static int scsi_handle_inquiry_reply(SCSIGenericReq *r, SCSIDevice *s, int len) + (r->req.cmd.buf[1] & 0x01)) { + page = r->req.cmd.buf[2]; + if (page == 0xb0) { +- uint64_t max_transfer = blk_get_max_hw_transfer(s->conf.blk); +- uint32_t max_iov = blk_get_max_hw_iov(s->conf.blk); +- +- assert(max_transfer); +- max_transfer = MIN_NON_ZERO(max_transfer, max_iov * qemu_real_host_page_size) +- / s->blocksize; ++ uint64_t max_transfer = calculate_max_transfer(s); + stl_be_p(&r->buf[8], max_transfer); + /* Also take care of the opt xfer len. */ + stl_be_p(&r->buf[12], +@@ -230,7 +237,7 @@ static int scsi_generic_emulate_block_limits(SCSIGenericReq *r, SCSIDevice *s) + uint8_t buf[64]; + + SCSIBlockLimits bl = { +- .max_io_sectors = blk_get_max_transfer(s->conf.blk) / s->blocksize ++ .max_io_sectors = calculate_max_transfer(s), + }; + + memset(r->buf, 0, r->buflen); +-- +2.31.1 + diff --git a/SOURCES/kvm-softmmu-fix-device-deletion-events-with-device-JSON-.patch b/SOURCES/kvm-softmmu-fix-device-deletion-events-with-device-JSON-.patch deleted file mode 100644 index 4ddfbe9..0000000 --- a/SOURCES/kvm-softmmu-fix-device-deletion-events-with-device-JSON-.patch +++ /dev/null @@ -1,130 +0,0 @@ -From 005339f7deaee639c38d30e5bf2235c292ce3937 Mon Sep 17 00:00:00 2001 -From: =?UTF-8?q?Daniel=20P=2E=20Berrang=C3=A9?= -Date: Wed, 5 Jan 2022 12:38:47 +0000 -Subject: [PATCH 3/3] softmmu: fix device deletion events with -device JSON - syntax -MIME-Version: 1.0 -Content-Type: text/plain; charset=UTF-8 -Content-Transfer-Encoding: 8bit - -RH-Author: Kevin Wolf -RH-MergeRequest: 62: Fix hot unplug of devices created with -device JSON syntax -RH-Commit: [1/1] 980e505ba215b5f9324c107481c5bb257ae03f42 (kmwolf/centos-qemu-kvm) -RH-Bugzilla: 2036669 -RH-Acked-by: Daniel P. Berrangé -RH-Acked-by: Laurent Vivier -RH-Acked-by: Jano Tomko - -The -device JSON syntax impl leaks a reference on the created -DeviceState instance. As a result when you hot-unplug the -device, the device_finalize method won't be called and thus -it will fail to emit the required DEVICE_DELETED event. - -A 'json-cli' feature was previously added against the -'device_add' QMP command QAPI schema to indicated to mgmt -apps that -device supported JSON syntax. Given the hotplug -bug that feature flag is not usable for its purpose, so -we add a new 'json-cli-hotplug' feature to indicate the --device supports JSON without breaking hotplug. - -Fixes: 5dacda5167560b3af8eadbce5814f60ba44b467e -Resolves: https://gitlab.com/qemu-project/qemu/-/issues/802 -Signed-off-by: Daniel P. Berrangé -Message-Id: <20220105123847.4047954-2-berrange@redhat.com> -Reviewed-by: Laurent Vivier -Tested-by: Ján Tomko -Reviewed-by: Thomas Huth -Signed-off-by: Kevin Wolf -(cherry picked from commit 64b4529a432507ee84a924be69a03432639e87ba) -Signed-off-by: Kevin Wolf ---- - qapi/qdev.json | 5 ++++- - softmmu/vl.c | 4 +++- - tests/qtest/device-plug-test.c | 19 +++++++++++++++++++ - 3 files changed, 26 insertions(+), 2 deletions(-) - -diff --git a/qapi/qdev.json b/qapi/qdev.json -index 69656b14df..26cd10106b 100644 ---- a/qapi/qdev.json -+++ b/qapi/qdev.json -@@ -44,6 +44,9 @@ - # @json-cli: If present, the "-device" command line option supports JSON - # syntax with a structure identical to the arguments of this - # command. -+# @json-cli-hotplug: If present, the "-device" command line option supports JSON -+# syntax without the reference counting leak that broke -+# hot-unplug - # - # Notes: - # -@@ -74,7 +77,7 @@ - { 'command': 'device_add', - 'data': {'driver': 'str', '*bus': 'str', '*id': 'str'}, - 'gen': false, # so we can get the additional arguments -- 'features': ['json-cli'] } -+ 'features': ['json-cli', 'json-cli-hotplug'] } - - ## - # @device_del: -diff --git a/softmmu/vl.c b/softmmu/vl.c -index d46b8fb4ab..b3829e2edd 100644 ---- a/softmmu/vl.c -+++ b/softmmu/vl.c -@@ -2690,6 +2690,7 @@ static void qemu_create_cli_devices(void) - qemu_opts_foreach(qemu_find_opts("device"), - device_init_func, NULL, &error_fatal); - QTAILQ_FOREACH(opt, &device_opts, next) { -+ DeviceState *dev; - loc_push_restore(&opt->loc); - /* - * TODO Eventually we should call qmp_device_add() here to make sure it -@@ -2698,7 +2699,8 @@ static void qemu_create_cli_devices(void) - * from the start, so call qdev_device_add_from_qdict() directly for - * now. - */ -- qdev_device_add_from_qdict(opt->opts, true, &error_fatal); -+ dev = qdev_device_add_from_qdict(opt->opts, true, &error_fatal); -+ object_unref(OBJECT(dev)); - loc_pop(&opt->loc); - } - rom_reset_order_override(); -diff --git a/tests/qtest/device-plug-test.c b/tests/qtest/device-plug-test.c -index 559d47727a..ad79bd4c14 100644 ---- a/tests/qtest/device-plug-test.c -+++ b/tests/qtest/device-plug-test.c -@@ -77,6 +77,23 @@ static void test_pci_unplug_request(void) - qtest_quit(qtest); - } - -+static void test_pci_unplug_json_request(void) -+{ -+ QTestState *qtest = qtest_initf( -+ "-device '{\"driver\": \"virtio-mouse-pci\", \"id\": \"dev0\"}'"); -+ -+ /* -+ * Request device removal. As the guest is not running, the request won't -+ * be processed. However during system reset, the removal will be -+ * handled, removing the device. -+ */ -+ device_del(qtest, "dev0"); -+ system_reset(qtest); -+ wait_device_deleted_event(qtest, "dev0"); -+ -+ qtest_quit(qtest); -+} -+ - static void test_ccw_unplug(void) - { - QTestState *qtest = qtest_initf("-device virtio-balloon-ccw,id=dev0"); -@@ -145,6 +162,8 @@ int main(int argc, char **argv) - */ - qtest_add_func("/device-plug/pci-unplug-request", - test_pci_unplug_request); -+ qtest_add_func("/device-plug/pci-unplug-json-request", -+ test_pci_unplug_json_request); - - if (!strcmp(arch, "s390x")) { - qtest_add_func("/device-plug/ccw-unplug", --- -2.27.0 - diff --git a/SOURCES/kvm-sysemu-tpm-Add-a-stub-function-for-TPM_IS_CRB.patch b/SOURCES/kvm-sysemu-tpm-Add-a-stub-function-for-TPM_IS_CRB.patch new file mode 100644 index 0000000..8fd2e16 --- /dev/null +++ b/SOURCES/kvm-sysemu-tpm-Add-a-stub-function-for-TPM_IS_CRB.patch @@ -0,0 +1,54 @@ +From 74b3e92dcb9e343e135a681259514b4fd28086ea Mon Sep 17 00:00:00 2001 +From: Eric Auger +Date: Fri, 6 May 2022 15:25:09 +0200 +Subject: [PATCH 4/5] sysemu: tpm: Add a stub function for TPM_IS_CRB + +RH-Author: Eric Auger +RH-MergeRequest: 84: vfio/common: Remove spurious tpm-crb-cmd misalignment warning +RH-Commit: [1/2] 0ab55ca1aa12a3a7cbdef5a378928f75e030e536 (eauger1/centos-qemu-kvm) +RH-Bugzilla: 2037612 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Cornelia Huck +RH-Acked-by: Andrew Jones + +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2037612 +Brew: https://brewweb.engineering.redhat.com/brew/taskinfo?taskID=45166961 +Upstream Status: YES +Tested: With TPM-CRB and VFIO + +In a subsequent patch, VFIO will need to recognize if +a memory region owner is a TPM CRB device. Hence VFIO +needs to use TPM_IS_CRB() even if CONFIG_TPM is unset. So +let's add a stub function. + +Signed-off-by: Eric Auger +Suggested-by: Cornelia Huck +Reviewed-by: Stefan Berger +Link: https://lore.kernel.org/r/20220506132510.1847942-2-eric.auger@redhat.com +Signed-off-by: Alex Williamson +(cherry picked from commit 4168cdad398843ed53d650a27651868b4d3e21c9) +Signed-off-by: Eric Auger +--- + include/sysemu/tpm.h | 6 ++++++ + 1 file changed, 6 insertions(+) + +diff --git a/include/sysemu/tpm.h b/include/sysemu/tpm.h +index 68b2206463..fb40e30ff6 100644 +--- a/include/sysemu/tpm.h ++++ b/include/sysemu/tpm.h +@@ -80,6 +80,12 @@ static inline TPMVersion tpm_get_version(TPMIf *ti) + #define tpm_init() (0) + #define tpm_cleanup() + ++/* needed for an alignment check in non-tpm code */ ++static inline Object *TPM_IS_CRB(Object *obj) ++{ ++ return NULL; ++} ++ + #endif /* CONFIG_TPM */ + + #endif /* QEMU_TPM_H */ +-- +2.31.1 + diff --git a/SOURCES/kvm-target-arm-deprecate-named-CPU-models.patch b/SOURCES/kvm-target-arm-deprecate-named-CPU-models.patch new file mode 100644 index 0000000..dbe8d24 --- /dev/null +++ b/SOURCES/kvm-target-arm-deprecate-named-CPU-models.patch @@ -0,0 +1,129 @@ +From 1f8528b71d96c01dd6106f11681f4a4e2776ef5f Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Daniel=20P=2E=20Berrang=C3=A9?= +Date: Mon, 21 Mar 2022 12:05:42 +0000 +Subject: [PATCH 06/18] target/arm: deprecate named CPU models +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Daniel P. Berrangé +RH-MergeRequest: 94: i386, aarch64, s390x: deprecate many named CPU models +RH-Commit: [6/6] afddeb9e898206fd04499f01c48caf7dc1a8b8ef (berrange/centos-src-qemu) +RH-Bugzilla: 2060839 +RH-Acked-by: Thomas Huth +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Cornelia Huck + +KVM requires use of the 'host' CPU model, so named CPU models are only +needed for TCG. Since we don't consider TCG to be supported we can +deprecate all the named CPU models. TCG users can rely on 'max' model. + +Note: this has the effect of deprecating the default built-in CPU +model 'cortex-a57'. Applications using QEMU are expected to make an +explicit choice about which CPU model they want, since no builtin +default can suit all purposes. + +https://bugzilla.redhat.com/show_bug.cgi?id=2060839 +Signed-off-by: Daniel P. Berrangé +--- + target/arm/cpu-qom.h | 1 + + target/arm/cpu.c | 5 +++++ + target/arm/cpu.h | 2 ++ + target/arm/cpu64.c | 8 +++++++- + target/arm/helper.c | 2 ++ + 5 files changed, 17 insertions(+), 1 deletion(-) + +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 5d4ca7a227..c74b0fb462 100644 +--- a/target/arm/cpu.c ++++ b/target/arm/cpu.c +@@ -2105,8 +2105,13 @@ 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 23879de5fa..c0c9f680e5 100644 +--- a/target/arm/cpu.h ++++ b/target/arm/cpu.h +@@ -33,6 +33,8 @@ + #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 e80b831073..c8f152891c 100644 +--- a/target/arm/cpu64.c ++++ b/target/arm/cpu64.c +@@ -975,7 +975,8 @@ static void aarch64_a64fx_initfn(Object *obj) + #endif /* disabled for RHEL */ + + static const ARMCPUInfo aarch64_cpus[] = { +- { .name = "cortex-a57", .initfn = aarch64_a57_initfn }, ++ { .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 }, +@@ -1052,8 +1053,13 @@ 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/helper.c b/target/arm/helper.c +index 7d14650615..3d34f63e49 100644 +--- a/target/arm/helper.c ++++ b/target/arm/helper.c +@@ -8560,6 +8560,7 @@ 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; +@@ -8569,6 +8570,7 @@ 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); + } +-- +2.35.3 + diff --git a/SOURCES/kvm-target-i386-deprecate-CPUs-older-than-x86_64-v2-ABI.patch b/SOURCES/kvm-target-i386-deprecate-CPUs-older-than-x86_64-v2-ABI.patch new file mode 100644 index 0000000..d63bfdb --- /dev/null +++ b/SOURCES/kvm-target-i386-deprecate-CPUs-older-than-x86_64-v2-ABI.patch @@ -0,0 +1,273 @@ +From 577b04770e47aed0f88acb4a415ed04ddbe087f1 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Daniel=20P=2E=20Berrang=C3=A9?= +Date: Thu, 17 Mar 2022 17:59:22 +0000 +Subject: [PATCH 04/18] target/i386: deprecate CPUs older than x86_64-v2 ABI +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Daniel P. Berrangé +RH-MergeRequest: 94: i386, aarch64, s390x: deprecate many named CPU models +RH-Commit: [4/6] 71f6043f11b31ffa841a2e14d24972e571c18a9e (berrange/centos-src-qemu) +RH-Bugzilla: 2060839 +RH-Acked-by: Thomas Huth +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Cornelia Huck + +RHEL-9 is compiled with the x86_64-v2 ABI. We use this as a baseline to +select which CPUs we want to support, such that there is at least one +supported guest CPU that can be launched for every physical machine +capable of running RHEL-9 KVM. + +Supported CPUs: + + * QEMU models + + base (QEMU internal) + host (host passthrough) + max (host passthrough for KVM, + all emulated features for TCG) + + * Intel models + + Icelake-Server + Icelake-Server-noTSX + Cascadelake-Server (2019) + Cascadelake-Server-noTSX (2019) + Skylake-Server (2016) + Skylake-Server-IBRS (2016) + Skylake-Server-noTSX-IBRS (2016) + Skylake-Client (2015) + Skylake-Client-IBRS (2015) + Skylake-Client-noTSX-IBRS (2015) + Broadwell (2014) + Broadwell-IBRS (2014) + Broadwell-noTSX (2014) + Broadwell-noTSX-IBRS (2014) + Haswell (2013) + Haswell-IBRS (2013) + Haswell-noTSX (2013) + Haswell-noTSX-IBRS (2013) + IvyBridge (2012) + IvyBridge-IBRS (2012) + SandyBridge (2011) + SandyBridge-IBRS (2011) + Westmere (2010) + Westmere-IBRS (2010) + Nehalem (2008) + Nehalem-IBRS (2008) + + Cooperlake (2020) + Snowridge (2019) + KnightsMill (2017) + Denverton (2016) + + * AMD models + + EPYC-Milan (2021) + EPYC-Rome (2019) + EPYC (2017) + EPYC-IBPB (2017) + Opteron_G5 (2012) + Opteron_G4 (2011) + + * Other + + Dhyana (2018) + +(I've omitted the many -vNNN versions for brevity) + +Deprecated CPUs: + + 486 + athlon + Conroe + core2duo + coreduo + Icelake-Client (already deprecated upstream) + Icelake-Client-noTSX (already deprecated upstream) + kvm32 + kvm64 + n270 + Opteron_G1 + Opteron_G2 + Opteron_G3 + Penryn + pentium2 + pentium3 + pentium + phenom + qemu32 + qemu64 + +The deprecated CPU models are subject to removal in a future +major version of RHEL. + +Note: this has the effect of deprecating the default built-in CPU +model 'qemu64'. Applications using QEMU are expected to make an +explicit choice about which CPU model they want, since no builtin +default can suit all purposes. + +https://bugzilla.redhat.com/show_bug.cgi?id=2060839 +Signed-off-by: Daniel P. Berrangé +--- + target/i386/cpu.c | 21 +++++++++++++++++++++ + 1 file changed, 21 insertions(+) + +diff --git a/target/i386/cpu.c b/target/i386/cpu.c +index cb6b5467d0..87cb641b5f 100644 +--- a/target/i386/cpu.c ++++ b/target/i386/cpu.c +@@ -1780,9 +1780,13 @@ 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, +@@ -1803,6 +1807,7 @@ static const X86CPUDefinition builtin_x86_defs[] = { + }, + { + .name = "phenom", ++ .deprecation_note = RHEL_CPU_DEPRECATION, + .level = 5, + .vendor = CPUID_VENDOR_AMD, + .family = 16, +@@ -1835,6 +1840,7 @@ static const X86CPUDefinition builtin_x86_defs[] = { + }, + { + .name = "core2duo", ++ .deprecation_note = RHEL_CPU_DEPRECATION, + .level = 10, + .vendor = CPUID_VENDOR_INTEL, + .family = 6, +@@ -1877,6 +1883,7 @@ static const X86CPUDefinition builtin_x86_defs[] = { + }, + { + .name = "kvm64", ++ .deprecation_note = RHEL_CPU_DEPRECATION, + .level = 0xd, + .vendor = CPUID_VENDOR_INTEL, + .family = 15, +@@ -1918,6 +1925,7 @@ static const X86CPUDefinition builtin_x86_defs[] = { + }, + { + .name = "qemu32", ++ .deprecation_note = RHEL_CPU_DEPRECATION, + .level = 4, + .vendor = CPUID_VENDOR_INTEL, + .family = 6, +@@ -1932,6 +1940,7 @@ static const X86CPUDefinition builtin_x86_defs[] = { + }, + { + .name = "kvm32", ++ .deprecation_note = RHEL_CPU_DEPRECATION, + .level = 5, + .vendor = CPUID_VENDOR_INTEL, + .family = 15, +@@ -1962,6 +1971,7 @@ static const X86CPUDefinition builtin_x86_defs[] = { + }, + { + .name = "coreduo", ++ .deprecation_note = RHEL_CPU_DEPRECATION, + .level = 10, + .vendor = CPUID_VENDOR_INTEL, + .family = 6, +@@ -1995,6 +2005,7 @@ static const X86CPUDefinition builtin_x86_defs[] = { + }, + { + .name = "486", ++ .deprecation_note = RHEL_CPU_DEPRECATION, + .level = 1, + .vendor = CPUID_VENDOR_INTEL, + .family = 4, +@@ -2007,6 +2018,7 @@ static const X86CPUDefinition builtin_x86_defs[] = { + }, + { + .name = "pentium", ++ .deprecation_note = RHEL_CPU_DEPRECATION, + .level = 1, + .vendor = CPUID_VENDOR_INTEL, + .family = 5, +@@ -2019,6 +2031,7 @@ static const X86CPUDefinition builtin_x86_defs[] = { + }, + { + .name = "pentium2", ++ .deprecation_note = RHEL_CPU_DEPRECATION, + .level = 2, + .vendor = CPUID_VENDOR_INTEL, + .family = 6, +@@ -2031,6 +2044,7 @@ static const X86CPUDefinition builtin_x86_defs[] = { + }, + { + .name = "pentium3", ++ .deprecation_note = RHEL_CPU_DEPRECATION, + .level = 3, + .vendor = CPUID_VENDOR_INTEL, + .family = 6, +@@ -2043,6 +2057,7 @@ static const X86CPUDefinition builtin_x86_defs[] = { + }, + { + .name = "athlon", ++ .deprecation_note = RHEL_CPU_DEPRECATION, + .level = 2, + .vendor = CPUID_VENDOR_AMD, + .family = 6, +@@ -2058,6 +2073,7 @@ static const X86CPUDefinition builtin_x86_defs[] = { + }, + { + .name = "n270", ++ .deprecation_note = RHEL_CPU_DEPRECATION, + .level = 10, + .vendor = CPUID_VENDOR_INTEL, + .family = 6, +@@ -2083,6 +2099,7 @@ static const X86CPUDefinition builtin_x86_defs[] = { + }, + { + .name = "Conroe", ++ .deprecation_note = RHEL_CPU_DEPRECATION, + .level = 10, + .vendor = CPUID_VENDOR_INTEL, + .family = 6, +@@ -2123,6 +2140,7 @@ static const X86CPUDefinition builtin_x86_defs[] = { + }, + { + .name = "Penryn", ++ .deprecation_note = RHEL_CPU_DEPRECATION, + .level = 10, + .vendor = CPUID_VENDOR_INTEL, + .family = 6, +@@ -3832,6 +3850,7 @@ static const X86CPUDefinition builtin_x86_defs[] = { + }, + { + .name = "Opteron_G1", ++ .deprecation_note = RHEL_CPU_DEPRECATION, + .level = 5, + .vendor = CPUID_VENDOR_AMD, + .family = 15, +@@ -3852,6 +3871,7 @@ static const X86CPUDefinition builtin_x86_defs[] = { + }, + { + .name = "Opteron_G2", ++ .deprecation_note = RHEL_CPU_DEPRECATION, + .level = 5, + .vendor = CPUID_VENDOR_AMD, + .family = 15, +@@ -3874,6 +3894,7 @@ static const X86CPUDefinition builtin_x86_defs[] = { + }, + { + .name = "Opteron_G3", ++ .deprecation_note = RHEL_CPU_DEPRECATION, + .level = 5, + .vendor = CPUID_VENDOR_AMD, + .family = 16, +-- +2.35.3 + diff --git a/SOURCES/kvm-target-ppc-cpu-models-Fix-ppc_cpu_aliases-list-for-R.patch b/SOURCES/kvm-target-ppc-cpu-models-Fix-ppc_cpu_aliases-list-for-R.patch new file mode 100644 index 0000000..c940cdb --- /dev/null +++ b/SOURCES/kvm-target-ppc-cpu-models-Fix-ppc_cpu_aliases-list-for-R.patch @@ -0,0 +1,48 @@ +From 39642d0d37e2ef61ce7fde0bc284d37a365e4482 Mon Sep 17 00:00:00 2001 +From: Murilo Opsfelder Araujo +Date: Mon, 2 May 2022 17:59:11 -0300 +Subject: [PATCH 2/2] target/ppc/cpu-models: Fix ppc_cpu_aliases list for RHEL +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Murilo Opsfelder Araújo +RH-MergeRequest: 81: target/ppc/cpu-models: remove extraneous "#endif" +RH-Commit: [1/1] 5fff003ad3deb84c6a8e69ab90552a31edb3b058 (mopsfelder/centos-stream-src-qemu-kvm) +RH-Bugzilla: 2081022 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Thomas Huth +RH-Acked-by: Laurent Vivier + +The commit b9d28ecdedaf ("Enable/disable devices for RHEL") removed the +"#if 0" from the beginning of the ppc_cpu_aliases list, which broke the +build on ppc64le: + + ../target/ppc/cpu-models.c:904:2: error: #endif without #if + #endif + ^ + 1 error generated. + +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2081022 + +Fixes: b9d28ecdedaf (Enable/disable devices for RHEL) +Signed-off-by: Murilo Opsfelder Araujo +--- + target/ppc/cpu-models.c | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/target/ppc/cpu-models.c b/target/ppc/cpu-models.c +index dd78883410..528467eac1 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" }, +-- +2.35.1 + diff --git a/SOURCES/kvm-target-s390x-deprecate-CPUs-older-than-z14.patch b/SOURCES/kvm-target-s390x-deprecate-CPUs-older-than-z14.patch new file mode 100644 index 0000000..212900d --- /dev/null +++ b/SOURCES/kvm-target-s390x-deprecate-CPUs-older-than-z14.patch @@ -0,0 +1,194 @@ +From 8459c305914e2a7a19dcd1662d54a89def7acfa6 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Daniel=20P=2E=20Berrang=C3=A9?= +Date: Thu, 17 Mar 2022 17:59:22 +0000 +Subject: [PATCH 05/18] target/s390x: deprecate CPUs older than z14 +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Daniel P. Berrangé +RH-MergeRequest: 94: i386, aarch64, s390x: deprecate many named CPU models +RH-Commit: [5/6] 2da9e06cf452287673f94f880a7eb8b2b37b7278 (berrange/centos-src-qemu) +RH-Bugzilla: 2060839 +RH-Acked-by: Thomas Huth +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Cornelia Huck + +RHEL-9 is compiled with the z14 ABI. We use this as a baseline to +select which CPUs we want to support, such that there is at least one +supported guest CPU that can be launched for every physical +machine capable of running RHEL-9 KVM. + +Supported CPUs: + + gen15a-base + gen15a + gen15b-base + gen15b + gen16a-base + gen16a + gen16b-base + gen16b + max + qemu + z14.2-base + z14.2 + z14-base + z14 + z14ZR1-base + z14ZR1 + +Deprecated CPUs: + + z10BC.2-base + z10BC.2 + z10BC-base + z10BC + z10EC.2-base + z10EC.2 + z10EC.3-base + z10EC.3 + z10EC-base + z10EC + z114-base + z114 + z13.2-base + z13.2 + z13-base + z13s-base + z13s + z13 + z196.2-base + z196.2 + z196-base + z196 + z800-base + z800 + z890.2-base + z890.2 + z890.3-base + z890.3 + z890-base + z890 + z900.2-base + z900.2 + z900.3-base + z900.3 + z900-base + z900 + z990.2-base + z990.2 + z990.3-base + z990.3 + z990.4-base + z990.4 + z990.5-base + z990.5 + z990-base + z990 + z9BC.2-base + z9BC.2 + z9BC-base + z9BC + z9EC.2-base + z9EC.2 + z9EC.3-base + z9EC.3 + z9EC-base + z9EC + zBC12-base + zBC12 + zEC12.2-base + zEC12.2 + zEC12-base + zEC12 + +https://bugzilla.redhat.com/show_bug.cgi?id=2060839 +Signed-off-by: Daniel P. Berrangé +--- + target/s390x/cpu_models.c | 11 +++++++++++ + target/s390x/cpu_models.h | 2 ++ + target/s390x/cpu_models_sysemu.c | 2 ++ + 3 files changed, 15 insertions(+) + +diff --git a/target/s390x/cpu_models.c b/target/s390x/cpu_models.c +index 6d71428056..9b9fc41676 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. + */ ++ ++#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"), +@@ -852,22 +855,30 @@ 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 74d1f87e4f..372160bcd7 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 6a04ccab1b..f3b7c304ec 100644 +--- a/target/s390x/cpu_models_sysemu.c ++++ b/target/s390x/cpu_models_sysemu.c +@@ -61,6 +61,7 @@ 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; +@@ -70,6 +71,7 @@ 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; +-- +2.35.3 + diff --git a/SOURCES/kvm-target-s390x-kvm-Honor-storage-keys-during-emulation.patch b/SOURCES/kvm-target-s390x-kvm-Honor-storage-keys-during-emulation.patch new file mode 100644 index 0000000..61752c7 --- /dev/null +++ b/SOURCES/kvm-target-s390x-kvm-Honor-storage-keys-during-emulation.patch @@ -0,0 +1,103 @@ +From 27c1d979a994f5afc59c3520af58d15aa5aae723 Mon Sep 17 00:00:00 2001 +From: Janis Schoetterl-Glausch +Date: Fri, 6 May 2022 17:39:56 +0200 +Subject: [PATCH 29/32] target/s390x: kvm: Honor storage keys during emulation + +RH-Author: Thomas Huth +RH-MergeRequest: 109: Honor storage keys during emulation of I/O instructions +RH-Commit: [2/2] 346dee1e13bfe1c074e4c6a4417091711d852f9c (thuth/qemu-kvm-cs9) +RH-Bugzilla: 2111994 +RH-Acked-by: Cornelia Huck +RH-Acked-by: David Hildenbrand +RH-Acked-by: Claudio Imbrenda + +Storage key controlled protection is currently not honored when +emulating instructions. +If available, enable key protection for the MEM_OP ioctl, thereby +enabling it for the s390_cpu_virt_mem_* functions, when using kvm. +As a result, the emulation of the following instructions honors storage +keys: + +* CLP + The Synch I/O CLP command would need special handling in order + to support storage keys, but is currently not supported. +* CHSC + Performing commands asynchronously would require special + handling, but commands are currently always synchronous. +* STSI +* TSCH + Must (and does) not change channel if terminated due to + protection. +* MSCH + Suppressed on protection, works because fetching instruction. +* SSCH + Suppressed on protection, works because fetching instruction. +* STSCH +* STCRW + Suppressed on protection, this works because no partial store is + possible, because the operand cannot span multiple pages. +* PCISTB +* MPCIFC +* STPCIFC + +Signed-off-by: Janis Schoetterl-Glausch +Message-Id: <20220506153956.2217601-3-scgl@linux.ibm.com> +Signed-off-by: Thomas Huth + +(cherry picked from commit 54354861d21b69ec0781f43e67b8d4f6edad7e3f) +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2111994 +Signed-off-by: Thomas Huth +--- + target/s390x/kvm/kvm.c | 9 +++++++++ + 1 file changed, 9 insertions(+) + +diff --git a/target/s390x/kvm/kvm.c b/target/s390x/kvm/kvm.c +index 74f089d87f..1f1d1a33b8 100644 +--- a/target/s390x/kvm/kvm.c ++++ b/target/s390x/kvm/kvm.c +@@ -152,12 +152,15 @@ const KVMCapabilityInfo kvm_arch_required_capabilities[] = { + static int cap_sync_regs; + static int cap_async_pf; + static int cap_mem_op; ++static int cap_mem_op_extension; + static int cap_s390_irq; + static int cap_ri; + static int cap_hpage_1m; + static int cap_vcpu_resets; + static int cap_protected; + ++static bool mem_op_storage_key_support; ++ + static int active_cmma; + + static int kvm_s390_query_mem_limit(uint64_t *memory_limit) +@@ -355,6 +358,8 @@ int kvm_arch_init(MachineState *ms, KVMState *s) + cap_sync_regs = kvm_check_extension(s, KVM_CAP_SYNC_REGS); + cap_async_pf = kvm_check_extension(s, KVM_CAP_ASYNC_PF); + cap_mem_op = kvm_check_extension(s, KVM_CAP_S390_MEM_OP); ++ cap_mem_op_extension = kvm_check_extension(s, KVM_CAP_S390_MEM_OP_EXTENSION); ++ mem_op_storage_key_support = cap_mem_op_extension > 0; + cap_s390_irq = kvm_check_extension(s, KVM_CAP_S390_INJECT_IRQ); + cap_vcpu_resets = kvm_check_extension(s, KVM_CAP_S390_VCPU_RESETS); + cap_protected = kvm_check_extension(s, KVM_CAP_S390_PROTECTED); +@@ -843,6 +848,7 @@ int kvm_s390_mem_op(S390CPU *cpu, vaddr addr, uint8_t ar, void *hostbuf, + : KVM_S390_MEMOP_LOGICAL_READ, + .buf = (uint64_t)hostbuf, + .ar = ar, ++ .key = (cpu->env.psw.mask & PSW_MASK_KEY) >> PSW_SHIFT_KEY, + }; + int ret; + +@@ -852,6 +858,9 @@ int kvm_s390_mem_op(S390CPU *cpu, vaddr addr, uint8_t ar, void *hostbuf, + if (!hostbuf) { + mem_op.flags |= KVM_S390_MEMOP_F_CHECK_ONLY; + } ++ if (mem_op_storage_key_support) { ++ mem_op.flags |= KVM_S390_MEMOP_F_SKEY_PROTECTION; ++ } + + ret = kvm_vcpu_ioctl(CPU(cpu), KVM_S390_MEM_OP, &mem_op); + if (ret < 0) { +-- +2.31.1 + diff --git a/SOURCES/kvm-tests-acpi-SLIC-update-expected-blobs.patch b/SOURCES/kvm-tests-acpi-SLIC-update-expected-blobs.patch deleted file mode 100644 index 91c5631..0000000 --- a/SOURCES/kvm-tests-acpi-SLIC-update-expected-blobs.patch +++ /dev/null @@ -1,36 +0,0 @@ -From 1dd4518bbf917158c9558dfb9e92be0a3f74b42b Mon Sep 17 00:00:00 2001 -From: Igor Mammedov -Date: Mon, 27 Dec 2021 14:31:20 -0500 -Subject: [PATCH 08/14] tests: acpi: SLIC: update expected blobs - -RH-Author: Igor Mammedov -RH-MergeRequest: 130: acpi: fix QEMU crash when started with SLIC table -RH-Commit: [4/10] 9023e98b18b9145ef889eec912b222e039fcc76f -RH-Bugzilla: 2043531 -RH-Acked-by: Gerd Hoffmann -RH-Acked-by: Miroslav Rezanina -RH-Acked-by: MST - -Signed-off-by: Igor Mammedov -Message-Id: <20211227193120.1084176-5-imammedo@redhat.com> -Reviewed-by: Michael S. Tsirkin -Signed-off-by: Michael S. Tsirkin -(cherry picked from commit c8adb4d222c42951a9d0367e5f5d4e1f5e2c9ad7) -Signed-off-by: Igor Mammedov ---- - tests/data/acpi/q35/FACP.slic | Bin 244 -> 244 bytes - tests/data/acpi/q35/SLIC.slic | Bin 0 -> 36 bytes - tests/qtest/bios-tables-test-allowed-diff.h | 2 -- - 3 files changed, 2 deletions(-) - -diff --git a/tests/qtest/bios-tables-test-allowed-diff.h b/tests/qtest/bios-tables-test-allowed-diff.h -index 49dbf8fa3e..dfb8523c8b 100644 ---- a/tests/qtest/bios-tables-test-allowed-diff.h -+++ b/tests/qtest/bios-tables-test-allowed-diff.h -@@ -1,3 +1 @@ - /* List of comma-separated changed AML files to ignore */ --"tests/data/acpi/q35/FACP.slic", --"tests/data/acpi/q35/SLIC.slic", --- -2.31.1 - diff --git a/SOURCES/kvm-tests-acpi-add-SLIC-table-test.patch b/SOURCES/kvm-tests-acpi-add-SLIC-table-test.patch deleted file mode 100644 index 9152c34..0000000 --- a/SOURCES/kvm-tests-acpi-add-SLIC-table-test.patch +++ /dev/null @@ -1,69 +0,0 @@ -From f897bc3aca1bb98b1907cfd76ba52cfa541b9b5c Mon Sep 17 00:00:00 2001 -From: Igor Mammedov -Date: Mon, 27 Dec 2021 14:31:19 -0500 -Subject: [PATCH 07/14] tests: acpi: add SLIC table test - -RH-Author: Igor Mammedov -RH-MergeRequest: 130: acpi: fix QEMU crash when started with SLIC table -RH-Commit: [3/10] b72e6f11e4d86bf39fa440df3902d9259d16d5db -RH-Bugzilla: 2043531 -RH-Acked-by: Gerd Hoffmann -RH-Acked-by: Miroslav Rezanina -RH-Acked-by: MST - -When user uses '-acpitable' to add SLIC table, some ACPI -tables (FADT) will change its 'Oem ID'/'Oem Table ID' fields to -match that of SLIC. Test makes sure thati QEMU handles -those fields correctly when SLIC table is added with -'-acpitable' option. - -Conflicts: - tests/qtest/bios-tables-test.c - due to missing 39d7554b2009 ("tests/acpi: add test case for VIOT") - -Signed-off-by: Igor Mammedov -Message-Id: <20211227193120.1084176-4-imammedo@redhat.com> -Reviewed-by: Michael S. Tsirkin -Signed-off-by: Michael S. Tsirkin -(cherry picked from commit 11edfabee443b149468a82b5efc88c96d1d259ec) -Signed-off-by: Igor Mammedov ---- - tests/qtest/bios-tables-test.c | 15 +++++++++++++++ - 1 file changed, 15 insertions(+) - -diff --git a/tests/qtest/bios-tables-test.c b/tests/qtest/bios-tables-test.c -index 62745181a8..088609c196 100644 ---- a/tests/qtest/bios-tables-test.c -+++ b/tests/qtest/bios-tables-test.c -@@ -1465,6 +1465,20 @@ static void test_acpi_virt_tcg(void) - free_test_data(&data); - } - -+static void test_acpi_q35_slic(void) -+{ -+ test_data data = { -+ .machine = MACHINE_Q35, -+ .variant = ".slic", -+ }; -+ -+ test_acpi_one("-acpitable sig=SLIC,oem_id='CRASH ',oem_table_id='ME'," -+ "oem_rev=00002210,asl_compiler_id='qemu'," -+ "asl_compiler_rev=00000000,data=/dev/null", -+ &data); -+ free_test_data(&data); -+} -+ - static void test_oem_fields(test_data *data) - { - int i; -@@ -1639,6 +1653,7 @@ int main(int argc, char *argv[]) - qtest_add_func("acpi/q35/kvm/xapic", test_acpi_q35_kvm_xapic); - qtest_add_func("acpi/q35/kvm/dmar", test_acpi_q35_kvm_dmar); - } -+ qtest_add_func("acpi/q35/slic", test_acpi_q35_slic); - } else if (strcmp(arch, "aarch64") == 0) { - if (has_tcg) { - qtest_add_func("acpi/virt", test_acpi_virt_tcg); --- -2.31.1 - diff --git a/SOURCES/kvm-tests-acpi-manually-pad-OEM_ID-OEM_TABLE_ID-for-test.patch b/SOURCES/kvm-tests-acpi-manually-pad-OEM_ID-OEM_TABLE_ID-for-test.patch deleted file mode 100644 index 5f5f300..0000000 --- a/SOURCES/kvm-tests-acpi-manually-pad-OEM_ID-OEM_TABLE_ID-for-test.patch +++ /dev/null @@ -1,76 +0,0 @@ -From 80fdb82bab21ab0d094795287ce903d0d48974fc Mon Sep 17 00:00:00 2001 -From: Igor Mammedov -Date: Wed, 12 Jan 2022 08:03:29 -0500 -Subject: [PATCH 09/14] tests: acpi: manually pad OEM_ID/OEM_TABLE_ID for - test_oem_fields() test - -RH-Author: Igor Mammedov -RH-MergeRequest: 130: acpi: fix QEMU crash when started with SLIC table -RH-Commit: [5/10] 7d55865be1e1574605734c2663bac233e87b8134 -RH-Bugzilla: 2043531 -RH-Acked-by: Gerd Hoffmann -RH-Acked-by: Miroslav Rezanina -RH-Acked-by: MST - -The next commit will revert OEM fields padding with whitespace to -padding with '\0' as it was before [1]. As result test_oem_fields() will -fail due to unexpectedly smaller ID sizes read from QEMU ACPI tables. - -Pad OEM_ID/OEM_TABLE_ID manually with spaces so that values the test -puts on QEMU CLI and expected values match. - -1) 602b458201 ("acpi: Permit OEM ID and OEM table ID fields to be changed") -Signed-off-by: Igor Mammedov -Message-Id: <20220112130332.1648664-2-imammedo@redhat.com> -Reviewed-by: Michael S. Tsirkin -Signed-off-by: Michael S. Tsirkin -(cherry picked from commit a849522f726767022203ef2b6c395ea19facb866) -Signed-off-by: Igor Mammedov ---- - tests/qtest/bios-tables-test.c | 15 ++++++--------- - 1 file changed, 6 insertions(+), 9 deletions(-) - -diff --git a/tests/qtest/bios-tables-test.c b/tests/qtest/bios-tables-test.c -index 088609c196..cfccfd4408 100644 ---- a/tests/qtest/bios-tables-test.c -+++ b/tests/qtest/bios-tables-test.c -@@ -71,9 +71,10 @@ - - #define ACPI_REBUILD_EXPECTED_AML "TEST_ACPI_REBUILD_AML" - --#define OEM_ID "TEST" --#define OEM_TABLE_ID "OEM" --#define OEM_TEST_ARGS "-machine x-oem-id="OEM_ID",x-oem-table-id="OEM_TABLE_ID -+#define OEM_ID "TEST " -+#define OEM_TABLE_ID "OEM " -+#define OEM_TEST_ARGS "-machine x-oem-id='" OEM_ID "',x-oem-table-id='" \ -+ OEM_TABLE_ID "'" - - typedef struct { - bool tcg_only; -@@ -1482,11 +1483,7 @@ static void test_acpi_q35_slic(void) - static void test_oem_fields(test_data *data) - { - int i; -- char oem_id[6]; -- char oem_table_id[8]; - -- strpadcpy(oem_id, sizeof oem_id, OEM_ID, ' '); -- strpadcpy(oem_table_id, sizeof oem_table_id, OEM_TABLE_ID, ' '); - for (i = 0; i < data->tables->len; ++i) { - AcpiSdtTable *sdt; - -@@ -1496,8 +1493,8 @@ static void test_oem_fields(test_data *data) - continue; - } - -- g_assert(memcmp(sdt->aml + 10, oem_id, 6) == 0); -- g_assert(memcmp(sdt->aml + 16, oem_table_id, 8) == 0); -+ g_assert(memcmp(sdt->aml + 10, OEM_ID, 6) == 0); -+ g_assert(memcmp(sdt->aml + 16, OEM_TABLE_ID, 8) == 0); - } - } - --- -2.31.1 - diff --git a/SOURCES/kvm-tests-acpi-test-short-OEM_ID-OEM_TABLE_ID-values-in-.patch b/SOURCES/kvm-tests-acpi-test-short-OEM_ID-OEM_TABLE_ID-values-in-.patch deleted file mode 100644 index b0abe81..0000000 --- a/SOURCES/kvm-tests-acpi-test-short-OEM_ID-OEM_TABLE_ID-values-in-.patch +++ /dev/null @@ -1,69 +0,0 @@ -From d08941e96003ea6bd26d73b4270912670e39e1bc Mon Sep 17 00:00:00 2001 -From: Igor Mammedov -Date: Fri, 14 Jan 2022 09:26:41 -0500 -Subject: [PATCH 13/14] tests: acpi: test short OEM_ID/OEM_TABLE_ID values in - test_oem_fields() - -RH-Author: Igor Mammedov -RH-MergeRequest: 130: acpi: fix QEMU crash when started with SLIC table -RH-Commit: [9/10] f1f9991d5d7ef5afb2f98f4fa81aeb3e3cf32d8f -RH-Bugzilla: 2043531 -RH-Acked-by: Gerd Hoffmann -RH-Acked-by: Miroslav Rezanina -RH-Acked-by: MST - -Previous patch [1] added explicit whitespace padding to OEM_ID/OEM_TABLE_ID -values used in test_oem_fields() testcase to avoid false positive and -bisection issues when QEMU is switched to \0' padding. As result -testcase ceased to test values that were shorter than max possible -length values. - -Update testcase to make sure that it's testing shorter IDs like it -used to before [2]. - -1) "tests: acpi: manually pad OEM_ID/OEM_TABLE_ID for test_oem_fields() test" -2) 602b458201 ("acpi: Permit OEM ID and OEM table ID fields to be changed") - -Signed-off-by: Igor Mammedov -Message-Id: <20220114142641.1727679-1-imammedo@redhat.com> -Reviewed-by: Michael S. Tsirkin -Signed-off-by: Michael S. Tsirkin -(cherry picked from commit 408ca92634770de5eac7965ed97c6260e770f2e7) -Signed-off-by: Igor Mammedov ---- - tests/qtest/bios-tables-test.c | 12 ++++++------ - 1 file changed, 6 insertions(+), 6 deletions(-) - -diff --git a/tests/qtest/bios-tables-test.c b/tests/qtest/bios-tables-test.c -index cfccfd4408..0dd9a0a55b 100644 ---- a/tests/qtest/bios-tables-test.c -+++ b/tests/qtest/bios-tables-test.c -@@ -71,10 +71,10 @@ - - #define ACPI_REBUILD_EXPECTED_AML "TEST_ACPI_REBUILD_AML" - --#define OEM_ID "TEST " --#define OEM_TABLE_ID "OEM " --#define OEM_TEST_ARGS "-machine x-oem-id='" OEM_ID "',x-oem-table-id='" \ -- OEM_TABLE_ID "'" -+#define OEM_ID "TEST" -+#define OEM_TABLE_ID "OEM" -+#define OEM_TEST_ARGS "-machine x-oem-id=" OEM_ID ",x-oem-table-id=" \ -+ OEM_TABLE_ID - - typedef struct { - bool tcg_only; -@@ -1493,8 +1493,8 @@ static void test_oem_fields(test_data *data) - continue; - } - -- g_assert(memcmp(sdt->aml + 10, OEM_ID, 6) == 0); -- g_assert(memcmp(sdt->aml + 16, OEM_TABLE_ID, 8) == 0); -+ g_assert(strncmp((char *)sdt->aml + 10, OEM_ID, 6) == 0); -+ g_assert(strncmp((char *)sdt->aml + 16, OEM_TABLE_ID, 8) == 0); - } - } - --- -2.31.1 - diff --git a/SOURCES/kvm-tests-acpi-update-expected-blobs.patch b/SOURCES/kvm-tests-acpi-update-expected-blobs.patch deleted file mode 100644 index d629202..0000000 --- a/SOURCES/kvm-tests-acpi-update-expected-blobs.patch +++ /dev/null @@ -1,50 +0,0 @@ -From b8831f75d186639385d75a4df9c510c7435fcdaf Mon Sep 17 00:00:00 2001 -From: Igor Mammedov -Date: Wed, 12 Jan 2022 08:03:32 -0500 -Subject: [PATCH 12/14] tests: acpi: update expected blobs - -RH-Author: Igor Mammedov -RH-MergeRequest: 130: acpi: fix QEMU crash when started with SLIC table -RH-Commit: [8/10] dddfa6e1b966bf7c5c00a20c98a778b060dc6983 -RH-Bugzilla: 2043531 -RH-Acked-by: Gerd Hoffmann -RH-Acked-by: Miroslav Rezanina -RH-Acked-by: MST - -Expected changes caused by previous commit: - -nvdimm ssdt (q35/pc/virt): - - * OEM Table ID "NVDIMM " - + * OEM Table ID "NVDIMM" - -SLIC test FADT (tests/data/acpi/q35/FACP.slic): - -[010h 0016 8] Oem Table ID : "ME " - +[010h 0016 8] Oem Table ID : "ME" - -Signed-off-by: Igor Mammedov -Message-Id: <20220112130332.1648664-5-imammedo@redhat.com> -Reviewed-by: Michael S. Tsirkin -Signed-off-by: Michael S. Tsirkin -(cherry picked from commit 5adc3aba875416b0e077d8a29ddd0357883746f4) -Signed-off-by: Igor Mammedov ---- - tests/data/acpi/pc/SSDT.dimmpxm | Bin 734 -> 734 bytes - tests/data/acpi/q35/FACP.slic | Bin 244 -> 244 bytes - tests/data/acpi/q35/SSDT.dimmpxm | Bin 734 -> 734 bytes - tests/data/acpi/virt/SSDT.memhp | Bin 736 -> 736 bytes - tests/qtest/bios-tables-test-allowed-diff.h | 4 ---- - 5 files changed, 4 deletions(-) - -diff --git a/tests/qtest/bios-tables-test-allowed-diff.h b/tests/qtest/bios-tables-test-allowed-diff.h -index 7faa8f53be..dfb8523c8b 100644 ---- a/tests/qtest/bios-tables-test-allowed-diff.h -+++ b/tests/qtest/bios-tables-test-allowed-diff.h -@@ -1,5 +1 @@ - /* List of comma-separated changed AML files to ignore */ --"tests/data/acpi/virt/SSDT.memhp", --"tests/data/acpi/pc/SSDT.dimmpxm", --"tests/data/acpi/q35/SSDT.dimmpxm", --"tests/data/acpi/q35/FACP.slic", --- -2.31.1 - diff --git a/SOURCES/kvm-tests-acpi-whitelist-expected-blobs-before-changing-.patch b/SOURCES/kvm-tests-acpi-whitelist-expected-blobs-before-changing-.patch deleted file mode 100644 index ebe3d36..0000000 --- a/SOURCES/kvm-tests-acpi-whitelist-expected-blobs-before-changing-.patch +++ /dev/null @@ -1,42 +0,0 @@ -From 9d8ab705fb0ffc55e78c22f4dd79c4c57437532e Mon Sep 17 00:00:00 2001 -From: Igor Mammedov -Date: Mon, 27 Dec 2021 14:31:18 -0500 -Subject: [PATCH 06/14] tests: acpi: whitelist expected blobs before changing - them - -RH-Author: Igor Mammedov -RH-MergeRequest: 130: acpi: fix QEMU crash when started with SLIC table -RH-Commit: [2/10] 677ac6f62a40479f88cc0d47bfece74bb39ae7a7 -RH-Bugzilla: 2043531 -RH-Acked-by: Gerd Hoffmann -RH-Acked-by: Miroslav Rezanina -RH-Acked-by: MST - -Signed-off-by: Igor Mammedov -Message-Id: <20211227193120.1084176-3-imammedo@redhat.com> -Reviewed-by: Michael S. Tsirkin -Signed-off-by: Michael S. Tsirkin -(cherry picked from commit e71f6ab9d93a7d01e833647e7010c1079c4cef30) -Signed-off-by: Igor Mammedov ---- - tests/data/acpi/q35/FACP.slic | Bin 0 -> 244 bytes - tests/data/acpi/q35/SLIC.slic | 0 - tests/qtest/bios-tables-test-allowed-diff.h | 2 ++ - 3 files changed, 2 insertions(+) - create mode 100644 tests/data/acpi/q35/FACP.slic - create mode 100644 tests/data/acpi/q35/SLIC.slic - -diff --git a/tests/data/acpi/q35/SLIC.slic b/tests/data/acpi/q35/SLIC.slic -new file mode 100644 -index 0000000000..e69de29bb2 -diff --git a/tests/qtest/bios-tables-test-allowed-diff.h b/tests/qtest/bios-tables-test-allowed-diff.h -index dfb8523c8b..49dbf8fa3e 100644 ---- a/tests/qtest/bios-tables-test-allowed-diff.h -+++ b/tests/qtest/bios-tables-test-allowed-diff.h -@@ -1 +1,3 @@ - /* List of comma-separated changed AML files to ignore */ -+"tests/data/acpi/q35/FACP.slic", -+"tests/data/acpi/q35/SLIC.slic", --- -2.31.1 - diff --git a/SOURCES/kvm-tests-acpi-whitelist-nvdimm-s-SSDT-and-FACP.slic-exp.patch b/SOURCES/kvm-tests-acpi-whitelist-nvdimm-s-SSDT-and-FACP.slic-exp.patch deleted file mode 100644 index 6774f18..0000000 --- a/SOURCES/kvm-tests-acpi-whitelist-nvdimm-s-SSDT-and-FACP.slic-exp.patch +++ /dev/null @@ -1,49 +0,0 @@ -From 667b82b02f7f3a1e5c37e3ff77b146cc3fd9da80 Mon Sep 17 00:00:00 2001 -From: Igor Mammedov -Date: Wed, 12 Jan 2022 08:03:30 -0500 -Subject: [PATCH 10/14] tests: acpi: whitelist nvdimm's SSDT and FACP.slic - expected blobs - -RH-Author: Igor Mammedov -RH-MergeRequest: 130: acpi: fix QEMU crash when started with SLIC table -RH-Commit: [6/10] 9b35b82e26499de3b7bdc0cdd089fda0a8ec031a -RH-Bugzilla: 2043531 -RH-Acked-by: Gerd Hoffmann -RH-Acked-by: Miroslav Rezanina -RH-Acked-by: MST - -The next commit will revert OEM fields whitespace padding to -padding with '\0' as it was before [1]. That will change OEM -Table ID for: - * SSDT.*: where it was padded from 6 characters to 8 - * FACP.slic: where it was padded from 2 characters to 8 -after reverting whitespace padding, it will be replaced with -'\0' which effectively will shorten OEM table ID to 6 and 2 -characters. - -Whitelist affected tables before introducing the change. - -1) 602b458201 ("acpi: Permit OEM ID and OEM table ID fields to be changed") -Signed-off-by: Igor Mammedov -Message-Id: <20220112130332.1648664-3-imammedo@redhat.com> -Reviewed-by: Michael S. Tsirkin -Signed-off-by: Michael S. Tsirkin -(cherry picked from commit d1e4a4654154925eddf0fc449fa9c92b806b9c8c) -Signed-off-by: Igor Mammedov ---- - tests/qtest/bios-tables-test-allowed-diff.h | 4 ++++ - 1 file changed, 4 insertions(+) - -diff --git a/tests/qtest/bios-tables-test-allowed-diff.h b/tests/qtest/bios-tables-test-allowed-diff.h -index dfb8523c8b..7faa8f53be 100644 ---- a/tests/qtest/bios-tables-test-allowed-diff.h -+++ b/tests/qtest/bios-tables-test-allowed-diff.h -@@ -1 +1,5 @@ - /* List of comma-separated changed AML files to ignore */ -+"tests/data/acpi/virt/SSDT.memhp", -+"tests/data/acpi/pc/SSDT.dimmpxm", -+"tests/data/acpi/q35/SSDT.dimmpxm", -+"tests/data/acpi/q35/FACP.slic", --- -2.31.1 - diff --git a/SOURCES/kvm-tests-avocado-update-aarch64_virt-test-to-exercise-c.patch b/SOURCES/kvm-tests-avocado-update-aarch64_virt-test-to-exercise-c.patch new file mode 100644 index 0000000..4fcf786 --- /dev/null +++ b/SOURCES/kvm-tests-avocado-update-aarch64_virt-test-to-exercise-c.patch @@ -0,0 +1,157 @@ +From f52aa60217634c96fef59ce76b803a94610bf5c8 Mon Sep 17 00:00:00 2001 +From: Andrew Jones +Date: Wed, 15 Jun 2022 15:28:27 +0200 +Subject: [PATCH 01/18] tests/avocado: update aarch64_virt test to exercise + -cpu max +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Daniel P. Berrangé +RH-MergeRequest: 94: i386, aarch64, s390x: deprecate many named CPU models +RH-Commit: [1/6] df6839e567180a4c32afd98852f68b2279e00f7c (berrange/centos-src-qemu) +RH-Bugzilla: 2060839 +RH-Acked-by: Thomas Huth +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Cornelia Huck + +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2066824 + +commit 11593544df6f8febb3ce87015c22b429bf43c4c7 +Author: Alex Bennée +Date: Tue Apr 19 10:09:56 2022 +0100 + + tests/avocado: update aarch64_virt test to exercise -cpu max + + The Fedora 29 kernel is quite old and importantly fails when running + in LPA2 scenarios. As it's not really exercising much of the CPU space + replace it with a custom 5.16.12 kernel with all the architecture + options turned on. There is a minimal buildroot initramfs included in + the kernel which has a few tools for stress testing the memory + subsystem. The userspace also targets the Neoverse N1 processor so + would fail with a v8.0 cpu like cortex-a53. + + While we are at it move the test into its own file so it can have an + assigned maintainer. + + Signed-off-by: Alex Bennée + Acked-by: Richard Henderson + Tested-by: Richard Henderson + Message-Id: <20220419091020.3008144-2-alex.bennee@linaro.org> + +Signed-off-by: Andrew Jones +--- + MAINTAINERS | 1 + + tests/avocado/boot_linux_console.py | 25 ------------- + tests/avocado/machine_aarch64_virt.py | 51 +++++++++++++++++++++++++++ + 3 files changed, 52 insertions(+), 25 deletions(-) + create mode 100644 tests/avocado/machine_aarch64_virt.py + +diff --git a/MAINTAINERS b/MAINTAINERS +index 2fe20a49ab..bfe8806f60 100644 +--- a/MAINTAINERS ++++ b/MAINTAINERS +@@ -942,6 +942,7 @@ S: Maintained + F: hw/arm/virt* + F: include/hw/arm/virt.h + F: docs/system/arm/virt.rst ++F: tests/avocado/machine_aarch64_virt.py + + Xilinx Zynq + M: Edgar E. Iglesias +diff --git a/tests/avocado/boot_linux_console.py b/tests/avocado/boot_linux_console.py +index b40a3abc81..45a2ceda22 100644 +--- a/tests/avocado/boot_linux_console.py ++++ b/tests/avocado/boot_linux_console.py +@@ -325,31 +325,6 @@ def test_mips_malta32el_nanomips_64k_dbg(self): + kernel_hash = '18d1c68f2e23429e266ca39ba5349ccd0aeb7180' + self.do_test_mips_malta32el_nanomips(kernel_url, kernel_hash) + +- def test_aarch64_virt(self): +- """ +- :avocado: tags=arch:aarch64 +- :avocado: tags=machine:virt +- :avocado: tags=accel:tcg +- :avocado: tags=cpu:cortex-a53 +- """ +- kernel_url = ('https://archives.fedoraproject.org/pub/archive/fedora' +- '/linux/releases/29/Everything/aarch64/os/images/pxeboot' +- '/vmlinuz') +- kernel_hash = '8c73e469fc6ea06a58dc83a628fc695b693b8493' +- kernel_path = self.fetch_asset(kernel_url, asset_hash=kernel_hash) +- +- self.vm.set_console() +- kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE + +- 'console=ttyAMA0') +- self.require_accelerator("tcg") +- self.vm.add_args('-cpu', 'cortex-a53', +- '-accel', 'tcg', +- '-kernel', kernel_path, +- '-append', kernel_command_line) +- self.vm.launch() +- console_pattern = 'Kernel command line: %s' % kernel_command_line +- self.wait_for_console_pattern(console_pattern) +- + def test_aarch64_xlnx_versal_virt(self): + """ + :avocado: tags=arch:aarch64 +diff --git a/tests/avocado/machine_aarch64_virt.py b/tests/avocado/machine_aarch64_virt.py +new file mode 100644 +index 0000000000..21848cba70 +--- /dev/null ++++ b/tests/avocado/machine_aarch64_virt.py +@@ -0,0 +1,51 @@ ++# Functional test that boots a Linux kernel and checks the console ++# ++# Copyright (c) 2022 Linaro Ltd. ++# ++# Author: ++# Alex Bennée ++# ++# SPDX-License-Identifier: GPL-2.0-or-later ++ ++import time ++ ++from avocado_qemu import QemuSystemTest ++from avocado_qemu import wait_for_console_pattern ++from avocado_qemu import exec_command ++ ++class Aarch64VirtMachine(QemuSystemTest): ++ KERNEL_COMMON_COMMAND_LINE = 'printk.time=0 ' ++ ++ def wait_for_console_pattern(self, success_message, vm=None): ++ wait_for_console_pattern(self, success_message, ++ failure_message='Kernel panic - not syncing', ++ vm=vm) ++ ++ def test_aarch64_virt(self): ++ """ ++ :avocado: tags=arch:aarch64 ++ :avocado: tags=machine:virt ++ :avocado: tags=accel:tcg ++ :avocado: tags=cpu:max ++ """ ++ kernel_url = ('https://fileserver.linaro.org/s/' ++ 'z6B2ARM7DQT3HWN/download') ++ ++ kernel_hash = 'ed11daab50c151dde0e1e9c9cb8b2d9bd3215347' ++ kernel_path = self.fetch_asset(kernel_url, asset_hash=kernel_hash) ++ ++ self.vm.set_console() ++ kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE + ++ 'console=ttyAMA0') ++ self.require_accelerator("tcg") ++ self.vm.add_args('-cpu', 'max,pauth-impdef=on', ++ '-accel', 'tcg', ++ '-kernel', kernel_path, ++ '-append', kernel_command_line) ++ self.vm.launch() ++ self.wait_for_console_pattern('Welcome to Buildroot') ++ time.sleep(0.1) ++ exec_command(self, 'root') ++ time.sleep(0.1) ++ exec_command(self, 'cat /proc/self/maps') ++ time.sleep(0.1) +-- +2.35.3 + diff --git a/SOURCES/kvm-tests-qtest-fdc-test-Add-a-regression-test-for-CVE-2.patch b/SOURCES/kvm-tests-qtest-fdc-test-Add-a-regression-test-for-CVE-2.patch new file mode 100644 index 0000000..7b9a8f3 --- /dev/null +++ b/SOURCES/kvm-tests-qtest-fdc-test-Add-a-regression-test-for-CVE-2.patch @@ -0,0 +1,119 @@ +From cea7b15c613a11ea15a1458d6990be7044df6643 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Philippe=20Mathieu-Daud=C3=A9?= +Date: Thu, 18 Nov 2021 12:57:33 +0100 +Subject: [PATCH 17/17] tests/qtest/fdc-test: Add a regression test for + CVE-2021-3507 +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Jon Maloy +RH-MergeRequest: 107: hw/block/fdc: Prevent end-of-track overrun (CVE-2021-3507) +RH-Commit: [2/2] 067c052df790959c28c1fcc16547676d36523bd9 (mrezanin/centos-src-qemu-kvm) +RH-Bugzilla: 1951522 +RH-Acked-by: Hanna Reitz +RH-Acked-by: Miroslav Rezanina + +Add the reproducer from https://gitlab.com/qemu-project/qemu/-/issues/339 + +Without the previous commit, when running 'make check-qtest-i386' +with QEMU configured with '--enable-sanitizers' we get: + + ==4028352==ERROR: AddressSanitizer: heap-buffer-overflow on address 0x619000062a00 at pc 0x5626d03c491a bp 0x7ffdb4199410 sp 0x7ffdb4198bc0 + READ of size 786432 at 0x619000062a00 thread T0 + #0 0x5626d03c4919 in __asan_memcpy (qemu-system-i386+0x1e65919) + #1 0x5626d1c023cc in flatview_write_continue softmmu/physmem.c:2787:13 + #2 0x5626d1bf0c0f in flatview_write softmmu/physmem.c:2822:14 + #3 0x5626d1bf0798 in address_space_write softmmu/physmem.c:2914:18 + #4 0x5626d1bf0f37 in address_space_rw softmmu/physmem.c:2924:16 + #5 0x5626d1bf14c8 in cpu_physical_memory_rw softmmu/physmem.c:2933:5 + #6 0x5626d0bd5649 in cpu_physical_memory_write include/exec/cpu-common.h:82:5 + #7 0x5626d0bd0a07 in i8257_dma_write_memory hw/dma/i8257.c:452:9 + #8 0x5626d09f825d in fdctrl_transfer_handler hw/block/fdc.c:1616:13 + #9 0x5626d0a048b4 in fdctrl_start_transfer hw/block/fdc.c:1539:13 + #10 0x5626d09f4c3e in fdctrl_write_data hw/block/fdc.c:2266:13 + #11 0x5626d09f22f7 in fdctrl_write hw/block/fdc.c:829:9 + #12 0x5626d1c20bc5 in portio_write softmmu/ioport.c:207:17 + + 0x619000062a00 is located 0 bytes to the right of 512-byte region [0x619000062800,0x619000062a00) + allocated by thread T0 here: + #0 0x5626d03c66ec in posix_memalign (qemu-system-i386+0x1e676ec) + #1 0x5626d2b988d4 in qemu_try_memalign util/oslib-posix.c:210:11 + #2 0x5626d2b98b0c in qemu_memalign util/oslib-posix.c:226:27 + #3 0x5626d09fbaf0 in fdctrl_realize_common hw/block/fdc.c:2341:20 + #4 0x5626d0a150ed in isabus_fdc_realize hw/block/fdc-isa.c:113:5 + #5 0x5626d2367935 in device_set_realized hw/core/qdev.c:531:13 + + SUMMARY: AddressSanitizer: heap-buffer-overflow (qemu-system-i386+0x1e65919) in __asan_memcpy + Shadow bytes around the buggy address: + 0x0c32800044f0: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa + 0x0c3280004500: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 + 0x0c3280004510: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 + 0x0c3280004520: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 + 0x0c3280004530: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 + =>0x0c3280004540:[fa]fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa + 0x0c3280004550: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa + 0x0c3280004560: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa + 0x0c3280004570: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa + 0x0c3280004580: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa + 0x0c3280004590: fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd + Shadow byte legend (one shadow byte represents 8 application bytes): + Addressable: 00 + Heap left redzone: fa + Freed heap region: fd + ==4028352==ABORTING + +[ kwolf: Added snapshot=on to prevent write file lock failure ] + +Reported-by: Alexander Bulekov +Signed-off-by: Philippe Mathieu-Daudé +Reviewed-by: Alexander Bulekov +Signed-off-by: Kevin Wolf +(cherry picked from commit 46609b90d9e3a6304def11038a76b58ff43f77bc) +Signed-off-by: Jon Maloy +--- + tests/qtest/fdc-test.c | 21 +++++++++++++++++++++ + 1 file changed, 21 insertions(+) + +diff --git a/tests/qtest/fdc-test.c b/tests/qtest/fdc-test.c +index b0d40012e6..1d4f852128 100644 +--- a/tests/qtest/fdc-test.c ++++ b/tests/qtest/fdc-test.c +@@ -583,6 +583,26 @@ static void test_cve_2021_20196(void) + qtest_quit(s); + } + ++static void test_cve_2021_3507(void) ++{ ++ QTestState *s; ++ ++ s = qtest_initf("-nographic -m 32M -nodefaults " ++ "-drive file=%s,format=raw,if=floppy,snapshot=on", ++ test_image); ++ qtest_outl(s, 0x9, 0x0a0206); ++ qtest_outw(s, 0x3f4, 0x1600); ++ qtest_outw(s, 0x3f4, 0x0000); ++ qtest_outw(s, 0x3f4, 0x0000); ++ qtest_outw(s, 0x3f4, 0x0000); ++ qtest_outw(s, 0x3f4, 0x0200); ++ qtest_outw(s, 0x3f4, 0x0200); ++ qtest_outw(s, 0x3f4, 0x0000); ++ qtest_outw(s, 0x3f4, 0x0000); ++ qtest_outw(s, 0x3f4, 0x0000); ++ qtest_quit(s); ++} ++ + int main(int argc, char **argv) + { + int fd; +@@ -614,6 +634,7 @@ int main(int argc, char **argv) + qtest_add_func("/fdc/read_no_dma_19", test_read_no_dma_19); + qtest_add_func("/fdc/fuzz-registers", fuzz_registers); + qtest_add_func("/fdc/fuzz/cve_2021_20196", test_cve_2021_20196); ++ qtest_add_func("/fdc/fuzz/cve_2021_3507", test_cve_2021_3507); + + ret = g_test_run(); + +-- +2.31.1 + diff --git a/SOURCES/kvm-ui-avoid-compiler-warnings-from-unused-clipboard-inf.patch b/SOURCES/kvm-ui-avoid-compiler-warnings-from-unused-clipboard-inf.patch deleted file mode 100644 index 6b7173e..0000000 --- a/SOURCES/kvm-ui-avoid-compiler-warnings-from-unused-clipboard-inf.patch +++ /dev/null @@ -1,63 +0,0 @@ -From c5ff43026547ea20fbb496c5b6734b7e64362151 Mon Sep 17 00:00:00 2001 -From: Gerd Hoffmann -Date: Mon, 14 Feb 2022 12:37:49 +0100 -Subject: [PATCH 2/6] ui: avoid compiler warnings from unused clipboard info - variable -MIME-Version: 1.0 -Content-Type: text/plain; charset=UTF-8 -Content-Transfer-Encoding: 8bit - -RH-Author: Gerd Hoffmann -RH-MergeRequest: 75: fix vnc cut+paste crash -RH-Commit: [2/4] 6a7982a0bab86bf843fd65842e730a61b2fa2cb0 (kraxel/centos-qemu-kvm) -RH-Bugzilla: 2042820 -RH-Acked-by: Marc-André Lureau -RH-Acked-by: Daniel P. Berrangé -RH-Acked-by: Miroslav Rezanina - -With latest clang 13.0.0 we get - -../ui/clipboard.c:47:34: error: variable 'old' set but not used [-Werror,-Wunused-but-set-variable] - g_autoptr(QemuClipboardInfo) old = NULL; - ^ - -The compiler can't tell that we only declared this variable in -order to get the side effect of free'ing it when out of scope. - -This pattern is a little dubious for a use of g_autoptr, so -rewrite the code to avoid it. - -Reviewed-by: Richard Henderson -Reviewed-by: Philippe Mathieu-Daudé -Tested-by: Philippe Mathieu-Daudé -Signed-off-by: Daniel P. Berrangé -[AJB: fix merge conflict] -Signed-off-by: Alex Bennée -Message-Id: <20211215141949.3512719-2-berrange@redhat.com> -Message-Id: <20220105135009.1584676-2-alex.bennee@linaro.org> -(cherry picked from commit 70a54b01693eda3c61814b05d699aba41015ac48) ---- - ui/clipboard.c | 3 +-- - 1 file changed, 1 insertion(+), 2 deletions(-) - -diff --git a/ui/clipboard.c b/ui/clipboard.c -index d7b008d62a..7672058e84 100644 ---- a/ui/clipboard.c -+++ b/ui/clipboard.c -@@ -44,12 +44,11 @@ void qemu_clipboard_peer_release(QemuClipboardPeer *peer, - - void qemu_clipboard_update(QemuClipboardInfo *info) - { -- g_autoptr(QemuClipboardInfo) old = NULL; - assert(info->selection < QEMU_CLIPBOARD_SELECTION__COUNT); - - notifier_list_notify(&clipboard_notifiers, info); - -- old = cbinfo[info->selection]; -+ qemu_clipboard_info_unref(cbinfo[info->selection]); - cbinfo[info->selection] = qemu_clipboard_info_ref(info); - } - --- -2.27.0 - diff --git a/SOURCES/kvm-ui-clipboard-fix-use-after-free-regression.patch b/SOURCES/kvm-ui-clipboard-fix-use-after-free-regression.patch deleted file mode 100644 index e14cb23..0000000 --- a/SOURCES/kvm-ui-clipboard-fix-use-after-free-regression.patch +++ /dev/null @@ -1,49 +0,0 @@ -From 965275cd87f8008f129509c6d6fd0096e8ac2d96 Mon Sep 17 00:00:00 2001 -From: =?UTF-8?q?Marc-Andr=C3=A9=20Lureau?= -Date: Mon, 14 Feb 2022 15:59:17 +0400 -Subject: [PATCH 3/6] ui/clipboard: fix use-after-free regression -MIME-Version: 1.0 -Content-Type: text/plain; charset=UTF-8 -Content-Transfer-Encoding: 8bit - -RH-Author: Gerd Hoffmann -RH-MergeRequest: 75: fix vnc cut+paste crash -RH-Commit: [3/4] d8f68e0eb60d9aaa9a703d969f215816bf35f6f0 (kraxel/centos-qemu-kvm) -RH-Bugzilla: 2042820 -RH-Acked-by: Marc-André Lureau -RH-Acked-by: Daniel P. Berrangé -RH-Acked-by: Miroslav Rezanina - -The same info may be used to update the clipboard, and may be freed -before being ref'ed again. - -Fixes: 70a54b01693ed ("ui: avoid compiler warnings from unused clipboard info variable") - -Signed-off-by: Marc-André Lureau -Reviewed-by: Daniel P. Berrangé -Message-Id: <20220214115917.1679568-1-marcandre.lureau@redhat.com> -Signed-off-by: Gerd Hoffmann ---- - ui/clipboard.c | 6 ++++-- - 1 file changed, 4 insertions(+), 2 deletions(-) - -diff --git a/ui/clipboard.c b/ui/clipboard.c -index 7672058e84..d7dae13760 100644 ---- a/ui/clipboard.c -+++ b/ui/clipboard.c -@@ -48,8 +48,10 @@ void qemu_clipboard_update(QemuClipboardInfo *info) - - notifier_list_notify(&clipboard_notifiers, info); - -- qemu_clipboard_info_unref(cbinfo[info->selection]); -- cbinfo[info->selection] = qemu_clipboard_info_ref(info); -+ if (cbinfo[info->selection] != info) { -+ qemu_clipboard_info_unref(cbinfo[info->selection]); -+ cbinfo[info->selection] = qemu_clipboard_info_ref(info); -+ } - } - - QemuClipboardInfo *qemu_clipboard_info(QemuClipboardSelection selection) --- -2.27.0 - diff --git a/SOURCES/kvm-ui-vnc.c-Fixed-a-deadlock-bug.patch b/SOURCES/kvm-ui-vnc.c-Fixed-a-deadlock-bug.patch deleted file mode 100644 index 6d3802c..0000000 --- a/SOURCES/kvm-ui-vnc.c-Fixed-a-deadlock-bug.patch +++ /dev/null @@ -1,80 +0,0 @@ -From 14582cfec72e52894f16ed5c3fb14adb2d6d8e25 Mon Sep 17 00:00:00 2001 -From: Rao Lei -Date: Wed, 5 Jan 2022 10:08:08 +0800 -Subject: [PATCH 4/6] ui/vnc.c: Fixed a deadlock bug. -MIME-Version: 1.0 -Content-Type: text/plain; charset=UTF-8 -Content-Transfer-Encoding: 8bit - -RH-Author: Gerd Hoffmann -RH-MergeRequest: 75: fix vnc cut+paste crash -RH-Commit: [4/4] 5321e447de974d91e9a6c0cf01f4352166ffb7ce (kraxel/centos-qemu-kvm) -RH-Bugzilla: 2042820 -RH-Acked-by: Marc-André Lureau -RH-Acked-by: Daniel P. Berrangé -RH-Acked-by: Miroslav Rezanina - -The GDB statck is as follows: -(gdb) bt -0 __lll_lock_wait (futex=futex@entry=0x56211df20360, private=0) at lowlevellock.c:52 -1 0x00007f263caf20a3 in __GI___pthread_mutex_lock (mutex=0x56211df20360) at ../nptl/pthread_mutex_lock.c:80 -2 0x000056211a757364 in qemu_mutex_lock_impl (mutex=0x56211df20360, file=0x56211a804857 "../ui/vnc-jobs.h", line=60) - at ../util/qemu-thread-posix.c:80 -3 0x000056211a0ef8c7 in vnc_lock_output (vs=0x56211df14200) at ../ui/vnc-jobs.h:60 -4 0x000056211a0efcb7 in vnc_clipboard_send (vs=0x56211df14200, count=1, dwords=0x7ffdf1701338) at ../ui/vnc-clipboard.c:138 -5 0x000056211a0f0129 in vnc_clipboard_notify (notifier=0x56211df244c8, data=0x56211dd1bbf0) at ../ui/vnc-clipboard.c:209 -6 0x000056211a75dde8 in notifier_list_notify (list=0x56211afa17d0 , data=0x56211dd1bbf0) at ../util/notify.c:39 -7 0x000056211a0bf0e6 in qemu_clipboard_update (info=0x56211dd1bbf0) at ../ui/clipboard.c:50 -8 0x000056211a0bf05d in qemu_clipboard_peer_release (peer=0x56211df244c0, selection=QEMU_CLIPBOARD_SELECTION_CLIPBOARD) - at ../ui/clipboard.c:41 -9 0x000056211a0bef9b in qemu_clipboard_peer_unregister (peer=0x56211df244c0) at ../ui/clipboard.c:19 -10 0x000056211a0d45f3 in vnc_disconnect_finish (vs=0x56211df14200) at ../ui/vnc.c:1358 -11 0x000056211a0d4c9d in vnc_client_read (vs=0x56211df14200) at ../ui/vnc.c:1611 -12 0x000056211a0d4df8 in vnc_client_io (ioc=0x56211ce70690, condition=G_IO_IN, opaque=0x56211df14200) at ../ui/vnc.c:1649 -13 0x000056211a5b976c in qio_channel_fd_source_dispatch - (source=0x56211ce50a00, callback=0x56211a0d4d71 , user_data=0x56211df14200) at ../io/channel-watch.c:84 -14 0x00007f263ccede8e in g_main_context_dispatch () at /lib/x86_64-linux-gnu/libglib-2.0.so.0 -15 0x000056211a77d4a1 in glib_pollfds_poll () at ../util/main-loop.c:232 -16 0x000056211a77d51f in os_host_main_loop_wait (timeout=958545) at ../util/main-loop.c:255 -17 0x000056211a77d630 in main_loop_wait (nonblocking=0) at ../util/main-loop.c:531 -18 0x000056211a45bc8e in qemu_main_loop () at ../softmmu/runstate.c:726 -19 0x000056211a0b45fa in main (argc=69, argv=0x7ffdf1701778, envp=0x7ffdf17019a8) at ../softmmu/main.c:50 - -From the call trace, we can see it is a deadlock bug. -vnc_disconnect_finish will acquire the output_mutex. -But, the output_mutex will be acquired again in vnc_clipboard_send. -Repeated locking will cause deadlock. So, I move -qemu_clipboard_peer_unregister() behind vnc_unlock_output(); - -Fixes: 0bf41cab93e ("ui/vnc: clipboard support") -Signed-off-by: Lei Rao -Reviewed-by: Marc-André Lureau -Message-Id: <20220105020808.597325-1-lei.rao@intel.com> -Signed-off-by: Gerd Hoffmann -(cherry picked from commit 1dbbe6f172810026c51dc84ed927a3cc23017949) ---- - ui/vnc.c | 4 ++-- - 1 file changed, 2 insertions(+), 2 deletions(-) - -diff --git a/ui/vnc.c b/ui/vnc.c -index af02522e84..b253e85c65 100644 ---- a/ui/vnc.c -+++ b/ui/vnc.c -@@ -1354,12 +1354,12 @@ void vnc_disconnect_finish(VncState *vs) - /* last client gone */ - vnc_update_server_surface(vs->vd); - } -+ vnc_unlock_output(vs); -+ - if (vs->cbpeer.update.notify) { - qemu_clipboard_peer_unregister(&vs->cbpeer); - } - -- vnc_unlock_output(vs); -- - qemu_mutex_destroy(&vs->output_mutex); - if (vs->bh != NULL) { - qemu_bh_delete(vs->bh); --- -2.27.0 - diff --git a/SOURCES/kvm-util-Return-void-on-iova_tree_remove.patch b/SOURCES/kvm-util-Return-void-on-iova_tree_remove.patch new file mode 100644 index 0000000..07c6f8e --- /dev/null +++ b/SOURCES/kvm-util-Return-void-on-iova_tree_remove.patch @@ -0,0 +1,70 @@ +From 74c829f82eafa8e42ae94f7ace55c8aaed3bb5f4 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Wed, 27 Apr 2022 17:49:31 +0200 +Subject: [PATCH 05/23] util: Return void on iova_tree_remove +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 116: vdpa: Restore device state on destination +RH-Bugzilla: 2114060 +RH-Acked-by: Cindy Lu +RH-Acked-by: Miroslav Rezanina +RH-Commit: [4/21] 252287acca896eba7b5d2b62fc6247cfc565ba57 (eperezmartin/qemu-kvm) +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2114060 +Upstream status: Merged + +It always returns IOVA_OK so nobody uses it. + +Acked-by: Jason Wang +Reviewed-by: Peter Xu +Signed-off-by: Eugenio Pérez +Message-Id: <20220427154931.3166388-1-eperezma@redhat.com> +Signed-off-by: Laurent Vivier +(cherry picked from commit 832fef7cc14d65f99d523f883ef384014e6476a7) +--- + include/qemu/iova-tree.h | 4 +--- + util/iova-tree.c | 4 +--- + 2 files changed, 2 insertions(+), 6 deletions(-) + +diff --git a/include/qemu/iova-tree.h b/include/qemu/iova-tree.h +index c938fb0793..16bbfdf5f8 100644 +--- a/include/qemu/iova-tree.h ++++ b/include/qemu/iova-tree.h +@@ -72,10 +72,8 @@ int iova_tree_insert(IOVATree *tree, const DMAMap *map); + * provided. The range does not need to be exactly what has inserted, + * all the mappings that are included in the provided range will be + * removed from the tree. Here map->translated_addr is meaningless. +- * +- * Return: 0 if succeeded, or <0 if error. + */ +-int iova_tree_remove(IOVATree *tree, const DMAMap *map); ++void iova_tree_remove(IOVATree *tree, const DMAMap *map); + + /** + * iova_tree_find: +diff --git a/util/iova-tree.c b/util/iova-tree.c +index 6dff29c1f6..fee530a579 100644 +--- a/util/iova-tree.c ++++ b/util/iova-tree.c +@@ -164,15 +164,13 @@ void iova_tree_foreach(IOVATree *tree, iova_tree_iterator iterator) + g_tree_foreach(tree->tree, iova_tree_traverse, iterator); + } + +-int iova_tree_remove(IOVATree *tree, const DMAMap *map) ++void iova_tree_remove(IOVATree *tree, const DMAMap *map) + { + const DMAMap *overlap; + + while ((overlap = iova_tree_find(tree, map))) { + g_tree_remove(tree->tree, overlap); + } +- +- return IOVA_OK; + } + + /** +-- +2.31.1 + diff --git a/SOURCES/kvm-util-accept-iova_tree_remove_parameter-by-value.patch b/SOURCES/kvm-util-accept-iova_tree_remove_parameter-by-value.patch new file mode 100644 index 0000000..cd073da --- /dev/null +++ b/SOURCES/kvm-util-accept-iova_tree_remove_parameter-by-value.patch @@ -0,0 +1,182 @@ +From 90697579eaf598614293d75f684d6e8c55f8ab9b Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Tue, 23 Aug 2022 20:20:04 +0200 +Subject: [PATCH 06/23] util: accept iova_tree_remove_parameter by value +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 116: vdpa: Restore device state on destination +RH-Bugzilla: 2114060 +RH-Acked-by: Cindy Lu +RH-Acked-by: Miroslav Rezanina +RH-Commit: [5/21] ddaf052789e7ab3c67a77c038347113301587ffb (eperezmartin/qemu-kvm) +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2114060 +Upstream status: git@github.com:jasowang/qemu.git net-next + +It's convenient to call iova_tree_remove from a map returned from +iova_tree_find or iova_tree_find_iova. With the current code this is not +possible, since we will free it, and then we will try to search for it +again. + +Fix it making accepting the map by value, forcing a copy of the +argument. Not applying a fixes tag, since there is no use like that at +the moment. + +Signed-off-by: Eugenio Pérez +Signed-off-by: Jason Wang +(cherry picked from commit d69ba6677405de86b3b617fc7688b549f84cf013) +--- + hw/i386/intel_iommu.c | 6 +++--- + hw/virtio/vhost-iova-tree.c | 2 +- + hw/virtio/vhost-iova-tree.h | 2 +- + hw/virtio/vhost-vdpa.c | 6 +++--- + include/qemu/iova-tree.h | 2 +- + net/vhost-vdpa.c | 4 ++-- + util/iova-tree.c | 4 ++-- + 7 files changed, 13 insertions(+), 13 deletions(-) + +diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c +index c64aa81a83..6738cf0929 100644 +--- a/hw/i386/intel_iommu.c ++++ b/hw/i386/intel_iommu.c +@@ -1157,7 +1157,7 @@ static int vtd_page_walk_one(IOMMUTLBEvent *event, vtd_page_walk_info *info) + return ret; + } + /* Drop any existing mapping */ +- iova_tree_remove(as->iova_tree, &target); ++ iova_tree_remove(as->iova_tree, target); + /* Recover the correct type */ + event->type = IOMMU_NOTIFIER_MAP; + entry->perm = cache_perm; +@@ -1170,7 +1170,7 @@ static int vtd_page_walk_one(IOMMUTLBEvent *event, vtd_page_walk_info *info) + trace_vtd_page_walk_one_skip_unmap(entry->iova, entry->addr_mask); + return 0; + } +- iova_tree_remove(as->iova_tree, &target); ++ iova_tree_remove(as->iova_tree, target); + } + + trace_vtd_page_walk_one(info->domain_id, entry->iova, +@@ -3532,7 +3532,7 @@ static void vtd_address_space_unmap(VTDAddressSpace *as, IOMMUNotifier *n) + + map.iova = n->start; + map.size = size; +- iova_tree_remove(as->iova_tree, &map); ++ iova_tree_remove(as->iova_tree, map); + } + + static void vtd_address_space_unmap_all(IntelIOMMUState *s) +diff --git a/hw/virtio/vhost-iova-tree.c b/hw/virtio/vhost-iova-tree.c +index 55fed1fefb..1339a4de8b 100644 +--- a/hw/virtio/vhost-iova-tree.c ++++ b/hw/virtio/vhost-iova-tree.c +@@ -104,7 +104,7 @@ int vhost_iova_tree_map_alloc(VhostIOVATree *tree, DMAMap *map) + * @iova_tree: The vhost iova tree + * @map: The map to remove + */ +-void vhost_iova_tree_remove(VhostIOVATree *iova_tree, const DMAMap *map) ++void vhost_iova_tree_remove(VhostIOVATree *iova_tree, DMAMap map) + { + iova_tree_remove(iova_tree->iova_taddr_map, map); + } +diff --git a/hw/virtio/vhost-iova-tree.h b/hw/virtio/vhost-iova-tree.h +index 6a4f24e0f9..4adfd79ff0 100644 +--- a/hw/virtio/vhost-iova-tree.h ++++ b/hw/virtio/vhost-iova-tree.h +@@ -22,6 +22,6 @@ G_DEFINE_AUTOPTR_CLEANUP_FUNC(VhostIOVATree, vhost_iova_tree_delete); + const DMAMap *vhost_iova_tree_find_iova(const VhostIOVATree *iova_tree, + const DMAMap *map); + int vhost_iova_tree_map_alloc(VhostIOVATree *iova_tree, DMAMap *map); +-void vhost_iova_tree_remove(VhostIOVATree *iova_tree, const DMAMap *map); ++void vhost_iova_tree_remove(VhostIOVATree *iova_tree, DMAMap map); + + #endif +diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c +index cc15b7d8ee..39aa70f52d 100644 +--- a/hw/virtio/vhost-vdpa.c ++++ b/hw/virtio/vhost-vdpa.c +@@ -238,7 +238,7 @@ static void vhost_vdpa_listener_region_add(MemoryListener *listener, + + fail_map: + if (v->shadow_vqs_enabled) { +- vhost_iova_tree_remove(v->iova_tree, &mem_region); ++ vhost_iova_tree_remove(v->iova_tree, mem_region); + } + + fail: +@@ -298,7 +298,7 @@ static void vhost_vdpa_listener_region_del(MemoryListener *listener, + return; + } + iova = result->iova; +- vhost_iova_tree_remove(v->iova_tree, result); ++ vhost_iova_tree_remove(v->iova_tree, *result); + } + vhost_vdpa_iotlb_batch_begin_once(v); + ret = vhost_vdpa_dma_unmap(v, iova, int128_get64(llsize)); +@@ -942,7 +942,7 @@ static bool vhost_vdpa_svq_map_ring(struct vhost_vdpa *v, DMAMap *needle, + needle->perm == IOMMU_RO); + if (unlikely(r != 0)) { + error_setg_errno(errp, -r, "Cannot map region to device"); +- vhost_iova_tree_remove(v->iova_tree, needle); ++ vhost_iova_tree_remove(v->iova_tree, *needle); + } + + return r == 0; +diff --git a/include/qemu/iova-tree.h b/include/qemu/iova-tree.h +index 16bbfdf5f8..8528e5c98f 100644 +--- a/include/qemu/iova-tree.h ++++ b/include/qemu/iova-tree.h +@@ -73,7 +73,7 @@ int iova_tree_insert(IOVATree *tree, const DMAMap *map); + * all the mappings that are included in the provided range will be + * removed from the tree. Here map->translated_addr is meaningless. + */ +-void iova_tree_remove(IOVATree *tree, const DMAMap *map); ++void iova_tree_remove(IOVATree *tree, DMAMap map); + + /** + * iova_tree_find: +diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c +index 411e71e6c2..ba65736f83 100644 +--- a/net/vhost-vdpa.c ++++ b/net/vhost-vdpa.c +@@ -244,7 +244,7 @@ static void vhost_vdpa_cvq_unmap_buf(struct vhost_vdpa *v, void *addr) + error_report("Device cannot unmap: %s(%d)", g_strerror(r), r); + } + +- vhost_iova_tree_remove(tree, map); ++ vhost_iova_tree_remove(tree, *map); + } + + static size_t vhost_vdpa_net_cvq_cmd_len(void) +@@ -297,7 +297,7 @@ static bool vhost_vdpa_cvq_map_buf(struct vhost_vdpa *v, + return true; + + dma_map_err: +- vhost_iova_tree_remove(v->iova_tree, &map); ++ vhost_iova_tree_remove(v->iova_tree, map); + return false; + } + +diff --git a/util/iova-tree.c b/util/iova-tree.c +index fee530a579..536789797e 100644 +--- a/util/iova-tree.c ++++ b/util/iova-tree.c +@@ -164,11 +164,11 @@ void iova_tree_foreach(IOVATree *tree, iova_tree_iterator iterator) + g_tree_foreach(tree->tree, iova_tree_traverse, iterator); + } + +-void iova_tree_remove(IOVATree *tree, const DMAMap *map) ++void iova_tree_remove(IOVATree *tree, DMAMap map) + { + const DMAMap *overlap; + +- while ((overlap = iova_tree_find(tree, map))) { ++ while ((overlap = iova_tree_find(tree, &map))) { + g_tree_remove(tree->tree, overlap); + } + } +-- +2.31.1 + diff --git a/SOURCES/kvm-util-event-loop-base-Introduce-options-to-set-the-th.patch b/SOURCES/kvm-util-event-loop-base-Introduce-options-to-set-the-th.patch new file mode 100644 index 0000000..77929a6 --- /dev/null +++ b/SOURCES/kvm-util-event-loop-base-Introduce-options-to-set-the-th.patch @@ -0,0 +1,385 @@ +From 7a6fa42d4a4263c94b9bf18290f9e7680ea9e7f4 Mon Sep 17 00:00:00 2001 +From: Nicolas Saenz Julienne +Date: Mon, 25 Apr 2022 09:57:23 +0200 +Subject: [PATCH 03/16] util/event-loop-base: Introduce options to set the + thread pool size + +RH-Author: Nicolas Saenz Julienne +RH-MergeRequest: 93: util/thread-pool: Expose minimum and maximum size +RH-Commit: [3/3] af78a88ff3c69701cbb5f9e980c3d6ebbd13ff98 +RH-Bugzilla: 2031024 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Stefan Hajnoczi + +The thread pool regulates itself: when idle, it kills threads until +empty, when in demand, it creates new threads until full. This behaviour +doesn't play well with latency sensitive workloads where the price of +creating a new thread is too high. For example, when paired with qemu's +'-mlock', or using safety features like SafeStack, creating a new thread +has been measured take multiple milliseconds. + +In order to mitigate this let's introduce a new 'EventLoopBase' +property to set the thread pool size. The threads will be created during +the pool's initialization or upon updating the property's value, remain +available during its lifetime regardless of demand, and destroyed upon +freeing it. A properly characterized workload will then be able to +configure the pool to avoid any latency spikes. + +Signed-off-by: Nicolas Saenz Julienne +Reviewed-by: Stefan Hajnoczi +Acked-by: Markus Armbruster +Message-id: 20220425075723.20019-4-nsaenzju@redhat.com +Signed-off-by: Stefan Hajnoczi +(cherry picked from commit 71ad4713cc1d7fca24388b828ef31ae6cb38a31c) +--- + event-loop-base.c | 23 +++++++++++++ + include/block/aio.h | 10 ++++++ + include/block/thread-pool.h | 3 ++ + include/sysemu/event-loop-base.h | 4 +++ + iothread.c | 3 ++ + qapi/qom.json | 10 +++++- + util/aio-posix.c | 1 + + util/async.c | 20 ++++++++++++ + util/main-loop.c | 9 ++++++ + util/thread-pool.c | 55 +++++++++++++++++++++++++++++--- + 10 files changed, 133 insertions(+), 5 deletions(-) + +diff --git a/event-loop-base.c b/event-loop-base.c +index e7f99a6ec8..d5be4dc6fc 100644 +--- a/event-loop-base.c ++++ b/event-loop-base.c +@@ -14,6 +14,7 @@ + #include "qemu/osdep.h" + #include "qom/object_interfaces.h" + #include "qapi/error.h" ++#include "block/thread-pool.h" + #include "sysemu/event-loop-base.h" + + typedef struct { +@@ -21,9 +22,22 @@ typedef struct { + ptrdiff_t offset; /* field's byte offset in EventLoopBase struct */ + } EventLoopBaseParamInfo; + ++static void event_loop_base_instance_init(Object *obj) ++{ ++ EventLoopBase *base = EVENT_LOOP_BASE(obj); ++ ++ base->thread_pool_max = THREAD_POOL_MAX_THREADS_DEFAULT; ++} ++ + static EventLoopBaseParamInfo aio_max_batch_info = { + "aio-max-batch", offsetof(EventLoopBase, aio_max_batch), + }; ++static EventLoopBaseParamInfo thread_pool_min_info = { ++ "thread-pool-min", offsetof(EventLoopBase, thread_pool_min), ++}; ++static EventLoopBaseParamInfo thread_pool_max_info = { ++ "thread-pool-max", offsetof(EventLoopBase, thread_pool_max), ++}; + + static void event_loop_base_get_param(Object *obj, Visitor *v, + const char *name, void *opaque, Error **errp) +@@ -95,12 +109,21 @@ static void event_loop_base_class_init(ObjectClass *klass, void *class_data) + event_loop_base_get_param, + event_loop_base_set_param, + NULL, &aio_max_batch_info); ++ object_class_property_add(klass, "thread-pool-min", "int", ++ event_loop_base_get_param, ++ event_loop_base_set_param, ++ NULL, &thread_pool_min_info); ++ object_class_property_add(klass, "thread-pool-max", "int", ++ event_loop_base_get_param, ++ event_loop_base_set_param, ++ NULL, &thread_pool_max_info); + } + + static const TypeInfo event_loop_base_info = { + .name = TYPE_EVENT_LOOP_BASE, + .parent = TYPE_OBJECT, + .instance_size = sizeof(EventLoopBase), ++ .instance_init = event_loop_base_instance_init, + .class_size = sizeof(EventLoopBaseClass), + .class_init = event_loop_base_class_init, + .abstract = true, +diff --git a/include/block/aio.h b/include/block/aio.h +index 5634173b12..d128558f1d 100644 +--- a/include/block/aio.h ++++ b/include/block/aio.h +@@ -192,6 +192,8 @@ struct AioContext { + QSLIST_HEAD(, Coroutine) scheduled_coroutines; + QEMUBH *co_schedule_bh; + ++ int thread_pool_min; ++ int thread_pool_max; + /* Thread pool for performing work and receiving completion callbacks. + * Has its own locking. + */ +@@ -769,4 +771,12 @@ void aio_context_set_poll_params(AioContext *ctx, int64_t max_ns, + void aio_context_set_aio_params(AioContext *ctx, int64_t max_batch, + Error **errp); + ++/** ++ * aio_context_set_thread_pool_params: ++ * @ctx: the aio context ++ * @min: min number of threads to have readily available in the thread pool ++ * @min: max number of threads the thread pool can contain ++ */ ++void aio_context_set_thread_pool_params(AioContext *ctx, int64_t min, ++ int64_t max, Error **errp); + #endif +diff --git a/include/block/thread-pool.h b/include/block/thread-pool.h +index 7dd7d730a0..2020bcc92d 100644 +--- a/include/block/thread-pool.h ++++ b/include/block/thread-pool.h +@@ -20,6 +20,8 @@ + + #include "block/block.h" + ++#define THREAD_POOL_MAX_THREADS_DEFAULT 64 ++ + typedef int ThreadPoolFunc(void *opaque); + + typedef struct ThreadPool ThreadPool; +@@ -33,5 +35,6 @@ BlockAIOCB *thread_pool_submit_aio(ThreadPool *pool, + int coroutine_fn thread_pool_submit_co(ThreadPool *pool, + ThreadPoolFunc *func, void *arg); + void thread_pool_submit(ThreadPool *pool, ThreadPoolFunc *func, void *arg); ++void thread_pool_update_params(ThreadPool *pool, struct AioContext *ctx); + + #endif +diff --git a/include/sysemu/event-loop-base.h b/include/sysemu/event-loop-base.h +index fced4c9fea..2748bf6ae1 100644 +--- a/include/sysemu/event-loop-base.h ++++ b/include/sysemu/event-loop-base.h +@@ -33,5 +33,9 @@ struct EventLoopBase { + + /* AioContext AIO engine parameters */ + int64_t aio_max_batch; ++ ++ /* AioContext thread pool parameters */ ++ int64_t thread_pool_min; ++ int64_t thread_pool_max; + }; + #endif +diff --git a/iothread.c b/iothread.c +index 8fa2f3bfb8..529194a566 100644 +--- a/iothread.c ++++ b/iothread.c +@@ -174,6 +174,9 @@ static void iothread_set_aio_context_params(EventLoopBase *base, Error **errp) + aio_context_set_aio_params(iothread->ctx, + iothread->parent_obj.aio_max_batch, + errp); ++ ++ aio_context_set_thread_pool_params(iothread->ctx, base->thread_pool_min, ++ base->thread_pool_max, errp); + } + + +diff --git a/qapi/qom.json b/qapi/qom.json +index 7d4a2ac1b9..6a653c6636 100644 +--- a/qapi/qom.json ++++ b/qapi/qom.json +@@ -508,10 +508,18 @@ + # 0 means that the engine will use its default. + # (default: 0) + # ++# @thread-pool-min: minimum number of threads reserved in the thread pool ++# (default:0) ++# ++# @thread-pool-max: maximum number of threads the thread pool can contain ++# (default:64) ++# + # Since: 7.1 + ## + { 'struct': 'EventLoopBaseProperties', +- 'data': { '*aio-max-batch': 'int' } } ++ 'data': { '*aio-max-batch': 'int', ++ '*thread-pool-min': 'int', ++ '*thread-pool-max': 'int' } } + + ## + # @IothreadProperties: +diff --git a/util/aio-posix.c b/util/aio-posix.c +index be0182a3c6..731f3826c0 100644 +--- a/util/aio-posix.c ++++ b/util/aio-posix.c +@@ -15,6 +15,7 @@ + + #include "qemu/osdep.h" + #include "block/block.h" ++#include "block/thread-pool.h" + #include "qemu/main-loop.h" + #include "qemu/rcu.h" + #include "qemu/rcu_queue.h" +diff --git a/util/async.c b/util/async.c +index 2ea1172f3e..554ba70cca 100644 +--- a/util/async.c ++++ b/util/async.c +@@ -563,6 +563,9 @@ AioContext *aio_context_new(Error **errp) + + ctx->aio_max_batch = 0; + ++ ctx->thread_pool_min = 0; ++ ctx->thread_pool_max = THREAD_POOL_MAX_THREADS_DEFAULT; ++ + return ctx; + fail: + g_source_destroy(&ctx->source); +@@ -696,3 +699,20 @@ void qemu_set_current_aio_context(AioContext *ctx) + assert(!get_my_aiocontext()); + set_my_aiocontext(ctx); + } ++ ++void aio_context_set_thread_pool_params(AioContext *ctx, int64_t min, ++ int64_t max, Error **errp) ++{ ++ ++ if (min > max || !max || min > INT_MAX || max > INT_MAX) { ++ error_setg(errp, "bad thread-pool-min/thread-pool-max values"); ++ return; ++ } ++ ++ ctx->thread_pool_min = min; ++ ctx->thread_pool_max = max; ++ ++ if (ctx->thread_pool) { ++ thread_pool_update_params(ctx->thread_pool, ctx); ++ } ++} +diff --git a/util/main-loop.c b/util/main-loop.c +index 5b13f456fa..a0f48186ab 100644 +--- a/util/main-loop.c ++++ b/util/main-loop.c +@@ -30,6 +30,7 @@ + #include "sysemu/replay.h" + #include "qemu/main-loop.h" + #include "block/aio.h" ++#include "block/thread-pool.h" + #include "qemu/error-report.h" + #include "qemu/queue.h" + #include "qemu/compiler.h" +@@ -187,12 +188,20 @@ int qemu_init_main_loop(Error **errp) + + static void main_loop_update_params(EventLoopBase *base, Error **errp) + { ++ ERRP_GUARD(); ++ + if (!qemu_aio_context) { + error_setg(errp, "qemu aio context not ready"); + return; + } + + aio_context_set_aio_params(qemu_aio_context, base->aio_max_batch, errp); ++ if (*errp) { ++ return; ++ } ++ ++ aio_context_set_thread_pool_params(qemu_aio_context, base->thread_pool_min, ++ base->thread_pool_max, errp); + } + + MainLoop *mloop; +diff --git a/util/thread-pool.c b/util/thread-pool.c +index d763cea505..196835b4d3 100644 +--- a/util/thread-pool.c ++++ b/util/thread-pool.c +@@ -58,7 +58,6 @@ struct ThreadPool { + QemuMutex lock; + QemuCond worker_stopped; + QemuSemaphore sem; +- int max_threads; + QEMUBH *new_thread_bh; + + /* The following variables are only accessed from one AioContext. */ +@@ -71,8 +70,27 @@ struct ThreadPool { + int new_threads; /* backlog of threads we need to create */ + int pending_threads; /* threads created but not running yet */ + bool stopping; ++ int min_threads; ++ int max_threads; + }; + ++static inline bool back_to_sleep(ThreadPool *pool, int ret) ++{ ++ /* ++ * The semaphore timed out, we should exit the loop except when: ++ * - There is work to do, we raced with the signal. ++ * - The max threads threshold just changed, we raced with the signal. ++ * - The thread pool forces a minimum number of readily available threads. ++ */ ++ if (ret == -1 && (!QTAILQ_EMPTY(&pool->request_list) || ++ pool->cur_threads > pool->max_threads || ++ pool->cur_threads <= pool->min_threads)) { ++ return true; ++ } ++ ++ return false; ++} ++ + static void *worker_thread(void *opaque) + { + ThreadPool *pool = opaque; +@@ -91,8 +109,9 @@ static void *worker_thread(void *opaque) + ret = qemu_sem_timedwait(&pool->sem, 10000); + qemu_mutex_lock(&pool->lock); + pool->idle_threads--; +- } while (ret == -1 && !QTAILQ_EMPTY(&pool->request_list)); +- if (ret == -1 || pool->stopping) { ++ } while (back_to_sleep(pool, ret)); ++ if (ret == -1 || pool->stopping || ++ pool->cur_threads > pool->max_threads) { + break; + } + +@@ -294,6 +313,33 @@ void thread_pool_submit(ThreadPool *pool, ThreadPoolFunc *func, void *arg) + thread_pool_submit_aio(pool, func, arg, NULL, NULL); + } + ++void thread_pool_update_params(ThreadPool *pool, AioContext *ctx) ++{ ++ qemu_mutex_lock(&pool->lock); ++ ++ pool->min_threads = ctx->thread_pool_min; ++ pool->max_threads = ctx->thread_pool_max; ++ ++ /* ++ * We either have to: ++ * - Increase the number available of threads until over the min_threads ++ * threshold. ++ * - Decrease the number of available threads until under the max_threads ++ * threshold. ++ * - Do nothing. The current number of threads fall in between the min and ++ * max thresholds. We'll let the pool manage itself. ++ */ ++ for (int i = pool->cur_threads; i < pool->min_threads; i++) { ++ spawn_thread(pool); ++ } ++ ++ for (int i = pool->cur_threads; i > pool->max_threads; i--) { ++ qemu_sem_post(&pool->sem); ++ } ++ ++ qemu_mutex_unlock(&pool->lock); ++} ++ + static void thread_pool_init_one(ThreadPool *pool, AioContext *ctx) + { + if (!ctx) { +@@ -306,11 +352,12 @@ static void thread_pool_init_one(ThreadPool *pool, AioContext *ctx) + qemu_mutex_init(&pool->lock); + qemu_cond_init(&pool->worker_stopped); + qemu_sem_init(&pool->sem, 0); +- pool->max_threads = 64; + pool->new_thread_bh = aio_bh_new(ctx, spawn_thread_bh_fn, pool); + + QLIST_INIT(&pool->head); + QTAILQ_INIT(&pool->request_list); ++ ++ thread_pool_update_params(pool, ctx); + } + + ThreadPool *thread_pool_new(AioContext *ctx) +-- +2.31.1 + diff --git a/SOURCES/kvm-util-main-loop-Introduce-the-main-loop-into-QOM.patch b/SOURCES/kvm-util-main-loop-Introduce-the-main-loop-into-QOM.patch new file mode 100644 index 0000000..2104424 --- /dev/null +++ b/SOURCES/kvm-util-main-loop-Introduce-the-main-loop-into-QOM.patch @@ -0,0 +1,233 @@ +From b4969662de01848f887a3918e97e516efc213f71 Mon Sep 17 00:00:00 2001 +From: Nicolas Saenz Julienne +Date: Mon, 25 Apr 2022 09:57:22 +0200 +Subject: [PATCH 02/16] util/main-loop: Introduce the main loop into QOM + +RH-Author: Nicolas Saenz Julienne +RH-MergeRequest: 93: util/thread-pool: Expose minimum and maximum size +RH-Commit: [2/3] a481b77e25ad50d13dcbe26b36c551b18c89bddd +RH-Bugzilla: 2031024 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Stefan Hajnoczi + +'event-loop-base' provides basic property handling for all 'AioContext' +based event loops. So let's define a new 'MainLoopClass' that inherits +from it. This will permit tweaking the main loop's properties through +qapi as well as through the command line using the '-object' keyword[1]. +Only one instance of 'MainLoopClass' might be created at any time. + +'EventLoopBaseClass' learns a new callback, 'can_be_deleted()' so as to +mark 'MainLoop' as non-deletable. + +[1] For example: + -object main-loop,id=main-loop,aio-max-batch= + +Signed-off-by: Nicolas Saenz Julienne +Reviewed-by: Stefan Hajnoczi +Acked-by: Markus Armbruster +Message-id: 20220425075723.20019-3-nsaenzju@redhat.com +Signed-off-by: Stefan Hajnoczi +(cherry picked from commit 70ac26b9e5ca8374bb3ef3f30b871726673c9f27) +--- + event-loop-base.c | 13 ++++++++ + include/qemu/main-loop.h | 10 ++++++ + include/sysemu/event-loop-base.h | 1 + + meson.build | 3 +- + qapi/qom.json | 13 ++++++++ + util/main-loop.c | 56 ++++++++++++++++++++++++++++++++ + 6 files changed, 95 insertions(+), 1 deletion(-) + +diff --git a/event-loop-base.c b/event-loop-base.c +index a924c73a7c..e7f99a6ec8 100644 +--- a/event-loop-base.c ++++ b/event-loop-base.c +@@ -73,10 +73,23 @@ static void event_loop_base_complete(UserCreatable *uc, Error **errp) + } + } + ++static bool event_loop_base_can_be_deleted(UserCreatable *uc) ++{ ++ EventLoopBaseClass *bc = EVENT_LOOP_BASE_GET_CLASS(uc); ++ EventLoopBase *backend = EVENT_LOOP_BASE(uc); ++ ++ if (bc->can_be_deleted) { ++ return bc->can_be_deleted(backend); ++ } ++ ++ return true; ++} ++ + static void event_loop_base_class_init(ObjectClass *klass, void *class_data) + { + UserCreatableClass *ucc = USER_CREATABLE_CLASS(klass); + ucc->complete = event_loop_base_complete; ++ ucc->can_be_deleted = event_loop_base_can_be_deleted; + + object_class_property_add(klass, "aio-max-batch", "int", + event_loop_base_get_param, +diff --git a/include/qemu/main-loop.h b/include/qemu/main-loop.h +index d3750c8e76..20c9387654 100644 +--- a/include/qemu/main-loop.h ++++ b/include/qemu/main-loop.h +@@ -26,9 +26,19 @@ + #define QEMU_MAIN_LOOP_H + + #include "block/aio.h" ++#include "qom/object.h" ++#include "sysemu/event-loop-base.h" + + #define SIG_IPI SIGUSR1 + ++#define TYPE_MAIN_LOOP "main-loop" ++OBJECT_DECLARE_TYPE(MainLoop, MainLoopClass, MAIN_LOOP) ++ ++struct MainLoop { ++ EventLoopBase parent_obj; ++}; ++typedef struct MainLoop MainLoop; ++ + /** + * qemu_init_main_loop: Set up the process so that it can run the main loop. + * +diff --git a/include/sysemu/event-loop-base.h b/include/sysemu/event-loop-base.h +index 8e77d8b69f..fced4c9fea 100644 +--- a/include/sysemu/event-loop-base.h ++++ b/include/sysemu/event-loop-base.h +@@ -25,6 +25,7 @@ struct EventLoopBaseClass { + + void (*init)(EventLoopBase *base, Error **errp); + void (*update_params)(EventLoopBase *base, Error **errp); ++ bool (*can_be_deleted)(EventLoopBase *base); + }; + + struct EventLoopBase { +diff --git a/meson.build b/meson.build +index b9c919a55e..5a7c10e639 100644 +--- a/meson.build ++++ b/meson.build +@@ -2832,7 +2832,8 @@ libqemuutil = static_library('qemuutil', + sources: util_ss.sources() + stub_ss.sources() + genh, + dependencies: [util_ss.dependencies(), libm, threads, glib, socket, malloc, pixman]) + qemuutil = declare_dependency(link_with: libqemuutil, +- sources: genh + version_res) ++ sources: genh + version_res, ++ dependencies: [event_loop_base]) + + if have_system or have_user + decodetree = generator(find_program('scripts/decodetree.py'), +diff --git a/qapi/qom.json b/qapi/qom.json +index a2439533c5..7d4a2ac1b9 100644 +--- a/qapi/qom.json ++++ b/qapi/qom.json +@@ -540,6 +540,17 @@ + '*poll-grow': 'int', + '*poll-shrink': 'int' } } + ++## ++# @MainLoopProperties: ++# ++# Properties for the main-loop object. ++# ++# Since: 7.1 ++## ++{ 'struct': 'MainLoopProperties', ++ 'base': 'EventLoopBaseProperties', ++ 'data': {} } ++ + ## + # @MemoryBackendProperties: + # +@@ -830,6 +841,7 @@ + { 'name': 'input-linux', + 'if': 'CONFIG_LINUX' }, + 'iothread', ++ 'main-loop', + { 'name': 'memory-backend-epc', + 'if': 'CONFIG_LINUX' }, + 'memory-backend-file', +@@ -895,6 +907,7 @@ + 'input-linux': { 'type': 'InputLinuxProperties', + 'if': 'CONFIG_LINUX' }, + 'iothread': 'IothreadProperties', ++ 'main-loop': 'MainLoopProperties', + 'memory-backend-epc': { 'type': 'MemoryBackendEpcProperties', + 'if': 'CONFIG_LINUX' }, + 'memory-backend-file': 'MemoryBackendFileProperties', +diff --git a/util/main-loop.c b/util/main-loop.c +index b7b0ce4ca0..5b13f456fa 100644 +--- a/util/main-loop.c ++++ b/util/main-loop.c +@@ -33,6 +33,7 @@ + #include "qemu/error-report.h" + #include "qemu/queue.h" + #include "qemu/compiler.h" ++#include "qom/object.h" + + #ifndef _WIN32 + #include +@@ -184,6 +185,61 @@ int qemu_init_main_loop(Error **errp) + return 0; + } + ++static void main_loop_update_params(EventLoopBase *base, Error **errp) ++{ ++ if (!qemu_aio_context) { ++ error_setg(errp, "qemu aio context not ready"); ++ return; ++ } ++ ++ aio_context_set_aio_params(qemu_aio_context, base->aio_max_batch, errp); ++} ++ ++MainLoop *mloop; ++ ++static void main_loop_init(EventLoopBase *base, Error **errp) ++{ ++ MainLoop *m = MAIN_LOOP(base); ++ ++ if (mloop) { ++ error_setg(errp, "only one main-loop instance allowed"); ++ return; ++ } ++ ++ main_loop_update_params(base, errp); ++ ++ mloop = m; ++ return; ++} ++ ++static bool main_loop_can_be_deleted(EventLoopBase *base) ++{ ++ return false; ++} ++ ++static void main_loop_class_init(ObjectClass *oc, void *class_data) ++{ ++ EventLoopBaseClass *bc = EVENT_LOOP_BASE_CLASS(oc); ++ ++ bc->init = main_loop_init; ++ bc->update_params = main_loop_update_params; ++ bc->can_be_deleted = main_loop_can_be_deleted; ++} ++ ++static const TypeInfo main_loop_info = { ++ .name = TYPE_MAIN_LOOP, ++ .parent = TYPE_EVENT_LOOP_BASE, ++ .class_init = main_loop_class_init, ++ .instance_size = sizeof(MainLoop), ++}; ++ ++static void main_loop_register_types(void) ++{ ++ type_register_static(&main_loop_info); ++} ++ ++type_init(main_loop_register_types) ++ + static int max_priority; + + #ifndef _WIN32 +-- +2.31.1 + diff --git a/SOURCES/kvm-vdpa-Add-device-migration-blocker.patch b/SOURCES/kvm-vdpa-Add-device-migration-blocker.patch new file mode 100644 index 0000000..1b83c98 --- /dev/null +++ b/SOURCES/kvm-vdpa-Add-device-migration-blocker.patch @@ -0,0 +1,106 @@ +From 8e0fdce814af4cfc84dce5e5920da989b1f1a86d Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Thu, 21 Jul 2022 16:06:05 +0200 +Subject: [PATCH 26/32] vdpa: Add device migration blocker +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 108: Net Control Virtqueue shadow Support +RH-Commit: [26/27] 53d94d45b5e5e88f12b95f9b0f243696cfcbd7ce (eperezmartin/qemu-kvm) +RH-Bugzilla: 1939363 +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Cindy Lu +RH-Acked-by: Laurent Vivier + +Bugzilla: https://bugzilla.redhat.com/1939363 + +Upstream Status: git://git.qemu.org/qemu.git + +commit c156d5bf2b142dcc06808ccee06882144f230aec +Author: Eugenio Pérez +Date: Wed Jul 20 08:59:45 2022 +0200 + + vdpa: Add device migration blocker + + Since the vhost-vdpa device is exposing _F_LOG, adding a migration blocker if + it uses CVQ. + + However, qemu is able to migrate simple devices with no CVQ as long as + they use SVQ. To allow it, add a placeholder error to vhost_vdpa, and + only add to vhost_dev when used. vhost_dev machinery place the migration + blocker if needed. + + Signed-off-by: Eugenio Pérez + Reviewed-by: Michael S. Tsirkin + Signed-off-by: Jason Wang + +Signed-off-by: Eugenio Pérez +--- + hw/virtio/vhost-vdpa.c | 15 +++++++++++++++ + include/hw/virtio/vhost-vdpa.h | 1 + + 2 files changed, 16 insertions(+) + +diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c +index 49effe5462..e3e5bce4bb 100644 +--- a/hw/virtio/vhost-vdpa.c ++++ b/hw/virtio/vhost-vdpa.c +@@ -20,6 +20,7 @@ + #include "hw/virtio/vhost-shadow-virtqueue.h" + #include "hw/virtio/vhost-vdpa.h" + #include "exec/address-spaces.h" ++#include "migration/blocker.h" + #include "qemu/main-loop.h" + #include "cpu.h" + #include "trace.h" +@@ -1020,6 +1021,13 @@ static bool vhost_vdpa_svqs_start(struct vhost_dev *dev) + return true; + } + ++ if (v->migration_blocker) { ++ int r = migrate_add_blocker(v->migration_blocker, &err); ++ if (unlikely(r < 0)) { ++ return false; ++ } ++ } ++ + for (i = 0; i < v->shadow_vqs->len; ++i) { + VirtQueue *vq = virtio_get_queue(dev->vdev, dev->vq_index + i); + VhostShadowVirtqueue *svq = g_ptr_array_index(v->shadow_vqs, i); +@@ -1062,6 +1070,10 @@ err: + vhost_svq_stop(svq); + } + ++ if (v->migration_blocker) { ++ migrate_del_blocker(v->migration_blocker); ++ } ++ + return false; + } + +@@ -1081,6 +1093,9 @@ static bool vhost_vdpa_svqs_stop(struct vhost_dev *dev) + } + } + ++ if (v->migration_blocker) { ++ migrate_del_blocker(v->migration_blocker); ++ } + return true; + } + +diff --git a/include/hw/virtio/vhost-vdpa.h b/include/hw/virtio/vhost-vdpa.h +index 1111d85643..d10a89303e 100644 +--- a/include/hw/virtio/vhost-vdpa.h ++++ b/include/hw/virtio/vhost-vdpa.h +@@ -35,6 +35,7 @@ typedef struct vhost_vdpa { + bool shadow_vqs_enabled; + /* IOVA mapping used by the Shadow Virtqueue */ + VhostIOVATree *iova_tree; ++ Error *migration_blocker; + GPtrArray *shadow_vqs; + const VhostShadowVirtqueueOps *shadow_vq_ops; + void *shadow_vq_ops_opaque; +-- +2.31.1 + diff --git a/SOURCES/kvm-vdpa-Add-virtio-net-mac-address-via-CVQ-at-start.patch b/SOURCES/kvm-vdpa-Add-virtio-net-mac-address-via-CVQ-at-start.patch new file mode 100644 index 0000000..4dede70 --- /dev/null +++ b/SOURCES/kvm-vdpa-Add-virtio-net-mac-address-via-CVQ-at-start.patch @@ -0,0 +1,87 @@ +From e1f9986cf77e4b2f16aca7b2523bc75bae0c4d3c Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Tue, 23 Aug 2022 20:30:36 +0200 +Subject: [PATCH 21/23] vdpa: Add virtio-net mac address via CVQ at start +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 116: vdpa: Restore device state on destination +RH-Bugzilla: 2114060 +RH-Acked-by: Cindy Lu +RH-Acked-by: Miroslav Rezanina +RH-Commit: [20/21] a7920816d5faf7a0cfbb7c2731a48ddfc456b8d4 (eperezmartin/qemu-kvm) +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2114060 +Upstream status: git@github.com:jasowang/qemu.git net-next + +This is needed so the destination vdpa device see the same state a the +guest set in the source. + +Signed-off-by: Eugenio Pérez +Acked-by: Jason Wang +Signed-off-by: Jason Wang +(cherry picked from commit f34cd09b13855657a0d49c5ea6a1e37ba9dc2334) +--- + net/vhost-vdpa.c | 40 ++++++++++++++++++++++++++++++++++++++++ + 1 file changed, 40 insertions(+) + +diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c +index f09f044ec1..79ebda7de1 100644 +--- a/net/vhost-vdpa.c ++++ b/net/vhost-vdpa.c +@@ -363,11 +363,51 @@ static ssize_t vhost_vdpa_net_cvq_add(VhostVDPAState *s, size_t out_len, + return vhost_svq_poll(svq); + } + ++static int vhost_vdpa_net_load(NetClientState *nc) ++{ ++ VhostVDPAState *s = DO_UPCAST(VhostVDPAState, nc, nc); ++ const struct vhost_vdpa *v = &s->vhost_vdpa; ++ const VirtIONet *n; ++ uint64_t features; ++ ++ assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_VDPA); ++ ++ if (!v->shadow_vqs_enabled) { ++ return 0; ++ } ++ ++ n = VIRTIO_NET(v->dev->vdev); ++ features = n->parent_obj.guest_features; ++ if (features & BIT_ULL(VIRTIO_NET_F_CTRL_MAC_ADDR)) { ++ const struct virtio_net_ctrl_hdr ctrl = { ++ .class = VIRTIO_NET_CTRL_MAC, ++ .cmd = VIRTIO_NET_CTRL_MAC_ADDR_SET, ++ }; ++ char *cursor = s->cvq_cmd_out_buffer; ++ ssize_t dev_written; ++ ++ memcpy(cursor, &ctrl, sizeof(ctrl)); ++ cursor += sizeof(ctrl); ++ memcpy(cursor, n->mac, sizeof(n->mac)); ++ ++ dev_written = vhost_vdpa_net_cvq_add(s, sizeof(ctrl) + sizeof(n->mac), ++ sizeof(virtio_net_ctrl_ack)); ++ if (unlikely(dev_written < 0)) { ++ return dev_written; ++ } ++ ++ return *((virtio_net_ctrl_ack *)s->cvq_cmd_in_buffer) != VIRTIO_NET_OK; ++ } ++ ++ return 0; ++} ++ + static NetClientInfo net_vhost_vdpa_cvq_info = { + .type = NET_CLIENT_DRIVER_VHOST_VDPA, + .size = sizeof(VhostVDPAState), + .receive = vhost_vdpa_receive, + .start = vhost_vdpa_net_cvq_start, ++ .load = vhost_vdpa_net_load, + .stop = vhost_vdpa_net_cvq_stop, + .cleanup = vhost_vdpa_cleanup, + .has_vnet_hdr = vhost_vdpa_has_vnet_hdr, +-- +2.31.1 + diff --git a/SOURCES/kvm-vdpa-Add-x-svq-to-NetdevVhostVDPAOptions.patch b/SOURCES/kvm-vdpa-Add-x-svq-to-NetdevVhostVDPAOptions.patch new file mode 100644 index 0000000..8a7b600 --- /dev/null +++ b/SOURCES/kvm-vdpa-Add-x-svq-to-NetdevVhostVDPAOptions.patch @@ -0,0 +1,223 @@ +From 0b27781f9984c67625c49a516c3e38fbf5fa1b1b Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Thu, 21 Jul 2022 16:06:16 +0200 +Subject: [PATCH 27/32] vdpa: Add x-svq to NetdevVhostVDPAOptions +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 108: Net Control Virtqueue shadow Support +RH-Commit: [27/27] bd85496c2a8c1ebf34f908fca2be2ab9852fd0e9 (eperezmartin/qemu-kvm) +RH-Bugzilla: 1939363 +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Cindy Lu +RH-Acked-by: Laurent Vivier + +Bugzilla: https://bugzilla.redhat.com/1939363 + +Upstream Status: git://git.qemu.org/qemu.git + +commit 1576dbb5bbc49344c606e969ec749be70c0fd94e +Author: Eugenio Pérez +Date: Wed Jul 20 08:59:46 2022 +0200 + + vdpa: Add x-svq to NetdevVhostVDPAOptions + + Finally offering the possibility to enable SVQ from the command line. + + Signed-off-by: Eugenio Pérez + Acked-by: Markus Armbruster + Reviewed-by: Michael S. Tsirkin + Signed-off-by: Jason Wang + +Signed-off-by: Eugenio Pérez +--- + net/vhost-vdpa.c | 72 ++++++++++++++++++++++++++++++++++++++++++++++-- + qapi/net.json | 9 +++++- + 2 files changed, 77 insertions(+), 4 deletions(-) + +diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c +index 8b76dac966..50672bcd66 100644 +--- a/net/vhost-vdpa.c ++++ b/net/vhost-vdpa.c +@@ -75,6 +75,28 @@ const int vdpa_feature_bits[] = { + VHOST_INVALID_FEATURE_BIT + }; + ++/** Supported device specific feature bits with SVQ */ ++static const uint64_t vdpa_svq_device_features = ++ BIT_ULL(VIRTIO_NET_F_CSUM) | ++ BIT_ULL(VIRTIO_NET_F_GUEST_CSUM) | ++ BIT_ULL(VIRTIO_NET_F_MTU) | ++ BIT_ULL(VIRTIO_NET_F_MAC) | ++ BIT_ULL(VIRTIO_NET_F_GUEST_TSO4) | ++ BIT_ULL(VIRTIO_NET_F_GUEST_TSO6) | ++ BIT_ULL(VIRTIO_NET_F_GUEST_ECN) | ++ BIT_ULL(VIRTIO_NET_F_GUEST_UFO) | ++ BIT_ULL(VIRTIO_NET_F_HOST_TSO4) | ++ BIT_ULL(VIRTIO_NET_F_HOST_TSO6) | ++ BIT_ULL(VIRTIO_NET_F_HOST_ECN) | ++ BIT_ULL(VIRTIO_NET_F_HOST_UFO) | ++ BIT_ULL(VIRTIO_NET_F_MRG_RXBUF) | ++ BIT_ULL(VIRTIO_NET_F_STATUS) | ++ BIT_ULL(VIRTIO_NET_F_CTRL_VQ) | ++ BIT_ULL(VIRTIO_F_ANY_LAYOUT) | ++ BIT_ULL(VIRTIO_NET_F_CTRL_MAC_ADDR) | ++ BIT_ULL(VIRTIO_NET_F_RSC_EXT) | ++ BIT_ULL(VIRTIO_NET_F_STANDBY); ++ + VHostNetState *vhost_vdpa_get_vhost_net(NetClientState *nc) + { + VhostVDPAState *s = DO_UPCAST(VhostVDPAState, nc, nc); +@@ -133,9 +155,13 @@ err_init: + static void vhost_vdpa_cleanup(NetClientState *nc) + { + VhostVDPAState *s = DO_UPCAST(VhostVDPAState, nc, nc); ++ struct vhost_dev *dev = &s->vhost_net->dev; + + qemu_vfree(s->cvq_cmd_out_buffer); + qemu_vfree(s->cvq_cmd_in_buffer); ++ if (dev->vq_index + dev->nvqs == dev->vq_index_end) { ++ g_clear_pointer(&s->vhost_vdpa.iova_tree, vhost_iova_tree_delete); ++ } + if (s->vhost_net) { + vhost_net_cleanup(s->vhost_net); + g_free(s->vhost_net); +@@ -437,7 +463,9 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer, + int vdpa_device_fd, + int queue_pair_index, + int nvqs, +- bool is_datapath) ++ bool is_datapath, ++ bool svq, ++ VhostIOVATree *iova_tree) + { + NetClientState *nc = NULL; + VhostVDPAState *s; +@@ -455,6 +483,8 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer, + + s->vhost_vdpa.device_fd = vdpa_device_fd; + s->vhost_vdpa.index = queue_pair_index; ++ s->vhost_vdpa.shadow_vqs_enabled = svq; ++ s->vhost_vdpa.iova_tree = iova_tree; + if (!is_datapath) { + s->cvq_cmd_out_buffer = qemu_memalign(qemu_real_host_page_size, + vhost_vdpa_net_cvq_cmd_page_len()); +@@ -465,6 +495,8 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer, + + s->vhost_vdpa.shadow_vq_ops = &vhost_vdpa_net_svq_ops; + s->vhost_vdpa.shadow_vq_ops_opaque = s; ++ error_setg(&s->vhost_vdpa.migration_blocker, ++ "Migration disabled: vhost-vdpa uses CVQ."); + } + ret = vhost_vdpa_add(nc, (void *)&s->vhost_vdpa, queue_pair_index, nvqs); + if (ret) { +@@ -474,6 +506,14 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer, + return nc; + } + ++static int vhost_vdpa_get_iova_range(int fd, ++ struct vhost_vdpa_iova_range *iova_range) ++{ ++ int ret = ioctl(fd, VHOST_VDPA_GET_IOVA_RANGE, iova_range); ++ ++ return ret < 0 ? -errno : 0; ++} ++ + static int vhost_vdpa_get_features(int fd, uint64_t *features, Error **errp) + { + int ret = ioctl(fd, VHOST_GET_FEATURES, features); +@@ -524,6 +564,7 @@ int net_init_vhost_vdpa(const Netdev *netdev, const char *name, + uint64_t features; + int vdpa_device_fd; + g_autofree NetClientState **ncs = NULL; ++ g_autoptr(VhostIOVATree) iova_tree = NULL; + NetClientState *nc; + int queue_pairs, r, i, has_cvq = 0; + +@@ -551,22 +592,45 @@ int net_init_vhost_vdpa(const Netdev *netdev, const char *name, + return queue_pairs; + } + ++ if (opts->x_svq) { ++ struct vhost_vdpa_iova_range iova_range; ++ ++ uint64_t invalid_dev_features = ++ features & ~vdpa_svq_device_features & ++ /* Transport are all accepted at this point */ ++ ~MAKE_64BIT_MASK(VIRTIO_TRANSPORT_F_START, ++ VIRTIO_TRANSPORT_F_END - VIRTIO_TRANSPORT_F_START); ++ ++ if (invalid_dev_features) { ++ error_setg(errp, "vdpa svq does not work with features 0x%" PRIx64, ++ invalid_dev_features); ++ goto err_svq; ++ } ++ ++ vhost_vdpa_get_iova_range(vdpa_device_fd, &iova_range); ++ iova_tree = vhost_iova_tree_new(iova_range.first, iova_range.last); ++ } ++ + ncs = g_malloc0(sizeof(*ncs) * queue_pairs); + + for (i = 0; i < queue_pairs; i++) { + ncs[i] = net_vhost_vdpa_init(peer, TYPE_VHOST_VDPA, name, +- vdpa_device_fd, i, 2, true); ++ vdpa_device_fd, i, 2, true, opts->x_svq, ++ iova_tree); + if (!ncs[i]) + goto err; + } + + if (has_cvq) { + nc = net_vhost_vdpa_init(peer, TYPE_VHOST_VDPA, name, +- vdpa_device_fd, i, 1, false); ++ vdpa_device_fd, i, 1, false, ++ opts->x_svq, iova_tree); + if (!nc) + goto err; + } + ++ /* iova_tree ownership belongs to last NetClientState */ ++ g_steal_pointer(&iova_tree); + return 0; + + err: +@@ -575,6 +639,8 @@ err: + qemu_del_net_client(ncs[i]); + } + } ++ ++err_svq: + qemu_close(vdpa_device_fd); + + return -1; +diff --git a/qapi/net.json b/qapi/net.json +index b92f3f5fb4..92848e4362 100644 +--- a/qapi/net.json ++++ b/qapi/net.json +@@ -445,12 +445,19 @@ + # @queues: number of queues to be created for multiqueue vhost-vdpa + # (default: 1) + # ++# @x-svq: Start device with (experimental) shadow virtqueue. (Since 7.1) ++# (default: false) ++# ++# Features: ++# @unstable: Member @x-svq is experimental. ++# + # Since: 5.1 + ## + { 'struct': 'NetdevVhostVDPAOptions', + 'data': { + '*vhostdev': 'str', +- '*queues': 'int' } } ++ '*queues': 'int', ++ '*x-svq': {'type': 'bool', 'features' : [ 'unstable'] } } } + + ## + # @NetClientDriver: +-- +2.31.1 + diff --git a/SOURCES/kvm-vdpa-Avoid-compiler-to-squash-reads-to-used-idx.patch b/SOURCES/kvm-vdpa-Avoid-compiler-to-squash-reads-to-used-idx.patch new file mode 100644 index 0000000..acd45e0 --- /dev/null +++ b/SOURCES/kvm-vdpa-Avoid-compiler-to-squash-reads-to-used-idx.patch @@ -0,0 +1,65 @@ +From df06ce560ddfefde98bef822ec2020382059921f Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Thu, 21 Jul 2022 15:38:55 +0200 +Subject: [PATCH 10/32] vdpa: Avoid compiler to squash reads to used idx +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 108: Net Control Virtqueue shadow Support +RH-Commit: [10/27] b28789302d4f64749da26f413763f918161d9b70 (eperezmartin/qemu-kvm) +RH-Bugzilla: 1939363 +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Cindy Lu +RH-Acked-by: Laurent Vivier + +Bugzilla: https://bugzilla.redhat.com/1939363 + +Upstream Status: git://git.qemu.org/qemu.git + +commit c381abc37f0aba42ed2e3b41cdace8f8438829e4 +Author: Eugenio Pérez +Date: Wed Jul 20 08:59:29 2022 +0200 + + vdpa: Avoid compiler to squash reads to used idx + + In the next patch we will allow busypolling of this value. The compiler + have a running path where shadow_used_idx, last_used_idx, and vring used + idx are not modified within the same thread busypolling. + + This was not an issue before since we always cleared device event + notifier before checking it, and that could act as memory barrier. + However, the busypoll needs something similar to kernel READ_ONCE. + + Let's add it here, sepparated from the polling. + + Signed-off-by: Eugenio Pérez + Signed-off-by: Jason Wang + +Signed-off-by: Eugenio Pérez +--- + hw/virtio/vhost-shadow-virtqueue.c | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +diff --git a/hw/virtio/vhost-shadow-virtqueue.c b/hw/virtio/vhost-shadow-virtqueue.c +index 3fbda1e3d4..9c46c3a8fa 100644 +--- a/hw/virtio/vhost-shadow-virtqueue.c ++++ b/hw/virtio/vhost-shadow-virtqueue.c +@@ -327,11 +327,12 @@ static void vhost_handle_guest_kick_notifier(EventNotifier *n) + + static bool vhost_svq_more_used(VhostShadowVirtqueue *svq) + { ++ uint16_t *used_idx = &svq->vring.used->idx; + if (svq->last_used_idx != svq->shadow_used_idx) { + return true; + } + +- svq->shadow_used_idx = cpu_to_le16(svq->vring.used->idx); ++ svq->shadow_used_idx = cpu_to_le16(*(volatile uint16_t *)used_idx); + + return svq->last_used_idx != svq->shadow_used_idx; + } +-- +2.31.1 + diff --git a/SOURCES/kvm-vdpa-Buffer-CVQ-support-on-shadow-virtqueue.patch b/SOURCES/kvm-vdpa-Buffer-CVQ-support-on-shadow-virtqueue.patch new file mode 100644 index 0000000..243aec8 --- /dev/null +++ b/SOURCES/kvm-vdpa-Buffer-CVQ-support-on-shadow-virtqueue.patch @@ -0,0 +1,323 @@ +From 881945094c0e4d33614d40959bfc20e395f5a478 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Thu, 21 Jul 2022 16:05:40 +0200 +Subject: [PATCH 24/32] vdpa: Buffer CVQ support on shadow virtqueue +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 108: Net Control Virtqueue shadow Support +RH-Commit: [24/27] 5486f80141a3ad968a32e782bdcdead32f417352 (eperezmartin/qemu-kvm) +RH-Bugzilla: 1939363 +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Cindy Lu +RH-Acked-by: Laurent Vivier + +Bugzilla: https://bugzilla.redhat.com/1939363 + +Upstream Status: git://git.qemu.org/qemu.git + +commit 2df4dd31e194c94da7d28c02e92449f4a989fca9 +Author: Eugenio Pérez +Date: Wed Jul 20 08:59:43 2022 +0200 + + vdpa: Buffer CVQ support on shadow virtqueue + + Introduce the control virtqueue support for vDPA shadow virtqueue. This + is needed for advanced networking features like rx filtering. + + Virtio-net control VQ copies the descriptors to qemu's VA, so we avoid + TOCTOU with the guest's or device's memory every time there is a device + model change. Otherwise, the guest could change the memory content in + the time between qemu and the device read it. + + To demonstrate command handling, VIRTIO_NET_F_CTRL_MACADDR is + implemented. If the virtio-net driver changes MAC the virtio-net device + model will be updated with the new one, and a rx filtering change event + will be raised. + + More cvq commands could be added here straightforwardly but they have + not been tested. + + Signed-off-by: Eugenio Pérez + Reviewed-by: Michael S. Tsirkin + Signed-off-by: Jason Wang + +Signed-off-by: Eugenio Pérez +--- + net/vhost-vdpa.c | 213 +++++++++++++++++++++++++++++++++++++++++++++-- + 1 file changed, 205 insertions(+), 8 deletions(-) + +diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c +index 2e3b6b10d8..df42822463 100644 +--- a/net/vhost-vdpa.c ++++ b/net/vhost-vdpa.c +@@ -33,6 +33,9 @@ typedef struct VhostVDPAState { + NetClientState nc; + struct vhost_vdpa vhost_vdpa; + VHostNetState *vhost_net; ++ ++ /* Control commands shadow buffers */ ++ void *cvq_cmd_out_buffer, *cvq_cmd_in_buffer; + bool started; + } VhostVDPAState; + +@@ -131,6 +134,8 @@ static void vhost_vdpa_cleanup(NetClientState *nc) + { + VhostVDPAState *s = DO_UPCAST(VhostVDPAState, nc, nc); + ++ qemu_vfree(s->cvq_cmd_out_buffer); ++ qemu_vfree(s->cvq_cmd_in_buffer); + if (s->vhost_net) { + vhost_net_cleanup(s->vhost_net); + g_free(s->vhost_net); +@@ -190,24 +195,191 @@ static NetClientInfo net_vhost_vdpa_info = { + .check_peer_type = vhost_vdpa_check_peer_type, + }; + ++static void vhost_vdpa_cvq_unmap_buf(struct vhost_vdpa *v, void *addr) ++{ ++ VhostIOVATree *tree = v->iova_tree; ++ DMAMap needle = { ++ /* ++ * No need to specify size or to look for more translations since ++ * this contiguous chunk was allocated by us. ++ */ ++ .translated_addr = (hwaddr)(uintptr_t)addr, ++ }; ++ const DMAMap *map = vhost_iova_tree_find_iova(tree, &needle); ++ int r; ++ ++ if (unlikely(!map)) { ++ error_report("Cannot locate expected map"); ++ return; ++ } ++ ++ r = vhost_vdpa_dma_unmap(v, map->iova, map->size + 1); ++ if (unlikely(r != 0)) { ++ error_report("Device cannot unmap: %s(%d)", g_strerror(r), r); ++ } ++ ++ vhost_iova_tree_remove(tree, map); ++} ++ ++static size_t vhost_vdpa_net_cvq_cmd_len(void) ++{ ++ /* ++ * MAC_TABLE_SET is the ctrl command that produces the longer out buffer. ++ * In buffer is always 1 byte, so it should fit here ++ */ ++ return sizeof(struct virtio_net_ctrl_hdr) + ++ 2 * sizeof(struct virtio_net_ctrl_mac) + ++ MAC_TABLE_ENTRIES * ETH_ALEN; ++} ++ ++static size_t vhost_vdpa_net_cvq_cmd_page_len(void) ++{ ++ return ROUND_UP(vhost_vdpa_net_cvq_cmd_len(), qemu_real_host_page_size); ++} ++ ++/** Copy and map a guest buffer. */ ++static bool vhost_vdpa_cvq_map_buf(struct vhost_vdpa *v, ++ const struct iovec *out_data, ++ size_t out_num, size_t data_len, void *buf, ++ size_t *written, bool write) ++{ ++ DMAMap map = {}; ++ int r; ++ ++ if (unlikely(!data_len)) { ++ qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid legnth of %s buffer\n", ++ __func__, write ? "in" : "out"); ++ return false; ++ } ++ ++ *written = iov_to_buf(out_data, out_num, 0, buf, data_len); ++ map.translated_addr = (hwaddr)(uintptr_t)buf; ++ map.size = vhost_vdpa_net_cvq_cmd_page_len() - 1; ++ map.perm = write ? IOMMU_RW : IOMMU_RO, ++ r = vhost_iova_tree_map_alloc(v->iova_tree, &map); ++ if (unlikely(r != IOVA_OK)) { ++ error_report("Cannot map injected element"); ++ return false; ++ } ++ ++ r = vhost_vdpa_dma_map(v, map.iova, vhost_vdpa_net_cvq_cmd_page_len(), buf, ++ !write); ++ if (unlikely(r < 0)) { ++ goto dma_map_err; ++ } ++ ++ return true; ++ ++dma_map_err: ++ vhost_iova_tree_remove(v->iova_tree, &map); ++ return false; ++} ++ + /** +- * Forward buffer for the moment. ++ * Copy the guest element into a dedicated buffer suitable to be sent to NIC ++ * ++ * @iov: [0] is the out buffer, [1] is the in one ++ */ ++static bool vhost_vdpa_net_cvq_map_elem(VhostVDPAState *s, ++ VirtQueueElement *elem, ++ struct iovec *iov) ++{ ++ size_t in_copied; ++ bool ok; ++ ++ iov[0].iov_base = s->cvq_cmd_out_buffer; ++ ok = vhost_vdpa_cvq_map_buf(&s->vhost_vdpa, elem->out_sg, elem->out_num, ++ vhost_vdpa_net_cvq_cmd_len(), iov[0].iov_base, ++ &iov[0].iov_len, false); ++ if (unlikely(!ok)) { ++ return false; ++ } ++ ++ iov[1].iov_base = s->cvq_cmd_in_buffer; ++ ok = vhost_vdpa_cvq_map_buf(&s->vhost_vdpa, NULL, 0, ++ sizeof(virtio_net_ctrl_ack), iov[1].iov_base, ++ &in_copied, true); ++ if (unlikely(!ok)) { ++ vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, s->cvq_cmd_out_buffer); ++ return false; ++ } ++ ++ iov[1].iov_len = sizeof(virtio_net_ctrl_ack); ++ return true; ++} ++ ++/** ++ * Do not forward commands not supported by SVQ. Otherwise, the device could ++ * accept it and qemu would not know how to update the device model. ++ */ ++static bool vhost_vdpa_net_cvq_validate_cmd(const struct iovec *out, ++ size_t out_num) ++{ ++ struct virtio_net_ctrl_hdr ctrl; ++ size_t n; ++ ++ n = iov_to_buf(out, out_num, 0, &ctrl, sizeof(ctrl)); ++ if (unlikely(n < sizeof(ctrl))) { ++ qemu_log_mask(LOG_GUEST_ERROR, ++ "%s: invalid legnth of out buffer %zu\n", __func__, n); ++ return false; ++ } ++ ++ switch (ctrl.class) { ++ case VIRTIO_NET_CTRL_MAC: ++ switch (ctrl.cmd) { ++ case VIRTIO_NET_CTRL_MAC_ADDR_SET: ++ return true; ++ default: ++ qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid mac cmd %u\n", ++ __func__, ctrl.cmd); ++ }; ++ break; ++ default: ++ qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid control class %u\n", ++ __func__, ctrl.class); ++ }; ++ ++ return false; ++} ++ ++/** ++ * Validate and copy control virtqueue commands. ++ * ++ * Following QEMU guidelines, we offer a copy of the buffers to the device to ++ * prevent TOCTOU bugs. + */ + static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq, + VirtQueueElement *elem, + void *opaque) + { +- unsigned int n = elem->out_num + elem->in_num; +- g_autofree struct iovec *dev_buffers = g_new(struct iovec, n); ++ VhostVDPAState *s = opaque; + size_t in_len, dev_written; + virtio_net_ctrl_ack status = VIRTIO_NET_ERR; +- int r; ++ /* out and in buffers sent to the device */ ++ struct iovec dev_buffers[2] = { ++ { .iov_base = s->cvq_cmd_out_buffer }, ++ { .iov_base = s->cvq_cmd_in_buffer }, ++ }; ++ /* in buffer used for device model */ ++ const struct iovec in = { ++ .iov_base = &status, ++ .iov_len = sizeof(status), ++ }; ++ int r = -EINVAL; ++ bool ok; ++ ++ ok = vhost_vdpa_net_cvq_map_elem(s, elem, dev_buffers); ++ if (unlikely(!ok)) { ++ goto out; ++ } + +- memcpy(dev_buffers, elem->out_sg, elem->out_num); +- memcpy(dev_buffers + elem->out_num, elem->in_sg, elem->in_num); ++ ok = vhost_vdpa_net_cvq_validate_cmd(&dev_buffers[0], 1); ++ if (unlikely(!ok)) { ++ goto out; ++ } + +- r = vhost_svq_add(svq, &dev_buffers[0], elem->out_num, &dev_buffers[1], +- elem->in_num, elem); ++ r = vhost_svq_add(svq, &dev_buffers[0], 1, &dev_buffers[1], 1, elem); + if (unlikely(r != 0)) { + if (unlikely(r == -ENOSPC)) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: No space on device queue\n", +@@ -224,6 +396,18 @@ static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq, + dev_written = vhost_svq_poll(svq); + if (unlikely(dev_written < sizeof(status))) { + error_report("Insufficient written data (%zu)", dev_written); ++ goto out; ++ } ++ ++ memcpy(&status, dev_buffers[1].iov_base, sizeof(status)); ++ if (status != VIRTIO_NET_OK) { ++ goto out; ++ } ++ ++ status = VIRTIO_NET_ERR; ++ virtio_net_handle_ctrl_iov(svq->vdev, &in, 1, dev_buffers, 1); ++ if (status != VIRTIO_NET_OK) { ++ error_report("Bad CVQ processing in model"); + } + + out: +@@ -234,6 +418,12 @@ out: + } + vhost_svq_push_elem(svq, elem, MIN(in_len, sizeof(status))); + g_free(elem); ++ if (dev_buffers[0].iov_base) { ++ vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, dev_buffers[0].iov_base); ++ } ++ if (dev_buffers[1].iov_base) { ++ vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, dev_buffers[1].iov_base); ++ } + return r; + } + +@@ -266,6 +456,13 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer, + s->vhost_vdpa.device_fd = vdpa_device_fd; + s->vhost_vdpa.index = queue_pair_index; + if (!is_datapath) { ++ s->cvq_cmd_out_buffer = qemu_memalign(qemu_real_host_page_size, ++ vhost_vdpa_net_cvq_cmd_page_len()); ++ memset(s->cvq_cmd_out_buffer, 0, vhost_vdpa_net_cvq_cmd_page_len()); ++ s->cvq_cmd_in_buffer = qemu_memalign(qemu_real_host_page_size, ++ vhost_vdpa_net_cvq_cmd_page_len()); ++ memset(s->cvq_cmd_in_buffer, 0, vhost_vdpa_net_cvq_cmd_page_len()); ++ + s->vhost_vdpa.shadow_vq_ops = &vhost_vdpa_net_svq_ops; + s->vhost_vdpa.shadow_vq_ops_opaque = s; + } +-- +2.31.1 + diff --git a/SOURCES/kvm-vdpa-Delete-CVQ-migration-blocker.patch b/SOURCES/kvm-vdpa-Delete-CVQ-migration-blocker.patch new file mode 100644 index 0000000..87dfb5a --- /dev/null +++ b/SOURCES/kvm-vdpa-Delete-CVQ-migration-blocker.patch @@ -0,0 +1,98 @@ +From 896f7749c72afe988ab28ac6af77b9c53b685c03 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Tue, 23 Aug 2022 20:30:37 +0200 +Subject: [PATCH 22/23] vdpa: Delete CVQ migration blocker +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 116: vdpa: Restore device state on destination +RH-Bugzilla: 2114060 +RH-Acked-by: Cindy Lu +RH-Acked-by: Miroslav Rezanina +RH-Commit: [21/21] 286f55177a132a8845c2912fb28cb4add472005a (eperezmartin/qemu-kvm) +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2114060 +Upstream status: git@github.com:jasowang/qemu.git net-next + +We can restore the device state in the destination via CVQ now. Remove +the migration blocker. + +Signed-off-by: Eugenio Pérez +Acked-by: Jason Wang +Signed-off-by: Jason Wang +(cherry picked from commit fe2b0cd71cddbec4eaf6e325eaf357a4e72a469d) +--- + hw/virtio/vhost-vdpa.c | 15 --------------- + include/hw/virtio/vhost-vdpa.h | 1 - + net/vhost-vdpa.c | 2 -- + 3 files changed, 18 deletions(-) + +diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c +index 0bea1e1eb9..b61e313953 100644 +--- a/hw/virtio/vhost-vdpa.c ++++ b/hw/virtio/vhost-vdpa.c +@@ -1031,13 +1031,6 @@ static bool vhost_vdpa_svqs_start(struct vhost_dev *dev) + return true; + } + +- if (v->migration_blocker) { +- int r = migrate_add_blocker(v->migration_blocker, &err); +- if (unlikely(r < 0)) { +- return false; +- } +- } +- + for (i = 0; i < v->shadow_vqs->len; ++i) { + VirtQueue *vq = virtio_get_queue(dev->vdev, dev->vq_index + i); + VhostShadowVirtqueue *svq = g_ptr_array_index(v->shadow_vqs, i); +@@ -1080,10 +1073,6 @@ err: + vhost_svq_stop(svq); + } + +- if (v->migration_blocker) { +- migrate_del_blocker(v->migration_blocker); +- } +- + return false; + } + +@@ -1099,10 +1088,6 @@ static void vhost_vdpa_svqs_stop(struct vhost_dev *dev) + VhostShadowVirtqueue *svq = g_ptr_array_index(v->shadow_vqs, i); + vhost_vdpa_svq_unmap_rings(dev, svq); + } +- +- if (v->migration_blocker) { +- migrate_del_blocker(v->migration_blocker); +- } + } + + static int vhost_vdpa_dev_start(struct vhost_dev *dev, bool started) +diff --git a/include/hw/virtio/vhost-vdpa.h b/include/hw/virtio/vhost-vdpa.h +index d10a89303e..1111d85643 100644 +--- a/include/hw/virtio/vhost-vdpa.h ++++ b/include/hw/virtio/vhost-vdpa.h +@@ -35,7 +35,6 @@ typedef struct vhost_vdpa { + bool shadow_vqs_enabled; + /* IOVA mapping used by the Shadow Virtqueue */ + VhostIOVATree *iova_tree; +- Error *migration_blocker; + GPtrArray *shadow_vqs; + const VhostShadowVirtqueueOps *shadow_vq_ops; + void *shadow_vq_ops_opaque; +diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c +index 79ebda7de1..f4f16583e4 100644 +--- a/net/vhost-vdpa.c ++++ b/net/vhost-vdpa.c +@@ -555,8 +555,6 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer, + + s->vhost_vdpa.shadow_vq_ops = &vhost_vdpa_net_svq_ops; + s->vhost_vdpa.shadow_vq_ops_opaque = s; +- error_setg(&s->vhost_vdpa.migration_blocker, +- "Migration disabled: vhost-vdpa uses CVQ."); + } + ret = vhost_vdpa_add(nc, (void *)&s->vhost_vdpa, queue_pair_index, nvqs); + if (ret) { +-- +2.31.1 + diff --git a/SOURCES/kvm-vdpa-Export-vhost_vdpa_dma_map-and-unmap-calls.patch b/SOURCES/kvm-vdpa-Export-vhost_vdpa_dma_map-and-unmap-calls.patch new file mode 100644 index 0000000..d6e72ac --- /dev/null +++ b/SOURCES/kvm-vdpa-Export-vhost_vdpa_dma_map-and-unmap-calls.patch @@ -0,0 +1,84 @@ +From 3a5d325fcb2958318262efac31d5fd25fb062523 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Thu, 21 Jul 2022 15:38:55 +0200 +Subject: [PATCH 21/32] vdpa: Export vhost_vdpa_dma_map and unmap calls +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 108: Net Control Virtqueue shadow Support +RH-Commit: [21/27] 97e7a583bbd3c12a0786d53132812ec41702c190 (eperezmartin/qemu-kvm) +RH-Bugzilla: 1939363 +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Cindy Lu +RH-Acked-by: Laurent Vivier + +Bugzilla: https://bugzilla.redhat.com/1939363 + +Upstream Status: git://git.qemu.org/qemu.git + +commit 463ba1e3b8cf080812895c5f26d95d8d7db2e692 +Author: Eugenio Pérez +Date: Wed Jul 20 08:59:40 2022 +0200 + + vdpa: Export vhost_vdpa_dma_map and unmap calls + + Shadow CVQ will copy buffers on qemu VA, so we avoid TOCTOU attacks from + the guest that could set a different state in qemu device model and vdpa + device. + + To do so, it needs to be able to map these new buffers to the device. + + Signed-off-by: Eugenio Pérez + Acked-by: Jason Wang + Reviewed-by: Michael S. Tsirkin + Signed-off-by: Jason Wang + +Signed-off-by: Eugenio Pérez +--- + hw/virtio/vhost-vdpa.c | 7 +++---- + include/hw/virtio/vhost-vdpa.h | 4 ++++ + 2 files changed, 7 insertions(+), 4 deletions(-) + +diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c +index 28df57b12e..14b02fe079 100644 +--- a/hw/virtio/vhost-vdpa.c ++++ b/hw/virtio/vhost-vdpa.c +@@ -71,8 +71,8 @@ static bool vhost_vdpa_listener_skipped_section(MemoryRegionSection *section, + return false; + } + +-static int vhost_vdpa_dma_map(struct vhost_vdpa *v, hwaddr iova, hwaddr size, +- void *vaddr, bool readonly) ++int vhost_vdpa_dma_map(struct vhost_vdpa *v, hwaddr iova, hwaddr size, ++ void *vaddr, bool readonly) + { + struct vhost_msg_v2 msg = {}; + int fd = v->device_fd; +@@ -97,8 +97,7 @@ static int vhost_vdpa_dma_map(struct vhost_vdpa *v, hwaddr iova, hwaddr size, + return ret; + } + +-static int vhost_vdpa_dma_unmap(struct vhost_vdpa *v, hwaddr iova, +- hwaddr size) ++int vhost_vdpa_dma_unmap(struct vhost_vdpa *v, hwaddr iova, hwaddr size) + { + struct vhost_msg_v2 msg = {}; + int fd = v->device_fd; +diff --git a/include/hw/virtio/vhost-vdpa.h b/include/hw/virtio/vhost-vdpa.h +index a29dbb3f53..7214eb47dc 100644 +--- a/include/hw/virtio/vhost-vdpa.h ++++ b/include/hw/virtio/vhost-vdpa.h +@@ -39,4 +39,8 @@ typedef struct vhost_vdpa { + VhostVDPAHostNotifier notifier[VIRTIO_QUEUE_MAX]; + } VhostVDPA; + ++int vhost_vdpa_dma_map(struct vhost_vdpa *v, hwaddr iova, hwaddr size, ++ void *vaddr, bool readonly); ++int vhost_vdpa_dma_unmap(struct vhost_vdpa *v, hwaddr iova, hwaddr size); ++ + #endif +-- +2.31.1 + diff --git a/SOURCES/kvm-vdpa-Extract-get-features-part-from-vhost_vdpa_get_m.patch b/SOURCES/kvm-vdpa-Extract-get-features-part-from-vhost_vdpa_get_m.patch new file mode 100644 index 0000000..44e97af --- /dev/null +++ b/SOURCES/kvm-vdpa-Extract-get-features-part-from-vhost_vdpa_get_m.patch @@ -0,0 +1,108 @@ +From 9a290bd74f983f3a65aa9ec5df2da9aa94bfdecd Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Thu, 21 Jul 2022 16:05:42 +0200 +Subject: [PATCH 25/32] vdpa: Extract get features part from + vhost_vdpa_get_max_queue_pairs +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 108: Net Control Virtqueue shadow Support +RH-Commit: [25/27] 654ad68e10a4df84cced923c64e72d500721ad67 (eperezmartin/qemu-kvm) +RH-Bugzilla: 1939363 +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Cindy Lu +RH-Acked-by: Laurent Vivier + +Bugzilla: https://bugzilla.redhat.com/1939363 + +Upstream Status: git://git.qemu.org/qemu.git + +commit 8170ab3f43989680491d00f1017f60b25d346114 +Author: Eugenio Pérez +Date: Wed Jul 20 08:59:44 2022 +0200 + + vdpa: Extract get features part from vhost_vdpa_get_max_queue_pairs + + To know the device features is needed for CVQ SVQ, so SVQ knows if it + can handle all commands or not. Extract from + vhost_vdpa_get_max_queue_pairs so we can reuse it. + + Signed-off-by: Eugenio Pérez + Acked-by: Jason Wang + Reviewed-by: Michael S. Tsirkin + Signed-off-by: Jason Wang + +Signed-off-by: Eugenio Pérez +--- + net/vhost-vdpa.c | 30 ++++++++++++++++++++---------- + 1 file changed, 20 insertions(+), 10 deletions(-) + +diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c +index df42822463..8b76dac966 100644 +--- a/net/vhost-vdpa.c ++++ b/net/vhost-vdpa.c +@@ -474,20 +474,24 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer, + return nc; + } + +-static int vhost_vdpa_get_max_queue_pairs(int fd, int *has_cvq, Error **errp) ++static int vhost_vdpa_get_features(int fd, uint64_t *features, Error **errp) ++{ ++ int ret = ioctl(fd, VHOST_GET_FEATURES, features); ++ if (unlikely(ret < 0)) { ++ error_setg_errno(errp, errno, ++ "Fail to query features from vhost-vDPA device"); ++ } ++ return ret; ++} ++ ++static int vhost_vdpa_get_max_queue_pairs(int fd, uint64_t features, ++ int *has_cvq, Error **errp) + { + unsigned long config_size = offsetof(struct vhost_vdpa_config, buf); + g_autofree struct vhost_vdpa_config *config = NULL; + __virtio16 *max_queue_pairs; +- uint64_t features; + int ret; + +- ret = ioctl(fd, VHOST_GET_FEATURES, &features); +- if (ret) { +- error_setg(errp, "Fail to query features from vhost-vDPA device"); +- return ret; +- } +- + if (features & (1 << VIRTIO_NET_F_CTRL_VQ)) { + *has_cvq = 1; + } else { +@@ -517,10 +521,11 @@ int net_init_vhost_vdpa(const Netdev *netdev, const char *name, + NetClientState *peer, Error **errp) + { + const NetdevVhostVDPAOptions *opts; ++ uint64_t features; + int vdpa_device_fd; + g_autofree NetClientState **ncs = NULL; + NetClientState *nc; +- int queue_pairs, i, has_cvq = 0; ++ int queue_pairs, r, i, has_cvq = 0; + + assert(netdev->type == NET_CLIENT_DRIVER_VHOST_VDPA); + opts = &netdev->u.vhost_vdpa; +@@ -534,7 +539,12 @@ int net_init_vhost_vdpa(const Netdev *netdev, const char *name, + return -errno; + } + +- queue_pairs = vhost_vdpa_get_max_queue_pairs(vdpa_device_fd, ++ r = vhost_vdpa_get_features(vdpa_device_fd, &features, errp); ++ if (unlikely(r < 0)) { ++ return r; ++ } ++ ++ queue_pairs = vhost_vdpa_get_max_queue_pairs(vdpa_device_fd, features, + &has_cvq, errp); + if (queue_pairs < 0) { + qemu_close(vdpa_device_fd); +-- +2.31.1 + diff --git a/SOURCES/kvm-vdpa-Fix-bad-index-calculus-at-vhost_vdpa_get_vring_.patch b/SOURCES/kvm-vdpa-Fix-bad-index-calculus-at-vhost_vdpa_get_vring_.patch new file mode 100644 index 0000000..2d0d55f --- /dev/null +++ b/SOURCES/kvm-vdpa-Fix-bad-index-calculus-at-vhost_vdpa_get_vring_.patch @@ -0,0 +1,50 @@ +From e19adb058502e24580dbc4f6f944cd951ca288ed Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Thu, 12 May 2022 19:57:44 +0200 +Subject: [PATCH 08/11] vdpa: Fix bad index calculus at + vhost_vdpa_get_vring_base +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 114: vdpa: Fix memory listener deletions of iova tree +RH-Commit: [1/4] 754fb8960684fa7a91bddb18c8df58c3b947ee75 (eperezmartin/qemu-kvm) +RH-Bugzilla: 2116876 +RH-Acked-by: Jason Wang +RH-Acked-by: Cindy Lu +RH-Acked-by: Laurent Vivier + +Fixes: 6d0b222666 ("vdpa: Adapt vhost_vdpa_get_vring_base to SVQ") + +Acked-by: Jason Wang +Signed-off-by: Eugenio Pérez +Message-Id: <20220512175747.142058-4-eperezma@redhat.com> +Reviewed-by: Michael S. Tsirkin +Signed-off-by: Michael S. Tsirkin +(cherry picked from commit 639036477ef890958415967e753ca2cbb348c16c) +--- + hw/virtio/vhost-vdpa.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c +index e3e5bce4bb..a7dfac530f 100644 +--- a/hw/virtio/vhost-vdpa.c ++++ b/hw/virtio/vhost-vdpa.c +@@ -1193,11 +1193,11 @@ static int vhost_vdpa_get_vring_base(struct vhost_dev *dev, + struct vhost_vring_state *ring) + { + struct vhost_vdpa *v = dev->opaque; ++ int vdpa_idx = ring->index - dev->vq_index; + int ret; + + if (v->shadow_vqs_enabled) { +- VhostShadowVirtqueue *svq = g_ptr_array_index(v->shadow_vqs, +- ring->index); ++ VhostShadowVirtqueue *svq = g_ptr_array_index(v->shadow_vqs, vdpa_idx); + + /* + * Setting base as last used idx, so destination will see as available +-- +2.31.1 + diff --git a/SOURCES/kvm-vdpa-Fix-file-descriptor-leak-on-get-features-error.patch b/SOURCES/kvm-vdpa-Fix-file-descriptor-leak-on-get-features-error.patch new file mode 100644 index 0000000..1757d3f --- /dev/null +++ b/SOURCES/kvm-vdpa-Fix-file-descriptor-leak-on-get-features-error.patch @@ -0,0 +1,58 @@ +From 71857062b7aea29fc418e107244cf4083cd78cd7 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Tue, 2 Aug 2022 13:24:46 +0200 +Subject: [PATCH 11/11] vdpa: Fix file descriptor leak on get features error +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 114: vdpa: Fix memory listener deletions of iova tree +RH-Commit: [4/4] bdfe6ed4539ecf68dc8bc4519755f9d5c096447d (eperezmartin/qemu-kvm) +RH-Bugzilla: 2116876 +RH-Acked-by: Jason Wang +RH-Acked-by: Cindy Lu +RH-Acked-by: Laurent Vivier + +File descriptor vdpa_device_fd is not free in the case of returning +error from vhost_vdpa_get_features. Fixing it by making all errors go to +the same error path. + +Resolves: Coverity CID 1490785 +Fixes: 8170ab3f43 ("vdpa: Extract get features part from vhost_vdpa_get_max_queue_pairs") + +Signed-off-by: Eugenio Pérez +Reviewed-by: Laurent Vivier +Reviewed-by: Michael S. Tsirkin +Message-Id: <20220802112447.249436-2-eperezma@redhat.com> +Signed-off-by: Laurent Vivier +(cherry picked from commit aed5da45daf734ddc543c0791e877dac75e16f61) +--- + net/vhost-vdpa.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c +index 50672bcd66..411e71e6c2 100644 +--- a/net/vhost-vdpa.c ++++ b/net/vhost-vdpa.c +@@ -566,7 +566,7 @@ int net_init_vhost_vdpa(const Netdev *netdev, const char *name, + g_autofree NetClientState **ncs = NULL; + g_autoptr(VhostIOVATree) iova_tree = NULL; + NetClientState *nc; +- int queue_pairs, r, i, has_cvq = 0; ++ int queue_pairs, r, i = 0, has_cvq = 0; + + assert(netdev->type == NET_CLIENT_DRIVER_VHOST_VDPA); + opts = &netdev->u.vhost_vdpa; +@@ -582,7 +582,7 @@ int net_init_vhost_vdpa(const Netdev *netdev, const char *name, + + r = vhost_vdpa_get_features(vdpa_device_fd, &features, errp); + if (unlikely(r < 0)) { +- return r; ++ goto err; + } + + queue_pairs = vhost_vdpa_get_max_queue_pairs(vdpa_device_fd, features, +-- +2.31.1 + diff --git a/SOURCES/kvm-vdpa-Fix-index-calculus-at-vhost_vdpa_svqs_start.patch b/SOURCES/kvm-vdpa-Fix-index-calculus-at-vhost_vdpa_svqs_start.patch new file mode 100644 index 0000000..8125cb2 --- /dev/null +++ b/SOURCES/kvm-vdpa-Fix-index-calculus-at-vhost_vdpa_svqs_start.patch @@ -0,0 +1,45 @@ +From 6335431b70dd55c1d52152d726fa462db2e10eb8 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Thu, 12 May 2022 19:57:45 +0200 +Subject: [PATCH 09/11] vdpa: Fix index calculus at vhost_vdpa_svqs_start +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 114: vdpa: Fix memory listener deletions of iova tree +RH-Commit: [2/4] 9ce732e6bba426f8e00020ee6ad77f972f3e75b5 (eperezmartin/qemu-kvm) +RH-Bugzilla: 2116876 +RH-Acked-by: Jason Wang +RH-Acked-by: Cindy Lu +RH-Acked-by: Laurent Vivier + +With the introduction of MQ the index of the vq needs to be calculated +with the device model vq_index. + +Signed-off-by: Eugenio Pérez +Acked-by: Jason Wang +Message-Id: <20220512175747.142058-5-eperezma@redhat.com> +Reviewed-by: Michael S. Tsirkin +Signed-off-by: Michael S. Tsirkin +(cherry picked from commit 1c82fdfef8a227518ffecae9d419bcada995c202) +--- + hw/virtio/vhost-vdpa.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c +index a7dfac530f..f877b354fa 100644 +--- a/hw/virtio/vhost-vdpa.c ++++ b/hw/virtio/vhost-vdpa.c +@@ -1032,7 +1032,7 @@ static bool vhost_vdpa_svqs_start(struct vhost_dev *dev) + VirtQueue *vq = virtio_get_queue(dev->vdev, dev->vq_index + i); + VhostShadowVirtqueue *svq = g_ptr_array_index(v->shadow_vqs, i); + struct vhost_vring_addr addr = { +- .index = i, ++ .index = dev->vq_index + i, + }; + int r; + bool ok = vhost_vdpa_svq_setup(dev, svq, i, &err); +-- +2.31.1 + diff --git a/SOURCES/kvm-vdpa-Fix-memory-listener-deletions-of-iova-tree.patch b/SOURCES/kvm-vdpa-Fix-memory-listener-deletions-of-iova-tree.patch new file mode 100644 index 0000000..e6f1d39 --- /dev/null +++ b/SOURCES/kvm-vdpa-Fix-memory-listener-deletions-of-iova-tree.patch @@ -0,0 +1,61 @@ +From b212edc97a471c75f8b8b44ee2a3a2cf82ef14d9 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Fri, 22 Jul 2022 10:26:30 +0200 +Subject: [PATCH 10/11] vdpa: Fix memory listener deletions of iova tree +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 114: vdpa: Fix memory listener deletions of iova tree +RH-Commit: [3/4] ad71f098b3fa8654962ac7872b5393c37c9825f2 (eperezmartin/qemu-kvm) +RH-Bugzilla: 2116876 +RH-Acked-by: Jason Wang +RH-Acked-by: Cindy Lu +RH-Acked-by: Laurent Vivier + +vhost_vdpa_listener_region_del is always deleting the first iova entry +of the tree, since it's using the needle iova instead of the result's +one. + +This was detected using a vga virtual device in the VM using vdpa SVQ. +It makes some extra memory adding and deleting, so the wrong one was +mapped / unmapped. This was undetected before since all the memory was +mappend and unmapped totally without that device, but other conditions +could trigger it too: + +* mem_region was with .iova = 0, .translated_addr = (correct GPA). +* iova_tree_find_iova returned right result, but does not update + mem_region. +* iova_tree_remove always removed region with .iova = 0. Right iova were + sent to the device. +* Next map will fill the first region with .iova = 0, causing a mapping + with the same iova and device complains, if the next action is a map. +* Next unmap will cause to try to unmap again iova = 0, causing the + device to complain that no region was mapped at iova = 0. + +Fixes: 34e3c94edaef ("vdpa: Add custom IOTLB translations to SVQ") +Reported-by: Lei Yang +Signed-off-by: Eugenio Pérez +Signed-off-by: Jason Wang +(cherry picked from commit 75a8ce64f6e37513698857fb4284170da163ed06) +--- + hw/virtio/vhost-vdpa.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c +index f877b354fa..03dc6014b0 100644 +--- a/hw/virtio/vhost-vdpa.c ++++ b/hw/virtio/vhost-vdpa.c +@@ -288,7 +288,7 @@ static void vhost_vdpa_listener_region_del(MemoryListener *listener, + + result = vhost_iova_tree_find_iova(v->iova_tree, &mem_region); + iova = result->iova; +- vhost_iova_tree_remove(v->iova_tree, &mem_region); ++ vhost_iova_tree_remove(v->iova_tree, result); + } + vhost_vdpa_iotlb_batch_begin_once(v); + ret = vhost_vdpa_dma_unmap(v, iova, int128_get64(llsize)); +-- +2.31.1 + diff --git a/SOURCES/kvm-vdpa-Make-SVQ-vring-unmapping-return-void.patch b/SOURCES/kvm-vdpa-Make-SVQ-vring-unmapping-return-void.patch new file mode 100644 index 0000000..e45a198 --- /dev/null +++ b/SOURCES/kvm-vdpa-Make-SVQ-vring-unmapping-return-void.patch @@ -0,0 +1,133 @@ +From 8e36feb4d3480b7c09d9dcbde18c9db1e8063f18 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Tue, 23 Aug 2022 20:20:06 +0200 +Subject: [PATCH 08/23] vdpa: Make SVQ vring unmapping return void +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 116: vdpa: Restore device state on destination +RH-Bugzilla: 2114060 +RH-Acked-by: Cindy Lu +RH-Acked-by: Miroslav Rezanina +RH-Commit: [7/21] 3366340dc7ae65f83894f5d0da0d1e0f64713751 (eperezmartin/qemu-kvm) +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2114060 +Upstream status: git@github.com:jasowang/qemu.git net-next + +Nothing actually reads the return value, but an error in cleaning some +entries could cause device stop to abort, making a restart impossible. +Better ignore explicitely the return value. + +Reported-by: Lei Yang +Fixes: 34e3c94eda ("vdpa: Add custom IOTLB translations to SVQ") +Signed-off-by: Eugenio Pérez +Acked-by: Jason Wang +Signed-off-by: Jason Wang +(cherry picked from commit bb5cf89ef2338ab6be946ede6821c3f61347eb1b) +--- + hw/virtio/vhost-vdpa.c | 32 ++++++++++---------------------- + 1 file changed, 10 insertions(+), 22 deletions(-) + +diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c +index e5c264fb29..8eddf39f2a 100644 +--- a/hw/virtio/vhost-vdpa.c ++++ b/hw/virtio/vhost-vdpa.c +@@ -882,7 +882,7 @@ static int vhost_vdpa_svq_set_fds(struct vhost_dev *dev, + /** + * Unmap a SVQ area in the device + */ +-static bool vhost_vdpa_svq_unmap_ring(struct vhost_vdpa *v, ++static void vhost_vdpa_svq_unmap_ring(struct vhost_vdpa *v, + const DMAMap *needle) + { + const DMAMap *result = vhost_iova_tree_find_iova(v->iova_tree, needle); +@@ -891,38 +891,33 @@ static bool vhost_vdpa_svq_unmap_ring(struct vhost_vdpa *v, + + if (unlikely(!result)) { + error_report("Unable to find SVQ address to unmap"); +- return false; ++ return; + } + + size = ROUND_UP(result->size, qemu_real_host_page_size); + r = vhost_vdpa_dma_unmap(v, result->iova, size); + if (unlikely(r < 0)) { + error_report("Unable to unmap SVQ vring: %s (%d)", g_strerror(-r), -r); +- return false; ++ return; + } + + vhost_iova_tree_remove(v->iova_tree, *result); +- return r == 0; + } + +-static bool vhost_vdpa_svq_unmap_rings(struct vhost_dev *dev, ++static void vhost_vdpa_svq_unmap_rings(struct vhost_dev *dev, + const VhostShadowVirtqueue *svq) + { + DMAMap needle = {}; + struct vhost_vdpa *v = dev->opaque; + struct vhost_vring_addr svq_addr; +- bool ok; + + vhost_svq_get_vring_addr(svq, &svq_addr); + + needle.translated_addr = svq_addr.desc_user_addr; +- ok = vhost_vdpa_svq_unmap_ring(v, &needle); +- if (unlikely(!ok)) { +- return false; +- } ++ vhost_vdpa_svq_unmap_ring(v, &needle); + + needle.translated_addr = svq_addr.used_user_addr; +- return vhost_vdpa_svq_unmap_ring(v, &needle); ++ vhost_vdpa_svq_unmap_ring(v, &needle); + } + + /** +@@ -1093,26 +1088,22 @@ err: + return false; + } + +-static bool vhost_vdpa_svqs_stop(struct vhost_dev *dev) ++static void vhost_vdpa_svqs_stop(struct vhost_dev *dev) + { + struct vhost_vdpa *v = dev->opaque; + + if (!v->shadow_vqs) { +- return true; ++ return; + } + + for (unsigned i = 0; i < v->shadow_vqs->len; ++i) { + VhostShadowVirtqueue *svq = g_ptr_array_index(v->shadow_vqs, i); +- bool ok = vhost_vdpa_svq_unmap_rings(dev, svq); +- if (unlikely(!ok)) { +- return false; +- } ++ vhost_vdpa_svq_unmap_rings(dev, svq); + } + + if (v->migration_blocker) { + migrate_del_blocker(v->migration_blocker); + } +- return true; + } + + static int vhost_vdpa_dev_start(struct vhost_dev *dev, bool started) +@@ -1129,10 +1120,7 @@ static int vhost_vdpa_dev_start(struct vhost_dev *dev, bool started) + } + vhost_vdpa_set_vring_ready(dev); + } else { +- ok = vhost_vdpa_svqs_stop(dev); +- if (unlikely(!ok)) { +- return -1; +- } ++ vhost_vdpa_svqs_stop(dev); + vhost_vdpa_host_notifiers_uninit(dev, dev->nvqs); + } + +-- +2.31.1 + diff --git a/SOURCES/kvm-vdpa-Move-command-buffers-map-to-start-of-net-device.patch b/SOURCES/kvm-vdpa-Move-command-buffers-map-to-start-of-net-device.patch new file mode 100644 index 0000000..7cdf05c --- /dev/null +++ b/SOURCES/kvm-vdpa-Move-command-buffers-map-to-start-of-net-device.patch @@ -0,0 +1,251 @@ +From 70c72316c26e95cd18b4d46b83e78ba3a148212c Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Tue, 23 Aug 2022 20:30:33 +0200 +Subject: [PATCH 18/23] vdpa: Move command buffers map to start of net device +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 116: vdpa: Restore device state on destination +RH-Bugzilla: 2114060 +RH-Acked-by: Cindy Lu +RH-Acked-by: Miroslav Rezanina +RH-Commit: [17/21] 7a9824fa618f5c2904648b50e3078474cd3987aa (eperezmartin/qemu-kvm) +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2114060 +Upstream status: git@github.com:jasowang/qemu.git net-next + +As this series will reuse them to restore the device state at the end of +a migration (or a device start), let's allocate only once at the device +start so we don't duplicate their map and unmap. + +Signed-off-by: Eugenio Pérez +Acked-by: Jason Wang +Signed-off-by: Jason Wang +(cherry picked from commit d7d73dec14cebcebd8de774424795aeb821236c1) +--- + net/vhost-vdpa.c | 123 ++++++++++++++++++++++------------------------- + 1 file changed, 58 insertions(+), 65 deletions(-) + +diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c +index 03e4cf1abc..17626feb8d 100644 +--- a/net/vhost-vdpa.c ++++ b/net/vhost-vdpa.c +@@ -263,29 +263,20 @@ static size_t vhost_vdpa_net_cvq_cmd_page_len(void) + return ROUND_UP(vhost_vdpa_net_cvq_cmd_len(), qemu_real_host_page_size); + } + +-/** Copy and map a guest buffer. */ +-static bool vhost_vdpa_cvq_map_buf(struct vhost_vdpa *v, +- const struct iovec *out_data, +- size_t out_num, size_t data_len, void *buf, +- size_t *written, bool write) ++/** Map CVQ buffer. */ ++static int vhost_vdpa_cvq_map_buf(struct vhost_vdpa *v, void *buf, size_t size, ++ bool write) + { + DMAMap map = {}; + int r; + +- if (unlikely(!data_len)) { +- qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid legnth of %s buffer\n", +- __func__, write ? "in" : "out"); +- return false; +- } +- +- *written = iov_to_buf(out_data, out_num, 0, buf, data_len); + map.translated_addr = (hwaddr)(uintptr_t)buf; +- map.size = vhost_vdpa_net_cvq_cmd_page_len() - 1; ++ map.size = size - 1; + map.perm = write ? IOMMU_RW : IOMMU_RO, + r = vhost_iova_tree_map_alloc(v->iova_tree, &map); + if (unlikely(r != IOVA_OK)) { + error_report("Cannot map injected element"); +- return false; ++ return r; + } + + r = vhost_vdpa_dma_map(v, map.iova, vhost_vdpa_net_cvq_cmd_page_len(), buf, +@@ -294,50 +285,58 @@ static bool vhost_vdpa_cvq_map_buf(struct vhost_vdpa *v, + goto dma_map_err; + } + +- return true; ++ return 0; + + dma_map_err: + vhost_iova_tree_remove(v->iova_tree, map); +- return false; ++ return r; + } + +-/** +- * Copy the guest element into a dedicated buffer suitable to be sent to NIC +- * +- * @iov: [0] is the out buffer, [1] is the in one +- */ +-static bool vhost_vdpa_net_cvq_map_elem(VhostVDPAState *s, +- VirtQueueElement *elem, +- struct iovec *iov) ++static int vhost_vdpa_net_cvq_start(NetClientState *nc) + { +- size_t in_copied; +- bool ok; ++ VhostVDPAState *s; ++ int r; + +- iov[0].iov_base = s->cvq_cmd_out_buffer; +- ok = vhost_vdpa_cvq_map_buf(&s->vhost_vdpa, elem->out_sg, elem->out_num, +- vhost_vdpa_net_cvq_cmd_len(), iov[0].iov_base, +- &iov[0].iov_len, false); +- if (unlikely(!ok)) { +- return false; ++ assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_VDPA); ++ ++ s = DO_UPCAST(VhostVDPAState, nc, nc); ++ if (!s->vhost_vdpa.shadow_vqs_enabled) { ++ return 0; + } + +- iov[1].iov_base = s->cvq_cmd_in_buffer; +- ok = vhost_vdpa_cvq_map_buf(&s->vhost_vdpa, NULL, 0, +- sizeof(virtio_net_ctrl_ack), iov[1].iov_base, +- &in_copied, true); +- if (unlikely(!ok)) { ++ r = vhost_vdpa_cvq_map_buf(&s->vhost_vdpa, s->cvq_cmd_out_buffer, ++ vhost_vdpa_net_cvq_cmd_page_len(), false); ++ if (unlikely(r < 0)) { ++ return r; ++ } ++ ++ r = vhost_vdpa_cvq_map_buf(&s->vhost_vdpa, s->cvq_cmd_in_buffer, ++ vhost_vdpa_net_cvq_cmd_page_len(), true); ++ if (unlikely(r < 0)) { + vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, s->cvq_cmd_out_buffer); +- return false; + } + +- iov[1].iov_len = sizeof(virtio_net_ctrl_ack); +- return true; ++ return r; ++} ++ ++static void vhost_vdpa_net_cvq_stop(NetClientState *nc) ++{ ++ VhostVDPAState *s = DO_UPCAST(VhostVDPAState, nc, nc); ++ ++ assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_VDPA); ++ ++ if (s->vhost_vdpa.shadow_vqs_enabled) { ++ vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, s->cvq_cmd_out_buffer); ++ vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, s->cvq_cmd_in_buffer); ++ } + } + + static NetClientInfo net_vhost_vdpa_cvq_info = { + .type = NET_CLIENT_DRIVER_VHOST_VDPA, + .size = sizeof(VhostVDPAState), + .receive = vhost_vdpa_receive, ++ .start = vhost_vdpa_net_cvq_start, ++ .stop = vhost_vdpa_net_cvq_stop, + .cleanup = vhost_vdpa_cleanup, + .has_vnet_hdr = vhost_vdpa_has_vnet_hdr, + .has_ufo = vhost_vdpa_has_ufo, +@@ -348,19 +347,17 @@ static NetClientInfo net_vhost_vdpa_cvq_info = { + * Do not forward commands not supported by SVQ. Otherwise, the device could + * accept it and qemu would not know how to update the device model. + */ +-static bool vhost_vdpa_net_cvq_validate_cmd(const struct iovec *out, +- size_t out_num) ++static bool vhost_vdpa_net_cvq_validate_cmd(const void *out_buf, size_t len) + { + struct virtio_net_ctrl_hdr ctrl; +- size_t n; + +- n = iov_to_buf(out, out_num, 0, &ctrl, sizeof(ctrl)); +- if (unlikely(n < sizeof(ctrl))) { ++ if (unlikely(len < sizeof(ctrl))) { + qemu_log_mask(LOG_GUEST_ERROR, +- "%s: invalid legnth of out buffer %zu\n", __func__, n); ++ "%s: invalid legnth of out buffer %zu\n", __func__, len); + return false; + } + ++ memcpy(&ctrl, out_buf, sizeof(ctrl)); + switch (ctrl.class) { + case VIRTIO_NET_CTRL_MAC: + switch (ctrl.cmd) { +@@ -392,10 +389,14 @@ static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq, + VhostVDPAState *s = opaque; + size_t in_len, dev_written; + virtio_net_ctrl_ack status = VIRTIO_NET_ERR; +- /* out and in buffers sent to the device */ +- struct iovec dev_buffers[2] = { +- { .iov_base = s->cvq_cmd_out_buffer }, +- { .iov_base = s->cvq_cmd_in_buffer }, ++ /* Out buffer sent to both the vdpa device and the device model */ ++ struct iovec out = { ++ .iov_base = s->cvq_cmd_out_buffer, ++ }; ++ /* In buffer sent to the device */ ++ const struct iovec dev_in = { ++ .iov_base = s->cvq_cmd_in_buffer, ++ .iov_len = sizeof(virtio_net_ctrl_ack), + }; + /* in buffer used for device model */ + const struct iovec in = { +@@ -405,17 +406,15 @@ static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq, + int r = -EINVAL; + bool ok; + +- ok = vhost_vdpa_net_cvq_map_elem(s, elem, dev_buffers); +- if (unlikely(!ok)) { +- goto out; +- } +- +- ok = vhost_vdpa_net_cvq_validate_cmd(&dev_buffers[0], 1); ++ out.iov_len = iov_to_buf(elem->out_sg, elem->out_num, 0, ++ s->cvq_cmd_out_buffer, ++ vhost_vdpa_net_cvq_cmd_len()); ++ ok = vhost_vdpa_net_cvq_validate_cmd(s->cvq_cmd_out_buffer, out.iov_len); + if (unlikely(!ok)) { + goto out; + } + +- r = vhost_svq_add(svq, &dev_buffers[0], 1, &dev_buffers[1], 1, elem); ++ r = vhost_svq_add(svq, &out, 1, &dev_in, 1, elem); + if (unlikely(r != 0)) { + if (unlikely(r == -ENOSPC)) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: No space on device queue\n", +@@ -435,13 +434,13 @@ static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq, + goto out; + } + +- memcpy(&status, dev_buffers[1].iov_base, sizeof(status)); ++ memcpy(&status, s->cvq_cmd_in_buffer, sizeof(status)); + if (status != VIRTIO_NET_OK) { + goto out; + } + + status = VIRTIO_NET_ERR; +- virtio_net_handle_ctrl_iov(svq->vdev, &in, 1, dev_buffers, 1); ++ virtio_net_handle_ctrl_iov(svq->vdev, &in, 1, &out, 1); + if (status != VIRTIO_NET_OK) { + error_report("Bad CVQ processing in model"); + } +@@ -454,12 +453,6 @@ out: + } + vhost_svq_push_elem(svq, elem, MIN(in_len, sizeof(status))); + g_free(elem); +- if (dev_buffers[0].iov_base) { +- vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, dev_buffers[0].iov_base); +- } +- if (dev_buffers[1].iov_base) { +- vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, dev_buffers[1].iov_base); +- } + return r; + } + +-- +2.31.1 + diff --git a/SOURCES/kvm-vdpa-Remove-SVQ-vring-from-iova_tree-at-shutdown.patch b/SOURCES/kvm-vdpa-Remove-SVQ-vring-from-iova_tree-at-shutdown.patch new file mode 100644 index 0000000..b23d64f --- /dev/null +++ b/SOURCES/kvm-vdpa-Remove-SVQ-vring-from-iova_tree-at-shutdown.patch @@ -0,0 +1,49 @@ +From 51c1e9cf1612727ec4c6e795576ae8fa0c0b2d4c Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Tue, 23 Aug 2022 20:20:05 +0200 +Subject: [PATCH 07/23] vdpa: Remove SVQ vring from iova_tree at shutdown +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 116: vdpa: Restore device state on destination +RH-Bugzilla: 2114060 +RH-Acked-by: Cindy Lu +RH-Acked-by: Miroslav Rezanina +RH-Commit: [6/21] f72e67b9c90103151cbf86bff53e8f14b30f0e5b (eperezmartin/qemu-kvm) +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2114060 +Upstream status: git@github.com:jasowang/qemu.git net-next + +Although the device will be reset before usage, the right thing to do is +to clean it. + +Reported-by: Lei Yang +Fixes: 34e3c94eda ("vdpa: Add custom IOTLB translations to SVQ") +Signed-off-by: Eugenio Pérez +Signed-off-by: Jason Wang +(cherry picked from commit 0c45fa6c420ec3a1dd9ea9c40fa11bd943bb3be9) +--- + hw/virtio/vhost-vdpa.c | 6 ++++++ + 1 file changed, 6 insertions(+) + +diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c +index 39aa70f52d..e5c264fb29 100644 +--- a/hw/virtio/vhost-vdpa.c ++++ b/hw/virtio/vhost-vdpa.c +@@ -896,6 +896,12 @@ static bool vhost_vdpa_svq_unmap_ring(struct vhost_vdpa *v, + + size = ROUND_UP(result->size, qemu_real_host_page_size); + r = vhost_vdpa_dma_unmap(v, result->iova, size); ++ if (unlikely(r < 0)) { ++ error_report("Unable to unmap SVQ vring: %s (%d)", g_strerror(-r), -r); ++ return false; ++ } ++ ++ vhost_iova_tree_remove(v->iova_tree, *result); + return r == 0; + } + +-- +2.31.1 + diff --git a/SOURCES/kvm-vdpa-Skip-the-maps-not-in-the-iova-tree.patch b/SOURCES/kvm-vdpa-Skip-the-maps-not-in-the-iova-tree.patch new file mode 100644 index 0000000..98697cb --- /dev/null +++ b/SOURCES/kvm-vdpa-Skip-the-maps-not-in-the-iova-tree.patch @@ -0,0 +1,48 @@ +From edde0b6a805085255bccc0ccdc3b9b6f81cef37b Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Tue, 23 Aug 2022 20:20:02 +0200 +Subject: [PATCH 03/23] vdpa: Skip the maps not in the iova tree +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 116: vdpa: Restore device state on destination +RH-Bugzilla: 2114060 +RH-Acked-by: Cindy Lu +RH-Acked-by: Miroslav Rezanina +RH-Commit: [2/21] 73acd16375a17cdf4c58830386541dd3a1b18bf7 (eperezmartin/qemu-kvm) +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2114060 +Upstream status: git@github.com:jasowang/qemu.git net-next + +Next patch will skip the registering of dma maps that the vdpa device +rejects in the iova tree. We need to consider that here or we cause a +SIGSEGV accessing result. + +Reported-by: Lei Yang +Signed-off-by: Eugenio Pérez +Acked-by: Jason Wang +Signed-off-by: Jason Wang +(cherry picked from commit a92ca0ffee5858636432a6059eb2790df1c9c77f) +--- + hw/virtio/vhost-vdpa.c | 4 ++++ + 1 file changed, 4 insertions(+) + +diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c +index 96334ab5b6..aa7765c6bc 100644 +--- a/hw/virtio/vhost-vdpa.c ++++ b/hw/virtio/vhost-vdpa.c +@@ -287,6 +287,10 @@ static void vhost_vdpa_listener_region_del(MemoryListener *listener, + }; + + result = vhost_iova_tree_find_iova(v->iova_tree, &mem_region); ++ if (!result) { ++ /* The memory listener map wasn't mapped */ ++ return; ++ } + iova = result->iova; + vhost_iova_tree_remove(v->iova_tree, result); + } +-- +2.31.1 + diff --git a/SOURCES/kvm-vdpa-Use-ring-hwaddr-at-vhost_vdpa_svq_unmap_ring.patch b/SOURCES/kvm-vdpa-Use-ring-hwaddr-at-vhost_vdpa_svq_unmap_ring.patch new file mode 100644 index 0000000..8398415 --- /dev/null +++ b/SOURCES/kvm-vdpa-Use-ring-hwaddr-at-vhost_vdpa_svq_unmap_ring.patch @@ -0,0 +1,79 @@ +From 89a67e0ce3e4c7b9f9b2d4cfb9fc5eeebc5643ac Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Tue, 23 Aug 2022 20:20:08 +0200 +Subject: [PATCH 10/23] vdpa: Use ring hwaddr at vhost_vdpa_svq_unmap_ring +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 116: vdpa: Restore device state on destination +RH-Bugzilla: 2114060 +RH-Acked-by: Cindy Lu +RH-Acked-by: Miroslav Rezanina +RH-Commit: [9/21] 4420134d7be60fa8b04dc9a56566524bf8daddd4 (eperezmartin/qemu-kvm) +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2114060 +Upstream status: git@github.com:jasowang/qemu.git net-next + +Reduce code duplication. + +Signed-off-by: Eugenio Pérez +Acked-by: Jason Wang +Signed-off-by: Jason Wang +(cherry picked from commit 5a92452da95b2edfbffdd42ddc2612a7d09a5db0) +--- + hw/virtio/vhost-vdpa.c | 17 ++++++++--------- + 1 file changed, 8 insertions(+), 9 deletions(-) + +diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c +index 8eddf39f2a..0bea1e1eb9 100644 +--- a/hw/virtio/vhost-vdpa.c ++++ b/hw/virtio/vhost-vdpa.c +@@ -882,10 +882,12 @@ static int vhost_vdpa_svq_set_fds(struct vhost_dev *dev, + /** + * Unmap a SVQ area in the device + */ +-static void vhost_vdpa_svq_unmap_ring(struct vhost_vdpa *v, +- const DMAMap *needle) ++static void vhost_vdpa_svq_unmap_ring(struct vhost_vdpa *v, hwaddr addr) + { +- const DMAMap *result = vhost_iova_tree_find_iova(v->iova_tree, needle); ++ const DMAMap needle = { ++ .translated_addr = addr, ++ }; ++ const DMAMap *result = vhost_iova_tree_find_iova(v->iova_tree, &needle); + hwaddr size; + int r; + +@@ -907,17 +909,14 @@ static void vhost_vdpa_svq_unmap_ring(struct vhost_vdpa *v, + static void vhost_vdpa_svq_unmap_rings(struct vhost_dev *dev, + const VhostShadowVirtqueue *svq) + { +- DMAMap needle = {}; + struct vhost_vdpa *v = dev->opaque; + struct vhost_vring_addr svq_addr; + + vhost_svq_get_vring_addr(svq, &svq_addr); + +- needle.translated_addr = svq_addr.desc_user_addr; +- vhost_vdpa_svq_unmap_ring(v, &needle); ++ vhost_vdpa_svq_unmap_ring(v, svq_addr.desc_user_addr); + +- needle.translated_addr = svq_addr.used_user_addr; +- vhost_vdpa_svq_unmap_ring(v, &needle); ++ vhost_vdpa_svq_unmap_ring(v, svq_addr.used_user_addr); + } + + /** +@@ -995,7 +994,7 @@ static bool vhost_vdpa_svq_map_rings(struct vhost_dev *dev, + ok = vhost_vdpa_svq_map_ring(v, &device_region, errp); + if (unlikely(!ok)) { + error_prepend(errp, "Cannot create vq device region: "); +- vhost_vdpa_svq_unmap_ring(v, &driver_region); ++ vhost_vdpa_svq_unmap_ring(v, driver_region.translated_addr); + } + addr->used_user_addr = device_region.iova; + +-- +2.31.1 + diff --git a/SOURCES/kvm-vdpa-add-net_vhost_vdpa_cvq_info-NetClientInfo.patch b/SOURCES/kvm-vdpa-add-net_vhost_vdpa_cvq_info-NetClientInfo.patch new file mode 100644 index 0000000..e1da31d --- /dev/null +++ b/SOURCES/kvm-vdpa-add-net_vhost_vdpa_cvq_info-NetClientInfo.patch @@ -0,0 +1,62 @@ +From f92b0ef80b4889ae0beb0b2a026ec3892d576d79 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Tue, 23 Aug 2022 20:30:32 +0200 +Subject: [PATCH 17/23] vdpa: add net_vhost_vdpa_cvq_info NetClientInfo +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 116: vdpa: Restore device state on destination +RH-Bugzilla: 2114060 +RH-Acked-by: Cindy Lu +RH-Acked-by: Miroslav Rezanina +RH-Commit: [16/21] c80c9fd89e81fc389e7d02e9d764331ab9fc7a0a (eperezmartin/qemu-kvm) +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2114060 +Upstream status: git@github.com:jasowang/qemu.git net-next + +Next patches will add a new info callback to restore NIC status through +CVQ. Since only the CVQ vhost device is needed, create it with a new +NetClientInfo. + +Signed-off-by: Eugenio Pérez +Acked-by: Jason Wang +Signed-off-by: Jason Wang +(cherry picked from commit 9d379453404303069f93f9b8163ae3805bcd8c2e) +--- + net/vhost-vdpa.c | 12 +++++++++++- + 1 file changed, 11 insertions(+), 1 deletion(-) + +diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c +index ba65736f83..03e4cf1abc 100644 +--- a/net/vhost-vdpa.c ++++ b/net/vhost-vdpa.c +@@ -334,6 +334,16 @@ static bool vhost_vdpa_net_cvq_map_elem(VhostVDPAState *s, + return true; + } + ++static NetClientInfo net_vhost_vdpa_cvq_info = { ++ .type = NET_CLIENT_DRIVER_VHOST_VDPA, ++ .size = sizeof(VhostVDPAState), ++ .receive = vhost_vdpa_receive, ++ .cleanup = vhost_vdpa_cleanup, ++ .has_vnet_hdr = vhost_vdpa_has_vnet_hdr, ++ .has_ufo = vhost_vdpa_has_ufo, ++ .check_peer_type = vhost_vdpa_check_peer_type, ++}; ++ + /** + * Do not forward commands not supported by SVQ. Otherwise, the device could + * accept it and qemu would not know how to update the device model. +@@ -475,7 +485,7 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer, + nc = qemu_new_net_client(&net_vhost_vdpa_info, peer, device, + name); + } else { +- nc = qemu_new_net_control_client(&net_vhost_vdpa_info, peer, ++ nc = qemu_new_net_control_client(&net_vhost_vdpa_cvq_info, peer, + device, name); + } + snprintf(nc->info_str, sizeof(nc->info_str), TYPE_VHOST_VDPA); +-- +2.31.1 + diff --git a/SOURCES/kvm-vdpa-do-not-save-failed-dma-maps-in-SVQ-iova-tree.patch b/SOURCES/kvm-vdpa-do-not-save-failed-dma-maps-in-SVQ-iova-tree.patch new file mode 100644 index 0000000..8c66f19 --- /dev/null +++ b/SOURCES/kvm-vdpa-do-not-save-failed-dma-maps-in-SVQ-iova-tree.patch @@ -0,0 +1,83 @@ +From 6d16102aca24bab16c846fe6457071f4466b8e35 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Tue, 23 Aug 2022 20:20:03 +0200 +Subject: [PATCH 04/23] vdpa: do not save failed dma maps in SVQ iova tree +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 116: vdpa: Restore device state on destination +RH-Bugzilla: 2114060 +RH-Acked-by: Cindy Lu +RH-Acked-by: Miroslav Rezanina +RH-Commit: [3/21] f9bea39f7fa14c5ef0f85774cbad0ca3b52c4498 (eperezmartin/qemu-kvm) +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2114060 +Upstream status: git@github.com:jasowang/qemu.git net-next + +If a map fails for whatever reason, it must not be saved in the tree. +Otherwise, qemu will try to unmap it in cleanup, leaving to more errors. + +Fixes: 34e3c94eda ("vdpa: Add custom IOTLB translations to SVQ") +Reported-by: Lei Yang +Signed-off-by: Eugenio Pérez +Acked-by: Jason Wang +Signed-off-by: Jason Wang +(cherry picked from commit 6cc2ec65382fde205511ac00a324995ce6ee8f28) +--- + hw/virtio/vhost-vdpa.c | 20 +++++++++++++------- + 1 file changed, 13 insertions(+), 7 deletions(-) + +diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c +index aa7765c6bc..cc15b7d8ee 100644 +--- a/hw/virtio/vhost-vdpa.c ++++ b/hw/virtio/vhost-vdpa.c +@@ -174,6 +174,7 @@ static void vhost_vdpa_listener_commit(MemoryListener *listener) + static void vhost_vdpa_listener_region_add(MemoryListener *listener, + MemoryRegionSection *section) + { ++ DMAMap mem_region = {}; + struct vhost_vdpa *v = container_of(listener, struct vhost_vdpa, listener); + hwaddr iova; + Int128 llend, llsize; +@@ -210,13 +211,13 @@ static void vhost_vdpa_listener_region_add(MemoryListener *listener, + + llsize = int128_sub(llend, int128_make64(iova)); + if (v->shadow_vqs_enabled) { +- DMAMap mem_region = { +- .translated_addr = (hwaddr)(uintptr_t)vaddr, +- .size = int128_get64(llsize) - 1, +- .perm = IOMMU_ACCESS_FLAG(true, section->readonly), +- }; ++ int r; + +- int r = vhost_iova_tree_map_alloc(v->iova_tree, &mem_region); ++ mem_region.translated_addr = (hwaddr)(uintptr_t)vaddr, ++ mem_region.size = int128_get64(llsize) - 1, ++ mem_region.perm = IOMMU_ACCESS_FLAG(true, section->readonly), ++ ++ r = vhost_iova_tree_map_alloc(v->iova_tree, &mem_region); + if (unlikely(r != IOVA_OK)) { + error_report("Can't allocate a mapping (%d)", r); + goto fail; +@@ -230,11 +231,16 @@ static void vhost_vdpa_listener_region_add(MemoryListener *listener, + vaddr, section->readonly); + if (ret) { + error_report("vhost vdpa map fail!"); +- goto fail; ++ goto fail_map; + } + + return; + ++fail_map: ++ if (v->shadow_vqs_enabled) { ++ vhost_iova_tree_remove(v->iova_tree, &mem_region); ++ } ++ + fail: + /* + * On the initfn path, store the first error in the container so we +-- +2.31.1 + diff --git a/SOURCES/kvm-vdpa-extract-vhost_vdpa_net_cvq_add-from-vhost_vdpa_.patch b/SOURCES/kvm-vdpa-extract-vhost_vdpa_net_cvq_add-from-vhost_vdpa_.patch new file mode 100644 index 0000000..3cc011f --- /dev/null +++ b/SOURCES/kvm-vdpa-extract-vhost_vdpa_net_cvq_add-from-vhost_vdpa_.patch @@ -0,0 +1,153 @@ +From 56f4bebc591893e590481617da7cd7ecffeb166d Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Tue, 23 Aug 2022 20:30:34 +0200 +Subject: [PATCH 19/23] vdpa: extract vhost_vdpa_net_cvq_add from + vhost_vdpa_net_handle_ctrl_avail +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 116: vdpa: Restore device state on destination +RH-Bugzilla: 2114060 +RH-Acked-by: Cindy Lu +RH-Acked-by: Miroslav Rezanina +RH-Commit: [18/21] 08ab71dbf050f5c2e97c622d1915f71a56c135b8 (eperezmartin/qemu-kvm) +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2114060 +Upstream status: git@github.com:jasowang/qemu.git net-next + +So we can reuse it to inject state messages. + +Signed-off-by: Eugenio Pérez +Acked-by: Jason Wang +-- +v7: +* Remove double free error + +v6: +* Do not assume in buffer sent to the device is sizeof(virtio_net_ctrl_ack) + +v5: +* Do not use an artificial !NULL VirtQueueElement +* Use only out size instead of iovec dev_buffers for these functions. + +Signed-off-by: Jason Wang +(cherry picked from commit d9afb1f0ee4d662ed67d3bc1220b943f7e4cfa6f) +--- + net/vhost-vdpa.c | 59 +++++++++++++++++++++++++++++++----------------- + 1 file changed, 38 insertions(+), 21 deletions(-) + +diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c +index 17626feb8d..f09f044ec1 100644 +--- a/net/vhost-vdpa.c ++++ b/net/vhost-vdpa.c +@@ -331,6 +331,38 @@ static void vhost_vdpa_net_cvq_stop(NetClientState *nc) + } + } + ++static ssize_t vhost_vdpa_net_cvq_add(VhostVDPAState *s, size_t out_len, ++ size_t in_len) ++{ ++ /* Buffers for the device */ ++ const struct iovec out = { ++ .iov_base = s->cvq_cmd_out_buffer, ++ .iov_len = out_len, ++ }; ++ const struct iovec in = { ++ .iov_base = s->cvq_cmd_in_buffer, ++ .iov_len = sizeof(virtio_net_ctrl_ack), ++ }; ++ VhostShadowVirtqueue *svq = g_ptr_array_index(s->vhost_vdpa.shadow_vqs, 0); ++ int r; ++ ++ r = vhost_svq_add(svq, &out, 1, &in, 1, NULL); ++ if (unlikely(r != 0)) { ++ if (unlikely(r == -ENOSPC)) { ++ qemu_log_mask(LOG_GUEST_ERROR, "%s: No space on device queue\n", ++ __func__); ++ } ++ return r; ++ } ++ ++ /* ++ * We can poll here since we've had BQL from the time we sent the ++ * descriptor. Also, we need to take the answer before SVQ pulls by itself, ++ * when BQL is released ++ */ ++ return vhost_svq_poll(svq); ++} ++ + static NetClientInfo net_vhost_vdpa_cvq_info = { + .type = NET_CLIENT_DRIVER_VHOST_VDPA, + .size = sizeof(VhostVDPAState), +@@ -387,23 +419,18 @@ static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq, + void *opaque) + { + VhostVDPAState *s = opaque; +- size_t in_len, dev_written; ++ size_t in_len; + virtio_net_ctrl_ack status = VIRTIO_NET_ERR; + /* Out buffer sent to both the vdpa device and the device model */ + struct iovec out = { + .iov_base = s->cvq_cmd_out_buffer, + }; +- /* In buffer sent to the device */ +- const struct iovec dev_in = { +- .iov_base = s->cvq_cmd_in_buffer, +- .iov_len = sizeof(virtio_net_ctrl_ack), +- }; + /* in buffer used for device model */ + const struct iovec in = { + .iov_base = &status, + .iov_len = sizeof(status), + }; +- int r = -EINVAL; ++ ssize_t dev_written = -EINVAL; + bool ok; + + out.iov_len = iov_to_buf(elem->out_sg, elem->out_num, 0, +@@ -414,21 +441,11 @@ static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq, + goto out; + } + +- r = vhost_svq_add(svq, &out, 1, &dev_in, 1, elem); +- if (unlikely(r != 0)) { +- if (unlikely(r == -ENOSPC)) { +- qemu_log_mask(LOG_GUEST_ERROR, "%s: No space on device queue\n", +- __func__); +- } ++ dev_written = vhost_vdpa_net_cvq_add(s, out.iov_len, sizeof(status)); ++ if (unlikely(dev_written < 0)) { + goto out; + } + +- /* +- * We can poll here since we've had BQL from the time we sent the +- * descriptor. Also, we need to take the answer before SVQ pulls by itself, +- * when BQL is released +- */ +- dev_written = vhost_svq_poll(svq); + if (unlikely(dev_written < sizeof(status))) { + error_report("Insufficient written data (%zu)", dev_written); + goto out; +@@ -436,7 +453,7 @@ static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq, + + memcpy(&status, s->cvq_cmd_in_buffer, sizeof(status)); + if (status != VIRTIO_NET_OK) { +- goto out; ++ return VIRTIO_NET_ERR; + } + + status = VIRTIO_NET_ERR; +@@ -453,7 +470,7 @@ out: + } + vhost_svq_push_elem(svq, elem, MIN(in_len, sizeof(status))); + g_free(elem); +- return r; ++ return dev_written < 0 ? dev_written : 0; + } + + static const VhostShadowVirtqueueOps vhost_vdpa_net_svq_ops = { +-- +2.31.1 + diff --git a/SOURCES/kvm-vdpa-manual-forward-CVQ-buffers.patch b/SOURCES/kvm-vdpa-manual-forward-CVQ-buffers.patch new file mode 100644 index 0000000..61909ff --- /dev/null +++ b/SOURCES/kvm-vdpa-manual-forward-CVQ-buffers.patch @@ -0,0 +1,166 @@ +From c33bc0b7f2b5cfa330a6d89d60ee94de129c65c1 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Thu, 21 Jul 2022 16:05:38 +0200 +Subject: [PATCH 23/32] vdpa: manual forward CVQ buffers +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 108: Net Control Virtqueue shadow Support +RH-Commit: [23/27] ce128d5152be7eebf87e186eb8b58c2ed95aff6d (eperezmartin/qemu-kvm) +RH-Bugzilla: 1939363 +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Cindy Lu +RH-Acked-by: Laurent Vivier + +Bugzilla: https://bugzilla.redhat.com/1939363 + +Upstream Status: git://git.qemu.org/qemu.git + +commit bd907ae4b00ebedad5e586af05ea3d6490318d45 +Author: Eugenio Pérez +Date: Wed Jul 20 08:59:42 2022 +0200 + + vdpa: manual forward CVQ buffers + + Do a simple forwarding of CVQ buffers, the same work SVQ could do but + through callbacks. No functional change intended. + + Signed-off-by: Eugenio Pérez + Reviewed-by: Michael S. Tsirkin + Signed-off-by: Jason Wang + +Signed-off-by: Eugenio Pérez +--- + hw/virtio/vhost-vdpa.c | 3 +- + include/hw/virtio/vhost-vdpa.h | 3 ++ + net/vhost-vdpa.c | 58 ++++++++++++++++++++++++++++++++++ + 3 files changed, 63 insertions(+), 1 deletion(-) + +diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c +index 14b02fe079..49effe5462 100644 +--- a/hw/virtio/vhost-vdpa.c ++++ b/hw/virtio/vhost-vdpa.c +@@ -417,7 +417,8 @@ static int vhost_vdpa_init_svq(struct vhost_dev *hdev, struct vhost_vdpa *v, + for (unsigned n = 0; n < hdev->nvqs; ++n) { + g_autoptr(VhostShadowVirtqueue) svq; + +- svq = vhost_svq_new(v->iova_tree, NULL, NULL); ++ svq = vhost_svq_new(v->iova_tree, v->shadow_vq_ops, ++ v->shadow_vq_ops_opaque); + if (unlikely(!svq)) { + error_setg(errp, "Cannot create svq %u", n); + return -1; +diff --git a/include/hw/virtio/vhost-vdpa.h b/include/hw/virtio/vhost-vdpa.h +index 7214eb47dc..1111d85643 100644 +--- a/include/hw/virtio/vhost-vdpa.h ++++ b/include/hw/virtio/vhost-vdpa.h +@@ -15,6 +15,7 @@ + #include + + #include "hw/virtio/vhost-iova-tree.h" ++#include "hw/virtio/vhost-shadow-virtqueue.h" + #include "hw/virtio/virtio.h" + #include "standard-headers/linux/vhost_types.h" + +@@ -35,6 +36,8 @@ typedef struct vhost_vdpa { + /* IOVA mapping used by the Shadow Virtqueue */ + VhostIOVATree *iova_tree; + GPtrArray *shadow_vqs; ++ const VhostShadowVirtqueueOps *shadow_vq_ops; ++ void *shadow_vq_ops_opaque; + struct vhost_dev *dev; + VhostVDPAHostNotifier notifier[VIRTIO_QUEUE_MAX]; + } VhostVDPA; +diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c +index df1e69ee72..2e3b6b10d8 100644 +--- a/net/vhost-vdpa.c ++++ b/net/vhost-vdpa.c +@@ -11,11 +11,14 @@ + + #include "qemu/osdep.h" + #include "clients.h" ++#include "hw/virtio/virtio-net.h" + #include "net/vhost_net.h" + #include "net/vhost-vdpa.h" + #include "hw/virtio/vhost-vdpa.h" + #include "qemu/config-file.h" + #include "qemu/error-report.h" ++#include "qemu/log.h" ++#include "qemu/memalign.h" + #include "qemu/option.h" + #include "qapi/error.h" + #include +@@ -187,6 +190,57 @@ static NetClientInfo net_vhost_vdpa_info = { + .check_peer_type = vhost_vdpa_check_peer_type, + }; + ++/** ++ * Forward buffer for the moment. ++ */ ++static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq, ++ VirtQueueElement *elem, ++ void *opaque) ++{ ++ unsigned int n = elem->out_num + elem->in_num; ++ g_autofree struct iovec *dev_buffers = g_new(struct iovec, n); ++ size_t in_len, dev_written; ++ virtio_net_ctrl_ack status = VIRTIO_NET_ERR; ++ int r; ++ ++ memcpy(dev_buffers, elem->out_sg, elem->out_num); ++ memcpy(dev_buffers + elem->out_num, elem->in_sg, elem->in_num); ++ ++ r = vhost_svq_add(svq, &dev_buffers[0], elem->out_num, &dev_buffers[1], ++ elem->in_num, elem); ++ if (unlikely(r != 0)) { ++ if (unlikely(r == -ENOSPC)) { ++ qemu_log_mask(LOG_GUEST_ERROR, "%s: No space on device queue\n", ++ __func__); ++ } ++ goto out; ++ } ++ ++ /* ++ * We can poll here since we've had BQL from the time we sent the ++ * descriptor. Also, we need to take the answer before SVQ pulls by itself, ++ * when BQL is released ++ */ ++ dev_written = vhost_svq_poll(svq); ++ if (unlikely(dev_written < sizeof(status))) { ++ error_report("Insufficient written data (%zu)", dev_written); ++ } ++ ++out: ++ in_len = iov_from_buf(elem->in_sg, elem->in_num, 0, &status, ++ sizeof(status)); ++ if (unlikely(in_len < sizeof(status))) { ++ error_report("Bad device CVQ written length"); ++ } ++ vhost_svq_push_elem(svq, elem, MIN(in_len, sizeof(status))); ++ g_free(elem); ++ return r; ++} ++ ++static const VhostShadowVirtqueueOps vhost_vdpa_net_svq_ops = { ++ .avail_handler = vhost_vdpa_net_handle_ctrl_avail, ++}; ++ + static NetClientState *net_vhost_vdpa_init(NetClientState *peer, + const char *device, + const char *name, +@@ -211,6 +265,10 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer, + + s->vhost_vdpa.device_fd = vdpa_device_fd; + s->vhost_vdpa.index = queue_pair_index; ++ if (!is_datapath) { ++ s->vhost_vdpa.shadow_vq_ops = &vhost_vdpa_net_svq_ops; ++ s->vhost_vdpa.shadow_vq_ops_opaque = s; ++ } + ret = vhost_vdpa_add(nc, (void *)&s->vhost_vdpa, queue_pair_index, nvqs); + if (ret) { + qemu_del_net_client(nc); +-- +2.31.1 + diff --git a/SOURCES/kvm-vfio-common-remove-spurious-tpm-crb-cmd-misalignment.patch b/SOURCES/kvm-vfio-common-remove-spurious-tpm-crb-cmd-misalignment.patch new file mode 100644 index 0000000..26083c1 --- /dev/null +++ b/SOURCES/kvm-vfio-common-remove-spurious-tpm-crb-cmd-misalignment.patch @@ -0,0 +1,114 @@ +From b90a5878355bd549200ed1eff52ea084325bfc8a Mon Sep 17 00:00:00 2001 +From: Eric Auger +Date: Fri, 6 May 2022 15:25:10 +0200 +Subject: [PATCH 5/5] vfio/common: remove spurious tpm-crb-cmd misalignment + warning +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eric Auger +RH-MergeRequest: 84: vfio/common: Remove spurious tpm-crb-cmd misalignment warning +RH-Commit: [2/2] 9b73a9aec59cb50d5e3468cc553464bf4a73d0a1 (eauger1/centos-qemu-kvm) +RH-Bugzilla: 2037612 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Cornelia Huck +RH-Acked-by: Andrew Jones + +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2037612 +Brew: https://brewweb.engineering.redhat.com/brew/taskinfo?taskID=45166961 +Upstream Status: YES +Tested: With TPM-CRB and VFIO + +The CRB command buffer currently is a RAM MemoryRegion and given +its base address alignment, it causes an error report on +vfio_listener_region_add(). This region could have been a RAM device +region, easing the detection of such safe situation but this option +was not well received. So let's add a helper function that uses the +memory region owner type to detect the situation is safe wrt +the assignment. Other device types can be checked here if such kind +of problem occurs again. + +Conflicts in hw/vfio/common.c +We don't have 8e3b0cbb721 ("Replace qemu_real_host_page variables with inlined functions") + +Signed-off-by: Eric Auger +Reviewed-by: Philippe Mathieu-Daudé +Acked-by: Stefan Berger +Reviewed-by: Cornelia Huck +Link: https://lore.kernel.org/r/20220506132510.1847942-3-eric.auger@redhat.com +Signed-off-by: Alex Williamson +(cherry picked from commit 851d6d1a0ff29a87ec588205842edf6b86d99b5c) +Signed-off-by: Eric Auger +--- + hw/vfio/common.c | 27 ++++++++++++++++++++++++++- + hw/vfio/trace-events | 1 + + 2 files changed, 27 insertions(+), 1 deletion(-) + +diff --git a/hw/vfio/common.c b/hw/vfio/common.c +index 080046e3f5..0fbe0d47af 100644 +--- a/hw/vfio/common.c ++++ b/hw/vfio/common.c +@@ -40,6 +40,7 @@ + #include "trace.h" + #include "qapi/error.h" + #include "migration/migration.h" ++#include "sysemu/tpm.h" + + VFIOGroupList vfio_group_list = + QLIST_HEAD_INITIALIZER(vfio_group_list); +@@ -861,6 +862,22 @@ static void vfio_unregister_ram_discard_listener(VFIOContainer *container, + g_free(vrdl); + } + ++static bool vfio_known_safe_misalignment(MemoryRegionSection *section) ++{ ++ MemoryRegion *mr = section->mr; ++ ++ if (!TPM_IS_CRB(mr->owner)) { ++ return false; ++ } ++ ++ /* this is a known safe misaligned region, just trace for debug purpose */ ++ trace_vfio_known_safe_misalignment(memory_region_name(mr), ++ section->offset_within_address_space, ++ section->offset_within_region, ++ qemu_real_host_page_size); ++ return true; ++} ++ + static void vfio_listener_region_add(MemoryListener *listener, + MemoryRegionSection *section) + { +@@ -884,7 +901,15 @@ static void vfio_listener_region_add(MemoryListener *listener, + if (unlikely((section->offset_within_address_space & + ~qemu_real_host_page_mask) != + (section->offset_within_region & ~qemu_real_host_page_mask))) { +- error_report("%s received unaligned region", __func__); ++ if (!vfio_known_safe_misalignment(section)) { ++ error_report("%s received unaligned region %s iova=0x%"PRIx64 ++ " offset_within_region=0x%"PRIx64 ++ " qemu_real_host_page_size=0x%"PRIxPTR, ++ __func__, memory_region_name(section->mr), ++ section->offset_within_address_space, ++ section->offset_within_region, ++ qemu_real_host_page_size); ++ } + return; + } + +diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events +index 0ef1b5f4a6..582882db91 100644 +--- a/hw/vfio/trace-events ++++ b/hw/vfio/trace-events +@@ -100,6 +100,7 @@ vfio_listener_region_add_skip(uint64_t start, uint64_t end) "SKIPPING region_add + vfio_spapr_group_attach(int groupfd, int tablefd) "Attached groupfd %d to liobn fd %d" + vfio_listener_region_add_iommu(uint64_t start, uint64_t end) "region_add [iommu] 0x%"PRIx64" - 0x%"PRIx64 + vfio_listener_region_add_ram(uint64_t iova_start, uint64_t iova_end, void *vaddr) "region_add [ram] 0x%"PRIx64" - 0x%"PRIx64" [%p]" ++vfio_known_safe_misalignment(const char *name, uint64_t iova, uint64_t offset_within_region, uintptr_t page_size) "Region \"%s\" iova=0x%"PRIx64" offset_within_region=0x%"PRIx64" qemu_real_host_page_size=0x%"PRIxPTR ": cannot be mapped for DMA" + vfio_listener_region_add_no_dma_map(const char *name, uint64_t iova, uint64_t size, uint64_t page_size) "Region \"%s\" 0x%"PRIx64" size=0x%"PRIx64" is not aligned to 0x%"PRIx64" and cannot be mapped for DMA" + vfio_listener_region_del_skip(uint64_t start, uint64_t end) "SKIPPING region_del 0x%"PRIx64" - 0x%"PRIx64 + vfio_listener_region_del(uint64_t start, uint64_t end) "region_del 0x%"PRIx64" - 0x%"PRIx64 +-- +2.31.1 + diff --git a/SOURCES/kvm-vfio-common-remove-spurious-warning-on-vfio_listener.patch b/SOURCES/kvm-vfio-common-remove-spurious-warning-on-vfio_listener.patch new file mode 100644 index 0000000..7e644c5 --- /dev/null +++ b/SOURCES/kvm-vfio-common-remove-spurious-warning-on-vfio_listener.patch @@ -0,0 +1,78 @@ +From 3de8fb9f3dba18d04efa10b70bcec641035effc5 Mon Sep 17 00:00:00 2001 +From: Eric Auger +Date: Tue, 24 May 2022 05:14:05 -0400 +Subject: [PATCH 16/16] vfio/common: remove spurious warning on + vfio_listener_region_del + +RH-Author: Eric Auger +RH-MergeRequest: 101: vfio/common: remove spurious warning on vfio_listener_region_del +RH-Commit: [1/1] dac688b8a981ebb964fea79ea198c329b9cdb551 (eauger1/centos-qemu-kvm) +RH-Bugzilla: 2086262 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Cornelia Huck +RH-Acked-by: Alex Williamson + + Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2086262 + Brew: https://brewweb.engineering.redhat.com/brew/taskinfo?taskID=45876133 + Upstream Status: YES + Tested: With TPM-CRB and VFIO + +851d6d1a0f ("vfio/common: remove spurious tpm-crb-cmd misalignment +warning") removed the warning on vfio_listener_region_add() path. + +However the same warning also hits on region_del path. Let's remove +it and reword the dynamic trace as this can be called on both +map and unmap path. + +Contextual Conflict in hw/vfio/common.c +We don't have 8e3b0cbb721 ("Replace qemu_real_host_page variables with inlined functions") + +Signed-off-by: Eric Auger +Reviewed-by: Cornelia Huck +Link: https://lore.kernel.org/r/20220524091405.416256-1-eric.auger@redhat.com +Fixes: 851d6d1a0ff2 ("vfio/common: remove spurious tpm-crb-cmd misalignment warning") +Signed-off-by: Alex Williamson +(cherry picked from commit ec6600be0dc16982181c7ad80d94c143c0807dd2) +Signed-off-by: Eric Auger +--- + hw/vfio/common.c | 10 +++++++++- + hw/vfio/trace-events | 2 +- + 2 files changed, 10 insertions(+), 2 deletions(-) + +diff --git a/hw/vfio/common.c b/hw/vfio/common.c +index 0fbe0d47af..637981f9a1 100644 +--- a/hw/vfio/common.c ++++ b/hw/vfio/common.c +@@ -1145,7 +1145,15 @@ static void vfio_listener_region_del(MemoryListener *listener, + if (unlikely((section->offset_within_address_space & + ~qemu_real_host_page_mask) != + (section->offset_within_region & ~qemu_real_host_page_mask))) { +- error_report("%s received unaligned region", __func__); ++ if (!vfio_known_safe_misalignment(section)) { ++ error_report("%s received unaligned region %s iova=0x%"PRIx64 ++ " offset_within_region=0x%"PRIx64 ++ " qemu_real_host_page_size=0x%"PRIxPTR, ++ __func__, memory_region_name(section->mr), ++ section->offset_within_address_space, ++ section->offset_within_region, ++ qemu_real_host_page_size); ++ } + return; + } + +diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events +index 582882db91..73dffe9e00 100644 +--- a/hw/vfio/trace-events ++++ b/hw/vfio/trace-events +@@ -100,7 +100,7 @@ vfio_listener_region_add_skip(uint64_t start, uint64_t end) "SKIPPING region_add + vfio_spapr_group_attach(int groupfd, int tablefd) "Attached groupfd %d to liobn fd %d" + vfio_listener_region_add_iommu(uint64_t start, uint64_t end) "region_add [iommu] 0x%"PRIx64" - 0x%"PRIx64 + vfio_listener_region_add_ram(uint64_t iova_start, uint64_t iova_end, void *vaddr) "region_add [ram] 0x%"PRIx64" - 0x%"PRIx64" [%p]" +-vfio_known_safe_misalignment(const char *name, uint64_t iova, uint64_t offset_within_region, uintptr_t page_size) "Region \"%s\" iova=0x%"PRIx64" offset_within_region=0x%"PRIx64" qemu_real_host_page_size=0x%"PRIxPTR ": cannot be mapped for DMA" ++vfio_known_safe_misalignment(const char *name, uint64_t iova, uint64_t offset_within_region, uintptr_t page_size) "Region \"%s\" iova=0x%"PRIx64" offset_within_region=0x%"PRIx64" qemu_real_host_page_size=0x%"PRIxPTR + vfio_listener_region_add_no_dma_map(const char *name, uint64_t iova, uint64_t size, uint64_t page_size) "Region \"%s\" 0x%"PRIx64" size=0x%"PRIx64" is not aligned to 0x%"PRIx64" and cannot be mapped for DMA" + vfio_listener_region_del_skip(uint64_t start, uint64_t end) "SKIPPING region_del 0x%"PRIx64" - 0x%"PRIx64 + vfio_listener_region_del(uint64_t start, uint64_t end) "region_del 0x%"PRIx64" - 0x%"PRIx64 +-- +2.31.1 + diff --git a/SOURCES/kvm-vhost-Add-SVQDescState.patch b/SOURCES/kvm-vhost-Add-SVQDescState.patch new file mode 100644 index 0000000..b1ea4bb --- /dev/null +++ b/SOURCES/kvm-vhost-Add-SVQDescState.patch @@ -0,0 +1,135 @@ +From 14200f493243f73152ea4a4b97274f0ec4fb36fa Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Thu, 21 Jul 2022 15:38:55 +0200 +Subject: [PATCH 15/32] vhost: Add SVQDescState +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 108: Net Control Virtqueue shadow Support +RH-Commit: [15/27] 2e2866f22e37cace8598ff44dfcdc07fcc915d6d (eperezmartin/qemu-kvm) +RH-Bugzilla: 1939363 +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Cindy Lu +RH-Acked-by: Laurent Vivier + +Bugzilla: https://bugzilla.redhat.com/1939363 + +Upstream Status: git://git.qemu.org/qemu.git + +commit 9e87868fcaf5785c8e1490c290505fa32305ff91 +Author: Eugenio Pérez +Date: Wed Jul 20 08:59:34 2022 +0200 + + vhost: Add SVQDescState + + This will allow SVQ to add context to the different queue elements. + + This patch only store the actual element, no functional change intended. + + Signed-off-by: Eugenio Pérez + Reviewed-by: Michael S. Tsirkin + Signed-off-by: Jason Wang + +Signed-off-by: Eugenio Pérez +--- + hw/virtio/vhost-shadow-virtqueue.c | 16 ++++++++-------- + hw/virtio/vhost-shadow-virtqueue.h | 8 ++++++-- + 2 files changed, 14 insertions(+), 10 deletions(-) + +diff --git a/hw/virtio/vhost-shadow-virtqueue.c b/hw/virtio/vhost-shadow-virtqueue.c +index 3cec03d709..a08e3d4025 100644 +--- a/hw/virtio/vhost-shadow-virtqueue.c ++++ b/hw/virtio/vhost-shadow-virtqueue.c +@@ -256,7 +256,7 @@ static int vhost_svq_add(VhostShadowVirtqueue *svq, const struct iovec *out_sg, + return -EINVAL; + } + +- svq->ring_id_maps[qemu_head] = elem; ++ svq->desc_state[qemu_head].elem = elem; + vhost_svq_kick(svq); + return 0; + } +@@ -411,21 +411,21 @@ static VirtQueueElement *vhost_svq_get_buf(VhostShadowVirtqueue *svq, + return NULL; + } + +- if (unlikely(!svq->ring_id_maps[used_elem.id])) { ++ if (unlikely(!svq->desc_state[used_elem.id].elem)) { + qemu_log_mask(LOG_GUEST_ERROR, + "Device %s says index %u is used, but it was not available", + svq->vdev->name, used_elem.id); + return NULL; + } + +- num = svq->ring_id_maps[used_elem.id]->in_num + +- svq->ring_id_maps[used_elem.id]->out_num; ++ num = svq->desc_state[used_elem.id].elem->in_num + ++ svq->desc_state[used_elem.id].elem->out_num; + last_used_chain = vhost_svq_last_desc_of_chain(svq, num, used_elem.id); + svq->desc_next[last_used_chain] = svq->free_head; + svq->free_head = used_elem.id; + + *len = used_elem.len; +- return g_steal_pointer(&svq->ring_id_maps[used_elem.id]); ++ return g_steal_pointer(&svq->desc_state[used_elem.id].elem); + } + + static void vhost_svq_flush(VhostShadowVirtqueue *svq, +@@ -595,7 +595,7 @@ void vhost_svq_start(VhostShadowVirtqueue *svq, VirtIODevice *vdev, + memset(svq->vring.desc, 0, driver_size); + svq->vring.used = qemu_memalign(qemu_real_host_page_size, device_size); + memset(svq->vring.used, 0, device_size); +- svq->ring_id_maps = g_new0(VirtQueueElement *, svq->vring.num); ++ svq->desc_state = g_new0(SVQDescState, svq->vring.num); + svq->desc_next = g_new0(uint16_t, svq->vring.num); + for (unsigned i = 0; i < svq->vring.num - 1; i++) { + svq->desc_next[i] = cpu_to_le16(i + 1); +@@ -620,7 +620,7 @@ void vhost_svq_stop(VhostShadowVirtqueue *svq) + + for (unsigned i = 0; i < svq->vring.num; ++i) { + g_autofree VirtQueueElement *elem = NULL; +- elem = g_steal_pointer(&svq->ring_id_maps[i]); ++ elem = g_steal_pointer(&svq->desc_state[i].elem); + if (elem) { + virtqueue_detach_element(svq->vq, elem, 0); + } +@@ -632,7 +632,7 @@ void vhost_svq_stop(VhostShadowVirtqueue *svq) + } + svq->vq = NULL; + g_free(svq->desc_next); +- g_free(svq->ring_id_maps); ++ g_free(svq->desc_state); + qemu_vfree(svq->vring.desc); + qemu_vfree(svq->vring.used); + } +diff --git a/hw/virtio/vhost-shadow-virtqueue.h b/hw/virtio/vhost-shadow-virtqueue.h +index c132c994e9..d646c35054 100644 +--- a/hw/virtio/vhost-shadow-virtqueue.h ++++ b/hw/virtio/vhost-shadow-virtqueue.h +@@ -15,6 +15,10 @@ + #include "standard-headers/linux/vhost_types.h" + #include "hw/virtio/vhost-iova-tree.h" + ++typedef struct SVQDescState { ++ VirtQueueElement *elem; ++} SVQDescState; ++ + /* Shadow virtqueue to relay notifications */ + typedef struct VhostShadowVirtqueue { + /* Shadow vring */ +@@ -47,8 +51,8 @@ typedef struct VhostShadowVirtqueue { + /* IOVA mapping */ + VhostIOVATree *iova_tree; + +- /* Map for use the guest's descriptors */ +- VirtQueueElement **ring_id_maps; ++ /* SVQ vring descriptors state */ ++ SVQDescState *desc_state; + + /* Next VirtQueue element that guest made available */ + VirtQueueElement *next_guest_avail_elem; +-- +2.31.1 + diff --git a/SOURCES/kvm-vhost-Add-svq-avail_handler-callback.patch b/SOURCES/kvm-vhost-Add-svq-avail_handler-callback.patch new file mode 100644 index 0000000..a8b585d --- /dev/null +++ b/SOURCES/kvm-vhost-Add-svq-avail_handler-callback.patch @@ -0,0 +1,164 @@ +From 433106c286a1961737300ebaece6f10b2747e7d8 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Thu, 21 Jul 2022 15:38:55 +0200 +Subject: [PATCH 20/32] vhost: Add svq avail_handler callback +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 108: Net Control Virtqueue shadow Support +RH-Commit: [20/27] d228eb89d204f8be623bc870503bbf0078dfc9ae (eperezmartin/qemu-kvm) +RH-Bugzilla: 1939363 +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Cindy Lu +RH-Acked-by: Laurent Vivier + +Bugzilla: https://bugzilla.redhat.com/1939363 + +Upstream Status: git://git.qemu.org/qemu.git + +commit e966c0b781aebabd2c0f5eef91678f08ce1d068c +Author: Eugenio Pérez +Date: Wed Jul 20 08:59:39 2022 +0200 + + vhost: Add svq avail_handler callback + + This allows external handlers to be aware of new buffers that the guest + places in the virtqueue. + + When this callback is defined the ownership of the guest's virtqueue + element is transferred to the callback. This means that if the user + wants to forward the descriptor it needs to manually inject it. The + callback is also free to process the command by itself and use the + element with svq_push. + + Signed-off-by: Eugenio Pérez + Reviewed-by: Michael S. Tsirkin + Signed-off-by: Jason Wang + +Signed-off-by: Eugenio Pérez +--- + hw/virtio/vhost-shadow-virtqueue.c | 14 ++++++++++++-- + hw/virtio/vhost-shadow-virtqueue.h | 31 +++++++++++++++++++++++++++++- + hw/virtio/vhost-vdpa.c | 3 ++- + 3 files changed, 44 insertions(+), 4 deletions(-) + +diff --git a/hw/virtio/vhost-shadow-virtqueue.c b/hw/virtio/vhost-shadow-virtqueue.c +index 95d0d7a7ee..e53aac45f6 100644 +--- a/hw/virtio/vhost-shadow-virtqueue.c ++++ b/hw/virtio/vhost-shadow-virtqueue.c +@@ -306,7 +306,11 @@ static void vhost_handle_guest_kick(VhostShadowVirtqueue *svq) + break; + } + +- r = vhost_svq_add_element(svq, elem); ++ if (svq->ops) { ++ r = svq->ops->avail_handler(svq, elem, svq->ops_opaque); ++ } else { ++ r = vhost_svq_add_element(svq, elem); ++ } + if (unlikely(r != 0)) { + if (r == -ENOSPC) { + /* +@@ -685,12 +689,16 @@ void vhost_svq_stop(VhostShadowVirtqueue *svq) + * shadow methods and file descriptors. + * + * @iova_tree: Tree to perform descriptors translations ++ * @ops: SVQ owner callbacks ++ * @ops_opaque: ops opaque pointer + * + * Returns the new virtqueue or NULL. + * + * In case of error, reason is reported through error_report. + */ +-VhostShadowVirtqueue *vhost_svq_new(VhostIOVATree *iova_tree) ++VhostShadowVirtqueue *vhost_svq_new(VhostIOVATree *iova_tree, ++ const VhostShadowVirtqueueOps *ops, ++ void *ops_opaque) + { + g_autofree VhostShadowVirtqueue *svq = g_new0(VhostShadowVirtqueue, 1); + int r; +@@ -712,6 +720,8 @@ VhostShadowVirtqueue *vhost_svq_new(VhostIOVATree *iova_tree) + event_notifier_init_fd(&svq->svq_kick, VHOST_FILE_UNBIND); + event_notifier_set_handler(&svq->hdev_call, vhost_svq_handle_call); + svq->iova_tree = iova_tree; ++ svq->ops = ops; ++ svq->ops_opaque = ops_opaque; + return g_steal_pointer(&svq); + + err_init_hdev_call: +diff --git a/hw/virtio/vhost-shadow-virtqueue.h b/hw/virtio/vhost-shadow-virtqueue.h +index cf442f7dea..d04c34a589 100644 +--- a/hw/virtio/vhost-shadow-virtqueue.h ++++ b/hw/virtio/vhost-shadow-virtqueue.h +@@ -25,6 +25,27 @@ typedef struct SVQDescState { + unsigned int ndescs; + } SVQDescState; + ++typedef struct VhostShadowVirtqueue VhostShadowVirtqueue; ++ ++/** ++ * Callback to handle an avail buffer. ++ * ++ * @svq: Shadow virtqueue ++ * @elem: Element placed in the queue by the guest ++ * @vq_callback_opaque: Opaque ++ * ++ * Returns 0 if the vq is running as expected. ++ * ++ * Note that ownership of elem is transferred to the callback. ++ */ ++typedef int (*VirtQueueAvailCallback)(VhostShadowVirtqueue *svq, ++ VirtQueueElement *elem, ++ void *vq_callback_opaque); ++ ++typedef struct VhostShadowVirtqueueOps { ++ VirtQueueAvailCallback avail_handler; ++} VhostShadowVirtqueueOps; ++ + /* Shadow virtqueue to relay notifications */ + typedef struct VhostShadowVirtqueue { + /* Shadow vring */ +@@ -69,6 +90,12 @@ typedef struct VhostShadowVirtqueue { + */ + uint16_t *desc_next; + ++ /* Caller callbacks */ ++ const VhostShadowVirtqueueOps *ops; ++ ++ /* Caller callbacks opaque */ ++ void *ops_opaque; ++ + /* Next head to expose to the device */ + uint16_t shadow_avail_idx; + +@@ -102,7 +129,9 @@ void vhost_svq_start(VhostShadowVirtqueue *svq, VirtIODevice *vdev, + VirtQueue *vq); + void vhost_svq_stop(VhostShadowVirtqueue *svq); + +-VhostShadowVirtqueue *vhost_svq_new(VhostIOVATree *iova_tree); ++VhostShadowVirtqueue *vhost_svq_new(VhostIOVATree *iova_tree, ++ const VhostShadowVirtqueueOps *ops, ++ void *ops_opaque); + + void vhost_svq_free(gpointer vq); + G_DEFINE_AUTOPTR_CLEANUP_FUNC(VhostShadowVirtqueue, vhost_svq_free); +diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c +index 33dcaa135e..28df57b12e 100644 +--- a/hw/virtio/vhost-vdpa.c ++++ b/hw/virtio/vhost-vdpa.c +@@ -416,8 +416,9 @@ static int vhost_vdpa_init_svq(struct vhost_dev *hdev, struct vhost_vdpa *v, + + shadow_vqs = g_ptr_array_new_full(hdev->nvqs, vhost_svq_free); + for (unsigned n = 0; n < hdev->nvqs; ++n) { +- g_autoptr(VhostShadowVirtqueue) svq = vhost_svq_new(v->iova_tree); ++ g_autoptr(VhostShadowVirtqueue) svq; + ++ svq = vhost_svq_new(v->iova_tree, NULL, NULL); + if (unlikely(!svq)) { + error_setg(errp, "Cannot create svq %u", n); + return -1; +-- +2.31.1 + diff --git a/SOURCES/kvm-vhost-Always-store-new-kick-fd-on-vhost_svq_set_svq_.patch b/SOURCES/kvm-vhost-Always-store-new-kick-fd-on-vhost_svq_set_svq_.patch new file mode 100644 index 0000000..9b6155b --- /dev/null +++ b/SOURCES/kvm-vhost-Always-store-new-kick-fd-on-vhost_svq_set_svq_.patch @@ -0,0 +1,67 @@ +From 6cde15c70c86819033337771eb522e94e3ea9e34 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Tue, 23 Aug 2022 20:20:07 +0200 +Subject: [PATCH 09/23] vhost: Always store new kick fd on + vhost_svq_set_svq_kick_fd +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 116: vdpa: Restore device state on destination +RH-Bugzilla: 2114060 +RH-Acked-by: Cindy Lu +RH-Acked-by: Miroslav Rezanina +RH-Commit: [8/21] a09b8851c39d7cea67414560f6d322e988b9d59a (eperezmartin/qemu-kvm) +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2114060 +Upstream status: git@github.com:jasowang/qemu.git net-next + +We can unbind twice a file descriptor if we call twice +vhost_svq_set_svq_kick_fd because of this. Since it comes from vhost and +not from SVQ, that file descriptor could be a different thing that +guest's vhost notifier. + +Likewise, it can happens the same if a guest start and stop the device +multiple times. + +Reported-by: Lei Yang +Fixes: dff4426fa6 ("vhost: Add Shadow VirtQueue kick forwarding capabilities") +Signed-off-by: Eugenio Pérez +Acked-by: Jason Wang +Signed-off-by: Jason Wang +(cherry picked from commit 6867f29c1425add7e0e8d1d8d58cc0ffbb8df0e4) +--- + hw/virtio/vhost-shadow-virtqueue.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +diff --git a/hw/virtio/vhost-shadow-virtqueue.c b/hw/virtio/vhost-shadow-virtqueue.c +index e53aac45f6..f420311b89 100644 +--- a/hw/virtio/vhost-shadow-virtqueue.c ++++ b/hw/virtio/vhost-shadow-virtqueue.c +@@ -602,13 +602,13 @@ void vhost_svq_set_svq_kick_fd(VhostShadowVirtqueue *svq, int svq_kick_fd) + event_notifier_set_handler(svq_kick, NULL); + } + ++ event_notifier_init_fd(svq_kick, svq_kick_fd); + /* + * event_notifier_set_handler already checks for guest's notifications if + * they arrive at the new file descriptor in the switch, so there is no + * need to explicitly check for them. + */ + if (poll_start) { +- event_notifier_init_fd(svq_kick, svq_kick_fd); + event_notifier_set(svq_kick); + event_notifier_set_handler(svq_kick, vhost_handle_guest_kick_notifier); + } +@@ -655,7 +655,7 @@ void vhost_svq_start(VhostShadowVirtqueue *svq, VirtIODevice *vdev, + */ + void vhost_svq_stop(VhostShadowVirtqueue *svq) + { +- event_notifier_set_handler(&svq->svq_kick, NULL); ++ vhost_svq_set_svq_kick_fd(svq, VHOST_FILE_UNBIND); + g_autofree VirtQueueElement *next_avail_elem = NULL; + + if (!svq->vq) { +-- +2.31.1 + diff --git a/SOURCES/kvm-vhost-Check-for-queue-full-at-vhost_svq_add.patch b/SOURCES/kvm-vhost-Check-for-queue-full-at-vhost_svq_add.patch new file mode 100644 index 0000000..9b09d42 --- /dev/null +++ b/SOURCES/kvm-vhost-Check-for-queue-full-at-vhost_svq_add.patch @@ -0,0 +1,134 @@ +From 893dffb820973361bcef33612a6b924554a856c1 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Thu, 21 Jul 2022 15:38:55 +0200 +Subject: [PATCH 13/32] vhost: Check for queue full at vhost_svq_add +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 108: Net Control Virtqueue shadow Support +RH-Commit: [13/27] d4bd8299fb7733a1e190618dfc92b4b53b7bbeb3 (eperezmartin/qemu-kvm) +RH-Bugzilla: 1939363 +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Cindy Lu +RH-Acked-by: Laurent Vivier + +Bugzilla: https://bugzilla.redhat.com/1939363 + +Upstream Status: git://git.qemu.org/qemu.git + +commit f20b70eb5a68cfd8fef74a13ccdd494ef1cb0221 +Author: Eugenio Pérez +Date: Wed Jul 20 08:59:32 2022 +0200 + + vhost: Check for queue full at vhost_svq_add + + The series need to expose vhost_svq_add with full functionality, + including checking for full queue. + + Signed-off-by: Eugenio Pérez + Reviewed-by: Michael S. Tsirkin + Signed-off-by: Jason Wang + +Signed-off-by: Eugenio Pérez +--- + hw/virtio/vhost-shadow-virtqueue.c | 59 +++++++++++++++++------------- + 1 file changed, 33 insertions(+), 26 deletions(-) + +diff --git a/hw/virtio/vhost-shadow-virtqueue.c b/hw/virtio/vhost-shadow-virtqueue.c +index e3fc3c2658..1d2bab287b 100644 +--- a/hw/virtio/vhost-shadow-virtqueue.c ++++ b/hw/virtio/vhost-shadow-virtqueue.c +@@ -233,21 +233,29 @@ static void vhost_svq_kick(VhostShadowVirtqueue *svq) + * Add an element to a SVQ. + * + * The caller must check that there is enough slots for the new element. It +- * takes ownership of the element: In case of failure, it is free and the SVQ +- * is considered broken. ++ * takes ownership of the element: In case of failure not ENOSPC, it is free. ++ * ++ * Return -EINVAL if element is invalid, -ENOSPC if dev queue is full + */ +-static bool vhost_svq_add(VhostShadowVirtqueue *svq, VirtQueueElement *elem) ++static int vhost_svq_add(VhostShadowVirtqueue *svq, VirtQueueElement *elem) + { + unsigned qemu_head; +- bool ok = vhost_svq_add_split(svq, elem, &qemu_head); ++ unsigned ndescs = elem->in_num + elem->out_num; ++ bool ok; ++ ++ if (unlikely(ndescs > vhost_svq_available_slots(svq))) { ++ return -ENOSPC; ++ } ++ ++ ok = vhost_svq_add_split(svq, elem, &qemu_head); + if (unlikely(!ok)) { + g_free(elem); +- return false; ++ return -EINVAL; + } + + svq->ring_id_maps[qemu_head] = elem; + vhost_svq_kick(svq); +- return true; ++ return 0; + } + + /** +@@ -274,7 +282,7 @@ static void vhost_handle_guest_kick(VhostShadowVirtqueue *svq) + + while (true) { + VirtQueueElement *elem; +- bool ok; ++ int r; + + if (svq->next_guest_avail_elem) { + elem = g_steal_pointer(&svq->next_guest_avail_elem); +@@ -286,25 +294,24 @@ static void vhost_handle_guest_kick(VhostShadowVirtqueue *svq) + break; + } + +- if (elem->out_num + elem->in_num > vhost_svq_available_slots(svq)) { +- /* +- * This condition is possible since a contiguous buffer in GPA +- * does not imply a contiguous buffer in qemu's VA +- * scatter-gather segments. If that happens, the buffer exposed +- * to the device needs to be a chain of descriptors at this +- * moment. +- * +- * SVQ cannot hold more available buffers if we are here: +- * queue the current guest descriptor and ignore further kicks +- * until some elements are used. +- */ +- svq->next_guest_avail_elem = elem; +- return; +- } +- +- ok = vhost_svq_add(svq, elem); +- if (unlikely(!ok)) { +- /* VQ is broken, just return and ignore any other kicks */ ++ r = vhost_svq_add(svq, elem); ++ if (unlikely(r != 0)) { ++ if (r == -ENOSPC) { ++ /* ++ * This condition is possible since a contiguous buffer in ++ * GPA does not imply a contiguous buffer in qemu's VA ++ * scatter-gather segments. If that happens, the buffer ++ * exposed to the device needs to be a chain of descriptors ++ * at this moment. ++ * ++ * SVQ cannot hold more available buffers if we are here: ++ * queue the current guest descriptor and ignore kicks ++ * until some elements are used. ++ */ ++ svq->next_guest_avail_elem = elem; ++ } ++ ++ /* VQ is full or broken, just return and ignore kicks */ + return; + } + } +-- +2.31.1 + diff --git a/SOURCES/kvm-vhost-Decouple-vhost_svq_add-from-VirtQueueElement.patch b/SOURCES/kvm-vhost-Decouple-vhost_svq_add-from-VirtQueueElement.patch new file mode 100644 index 0000000..6755aad --- /dev/null +++ b/SOURCES/kvm-vhost-Decouple-vhost_svq_add-from-VirtQueueElement.patch @@ -0,0 +1,138 @@ +From 5c8de23e185a1a1f0b19eac3c9fa03411c9f545c Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Thu, 21 Jul 2022 15:38:55 +0200 +Subject: [PATCH 14/32] vhost: Decouple vhost_svq_add from VirtQueueElement +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 108: Net Control Virtqueue shadow Support +RH-Commit: [14/27] 463087dd316adc91b9c7a4e6634c6fc1745c1849 (eperezmartin/qemu-kvm) +RH-Bugzilla: 1939363 +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Cindy Lu +RH-Acked-by: Laurent Vivier + +Bugzilla: https://bugzilla.redhat.com/1939363 + +Upstream Status: git://git.qemu.org/qemu.git + +commit 1f46ae65d85f677b660bda46685dd3e94885a7cb +Author: Eugenio Pérez +Date: Wed Jul 20 08:59:33 2022 +0200 + + vhost: Decouple vhost_svq_add from VirtQueueElement + + VirtQueueElement comes from the guest, but we're heading SVQ to be able + to modify the element presented to the device without the guest's + knowledge. + + To do so, make SVQ accept sg buffers directly, instead of using + VirtQueueElement. + + Add vhost_svq_add_element to maintain element convenience. + + Signed-off-by: Eugenio Pérez + Acked-by: Jason Wang + Reviewed-by: Michael S. Tsirkin + Signed-off-by: Jason Wang + +Signed-off-by: Eugenio Pérez +--- + hw/virtio/vhost-shadow-virtqueue.c | 33 ++++++++++++++++++++---------- + 1 file changed, 22 insertions(+), 11 deletions(-) + +diff --git a/hw/virtio/vhost-shadow-virtqueue.c b/hw/virtio/vhost-shadow-virtqueue.c +index 1d2bab287b..3cec03d709 100644 +--- a/hw/virtio/vhost-shadow-virtqueue.c ++++ b/hw/virtio/vhost-shadow-virtqueue.c +@@ -172,30 +172,31 @@ static bool vhost_svq_vring_write_descs(VhostShadowVirtqueue *svq, hwaddr *sg, + } + + static bool vhost_svq_add_split(VhostShadowVirtqueue *svq, +- VirtQueueElement *elem, unsigned *head) ++ const struct iovec *out_sg, size_t out_num, ++ const struct iovec *in_sg, size_t in_num, ++ unsigned *head) + { + unsigned avail_idx; + vring_avail_t *avail = svq->vring.avail; + bool ok; +- g_autofree hwaddr *sgs = g_new(hwaddr, MAX(elem->out_num, elem->in_num)); ++ g_autofree hwaddr *sgs = g_new(hwaddr, MAX(out_num, in_num)); + + *head = svq->free_head; + + /* We need some descriptors here */ +- if (unlikely(!elem->out_num && !elem->in_num)) { ++ if (unlikely(!out_num && !in_num)) { + qemu_log_mask(LOG_GUEST_ERROR, + "Guest provided element with no descriptors"); + return false; + } + +- ok = vhost_svq_vring_write_descs(svq, sgs, elem->out_sg, elem->out_num, +- elem->in_num > 0, false); ++ ok = vhost_svq_vring_write_descs(svq, sgs, out_sg, out_num, in_num > 0, ++ false); + if (unlikely(!ok)) { + return false; + } + +- ok = vhost_svq_vring_write_descs(svq, sgs, elem->in_sg, elem->in_num, false, +- true); ++ ok = vhost_svq_vring_write_descs(svq, sgs, in_sg, in_num, false, true); + if (unlikely(!ok)) { + return false; + } +@@ -237,17 +238,19 @@ static void vhost_svq_kick(VhostShadowVirtqueue *svq) + * + * Return -EINVAL if element is invalid, -ENOSPC if dev queue is full + */ +-static int vhost_svq_add(VhostShadowVirtqueue *svq, VirtQueueElement *elem) ++static int vhost_svq_add(VhostShadowVirtqueue *svq, const struct iovec *out_sg, ++ size_t out_num, const struct iovec *in_sg, ++ size_t in_num, VirtQueueElement *elem) + { + unsigned qemu_head; +- unsigned ndescs = elem->in_num + elem->out_num; ++ unsigned ndescs = in_num + out_num; + bool ok; + + if (unlikely(ndescs > vhost_svq_available_slots(svq))) { + return -ENOSPC; + } + +- ok = vhost_svq_add_split(svq, elem, &qemu_head); ++ ok = vhost_svq_add_split(svq, out_sg, out_num, in_sg, in_num, &qemu_head); + if (unlikely(!ok)) { + g_free(elem); + return -EINVAL; +@@ -258,6 +261,14 @@ static int vhost_svq_add(VhostShadowVirtqueue *svq, VirtQueueElement *elem) + return 0; + } + ++/* Convenience wrapper to add a guest's element to SVQ */ ++static int vhost_svq_add_element(VhostShadowVirtqueue *svq, ++ VirtQueueElement *elem) ++{ ++ return vhost_svq_add(svq, elem->out_sg, elem->out_num, elem->in_sg, ++ elem->in_num, elem); ++} ++ + /** + * Forward available buffers. + * +@@ -294,7 +305,7 @@ static void vhost_handle_guest_kick(VhostShadowVirtqueue *svq) + break; + } + +- r = vhost_svq_add(svq, elem); ++ r = vhost_svq_add_element(svq, elem); + if (unlikely(r != 0)) { + if (r == -ENOSPC) { + /* +-- +2.31.1 + diff --git a/SOURCES/kvm-vhost-Delete-useless-read-memory-barrier.patch b/SOURCES/kvm-vhost-Delete-useless-read-memory-barrier.patch new file mode 100644 index 0000000..f5aad51 --- /dev/null +++ b/SOURCES/kvm-vhost-Delete-useless-read-memory-barrier.patch @@ -0,0 +1,47 @@ +From 773d1bb4e9ea9ca704372e52569955937f91f15c Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Tue, 23 Aug 2022 20:30:28 +0200 +Subject: [PATCH 13/23] vhost: Delete useless read memory barrier +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 116: vdpa: Restore device state on destination +RH-Bugzilla: 2114060 +RH-Acked-by: Cindy Lu +RH-Acked-by: Miroslav Rezanina +RH-Commit: [12/21] 0e238fe934b1fc2c7e10b6f693468bc25ea3243f (eperezmartin/qemu-kvm) +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2114060 +Upstream status: git@github.com:jasowang/qemu.git net-next + +As discussed in previous series [1], this memory barrier is useless with +the atomic read of used idx at vhost_svq_more_used. Deleting it. + +[1] https://lists.nongnu.org/archive/html/qemu-devel/2022-07/msg02616.html + +Signed-off-by: Eugenio Pérez +Acked-by: Jason Wang +Signed-off-by: Jason Wang +(cherry picked from commit cdfb1612ba0f9b76367c96ce26ba94fedc7a0e61) +--- + hw/virtio/vhost-shadow-virtqueue.c | 3 --- + 1 file changed, 3 deletions(-) + +diff --git a/hw/virtio/vhost-shadow-virtqueue.c b/hw/virtio/vhost-shadow-virtqueue.c +index 7792f3db1d..d36afbc547 100644 +--- a/hw/virtio/vhost-shadow-virtqueue.c ++++ b/hw/virtio/vhost-shadow-virtqueue.c +@@ -509,9 +509,6 @@ size_t vhost_svq_poll(VhostShadowVirtqueue *svq) + if (unlikely(g_get_monotonic_time() - start_us > 10e6)) { + return 0; + } +- +- /* Make sure we read new used_idx */ +- smp_rmb(); + } while (true); + } + +-- +2.31.1 + diff --git a/SOURCES/kvm-vhost-Do-not-depend-on-NULL-VirtQueueElement-on-vhos.patch b/SOURCES/kvm-vhost-Do-not-depend-on-NULL-VirtQueueElement-on-vhos.patch new file mode 100644 index 0000000..81ed89e --- /dev/null +++ b/SOURCES/kvm-vhost-Do-not-depend-on-NULL-VirtQueueElement-on-vhos.patch @@ -0,0 +1,63 @@ +From 2f134d800a7ac521a637a0da2116b2603b12c8c0 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Tue, 23 Aug 2022 20:30:29 +0200 +Subject: [PATCH 14/23] vhost: Do not depend on !NULL VirtQueueElement on + vhost_svq_flush +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 116: vdpa: Restore device state on destination +RH-Bugzilla: 2114060 +RH-Acked-by: Cindy Lu +RH-Acked-by: Miroslav Rezanina +RH-Commit: [13/21] 93ec7baa2a29031db25d86b7dc1a949388623370 (eperezmartin/qemu-kvm) +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2114060 +Upstream status: git@github.com:jasowang/qemu.git net-next + +Since QEMU will be able to inject new elements on CVQ to restore the +state, we need not to depend on a VirtQueueElement to know if a new +element has been used by the device or not. Instead of check that, check +if there are new elements only using used idx on vhost_svq_flush. + +Signed-off-by: Eugenio Pérez +Acked-by: Jason Wang +Signed-off-by: Jason Wang +(cherry picked from commit 7599f71c11c08b90f173c35ded1aaa1fdca86f1b) +--- + hw/virtio/vhost-shadow-virtqueue.c | 11 +++++++---- + 1 file changed, 7 insertions(+), 4 deletions(-) + +diff --git a/hw/virtio/vhost-shadow-virtqueue.c b/hw/virtio/vhost-shadow-virtqueue.c +index d36afbc547..c0e3c92e96 100644 +--- a/hw/virtio/vhost-shadow-virtqueue.c ++++ b/hw/virtio/vhost-shadow-virtqueue.c +@@ -499,17 +499,20 @@ static void vhost_svq_flush(VhostShadowVirtqueue *svq, + size_t vhost_svq_poll(VhostShadowVirtqueue *svq) + { + int64_t start_us = g_get_monotonic_time(); ++ uint32_t len; ++ + do { +- uint32_t len; +- VirtQueueElement *elem = vhost_svq_get_buf(svq, &len); +- if (elem) { +- return len; ++ if (vhost_svq_more_used(svq)) { ++ break; + } + + if (unlikely(g_get_monotonic_time() - start_us > 10e6)) { + return 0; + } + } while (true); ++ ++ vhost_svq_get_buf(svq, &len); ++ return len; + } + + /** +-- +2.31.1 + diff --git a/SOURCES/kvm-vhost-Expose-vhost_svq_add.patch b/SOURCES/kvm-vhost-Expose-vhost_svq_add.patch new file mode 100644 index 0000000..70dc774 --- /dev/null +++ b/SOURCES/kvm-vhost-Expose-vhost_svq_add.patch @@ -0,0 +1,73 @@ +From cefd6583a8483c7a80f9cde8f7ad4705983af9e7 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Thu, 21 Jul 2022 15:38:55 +0200 +Subject: [PATCH 18/32] vhost: Expose vhost_svq_add +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 108: Net Control Virtqueue shadow Support +RH-Commit: [18/27] bfb44f597d350336113783bcc9b3c9d9d32ff8c0 (eperezmartin/qemu-kvm) +RH-Bugzilla: 1939363 +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Cindy Lu +RH-Acked-by: Laurent Vivier + +Bugzilla: https://bugzilla.redhat.com/1939363 + +Upstream Status: git://git.qemu.org/qemu.git + +commit d0291f3f284d3bc220cdb13b0d8ac8a44eb5fd4c +Author: Eugenio Pérez +Date: Wed Jul 20 08:59:37 2022 +0200 + + vhost: Expose vhost_svq_add + + This allows external parts of SVQ to forward custom buffers to the + device. + + Signed-off-by: Eugenio Pérez + Reviewed-by: Michael S. Tsirkin + Signed-off-by: Jason Wang + +Signed-off-by: Eugenio Pérez +--- + hw/virtio/vhost-shadow-virtqueue.c | 6 +++--- + hw/virtio/vhost-shadow-virtqueue.h | 3 +++ + 2 files changed, 6 insertions(+), 3 deletions(-) + +diff --git a/hw/virtio/vhost-shadow-virtqueue.c b/hw/virtio/vhost-shadow-virtqueue.c +index 1ce52d5b4a..cb879e7b88 100644 +--- a/hw/virtio/vhost-shadow-virtqueue.c ++++ b/hw/virtio/vhost-shadow-virtqueue.c +@@ -238,9 +238,9 @@ static void vhost_svq_kick(VhostShadowVirtqueue *svq) + * + * Return -EINVAL if element is invalid, -ENOSPC if dev queue is full + */ +-static int vhost_svq_add(VhostShadowVirtqueue *svq, const struct iovec *out_sg, +- size_t out_num, const struct iovec *in_sg, +- size_t in_num, VirtQueueElement *elem) ++int vhost_svq_add(VhostShadowVirtqueue *svq, const struct iovec *out_sg, ++ size_t out_num, const struct iovec *in_sg, size_t in_num, ++ VirtQueueElement *elem) + { + unsigned qemu_head; + unsigned ndescs = in_num + out_num; +diff --git a/hw/virtio/vhost-shadow-virtqueue.h b/hw/virtio/vhost-shadow-virtqueue.h +index d9fc1f1799..dd78f4bec2 100644 +--- a/hw/virtio/vhost-shadow-virtqueue.h ++++ b/hw/virtio/vhost-shadow-virtqueue.h +@@ -86,6 +86,9 @@ bool vhost_svq_valid_features(uint64_t features, Error **errp); + + void vhost_svq_push_elem(VhostShadowVirtqueue *svq, + const VirtQueueElement *elem, uint32_t len); ++int vhost_svq_add(VhostShadowVirtqueue *svq, const struct iovec *out_sg, ++ size_t out_num, const struct iovec *in_sg, size_t in_num, ++ VirtQueueElement *elem); + + void vhost_svq_set_svq_kick_fd(VhostShadowVirtqueue *svq, int svq_kick_fd); + void vhost_svq_set_svq_call_fd(VhostShadowVirtqueue *svq, int call_fd); +-- +2.31.1 + diff --git a/SOURCES/kvm-vhost-Fix-device-s-used-descriptor-dequeue.patch b/SOURCES/kvm-vhost-Fix-device-s-used-descriptor-dequeue.patch new file mode 100644 index 0000000..f149c05 --- /dev/null +++ b/SOURCES/kvm-vhost-Fix-device-s-used-descriptor-dequeue.patch @@ -0,0 +1,83 @@ +From 793d6d56190397624efdcaf6e0112bd12e39c05d Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Thu, 21 Jul 2022 15:25:01 +0200 +Subject: [PATCH 02/32] vhost: Fix device's used descriptor dequeue +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 108: Net Control Virtqueue shadow Support +RH-Commit: [2/27] b92803a0681c94c65d243dd07424522387594760 (eperezmartin/qemu-kvm) +RH-Bugzilla: 1939363 +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Cindy Lu +RH-Acked-by: Laurent Vivier + +Bugzilla: https://bugzilla.redhat.com/1939363 + +Upstream Status: git://git.qemu.org/qemu.git + +commit 81abfa5724c9a6502d7a1d3a67c55f2a303a1170 +Author: Eugenio Pérez +Date: Thu May 12 19:57:43 2022 +0200 + + vhost: Fix device's used descriptor dequeue + + Only the first one of them were properly enqueued back. + + Fixes: 100890f7ca ("vhost: Shadow virtqueue buffers forwarding") + + Signed-off-by: Eugenio Pérez + Message-Id: <20220512175747.142058-3-eperezma@redhat.com> + Reviewed-by: Michael S. Tsirkin + Signed-off-by: Michael S. Tsirkin + +Signed-off-by: Eugenio Pérez +--- + hw/virtio/vhost-shadow-virtqueue.c | 17 +++++++++++++++-- + 1 file changed, 15 insertions(+), 2 deletions(-) + +diff --git a/hw/virtio/vhost-shadow-virtqueue.c b/hw/virtio/vhost-shadow-virtqueue.c +index 3155801f50..31fc50907d 100644 +--- a/hw/virtio/vhost-shadow-virtqueue.c ++++ b/hw/virtio/vhost-shadow-virtqueue.c +@@ -334,12 +334,22 @@ static void vhost_svq_disable_notification(VhostShadowVirtqueue *svq) + svq->vring.avail->flags |= cpu_to_le16(VRING_AVAIL_F_NO_INTERRUPT); + } + ++static uint16_t vhost_svq_last_desc_of_chain(const VhostShadowVirtqueue *svq, ++ uint16_t num, uint16_t i) ++{ ++ for (uint16_t j = 0; j < (num - 1); ++j) { ++ i = le16_to_cpu(svq->desc_next[i]); ++ } ++ ++ return i; ++} ++ + static VirtQueueElement *vhost_svq_get_buf(VhostShadowVirtqueue *svq, + uint32_t *len) + { + const vring_used_t *used = svq->vring.used; + vring_used_elem_t used_elem; +- uint16_t last_used; ++ uint16_t last_used, last_used_chain, num; + + if (!vhost_svq_more_used(svq)) { + return NULL; +@@ -365,7 +375,10 @@ static VirtQueueElement *vhost_svq_get_buf(VhostShadowVirtqueue *svq, + return NULL; + } + +- svq->desc_next[used_elem.id] = svq->free_head; ++ num = svq->ring_id_maps[used_elem.id]->in_num + ++ svq->ring_id_maps[used_elem.id]->out_num; ++ last_used_chain = vhost_svq_last_desc_of_chain(svq, num, used_elem.id); ++ svq->desc_next[last_used_chain] = svq->free_head; + svq->free_head = used_elem.id; + + *len = used_elem.len; +-- +2.31.1 + diff --git a/SOURCES/kvm-vhost-Fix-element-in-vhost_svq_add-failure.patch b/SOURCES/kvm-vhost-Fix-element-in-vhost_svq_add-failure.patch new file mode 100644 index 0000000..51eb700 --- /dev/null +++ b/SOURCES/kvm-vhost-Fix-element-in-vhost_svq_add-failure.patch @@ -0,0 +1,68 @@ +From aa99cf129923e0203c0caeb3b4e94a0eb973746f Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Thu, 21 Jul 2022 15:36:38 +0200 +Subject: [PATCH 04/32] vhost: Fix element in vhost_svq_add failure +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 108: Net Control Virtqueue shadow Support +RH-Commit: [4/27] 96689c99a47dd49591c0d126cb1fbb975b2f79b4 (eperezmartin/qemu-kvm) +RH-Bugzilla: 1939363 +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Cindy Lu +RH-Acked-by: Laurent Vivier + +Bugzilla: https://bugzilla.redhat.com/1939363 + +Upstream Status: git://git.qemu.org/qemu.git + +commit 5181db132b587754dda3a520eec923b87a65bbb7 +Author: Eugenio Pérez +Date: Thu May 12 19:57:47 2022 +0200 + + vhost: Fix element in vhost_svq_add failure + + Coverity rightly reports that is not free in that case. + + Fixes: Coverity CID 1487559 + Fixes: 100890f7ca ("vhost: Shadow virtqueue buffers forwarding") + + Signed-off-by: Eugenio Pérez + Message-Id: <20220512175747.142058-7-eperezma@redhat.com> + Reviewed-by: Michael S. Tsirkin + Signed-off-by: Michael S. Tsirkin + +Signed-off-by: Eugenio Pérez +--- + hw/virtio/vhost-shadow-virtqueue.c | 8 ++++++++ + 1 file changed, 8 insertions(+) + +diff --git a/hw/virtio/vhost-shadow-virtqueue.c b/hw/virtio/vhost-shadow-virtqueue.c +index 31fc50907d..06d0bb39d9 100644 +--- a/hw/virtio/vhost-shadow-virtqueue.c ++++ b/hw/virtio/vhost-shadow-virtqueue.c +@@ -199,11 +199,19 @@ static bool vhost_svq_add_split(VhostShadowVirtqueue *svq, + return true; + } + ++/** ++ * Add an element to a SVQ. ++ * ++ * The caller must check that there is enough slots for the new element. It ++ * takes ownership of the element: In case of failure, it is free and the SVQ ++ * is considered broken. ++ */ + static bool vhost_svq_add(VhostShadowVirtqueue *svq, VirtQueueElement *elem) + { + unsigned qemu_head; + bool ok = vhost_svq_add_split(svq, elem, &qemu_head); + if (unlikely(!ok)) { ++ g_free(elem); + return false; + } + +-- +2.31.1 + diff --git a/SOURCES/kvm-vhost-Get-vring-base-from-vq-not-svq.patch b/SOURCES/kvm-vhost-Get-vring-base-from-vq-not-svq.patch new file mode 100644 index 0000000..1c8e586 --- /dev/null +++ b/SOURCES/kvm-vhost-Get-vring-base-from-vq-not-svq.patch @@ -0,0 +1,87 @@ +From 3f2ba7cce6b272a8b5c8953e8923e799e4aa7b88 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Mon, 18 Jul 2022 14:05:45 +0200 +Subject: [PATCH 02/23] vhost: Get vring base from vq, not svq +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 116: vdpa: Restore device state on destination +RH-Bugzilla: 2114060 +RH-Acked-by: Cindy Lu +RH-Acked-by: Miroslav Rezanina +RH-Commit: [1/21] e7e0294bbc98f69ccdbc4af4715857e77b017f80 (eperezmartin/qemu-kvm) +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2114060 +Upstream status: Merged + +The SVQ vring used idx usually match with the guest visible one, as long +as all the guest buffers (GPA) maps to exactly one buffer within qemu's +VA. However, as we can see in virtqueue_map_desc, a single guest buffer +could map to many buffers in SVQ vring. + +Also, its also a mistake to rewind them at the source of migration. +Since VirtQueue is able to migrate the inflight descriptors, its +responsability of the destination to perform the rewind just in case it +cannot report the inflight descriptors to the device. + +This makes easier to migrate between backends or to recover them in +vhost devices that support set in flight descriptors. + +Fixes: 6d0b22266633 ("vdpa: Adapt vhost_vdpa_get_vring_base to SVQ") +Signed-off-by: Eugenio Pérez +Signed-off-by: Jason Wang +(cherry picked from commit 2fdac348fd3d243bb964937236af3cc27ae7af2b) +--- + hw/virtio/vhost-vdpa.c | 24 ++++++++++++------------ + 1 file changed, 12 insertions(+), 12 deletions(-) + +diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c +index 03dc6014b0..96334ab5b6 100644 +--- a/hw/virtio/vhost-vdpa.c ++++ b/hw/virtio/vhost-vdpa.c +@@ -1177,7 +1177,18 @@ static int vhost_vdpa_set_vring_base(struct vhost_dev *dev, + struct vhost_vring_state *ring) + { + struct vhost_vdpa *v = dev->opaque; ++ VirtQueue *vq = virtio_get_queue(dev->vdev, ring->index); + ++ /* ++ * vhost-vdpa devices does not support in-flight requests. Set all of them ++ * as available. ++ * ++ * TODO: This is ok for networking, but other kinds of devices might ++ * have problems with these retransmissions. ++ */ ++ while (virtqueue_rewind(vq, 1)) { ++ continue; ++ } + if (v->shadow_vqs_enabled) { + /* + * Device vring base was set at device start. SVQ base is handled by +@@ -1193,21 +1204,10 @@ static int vhost_vdpa_get_vring_base(struct vhost_dev *dev, + struct vhost_vring_state *ring) + { + struct vhost_vdpa *v = dev->opaque; +- int vdpa_idx = ring->index - dev->vq_index; + int ret; + + if (v->shadow_vqs_enabled) { +- VhostShadowVirtqueue *svq = g_ptr_array_index(v->shadow_vqs, vdpa_idx); +- +- /* +- * Setting base as last used idx, so destination will see as available +- * all the entries that the device did not use, including the in-flight +- * processing ones. +- * +- * TODO: This is ok for networking, but other kinds of devices might +- * have problems with these retransmissions. +- */ +- ring->num = svq->last_used_idx; ++ ring->num = virtio_queue_get_last_avail_idx(dev->vdev, ring->index); + return 0; + } + +-- +2.31.1 + diff --git a/SOURCES/kvm-vhost-Move-vhost_svq_kick-call-to-vhost_svq_add.patch b/SOURCES/kvm-vhost-Move-vhost_svq_kick-call-to-vhost_svq_add.patch new file mode 100644 index 0000000..513d7b4 --- /dev/null +++ b/SOURCES/kvm-vhost-Move-vhost_svq_kick-call-to-vhost_svq_add.patch @@ -0,0 +1,61 @@ +From 3a944d8cd3d35b2398ff68d9ed8ea51d27dfab3c Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Thu, 21 Jul 2022 15:38:55 +0200 +Subject: [PATCH 12/32] vhost: Move vhost_svq_kick call to vhost_svq_add +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 108: Net Control Virtqueue shadow Support +RH-Commit: [12/27] 29a7e1fb4992c4beca1e9a3379bb4c8a0f567459 (eperezmartin/qemu-kvm) +RH-Bugzilla: 1939363 +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Cindy Lu +RH-Acked-by: Laurent Vivier + +Bugzilla: https://bugzilla.redhat.com/1939363 + +Upstream Status: git://git.qemu.org/qemu.git + +commit 98b5adef8493a2bfad6655cfee84299e88bedbf7 +Author: Eugenio Pérez +Date: Wed Jul 20 08:59:31 2022 +0200 + + vhost: Move vhost_svq_kick call to vhost_svq_add + + The series needs to expose vhost_svq_add with full functionality, + including kick + + Signed-off-by: Eugenio Pérez + Reviewed-by: Michael S. Tsirkin + Signed-off-by: Jason Wang + +Signed-off-by: Eugenio Pérez +--- + hw/virtio/vhost-shadow-virtqueue.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/hw/virtio/vhost-shadow-virtqueue.c b/hw/virtio/vhost-shadow-virtqueue.c +index 05cd39d1eb..e3fc3c2658 100644 +--- a/hw/virtio/vhost-shadow-virtqueue.c ++++ b/hw/virtio/vhost-shadow-virtqueue.c +@@ -246,6 +246,7 @@ static bool vhost_svq_add(VhostShadowVirtqueue *svq, VirtQueueElement *elem) + } + + svq->ring_id_maps[qemu_head] = elem; ++ vhost_svq_kick(svq); + return true; + } + +@@ -306,7 +307,6 @@ static void vhost_handle_guest_kick(VhostShadowVirtqueue *svq) + /* VQ is broken, just return and ignore any other kicks */ + return; + } +- vhost_svq_kick(svq); + } + + virtio_queue_set_notification(svq->vq, true); +-- +2.31.1 + diff --git a/SOURCES/kvm-vhost-Reorder-vhost_svq_kick.patch b/SOURCES/kvm-vhost-Reorder-vhost_svq_kick.patch new file mode 100644 index 0000000..f61f3c3 --- /dev/null +++ b/SOURCES/kvm-vhost-Reorder-vhost_svq_kick.patch @@ -0,0 +1,88 @@ +From fdbf66e4c70de16ab36d70ea591322b1b24df591 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Thu, 21 Jul 2022 15:38:55 +0200 +Subject: [PATCH 11/32] vhost: Reorder vhost_svq_kick +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 108: Net Control Virtqueue shadow Support +RH-Commit: [11/27] 1d08b97eb3960a0f85f2dd48c3331b803f7ea205 (eperezmartin/qemu-kvm) +RH-Bugzilla: 1939363 +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Cindy Lu +RH-Acked-by: Laurent Vivier + +Bugzilla: https://bugzilla.redhat.com/1939363 + +Upstream Status: git://git.qemu.org/qemu.git + +commit d93a2405ca6efa9dc1c420cee5a34bd8242818d0 +Author: Eugenio Pérez +Date: Wed Jul 20 08:59:30 2022 +0200 + + vhost: Reorder vhost_svq_kick + + Future code needs to call it from vhost_svq_add. + + No functional change intended. + + Signed-off-by: Eugenio Pérez + Reviewed-by: Michael S. Tsirkin + Signed-off-by: Jason Wang + +Signed-off-by: Eugenio Pérez +--- + hw/virtio/vhost-shadow-virtqueue.c | 28 ++++++++++++++-------------- + 1 file changed, 14 insertions(+), 14 deletions(-) + +diff --git a/hw/virtio/vhost-shadow-virtqueue.c b/hw/virtio/vhost-shadow-virtqueue.c +index 9c46c3a8fa..05cd39d1eb 100644 +--- a/hw/virtio/vhost-shadow-virtqueue.c ++++ b/hw/virtio/vhost-shadow-virtqueue.c +@@ -215,6 +215,20 @@ static bool vhost_svq_add_split(VhostShadowVirtqueue *svq, + return true; + } + ++static void vhost_svq_kick(VhostShadowVirtqueue *svq) ++{ ++ /* ++ * We need to expose the available array entries before checking the used ++ * flags ++ */ ++ smp_mb(); ++ if (svq->vring.used->flags & VRING_USED_F_NO_NOTIFY) { ++ return; ++ } ++ ++ event_notifier_set(&svq->hdev_kick); ++} ++ + /** + * Add an element to a SVQ. + * +@@ -235,20 +249,6 @@ static bool vhost_svq_add(VhostShadowVirtqueue *svq, VirtQueueElement *elem) + return true; + } + +-static void vhost_svq_kick(VhostShadowVirtqueue *svq) +-{ +- /* +- * We need to expose the available array entries before checking the used +- * flags +- */ +- smp_mb(); +- if (svq->vring.used->flags & VRING_USED_F_NO_NOTIFY) { +- return; +- } +- +- event_notifier_set(&svq->hdev_kick); +-} +- + /** + * Forward available buffers. + * +-- +2.31.1 + diff --git a/SOURCES/kvm-vhost-Track-descriptor-chain-in-private-at-SVQ.patch b/SOURCES/kvm-vhost-Track-descriptor-chain-in-private-at-SVQ.patch new file mode 100644 index 0000000..31bfccc --- /dev/null +++ b/SOURCES/kvm-vhost-Track-descriptor-chain-in-private-at-SVQ.patch @@ -0,0 +1,123 @@ +From 486647551223cc01f4dba87197030bbf4e674f0f Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Thu, 21 Jul 2022 15:24:48 +0200 +Subject: [PATCH 01/32] vhost: Track descriptor chain in private at SVQ +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 108: Net Control Virtqueue shadow Support +RH-Commit: [1/27] 26d16dc383e3064ac6e4288d5c52b39fee0ad204 (eperezmartin/qemu-kvm) +RH-Bugzilla: 1939363 +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Cindy Lu +RH-Acked-by: Laurent Vivier + +Bugzilla: https://bugzilla.redhat.com/1939363 + +Upstream Status: git://git.qemu.org/qemu.git + +commit 495fe3a78749c39c0e772c4e1a55d6cb8a7e5292 +Author: Eugenio Pérez +Date: Thu May 12 19:57:42 2022 +0200 + + vhost: Track descriptor chain in private at SVQ + + The device could have access to modify them, and it definitely have + access when we implement packed vq. Harden SVQ maintaining a private + copy of the descriptor chain. Other fields like buffer addresses are + already maintained sepparatedly. + + Signed-off-by: Eugenio Pérez + Message-Id: <20220512175747.142058-2-eperezma@redhat.com> + Reviewed-by: Michael S. Tsirkin + Signed-off-by: Michael S. Tsirkin + +Signed-off-by: Eugenio Pérez +--- + hw/virtio/vhost-shadow-virtqueue.c | 12 +++++++----- + hw/virtio/vhost-shadow-virtqueue.h | 6 ++++++ + 2 files changed, 13 insertions(+), 5 deletions(-) + +diff --git a/hw/virtio/vhost-shadow-virtqueue.c b/hw/virtio/vhost-shadow-virtqueue.c +index b232803d1b..3155801f50 100644 +--- a/hw/virtio/vhost-shadow-virtqueue.c ++++ b/hw/virtio/vhost-shadow-virtqueue.c +@@ -138,6 +138,7 @@ static void vhost_vring_write_descs(VhostShadowVirtqueue *svq, hwaddr *sg, + for (n = 0; n < num; n++) { + if (more_descs || (n + 1 < num)) { + descs[i].flags = flags | cpu_to_le16(VRING_DESC_F_NEXT); ++ descs[i].next = cpu_to_le16(svq->desc_next[i]); + } else { + descs[i].flags = flags; + } +@@ -145,10 +146,10 @@ static void vhost_vring_write_descs(VhostShadowVirtqueue *svq, hwaddr *sg, + descs[i].len = cpu_to_le32(iovec[n].iov_len); + + last = i; +- i = cpu_to_le16(descs[i].next); ++ i = cpu_to_le16(svq->desc_next[i]); + } + +- svq->free_head = le16_to_cpu(descs[last].next); ++ svq->free_head = le16_to_cpu(svq->desc_next[last]); + } + + static bool vhost_svq_add_split(VhostShadowVirtqueue *svq, +@@ -336,7 +337,6 @@ static void vhost_svq_disable_notification(VhostShadowVirtqueue *svq) + static VirtQueueElement *vhost_svq_get_buf(VhostShadowVirtqueue *svq, + uint32_t *len) + { +- vring_desc_t *descs = svq->vring.desc; + const vring_used_t *used = svq->vring.used; + vring_used_elem_t used_elem; + uint16_t last_used; +@@ -365,7 +365,7 @@ static VirtQueueElement *vhost_svq_get_buf(VhostShadowVirtqueue *svq, + return NULL; + } + +- descs[used_elem.id].next = svq->free_head; ++ svq->desc_next[used_elem.id] = svq->free_head; + svq->free_head = used_elem.id; + + *len = used_elem.len; +@@ -540,8 +540,9 @@ void vhost_svq_start(VhostShadowVirtqueue *svq, VirtIODevice *vdev, + svq->vring.used = qemu_memalign(qemu_real_host_page_size, device_size); + memset(svq->vring.used, 0, device_size); + svq->ring_id_maps = g_new0(VirtQueueElement *, svq->vring.num); ++ svq->desc_next = g_new0(uint16_t, svq->vring.num); + for (unsigned i = 0; i < svq->vring.num - 1; i++) { +- svq->vring.desc[i].next = cpu_to_le16(i + 1); ++ svq->desc_next[i] = cpu_to_le16(i + 1); + } + } + +@@ -574,6 +575,7 @@ void vhost_svq_stop(VhostShadowVirtqueue *svq) + virtqueue_detach_element(svq->vq, next_avail_elem, 0); + } + svq->vq = NULL; ++ g_free(svq->desc_next); + g_free(svq->ring_id_maps); + qemu_vfree(svq->vring.desc); + qemu_vfree(svq->vring.used); +diff --git a/hw/virtio/vhost-shadow-virtqueue.h b/hw/virtio/vhost-shadow-virtqueue.h +index e5e24c536d..c132c994e9 100644 +--- a/hw/virtio/vhost-shadow-virtqueue.h ++++ b/hw/virtio/vhost-shadow-virtqueue.h +@@ -53,6 +53,12 @@ typedef struct VhostShadowVirtqueue { + /* Next VirtQueue element that guest made available */ + VirtQueueElement *next_guest_avail_elem; + ++ /* ++ * Backup next field for each descriptor so we can recover securely, not ++ * needing to trust the device access. ++ */ ++ uint16_t *desc_next; ++ + /* Next head to expose to the device */ + uint16_t shadow_avail_idx; + +-- +2.31.1 + diff --git a/SOURCES/kvm-vhost-Track-number-of-descs-in-SVQDescState.patch b/SOURCES/kvm-vhost-Track-number-of-descs-in-SVQDescState.patch new file mode 100644 index 0000000..6a2e147 --- /dev/null +++ b/SOURCES/kvm-vhost-Track-number-of-descs-in-SVQDescState.patch @@ -0,0 +1,81 @@ +From 24b8cf88f53f9fc7cb393c9cad908f759980bfee Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Thu, 21 Jul 2022 15:38:55 +0200 +Subject: [PATCH 16/32] vhost: Track number of descs in SVQDescState +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 108: Net Control Virtqueue shadow Support +RH-Commit: [16/27] 26f30cb6dd35c1eb1ddabe25113431bed3d744aa (eperezmartin/qemu-kvm) +RH-Bugzilla: 1939363 +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Cindy Lu +RH-Acked-by: Laurent Vivier + +Bugzilla: https://bugzilla.redhat.com/1939363 + +Upstream Status: git://git.qemu.org/qemu.git + +commit ac4cfdc6f39c06732d27554523f9d5f8a53b4ffa +Author: Eugenio Pérez +Date: Wed Jul 20 08:59:35 2022 +0200 + + vhost: Track number of descs in SVQDescState + + A guest's buffer continuos on GPA may need multiple descriptors on + qemu's VA, so SVQ should track its length sepparatedly. + + Signed-off-by: Eugenio Pérez + Reviewed-by: Michael S. Tsirkin + Signed-off-by: Jason Wang + +Signed-off-by: Eugenio Pérez +--- + hw/virtio/vhost-shadow-virtqueue.c | 4 ++-- + hw/virtio/vhost-shadow-virtqueue.h | 6 ++++++ + 2 files changed, 8 insertions(+), 2 deletions(-) + +diff --git a/hw/virtio/vhost-shadow-virtqueue.c b/hw/virtio/vhost-shadow-virtqueue.c +index a08e3d4025..4d99075e73 100644 +--- a/hw/virtio/vhost-shadow-virtqueue.c ++++ b/hw/virtio/vhost-shadow-virtqueue.c +@@ -257,6 +257,7 @@ static int vhost_svq_add(VhostShadowVirtqueue *svq, const struct iovec *out_sg, + } + + svq->desc_state[qemu_head].elem = elem; ++ svq->desc_state[qemu_head].ndescs = ndescs; + vhost_svq_kick(svq); + return 0; + } +@@ -418,8 +419,7 @@ static VirtQueueElement *vhost_svq_get_buf(VhostShadowVirtqueue *svq, + return NULL; + } + +- num = svq->desc_state[used_elem.id].elem->in_num + +- svq->desc_state[used_elem.id].elem->out_num; ++ num = svq->desc_state[used_elem.id].ndescs; + last_used_chain = vhost_svq_last_desc_of_chain(svq, num, used_elem.id); + svq->desc_next[last_used_chain] = svq->free_head; + svq->free_head = used_elem.id; +diff --git a/hw/virtio/vhost-shadow-virtqueue.h b/hw/virtio/vhost-shadow-virtqueue.h +index d646c35054..5c7e7cbab6 100644 +--- a/hw/virtio/vhost-shadow-virtqueue.h ++++ b/hw/virtio/vhost-shadow-virtqueue.h +@@ -17,6 +17,12 @@ + + typedef struct SVQDescState { + VirtQueueElement *elem; ++ ++ /* ++ * Number of descriptors exposed to the device. May or may not match ++ * guest's ++ */ ++ unsigned int ndescs; + } SVQDescState; + + /* Shadow virtqueue to relay notifications */ +-- +2.31.1 + diff --git a/SOURCES/kvm-vhost-add-vhost_svq_poll.patch b/SOURCES/kvm-vhost-add-vhost_svq_poll.patch new file mode 100644 index 0000000..fa27e5e --- /dev/null +++ b/SOURCES/kvm-vhost-add-vhost_svq_poll.patch @@ -0,0 +1,92 @@ +From 0ab3da1092362470d256b433c546bd365d34f930 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Thu, 21 Jul 2022 15:38:55 +0200 +Subject: [PATCH 19/32] vhost: add vhost_svq_poll +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 108: Net Control Virtqueue shadow Support +RH-Commit: [19/27] 6807bb0bb6e5183b46a03b12b4027c7d767e8555 (eperezmartin/qemu-kvm) +RH-Bugzilla: 1939363 +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Cindy Lu +RH-Acked-by: Laurent Vivier + +Bugzilla: https://bugzilla.redhat.com/1939363 + +Upstream Status: git://git.qemu.org/qemu.git + +commit 3f44d13dda83d390cc9563e56e7d337e4f6223f4 +Author: Eugenio Pérez +Date: Wed Jul 20 08:59:38 2022 +0200 + + vhost: add vhost_svq_poll + + It allows the Shadow Control VirtQueue to wait for the device to use the + available buffers. + + Signed-off-by: Eugenio Pérez + Reviewed-by: Michael S. Tsirkin + Signed-off-by: Jason Wang + +Signed-off-by: Eugenio Pérez +--- + hw/virtio/vhost-shadow-virtqueue.c | 27 +++++++++++++++++++++++++++ + hw/virtio/vhost-shadow-virtqueue.h | 1 + + 2 files changed, 28 insertions(+) + +diff --git a/hw/virtio/vhost-shadow-virtqueue.c b/hw/virtio/vhost-shadow-virtqueue.c +index cb879e7b88..95d0d7a7ee 100644 +--- a/hw/virtio/vhost-shadow-virtqueue.c ++++ b/hw/virtio/vhost-shadow-virtqueue.c +@@ -485,6 +485,33 @@ static void vhost_svq_flush(VhostShadowVirtqueue *svq, + } while (!vhost_svq_enable_notification(svq)); + } + ++/** ++ * Poll the SVQ for one device used buffer. ++ * ++ * This function race with main event loop SVQ polling, so extra ++ * synchronization is needed. ++ * ++ * Return the length written by the device. ++ */ ++size_t vhost_svq_poll(VhostShadowVirtqueue *svq) ++{ ++ int64_t start_us = g_get_monotonic_time(); ++ do { ++ uint32_t len; ++ VirtQueueElement *elem = vhost_svq_get_buf(svq, &len); ++ if (elem) { ++ return len; ++ } ++ ++ if (unlikely(g_get_monotonic_time() - start_us > 10e6)) { ++ return 0; ++ } ++ ++ /* Make sure we read new used_idx */ ++ smp_rmb(); ++ } while (true); ++} ++ + /** + * Forward used buffers. + * +diff --git a/hw/virtio/vhost-shadow-virtqueue.h b/hw/virtio/vhost-shadow-virtqueue.h +index dd78f4bec2..cf442f7dea 100644 +--- a/hw/virtio/vhost-shadow-virtqueue.h ++++ b/hw/virtio/vhost-shadow-virtqueue.h +@@ -89,6 +89,7 @@ void vhost_svq_push_elem(VhostShadowVirtqueue *svq, + int vhost_svq_add(VhostShadowVirtqueue *svq, const struct iovec *out_sg, + size_t out_num, const struct iovec *in_sg, size_t in_num, + VirtQueueElement *elem); ++size_t vhost_svq_poll(VhostShadowVirtqueue *svq); + + void vhost_svq_set_svq_kick_fd(VhostShadowVirtqueue *svq, int svq_kick_fd); + void vhost_svq_set_svq_call_fd(VhostShadowVirtqueue *svq, int call_fd); +-- +2.31.1 + diff --git a/SOURCES/kvm-vhost-add-vhost_svq_push_elem.patch b/SOURCES/kvm-vhost-add-vhost_svq_push_elem.patch new file mode 100644 index 0000000..2a9ec40 --- /dev/null +++ b/SOURCES/kvm-vhost-add-vhost_svq_push_elem.patch @@ -0,0 +1,83 @@ +From a26eb02b3a49c5d1163685ba5b83b67138c09047 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Thu, 21 Jul 2022 15:38:55 +0200 +Subject: [PATCH 17/32] vhost: add vhost_svq_push_elem +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 108: Net Control Virtqueue shadow Support +RH-Commit: [17/27] d064b40a262f2dfdc9f648d250aa8c8020c40385 (eperezmartin/qemu-kvm) +RH-Bugzilla: 1939363 +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Cindy Lu +RH-Acked-by: Laurent Vivier + +Bugzilla: https://bugzilla.redhat.com/1939363 + +Upstream Status: git://git.qemu.org/qemu.git + +commit 432efd144e990b6e040862de25f8f0b6a6eeb03d +Author: Eugenio Pérez +Date: Wed Jul 20 08:59:36 2022 +0200 + + vhost: add vhost_svq_push_elem + + This function allows external SVQ users to return guest's available + buffers. + + Signed-off-by: Eugenio Pérez + Reviewed-by: Michael S. Tsirkin + Signed-off-by: Jason Wang + +Signed-off-by: Eugenio Pérez +--- + hw/virtio/vhost-shadow-virtqueue.c | 16 ++++++++++++++++ + hw/virtio/vhost-shadow-virtqueue.h | 3 +++ + 2 files changed, 19 insertions(+) + +diff --git a/hw/virtio/vhost-shadow-virtqueue.c b/hw/virtio/vhost-shadow-virtqueue.c +index 4d99075e73..1ce52d5b4a 100644 +--- a/hw/virtio/vhost-shadow-virtqueue.c ++++ b/hw/virtio/vhost-shadow-virtqueue.c +@@ -428,6 +428,22 @@ static VirtQueueElement *vhost_svq_get_buf(VhostShadowVirtqueue *svq, + return g_steal_pointer(&svq->desc_state[used_elem.id].elem); + } + ++/** ++ * Push an element to SVQ, returning it to the guest. ++ */ ++void vhost_svq_push_elem(VhostShadowVirtqueue *svq, ++ const VirtQueueElement *elem, uint32_t len) ++{ ++ virtqueue_push(svq->vq, elem, len); ++ if (svq->next_guest_avail_elem) { ++ /* ++ * Avail ring was full when vhost_svq_flush was called, so it's a ++ * good moment to make more descriptors available if possible. ++ */ ++ vhost_handle_guest_kick(svq); ++ } ++} ++ + static void vhost_svq_flush(VhostShadowVirtqueue *svq, + bool check_for_avail_queue) + { +diff --git a/hw/virtio/vhost-shadow-virtqueue.h b/hw/virtio/vhost-shadow-virtqueue.h +index 5c7e7cbab6..d9fc1f1799 100644 +--- a/hw/virtio/vhost-shadow-virtqueue.h ++++ b/hw/virtio/vhost-shadow-virtqueue.h +@@ -84,6 +84,9 @@ typedef struct VhostShadowVirtqueue { + + bool vhost_svq_valid_features(uint64_t features, Error **errp); + ++void vhost_svq_push_elem(VhostShadowVirtqueue *svq, ++ const VirtQueueElement *elem, uint32_t len); ++ + void vhost_svq_set_svq_kick_fd(VhostShadowVirtqueue *svq, int svq_kick_fd); + void vhost_svq_set_svq_call_fd(VhostShadowVirtqueue *svq, int call_fd); + void vhost_svq_get_vring_addr(const VhostShadowVirtqueue *svq, +-- +2.31.1 + diff --git a/SOURCES/kvm-vhost-move-descriptor-translation-to-vhost_svq_vring.patch b/SOURCES/kvm-vhost-move-descriptor-translation-to-vhost_svq_vring.patch new file mode 100644 index 0000000..08bcaf2 --- /dev/null +++ b/SOURCES/kvm-vhost-move-descriptor-translation-to-vhost_svq_vring.patch @@ -0,0 +1,120 @@ +From 2bdea90bfbce3b8d5bfa86178a942a470b85b835 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Thu, 21 Jul 2022 15:38:55 +0200 +Subject: [PATCH 07/32] vhost: move descriptor translation to + vhost_svq_vring_write_descs +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 108: Net Control Virtqueue shadow Support +RH-Commit: [7/27] 5533c72065e4ebf8ea7db966c976a3b29bdafb82 (eperezmartin/qemu-kvm) +RH-Bugzilla: 1939363 +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Cindy Lu +RH-Acked-by: Laurent Vivier + +Bugzilla: https://bugzilla.redhat.com/1939363 + +Upstream Status: git://git.qemu.org/qemu.git + +commit 009c2549bb9dc7f7061009eb87f2a53d4b364983 +Author: Eugenio Pérez +Date: Wed Jul 20 08:59:26 2022 +0200 + + vhost: move descriptor translation to vhost_svq_vring_write_descs + + It's done for both in and out descriptors so it's better placed here. + + Acked-by: Jason Wang + Signed-off-by: Eugenio Pérez + Reviewed-by: Michael S. Tsirkin + Signed-off-by: Jason Wang + +Signed-off-by: Eugenio Pérez +--- + hw/virtio/vhost-shadow-virtqueue.c | 38 +++++++++++++++++++++--------- + 1 file changed, 27 insertions(+), 11 deletions(-) + +diff --git a/hw/virtio/vhost-shadow-virtqueue.c b/hw/virtio/vhost-shadow-virtqueue.c +index 06d0bb39d9..3fbda1e3d4 100644 +--- a/hw/virtio/vhost-shadow-virtqueue.c ++++ b/hw/virtio/vhost-shadow-virtqueue.c +@@ -122,17 +122,35 @@ static bool vhost_svq_translate_addr(const VhostShadowVirtqueue *svq, + return true; + } + +-static void vhost_vring_write_descs(VhostShadowVirtqueue *svq, hwaddr *sg, +- const struct iovec *iovec, size_t num, +- bool more_descs, bool write) ++/** ++ * Write descriptors to SVQ vring ++ * ++ * @svq: The shadow virtqueue ++ * @sg: Cache for hwaddr ++ * @iovec: The iovec from the guest ++ * @num: iovec length ++ * @more_descs: True if more descriptors come in the chain ++ * @write: True if they are writeable descriptors ++ * ++ * Return true if success, false otherwise and print error. ++ */ ++static bool vhost_svq_vring_write_descs(VhostShadowVirtqueue *svq, hwaddr *sg, ++ const struct iovec *iovec, size_t num, ++ bool more_descs, bool write) + { + uint16_t i = svq->free_head, last = svq->free_head; + unsigned n; + uint16_t flags = write ? cpu_to_le16(VRING_DESC_F_WRITE) : 0; + vring_desc_t *descs = svq->vring.desc; ++ bool ok; + + if (num == 0) { +- return; ++ return true; ++ } ++ ++ ok = vhost_svq_translate_addr(svq, sg, iovec, num); ++ if (unlikely(!ok)) { ++ return false; + } + + for (n = 0; n < num; n++) { +@@ -150,6 +168,7 @@ static void vhost_vring_write_descs(VhostShadowVirtqueue *svq, hwaddr *sg, + } + + svq->free_head = le16_to_cpu(svq->desc_next[last]); ++ return true; + } + + static bool vhost_svq_add_split(VhostShadowVirtqueue *svq, +@@ -169,21 +188,18 @@ static bool vhost_svq_add_split(VhostShadowVirtqueue *svq, + return false; + } + +- ok = vhost_svq_translate_addr(svq, sgs, elem->out_sg, elem->out_num); ++ ok = vhost_svq_vring_write_descs(svq, sgs, elem->out_sg, elem->out_num, ++ elem->in_num > 0, false); + if (unlikely(!ok)) { + return false; + } +- vhost_vring_write_descs(svq, sgs, elem->out_sg, elem->out_num, +- elem->in_num > 0, false); +- + +- ok = vhost_svq_translate_addr(svq, sgs, elem->in_sg, elem->in_num); ++ ok = vhost_svq_vring_write_descs(svq, sgs, elem->in_sg, elem->in_num, false, ++ true); + if (unlikely(!ok)) { + return false; + } + +- vhost_vring_write_descs(svq, sgs, elem->in_sg, elem->in_num, false, true); +- + /* + * Put the entry in the available array (but don't update avail->idx until + * they do sync). +-- +2.31.1 + diff --git a/SOURCES/kvm-vhost-net-fix-improper-cleanup-in-vhost_net_start.patch b/SOURCES/kvm-vhost-net-fix-improper-cleanup-in-vhost_net_start.patch index e0df99e..70e8f59 100644 --- a/SOURCES/kvm-vhost-net-fix-improper-cleanup-in-vhost_net_start.patch +++ b/SOURCES/kvm-vhost-net-fix-improper-cleanup-in-vhost_net_start.patch @@ -1,18 +1,18 @@ -From 1e3faef7048c8d36c9e3f004c7e08d96b30d055f Mon Sep 17 00:00:00 2001 +From edb2bd99355f300b512c040e91f5870ea14a5d7e Mon Sep 17 00:00:00 2001 From: Si-Wei Liu Date: Fri, 6 May 2022 19:28:15 -0700 -Subject: [PATCH 4/7] vhost-net: fix improper cleanup in vhost_net_start +Subject: [PATCH 11/16] vhost-net: fix improper cleanup in vhost_net_start MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit -RH-Author: Cindy Lu -RH-MergeRequest: 204: vdpa :sync the Multiqueue fixes for vhost-vDPA -RH-Commit: [4/7] 31575b626fd5b381a4640e4f2608033bb141dc62 -RH-Bugzilla: 2095795 -RH-Acked-by: Laurent Vivier +RH-Author: Jason Wang +RH-MergeRequest: 98: Multiqueue fixes for vhost-vDPA +RH-Commit: [4/7] e88e482dd4b344f0cc887a358268beaed4d62917 (jasowang/qemu-kvm-cs) +RH-Bugzilla: 2070804 RH-Acked-by: Eugenio Pérez -RH-Acked-by: Jason Wang +RH-Acked-by: Laurent Vivier +RH-Acked-by: Cindy Lu vhost_net_start() missed a corresponding stop_one() upon error from vhost_set_vring_enable(). While at it, make the error handling for @@ -24,7 +24,7 @@ Message-Id: <1651890498-24478-5-git-send-email-si-wei.liu@oracle.com> Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin (cherry picked from commit 6f3910b5eee00b8cc959e94659c0d524c482a418) -Signed-off-by: Cindy Lu +Signed-off-by: Jason Wang --- hw/net/vhost_net.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/SOURCES/kvm-vhost-net-vdpa-add-stubs-for-when-no-virtio-net-devi.patch b/SOURCES/kvm-vhost-net-vdpa-add-stubs-for-when-no-virtio-net-devi.patch new file mode 100644 index 0000000..31677fd --- /dev/null +++ b/SOURCES/kvm-vhost-net-vdpa-add-stubs-for-when-no-virtio-net-devi.patch @@ -0,0 +1,87 @@ +From a9095850da8dd4ea3fdb725cb7f79118144e22fa Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Thu, 21 Jul 2022 15:39:27 +0200 +Subject: [PATCH 22/32] vhost-net-vdpa: add stubs for when no virtio-net device + is present +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 108: Net Control Virtqueue shadow Support +RH-Commit: [22/27] a2b25a805bb06094a5fab27ce8f82bee12a9fcb5 (eperezmartin/qemu-kvm) +RH-Bugzilla: 1939363 +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Cindy Lu +RH-Acked-by: Laurent Vivier + +Bugzilla: https://bugzilla.redhat.com/1939363 + +Upstream Status: git://git.qemu.org/qemu.git + +commit 94c643732dc110d04bbdf0eb43c41bce23b3593e +Author: Eugenio Pérez +Date: Wed Jul 20 08:59:41 2022 +0200 + + vhost-net-vdpa: add stubs for when no virtio-net device is present + + net/vhost-vdpa.c will need functions that are declared in + vhost-shadow-virtqueue.c, that needs functions of virtio-net.c. + + Copy the vhost-vdpa-stub.c code so + only the constructor net_init_vhost_vdpa needs to be defined. + + Signed-off-by: Eugenio Pérez + Signed-off-by: Jason Wang + +Signed-off-by: Eugenio Pérez +--- + net/meson.build | 3 ++- + net/vhost-vdpa-stub.c | 21 +++++++++++++++++++++ + 2 files changed, 23 insertions(+), 1 deletion(-) + create mode 100644 net/vhost-vdpa-stub.c + +diff --git a/net/meson.build b/net/meson.build +index c965e83b26..116a9e7cbb 100644 +--- a/net/meson.build ++++ b/net/meson.build +@@ -41,7 +41,8 @@ endif + softmmu_ss.add(when: 'CONFIG_POSIX', if_true: files(tap_posix)) + softmmu_ss.add(when: 'CONFIG_WIN32', if_true: files('tap-win32.c')) + if have_vhost_net_vdpa +- softmmu_ss.add(files('vhost-vdpa.c')) ++ softmmu_ss.add(when: 'CONFIG_VIRTIO_NET', if_true: files('vhost-vdpa.c'), if_false: files('vhost-vdpa-stub.c')) ++ softmmu_ss.add(when: 'CONFIG_ALL', if_true: files('vhost-vdpa-stub.c')) + endif + + subdir('can') +diff --git a/net/vhost-vdpa-stub.c b/net/vhost-vdpa-stub.c +new file mode 100644 +index 0000000000..1732ed2443 +--- /dev/null ++++ b/net/vhost-vdpa-stub.c +@@ -0,0 +1,21 @@ ++/* ++ * vhost-vdpa-stub.c ++ * ++ * Copyright (c) 2022 Red Hat, Inc. ++ * ++ * This work is licensed under the terms of the GNU GPL, version 2 or later. ++ * See the COPYING file in the top-level directory. ++ * ++ */ ++ ++#include "qemu/osdep.h" ++#include "clients.h" ++#include "net/vhost-vdpa.h" ++#include "qapi/error.h" ++ ++int net_init_vhost_vdpa(const Netdev *netdev, const char *name, ++ NetClientState *peer, Error **errp) ++{ ++ error_setg(errp, "vhost-vdpa requires frontend driver virtio-net-*"); ++ return -1; ++} +-- +2.31.1 + diff --git a/SOURCES/kvm-vhost-stop-transfer-elem-ownership-in-vhost_handle_g.patch b/SOURCES/kvm-vhost-stop-transfer-elem-ownership-in-vhost_handle_g.patch new file mode 100644 index 0000000..7125f6a --- /dev/null +++ b/SOURCES/kvm-vhost-stop-transfer-elem-ownership-in-vhost_handle_g.patch @@ -0,0 +1,80 @@ +From 45305ab202fa2191962152e5a501a9a13e31a0b2 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Tue, 23 Aug 2022 20:30:26 +0200 +Subject: [PATCH 11/23] vhost: stop transfer elem ownership in + vhost_handle_guest_kick +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 116: vdpa: Restore device state on destination +RH-Bugzilla: 2114060 +RH-Acked-by: Cindy Lu +RH-Acked-by: Miroslav Rezanina +RH-Commit: [10/21] 697a5c0ad59efe27abf447f7965091993bc39756 (eperezmartin/qemu-kvm) +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2114060 +Upstream status: git@github.com:jasowang/qemu.git net-next + +It was easier to allow vhost_svq_add to handle the memory. Now that we +will allow qemu to add elements to a SVQ without the guest's knowledge, +it's better to handle it in the caller. + +Signed-off-by: Eugenio Pérez +Acked-by: Jason Wang +Signed-off-by: Jason Wang +(cherry picked from commit eb42df8bb2c92a7313343d97409cd99ccba25b25) +--- + hw/virtio/vhost-shadow-virtqueue.c | 10 ++++------ + 1 file changed, 4 insertions(+), 6 deletions(-) + +diff --git a/hw/virtio/vhost-shadow-virtqueue.c b/hw/virtio/vhost-shadow-virtqueue.c +index f420311b89..2ae47d90a1 100644 +--- a/hw/virtio/vhost-shadow-virtqueue.c ++++ b/hw/virtio/vhost-shadow-virtqueue.c +@@ -233,9 +233,6 @@ static void vhost_svq_kick(VhostShadowVirtqueue *svq) + /** + * Add an element to a SVQ. + * +- * The caller must check that there is enough slots for the new element. It +- * takes ownership of the element: In case of failure not ENOSPC, it is free. +- * + * Return -EINVAL if element is invalid, -ENOSPC if dev queue is full + */ + int vhost_svq_add(VhostShadowVirtqueue *svq, const struct iovec *out_sg, +@@ -252,7 +249,6 @@ int vhost_svq_add(VhostShadowVirtqueue *svq, const struct iovec *out_sg, + + ok = vhost_svq_add_split(svq, out_sg, out_num, in_sg, in_num, &qemu_head); + if (unlikely(!ok)) { +- g_free(elem); + return -EINVAL; + } + +@@ -293,7 +289,7 @@ static void vhost_handle_guest_kick(VhostShadowVirtqueue *svq) + virtio_queue_set_notification(svq->vq, false); + + while (true) { +- VirtQueueElement *elem; ++ g_autofree VirtQueueElement *elem; + int r; + + if (svq->next_guest_avail_elem) { +@@ -324,12 +320,14 @@ static void vhost_handle_guest_kick(VhostShadowVirtqueue *svq) + * queue the current guest descriptor and ignore kicks + * until some elements are used. + */ +- svq->next_guest_avail_elem = elem; ++ svq->next_guest_avail_elem = g_steal_pointer(&elem); + } + + /* VQ is full or broken, just return and ignore kicks */ + return; + } ++ /* elem belongs to SVQ or external caller now */ ++ elem = NULL; + } + + virtio_queue_set_notification(svq->vq, true); +-- +2.31.1 + diff --git a/SOURCES/kvm-vhost-use-SVQ-element-ndescs-instead-of-opaque-data-.patch b/SOURCES/kvm-vhost-use-SVQ-element-ndescs-instead-of-opaque-data-.patch new file mode 100644 index 0000000..b908739 --- /dev/null +++ b/SOURCES/kvm-vhost-use-SVQ-element-ndescs-instead-of-opaque-data-.patch @@ -0,0 +1,55 @@ +From 78b7d9af26ae802b3ca0d7b794b366ab4d515647 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Tue, 23 Aug 2022 20:30:27 +0200 +Subject: [PATCH 12/23] vhost: use SVQ element ndescs instead of opaque data + for desc validation +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 116: vdpa: Restore device state on destination +RH-Bugzilla: 2114060 +RH-Acked-by: Cindy Lu +RH-Acked-by: Miroslav Rezanina +RH-Commit: [11/21] 536ba65ff7241c4dc66362294ba8de4354260d6f (eperezmartin/qemu-kvm) +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2114060 +Upstream status: git@github.com:jasowang/qemu.git net-next + +Since we're going to allow SVQ to add elements without the guest's +knowledge and without its own VirtQueueElement, it's easier to check if +an element is a valid head checking a different thing than the +VirtQueueElement. + +Signed-off-by: Eugenio Pérez +Acked-by: Jason Wang +Signed-off-by: Jason Wang +(cherry picked from commit 70e0841722deb363b53cdcd465af12a0d1461b60) +--- + hw/virtio/vhost-shadow-virtqueue.c | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +diff --git a/hw/virtio/vhost-shadow-virtqueue.c b/hw/virtio/vhost-shadow-virtqueue.c +index 2ae47d90a1..7792f3db1d 100644 +--- a/hw/virtio/vhost-shadow-virtqueue.c ++++ b/hw/virtio/vhost-shadow-virtqueue.c +@@ -414,7 +414,7 @@ static VirtQueueElement *vhost_svq_get_buf(VhostShadowVirtqueue *svq, + return NULL; + } + +- if (unlikely(!svq->desc_state[used_elem.id].elem)) { ++ if (unlikely(!svq->desc_state[used_elem.id].ndescs)) { + qemu_log_mask(LOG_GUEST_ERROR, + "Device %s says index %u is used, but it was not available", + svq->vdev->name, used_elem.id); +@@ -422,6 +422,7 @@ static VirtQueueElement *vhost_svq_get_buf(VhostShadowVirtqueue *svq, + } + + num = svq->desc_state[used_elem.id].ndescs; ++ svq->desc_state[used_elem.id].ndescs = 0; + last_used_chain = vhost_svq_last_desc_of_chain(svq, num, used_elem.id); + svq->desc_next[last_used_chain] = svq->free_head; + svq->free_head = used_elem.id; +-- +2.31.1 + diff --git a/SOURCES/kvm-vhost-vdpa-backend-feature-should-set-only-once.patch b/SOURCES/kvm-vhost-vdpa-backend-feature-should-set-only-once.patch index 961174f..747bf5f 100644 --- a/SOURCES/kvm-vhost-vdpa-backend-feature-should-set-only-once.patch +++ b/SOURCES/kvm-vhost-vdpa-backend-feature-should-set-only-once.patch @@ -1,18 +1,18 @@ -From 4e7f13419c3c45563210e8aed01ebbdf0dd43a01 Mon Sep 17 00:00:00 2001 +From 46c5a35aa56cf0dd55376638dbf7d46e85f497e1 Mon Sep 17 00:00:00 2001 From: Si-Wei Liu Date: Fri, 6 May 2022 19:28:16 -0700 -Subject: [PATCH 5/7] vhost-vdpa: backend feature should set only once +Subject: [PATCH 12/16] vhost-vdpa: backend feature should set only once MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit -RH-Author: Cindy Lu -RH-MergeRequest: 204: vdpa :sync the Multiqueue fixes for vhost-vDPA -RH-Commit: [5/7] 338375ebeab833b8ddd7c7f501aa348f28953778 -RH-Bugzilla: 2095795 -RH-Acked-by: Laurent Vivier +RH-Author: Jason Wang +RH-MergeRequest: 98: Multiqueue fixes for vhost-vDPA +RH-Commit: [5/7] 7531bb8da0c99b29997e8bfc6d1e811daf3cdd38 (jasowang/qemu-kvm-cs) +RH-Bugzilla: 2070804 RH-Acked-by: Eugenio Pérez -RH-Acked-by: Jason Wang +RH-Acked-by: Laurent Vivier +RH-Acked-by: Cindy Lu The vhost_vdpa_one_time_request() branch in vhost_vdpa_set_backend_cap() incorrectly sends down @@ -35,16 +35,16 @@ Message-Id: <1651890498-24478-6-git-send-email-si-wei.liu@oracle.com> Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin (cherry picked from commit 6aee7e4233f6467f69531fcd352adff028f3f5ea) -Signed-off-by: Cindy Lu +Signed-off-by: Jason Wang --- hw/virtio/vhost-vdpa.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c -index 78da48a333..a9be24776a 100644 +index 8adf7c0b92..6e3dbd9e89 100644 --- a/hw/virtio/vhost-vdpa.c +++ b/hw/virtio/vhost-vdpa.c -@@ -525,7 +525,7 @@ static int vhost_vdpa_set_backend_cap(struct vhost_dev *dev) +@@ -665,7 +665,7 @@ static int vhost_vdpa_set_backend_cap(struct vhost_dev *dev) features &= f; diff --git a/SOURCES/kvm-vhost-vdpa-change-name-and-polarity-for-vhost_vdpa_o.patch b/SOURCES/kvm-vhost-vdpa-change-name-and-polarity-for-vhost_vdpa_o.patch index 4a971c3..2466557 100644 --- a/SOURCES/kvm-vhost-vdpa-change-name-and-polarity-for-vhost_vdpa_o.patch +++ b/SOURCES/kvm-vhost-vdpa-change-name-and-polarity-for-vhost_vdpa_o.patch @@ -1,19 +1,19 @@ -From 0074686ee2de7ffb06b4eb2f9c14a2f7dcea248b Mon Sep 17 00:00:00 2001 +From 58acdab17ec00ab76105ab92a51c5ba4dec3df5a Mon Sep 17 00:00:00 2001 From: Si-Wei Liu Date: Fri, 6 May 2022 19:28:17 -0700 -Subject: [PATCH 6/7] vhost-vdpa: change name and polarity for +Subject: [PATCH 13/16] vhost-vdpa: change name and polarity for vhost_vdpa_one_time_request() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit -RH-Author: Cindy Lu -RH-MergeRequest: 204: vdpa :sync the Multiqueue fixes for vhost-vDPA -RH-Commit: [6/7] 9cc673a62032fdf8c84e3d82ff504ae4f4100ecf -RH-Bugzilla: 2095795 -RH-Acked-by: Laurent Vivier +RH-Author: Jason Wang +RH-MergeRequest: 98: Multiqueue fixes for vhost-vDPA +RH-Commit: [6/7] 7029778f463a136ff412c63b86b6953390e47bf8 (jasowang/qemu-kvm-cs) +RH-Bugzilla: 2070804 RH-Acked-by: Eugenio Pérez -RH-Acked-by: Jason Wang +RH-Acked-by: Laurent Vivier +RH-Acked-by: Cindy Lu The name vhost_vdpa_one_time_request() was confusing. No matter whatever it returns, its typical occurrence had @@ -34,16 +34,16 @@ Signed-off-by: Michael S. Tsirkin Reviewed-by: Stefano Garzarella Acked-by: Jason Wang (cherry picked from commit d71b0609fc04217e28d17009f04d74b08be6f466) -Signed-off-by: Cindy Lu +Signed-off-by: Jason Wang --- hw/virtio/vhost-vdpa.c | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c -index a9be24776a..38bbcb3c18 100644 +index 6e3dbd9e89..33dcaa135e 100644 --- a/hw/virtio/vhost-vdpa.c +++ b/hw/virtio/vhost-vdpa.c -@@ -319,11 +319,18 @@ static void vhost_vdpa_get_iova_range(struct vhost_vdpa *v) +@@ -366,11 +366,18 @@ static void vhost_vdpa_get_iova_range(struct vhost_vdpa *v) v->iova_range.last); } @@ -63,8 +63,8 @@ index a9be24776a..38bbcb3c18 100644 + return v->index == 0; } - static int vhost_vdpa_init(struct vhost_dev *dev, void *opaque, Error **errp) -@@ -351,7 +358,7 @@ static int vhost_vdpa_init(struct vhost_dev *dev, void *opaque, Error **errp) + static int vhost_vdpa_get_dev_features(struct vhost_dev *dev, +@@ -451,7 +458,7 @@ static int vhost_vdpa_init(struct vhost_dev *dev, void *opaque, Error **errp) vhost_vdpa_get_iova_range(v); @@ -73,7 +73,7 @@ index a9be24776a..38bbcb3c18 100644 return 0; } -@@ -468,7 +475,7 @@ static int vhost_vdpa_memslots_limit(struct vhost_dev *dev) +@@ -594,7 +601,7 @@ static int vhost_vdpa_memslots_limit(struct vhost_dev *dev) static int vhost_vdpa_set_mem_table(struct vhost_dev *dev, struct vhost_memory *mem) { @@ -82,8 +82,8 @@ index a9be24776a..38bbcb3c18 100644 return 0; } -@@ -496,7 +503,7 @@ static int vhost_vdpa_set_features(struct vhost_dev *dev, - { +@@ -623,7 +630,7 @@ static int vhost_vdpa_set_features(struct vhost_dev *dev, + struct vhost_vdpa *v = dev->opaque; int ret; - if (vhost_vdpa_one_time_request(dev)) { @@ -91,7 +91,7 @@ index a9be24776a..38bbcb3c18 100644 return 0; } -@@ -525,7 +532,7 @@ static int vhost_vdpa_set_backend_cap(struct vhost_dev *dev) +@@ -665,7 +672,7 @@ static int vhost_vdpa_set_backend_cap(struct vhost_dev *dev) features &= f; @@ -100,16 +100,16 @@ index a9be24776a..38bbcb3c18 100644 r = vhost_vdpa_call(dev, VHOST_SET_BACKEND_FEATURES, &features); if (r) { return -EFAULT; -@@ -670,7 +677,7 @@ static int vhost_vdpa_dev_start(struct vhost_dev *dev, bool started) - static int vhost_vdpa_set_log_base(struct vhost_dev *dev, uint64_t base, +@@ -1118,7 +1125,7 @@ static int vhost_vdpa_set_log_base(struct vhost_dev *dev, uint64_t base, struct vhost_log *log) { -- if (vhost_vdpa_one_time_request(dev)) { -+ if (!vhost_vdpa_first_dev(dev)) { + struct vhost_vdpa *v = dev->opaque; +- if (v->shadow_vqs_enabled || vhost_vdpa_one_time_request(dev)) { ++ if (v->shadow_vqs_enabled || !vhost_vdpa_first_dev(dev)) { return 0; } -@@ -739,7 +746,7 @@ static int vhost_vdpa_get_features(struct vhost_dev *dev, +@@ -1240,7 +1247,7 @@ static int vhost_vdpa_get_features(struct vhost_dev *dev, static int vhost_vdpa_set_owner(struct vhost_dev *dev) { diff --git a/SOURCES/kvm-vhost-vdpa-fix-improper-cleanup-in-net_init_vhost_vd.patch b/SOURCES/kvm-vhost-vdpa-fix-improper-cleanup-in-net_init_vhost_vd.patch index c9a4d7f..7716cbf 100644 --- a/SOURCES/kvm-vhost-vdpa-fix-improper-cleanup-in-net_init_vhost_vd.patch +++ b/SOURCES/kvm-vhost-vdpa-fix-improper-cleanup-in-net_init_vhost_vd.patch @@ -1,18 +1,18 @@ -From b140a9fdeaab84d4a2d8828604ffb6aa8367dcbe Mon Sep 17 00:00:00 2001 +From 3142102adb98f46518c0ac1773b0c48710c6bed6 Mon Sep 17 00:00:00 2001 From: Si-Wei Liu Date: Fri, 6 May 2022 19:28:14 -0700 -Subject: [PATCH 3/7] vhost-vdpa: fix improper cleanup in net_init_vhost_vdpa +Subject: [PATCH 10/16] vhost-vdpa: fix improper cleanup in net_init_vhost_vdpa MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit -RH-Author: Cindy Lu -RH-MergeRequest: 204: vdpa :sync the Multiqueue fixes for vhost-vDPA -RH-Commit: [3/7] 600138cb9945013179f5a3c14f52d637c4b9f6c7 -RH-Bugzilla: 2095795 -RH-Acked-by: Laurent Vivier +RH-Author: Jason Wang +RH-MergeRequest: 98: Multiqueue fixes for vhost-vDPA +RH-Commit: [3/7] c83ff6c97d34cfae3c3447edde934b42a9ace75f (jasowang/qemu-kvm-cs) +RH-Bugzilla: 2070804 RH-Acked-by: Eugenio Pérez -RH-Acked-by: Jason Wang +RH-Acked-by: Laurent Vivier +RH-Acked-by: Cindy Lu ... such that no memory leaks on dangling net clients in case of error. @@ -23,13 +23,13 @@ Message-Id: <1651890498-24478-4-git-send-email-si-wei.liu@oracle.com> Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin (cherry picked from commit 9bd055073e375c8a0d7ebce925e05d914d69fc7f) -Signed-off-by: Cindy Lu +Signed-off-by: Jason Wang --- net/vhost-vdpa.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c -index 25dd6dd975..814f704687 100644 +index 1e9fe47c03..df1e69ee72 100644 --- a/net/vhost-vdpa.c +++ b/net/vhost-vdpa.c @@ -306,7 +306,9 @@ int net_init_vhost_vdpa(const Netdev *netdev, const char *name, @@ -42,7 +42,7 @@ index 25dd6dd975..814f704687 100644 + } } qemu_close(vdpa_device_fd); - g_free(ncs); + -- 2.31.1 diff --git a/SOURCES/kvm-vhost-vsock-detach-the-virqueue-element-in-case-of-e.patch b/SOURCES/kvm-vhost-vsock-detach-the-virqueue-element-in-case-of-e.patch deleted file mode 100644 index 7f4388a..0000000 --- a/SOURCES/kvm-vhost-vsock-detach-the-virqueue-element-in-case-of-e.patch +++ /dev/null @@ -1,77 +0,0 @@ -From 3a8dff1446aaa9a3b93a16ea027214064e84a582 Mon Sep 17 00:00:00 2001 -From: Jon Maloy -Date: Thu, 14 Apr 2022 10:38:26 -0400 -Subject: [PATCH 3/3] vhost-vsock: detach the virqueue element in case of error - -RH-Author: Jon Maloy -RH-MergeRequest: 179: vhost-vsock: detach the virqueue element in case of error -RH-Commit: [1/1] 9275dbff40eb3c7be2abca8369055ca4a1e1e52d (jmaloy/qemu-kvm) -RH-Bugzilla: 2075640 -RH-Acked-by: Miroslav Rezanina -RH-Acked-by: Stefano Garzarella -RH-Acked-by: Laurent Vivier - -Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2075640 -Upstream: Merged -CVE: CVE-2022-26354 - -commit 8d1b247f3748ac4078524130c6d7ae42b6140aaf -Author: Stefano Garzarella -Date: Mon Feb 28 10:50:58 2022 +0100 - - vhost-vsock: detach the virqueue element in case of error - - In vhost_vsock_common_send_transport_reset(), if an element popped from - the virtqueue is invalid, we should call virtqueue_detach_element() to - detach it from the virtqueue before freeing its memory. - - Fixes: fc0b9b0e1c ("vhost-vsock: add virtio sockets device") - Fixes: CVE-2022-26354 - Cc: qemu-stable@nongnu.org - Reported-by: VictorV - Signed-off-by: Stefano Garzarella - Message-Id: <20220228095058.27899-1-sgarzare@redhat.com> - Reviewed-by: Stefan Hajnoczi - Reviewed-by: Michael S. Tsirkin - Signed-off-by: Michael S. Tsirkin - -(cherry picked from commit 8d1b247f3748ac4078524130c6d7ae42b6140aaf) -Signed-off-by: Jon Maloy ---- - hw/virtio/vhost-vsock-common.c | 10 +++++++--- - 1 file changed, 7 insertions(+), 3 deletions(-) - -diff --git a/hw/virtio/vhost-vsock-common.c b/hw/virtio/vhost-vsock-common.c -index 3f3771274e..ed706681ac 100644 ---- a/hw/virtio/vhost-vsock-common.c -+++ b/hw/virtio/vhost-vsock-common.c -@@ -153,19 +153,23 @@ static void vhost_vsock_common_send_transport_reset(VHostVSockCommon *vvc) - if (elem->out_num) { - error_report("invalid vhost-vsock event virtqueue element with " - "out buffers"); -- goto out; -+ goto err; - } - - if (iov_from_buf(elem->in_sg, elem->in_num, 0, - &event, sizeof(event)) != sizeof(event)) { - error_report("vhost-vsock event virtqueue element is too short"); -- goto out; -+ goto err; - } - - virtqueue_push(vq, elem, sizeof(event)); - virtio_notify(VIRTIO_DEVICE(vvc), vq); - --out: -+ g_free(elem); -+ return; -+ -+err: -+ virtqueue_detach_element(vq, elem, 0); - g_free(elem); - } - --- -2.31.1 - diff --git a/SOURCES/kvm-vhost_net-Add-NetClientInfo-start-callback.patch b/SOURCES/kvm-vhost_net-Add-NetClientInfo-start-callback.patch new file mode 100644 index 0000000..40bf5f6 --- /dev/null +++ b/SOURCES/kvm-vhost_net-Add-NetClientInfo-start-callback.patch @@ -0,0 +1,73 @@ +From 6a6999311742b6dccdfce09f30742a63d72d1bd7 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Tue, 23 Aug 2022 20:30:30 +0200 +Subject: [PATCH 15/23] vhost_net: Add NetClientInfo start callback +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 116: vdpa: Restore device state on destination +RH-Bugzilla: 2114060 +RH-Acked-by: Cindy Lu +RH-Acked-by: Miroslav Rezanina +RH-Commit: [14/21] df6a96ae3aec02ecae793bdbd8e9c2fcfac7871a (eperezmartin/qemu-kvm) +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2114060 +Upstream status: git@github.com:jasowang/qemu.git net-next + +This is used by the backend to perform actions before the device is +started. + +In particular, vdpa net use it to map CVQ buffers to the device, so it +can send control commands using them. + +Signed-off-by: Eugenio Pérez +Acked-by: Jason Wang +Signed-off-by: Jason Wang +(cherry picked from commit 80bda0e674fd0b439ac627ab7ecdbd4a1b46d525) +--- + hw/net/vhost_net.c | 7 +++++++ + include/net/net.h | 2 ++ + 2 files changed, 9 insertions(+) + +diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c +index d6d7c51f62..1005f9d8e6 100644 +--- a/hw/net/vhost_net.c ++++ b/hw/net/vhost_net.c +@@ -244,6 +244,13 @@ static int vhost_net_start_one(struct vhost_net *net, + struct vhost_vring_file file = { }; + int r; + ++ if (net->nc->info->start) { ++ r = net->nc->info->start(net->nc); ++ if (r < 0) { ++ return r; ++ } ++ } ++ + r = vhost_dev_enable_notifiers(&net->dev, dev); + if (r < 0) { + goto fail_notifiers; +diff --git a/include/net/net.h b/include/net/net.h +index 523136c7ac..ad9e80083a 100644 +--- a/include/net/net.h ++++ b/include/net/net.h +@@ -44,6 +44,7 @@ typedef struct NICConf { + + typedef void (NetPoll)(NetClientState *, bool enable); + typedef bool (NetCanReceive)(NetClientState *); ++typedef int (NetStart)(NetClientState *); + typedef ssize_t (NetReceive)(NetClientState *, const uint8_t *, size_t); + typedef ssize_t (NetReceiveIOV)(NetClientState *, const struct iovec *, int); + typedef void (NetCleanup) (NetClientState *); +@@ -71,6 +72,7 @@ typedef struct NetClientInfo { + NetReceive *receive_raw; + NetReceiveIOV *receive_iov; + NetCanReceive *can_receive; ++ NetStart *start; + NetCleanup *cleanup; + LinkStatusChanged *link_status_changed; + QueryRxFilter *query_rx_filter; +-- +2.31.1 + diff --git a/SOURCES/kvm-vhost_net-Add-NetClientInfo-stop-callback.patch b/SOURCES/kvm-vhost_net-Add-NetClientInfo-stop-callback.patch new file mode 100644 index 0000000..c622824 --- /dev/null +++ b/SOURCES/kvm-vhost_net-Add-NetClientInfo-stop-callback.patch @@ -0,0 +1,68 @@ +From effd0ed379deb43bb850f1aeff24fa85935d7f52 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Tue, 23 Aug 2022 20:30:31 +0200 +Subject: [PATCH 16/23] vhost_net: Add NetClientInfo stop callback +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 116: vdpa: Restore device state on destination +RH-Bugzilla: 2114060 +RH-Acked-by: Cindy Lu +RH-Acked-by: Miroslav Rezanina +RH-Commit: [15/21] 9f8a3e9bfb0d21fa0479f54a7a17cb738aa46359 (eperezmartin/qemu-kvm) +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2114060 +Upstream status: git@github.com:jasowang/qemu.git net-next + +Used by the backend to perform actions after the device is stopped. + +In particular, vdpa net use it to unmap CVQ buffers to the device, +cleaning the actions performed in prepare(). + +Signed-off-by: Eugenio Pérez +Acked-by: Jason Wang +Signed-off-by: Jason Wang +(cherry picked from commit c6544e2331d721627fa7356da3592bcb46340f1b) +--- + hw/net/vhost_net.c | 3 +++ + include/net/net.h | 2 ++ + 2 files changed, 5 insertions(+) + +diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c +index 1005f9d8e6..275ece5324 100644 +--- a/hw/net/vhost_net.c ++++ b/hw/net/vhost_net.c +@@ -320,6 +320,9 @@ static void vhost_net_stop_one(struct vhost_net *net, + net->nc->info->poll(net->nc, true); + } + vhost_dev_stop(&net->dev, dev); ++ if (net->nc->info->stop) { ++ net->nc->info->stop(net->nc); ++ } + vhost_dev_disable_notifiers(&net->dev, dev); + } + +diff --git a/include/net/net.h b/include/net/net.h +index ad9e80083a..476ad45b9a 100644 +--- a/include/net/net.h ++++ b/include/net/net.h +@@ -45,6 +45,7 @@ typedef struct NICConf { + typedef void (NetPoll)(NetClientState *, bool enable); + typedef bool (NetCanReceive)(NetClientState *); + typedef int (NetStart)(NetClientState *); ++typedef void (NetStop)(NetClientState *); + typedef ssize_t (NetReceive)(NetClientState *, const uint8_t *, size_t); + typedef ssize_t (NetReceiveIOV)(NetClientState *, const struct iovec *, int); + typedef void (NetCleanup) (NetClientState *); +@@ -73,6 +74,7 @@ typedef struct NetClientInfo { + NetReceiveIOV *receive_iov; + NetCanReceive *can_receive; + NetStart *start; ++ NetStop *stop; + NetCleanup *cleanup; + LinkStatusChanged *link_status_changed; + QueryRxFilter *query_rx_filter; +-- +2.31.1 + diff --git a/SOURCES/kvm-vhost_net-add-NetClientState-load-callback.patch b/SOURCES/kvm-vhost_net-add-NetClientState-load-callback.patch new file mode 100644 index 0000000..92a9078 --- /dev/null +++ b/SOURCES/kvm-vhost_net-add-NetClientState-load-callback.patch @@ -0,0 +1,73 @@ +From 6a5c236b95ce475c556ccd92c2135ad48474e8fb Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Tue, 23 Aug 2022 20:30:35 +0200 +Subject: [PATCH 20/23] vhost_net: add NetClientState->load() callback +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 116: vdpa: Restore device state on destination +RH-Bugzilla: 2114060 +RH-Acked-by: Cindy Lu +RH-Acked-by: Miroslav Rezanina +RH-Commit: [19/21] 439b4133a757b2f1c5f4a1441eca25329896491a (eperezmartin/qemu-kvm) +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2114060 +Upstream status: git@github.com:jasowang/qemu.git net-next + +It allows per-net client operations right after device's successful +start. In particular, to load the device status. + +Vhost-vdpa net will use it to add the CVQ buffers to restore the device +status. + +Signed-off-by: Eugenio Pérez +Acked-by: Jason Wang +Signed-off-by: Jason Wang +(cherry picked from commit 302f3d20e68a8a120d431f7ff7cb02a75917f54c) +--- + hw/net/vhost_net.c | 7 +++++++ + include/net/net.h | 2 ++ + 2 files changed, 9 insertions(+) + +diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c +index 275ece5324..ea3a8be1c9 100644 +--- a/hw/net/vhost_net.c ++++ b/hw/net/vhost_net.c +@@ -281,6 +281,13 @@ static int vhost_net_start_one(struct vhost_net *net, + } + } + } ++ ++ if (net->nc->info->load) { ++ r = net->nc->info->load(net->nc); ++ if (r < 0) { ++ goto fail; ++ } ++ } + return 0; + fail: + file.fd = -1; +diff --git a/include/net/net.h b/include/net/net.h +index 476ad45b9a..81d0b21def 100644 +--- a/include/net/net.h ++++ b/include/net/net.h +@@ -45,6 +45,7 @@ typedef struct NICConf { + typedef void (NetPoll)(NetClientState *, bool enable); + typedef bool (NetCanReceive)(NetClientState *); + typedef int (NetStart)(NetClientState *); ++typedef int (NetLoad)(NetClientState *); + typedef void (NetStop)(NetClientState *); + typedef ssize_t (NetReceive)(NetClientState *, const uint8_t *, size_t); + typedef ssize_t (NetReceiveIOV)(NetClientState *, const struct iovec *, int); +@@ -74,6 +75,7 @@ typedef struct NetClientInfo { + NetReceiveIOV *receive_iov; + NetCanReceive *can_receive; + NetStart *start; ++ NetLoad *load; + NetStop *stop; + NetCleanup *cleanup; + LinkStatusChanged *link_status_changed; +-- +2.31.1 + diff --git a/SOURCES/kvm-virtio-iommu-Add-an-assert-check-in-translate-routin.patch b/SOURCES/kvm-virtio-iommu-Add-an-assert-check-in-translate-routin.patch new file mode 100644 index 0000000..2a72cc7 --- /dev/null +++ b/SOURCES/kvm-virtio-iommu-Add-an-assert-check-in-translate-routin.patch @@ -0,0 +1,46 @@ +From 643d9c28ff8b15c333cc748c5e712659ad2a257c Mon Sep 17 00:00:00 2001 +From: Zhenzhong Duan +Date: Mon, 13 Jun 2022 14:10:10 +0800 +Subject: [PATCH 03/17] virtio-iommu: Add an assert check in translate routine + +RH-Author: Eric Auger +RH-MergeRequest: 105: virtio-iommu: Fix bypass mode for assigned devices +RH-Commit: [3/5] 19f309fd0beda40d65f51c454e37936658ac9f38 (eauger1/centos-qemu-kvm) +RH-Bugzilla: 2100106 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Peter Xu +RH-Acked-by: Cornelia Huck + +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2100106 + +With address space switch supported, dma access translation only +happen after endpoint is attached to a non-bypass domain. + +Signed-off-by: Zhenzhong Duan +Message-Id: <20220613061010.2674054-4-zhenzhong.duan@intel.com> +Reviewed-by: Michael S. Tsirkin +Signed-off-by: Michael S. Tsirkin +(cherry picked from commit 23b5f0ff6d923d3bca11cf44eed3daf7a0a836a8) +Signed-off-by: Eric Auger +--- + hw/virtio/virtio-iommu.c | 4 ++++ + 1 file changed, 4 insertions(+) + +diff --git a/hw/virtio/virtio-iommu.c b/hw/virtio/virtio-iommu.c +index 440a1c28a7..e970d4d5a6 100644 +--- a/hw/virtio/virtio-iommu.c ++++ b/hw/virtio/virtio-iommu.c +@@ -866,6 +866,10 @@ static IOMMUTLBEntry virtio_iommu_translate(IOMMUMemoryRegion *mr, hwaddr addr, + qemu_rec_mutex_lock(&s->mutex); + + ep = g_tree_lookup(s->endpoints, GUINT_TO_POINTER(sid)); ++ ++ if (bypass_allowed) ++ assert(ep && ep->domain && !ep->domain->bypass); ++ + if (!ep) { + if (!bypass_allowed) { + error_report_once("%s sid=%d is not known!!", __func__, sid); +-- +2.31.1 + diff --git a/SOURCES/kvm-virtio-iommu-Add-bypass-mode-support-to-assigned-dev.patch b/SOURCES/kvm-virtio-iommu-Add-bypass-mode-support-to-assigned-dev.patch new file mode 100644 index 0000000..3352666 --- /dev/null +++ b/SOURCES/kvm-virtio-iommu-Add-bypass-mode-support-to-assigned-dev.patch @@ -0,0 +1,250 @@ +From d60774ee3168eefb21a4120a38107cd36ae17e07 Mon Sep 17 00:00:00 2001 +From: Zhenzhong Duan +Date: Mon, 13 Jun 2022 14:10:08 +0800 +Subject: [PATCH 01/17] virtio-iommu: Add bypass mode support to assigned + device + +RH-Author: Eric Auger +RH-MergeRequest: 105: virtio-iommu: Fix bypass mode for assigned devices +RH-Commit: [1/5] 4777815533b31c7f4f09af8902e378fd3fc1186a (eauger1/centos-qemu-kvm) +RH-Bugzilla: 2100106 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Peter Xu +RH-Acked-by: Cornelia Huck + +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2100106 + +Currently assigned devices can not work in virtio-iommu bypass mode. +Guest driver fails to probe the device due to DMA failure. And the +reason is because of lacking GPA -> HPA mappings when VM is created. + +Add a root container memory region to hold both bypass memory region +and iommu memory region, so the switch between them is supported +just like the implementation in virtual VT-d. + +Signed-off-by: Zhenzhong Duan +Message-Id: <20220613061010.2674054-2-zhenzhong.duan@intel.com> +Reviewed-by: Michael S. Tsirkin +Signed-off-by: Michael S. Tsirkin +(cherry picked from commit 90519b90539b16258d1d52b908b199f44877dc18) +Signed-off-by: Eric Auger +--- + hw/virtio/trace-events | 1 + + hw/virtio/virtio-iommu.c | 115 ++++++++++++++++++++++++++++++- + include/hw/virtio/virtio-iommu.h | 2 + + 3 files changed, 116 insertions(+), 2 deletions(-) + +diff --git a/hw/virtio/trace-events b/hw/virtio/trace-events +index a5102eac9e..2ab5881b88 100644 +--- a/hw/virtio/trace-events ++++ b/hw/virtio/trace-events +@@ -114,6 +114,7 @@ virtio_iommu_remap(const char *name, uint64_t virt_start, uint64_t virt_end, uin + virtio_iommu_set_page_size_mask(const char *name, uint64_t old, uint64_t new) "mr=%s old_mask=0x%"PRIx64" new_mask=0x%"PRIx64 + virtio_iommu_notify_flag_add(const char *name) "add notifier to mr %s" + virtio_iommu_notify_flag_del(const char *name) "del notifier from mr %s" ++virtio_iommu_switch_address_space(uint8_t bus, uint8_t slot, uint8_t fn, bool on) "Device %02x:%02x.%x switching address space (iommu enabled=%d)" + + # virtio-mem.c + virtio_mem_send_response(uint16_t type) "type=%" PRIu16 +diff --git a/hw/virtio/virtio-iommu.c b/hw/virtio/virtio-iommu.c +index 6d5ea0bdf1..5e99e6c62b 100644 +--- a/hw/virtio/virtio-iommu.c ++++ b/hw/virtio/virtio-iommu.c +@@ -70,6 +70,77 @@ static inline uint16_t virtio_iommu_get_bdf(IOMMUDevice *dev) + return PCI_BUILD_BDF(pci_bus_num(dev->bus), dev->devfn); + } + ++static bool virtio_iommu_device_bypassed(IOMMUDevice *sdev) ++{ ++ uint32_t sid; ++ bool bypassed; ++ VirtIOIOMMU *s = sdev->viommu; ++ VirtIOIOMMUEndpoint *ep; ++ ++ sid = virtio_iommu_get_bdf(sdev); ++ ++ qemu_mutex_lock(&s->mutex); ++ /* need to check bypass before system reset */ ++ if (!s->endpoints) { ++ bypassed = s->config.bypass; ++ goto unlock; ++ } ++ ++ ep = g_tree_lookup(s->endpoints, GUINT_TO_POINTER(sid)); ++ if (!ep || !ep->domain) { ++ bypassed = s->config.bypass; ++ } else { ++ bypassed = ep->domain->bypass; ++ } ++ ++unlock: ++ qemu_mutex_unlock(&s->mutex); ++ return bypassed; ++} ++ ++/* Return whether the device is using IOMMU translation. */ ++static bool virtio_iommu_switch_address_space(IOMMUDevice *sdev) ++{ ++ bool use_remapping; ++ ++ assert(sdev); ++ ++ use_remapping = !virtio_iommu_device_bypassed(sdev); ++ ++ trace_virtio_iommu_switch_address_space(pci_bus_num(sdev->bus), ++ PCI_SLOT(sdev->devfn), ++ PCI_FUNC(sdev->devfn), ++ use_remapping); ++ ++ /* Turn off first then on the other */ ++ if (use_remapping) { ++ memory_region_set_enabled(&sdev->bypass_mr, false); ++ memory_region_set_enabled(MEMORY_REGION(&sdev->iommu_mr), true); ++ } else { ++ memory_region_set_enabled(MEMORY_REGION(&sdev->iommu_mr), false); ++ memory_region_set_enabled(&sdev->bypass_mr, true); ++ } ++ ++ return use_remapping; ++} ++ ++static void virtio_iommu_switch_address_space_all(VirtIOIOMMU *s) ++{ ++ GHashTableIter iter; ++ IOMMUPciBus *iommu_pci_bus; ++ int i; ++ ++ g_hash_table_iter_init(&iter, s->as_by_busptr); ++ while (g_hash_table_iter_next(&iter, NULL, (void **)&iommu_pci_bus)) { ++ for (i = 0; i < PCI_DEVFN_MAX; i++) { ++ if (!iommu_pci_bus->pbdev[i]) { ++ continue; ++ } ++ virtio_iommu_switch_address_space(iommu_pci_bus->pbdev[i]); ++ } ++ } ++} ++ + /** + * The bus number is used for lookup when SID based operations occur. + * In that case we lazily populate the IOMMUPciBus array from the bus hash +@@ -214,6 +285,7 @@ static gboolean virtio_iommu_notify_map_cb(gpointer key, gpointer value, + static void virtio_iommu_detach_endpoint_from_domain(VirtIOIOMMUEndpoint *ep) + { + VirtIOIOMMUDomain *domain = ep->domain; ++ IOMMUDevice *sdev = container_of(ep->iommu_mr, IOMMUDevice, iommu_mr); + + if (!ep->domain) { + return; +@@ -222,6 +294,7 @@ static void virtio_iommu_detach_endpoint_from_domain(VirtIOIOMMUEndpoint *ep) + ep->iommu_mr); + QLIST_REMOVE(ep, next); + ep->domain = NULL; ++ virtio_iommu_switch_address_space(sdev); + } + + static VirtIOIOMMUEndpoint *virtio_iommu_get_endpoint(VirtIOIOMMU *s, +@@ -324,12 +397,39 @@ static AddressSpace *virtio_iommu_find_add_as(PCIBus *bus, void *opaque, + + trace_virtio_iommu_init_iommu_mr(name); + ++ memory_region_init(&sdev->root, OBJECT(s), name, UINT64_MAX); ++ address_space_init(&sdev->as, &sdev->root, TYPE_VIRTIO_IOMMU); ++ ++ /* ++ * Build the IOMMU disabled container with aliases to the ++ * shared MRs. Note that aliasing to a shared memory region ++ * could help the memory API to detect same FlatViews so we ++ * can have devices to share the same FlatView when in bypass ++ * mode. (either by not configuring virtio-iommu driver or with ++ * "iommu=pt"). It will greatly reduce the total number of ++ * FlatViews of the system hence VM runs faster. ++ */ ++ memory_region_init_alias(&sdev->bypass_mr, OBJECT(s), ++ "system", get_system_memory(), 0, ++ memory_region_size(get_system_memory())); ++ + memory_region_init_iommu(&sdev->iommu_mr, sizeof(sdev->iommu_mr), + TYPE_VIRTIO_IOMMU_MEMORY_REGION, + OBJECT(s), name, + UINT64_MAX); +- address_space_init(&sdev->as, +- MEMORY_REGION(&sdev->iommu_mr), TYPE_VIRTIO_IOMMU); ++ ++ /* ++ * Hook both the containers under the root container, we ++ * switch between iommu & bypass MRs by enable/disable ++ * corresponding sub-containers ++ */ ++ memory_region_add_subregion_overlap(&sdev->root, 0, ++ MEMORY_REGION(&sdev->iommu_mr), ++ 0); ++ memory_region_add_subregion_overlap(&sdev->root, 0, ++ &sdev->bypass_mr, 0); ++ ++ virtio_iommu_switch_address_space(sdev); + g_free(name); + } + return &sdev->as; +@@ -343,6 +443,7 @@ static int virtio_iommu_attach(VirtIOIOMMU *s, + uint32_t flags = le32_to_cpu(req->flags); + VirtIOIOMMUDomain *domain; + VirtIOIOMMUEndpoint *ep; ++ IOMMUDevice *sdev; + + trace_virtio_iommu_attach(domain_id, ep_id); + +@@ -376,6 +477,8 @@ static int virtio_iommu_attach(VirtIOIOMMU *s, + QLIST_INSERT_HEAD(&domain->endpoint_list, ep, next); + + ep->domain = domain; ++ sdev = container_of(ep->iommu_mr, IOMMUDevice, iommu_mr); ++ virtio_iommu_switch_address_space(sdev); + + /* Replay domain mappings on the associated memory region */ + g_tree_foreach(domain->mappings, virtio_iommu_notify_map_cb, +@@ -888,6 +991,7 @@ static void virtio_iommu_set_config(VirtIODevice *vdev, + return; + } + dev_config->bypass = in_config->bypass; ++ virtio_iommu_switch_address_space_all(dev); + } + + trace_virtio_iommu_set_config(in_config->bypass); +@@ -1027,6 +1131,8 @@ static void virtio_iommu_system_reset(void *opaque) + * system reset + */ + s->config.bypass = s->boot_bypass; ++ virtio_iommu_switch_address_space_all(s); ++ + } + + static void virtio_iommu_device_realize(DeviceState *dev, Error **errp) +@@ -1043,6 +1149,11 @@ static void virtio_iommu_device_realize(DeviceState *dev, Error **errp) + virtio_iommu_handle_command); + s->event_vq = virtio_add_queue(vdev, VIOMMU_DEFAULT_QUEUE_SIZE, NULL); + ++ /* ++ * config.bypass is needed to get initial address space early, such as ++ * in vfio realize ++ */ ++ s->config.bypass = s->boot_bypass; + s->config.page_size_mask = TARGET_PAGE_MASK; + s->config.input_range.end = UINT64_MAX; + s->config.domain_range.end = UINT32_MAX; +diff --git a/include/hw/virtio/virtio-iommu.h b/include/hw/virtio/virtio-iommu.h +index 84391f8448..102eeefa73 100644 +--- a/include/hw/virtio/virtio-iommu.h ++++ b/include/hw/virtio/virtio-iommu.h +@@ -37,6 +37,8 @@ typedef struct IOMMUDevice { + int devfn; + IOMMUMemoryRegion iommu_mr; + AddressSpace as; ++ MemoryRegion root; /* The root container of the device */ ++ MemoryRegion bypass_mr; /* The alias of shared memory MR */ + } IOMMUDevice; + + typedef struct IOMMUPciBus { +-- +2.31.1 + diff --git a/SOURCES/kvm-virtio-iommu-Fix-migration-regression.patch b/SOURCES/kvm-virtio-iommu-Fix-migration-regression.patch new file mode 100644 index 0000000..f5ae4d6 --- /dev/null +++ b/SOURCES/kvm-virtio-iommu-Fix-migration-regression.patch @@ -0,0 +1,54 @@ +From 8d45902b4884315ec090e607e9f03606b21001cf Mon Sep 17 00:00:00 2001 +From: Zhenzhong Duan +Date: Fri, 24 Jun 2022 17:37:40 +0800 +Subject: [PATCH 05/17] virtio-iommu: Fix migration regression + +RH-Author: Eric Auger +RH-MergeRequest: 105: virtio-iommu: Fix bypass mode for assigned devices +RH-Commit: [5/5] 9652c4aaaf88e24083fab1fbc3d1423260c93ca6 (eauger1/centos-qemu-kvm) +RH-Bugzilla: 2100106 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Peter Xu +RH-Acked-by: Cornelia Huck + +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2100106 + +We also need to switch to the right address space on dest side +after loading the device status. DMA to wrong address space is +destructive. + +Fixes: 3facd774962fd ("virtio-iommu: Add bypass mode support to assigned device") +Suggested-by: Eric Auger +Signed-off-by: Zhenzhong Duan +Message-Id: <20220624093740.3525267-1-zhenzhong.duan@intel.com> +Reviewed-by: Michael S. Tsirkin +Signed-off-by: Michael S. Tsirkin +Reviewed-by: Eric Auger +(cherry picked from commit d355566bd958e24e7e384da6ea89a9fc88d7bfed) +Signed-off-by: Eric Auger +--- + hw/virtio/virtio-iommu.c | 8 ++++++++ + 1 file changed, 8 insertions(+) + +diff --git a/hw/virtio/virtio-iommu.c b/hw/virtio/virtio-iommu.c +index 44a041dec9..2012835554 100644 +--- a/hw/virtio/virtio-iommu.c ++++ b/hw/virtio/virtio-iommu.c +@@ -1324,6 +1324,14 @@ static int iommu_post_load(void *opaque, int version_id) + VirtIOIOMMU *s = opaque; + + g_tree_foreach(s->domains, reconstruct_endpoints, s); ++ ++ /* ++ * Memory regions are dynamically turned on/off depending on ++ * 'config.bypass' and attached domain type if there is. After ++ * migration, we need to make sure the memory regions are ++ * still correct. ++ */ ++ virtio_iommu_switch_address_space_all(s); + return 0; + } + +-- +2.31.1 + diff --git a/SOURCES/kvm-virtio-iommu-Fix-the-partial-copy-of-probe-request.patch b/SOURCES/kvm-virtio-iommu-Fix-the-partial-copy-of-probe-request.patch new file mode 100644 index 0000000..7747bfe --- /dev/null +++ b/SOURCES/kvm-virtio-iommu-Fix-the-partial-copy-of-probe-request.patch @@ -0,0 +1,67 @@ +From b681247c29b59af40c86f8f0ae5709138ae9bf1a Mon Sep 17 00:00:00 2001 +From: Zhenzhong Duan +Date: Thu, 23 Jun 2022 10:31:52 +0800 +Subject: [PATCH 04/17] virtio-iommu: Fix the partial copy of probe request + +RH-Author: Eric Auger +RH-MergeRequest: 105: virtio-iommu: Fix bypass mode for assigned devices +RH-Commit: [4/5] c402164414a8e69bbb6df20af3c2b6d2589d6f3e (eauger1/centos-qemu-kvm) +RH-Bugzilla: 2100106 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Peter Xu +RH-Acked-by: Cornelia Huck + +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2100106 + +The structure of probe request doesn't include the tail, this leads +to a few field missed to be copied. Currently this isn't an issue as +those missed field belong to reserved field, just in case reserved +field will be used in the future. + +Changed 4th parameter of virtio_iommu_iov_to_req() to receive size +of device-readable part. + +Fixes: 1733eebb9e75b ("virtio-iommu: Implement RESV_MEM probe request") +Signed-off-by: Zhenzhong Duan +Message-Id: <20220623023152.3473231-1-zhenzhong.duan@intel.com> +Reviewed-by: Michael S. Tsirkin +Signed-off-by: Michael S. Tsirkin +Reviewed-by: Jean-Philippe Brucker +Reviewed-by: Eric Auger +(cherry picked from commit 45461aace83d961e933b27519b81d17b4c690514) +Signed-off-by: Eric Auger +--- + hw/virtio/virtio-iommu.c | 8 ++++---- + 1 file changed, 4 insertions(+), 4 deletions(-) + +diff --git a/hw/virtio/virtio-iommu.c b/hw/virtio/virtio-iommu.c +index e970d4d5a6..44a041dec9 100644 +--- a/hw/virtio/virtio-iommu.c ++++ b/hw/virtio/virtio-iommu.c +@@ -676,11 +676,10 @@ static int virtio_iommu_probe(VirtIOIOMMU *s, + + static int virtio_iommu_iov_to_req(struct iovec *iov, + unsigned int iov_cnt, +- void *req, size_t req_sz) ++ void *req, size_t payload_sz) + { +- size_t sz, payload_sz = req_sz - sizeof(struct virtio_iommu_req_tail); ++ size_t sz = iov_to_buf(iov, iov_cnt, 0, req, payload_sz); + +- sz = iov_to_buf(iov, iov_cnt, 0, req, payload_sz); + if (unlikely(sz != payload_sz)) { + return VIRTIO_IOMMU_S_INVAL; + } +@@ -693,7 +692,8 @@ static int virtio_iommu_handle_ ## __req(VirtIOIOMMU *s, \ + unsigned int iov_cnt) \ + { \ + struct virtio_iommu_req_ ## __req req; \ +- int ret = virtio_iommu_iov_to_req(iov, iov_cnt, &req, sizeof(req)); \ ++ int ret = virtio_iommu_iov_to_req(iov, iov_cnt, &req, \ ++ sizeof(req) - sizeof(struct virtio_iommu_req_tail));\ + \ + return ret ? ret : virtio_iommu_ ## __req(s, &req); \ + } +-- +2.31.1 + diff --git a/SOURCES/kvm-virtio-iommu-Use-recursive-lock-to-avoid-deadlock.patch b/SOURCES/kvm-virtio-iommu-Use-recursive-lock-to-avoid-deadlock.patch new file mode 100644 index 0000000..df961b0 --- /dev/null +++ b/SOURCES/kvm-virtio-iommu-Use-recursive-lock-to-avoid-deadlock.patch @@ -0,0 +1,141 @@ +From 881c999e302e7ee1212b47c523a2cf442c549417 Mon Sep 17 00:00:00 2001 +From: Zhenzhong Duan +Date: Mon, 13 Jun 2022 14:10:09 +0800 +Subject: [PATCH 02/17] virtio-iommu: Use recursive lock to avoid deadlock + +RH-Author: Eric Auger +RH-MergeRequest: 105: virtio-iommu: Fix bypass mode for assigned devices +RH-Commit: [2/5] 67dce1eecb49555f728f119f8efac00417ff65bf (eauger1/centos-qemu-kvm) +RH-Bugzilla: 2100106 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Peter Xu +RH-Acked-by: Cornelia Huck + +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2100106 + +When switching address space with mutex lock hold, mapping will be +replayed for assigned device. This will trigger relock deadlock. + +Also release the mutex resource in unrealize routine. + +Signed-off-by: Zhenzhong Duan +Message-Id: <20220613061010.2674054-3-zhenzhong.duan@intel.com> +Reviewed-by: Michael S. Tsirkin +Signed-off-by: Michael S. Tsirkin +(cherry picked from commit 08f2030a2e46f1e93d186b3a683e5caef1df562b) +Signed-off-by: Eric Auger +--- + hw/virtio/virtio-iommu.c | 20 +++++++++++--------- + include/hw/virtio/virtio-iommu.h | 2 +- + 2 files changed, 12 insertions(+), 10 deletions(-) + +diff --git a/hw/virtio/virtio-iommu.c b/hw/virtio/virtio-iommu.c +index 5e99e6c62b..440a1c28a7 100644 +--- a/hw/virtio/virtio-iommu.c ++++ b/hw/virtio/virtio-iommu.c +@@ -79,7 +79,7 @@ static bool virtio_iommu_device_bypassed(IOMMUDevice *sdev) + + sid = virtio_iommu_get_bdf(sdev); + +- qemu_mutex_lock(&s->mutex); ++ qemu_rec_mutex_lock(&s->mutex); + /* need to check bypass before system reset */ + if (!s->endpoints) { + bypassed = s->config.bypass; +@@ -94,7 +94,7 @@ static bool virtio_iommu_device_bypassed(IOMMUDevice *sdev) + } + + unlock: +- qemu_mutex_unlock(&s->mutex); ++ qemu_rec_mutex_unlock(&s->mutex); + return bypassed; + } + +@@ -746,7 +746,7 @@ static void virtio_iommu_handle_command(VirtIODevice *vdev, VirtQueue *vq) + tail.status = VIRTIO_IOMMU_S_DEVERR; + goto out; + } +- qemu_mutex_lock(&s->mutex); ++ qemu_rec_mutex_lock(&s->mutex); + switch (head.type) { + case VIRTIO_IOMMU_T_ATTACH: + tail.status = virtio_iommu_handle_attach(s, iov, iov_cnt); +@@ -775,7 +775,7 @@ static void virtio_iommu_handle_command(VirtIODevice *vdev, VirtQueue *vq) + default: + tail.status = VIRTIO_IOMMU_S_UNSUPP; + } +- qemu_mutex_unlock(&s->mutex); ++ qemu_rec_mutex_unlock(&s->mutex); + + out: + sz = iov_from_buf(elem->in_sg, elem->in_num, 0, +@@ -863,7 +863,7 @@ static IOMMUTLBEntry virtio_iommu_translate(IOMMUMemoryRegion *mr, hwaddr addr, + sid = virtio_iommu_get_bdf(sdev); + + trace_virtio_iommu_translate(mr->parent_obj.name, sid, addr, flag); +- qemu_mutex_lock(&s->mutex); ++ qemu_rec_mutex_lock(&s->mutex); + + ep = g_tree_lookup(s->endpoints, GUINT_TO_POINTER(sid)); + if (!ep) { +@@ -947,7 +947,7 @@ static IOMMUTLBEntry virtio_iommu_translate(IOMMUMemoryRegion *mr, hwaddr addr, + trace_virtio_iommu_translate_out(addr, entry.translated_addr, sid); + + unlock: +- qemu_mutex_unlock(&s->mutex); ++ qemu_rec_mutex_unlock(&s->mutex); + return entry; + } + +@@ -1036,7 +1036,7 @@ static void virtio_iommu_replay(IOMMUMemoryRegion *mr, IOMMUNotifier *n) + + sid = virtio_iommu_get_bdf(sdev); + +- qemu_mutex_lock(&s->mutex); ++ qemu_rec_mutex_lock(&s->mutex); + + if (!s->endpoints) { + goto unlock; +@@ -1050,7 +1050,7 @@ static void virtio_iommu_replay(IOMMUMemoryRegion *mr, IOMMUNotifier *n) + g_tree_foreach(ep->domain->mappings, virtio_iommu_remap, mr); + + unlock: +- qemu_mutex_unlock(&s->mutex); ++ qemu_rec_mutex_unlock(&s->mutex); + } + + static int virtio_iommu_notify_flag_changed(IOMMUMemoryRegion *iommu_mr, +@@ -1169,7 +1169,7 @@ static void virtio_iommu_device_realize(DeviceState *dev, Error **errp) + virtio_add_feature(&s->features, VIRTIO_IOMMU_F_PROBE); + virtio_add_feature(&s->features, VIRTIO_IOMMU_F_BYPASS_CONFIG); + +- qemu_mutex_init(&s->mutex); ++ qemu_rec_mutex_init(&s->mutex); + + s->as_by_busptr = g_hash_table_new_full(NULL, NULL, NULL, g_free); + +@@ -1197,6 +1197,8 @@ static void virtio_iommu_device_unrealize(DeviceState *dev) + g_tree_destroy(s->endpoints); + } + ++ qemu_rec_mutex_destroy(&s->mutex); ++ + virtio_delete_queue(s->req_vq); + virtio_delete_queue(s->event_vq); + virtio_cleanup(vdev); +diff --git a/include/hw/virtio/virtio-iommu.h b/include/hw/virtio/virtio-iommu.h +index 102eeefa73..2ad5ee320b 100644 +--- a/include/hw/virtio/virtio-iommu.h ++++ b/include/hw/virtio/virtio-iommu.h +@@ -58,7 +58,7 @@ struct VirtIOIOMMU { + ReservedRegion *reserved_regions; + uint32_t nb_reserved_regions; + GTree *domains; +- QemuMutex mutex; ++ QemuRecMutex mutex; + GTree *endpoints; + bool boot_bypass; + }; +-- +2.31.1 + diff --git a/SOURCES/kvm-virtio-net-Expose-MAC_TABLE_ENTRIES.patch b/SOURCES/kvm-virtio-net-Expose-MAC_TABLE_ENTRIES.patch new file mode 100644 index 0000000..4ae4cc4 --- /dev/null +++ b/SOURCES/kvm-virtio-net-Expose-MAC_TABLE_ENTRIES.patch @@ -0,0 +1,69 @@ +From dffe24d5c1f5a4676e9d2a5bc032effd420b008f Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Thu, 21 Jul 2022 15:38:55 +0200 +Subject: [PATCH 08/32] virtio-net: Expose MAC_TABLE_ENTRIES +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 108: Net Control Virtqueue shadow Support +RH-Commit: [8/27] 5c3b96215ddf853cafc594da47f57d7e157db4ee (eperezmartin/qemu-kvm) +RH-Bugzilla: 1939363 +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Cindy Lu +RH-Acked-by: Laurent Vivier + +Bugzilla: https://bugzilla.redhat.com/1939363 + +Upstream Status: git://git.qemu.org/qemu.git + +commit 6758c01f054c2a842d41d927d628b09f649d3254 +Author: Eugenio Pérez +Date: Wed Jul 20 08:59:27 2022 +0200 + + virtio-net: Expose MAC_TABLE_ENTRIES + + vhost-vdpa control virtqueue needs to know the maximum entries supported + by the virtio-net device, so we know if it is possible to apply the + filter. + + Signed-off-by: Eugenio Pérez + Reviewed-by: Michael S. Tsirkin + Signed-off-by: Jason Wang + +Signed-off-by: Eugenio Pérez +--- + hw/net/virtio-net.c | 1 - + include/hw/virtio/virtio-net.h | 3 +++ + 2 files changed, 3 insertions(+), 1 deletion(-) + +diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c +index 633de61513..2a127f0a3b 100644 +--- a/hw/net/virtio-net.c ++++ b/hw/net/virtio-net.c +@@ -49,7 +49,6 @@ + + #define VIRTIO_NET_VM_VERSION 11 + +-#define MAC_TABLE_ENTRIES 64 + #define MAX_VLAN (1 << 12) /* Per 802.1Q definition */ + + /* previously fixed value */ +diff --git a/include/hw/virtio/virtio-net.h b/include/hw/virtio/virtio-net.h +index eb87032627..cce1c554f7 100644 +--- a/include/hw/virtio/virtio-net.h ++++ b/include/hw/virtio/virtio-net.h +@@ -35,6 +35,9 @@ OBJECT_DECLARE_SIMPLE_TYPE(VirtIONet, VIRTIO_NET) + * and latency. */ + #define TX_BURST 256 + ++/* Maximum VIRTIO_NET_CTRL_MAC_TABLE_SET unicast + multicast entries. */ ++#define MAC_TABLE_ENTRIES 64 ++ + typedef struct virtio_net_conf + { + uint32_t txtimer; +-- +2.31.1 + diff --git a/SOURCES/kvm-virtio-net-Expose-ctrl-virtqueue-logic.patch b/SOURCES/kvm-virtio-net-Expose-ctrl-virtqueue-logic.patch new file mode 100644 index 0000000..b4b9012 --- /dev/null +++ b/SOURCES/kvm-virtio-net-Expose-ctrl-virtqueue-logic.patch @@ -0,0 +1,169 @@ +From 49e91b34b62f5da147fa2fb80d203dd675c48f64 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= +Date: Thu, 21 Jul 2022 15:38:55 +0200 +Subject: [PATCH 09/32] virtio-net: Expose ctrl virtqueue logic +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Eugenio Pérez +RH-MergeRequest: 108: Net Control Virtqueue shadow Support +RH-Commit: [9/27] c4ab1e35f4ca728df82a687763c662369282c513 (eperezmartin/qemu-kvm) +RH-Bugzilla: 1939363 +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Cindy Lu +RH-Acked-by: Laurent Vivier + +Bugzilla: https://bugzilla.redhat.com/1939363 + +Upstream Status: git://git.qemu.org/qemu.git + +commit 640b8a1c588b56349b3307d88459ea1cd86181fb +Author: Eugenio Pérez +Date: Wed Jul 20 08:59:28 2022 +0200 + + virtio-net: Expose ctrl virtqueue logic + + This allows external vhost-net devices to modify the state of the + VirtIO device model once the vhost-vdpa device has acknowledged the + control commands. + + Signed-off-by: Eugenio Pérez + Reviewed-by: Michael S. Tsirkin + Signed-off-by: Jason Wang + +Signed-off-by: Eugenio Pérez +--- + hw/net/virtio-net.c | 84 ++++++++++++++++++++-------------- + include/hw/virtio/virtio-net.h | 4 ++ + 2 files changed, 53 insertions(+), 35 deletions(-) + +diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c +index 2a127f0a3b..59bedba681 100644 +--- a/hw/net/virtio-net.c ++++ b/hw/net/virtio-net.c +@@ -1433,57 +1433,71 @@ static int virtio_net_handle_mq(VirtIONet *n, uint8_t cmd, + return VIRTIO_NET_OK; + } + +-static void virtio_net_handle_ctrl(VirtIODevice *vdev, VirtQueue *vq) ++size_t virtio_net_handle_ctrl_iov(VirtIODevice *vdev, ++ const struct iovec *in_sg, unsigned in_num, ++ const struct iovec *out_sg, ++ unsigned out_num) + { + VirtIONet *n = VIRTIO_NET(vdev); + struct virtio_net_ctrl_hdr ctrl; + virtio_net_ctrl_ack status = VIRTIO_NET_ERR; +- VirtQueueElement *elem; + size_t s; + struct iovec *iov, *iov2; +- unsigned int iov_cnt; ++ ++ if (iov_size(in_sg, in_num) < sizeof(status) || ++ iov_size(out_sg, out_num) < sizeof(ctrl)) { ++ virtio_error(vdev, "virtio-net ctrl missing headers"); ++ return 0; ++ } ++ ++ iov2 = iov = g_memdup2(out_sg, sizeof(struct iovec) * out_num); ++ s = iov_to_buf(iov, out_num, 0, &ctrl, sizeof(ctrl)); ++ iov_discard_front(&iov, &out_num, sizeof(ctrl)); ++ if (s != sizeof(ctrl)) { ++ status = VIRTIO_NET_ERR; ++ } else if (ctrl.class == VIRTIO_NET_CTRL_RX) { ++ status = virtio_net_handle_rx_mode(n, ctrl.cmd, iov, out_num); ++ } else if (ctrl.class == VIRTIO_NET_CTRL_MAC) { ++ status = virtio_net_handle_mac(n, ctrl.cmd, iov, out_num); ++ } else if (ctrl.class == VIRTIO_NET_CTRL_VLAN) { ++ status = virtio_net_handle_vlan_table(n, ctrl.cmd, iov, out_num); ++ } else if (ctrl.class == VIRTIO_NET_CTRL_ANNOUNCE) { ++ status = virtio_net_handle_announce(n, ctrl.cmd, iov, out_num); ++ } else if (ctrl.class == VIRTIO_NET_CTRL_MQ) { ++ status = virtio_net_handle_mq(n, ctrl.cmd, iov, out_num); ++ } else if (ctrl.class == VIRTIO_NET_CTRL_GUEST_OFFLOADS) { ++ status = virtio_net_handle_offloads(n, ctrl.cmd, iov, out_num); ++ } ++ ++ s = iov_from_buf(in_sg, in_num, 0, &status, sizeof(status)); ++ assert(s == sizeof(status)); ++ ++ g_free(iov2); ++ return sizeof(status); ++} ++ ++static void virtio_net_handle_ctrl(VirtIODevice *vdev, VirtQueue *vq) ++{ ++ VirtQueueElement *elem; + + for (;;) { ++ size_t written; + elem = virtqueue_pop(vq, sizeof(VirtQueueElement)); + if (!elem) { + break; + } +- if (iov_size(elem->in_sg, elem->in_num) < sizeof(status) || +- iov_size(elem->out_sg, elem->out_num) < sizeof(ctrl)) { +- virtio_error(vdev, "virtio-net ctrl missing headers"); ++ ++ written = virtio_net_handle_ctrl_iov(vdev, elem->in_sg, elem->in_num, ++ elem->out_sg, elem->out_num); ++ if (written > 0) { ++ virtqueue_push(vq, elem, written); ++ virtio_notify(vdev, vq); ++ g_free(elem); ++ } else { + virtqueue_detach_element(vq, elem, 0); + g_free(elem); + break; + } +- +- iov_cnt = 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)) { +- status = VIRTIO_NET_ERR; +- } else if (ctrl.class == VIRTIO_NET_CTRL_RX) { +- status = virtio_net_handle_rx_mode(n, ctrl.cmd, iov, iov_cnt); +- } else if (ctrl.class == VIRTIO_NET_CTRL_MAC) { +- status = virtio_net_handle_mac(n, ctrl.cmd, iov, iov_cnt); +- } else if (ctrl.class == VIRTIO_NET_CTRL_VLAN) { +- status = virtio_net_handle_vlan_table(n, ctrl.cmd, iov, iov_cnt); +- } else if (ctrl.class == VIRTIO_NET_CTRL_ANNOUNCE) { +- status = virtio_net_handle_announce(n, ctrl.cmd, iov, iov_cnt); +- } else if (ctrl.class == VIRTIO_NET_CTRL_MQ) { +- status = virtio_net_handle_mq(n, ctrl.cmd, iov, iov_cnt); +- } else if (ctrl.class == VIRTIO_NET_CTRL_GUEST_OFFLOADS) { +- status = virtio_net_handle_offloads(n, ctrl.cmd, iov, iov_cnt); +- } +- +- s = iov_from_buf(elem->in_sg, elem->in_num, 0, &status, sizeof(status)); +- assert(s == sizeof(status)); +- +- virtqueue_push(vq, elem, sizeof(status)); +- virtio_notify(vdev, vq); +- g_free(iov2); +- g_free(elem); + } + } + +diff --git a/include/hw/virtio/virtio-net.h b/include/hw/virtio/virtio-net.h +index cce1c554f7..ef234ffe7e 100644 +--- a/include/hw/virtio/virtio-net.h ++++ b/include/hw/virtio/virtio-net.h +@@ -221,6 +221,10 @@ struct VirtIONet { + struct EBPFRSSContext ebpf_rss; + }; + ++size_t virtio_net_handle_ctrl_iov(VirtIODevice *vdev, ++ const struct iovec *in_sg, unsigned in_num, ++ const struct iovec *out_sg, ++ unsigned out_num); + void virtio_net_set_netclient_name(VirtIONet *n, const char *name, + const char *type); + +-- +2.31.1 + diff --git a/SOURCES/kvm-virtio-net-align-ctrl_vq-index-for-non-mq-guest-for-.patch b/SOURCES/kvm-virtio-net-align-ctrl_vq-index-for-non-mq-guest-for-.patch index d834255..9da7ea7 100644 --- a/SOURCES/kvm-virtio-net-align-ctrl_vq-index-for-non-mq-guest-for-.patch +++ b/SOURCES/kvm-virtio-net-align-ctrl_vq-index-for-non-mq-guest-for-.patch @@ -1,19 +1,19 @@ -From 370df65141aa7ca10c4eaca8e862580e50dead65 Mon Sep 17 00:00:00 2001 +From 316b73277de233c7a9b6917077c00d7012060944 Mon Sep 17 00:00:00 2001 From: Si-Wei Liu Date: Fri, 6 May 2022 19:28:13 -0700 -Subject: [PATCH 2/7] virtio-net: align ctrl_vq index for non-mq guest for +Subject: [PATCH 09/16] virtio-net: align ctrl_vq index for non-mq guest for vhost_vdpa MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit -RH-Author: Cindy Lu -RH-MergeRequest: 204: vdpa :sync the Multiqueue fixes for vhost-vDPA -RH-Commit: [2/7] bb12ad61fac82935ef1ca6e37da6da2f04e43d51 -RH-Bugzilla: 2095795 -RH-Acked-by: Laurent Vivier +RH-Author: Jason Wang +RH-MergeRequest: 98: Multiqueue fixes for vhost-vDPA +RH-Commit: [2/7] 7f764bbb579c7b473ad67fc25b46e698d277e781 (jasowang/qemu-kvm-cs) +RH-Bugzilla: 2070804 RH-Acked-by: Eugenio Pérez -RH-Acked-by: Jason Wang +RH-Acked-by: Laurent Vivier +RH-Acked-by: Cindy Lu With MQ enabled vdpa device and non-MQ supporting guest e.g. booting vdpa with mq=on over OVMF of single vqp, below assert @@ -73,13 +73,13 @@ Message-Id: <1651890498-24478-3-git-send-email-si-wei.liu@oracle.com> Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin (cherry picked from commit 68b0a6395f36a8f48f56f46d05f30be2067598b0) -Signed-off-by: Cindy Lu +Signed-off-by: Jason Wang --- hw/net/virtio-net.c | 33 +++++++++++++++++++++++++++++++-- 1 file changed, 31 insertions(+), 2 deletions(-) diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c -index ec045c3f41..f118379bb4 100644 +index ffb3475201..f0bb29c741 100644 --- a/hw/net/virtio-net.c +++ b/hw/net/virtio-net.c @@ -14,6 +14,7 @@ @@ -90,7 +90,7 @@ index ec045c3f41..f118379bb4 100644 #include "qemu/main-loop.h" #include "qemu/module.h" #include "hw/virtio/virtio.h" -@@ -3163,8 +3164,22 @@ static NetClientInfo net_virtio_info = { +@@ -3171,8 +3172,22 @@ static NetClientInfo net_virtio_info = { static bool virtio_net_guest_notifier_pending(VirtIODevice *vdev, int idx) { VirtIONet *n = VIRTIO_NET(vdev); @@ -114,7 +114,7 @@ index ec045c3f41..f118379bb4 100644 return vhost_net_virtqueue_pending(get_vhost_net(nc->peer), idx); } -@@ -3172,8 +3187,22 @@ static void virtio_net_guest_notifier_mask(VirtIODevice *vdev, int idx, +@@ -3180,8 +3195,22 @@ static void virtio_net_guest_notifier_mask(VirtIODevice *vdev, int idx, bool mask) { VirtIONet *n = VIRTIO_NET(vdev); diff --git a/SOURCES/kvm-virtio-net-don-t-handle-mq-request-in-userspace-hand.patch b/SOURCES/kvm-virtio-net-don-t-handle-mq-request-in-userspace-hand.patch index efc164f..3930cc2 100644 --- a/SOURCES/kvm-virtio-net-don-t-handle-mq-request-in-userspace-hand.patch +++ b/SOURCES/kvm-virtio-net-don-t-handle-mq-request-in-userspace-hand.patch @@ -1,19 +1,19 @@ -From 6182990c1327658c417280a557d16191f70c91b7 Mon Sep 17 00:00:00 2001 +From 521a1953bc11ab6823dcbbee773bcf86e926a9e7 Mon Sep 17 00:00:00 2001 From: Si-Wei Liu Date: Fri, 6 May 2022 19:28:18 -0700 -Subject: [PATCH 7/7] virtio-net: don't handle mq request in userspace handler - for vhost-vdpa +Subject: [PATCH 14/16] virtio-net: don't handle mq request in userspace + handler for vhost-vdpa MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit -RH-Author: Cindy Lu -RH-MergeRequest: 204: vdpa :sync the Multiqueue fixes for vhost-vDPA -RH-Commit: [7/7] 2e636b805ab3f365b1f26fbdac7a7d0ade62508d -RH-Bugzilla: 2095795 -RH-Acked-by: Laurent Vivier +RH-Author: Jason Wang +RH-MergeRequest: 98: Multiqueue fixes for vhost-vDPA +RH-Commit: [7/7] 9781cab45448ae16a00fbf10cf7995df6b984a0a (jasowang/qemu-kvm-cs) +RH-Bugzilla: 2070804 RH-Acked-by: Eugenio Pérez -RH-Acked-by: Jason Wang +RH-Acked-by: Laurent Vivier +RH-Acked-by: Cindy Lu virtio_queue_host_notifier_read() tends to read pending event left behind on ioeventfd in the vhost_net_stop() path, and @@ -68,16 +68,16 @@ Message-Id: <1651890498-24478-8-git-send-email-si-wei.liu@oracle.com> Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin (cherry picked from commit 2a7888cc3aa31faee839fa5dddad354ff8941f4c) -Signed-off-by: Cindy Lu +Signed-off-by: Jason Wang --- hw/net/virtio-net.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c -index f118379bb4..7e172ef829 100644 +index f0bb29c741..099e65036d 100644 --- a/hw/net/virtio-net.c +++ b/hw/net/virtio-net.c -@@ -1373,6 +1373,7 @@ static int virtio_net_handle_mq(VirtIONet *n, uint8_t cmd, +@@ -1381,6 +1381,7 @@ static int virtio_net_handle_mq(VirtIONet *n, uint8_t cmd, { VirtIODevice *vdev = VIRTIO_DEVICE(n); uint16_t queue_pairs; @@ -85,7 +85,7 @@ index f118379bb4..7e172ef829 100644 virtio_net_disable_rss(n); if (cmd == VIRTIO_NET_CTRL_MQ_HASH_CONFIG) { -@@ -1404,6 +1405,18 @@ static int virtio_net_handle_mq(VirtIONet *n, uint8_t cmd, +@@ -1412,6 +1413,18 @@ static int virtio_net_handle_mq(VirtIONet *n, uint8_t cmd, return VIRTIO_NET_ERR; } diff --git a/SOURCES/kvm-virtio-net-fix-map-leaking-on-error-during-receive.patch b/SOURCES/kvm-virtio-net-fix-map-leaking-on-error-during-receive.patch deleted file mode 100644 index aa52233..0000000 --- a/SOURCES/kvm-virtio-net-fix-map-leaking-on-error-during-receive.patch +++ /dev/null @@ -1,61 +0,0 @@ -From d1a64781c4f7fa698a359ea078a98029f4f67c1b Mon Sep 17 00:00:00 2001 -From: Jason Wang -Date: Tue, 8 Mar 2022 10:42:51 +0800 -Subject: [PATCH 2/3] virtio-net: fix map leaking on error during receive - -RH-Author: Jon Maloy -RH-MergeRequest: 178: virtio-net: fix map leaking on error during receive -RH-Commit: [1/1] afdfa3198fcf815de59915136222f73711efd292 (jmaloy/qemu-kvm) -RH-Bugzilla: 2075635 -RH-Acked-by: Jason Wang -RH-Acked-by: Miroslav Rezanina -RH-Acked-by: Kevin Wolf -RH-Acked-by: Laurent Vivier - -Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2075635 -Upstream: Merged -CVE: CVE-2022-26353 - -commit abe300d9d894f7138e1af7c8e9c88c04bfe98b37 -Author: Jason Wang -Date: Tue Mar 8 10:42:51 2022 +0800 - - virtio-net: fix map leaking on error during receive - - Commit bedd7e93d0196 ("virtio-net: fix use after unmap/free for sg") - tries to fix the use after free of the sg by caching the virtqueue - elements in an array and unmap them at once after receiving the - packets, But it forgot to unmap the cached elements on error which - will lead to leaking of mapping and other unexpected results. - - Fixing this by detaching the cached elements on error. This addresses - CVE-2022-26353. - - Reported-by: Victor Tom - Cc: qemu-stable@nongnu.org - Fixes: CVE-2022-26353 - Fixes: bedd7e93d0196 ("virtio-net: fix use after unmap/free for sg") - Reviewed-by: Michael S. Tsirkin - Signed-off-by: Jason Wang - -(cherry picked from commit abe300d9d894f7138e1af7c8e9c88c04bfe98b37) -Signed-off-by: Jon Maloy ---- - hw/net/virtio-net.c | 1 + - 1 file changed, 1 insertion(+) - -diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c -index f2014d5ea0..e1f4748831 100644 ---- a/hw/net/virtio-net.c -+++ b/hw/net/virtio-net.c -@@ -1862,6 +1862,7 @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf, - - err: - for (j = 0; j < i; j++) { -+ virtqueue_detach_element(q->rx_vq, elems[j], lens[j]); - g_free(elems[j]); - } - --- -2.31.1 - diff --git a/SOURCES/kvm-virtio-net-setup-vhost_dev-and-notifiers-for-cvq-onl.patch b/SOURCES/kvm-virtio-net-setup-vhost_dev-and-notifiers-for-cvq-onl.patch index 19307ea..f6072d2 100644 --- a/SOURCES/kvm-virtio-net-setup-vhost_dev-and-notifiers-for-cvq-onl.patch +++ b/SOURCES/kvm-virtio-net-setup-vhost_dev-and-notifiers-for-cvq-onl.patch @@ -1,19 +1,19 @@ -From b956af02efde25f458205cb5bc2c389409564e3f Mon Sep 17 00:00:00 2001 +From 9e737aba614e94da4458f02d4ff97e95ffffd19f Mon Sep 17 00:00:00 2001 From: Si-Wei Liu Date: Fri, 6 May 2022 19:28:12 -0700 -Subject: [PATCH 1/7] virtio-net: setup vhost_dev and notifiers for cvq only +Subject: [PATCH 08/16] virtio-net: setup vhost_dev and notifiers for cvq only when feature is negotiated MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit -RH-Author: Cindy Lu -RH-MergeRequest: 204: vdpa :sync the Multiqueue fixes for vhost-vDPA -RH-Commit: [1/7] 4e1e54bbf5d91a590a61e3fee1100716b50837ee -RH-Bugzilla: 2095795 -RH-Acked-by: Laurent Vivier +RH-Author: Jason Wang +RH-MergeRequest: 98: Multiqueue fixes for vhost-vDPA +RH-Commit: [1/7] a5c5a2862b2e4d15ef7c09da3e4234fdef37cc66 (jasowang/qemu-kvm-cs) +RH-Bugzilla: 2070804 RH-Acked-by: Eugenio Pérez -RH-Acked-by: Jason Wang +RH-Acked-by: Laurent Vivier +RH-Acked-by: Cindy Lu When the control virtqueue feature is absent or not negotiated, vhost_net_start() still tries to set up vhost_dev and install @@ -28,16 +28,16 @@ Message-Id: <1651890498-24478-2-git-send-email-si-wei.liu@oracle.com> Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin (cherry picked from commit aa8581945a13712ff3eed0ad3ba7a9664fc1604b) -Signed-off-by: Cindy Lu +Signed-off-by: Jason Wang --- hw/net/virtio-net.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c -index e1f4748831..ec045c3f41 100644 +index 1067e72b39..ffb3475201 100644 --- a/hw/net/virtio-net.c +++ b/hw/net/virtio-net.c -@@ -244,7 +244,8 @@ static void virtio_net_vhost_status(VirtIONet *n, uint8_t status) +@@ -245,7 +245,8 @@ static void virtio_net_vhost_status(VirtIONet *n, uint8_t status) VirtIODevice *vdev = VIRTIO_DEVICE(n); NetClientState *nc = qemu_get_queue(n->nic); int queue_pairs = n->multiqueue ? n->max_queue_pairs : 1; diff --git a/SOURCES/kvm-virtio-scsi-clean-up-virtio_scsi_handle_cmd_vq.patch b/SOURCES/kvm-virtio-scsi-clean-up-virtio_scsi_handle_cmd_vq.patch new file mode 100644 index 0000000..897e04c --- /dev/null +++ b/SOURCES/kvm-virtio-scsi-clean-up-virtio_scsi_handle_cmd_vq.patch @@ -0,0 +1,77 @@ +From 975af1b9f1811e113e1babd928ae70f8e4ebefb5 Mon Sep 17 00:00:00 2001 +From: Stefan Hajnoczi +Date: Tue, 17 May 2022 09:28:19 +0100 +Subject: [PATCH 13/16] virtio-scsi: clean up virtio_scsi_handle_cmd_vq() + +RH-Author: Stefan Hajnoczi +RH-MergeRequest: 88: virtio-scsi: fix 100% CPU consumption with IOThreads +RH-Commit: [5/6] 27b0225783fa9bbb8fe5ee692bd3f0a888d49d07 (stefanha/centos-stream-qemu-kvm) +RH-Bugzilla: 2079347 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Kevin Wolf +RH-Acked-by: Stefano Garzarella + +virtio_scsi_handle_cmd_vq() is only called from hw/scsi/virtio-scsi.c +now and its return value is no longer used. Remove the function +prototype from virtio-scsi.h and drop the return value. + +Signed-off-by: Stefan Hajnoczi +Reviewed-by: Paolo Bonzini +Message-id: 20220427143541.119567-6-stefanha@redhat.com +Signed-off-by: Stefan Hajnoczi +(cherry picked from commit ad482b57ef841b2d4883c5079d20ba44ff5e4b3e) +Signed-off-by: Stefan Hajnoczi +--- + hw/scsi/virtio-scsi.c | 5 +---- + include/hw/virtio/virtio-scsi.h | 1 - + 2 files changed, 1 insertion(+), 5 deletions(-) + +diff --git a/hw/scsi/virtio-scsi.c b/hw/scsi/virtio-scsi.c +index a47033d91d..df5ff8bab7 100644 +--- a/hw/scsi/virtio-scsi.c ++++ b/hw/scsi/virtio-scsi.c +@@ -685,12 +685,11 @@ static void virtio_scsi_handle_cmd_req_submit(VirtIOSCSI *s, VirtIOSCSIReq *req) + scsi_req_unref(sreq); + } + +-bool virtio_scsi_handle_cmd_vq(VirtIOSCSI *s, VirtQueue *vq) ++static void virtio_scsi_handle_cmd_vq(VirtIOSCSI *s, VirtQueue *vq) + { + VirtIOSCSIReq *req, *next; + int ret = 0; + bool suppress_notifications = virtio_queue_get_notification(vq); +- bool progress = false; + + QTAILQ_HEAD(, VirtIOSCSIReq) reqs = QTAILQ_HEAD_INITIALIZER(reqs); + +@@ -700,7 +699,6 @@ bool virtio_scsi_handle_cmd_vq(VirtIOSCSI *s, VirtQueue *vq) + } + + while ((req = virtio_scsi_pop_req(s, vq))) { +- progress = true; + ret = virtio_scsi_handle_cmd_req_prepare(s, req); + if (!ret) { + QTAILQ_INSERT_TAIL(&reqs, req, next); +@@ -725,7 +723,6 @@ bool virtio_scsi_handle_cmd_vq(VirtIOSCSI *s, VirtQueue *vq) + QTAILQ_FOREACH_SAFE(req, &reqs, next, next) { + virtio_scsi_handle_cmd_req_submit(s, req); + } +- return progress; + } + + static void virtio_scsi_handle_cmd(VirtIODevice *vdev, VirtQueue *vq) +diff --git a/include/hw/virtio/virtio-scsi.h b/include/hw/virtio/virtio-scsi.h +index 44dc3b81ec..2497530064 100644 +--- a/include/hw/virtio/virtio-scsi.h ++++ b/include/hw/virtio/virtio-scsi.h +@@ -151,7 +151,6 @@ void virtio_scsi_common_realize(DeviceState *dev, + Error **errp); + + void virtio_scsi_common_unrealize(DeviceState *dev); +-bool virtio_scsi_handle_cmd_vq(VirtIOSCSI *s, VirtQueue *vq); + void virtio_scsi_init_req(VirtIOSCSI *s, VirtQueue *vq, VirtIOSCSIReq *req); + void virtio_scsi_free_req(VirtIOSCSIReq *req); + void virtio_scsi_push_event(VirtIOSCSI *s, SCSIDevice *dev, +-- +2.31.1 + diff --git a/SOURCES/kvm-virtio-scsi-clean-up-virtio_scsi_handle_ctrl_vq.patch b/SOURCES/kvm-virtio-scsi-clean-up-virtio_scsi_handle_ctrl_vq.patch new file mode 100644 index 0000000..30f012f --- /dev/null +++ b/SOURCES/kvm-virtio-scsi-clean-up-virtio_scsi_handle_ctrl_vq.patch @@ -0,0 +1,65 @@ +From c6e16a7a5a18ec2bc4f8a6f5cc1c887e18b16cdf Mon Sep 17 00:00:00 2001 +From: Stefan Hajnoczi +Date: Tue, 17 May 2022 09:28:12 +0100 +Subject: [PATCH 12/16] virtio-scsi: clean up virtio_scsi_handle_ctrl_vq() + +RH-Author: Stefan Hajnoczi +RH-MergeRequest: 88: virtio-scsi: fix 100% CPU consumption with IOThreads +RH-Commit: [4/6] ca3751b7bfad5163c5b1c81b8525936a848d42ea (stefanha/centos-stream-qemu-kvm) +RH-Bugzilla: 2079347 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Kevin Wolf +RH-Acked-by: Stefano Garzarella + +virtio_scsi_handle_ctrl_vq() is only called from hw/scsi/virtio-scsi.c +now and its return value is no longer used. Remove the function +prototype from virtio-scsi.h and drop the return value. + +Signed-off-by: Stefan Hajnoczi +Reviewed-by: Paolo Bonzini +Message-id: 20220427143541.119567-5-stefanha@redhat.com +Signed-off-by: Stefan Hajnoczi +(cherry picked from commit 73b3b49f1880f236b4d0ffd7efb00280c05a5fab) +Signed-off-by: Stefan Hajnoczi +--- + hw/scsi/virtio-scsi.c | 5 +---- + include/hw/virtio/virtio-scsi.h | 1 - + 2 files changed, 1 insertion(+), 5 deletions(-) + +diff --git a/hw/scsi/virtio-scsi.c b/hw/scsi/virtio-scsi.c +index dd2185b943..a47033d91d 100644 +--- a/hw/scsi/virtio-scsi.c ++++ b/hw/scsi/virtio-scsi.c +@@ -460,16 +460,13 @@ static void virtio_scsi_handle_ctrl_req(VirtIOSCSI *s, VirtIOSCSIReq *req) + } + } + +-bool virtio_scsi_handle_ctrl_vq(VirtIOSCSI *s, VirtQueue *vq) ++static void virtio_scsi_handle_ctrl_vq(VirtIOSCSI *s, VirtQueue *vq) + { + VirtIOSCSIReq *req; +- bool progress = false; + + while ((req = virtio_scsi_pop_req(s, vq))) { +- progress = true; + virtio_scsi_handle_ctrl_req(s, req); + } +- return progress; + } + + /* +diff --git a/include/hw/virtio/virtio-scsi.h b/include/hw/virtio/virtio-scsi.h +index 5957597825..44dc3b81ec 100644 +--- a/include/hw/virtio/virtio-scsi.h ++++ b/include/hw/virtio/virtio-scsi.h +@@ -152,7 +152,6 @@ void virtio_scsi_common_realize(DeviceState *dev, + + void virtio_scsi_common_unrealize(DeviceState *dev); + bool virtio_scsi_handle_cmd_vq(VirtIOSCSI *s, VirtQueue *vq); +-bool virtio_scsi_handle_ctrl_vq(VirtIOSCSI *s, VirtQueue *vq); + void virtio_scsi_init_req(VirtIOSCSI *s, VirtQueue *vq, VirtIOSCSIReq *req); + void virtio_scsi_free_req(VirtIOSCSIReq *req); + void virtio_scsi_push_event(VirtIOSCSI *s, SCSIDevice *dev, +-- +2.31.1 + diff --git a/SOURCES/kvm-virtio-scsi-clean-up-virtio_scsi_handle_event_vq.patch b/SOURCES/kvm-virtio-scsi-clean-up-virtio_scsi_handle_event_vq.patch new file mode 100644 index 0000000..bfdd39b --- /dev/null +++ b/SOURCES/kvm-virtio-scsi-clean-up-virtio_scsi_handle_event_vq.patch @@ -0,0 +1,62 @@ +From 019d5a0ca5d13f837a59b9e2815e2fd7ac120807 Mon Sep 17 00:00:00 2001 +From: Stefan Hajnoczi +Date: Tue, 17 May 2022 09:28:06 +0100 +Subject: [PATCH 11/16] virtio-scsi: clean up virtio_scsi_handle_event_vq() + +RH-Author: Stefan Hajnoczi +RH-MergeRequest: 88: virtio-scsi: fix 100% CPU consumption with IOThreads +RH-Commit: [3/6] f8dbc4c1991c61e4cf8dea50942c3cd509c9c4bd (stefanha/centos-stream-qemu-kvm) +RH-Bugzilla: 2079347 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Kevin Wolf +RH-Acked-by: Stefano Garzarella + +virtio_scsi_handle_event_vq() is only called from hw/scsi/virtio-scsi.c +now and its return value is no longer used. Remove the function +prototype from virtio-scsi.h and drop the return value. + +Signed-off-by: Stefan Hajnoczi +Reviewed-by: Paolo Bonzini +Message-id: 20220427143541.119567-4-stefanha@redhat.com +Signed-off-by: Stefan Hajnoczi +(cherry picked from commit 37ce2de95169dacab3fb53d11bd4509b9c2e3a4c) +Signed-off-by: Stefan Hajnoczi +--- + hw/scsi/virtio-scsi.c | 4 +--- + include/hw/virtio/virtio-scsi.h | 1 - + 2 files changed, 1 insertion(+), 4 deletions(-) + +diff --git a/hw/scsi/virtio-scsi.c b/hw/scsi/virtio-scsi.c +index 7b69eeed64..dd2185b943 100644 +--- a/hw/scsi/virtio-scsi.c ++++ b/hw/scsi/virtio-scsi.c +@@ -856,13 +856,11 @@ void virtio_scsi_push_event(VirtIOSCSI *s, SCSIDevice *dev, + virtio_scsi_complete_req(req); + } + +-bool virtio_scsi_handle_event_vq(VirtIOSCSI *s, VirtQueue *vq) ++static void virtio_scsi_handle_event_vq(VirtIOSCSI *s, VirtQueue *vq) + { + if (s->events_dropped) { + virtio_scsi_push_event(s, NULL, VIRTIO_SCSI_T_NO_EVENT, 0); +- return true; + } +- return false; + } + + static void virtio_scsi_handle_event(VirtIODevice *vdev, VirtQueue *vq) +diff --git a/include/hw/virtio/virtio-scsi.h b/include/hw/virtio/virtio-scsi.h +index 543681bc18..5957597825 100644 +--- a/include/hw/virtio/virtio-scsi.h ++++ b/include/hw/virtio/virtio-scsi.h +@@ -151,7 +151,6 @@ void virtio_scsi_common_realize(DeviceState *dev, + Error **errp); + + void virtio_scsi_common_unrealize(DeviceState *dev); +-bool virtio_scsi_handle_event_vq(VirtIOSCSI *s, VirtQueue *vq); + bool virtio_scsi_handle_cmd_vq(VirtIOSCSI *s, VirtQueue *vq); + bool virtio_scsi_handle_ctrl_vq(VirtIOSCSI *s, VirtQueue *vq); + void virtio_scsi_init_req(VirtIOSCSI *s, VirtQueue *vq, VirtIOSCSIReq *req); +-- +2.31.1 + diff --git a/SOURCES/kvm-virtio-scsi-don-t-waste-CPU-polling-the-event-virtqu.patch b/SOURCES/kvm-virtio-scsi-don-t-waste-CPU-polling-the-event-virtqu.patch new file mode 100644 index 0000000..5ba11a2 --- /dev/null +++ b/SOURCES/kvm-virtio-scsi-don-t-waste-CPU-polling-the-event-virtqu.patch @@ -0,0 +1,103 @@ +From 1b609b2af303fb6498b2ef94ac4f2e900dc8c1b2 Mon Sep 17 00:00:00 2001 +From: Stefan Hajnoczi +Date: Tue, 17 May 2022 09:27:45 +0100 +Subject: [PATCH 10/16] virtio-scsi: don't waste CPU polling the event + virtqueue + +RH-Author: Stefan Hajnoczi +RH-MergeRequest: 88: virtio-scsi: fix 100% CPU consumption with IOThreads +RH-Commit: [2/6] 7e613d9b9fa8ceb668c78cb3ce7ebe1d73a004b5 (stefanha/centos-stream-qemu-kvm) +RH-Bugzilla: 2079347 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Kevin Wolf +RH-Acked-by: Stefano Garzarella + +The virtio-scsi event virtqueue is not emptied by its handler function. +This is typical for rx virtqueues where the device uses buffers when +some event occurs (e.g. a packet is received, an error condition +happens, etc). + +Polling non-empty virtqueues wastes CPU cycles. We are not waiting for +new buffers to become available, we are waiting for an event to occur, +so it's a misuse of CPU resources to poll for buffers. + +Introduce the new virtio_queue_aio_attach_host_notifier_no_poll() API, +which is identical to virtio_queue_aio_attach_host_notifier() except +that it does not poll the virtqueue. + +Before this patch the following command-line consumed 100% CPU in the +IOThread polling and calling virtio_scsi_handle_event(): + + $ qemu-system-x86_64 -M accel=kvm -m 1G -cpu host \ + --object iothread,id=iothread0 \ + --device virtio-scsi-pci,iothread=iothread0 \ + --blockdev file,filename=test.img,aio=native,cache.direct=on,node-name=drive0 \ + --device scsi-hd,drive=drive0 + +After this patch CPU is no longer wasted. + +Reported-by: Nir Soffer +Signed-off-by: Stefan Hajnoczi +Tested-by: Nir Soffer +Message-id: 20220427143541.119567-3-stefanha@redhat.com +Signed-off-by: Stefan Hajnoczi +(cherry picked from commit 38738f7dbbda90fbc161757b7f4be35b52205552) +Signed-off-by: Stefan Hajnoczi +--- + hw/scsi/virtio-scsi-dataplane.c | 2 +- + hw/virtio/virtio.c | 13 +++++++++++++ + include/hw/virtio/virtio.h | 1 + + 3 files changed, 15 insertions(+), 1 deletion(-) + +diff --git a/hw/scsi/virtio-scsi-dataplane.c b/hw/scsi/virtio-scsi-dataplane.c +index 29575cbaf6..8bb6e6acfc 100644 +--- a/hw/scsi/virtio-scsi-dataplane.c ++++ b/hw/scsi/virtio-scsi-dataplane.c +@@ -138,7 +138,7 @@ int virtio_scsi_dataplane_start(VirtIODevice *vdev) + + aio_context_acquire(s->ctx); + virtio_queue_aio_attach_host_notifier(vs->ctrl_vq, s->ctx); +- virtio_queue_aio_attach_host_notifier(vs->event_vq, s->ctx); ++ virtio_queue_aio_attach_host_notifier_no_poll(vs->event_vq, s->ctx); + + for (i = 0; i < vs->conf.num_queues; i++) { + virtio_queue_aio_attach_host_notifier(vs->cmd_vqs[i], s->ctx); +diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c +index 9d637e043e..67a873f54a 100644 +--- a/hw/virtio/virtio.c ++++ b/hw/virtio/virtio.c +@@ -3534,6 +3534,19 @@ void virtio_queue_aio_attach_host_notifier(VirtQueue *vq, AioContext *ctx) + virtio_queue_host_notifier_aio_poll_end); + } + ++/* ++ * Same as virtio_queue_aio_attach_host_notifier() but without polling. Use ++ * this for rx virtqueues and similar cases where the virtqueue handler ++ * function does not pop all elements. When the virtqueue is left non-empty ++ * polling consumes CPU cycles and should not be used. ++ */ ++void virtio_queue_aio_attach_host_notifier_no_poll(VirtQueue *vq, AioContext *ctx) ++{ ++ aio_set_event_notifier(ctx, &vq->host_notifier, true, ++ virtio_queue_host_notifier_read, ++ NULL, NULL); ++} ++ + void virtio_queue_aio_detach_host_notifier(VirtQueue *vq, AioContext *ctx) + { + aio_set_event_notifier(ctx, &vq->host_notifier, true, NULL, NULL, NULL); +diff --git a/include/hw/virtio/virtio.h b/include/hw/virtio/virtio.h +index b31c4507f5..b62a35fdca 100644 +--- a/include/hw/virtio/virtio.h ++++ b/include/hw/virtio/virtio.h +@@ -317,6 +317,7 @@ EventNotifier *virtio_queue_get_host_notifier(VirtQueue *vq); + void virtio_queue_set_host_notifier_enabled(VirtQueue *vq, bool enabled); + void virtio_queue_host_notifier_read(EventNotifier *n); + void virtio_queue_aio_attach_host_notifier(VirtQueue *vq, AioContext *ctx); ++void virtio_queue_aio_attach_host_notifier_no_poll(VirtQueue *vq, AioContext *ctx); + void virtio_queue_aio_detach_host_notifier(VirtQueue *vq, AioContext *ctx); + VirtQueue *virtio_vector_first_queue(VirtIODevice *vdev, uint16_t vector); + VirtQueue *virtio_vector_next_queue(VirtQueue *vq); +-- +2.31.1 + diff --git a/SOURCES/kvm-virtio-scsi-fix-ctrl-and-event-handler-functions-in-.patch b/SOURCES/kvm-virtio-scsi-fix-ctrl-and-event-handler-functions-in-.patch new file mode 100644 index 0000000..1f22ba0 --- /dev/null +++ b/SOURCES/kvm-virtio-scsi-fix-ctrl-and-event-handler-functions-in-.patch @@ -0,0 +1,119 @@ +From 5aaf33dbbbc89d58a52337985641723b9ee13541 Mon Sep 17 00:00:00 2001 +From: Stefan Hajnoczi +Date: Wed, 27 Apr 2022 15:35:36 +0100 +Subject: [PATCH 09/16] virtio-scsi: fix ctrl and event handler functions in + dataplane mode + +RH-Author: Stefan Hajnoczi +RH-MergeRequest: 88: virtio-scsi: fix 100% CPU consumption with IOThreads +RH-Commit: [1/6] 3087889041b960f14a6b3893243f78523a78f637 (stefanha/centos-stream-qemu-kvm) +RH-Bugzilla: 2079347 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Kevin Wolf +RH-Acked-by: Stefano Garzarella + +Commit f34e8d8b8d48d73f36a67b6d5e492ef9784b5012 ("virtio-scsi: prepare +virtio_scsi_handle_cmd for dataplane") prepared the virtio-scsi cmd +virtqueue handler function to be used in both the dataplane and +non-datpalane code paths. + +It failed to convert the ctrl and event virtqueue handler functions, +which are not designed to be called from the dataplane code path but +will be since the ioeventfd is set up for those virtqueues when +dataplane starts. + +Convert the ctrl and event virtqueue handler functions now so they +operate correctly when called from the dataplane code path. Avoid code +duplication by extracting this code into a helper function. + +Fixes: f34e8d8b8d48d73f36a67b6d5e492ef9784b5012 ("virtio-scsi: prepare virtio_scsi_handle_cmd for dataplane") +Signed-off-by: Stefan Hajnoczi +Reviewed-by: Paolo Bonzini +Message-id: 20220427143541.119567-2-stefanha@redhat.com +[Fixed s/by used/be used/ typo pointed out by Michael Tokarev +. +--Stefan] +Signed-off-by: Stefan Hajnoczi +(cherry picked from commit 2f743ef6366c2df4ef51ef3ae318138cdc0125ab) +Signed-off-by: Stefan Hajnoczi +--- + hw/scsi/virtio-scsi.c | 42 +++++++++++++++++++++++++++--------------- + 1 file changed, 27 insertions(+), 15 deletions(-) + +diff --git a/hw/scsi/virtio-scsi.c b/hw/scsi/virtio-scsi.c +index 7f6da33a8a..7b69eeed64 100644 +--- a/hw/scsi/virtio-scsi.c ++++ b/hw/scsi/virtio-scsi.c +@@ -472,16 +472,32 @@ bool virtio_scsi_handle_ctrl_vq(VirtIOSCSI *s, VirtQueue *vq) + return progress; + } + ++/* ++ * If dataplane is configured but not yet started, do so now and return true on ++ * success. ++ * ++ * Dataplane is started by the core virtio code but virtqueue handler functions ++ * can also be invoked when a guest kicks before DRIVER_OK, so this helper ++ * function helps us deal with manually starting ioeventfd in that case. ++ */ ++static bool virtio_scsi_defer_to_dataplane(VirtIOSCSI *s) ++{ ++ if (!s->ctx || s->dataplane_started) { ++ return false; ++ } ++ ++ virtio_device_start_ioeventfd(&s->parent_obj.parent_obj); ++ return !s->dataplane_fenced; ++} ++ + static void virtio_scsi_handle_ctrl(VirtIODevice *vdev, VirtQueue *vq) + { + VirtIOSCSI *s = (VirtIOSCSI *)vdev; + +- if (s->ctx) { +- virtio_device_start_ioeventfd(vdev); +- if (!s->dataplane_fenced) { +- return; +- } ++ if (virtio_scsi_defer_to_dataplane(s)) { ++ return; + } ++ + virtio_scsi_acquire(s); + virtio_scsi_handle_ctrl_vq(s, vq); + virtio_scsi_release(s); +@@ -720,12 +736,10 @@ static void virtio_scsi_handle_cmd(VirtIODevice *vdev, VirtQueue *vq) + /* use non-QOM casts in the data path */ + VirtIOSCSI *s = (VirtIOSCSI *)vdev; + +- if (s->ctx && !s->dataplane_started) { +- virtio_device_start_ioeventfd(vdev); +- if (!s->dataplane_fenced) { +- return; +- } ++ if (virtio_scsi_defer_to_dataplane(s)) { ++ return; + } ++ + virtio_scsi_acquire(s); + virtio_scsi_handle_cmd_vq(s, vq); + virtio_scsi_release(s); +@@ -855,12 +869,10 @@ static void virtio_scsi_handle_event(VirtIODevice *vdev, VirtQueue *vq) + { + VirtIOSCSI *s = VIRTIO_SCSI(vdev); + +- if (s->ctx) { +- virtio_device_start_ioeventfd(vdev); +- if (!s->dataplane_fenced) { +- return; +- } ++ if (virtio_scsi_defer_to_dataplane(s)) { ++ return; + } ++ + virtio_scsi_acquire(s); + virtio_scsi_handle_event_vq(s, vq); + virtio_scsi_release(s); +-- +2.31.1 + diff --git a/SOURCES/kvm-virtio-scsi-fix-race-in-virtio_scsi_dataplane_start.patch b/SOURCES/kvm-virtio-scsi-fix-race-in-virtio_scsi_dataplane_start.patch new file mode 100644 index 0000000..8f1fb3e --- /dev/null +++ b/SOURCES/kvm-virtio-scsi-fix-race-in-virtio_scsi_dataplane_start.patch @@ -0,0 +1,117 @@ +From cbcab5ed1686fddeb2c6adb3a3f6ed0678a36e71 Mon Sep 17 00:00:00 2001 +From: Stefan Hajnoczi +Date: Mon, 8 Aug 2022 12:21:34 -0400 +Subject: [PATCH 23/23] virtio-scsi: fix race in virtio_scsi_dataplane_start() + +RH-Author: Stefan Hajnoczi +RH-MergeRequest: 211: virtio-scsi: fix race in virtio_scsi_dataplane_start() (RHEL src-git) +RH-Commit: [1/1] 2d4964d8863e259326a73fb918fa2f5f63b4a60a +RH-Bugzilla: 2099541 +RH-Acked-by: Emanuele Giuseppe Esposito +RH-Acked-by: Kevin Wolf +RH-Acked-by: Hanna Reitz +RH-Acked-by: Paolo Bonzini + +As soon as virtio_scsi_data_plane_start() attaches host notifiers the +IOThread may start virtqueue processing. There is a race between +IOThread virtqueue processing and virtio_scsi_data_plane_start() because +it only assigns s->dataplane_started after attaching host notifiers. + +When a virtqueue handler function in the IOThread calls +virtio_scsi_defer_to_dataplane() it may see !s->dataplane_started and +attempt to start dataplane even though we're already in the IOThread: + + #0 0x00007f67b360857c __pthread_kill_implementation (libc.so.6 + 0xa257c) + #1 0x00007f67b35bbd56 raise (libc.so.6 + 0x55d56) + #2 0x00007f67b358e833 abort (libc.so.6 + 0x28833) + #3 0x00007f67b358e75b __assert_fail_base.cold (libc.so.6 + 0x2875b) + #4 0x00007f67b35b4cd6 __assert_fail (libc.so.6 + 0x4ecd6) + #5 0x000055ca87fd411b memory_region_transaction_commit (qemu-kvm + 0x67511b) + #6 0x000055ca87e17811 virtio_pci_ioeventfd_assign (qemu-kvm + 0x4b8811) + #7 0x000055ca87e14836 virtio_bus_set_host_notifier (qemu-kvm + 0x4b5836) + #8 0x000055ca87f8e14e virtio_scsi_set_host_notifier (qemu-kvm + 0x62f14e) + #9 0x000055ca87f8dd62 virtio_scsi_dataplane_start (qemu-kvm + 0x62ed62) + #10 0x000055ca87e14610 virtio_bus_start_ioeventfd (qemu-kvm + 0x4b5610) + #11 0x000055ca87f8c29a virtio_scsi_handle_ctrl (qemu-kvm + 0x62d29a) + #12 0x000055ca87fa5902 virtio_queue_host_notifier_read (qemu-kvm + 0x646902) + #13 0x000055ca882c099e aio_dispatch_handler (qemu-kvm + 0x96199e) + #14 0x000055ca882c1761 aio_poll (qemu-kvm + 0x962761) + #15 0x000055ca880e1052 iothread_run (qemu-kvm + 0x782052) + #16 0x000055ca882c562a qemu_thread_start (qemu-kvm + 0x96662a) + +This patch assigns s->dataplane_started before attaching host notifiers +so that virtqueue handler functions that run in the IOThread before +virtio_scsi_data_plane_start() returns correctly identify that dataplane +does not need to be started. This fix is taken from the virtio-blk +dataplane code and it's worth adding a comment in virtio-blk as well to +explain why it works. + +Note that s->dataplane_started does not need the AioContext lock because +it is set before attaching host notifiers and cleared after detaching +host notifiers. In other words, the IOThread always sees the value true +and the main loop thread does not modify it while the IOThread is +active. + +Buglink: https://bugzilla.redhat.com/show_bug.cgi?id=2099541 +Reported-by: Qing Wang +Signed-off-by: Stefan Hajnoczi +Message-Id: <20220808162134.240405-1-stefanha@redhat.com> +Reviewed-by: Emanuele Giuseppe Esposito +Reviewed-by: Michael S. Tsirkin +Signed-off-by: Michael S. Tsirkin +(cherry picked from commit 9a4b6a63aee885931622549c85669dcca03bed39) +Signed-off-by: Stefan Hajnoczi +Signed-off-by: Miroslav Rezanina +--- + hw/block/dataplane/virtio-blk.c | 5 +++++ + hw/scsi/virtio-scsi-dataplane.c | 11 ++++++++--- + 2 files changed, 13 insertions(+), 3 deletions(-) + +diff --git a/hw/block/dataplane/virtio-blk.c b/hw/block/dataplane/virtio-blk.c +index 49276e46f2..26f965cabc 100644 +--- a/hw/block/dataplane/virtio-blk.c ++++ b/hw/block/dataplane/virtio-blk.c +@@ -219,6 +219,11 @@ int virtio_blk_data_plane_start(VirtIODevice *vdev) + + memory_region_transaction_commit(); + ++ /* ++ * These fields are visible to the IOThread so we rely on implicit barriers ++ * in aio_context_acquire() on the write side and aio_notify_accept() on ++ * the read side. ++ */ + s->starting = false; + vblk->dataplane_started = true; + trace_virtio_blk_data_plane_start(s); +diff --git a/hw/scsi/virtio-scsi-dataplane.c b/hw/scsi/virtio-scsi-dataplane.c +index 8bb6e6acfc..20bb91766e 100644 +--- a/hw/scsi/virtio-scsi-dataplane.c ++++ b/hw/scsi/virtio-scsi-dataplane.c +@@ -136,6 +136,14 @@ int virtio_scsi_dataplane_start(VirtIODevice *vdev) + + memory_region_transaction_commit(); + ++ /* ++ * These fields are visible to the IOThread so we rely on implicit barriers ++ * in aio_context_acquire() on the write side and aio_notify_accept() on ++ * the read side. ++ */ ++ s->dataplane_starting = false; ++ s->dataplane_started = true; ++ + aio_context_acquire(s->ctx); + virtio_queue_aio_attach_host_notifier(vs->ctrl_vq, s->ctx); + virtio_queue_aio_attach_host_notifier_no_poll(vs->event_vq, s->ctx); +@@ -143,9 +151,6 @@ int virtio_scsi_dataplane_start(VirtIODevice *vdev) + for (i = 0; i < vs->conf.num_queues; i++) { + virtio_queue_aio_attach_host_notifier(vs->cmd_vqs[i], s->ctx); + } +- +- s->dataplane_starting = false; +- s->dataplane_started = true; + aio_context_release(s->ctx); + return 0; + +-- +2.31.1 + diff --git a/SOURCES/kvm-virtio-scsi-move-request-related-items-from-.h-to-.c.patch b/SOURCES/kvm-virtio-scsi-move-request-related-items-from-.h-to-.c.patch new file mode 100644 index 0000000..8487f5c --- /dev/null +++ b/SOURCES/kvm-virtio-scsi-move-request-related-items-from-.h-to-.c.patch @@ -0,0 +1,168 @@ +From 6603f216dbc07a1d221b1665409cfec6cc9960e2 Mon Sep 17 00:00:00 2001 +From: Stefan Hajnoczi +Date: Tue, 17 May 2022 09:28:26 +0100 +Subject: [PATCH 14/16] virtio-scsi: move request-related items from .h to .c + +RH-Author: Stefan Hajnoczi +RH-MergeRequest: 88: virtio-scsi: fix 100% CPU consumption with IOThreads +RH-Commit: [6/6] ecdf5289abd04062c85c5ed8e577a5249684a3b0 (stefanha/centos-stream-qemu-kvm) +RH-Bugzilla: 2079347 +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Kevin Wolf +RH-Acked-by: Stefano Garzarella + +There is no longer a need to expose the request and related APIs in +virtio-scsi.h since there are no callers outside virtio-scsi.c. + +Note the block comment in VirtIOSCSIReq has been adjusted to meet the +coding style. + +Signed-off-by: Stefan Hajnoczi +Reviewed-by: Paolo Bonzini +Message-id: 20220427143541.119567-7-stefanha@redhat.com +Signed-off-by: Stefan Hajnoczi +(cherry picked from commit 3dc584abeef0e1277c2de8c1c1974cb49444eb0a) +Signed-off-by: Stefan Hajnoczi +--- + hw/scsi/virtio-scsi.c | 45 ++++++++++++++++++++++++++++++--- + include/hw/virtio/virtio-scsi.h | 40 ----------------------------- + 2 files changed, 41 insertions(+), 44 deletions(-) + +diff --git a/hw/scsi/virtio-scsi.c b/hw/scsi/virtio-scsi.c +index df5ff8bab7..2450c9438c 100644 +--- a/hw/scsi/virtio-scsi.c ++++ b/hw/scsi/virtio-scsi.c +@@ -29,6 +29,43 @@ + #include "hw/virtio/virtio-access.h" + #include "trace.h" + ++typedef struct VirtIOSCSIReq { ++ /* ++ * Note: ++ * - fields up to resp_iov are initialized by virtio_scsi_init_req; ++ * - fields starting at vring are zeroed by virtio_scsi_init_req. ++ */ ++ VirtQueueElement elem; ++ ++ VirtIOSCSI *dev; ++ VirtQueue *vq; ++ QEMUSGList qsgl; ++ QEMUIOVector resp_iov; ++ ++ union { ++ /* Used for two-stage request submission */ ++ QTAILQ_ENTRY(VirtIOSCSIReq) next; ++ ++ /* Used for cancellation of request during TMFs */ ++ int remaining; ++ }; ++ ++ SCSIRequest *sreq; ++ size_t resp_size; ++ enum SCSIXferMode mode; ++ union { ++ VirtIOSCSICmdResp cmd; ++ VirtIOSCSICtrlTMFResp tmf; ++ VirtIOSCSICtrlANResp an; ++ VirtIOSCSIEvent event; ++ } resp; ++ union { ++ VirtIOSCSICmdReq cmd; ++ VirtIOSCSICtrlTMFReq tmf; ++ VirtIOSCSICtrlANReq an; ++ } req; ++} VirtIOSCSIReq; ++ + static inline int virtio_scsi_get_lun(uint8_t *lun) + { + return ((lun[2] << 8) | lun[3]) & 0x3FFF; +@@ -45,7 +82,7 @@ static inline SCSIDevice *virtio_scsi_device_get(VirtIOSCSI *s, uint8_t *lun) + return scsi_device_get(&s->bus, 0, lun[1], virtio_scsi_get_lun(lun)); + } + +-void virtio_scsi_init_req(VirtIOSCSI *s, VirtQueue *vq, VirtIOSCSIReq *req) ++static void virtio_scsi_init_req(VirtIOSCSI *s, VirtQueue *vq, VirtIOSCSIReq *req) + { + VirtIODevice *vdev = VIRTIO_DEVICE(s); + const size_t zero_skip = +@@ -58,7 +95,7 @@ void virtio_scsi_init_req(VirtIOSCSI *s, VirtQueue *vq, VirtIOSCSIReq *req) + memset((uint8_t *)req + zero_skip, 0, sizeof(*req) - zero_skip); + } + +-void virtio_scsi_free_req(VirtIOSCSIReq *req) ++static void virtio_scsi_free_req(VirtIOSCSIReq *req) + { + qemu_iovec_destroy(&req->resp_iov); + qemu_sglist_destroy(&req->qsgl); +@@ -801,8 +838,8 @@ static void virtio_scsi_reset(VirtIODevice *vdev) + s->events_dropped = false; + } + +-void virtio_scsi_push_event(VirtIOSCSI *s, SCSIDevice *dev, +- uint32_t event, uint32_t reason) ++static void virtio_scsi_push_event(VirtIOSCSI *s, SCSIDevice *dev, ++ uint32_t event, uint32_t reason) + { + VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(s); + VirtIOSCSIReq *req; +diff --git a/include/hw/virtio/virtio-scsi.h b/include/hw/virtio/virtio-scsi.h +index 2497530064..abdda2cbd0 100644 +--- a/include/hw/virtio/virtio-scsi.h ++++ b/include/hw/virtio/virtio-scsi.h +@@ -94,42 +94,6 @@ struct VirtIOSCSI { + uint32_t host_features; + }; + +-typedef struct VirtIOSCSIReq { +- /* Note: +- * - fields up to resp_iov are initialized by virtio_scsi_init_req; +- * - fields starting at vring are zeroed by virtio_scsi_init_req. +- * */ +- VirtQueueElement elem; +- +- VirtIOSCSI *dev; +- VirtQueue *vq; +- QEMUSGList qsgl; +- QEMUIOVector resp_iov; +- +- union { +- /* Used for two-stage request submission */ +- QTAILQ_ENTRY(VirtIOSCSIReq) next; +- +- /* Used for cancellation of request during TMFs */ +- int remaining; +- }; +- +- SCSIRequest *sreq; +- size_t resp_size; +- enum SCSIXferMode mode; +- union { +- VirtIOSCSICmdResp cmd; +- VirtIOSCSICtrlTMFResp tmf; +- VirtIOSCSICtrlANResp an; +- VirtIOSCSIEvent event; +- } resp; +- union { +- VirtIOSCSICmdReq cmd; +- VirtIOSCSICtrlTMFReq tmf; +- VirtIOSCSICtrlANReq an; +- } req; +-} VirtIOSCSIReq; +- + static inline void virtio_scsi_acquire(VirtIOSCSI *s) + { + if (s->ctx) { +@@ -151,10 +115,6 @@ void virtio_scsi_common_realize(DeviceState *dev, + Error **errp); + + void virtio_scsi_common_unrealize(DeviceState *dev); +-void virtio_scsi_init_req(VirtIOSCSI *s, VirtQueue *vq, VirtIOSCSIReq *req); +-void virtio_scsi_free_req(VirtIOSCSIReq *req); +-void virtio_scsi_push_event(VirtIOSCSI *s, SCSIDevice *dev, +- uint32_t event, uint32_t reason); + + void virtio_scsi_dataplane_setup(VirtIOSCSI *s, Error **errp); + int virtio_scsi_dataplane_start(VirtIODevice *s); +-- +2.31.1 + diff --git a/SOURCES/kvm-virtiofsd-Drop-membership-of-all-supplementary-group.patch b/SOURCES/kvm-virtiofsd-Drop-membership-of-all-supplementary-group.patch deleted file mode 100644 index 539b8fe..0000000 --- a/SOURCES/kvm-virtiofsd-Drop-membership-of-all-supplementary-group.patch +++ /dev/null @@ -1,110 +0,0 @@ -From 846192d22a1ddfa87682bb0b67febef5c30c9743 Mon Sep 17 00:00:00 2001 -From: Vivek Goyal -Date: Tue, 25 Jan 2022 13:51:14 -0500 -Subject: [PATCH 3/5] virtiofsd: Drop membership of all supplementary groups - (CVE-2022-0358) - -RH-Author: Dr. David Alan Gilbert -RH-MergeRequest: 66: c9s: virtiofsd security fix - drop secondary groups -RH-Commit: [1/1] cdf3b0405ea3369933e76761890f16b040641036 (redhat/centos-stream/src/qemu-kvm) -RH-Bugzilla: 2046201 -RH-Acked-by: Hanna Reitz -RH-Acked-by: Sergio Lopez -RH-Acked-by: Vivek Goyal - -At the start, drop membership of all supplementary groups. This is -not required. - -If we have membership of "root" supplementary group and when we switch -uid/gid using setresuid/setsgid, we still retain membership of existing -supplemntary groups. And that can allow some operations which are not -normally allowed. - -For example, if root in guest creates a dir as follows. - -$ mkdir -m 03777 test_dir - -This sets SGID on dir as well as allows unprivileged users to write into -this dir. - -And now as unprivileged user open file as follows. - -$ su test -$ fd = open("test_dir/priviledge_id", O_RDWR|O_CREAT|O_EXCL, 02755); - -This will create SGID set executable in test_dir/. - -And that's a problem because now an unpriviliged user can execute it, -get egid=0 and get access to resources owned by "root" group. This is -privilege escalation. - -Fixes: https://bugzilla.redhat.com/show_bug.cgi?id=2044863 -Fixes: CVE-2022-0358 -Reported-by: JIETAO XIAO -Suggested-by: Miklos Szeredi -Reviewed-by: Stefan Hajnoczi -Reviewed-by: Dr. David Alan Gilbert -Signed-off-by: Vivek Goyal -Message-Id: -Signed-off-by: Dr. David Alan Gilbert - dgilbert: Fixed missing {}'s style nit -(cherry picked from commit 449e8171f96a6a944d1f3b7d3627ae059eae21ca) ---- - tools/virtiofsd/passthrough_ll.c | 27 +++++++++++++++++++++++++++ - 1 file changed, 27 insertions(+) - -diff --git a/tools/virtiofsd/passthrough_ll.c b/tools/virtiofsd/passthrough_ll.c -index 64b5b4fbb1..b3d0674f6d 100644 ---- a/tools/virtiofsd/passthrough_ll.c -+++ b/tools/virtiofsd/passthrough_ll.c -@@ -54,6 +54,7 @@ - #include - #include - #include -+#include - - #include "qemu/cutils.h" - #include "passthrough_helpers.h" -@@ -1161,6 +1162,30 @@ static void lo_lookup(fuse_req_t req, fuse_ino_t parent, const char *name) - #define OURSYS_setresuid SYS_setresuid - #endif - -+static void drop_supplementary_groups(void) -+{ -+ int ret; -+ -+ ret = getgroups(0, NULL); -+ if (ret == -1) { -+ fuse_log(FUSE_LOG_ERR, "getgroups() failed with error=%d:%s\n", -+ errno, strerror(errno)); -+ exit(1); -+ } -+ -+ if (!ret) { -+ return; -+ } -+ -+ /* Drop all supplementary groups. We should not need it */ -+ ret = setgroups(0, NULL); -+ if (ret == -1) { -+ fuse_log(FUSE_LOG_ERR, "setgroups() failed with error=%d:%s\n", -+ errno, strerror(errno)); -+ exit(1); -+ } -+} -+ - /* - * Change to uid/gid of caller so that file is created with - * ownership of caller. -@@ -3926,6 +3951,8 @@ int main(int argc, char *argv[]) - - qemu_init_exec_dir(argv[0]); - -+ drop_supplementary_groups(); -+ - pthread_mutex_init(&lo.mutex, NULL); - lo.inodes = g_hash_table_new(lo_key_hash, lo_key_equal); - lo.root.fd = -1; --- -2.27.0 - diff --git a/SOURCES/kvm-vmxcap-Add-5-level-EPT-bit.patch b/SOURCES/kvm-vmxcap-Add-5-level-EPT-bit.patch deleted file mode 100644 index 0701cc0..0000000 --- a/SOURCES/kvm-vmxcap-Add-5-level-EPT-bit.patch +++ /dev/null @@ -1,49 +0,0 @@ -From 5d8e4aefe49d4ea5237efc8132e44183b99ebabc Mon Sep 17 00:00:00 2001 -From: Vitaly Kuznetsov -Date: Wed, 16 Mar 2022 09:35:23 +0100 -Subject: [PATCH 03/14] vmxcap: Add 5-level EPT bit - -RH-Author: Vitaly Kuznetsov -RH-MergeRequest: 126: i386: Add Icelake-Server-v6 CPU model with 5-level EPT support -RH-Commit: [1/2] 3f74e192278b8886de5dbeaf607521e9d3b744eb -RH-Bugzilla: 2038051 -RH-Acked-by: Igor Mammedov -RH-Acked-by: Cornelia Huck -RH-Acked-by: Paolo Bonzini - -Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2038051 -Brew: https://brewweb.engineering.redhat.com/brew/taskinfo?taskID=43862630 - -commit d312378e59658473aa91aa15c67ec6200d92e5ff -Author: Vitaly Kuznetsov -Date: Mon Feb 21 15:53:16 2022 +0100 - - vmxcap: Add 5-level EPT bit - - 5-level EPT is present in Icelake Server CPUs and is supported by QEMU - ('vmx-page-walk-5'). - - Signed-off-by: Vitaly Kuznetsov - Message-Id: <20220221145316.576138-2-vkuznets@redhat.com> - Signed-off-by: Paolo Bonzini - -Signed-off-by: Vitaly Kuznetsov ---- - scripts/kvm/vmxcap | 1 + - 1 file changed, 1 insertion(+) - -diff --git a/scripts/kvm/vmxcap b/scripts/kvm/vmxcap -index 6fe66d5f57..f140040104 100755 ---- a/scripts/kvm/vmxcap -+++ b/scripts/kvm/vmxcap -@@ -249,6 +249,7 @@ controls = [ - bits = { - 0: 'Execute-only EPT translations', - 6: 'Page-walk length 4', -+ 7: 'Page-walk length 5', - 8: 'Paging-structure memory type UC', - 14: 'Paging-structure memory type WB', - 16: '2MB EPT pages', --- -2.31.1 - diff --git a/SOURCES/kvm-x86-Add-q35-RHEL-8.6.0-machine-type.patch b/SOURCES/kvm-x86-Add-q35-RHEL-8.6.0-machine-type.patch deleted file mode 100644 index eb3273c..0000000 --- a/SOURCES/kvm-x86-Add-q35-RHEL-8.6.0-machine-type.patch +++ /dev/null @@ -1,65 +0,0 @@ -From 1b8eeb1323fa21c7b26d0396fae5ae4a8cdb1ace Mon Sep 17 00:00:00 2001 -From: "Dr. David Alan Gilbert" -Date: Tue, 11 Jan 2022 18:29:31 +0000 -Subject: [PATCH 1/3] x86: Add q35 RHEL 8.6.0 machine type - -RH-Author: Dr. David Alan Gilbert -RH-MergeRequest: 61: x86: Add rhel 8.6.0 & 9.0.0 machine types -RH-Commit: [1/2] 189335cf0e4ad117e3e401f23aa07cddbbac50df (dagrh/c-9-s-qemu-kvm) -RH-Bugzilla: 1945666 -RH-Acked-by: Miroslav Rezanina -RH-Acked-by: Stefano Garzarella -RH-Acked-by: Cornelia Huck - -Add the new 8.6.0 machine type; note that while the -AV -notation has gone in the product naming, just keep the smbios -definitions the same for consistency. - -Signed-off-by: Dr. David Alan Gilbert ---- - hw/i386/pc_q35.c | 21 ++++++++++++++++++++- - 1 file changed, 20 insertions(+), 1 deletion(-) - -diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c -index 3b748ddd7b..0c25305f15 100644 ---- a/hw/i386/pc_q35.c -+++ b/hw/i386/pc_q35.c -@@ -646,6 +646,24 @@ 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_rhel860(MachineState *machine) -+{ -+ pc_q35_init(machine); -+} -+ -+static void pc_q35_machine_rhel860_options(MachineClass *m) -+{ -+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m); -+ pc_q35_machine_rhel_options(m); -+ m->desc = "RHEL-8.6.0 PC (Q35 + ICH9, 2009)"; -+ pcmc->smbios_stream_product = "RHEL-AV"; -+ pcmc->smbios_stream_version = "8.6.0"; -+} -+ -+DEFINE_PC_MACHINE(q35_rhel860, "pc-q35-rhel8.6.0", pc_q35_init_rhel860, -+ pc_q35_machine_rhel860_options); -+ -+ - static void pc_q35_init_rhel850(MachineState *machine) - { - pc_q35_init(machine); -@@ -654,8 +672,9 @@ static void pc_q35_init_rhel850(MachineState *machine) - static void pc_q35_machine_rhel850_options(MachineClass *m) - { - PCMachineClass *pcmc = PC_MACHINE_CLASS(m); -- pc_q35_machine_rhel_options(m); -+ pc_q35_machine_rhel860_options(m); - m->desc = "RHEL-8.5.0 PC (Q35 + ICH9, 2009)"; -+ m->alias = NULL; - pcmc->smbios_stream_product = "RHEL-AV"; - pcmc->smbios_stream_version = "8.5.0"; - compat_props_add(m->compat_props, hw_compat_rhel_8_5, --- -2.27.0 - diff --git a/SOURCES/kvm-x86-Add-q35-RHEL-9.0.0-machine-type.patch b/SOURCES/kvm-x86-Add-q35-RHEL-9.0.0-machine-type.patch deleted file mode 100644 index 4367495..0000000 --- a/SOURCES/kvm-x86-Add-q35-RHEL-9.0.0-machine-type.patch +++ /dev/null @@ -1,75 +0,0 @@ -From 3d5024fb9c904a649d07f0def3a90b3d36611215 Mon Sep 17 00:00:00 2001 -From: "Dr. David Alan Gilbert" -Date: Wed, 12 Jan 2022 13:21:57 +0000 -Subject: [PATCH 2/3] x86: Add q35 RHEL 9.0.0 machine type - -RH-Author: Dr. David Alan Gilbert -RH-MergeRequest: 61: x86: Add rhel 8.6.0 & 9.0.0 machine types -RH-Commit: [2/2] 743378502459b978efd632271f97ddb824422203 (dagrh/c-9-s-qemu-kvm) -RH-Bugzilla: 1945666 -RH-Acked-by: Miroslav Rezanina -RH-Acked-by: Stefano Garzarella -RH-Acked-by: Cornelia Huck - -Add a rhel-9.0.0 q35 machine type; it's currently identical to 8.6.0; -but having a separate machine type will make life easier in the future -when the 8.x types go away. - -Note: The smbios stream product name has now changed to 'RHEL' - -bz: https://bugzilla.redhat.com/show_bug.cgi?id=1945666 -Signed-off-by: Dr. David Alan Gilbert ---- - hw/i386/pc_q35.c | 21 +++++++++++++++++++-- - 1 file changed, 19 insertions(+), 2 deletions(-) - -diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c -index 0c25305f15..bf9ad32f0e 100644 ---- a/hw/i386/pc_q35.c -+++ b/hw/i386/pc_q35.c -@@ -646,6 +646,23 @@ 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_rhel900(MachineState *machine) -+{ -+ pc_q35_init(machine); -+} -+ -+static void pc_q35_machine_rhel900_options(MachineClass *m) -+{ -+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m); -+ pc_q35_machine_rhel_options(m); -+ m->desc = "RHEL-9.0.0 PC (Q35 + ICH9, 2009)"; -+ pcmc->smbios_stream_product = "RHEL"; -+ pcmc->smbios_stream_version = "9.0.0"; -+} -+ -+DEFINE_PC_MACHINE(q35_rhel900, "pc-q35-rhel9.0.0", pc_q35_init_rhel900, -+ pc_q35_machine_rhel900_options); -+ - static void pc_q35_init_rhel860(MachineState *machine) - { - pc_q35_init(machine); -@@ -654,8 +671,9 @@ static void pc_q35_init_rhel860(MachineState *machine) - static void pc_q35_machine_rhel860_options(MachineClass *m) - { - PCMachineClass *pcmc = PC_MACHINE_CLASS(m); -- pc_q35_machine_rhel_options(m); -+ pc_q35_machine_rhel900_options(m); - m->desc = "RHEL-8.6.0 PC (Q35 + ICH9, 2009)"; -+ m->alias = NULL; - pcmc->smbios_stream_product = "RHEL-AV"; - pcmc->smbios_stream_version = "8.6.0"; - } -@@ -674,7 +692,6 @@ static void pc_q35_machine_rhel850_options(MachineClass *m) - PCMachineClass *pcmc = PC_MACHINE_CLASS(m); - pc_q35_machine_rhel860_options(m); - m->desc = "RHEL-8.5.0 PC (Q35 + ICH9, 2009)"; -- m->alias = NULL; - pcmc->smbios_stream_product = "RHEL-AV"; - pcmc->smbios_stream_version = "8.5.0"; - compat_props_add(m->compat_props, hw_compat_rhel_8_5, --- -2.27.0 - diff --git a/SOURCES/tests_data_acpi_pc_SSDT.dimmpxm b/SOURCES/tests_data_acpi_pc_SSDT.dimmpxm deleted file mode 100644 index ac55387..0000000 Binary files a/SOURCES/tests_data_acpi_pc_SSDT.dimmpxm and /dev/null differ diff --git a/SOURCES/tests_data_acpi_q35_FACP.slic b/SOURCES/tests_data_acpi_q35_FACP.slic deleted file mode 100644 index 15986e0..0000000 Binary files a/SOURCES/tests_data_acpi_q35_FACP.slic and /dev/null differ diff --git a/SOURCES/tests_data_acpi_q35_SSDT.dimmpxm b/SOURCES/tests_data_acpi_q35_SSDT.dimmpxm deleted file mode 100644 index 98e6f0e..0000000 Binary files a/SOURCES/tests_data_acpi_q35_SSDT.dimmpxm and /dev/null differ diff --git a/SOURCES/tests_data_acpi_virt_SSDT.memhp b/SOURCES/tests_data_acpi_virt_SSDT.memhp deleted file mode 100644 index 375d7b6..0000000 Binary files a/SOURCES/tests_data_acpi_virt_SSDT.memhp and /dev/null differ diff --git a/SPECS/qemu-kvm.spec b/SPECS/qemu-kvm.spec index 54ac6fa..6ee557d 100644 --- a/SPECS/qemu-kvm.spec +++ b/SPECS/qemu-kvm.spec @@ -101,7 +101,7 @@ %global target_list %{kvm_target}-softmmu %global block_drivers_rw_list qcow2,raw,file,host_device,nbd,iscsi,rbd,blkdebug,luks,null-co,nvme,copy-on-read,throttle,compress -%global block_drivers_ro_list vdi,vmdk,vhdx,vpc,https,ssh +%global block_drivers_ro_list vdi,vmdk,vhdx,vpc,https %define qemudocdir %{_docdir}/%{name} %global firmwaredirs "%{_datadir}/qemu-firmware:%{_datadir}/ipxe/qemu:%{_datadir}/seavgabios:%{_datadir}/seabios" @@ -150,8 +150,8 @@ Obsoletes: %{name}-block-ssh <= %{epoch}:%{version} \ Summary: QEMU is a machine emulator and virtualizer Name: qemu-kvm -Version: 6.2.0 -Release: 11%{?rcrel}%{?dist}%{?cc_suffix}.5 +Version: 7.0.0 +Release: 13%{?rcrel}%{?dist}%{?cc_suffix} # Epoch because we pushed a qemu-1.0 package. AIUI this can't ever be dropped # Epoch 15 used for RHEL 8 # Epoch 17 used for RHEL 9 (due to release versioning offset in RHEL 8.5) @@ -174,176 +174,326 @@ Source28: 95-kvm-memlock.conf Source30: kvm-s390x.conf Source31: kvm-x86.conf Source36: README.tests -Source37: tests_data_acpi_pc_SSDT.dimmpxm -Source38: tests_data_acpi_q35_FACP.slic -Source39: tests_data_acpi_q35_SSDT.dimmpxm -Source40: tests_data_acpi_virt_SSDT.memhp - - -Patch0001: 0001-ui-clipboard-Don-t-use-g_autoptr-just-to-free-a-vari.patch -Patch0005: 0005-Initial-redhat-build.patch -Patch0006: 0006-Enable-disable-devices-for-RHEL.patch -Patch0007: 0007-Machine-type-related-general-changes.patch -Patch0008: 0008-Add-aarch64-machine-types.patch -Patch0009: 0009-Add-ppc64-machine-types.patch -Patch0010: 0010-Add-s390x-machine-types.patch -Patch0011: 0011-Add-x86_64-machine-types.patch -Patch0012: 0012-Enable-make-check.patch -Patch0013: 0013-vfio-cap-number-of-devices-that-can-be-assigned.patch -Patch0014: 0014-Add-support-statement-to-help-output.patch -Patch0015: 0015-globally-limit-the-maximum-number-of-CPUs.patch -Patch0016: 0016-Use-qemu-kvm-in-documentation-instead-of-qemu-system.patch -Patch0017: 0017-virtio-scsi-Reject-scsi-cd-if-data-plane-enabled-RHE.patch -Patch0018: 0018-BZ1653590-Require-at-least-64kiB-pages-for-downstrea.patch -Patch0019: 0019-qcow2-Deprecation-warning-when-opening-v2-images-rw.patch -Patch0020: 0020-Fix-virtio-net-pci-vectors-compat.patch -Patch0021: 0021-x86-rhel-machine-types-Add-pc_rhel_8_5_compat.patch -Patch0022: 0022-x86-rhel-machine-types-Wire-compat-into-q35-and-i440.patch -Patch0023: 0023-redhat-virt-rhel8.5.0-Update-machine-type-compatibil.patch -Patch0024: 0024-redhat-Add-s390x-machine-type-compatibility-handling.patch -Patch0025: 0025-compat-Update-hw_compat_rhel_8_5-with-6.2.0-RC2-chan.patch -# For bz#2008060 - Fix CPU Model for new IBM Z Hardware - qemu part -Patch26: kvm-redhat-Add-rhel8.6.0-and-rhel9.0.0-machine-types-for.patch -# For bz#2014484 - [RHEL9] Enable virtio-mem as tech-preview on x86-64 - QEMU -Patch27: kvm-redhat-Enable-virtio-mem-as-tech-preview-on-x86-64.patch -# For bz#2031044 - Add rhel-9.0.0 machine types for RHEL 9.0 [aarch64] -Patch28: kvm-hw-arm-virt-Register-iommu-as-a-class-property.patch -# For bz#2031044 - Add rhel-9.0.0 machine types for RHEL 9.0 [aarch64] -Patch29: kvm-hw-arm-virt-Register-its-as-a-class-property.patch -# For bz#2031044 - Add rhel-9.0.0 machine types for RHEL 9.0 [aarch64] -Patch30: kvm-hw-arm-virt-Rename-default_bus_bypass_iommu.patch -# For bz#2031044 - Add rhel-9.0.0 machine types for RHEL 9.0 [aarch64] -Patch31: kvm-hw-arm-virt-Expose-the-RAS-option.patch -# For bz#2031044 - Add rhel-9.0.0 machine types for RHEL 9.0 [aarch64] -Patch32: kvm-hw-arm-virt-Add-9.0-machine-type-and-remove-8.5-one.patch -# For bz#2031044 - Add rhel-9.0.0 machine types for RHEL 9.0 [aarch64] -Patch33: kvm-hw-arm-virt-Check-no_tcg_its-and-minor-style-changes.patch -# For bz#2024544 - Fio workers hangs when running fio with 32 jobs iodepth 32 and QEMU's userspace NVMe driver -Patch34: kvm-block-nvme-fix-infinite-loop-in-nvme_free_req_queue_.patch -# For bz#2028623 - [9.0] machine types: 6.2: Fix prefer_sockets -Patch35: kvm-rhel-machine-types-x86-set-prefer_sockets.patch -# For bz#1945666 - 9.0: x86 machine types -Patch36: kvm-x86-Add-q35-RHEL-8.6.0-machine-type.patch -# For bz#1945666 - 9.0: x86 machine types -Patch37: kvm-x86-Add-q35-RHEL-9.0.0-machine-type.patch -# For bz#2036669 - DEVICE_DELETED event is not delivered for device frontend if -device is configured via JSON -Patch38: kvm-softmmu-fix-device-deletion-events-with-device-JSON-.patch -# For bz#1962088 - [QSD] wrong help message for the fuse -Patch39: kvm-qemu-storage-daemon-Add-vhost-user-blk-help.patch -# For bz#1962088 - [QSD] wrong help message for the fuse -Patch40: kvm-qemu-storage-daemon-Fix-typo-in-vhost-user-blk-help.patch -# For bz#2046201 - CVE-2022-0358 qemu-kvm: QEMU: virtiofsd: potential privilege escalation via CVE-2018-13405 [rhel-9.0] -Patch41: kvm-virtiofsd-Drop-membership-of-all-supplementary-group.patch -# For bz#2034791 - Booting from Local Snapshot Core Dumped Whose Backing File Is Based on RBD -Patch42: kvm-block-rbd-fix-handling-of-holes-in-.bdrv_co_block_st.patch -# For bz#2034791 - Booting from Local Snapshot Core Dumped Whose Backing File Is Based on RBD -Patch43: kvm-block-rbd-workaround-for-ceph-issue-53784.patch -# For bz#2033708 - [Intel 9.0 Feat] qemu-kvm: SGX 1.5 (SGX1 + Flexible Launch Control) support -Patch44: kvm-numa-Enable-numa-for-SGX-EPC-sections.patch -# For bz#2033708 - [Intel 9.0 Feat] qemu-kvm: SGX 1.5 (SGX1 + Flexible Launch Control) support -Patch45: kvm-numa-Support-SGX-numa-in-the-monitor-and-Libvirt-int.patch -# For bz#2033708 - [Intel 9.0 Feat] qemu-kvm: SGX 1.5 (SGX1 + Flexible Launch Control) support -Patch46: kvm-doc-Add-the-SGX-numa-description.patch -# For bz#2033708 - [Intel 9.0 Feat] qemu-kvm: SGX 1.5 (SGX1 + Flexible Launch Control) support -Patch47: kvm-Enable-SGX-RH-Only.patch -# For bz#2033708 - [Intel 9.0 Feat] qemu-kvm: SGX 1.5 (SGX1 + Flexible Launch Control) support -Patch48: kvm-qapi-Cleanup-SGX-related-comments-and-restore-sectio.patch -# For bz#2041461 - Inconsistent block status reply in qemu-nbd -Patch49: kvm-block-io-Update-BSC-only-if-want_zero-is-true.patch -# For bz#2041461 - Inconsistent block status reply in qemu-nbd -Patch50: kvm-iotests-block-status-cache-New-test.patch -# For bz#1882917 - the target image size is incorrect when converting a badly fragmented file -Patch51: kvm-iotests-Test-qemu-img-convert-of-zeroed-data-cluster.patch -# For bz#1882917 - the target image size is incorrect when converting a badly fragmented file -Patch52: kvm-qemu-img-make-is_allocated_sectors-more-efficient.patch -# For bz#2040123 - Qemu core dumped when do block-stream to a snapshot node on non-enough space storage -Patch53: kvm-block-backend-prevent-dangling-BDS-pointers-across-a.patch -# For bz#2040123 - Qemu core dumped when do block-stream to a snapshot node on non-enough space storage -Patch54: kvm-iotests-stream-error-on-reset-New-test.patch -# For bz#2042481 - [aarch64] Launch guest with "default-bus-bypass-iommu=off,iommu=smmuv3" and "iommu_platform=on", guest hangs after system_reset -Patch55: kvm-hw-arm-smmuv3-Fix-device-reset.patch -# For bz#2046659 - qemu crash after execute blockdev-reopen with iothread -Patch56: kvm-block-Lock-AioContext-for-drain_end-in-blockdev-reop.patch -# For bz#2046659 - qemu crash after execute blockdev-reopen with iothread -Patch57: kvm-iotests-Test-blockdev-reopen-with-iothreads-and-thro.patch -# For bz#2033626 - Qemu core dump when start guest with nbd node or do block jobs to nbd node -Patch58: kvm-block-nbd-Delete-reconnect-delay-timer-when-done.patch -# For bz#2033626 - Qemu core dump when start guest with nbd node or do block jobs to nbd node -Patch59: kvm-block-nbd-Assert-there-are-no-timers-when-closed.patch -# For bz#2033626 - Qemu core dump when start guest with nbd node or do block jobs to nbd node -Patch60: kvm-iotests.py-Add-QemuStorageDaemon-class.patch -# For bz#2033626 - Qemu core dump when start guest with nbd node or do block jobs to nbd node -Patch61: kvm-iotests-281-Test-lingering-timers.patch -# For bz#2033626 - Qemu core dump when start guest with nbd node or do block jobs to nbd node -Patch62: kvm-block-nbd-Move-s-ioc-on-AioContext-change.patch -# For bz#2033626 - Qemu core dump when start guest with nbd node or do block jobs to nbd node -Patch63: kvm-iotests-281-Let-NBD-connection-yield-in-iothread.patch -# For bz#2042820 - qemu crash when try to copy and paste contents from client to VM -Patch64: kvm-Revert-ui-clipboard-Don-t-use-g_autoptr-just-to-free.patch -# For bz#2042820 - qemu crash when try to copy and paste contents from client to VM -Patch65: kvm-ui-avoid-compiler-warnings-from-unused-clipboard-inf.patch -# For bz#2042820 - qemu crash when try to copy and paste contents from client to VM -Patch66: kvm-ui-clipboard-fix-use-after-free-regression.patch -# For bz#2042820 - qemu crash when try to copy and paste contents from client to VM -Patch67: kvm-ui-vnc.c-Fixed-a-deadlock-bug.patch -# For bz#2044818 - Qemu Core Dumped when migrate -> migrate_cancel -> migrate again during guest is paused -Patch68: kvm-memory-Fix-incorrect-calls-of-log_global_start-stop.patch -# For bz#2044818 - Qemu Core Dumped when migrate -> migrate_cancel -> migrate again during guest is paused -Patch69: kvm-memory-Fix-qemu-crash-on-starting-dirty-log-twice-wi.patch -# For bz#2052050 - Mark all RHEL-8 and earlier machine types as deprecated -Patch70: kvm-RHEL-mark-old-machine-types-as-deprecated.patch -# For bz#2059786 - [virtual network][rhel9][vDPA] qemu crash after hot unplug vdpa device -Patch71: kvm-hw-virtio-vdpa-Fix-leak-of-host-notifier-memory-regi.patch -# For bz#2053584 - watchdog: BUG: soft lockup - CPU#3 stuck for 22s! [cat:2843] -Patch72: kvm-pci-expose-TYPE_XIO3130_DOWNSTREAM-name.patch -# For bz#2053584 - watchdog: BUG: soft lockup - CPU#3 stuck for 22s! [cat:2843] -Patch73: kvm-acpi-pcihp-pcie-set-power-on-cap-on-parent-slot.patch -# For bz#2038051 - Win11 (q35+edk2) guest broke after install wsl2 through 'wsl --install -d Ubuntu-20.04' -Patch74: kvm-vmxcap-Add-5-level-EPT-bit.patch -# For bz#2038051 - Win11 (q35+edk2) guest broke after install wsl2 through 'wsl --install -d Ubuntu-20.04' -Patch75: kvm-i386-Add-Icelake-Server-v6-CPU-model-with-5-level-EP.patch -# For bz#2043531 - Guest can not start with SLIC acpi table -Patch76: kvm-acpi-fix-QEMU-crash-when-started-with-SLIC-table.patch -# For bz#2043531 - Guest can not start with SLIC acpi table -Patch77: kvm-tests-acpi-whitelist-expected-blobs-before-changing-.patch -# For bz#2043531 - Guest can not start with SLIC acpi table -Patch78: kvm-tests-acpi-add-SLIC-table-test.patch -# For bz#2043531 - Guest can not start with SLIC acpi table -Patch79: kvm-tests-acpi-SLIC-update-expected-blobs.patch -# For bz#2043531 - Guest can not start with SLIC acpi table -Patch80: kvm-tests-acpi-manually-pad-OEM_ID-OEM_TABLE_ID-for-test.patch -# For bz#2043531 - Guest can not start with SLIC acpi table -Patch81: kvm-tests-acpi-whitelist-nvdimm-s-SSDT-and-FACP.slic-exp.patch -# For bz#2043531 - Guest can not start with SLIC acpi table -Patch82: kvm-acpi-fix-OEM-ID-OEM-Table-ID-padding.patch -# For bz#2043531 - Guest can not start with SLIC acpi table -Patch83: kvm-tests-acpi-update-expected-blobs.patch -# For bz#2043531 - Guest can not start with SLIC acpi table -Patch84: kvm-tests-acpi-test-short-OEM_ID-OEM_TABLE_ID-values-in-.patch -# For bz#2071102 - RHEL 9.0 guest with vsock device migration failed from RHEL 9.0 > RHEL 8.6 [rhel-9.0.0.z] -Patch85: kvm-RHEL-disable-seqpacket-for-vhost-vsock-device-in-rhe.patch -# For bz#2075635 - CVE-2022-26353 qemu-kvm: QEMU: virtio-net: map leaking on error during receive [rhel-9] [rhel-9.0.0.z] -Patch86: kvm-virtio-net-fix-map-leaking-on-error-during-receive.patch -# For bz#2075640 - CVE-2022-26354 qemu-kvm: QEMU: vhost-vsock: missing virtqueue detach on error can lead to memory leak [rhel-9] [rhel-9.0.0.z] -Patch87: kvm-vhost-vsock-detach-the-virqueue-element-in-case-of-e.patch -# For bz#2095795 - PXE boot crash qemu when using multiqueue vDPA [rhel-9.0.0.z] -Patch88: kvm-virtio-net-setup-vhost_dev-and-notifiers-for-cvq-onl.patch -# For bz#2095795 - PXE boot crash qemu when using multiqueue vDPA [rhel-9.0.0.z] -Patch89: kvm-virtio-net-align-ctrl_vq-index-for-non-mq-guest-for-.patch -# For bz#2095795 - PXE boot crash qemu when using multiqueue vDPA [rhel-9.0.0.z] -Patch90: kvm-vhost-vdpa-fix-improper-cleanup-in-net_init_vhost_vd.patch -# For bz#2095795 - PXE boot crash qemu when using multiqueue vDPA [rhel-9.0.0.z] -Patch91: kvm-vhost-net-fix-improper-cleanup-in-vhost_net_start.patch -# For bz#2095795 - PXE boot crash qemu when using multiqueue vDPA [rhel-9.0.0.z] -Patch92: kvm-vhost-vdpa-backend-feature-should-set-only-once.patch -# For bz#2095795 - PXE boot crash qemu when using multiqueue vDPA [rhel-9.0.0.z] -Patch93: kvm-vhost-vdpa-change-name-and-polarity-for-vhost_vdpa_o.patch -# For bz#2095795 - PXE boot crash qemu when using multiqueue vDPA [rhel-9.0.0.z] -Patch94: kvm-virtio-net-don-t-handle-mq-request-in-userspace-hand.patch -# For bz#2109569 - Stalled IO Operations in VM [rhel-9.0.0.z] -Patch95: kvm-linux-aio-fix-unbalanced-plugged-counter-in-laio_io_.patch -# For bz#2109569 - Stalled IO Operations in VM [rhel-9.0.0.z] -Patch96: kvm-linux-aio-explain-why-max-batch-is-checked-in-laio_i.patch + + +Patch0004: 0004-Initial-redhat-build.patch +Patch0005: 0005-Enable-disable-devices-for-RHEL.patch +Patch0006: 0006-Machine-type-related-general-changes.patch +Patch0007: 0007-Add-aarch64-machine-types.patch +Patch0008: 0008-Add-ppc64-machine-types.patch +Patch0009: 0009-Add-s390x-machine-types.patch +Patch0010: 0010-Add-x86_64-machine-types.patch +Patch0011: 0011-Enable-make-check.patch +Patch0012: 0012-vfio-cap-number-of-devices-that-can-be-assigned.patch +Patch0013: 0013-Add-support-statement-to-help-output.patch +Patch0014: 0014-globally-limit-the-maximum-number-of-CPUs.patch +Patch0015: 0015-Use-qemu-kvm-in-documentation-instead-of-qemu-system.patch +Patch0016: 0016-virtio-scsi-Reject-scsi-cd-if-data-plane-enabled-RHE.patch +Patch0017: 0017-BZ1653590-Require-at-least-64kiB-pages-for-downstrea.patch +Patch0018: 0018-qcow2-Deprecation-warning-when-opening-v2-images-rw.patch +Patch0019: 0019-WRB-Introduce-RHEL-9.0.0-hw-compat-structure.patch +Patch0020: 0020-redhat-Update-s390x-machine-type-compatibility-for-r.patch +Patch0021: 0021-pc-Move-s3-s4-suspend-disabling-to-compat.patch +# For bz#2044162 - [RHEL9.1] Enable virtio-mem as tech-preview on ARM64 QEMU +Patch22: kvm-configs-devices-aarch64-softmmu-Enable-CONFIG_VIRTIO.patch +# For bz#2081022 - Build regression on ppc64le with c9s qemu-kvm 7.0.0-1 changes +Patch23: kvm-target-ppc-cpu-models-Fix-ppc_cpu_aliases-list-for-R.patch +# For bz#2046029 - [WRB] New machine type property - dtb-kaslr-seed +Patch24: kvm-hw-arm-virt-Remove-the-dtb-kaslr-seed-machine-option.patch +# For bz#2046029 - [WRB] New machine type property - dtb-kaslr-seed +Patch25: kvm-hw-arm-virt-Fix-missing-initialization-in-instance-c.patch +# For bz#1477099 - virtio-iommu (including ACPI, VHOST/VFIO integration, migration support) +Patch26: kvm-Enable-virtio-iommu-pci-on-aarch64.patch +# For bz#2037612 - [Win11][tpm][QL41112 PF] vfio_listener_region_add received unaligned region +Patch27: kvm-sysemu-tpm-Add-a-stub-function-for-TPM_IS_CRB.patch +# For bz#2037612 - [Win11][tpm][QL41112 PF] vfio_listener_region_add received unaligned region +Patch28: kvm-vfio-common-remove-spurious-tpm-crb-cmd-misalignment.patch +# For bz#2041823 - [aarch64][numa] When there are at least 6 Numa nodes serial log shows 'arch topology borken' +Patch29: kvm-qapi-machine.json-Add-cluster-id.patch +# For bz#2041823 - [aarch64][numa] When there are at least 6 Numa nodes serial log shows 'arch topology borken' +Patch30: kvm-qtest-numa-test-Specify-CPU-topology-in-aarch64_numa.patch +# For bz#2041823 - [aarch64][numa] When there are at least 6 Numa nodes serial log shows 'arch topology borken' +Patch31: kvm-hw-arm-virt-Consider-SMP-configuration-in-CPU-topolo.patch +# For bz#2041823 - [aarch64][numa] When there are at least 6 Numa nodes serial log shows 'arch topology borken' +Patch32: kvm-qtest-numa-test-Correct-CPU-and-NUMA-association-in-.patch +# For bz#2041823 - [aarch64][numa] When there are at least 6 Numa nodes serial log shows 'arch topology borken' +Patch33: kvm-hw-arm-virt-Fix-CPU-s-default-NUMA-node-ID.patch +# For bz#2041823 - [aarch64][numa] When there are at least 6 Numa nodes serial log shows 'arch topology borken' +Patch34: kvm-hw-acpi-aml-build-Use-existing-CPU-topology-to-build.patch +# For bz#2079938 - qemu coredump when boot with multi disks (qemu) failed to set up stack guard page: Cannot allocate memory +Patch35: kvm-coroutine-Rename-qemu_coroutine_inc-dec_pool_size.patch +# For bz#2079938 - qemu coredump when boot with multi disks (qemu) failed to set up stack guard page: Cannot allocate memory +Patch36: kvm-coroutine-Revert-to-constant-batch-size.patch +# For bz#2079347 - Guest boot blocked when scsi disks using same iothread and 100% CPU consumption +Patch37: kvm-virtio-scsi-fix-ctrl-and-event-handler-functions-in-.patch +# For bz#2079347 - Guest boot blocked when scsi disks using same iothread and 100% CPU consumption +Patch38: kvm-virtio-scsi-don-t-waste-CPU-polling-the-event-virtqu.patch +# For bz#2079347 - Guest boot blocked when scsi disks using same iothread and 100% CPU consumption +Patch39: kvm-virtio-scsi-clean-up-virtio_scsi_handle_event_vq.patch +# For bz#2079347 - Guest boot blocked when scsi disks using same iothread and 100% CPU consumption +Patch40: kvm-virtio-scsi-clean-up-virtio_scsi_handle_ctrl_vq.patch +# For bz#2079347 - Guest boot blocked when scsi disks using same iothread and 100% CPU consumption +Patch41: kvm-virtio-scsi-clean-up-virtio_scsi_handle_cmd_vq.patch +# For bz#2079347 - Guest boot blocked when scsi disks using same iothread and 100% CPU consumption +Patch42: kvm-virtio-scsi-move-request-related-items-from-.h-to-.c.patch +# For bz#1995710 - RFE: Allow virtio-scsi CD-ROM media change with IOThreads +Patch43: kvm-Revert-virtio-scsi-Reject-scsi-cd-if-data-plane-enab.patch +# For bz#2064530 - Rebuild qemu-kvm with clang-14 +Patch44: kvm-migration-Fix-operator-type.patch +# For bz#1708300 - RFE: qemu-nbd vs NBD_FLAG_CAN_MULTI_CONN +Patch45: kvm-qemu-nbd-Pass-max-connections-to-blockdev-layer.patch +# For bz#1708300 - RFE: qemu-nbd vs NBD_FLAG_CAN_MULTI_CONN +Patch46: kvm-nbd-server-Allow-MULTI_CONN-for-shared-writable-expo.patch +# For bz#2031024 - Add support for fixing thread pool size [QEMU] +Patch47: kvm-Introduce-event-loop-base-abstract-class.patch +# For bz#2031024 - Add support for fixing thread pool size [QEMU] +Patch48: kvm-util-main-loop-Introduce-the-main-loop-into-QOM.patch +# For bz#2031024 - Add support for fixing thread pool size [QEMU] +Patch49: kvm-util-event-loop-base-Introduce-options-to-set-the-th.patch +# For bz#2072379 - Fail to rebuild the reference count tables of qcow2 image on host block devices (e.g. LVs) +Patch50: kvm-qcow2-Improve-refcount-structure-rebuilding.patch +# For bz#2072379 - Fail to rebuild the reference count tables of qcow2 image on host block devices (e.g. LVs) +Patch51: kvm-iotests-108-Test-new-refcount-rebuild-algorithm.patch +# For bz#2072379 - Fail to rebuild the reference count tables of qcow2 image on host block devices (e.g. LVs) +Patch52: kvm-qcow2-Add-errp-to-rebuild_refcount_structure.patch +# For bz#2072379 - Fail to rebuild the reference count tables of qcow2 image on host block devices (e.g. LVs) +Patch53: kvm-iotests-108-Fix-when-missing-user_allow_other.patch +# For bz#2070804 - PXE boot crash qemu when using multiqueue vDPA +Patch54: kvm-virtio-net-setup-vhost_dev-and-notifiers-for-cvq-onl.patch +# For bz#2070804 - PXE boot crash qemu when using multiqueue vDPA +Patch55: kvm-virtio-net-align-ctrl_vq-index-for-non-mq-guest-for-.patch +# For bz#2070804 - PXE boot crash qemu when using multiqueue vDPA +Patch56: kvm-vhost-vdpa-fix-improper-cleanup-in-net_init_vhost_vd.patch +# For bz#2070804 - PXE boot crash qemu when using multiqueue vDPA +Patch57: kvm-vhost-net-fix-improper-cleanup-in-vhost_net_start.patch +# For bz#2070804 - PXE boot crash qemu when using multiqueue vDPA +Patch58: kvm-vhost-vdpa-backend-feature-should-set-only-once.patch +# For bz#2070804 - PXE boot crash qemu when using multiqueue vDPA +Patch59: kvm-vhost-vdpa-change-name-and-polarity-for-vhost_vdpa_o.patch +# For bz#2070804 - PXE boot crash qemu when using multiqueue vDPA +Patch60: kvm-virtio-net-don-t-handle-mq-request-in-userspace-hand.patch +# For bz#2094270 - Do not set the hard vCPU limit to the soft vCPU limit in downstream qemu-kvm anymore +Patch61: kvm-Revert-globally-limit-the-maximum-number-of-CPUs.patch +# For bz#2086262 - [Win11][tpm]vfio_listener_region_del received unaligned region +Patch62: kvm-vfio-common-remove-spurious-warning-on-vfio_listener.patch +# For bz#1952483 - RFE: QEMU's coroutines fail with CFLAGS=-flto on non-x86_64 architectures +Patch63: kvm-coroutine-ucontext-use-QEMU_DEFINE_STATIC_CO_TLS.patch +# For bz#1952483 - RFE: QEMU's coroutines fail with CFLAGS=-flto on non-x86_64 architectures +Patch64: kvm-coroutine-use-QEMU_DEFINE_STATIC_CO_TLS.patch +# For bz#1952483 - RFE: QEMU's coroutines fail with CFLAGS=-flto on non-x86_64 architectures +Patch65: kvm-coroutine-win32-use-QEMU_DEFINE_STATIC_CO_TLS.patch +# For bz#2094252 - Compile the virtio-iommu device on x86_64 +Patch66: kvm-Enable-virtio-iommu-pci-on-x86_64.patch +# For bz#2092788 - Stalled IO Operations in VM +Patch67: kvm-linux-aio-fix-unbalanced-plugged-counter-in-laio_io_.patch +# For bz#2092788 - Stalled IO Operations in VM +Patch68: kvm-linux-aio-explain-why-max-batch-is-checked-in-laio_i.patch +# For bz#2060839 - Consider deprecating CPU models like "kvm64" / "qemu64" on RHEL 9 +Patch69: kvm-tests-avocado-update-aarch64_virt-test-to-exercise-c.patch +# For bz#2060839 - Consider deprecating CPU models like "kvm64" / "qemu64" on RHEL 9 +Patch70: kvm-RHEL-only-tests-avocado-Switch-aarch64-tests-from-a5.patch +# For bz#2060839 - Consider deprecating CPU models like "kvm64" / "qemu64" on RHEL 9 +Patch71: kvm-RHEL-only-AArch64-Drop-unsupported-CPU-types.patch +# For bz#2060839 - Consider deprecating CPU models like "kvm64" / "qemu64" on RHEL 9 +Patch72: kvm-target-i386-deprecate-CPUs-older-than-x86_64-v2-ABI.patch +# For bz#2060839 - Consider deprecating CPU models like "kvm64" / "qemu64" on RHEL 9 +Patch73: kvm-target-s390x-deprecate-CPUs-older-than-z14.patch +# For bz#2060839 - Consider deprecating CPU models like "kvm64" / "qemu64" on RHEL 9 +Patch74: kvm-target-arm-deprecate-named-CPU-models.patch +# For bz#1968509 - Use MSG_ZEROCOPY on QEMU Live Migration +Patch75: kvm-meson.build-Fix-docker-test-build-alpine-when-includ.patch +# For bz#1968509 - Use MSG_ZEROCOPY on QEMU Live Migration +Patch76: kvm-QIOChannel-Add-flags-on-io_writev-and-introduce-io_f.patch +# For bz#1968509 - Use MSG_ZEROCOPY on QEMU Live Migration +Patch77: kvm-QIOChannelSocket-Implement-io_writev-zero-copy-flag-.patch +# For bz#1968509 - Use MSG_ZEROCOPY on QEMU Live Migration +Patch78: kvm-migration-Add-zero-copy-send-parameter-for-QMP-HMP-f.patch +# For bz#1968509 - Use MSG_ZEROCOPY on QEMU Live Migration +Patch79: kvm-migration-Add-migrate_use_tls-helper.patch +# For bz#1968509 - Use MSG_ZEROCOPY on QEMU Live Migration +Patch80: kvm-multifd-multifd_send_sync_main-now-returns-negative-.patch +# For bz#1968509 - Use MSG_ZEROCOPY on QEMU Live Migration +Patch81: kvm-multifd-Send-header-packet-without-flags-if-zero-cop.patch +# For bz#1968509 - Use MSG_ZEROCOPY on QEMU Live Migration +Patch82: kvm-multifd-Implement-zero-copy-write-in-multifd-migrati.patch +# For bz#1968509 - Use MSG_ZEROCOPY on QEMU Live Migration +Patch83: kvm-QIOChannelSocket-Introduce-assert-and-reduce-ifdefs-.patch +# For bz#1968509 - Use MSG_ZEROCOPY on QEMU Live Migration +Patch84: kvm-QIOChannelSocket-Fix-zero-copy-send-so-socket-flush-.patch +# For bz#1968509 - Use MSG_ZEROCOPY on QEMU Live Migration +Patch85: kvm-migration-Change-zero_copy_send-from-migration-param.patch +# For bz#2096143 - The migration port is not released if use it again for recovering postcopy migration +Patch86: kvm-migration-Allow-migrate-recover-to-run-multiple-time.patch +# For bz#2100106 - Fix virtio-iommu/vfio bypass +Patch87: kvm-virtio-iommu-Add-bypass-mode-support-to-assigned-dev.patch +# For bz#2100106 - Fix virtio-iommu/vfio bypass +Patch88: kvm-virtio-iommu-Use-recursive-lock-to-avoid-deadlock.patch +# For bz#2100106 - Fix virtio-iommu/vfio bypass +Patch89: kvm-virtio-iommu-Add-an-assert-check-in-translate-routin.patch +# For bz#2100106 - Fix virtio-iommu/vfio bypass +Patch90: kvm-virtio-iommu-Fix-the-partial-copy-of-probe-request.patch +# For bz#2100106 - Fix virtio-iommu/vfio bypass +Patch91: kvm-virtio-iommu-Fix-migration-regression.patch +# For bz#2098077 - virtio-blk: Can't boot fresh installation from used virtio-blk dasd disk under certain conditions +Patch92: kvm-pc-bios-s390-ccw-virtio-Introduce-a-macro-for-the-DA.patch +# For bz#2098077 - virtio-blk: Can't boot fresh installation from used virtio-blk dasd disk under certain conditions +Patch93: kvm-pc-bios-s390-ccw-bootmap-Improve-the-guessing-logic-.patch +# For bz#2098077 - virtio-blk: Can't boot fresh installation from used virtio-blk dasd disk under certain conditions +Patch94: kvm-pc-bios-s390-ccw-virtio-blkdev-Simplify-fix-virtio_i.patch +# For bz#2098077 - virtio-blk: Can't boot fresh installation from used virtio-blk dasd disk under certain conditions +Patch95: kvm-pc-bios-s390-ccw-virtio-blkdev-Remove-virtio_assume_.patch +# For bz#2098077 - virtio-blk: Can't boot fresh installation from used virtio-blk dasd disk under certain conditions +Patch96: kvm-pc-bios-s390-ccw-virtio-Set-missing-status-bits-whil.patch +# For bz#2098077 - virtio-blk: Can't boot fresh installation from used virtio-blk dasd disk under certain conditions +Patch97: kvm-pc-bios-s390-ccw-virtio-Read-device-config-after-fea.patch +# For bz#2098077 - virtio-blk: Can't boot fresh installation from used virtio-blk dasd disk under certain conditions +Patch98: kvm-pc-bios-s390-ccw-virtio-Beautify-the-code-for-readin.patch +# For bz#2098077 - virtio-blk: Can't boot fresh installation from used virtio-blk dasd disk under certain conditions +Patch99: kvm-pc-bios-s390-ccw-Split-virtio-scsi-code-from-virtio_.patch +# For bz#2098077 - virtio-blk: Can't boot fresh installation from used virtio-blk dasd disk under certain conditions +Patch100: kvm-pc-bios-s390-ccw-virtio-blkdev-Request-the-right-fea.patch +# For bz#2098077 - virtio-blk: Can't boot fresh installation from used virtio-blk dasd disk under certain conditions +Patch101: kvm-pc-bios-s390-ccw-netboot.mak-Ignore-Clang-s-warnings.patch +# For bz#1951522 - CVE-2021-3507 qemu-kvm: QEMU: fdc: heap buffer overflow in DMA read data transfers [rhel-9.0] +Patch102: kvm-hw-block-fdc-Prevent-end-of-track-overrun-CVE-2021-3.patch +# For bz#1951522 - CVE-2021-3507 qemu-kvm: QEMU: fdc: heap buffer overflow in DMA read data transfers [rhel-9.0] +Patch103: kvm-tests-qtest-fdc-test-Add-a-regression-test-for-CVE-2.patch +# For bz#1939363 - vDPA control virtqueue support in Qemu +Patch104: kvm-vhost-Track-descriptor-chain-in-private-at-SVQ.patch +# For bz#1939363 - vDPA control virtqueue support in Qemu +Patch105: kvm-vhost-Fix-device-s-used-descriptor-dequeue.patch +# For bz#1939363 - vDPA control virtqueue support in Qemu +Patch106: kvm-hw-virtio-Replace-g_memdup-by-g_memdup2.patch +# For bz#1939363 - vDPA control virtqueue support in Qemu +Patch107: kvm-vhost-Fix-element-in-vhost_svq_add-failure.patch +# For bz#1939363 - vDPA control virtqueue support in Qemu +Patch108: kvm-meson-create-have_vhost_-variables.patch +# For bz#1939363 - vDPA control virtqueue support in Qemu +Patch109: kvm-meson-use-have_vhost_-variables-to-pick-sources.patch +# For bz#1939363 - vDPA control virtqueue support in Qemu +Patch110: kvm-vhost-move-descriptor-translation-to-vhost_svq_vring.patch +# For bz#1939363 - vDPA control virtqueue support in Qemu +Patch111: kvm-virtio-net-Expose-MAC_TABLE_ENTRIES.patch +# For bz#1939363 - vDPA control virtqueue support in Qemu +Patch112: kvm-virtio-net-Expose-ctrl-virtqueue-logic.patch +# For bz#1939363 - vDPA control virtqueue support in Qemu +Patch113: kvm-vdpa-Avoid-compiler-to-squash-reads-to-used-idx.patch +# For bz#1939363 - vDPA control virtqueue support in Qemu +Patch114: kvm-vhost-Reorder-vhost_svq_kick.patch +# For bz#1939363 - vDPA control virtqueue support in Qemu +Patch115: kvm-vhost-Move-vhost_svq_kick-call-to-vhost_svq_add.patch +# For bz#1939363 - vDPA control virtqueue support in Qemu +Patch116: kvm-vhost-Check-for-queue-full-at-vhost_svq_add.patch +# For bz#1939363 - vDPA control virtqueue support in Qemu +Patch117: kvm-vhost-Decouple-vhost_svq_add-from-VirtQueueElement.patch +# For bz#1939363 - vDPA control virtqueue support in Qemu +Patch118: kvm-vhost-Add-SVQDescState.patch +# For bz#1939363 - vDPA control virtqueue support in Qemu +Patch119: kvm-vhost-Track-number-of-descs-in-SVQDescState.patch +# For bz#1939363 - vDPA control virtqueue support in Qemu +Patch120: kvm-vhost-add-vhost_svq_push_elem.patch +# For bz#1939363 - vDPA control virtqueue support in Qemu +Patch121: kvm-vhost-Expose-vhost_svq_add.patch +# For bz#1939363 - vDPA control virtqueue support in Qemu +Patch122: kvm-vhost-add-vhost_svq_poll.patch +# For bz#1939363 - vDPA control virtqueue support in Qemu +Patch123: kvm-vhost-Add-svq-avail_handler-callback.patch +# For bz#1939363 - vDPA control virtqueue support in Qemu +Patch124: kvm-vdpa-Export-vhost_vdpa_dma_map-and-unmap-calls.patch +# For bz#1939363 - vDPA control virtqueue support in Qemu +Patch125: kvm-vhost-net-vdpa-add-stubs-for-when-no-virtio-net-devi.patch +# For bz#1939363 - vDPA control virtqueue support in Qemu +Patch126: kvm-vdpa-manual-forward-CVQ-buffers.patch +# For bz#1939363 - vDPA control virtqueue support in Qemu +Patch127: kvm-vdpa-Buffer-CVQ-support-on-shadow-virtqueue.patch +# For bz#1939363 - vDPA control virtqueue support in Qemu +Patch128: kvm-vdpa-Extract-get-features-part-from-vhost_vdpa_get_m.patch +# For bz#1939363 - vDPA control virtqueue support in Qemu +Patch129: kvm-vdpa-Add-device-migration-blocker.patch +# For bz#1939363 - vDPA control virtqueue support in Qemu +Patch130: kvm-vdpa-Add-x-svq-to-NetdevVhostVDPAOptions.patch +# For bz#2111994 - RHEL9: skey test in kvm_unit_test got failed +Patch131: kvm-redhat-Update-linux-headers-linux-kvm.h-to-v5.18-rc6.patch +# For bz#2111994 - RHEL9: skey test in kvm_unit_test got failed +Patch132: kvm-target-s390x-kvm-Honor-storage-keys-during-emulation.patch +# For bz#2095608 - Please correct the error message when try to start qemu with "-M kernel-irqchip=split" +Patch133: kvm-kvm-don-t-use-perror-without-useful-errno.patch +# For bz#2099934 - Guest reboot on destination host after postcopy migration completed +Patch134: kvm-multifd-Copy-pages-before-compressing-them-with-zlib.patch +# For bz#2099934 - Guest reboot on destination host after postcopy migration completed +Patch135: kvm-Revert-migration-Simplify-unqueue_page.patch +# For bz#2107466 - zerocopy capability can be enabled when set migrate capabilities with multifd and compress/xbzrle together +Patch136: kvm-QIOChannelSocket-Fix-zero-copy-flush-returning-code-.patch +# For bz#2107466 - zerocopy capability can be enabled when set migrate capabilities with multifd and compress/xbzrle together +Patch137: kvm-Add-dirty-sync-missed-zero-copy-migration-stat.patch +# For bz#2107466 - zerocopy capability can be enabled when set migrate capabilities with multifd and compress/xbzrle together +Patch138: kvm-migration-multifd-Report-to-user-when-zerocopy-not-w.patch +# For bz#2107466 - zerocopy capability can be enabled when set migrate capabilities with multifd and compress/xbzrle together +Patch139: kvm-migration-Avoid-false-positive-on-non-supported-scen.patch +# For bz#2107466 - zerocopy capability can be enabled when set migrate capabilities with multifd and compress/xbzrle together +Patch140: kvm-migration-add-remaining-params-has_-true-in-migratio.patch +# For bz#2107466 - zerocopy capability can be enabled when set migrate capabilities with multifd and compress/xbzrle together +Patch141: kvm-QIOChannelSocket-Add-support-for-MSG_ZEROCOPY-IPV6.patch +# For bz#2112303 - virtio-blk: Can't boot fresh installation from used 512 cluster_size image under certain conditions +Patch142: kvm-pc-bios-s390-ccw-Fix-booting-with-logical-block-size.patch +# For bz#2116876 - Fixes for vDPA control virtqueue support in Qemu +Patch143: kvm-vdpa-Fix-bad-index-calculus-at-vhost_vdpa_get_vring_.patch +# For bz#2116876 - Fixes for vDPA control virtqueue support in Qemu +Patch144: kvm-vdpa-Fix-index-calculus-at-vhost_vdpa_svqs_start.patch +# For bz#2116876 - Fixes for vDPA control virtqueue support in Qemu +Patch145: kvm-vdpa-Fix-memory-listener-deletions-of-iova-tree.patch +# For bz#2116876 - Fixes for vDPA control virtqueue support in Qemu +Patch146: kvm-vdpa-Fix-file-descriptor-leak-on-get-features-error.patch +# For bz#2120275 - Wrong max_sectors_kb and Maximum transfer length on the pass-through device [rhel-9.1] +Patch147: kvm-scsi-generic-Fix-emulated-block-limits-VPD-page.patch +# For bz#2114060 - vDPA state restore support through control virtqueue in Qemu +Patch148: kvm-vhost-Get-vring-base-from-vq-not-svq.patch +# For bz#2114060 - vDPA state restore support through control virtqueue in Qemu +Patch149: kvm-vdpa-Skip-the-maps-not-in-the-iova-tree.patch +# For bz#2114060 - vDPA state restore support through control virtqueue in Qemu +Patch150: kvm-vdpa-do-not-save-failed-dma-maps-in-SVQ-iova-tree.patch +# For bz#2114060 - vDPA state restore support through control virtqueue in Qemu +Patch151: kvm-util-Return-void-on-iova_tree_remove.patch +# For bz#2114060 - vDPA state restore support through control virtqueue in Qemu +Patch152: kvm-util-accept-iova_tree_remove_parameter-by-value.patch +# For bz#2114060 - vDPA state restore support through control virtqueue in Qemu +Patch153: kvm-vdpa-Remove-SVQ-vring-from-iova_tree-at-shutdown.patch +# For bz#2114060 - vDPA state restore support through control virtqueue in Qemu +Patch154: kvm-vdpa-Make-SVQ-vring-unmapping-return-void.patch +# For bz#2114060 - vDPA state restore support through control virtqueue in Qemu +Patch155: kvm-vhost-Always-store-new-kick-fd-on-vhost_svq_set_svq_.patch +# For bz#2114060 - vDPA state restore support through control virtqueue in Qemu +Patch156: kvm-vdpa-Use-ring-hwaddr-at-vhost_vdpa_svq_unmap_ring.patch +# For bz#2114060 - vDPA state restore support through control virtqueue in Qemu +Patch157: kvm-vhost-stop-transfer-elem-ownership-in-vhost_handle_g.patch +# For bz#2114060 - vDPA state restore support through control virtqueue in Qemu +Patch158: kvm-vhost-use-SVQ-element-ndescs-instead-of-opaque-data-.patch +# For bz#2114060 - vDPA state restore support through control virtqueue in Qemu +Patch159: kvm-vhost-Delete-useless-read-memory-barrier.patch +# For bz#2114060 - vDPA state restore support through control virtqueue in Qemu +Patch160: kvm-vhost-Do-not-depend-on-NULL-VirtQueueElement-on-vhos.patch +# For bz#2114060 - vDPA state restore support through control virtqueue in Qemu +Patch161: kvm-vhost_net-Add-NetClientInfo-start-callback.patch +# For bz#2114060 - vDPA state restore support through control virtqueue in Qemu +Patch162: kvm-vhost_net-Add-NetClientInfo-stop-callback.patch +# For bz#2114060 - vDPA state restore support through control virtqueue in Qemu +Patch163: kvm-vdpa-add-net_vhost_vdpa_cvq_info-NetClientInfo.patch +# For bz#2114060 - vDPA state restore support through control virtqueue in Qemu +Patch164: kvm-vdpa-Move-command-buffers-map-to-start-of-net-device.patch +# For bz#2114060 - vDPA state restore support through control virtqueue in Qemu +Patch165: kvm-vdpa-extract-vhost_vdpa_net_cvq_add-from-vhost_vdpa_.patch +# For bz#2114060 - vDPA state restore support through control virtqueue in Qemu +Patch166: kvm-vhost_net-add-NetClientState-load-callback.patch +# For bz#2114060 - vDPA state restore support through control virtqueue in Qemu +Patch167: kvm-vdpa-Add-virtio-net-mac-address-via-CVQ-at-start.patch +# For bz#2114060 - vDPA state restore support through control virtqueue in Qemu +Patch168: kvm-vdpa-Delete-CVQ-migration-blocker.patch +# For bz#2099541 - qemu coredump with error Assertion `qemu_mutex_iothread_locked()' failed when repeatly hotplug/unplug disks in pause status +Patch169: kvm-virtio-scsi-fix-race-in-virtio_scsi_dataplane_start.patch +# For bz#2117546 - [RHEL9.1] Guests in VMX root operation fail to reboot with QEMU's 'system_reset' command +Patch170: kvm-i386-reset-KVM-nested-state-upon-CPU-reset.patch +# For bz#2117546 - [RHEL9.1] Guests in VMX root operation fail to reboot with QEMU's 'system_reset' command +Patch171: kvm-i386-do-kvm_put_msr_feature_control-first-thing-when.patch # Source-git patches @@ -374,7 +524,6 @@ BuildRequires: python3-sphinx_rtd_theme BuildRequires: libseccomp-devel >= %{libseccomp_version} # For network block driver BuildRequires: libcurl-devel -BuildRequires: libssh-devel %if %{have_block_rbd} BuildRequires: librbd-devel %endif @@ -565,16 +714,6 @@ using the rbd protocol. %endif -%package block-ssh -Summary: QEMU SSH block driver -Requires: %{name}-common%{?_isa} = %{epoch}:%{version}-%{release} -%description block-ssh -This package provides the additional SSH block driver for QEMU. - -Install this package if you want to access remote disks using -the Secure Shell (SSH) protocol. - - %package audio-pa Summary: QEMU PulseAudio audio driver Requires: %{name}-common%{?_isa} = %{epoch}:%{version}-%{release} @@ -672,10 +811,6 @@ This package provides usbredir support. %global qemu_kvm_build qemu_kvm_build mkdir -p %{qemu_kvm_build} -cp -f %{SOURCE37} tests/data/acpi/pc/SSDT.dimmpxm -cp -f %{SOURCE38} tests/data/acpi/q35/FACP.slic -cp -f %{SOURCE39} tests/data/acpi/q35/SSDT.dimmpxm -cp -f %{SOURCE40} tests/data/acpi/virt/SSDT.memhp %build %define disable_everything \\\ @@ -702,6 +837,7 @@ cp -f %{SOURCE40} tests/data/acpi/virt/SSDT.memhp --disable-crypto-afalg \\\ --disable-curl \\\ --disable-curses \\\ + --disable-dbus-display \\\ --disable-debug-info \\\ --disable-debug-mutex \\\ --disable-debug-tcg \\\ @@ -732,7 +868,6 @@ cp -f %{SOURCE40} tests/data/acpi/virt/SSDT.memhp --disable-libssh \\\ --disable-libudev \\\ --disable-libusb \\\ - --disable-libxml2 \\\ --disable-linux-aio \\\ --disable-linux-io-uring \\\ --disable-linux-user \\\ @@ -758,6 +893,7 @@ cp -f %{SOURCE40} tests/data/acpi/virt/SSDT.memhp --disable-pvrdma \\\ --disable-qcow1 \\\ --disable-qed \\\ + --disable-qga-vss \\\ --disable-qom-cast-debug \\\ --disable-rbd \\\ --disable-rdma \\\ @@ -807,7 +943,6 @@ cp -f %{SOURCE40} tests/data/acpi/virt/SSDT.memhp --disable-whpx \\\ --disable-xen \\\ --disable-xen-pci-passthrough \\\ - --disable-xfsctl \\\ --disable-xkbcommon \\\ --disable-zstd \\\ --with-git-submodules=ignore \\\ @@ -831,7 +966,7 @@ run_configure() { --with-pkgversion="%{name}-%{version}-%{release}" \ --with-suffix="%{name}" \ --firmwarepath=%{firmwaredirs} \ - --meson="%{__meson}" \ + --meson="internal" \ --enable-trace-backend=dtrace \ --with-coroutine=ucontext \ --with-git=git \ @@ -859,9 +994,6 @@ run_configure \ --block-drv-ro-whitelist=%{block_drivers_ro_list} \ %endif --enable-attr \ -%ifarch %{ix86} x86_64 - --enable-avx2 \ -%endif --enable-cap-ng \ --enable-capstone=internal \ --enable-coroutine-pool \ @@ -878,7 +1010,6 @@ run_configure \ %if %{have_pmem} --enable-libpmem \ %endif - --enable-libssh \ --enable-libusb \ --enable-libudev \ --enable-linux-aio \ @@ -931,7 +1062,6 @@ run_configure \ --enable-safe-stack \ %endif - %if %{tools_only} %make_build qemu-img %make_build qemu-io @@ -1036,7 +1166,7 @@ cp -R %{qemu_kvm_build}/tests/avocado/* %{buildroot}%{testsdir}/tests/avocado/ # Install qemu.py and qmp/ scripts required to run avocado_qemu tests cp -R %{qemu_kvm_build}/python/qemu %{buildroot}%{testsdir}/python cp -R %{qemu_kvm_build}/scripts/qmp/* %{buildroot}%{testsdir}/scripts/qmp -install -p -m 0755 tests/Makefile.include %{buildroot}%{testsdir}/tests/ +install -p -m 0644 tests/Makefile.include %{buildroot}%{testsdir}/tests/ # Install qemu-iotests cp -R tests/qemu-iotests/* %{buildroot}%{testsdir}/tests/qemu-iotests/ @@ -1170,10 +1300,9 @@ rm -rf %{buildroot}%{_datadir}/%{name}/vgabios*bin rm -rf %{buildroot}%{_datadir}/%{name}/bios*.bin rm -rf %{buildroot}%{_datadir}/%{name}/sgabios.bin -# Remove virtiofsd (we use separate package for virtiofsd) -rm -rf %{buildroot}%{_mandir}/man1/virtiofsd.1* -rm -rf %{buildroot}%{_libexecdir}/virtiofsd -rm -rf %{buildroot}%{_datadir}/qemu/vhost-user/50-qemu-virtiofsd.json +# Remove vof roms +rm -rf %{buildroot}%{_datadir}/%{name}/vof-nvram.bin +rm -rf %{buildroot}%{_datadir}/%{name}/vof.bin %if %{have_modules_load} install -D -p -m 644 %{_sourcedir}/modules-load.conf %{buildroot}%{_sysconfdir}/modules-load.d/kvm.conf @@ -1201,6 +1330,10 @@ rm -rf %{buildroot}%{qemudocdir}/specs # endif !tools_only %endif +# Remove virtiofsd (we use separate package for virtiofsd) +rm -rf %{buildroot}%{_mandir}/man1/virtiofsd.1* +rm -rf %{buildroot}%{_libexecdir}/virtiofsd +rm -rf %{buildroot}%{_datadir}/qemu/vhost-user/50-qemu-virtiofsd.json %check %if !%{tools_only} @@ -1342,17 +1475,21 @@ useradd -r -u 107 -g qemu -G kvm -d / -s /sbin/nologin \ %files device-display-virtio-gpu %{_libdir}/%{name}/hw-display-virtio-gpu.so + %files device-display-virtio-gpu-gl %{_libdir}/%{name}/hw-display-virtio-gpu-gl.so + %ifarch s390x %files device-display-virtio-gpu-ccw %{_libdir}/%{name}/hw-s390x-virtio-gpu-ccw.so %else %files device-display-virtio-gpu-pci %{_libdir}/%{name}/hw-display-virtio-gpu-pci.so + %files device-display-virtio-gpu-pci-gl %{_libdir}/%{name}/hw-display-virtio-gpu-pci-gl.so %endif + %ifarch x86_64 %{power64} %files device-display-virtio-vga %{_libdir}/%{name}/hw-display-virtio-vga.so @@ -1370,8 +1507,6 @@ useradd -r -u 107 -g qemu -G kvm -d / -s /sbin/nologin \ %files block-rbd %{_libdir}/%{name}/block-rbd.so %endif -%files block-ssh -%{_libdir}/%{name}/block-ssh.so %files audio-pa %{_libdir}/%{name}/audio-pa.so @@ -1386,7 +1521,7 @@ useradd -r -u 107 -g qemu -G kvm -d / -s /sbin/nologin \ %{_libdir}/%{name}/hw-usb-host.so %if %{have_usbredir} -%files device-usb-redirect +%files device-usb-redirect %{_libdir}/%{name}/hw-usb-redirect.so %endif @@ -1394,70 +1529,287 @@ useradd -r -u 107 -g qemu -G kvm -d / -s /sbin/nologin \ %endif %changelog -* Tue Aug 30 2022 Miroslav Rezanina - 6.2.0-11.el9_0.5 -- kvm-linux-aio-fix-unbalanced-plugged-counter-in-laio_io_.patch [bz#2109569] -- kvm-linux-aio-explain-why-max-batch-is-checked-in-laio_i.patch [bz#2109569] -- Resolves: bz#2109569 - (Stalled IO Operations in VM [rhel-9.0.0.z]) - -* Fri Aug 05 2022 Miroslav Rezanina - 6.2.0-11.el9_0.4 -- kvm-virtio-net-setup-vhost_dev-and-notifiers-for-cvq-onl.patch [bz#2095795] -- kvm-virtio-net-align-ctrl_vq-index-for-non-mq-guest-for-.patch [bz#2095795] -- kvm-vhost-vdpa-fix-improper-cleanup-in-net_init_vhost_vd.patch [bz#2095795] -- kvm-vhost-net-fix-improper-cleanup-in-vhost_net_start.patch [bz#2095795] -- kvm-vhost-vdpa-backend-feature-should-set-only-once.patch [bz#2095795] -- kvm-vhost-vdpa-change-name-and-polarity-for-vhost_vdpa_o.patch [bz#2095795] -- kvm-virtio-net-don-t-handle-mq-request-in-userspace-hand.patch [bz#2095795] -- Resolves: bz#2095795 - (PXE boot crash qemu when using multiqueue vDPA [rhel-9.0.0.z]) - -* Mon May 09 2022 Miroslav Rezanina - 6.2.0-11.el9_0.3 -- kvm-RHEL-disable-seqpacket-for-vhost-vsock-device-in-rhe.patch [bz#2071102] -- kvm-virtio-net-fix-map-leaking-on-error-during-receive.patch [bz#2075635] -- kvm-vhost-vsock-detach-the-virqueue-element-in-case-of-e.patch [bz#2075640] -- Resolves: bz#2071102 - (RHEL 9.0 guest with vsock device migration failed from RHEL 9.0 > RHEL 8.6 [rhel-9.0.0.z]) -- Resolves: bz#2075635 - (CVE-2022-26353 qemu-kvm: QEMU: virtio-net: map leaking on error during receive [rhel-9] [rhel-9.0.0.z]) -- Resolves: bz#2075640 - (CVE-2022-26354 qemu-kvm: QEMU: vhost-vsock: missing virtqueue detach on error can lead to memory leak [rhel-9] [rhel-9.0.0.z]) - -* Tue Mar 22 2022 - 6.2.0-11.el9_0.2 -- kvm-pci-expose-TYPE_XIO3130_DOWNSTREAM-name.patch [bz#2053584] -- kvm-acpi-pcihp-pcie-set-power-on-cap-on-parent-slot.patch [bz#2053584] -- kvm-vmxcap-Add-5-level-EPT-bit.patch [bz#2038051] -- kvm-i386-Add-Icelake-Server-v6-CPU-model-with-5-level-EP.patch [bz#2038051] -- kvm-acpi-fix-QEMU-crash-when-started-with-SLIC-table.patch [bz#2043531] -- kvm-tests-acpi-whitelist-expected-blobs-before-changing-.patch [bz#2043531] -- kvm-tests-acpi-add-SLIC-table-test.patch [bz#2043531] -- kvm-tests-acpi-SLIC-update-expected-blobs.patch [bz#2043531] -- kvm-tests-acpi-manually-pad-OEM_ID-OEM_TABLE_ID-for-test.patch [bz#2043531] -- kvm-tests-acpi-whitelist-nvdimm-s-SSDT-and-FACP.slic-exp.patch [bz#2043531] -- kvm-acpi-fix-OEM-ID-OEM-Table-ID-padding.patch [bz#2043531] -- kvm-tests-acpi-update-expected-blobs.patch [bz#2043531] -- kvm-tests-acpi-test-short-OEM_ID-OEM_TABLE_ID-values-in-.patch [bz#2043531] -- kvm-rhel-workaround-for-lack-of-binary-patches-in-SRPM.patch [bz#2043531] -- Resolves: bz#2053584 - (watchdog: BUG: soft lockup - CPU#3 stuck for 22s! [cat:2843]) -- Resolves: bz#2038051 - (Win11 (q35+edk2) guest broke after install wsl2 through 'wsl --install -d Ubuntu-20.04') -- Resolves: bz#2043531 - (Guest can not start with SLIC acpi table) - -* Tue Mar 15 2022 Miroslav Rezanina - 6.2.0-11.el9_0.1 -- kvm-RHEL-mark-old-machine-types-as-deprecated.patch [bz#2052050] -- kvm-hw-virtio-vdpa-Fix-leak-of-host-notifier-memory-regi.patch [bz#2059786] -- kvm-spec-Fix-obsolete-for-spice-subpackages.patch [bz#2059175 bz#2059146] -- kvm-spec-Obsolete-old-usb-redir-subpackage.patch [bz#2059175 bz#2059146] -- kvm-spec-Obsolete-ssh-driver.patch [bz#2059175 bz#2059146] -- Resolves: bz#2052050 - (Mark all RHEL-8 and earlier machine types as deprecated) -- Resolves: bz#2059786 - ([virtual network][rhel9][vDPA] qemu crash after hot unplug vdpa device) -- Resolves: bz#2059175 - (Broken upgrade path due to qemu-kvm-hw-usbredir rename) -- Resolves: bz#2059146 - (Missing qemu-kvm-block-ssh obsolete breaks upgrade path) +* Tue Sep 13 2022 Miroslav Rezanina - 7.0.0-13 +- kvm-i386-reset-KVM-nested-state-upon-CPU-reset.patch [bz#2117546] +- kvm-i386-do-kvm_put_msr_feature_control-first-thing-when.patch [bz#2117546] +- Resolves: bz#2117546 + ([RHEL9.1] Guests in VMX root operation fail to reboot with QEMU's 'system_reset' command) + +* Fri Aug 26 2022 Miroslav Rezanina - 7.0.0-12 +- kvm-scsi-generic-Fix-emulated-block-limits-VPD-page.patch [bz#2120275] +- kvm-vhost-Get-vring-base-from-vq-not-svq.patch [bz#2114060] +- kvm-vdpa-Skip-the-maps-not-in-the-iova-tree.patch [bz#2114060] +- kvm-vdpa-do-not-save-failed-dma-maps-in-SVQ-iova-tree.patch [bz#2114060] +- kvm-util-Return-void-on-iova_tree_remove.patch [bz#2114060] +- kvm-util-accept-iova_tree_remove_parameter-by-value.patch [bz#2114060] +- kvm-vdpa-Remove-SVQ-vring-from-iova_tree-at-shutdown.patch [bz#2114060] +- kvm-vdpa-Make-SVQ-vring-unmapping-return-void.patch [bz#2114060] +- kvm-vhost-Always-store-new-kick-fd-on-vhost_svq_set_svq_.patch [bz#2114060] +- kvm-vdpa-Use-ring-hwaddr-at-vhost_vdpa_svq_unmap_ring.patch [bz#2114060] +- kvm-vhost-stop-transfer-elem-ownership-in-vhost_handle_g.patch [bz#2114060] +- kvm-vhost-use-SVQ-element-ndescs-instead-of-opaque-data-.patch [bz#2114060] +- kvm-vhost-Delete-useless-read-memory-barrier.patch [bz#2114060] +- kvm-vhost-Do-not-depend-on-NULL-VirtQueueElement-on-vhos.patch [bz#2114060] +- kvm-vhost_net-Add-NetClientInfo-start-callback.patch [bz#2114060] +- kvm-vhost_net-Add-NetClientInfo-stop-callback.patch [bz#2114060] +- kvm-vdpa-add-net_vhost_vdpa_cvq_info-NetClientInfo.patch [bz#2114060] +- kvm-vdpa-Move-command-buffers-map-to-start-of-net-device.patch [bz#2114060] +- kvm-vdpa-extract-vhost_vdpa_net_cvq_add-from-vhost_vdpa_.patch [bz#2114060] +- kvm-vhost_net-add-NetClientState-load-callback.patch [bz#2114060] +- kvm-vdpa-Add-virtio-net-mac-address-via-CVQ-at-start.patch [bz#2114060] +- kvm-vdpa-Delete-CVQ-migration-blocker.patch [bz#2114060] +- kvm-virtio-scsi-fix-race-in-virtio_scsi_dataplane_start.patch [bz#2099541] +- Resolves: bz#2120275 + (Wrong max_sectors_kb and Maximum transfer length on the pass-through device [rhel-9.1]) +- Resolves: bz#2114060 + (vDPA state restore support through control virtqueue in Qemu) +- Resolves: bz#2099541 + (qemu coredump with error Assertion `qemu_mutex_iothread_locked()' failed when repeatly hotplug/unplug disks in pause status) + +* Mon Aug 15 2022 Miroslav Rezanina - 7.0.0-11 +- kvm-QIOChannelSocket-Fix-zero-copy-flush-returning-code-.patch [bz#2107466] +- kvm-Add-dirty-sync-missed-zero-copy-migration-stat.patch [bz#2107466] +- kvm-migration-multifd-Report-to-user-when-zerocopy-not-w.patch [bz#2107466] +- kvm-migration-Avoid-false-positive-on-non-supported-scen.patch [bz#2107466] +- kvm-migration-add-remaining-params-has_-true-in-migratio.patch [bz#2107466] +- kvm-QIOChannelSocket-Add-support-for-MSG_ZEROCOPY-IPV6.patch [bz#2107466] +- kvm-pc-bios-s390-ccw-Fix-booting-with-logical-block-size.patch [bz#2112303] +- kvm-vdpa-Fix-bad-index-calculus-at-vhost_vdpa_get_vring_.patch [bz#2116876] +- kvm-vdpa-Fix-index-calculus-at-vhost_vdpa_svqs_start.patch [bz#2116876] +- kvm-vdpa-Fix-memory-listener-deletions-of-iova-tree.patch [bz#2116876] +- kvm-vdpa-Fix-file-descriptor-leak-on-get-features-error.patch [bz#2116876] +- Resolves: bz#2107466 + (zerocopy capability can be enabled when set migrate capabilities with multifd and compress/xbzrle together) +- Resolves: bz#2112303 + (virtio-blk: Can't boot fresh installation from used 512 cluster_size image under certain conditions) +- Resolves: bz#2116876 + (Fixes for vDPA control virtqueue support in Qemu) + +* Mon Aug 08 2022 Miroslav Rezanina - 7.0.0-10 +- kvm-vhost-Track-descriptor-chain-in-private-at-SVQ.patch [bz#1939363] +- kvm-vhost-Fix-device-s-used-descriptor-dequeue.patch [bz#1939363] +- kvm-hw-virtio-Replace-g_memdup-by-g_memdup2.patch [bz#1939363] +- kvm-vhost-Fix-element-in-vhost_svq_add-failure.patch [bz#1939363] +- kvm-meson-create-have_vhost_-variables.patch [bz#1939363] +- kvm-meson-use-have_vhost_-variables-to-pick-sources.patch [bz#1939363] +- kvm-vhost-move-descriptor-translation-to-vhost_svq_vring.patch [bz#1939363] +- kvm-virtio-net-Expose-MAC_TABLE_ENTRIES.patch [bz#1939363] +- kvm-virtio-net-Expose-ctrl-virtqueue-logic.patch [bz#1939363] +- kvm-vdpa-Avoid-compiler-to-squash-reads-to-used-idx.patch [bz#1939363] +- kvm-vhost-Reorder-vhost_svq_kick.patch [bz#1939363] +- kvm-vhost-Move-vhost_svq_kick-call-to-vhost_svq_add.patch [bz#1939363] +- kvm-vhost-Check-for-queue-full-at-vhost_svq_add.patch [bz#1939363] +- kvm-vhost-Decouple-vhost_svq_add-from-VirtQueueElement.patch [bz#1939363] +- kvm-vhost-Add-SVQDescState.patch [bz#1939363] +- kvm-vhost-Track-number-of-descs-in-SVQDescState.patch [bz#1939363] +- kvm-vhost-add-vhost_svq_push_elem.patch [bz#1939363] +- kvm-vhost-Expose-vhost_svq_add.patch [bz#1939363] +- kvm-vhost-add-vhost_svq_poll.patch [bz#1939363] +- kvm-vhost-Add-svq-avail_handler-callback.patch [bz#1939363] +- kvm-vdpa-Export-vhost_vdpa_dma_map-and-unmap-calls.patch [bz#1939363] +- kvm-vhost-net-vdpa-add-stubs-for-when-no-virtio-net-devi.patch [bz#1939363] +- kvm-vdpa-manual-forward-CVQ-buffers.patch [bz#1939363] +- kvm-vdpa-Buffer-CVQ-support-on-shadow-virtqueue.patch [bz#1939363] +- kvm-vdpa-Extract-get-features-part-from-vhost_vdpa_get_m.patch [bz#1939363] +- kvm-vdpa-Add-device-migration-blocker.patch [bz#1939363] +- kvm-vdpa-Add-x-svq-to-NetdevVhostVDPAOptions.patch [bz#1939363] +- kvm-redhat-Update-linux-headers-linux-kvm.h-to-v5.18-rc6.patch [bz#2111994] +- kvm-target-s390x-kvm-Honor-storage-keys-during-emulation.patch [bz#2111994] +- kvm-kvm-don-t-use-perror-without-useful-errno.patch [bz#2095608] +- kvm-multifd-Copy-pages-before-compressing-them-with-zlib.patch [bz#2099934] +- kvm-Revert-migration-Simplify-unqueue_page.patch [bz#2099934] +- Resolves: bz#1939363 + (vDPA control virtqueue support in Qemu) +- Resolves: bz#2111994 + (RHEL9: skey test in kvm_unit_test got failed) +- Resolves: bz#2095608 + (Please correct the error message when try to start qemu with "-M kernel-irqchip=split") +- Resolves: bz#2099934 + (Guest reboot on destination host after postcopy migration completed) + +* Mon Jul 18 2022 Miroslav Rezanina - 7.0.0-9 +- kvm-virtio-iommu-Add-bypass-mode-support-to-assigned-dev.patch [bz#2100106] +- kvm-virtio-iommu-Use-recursive-lock-to-avoid-deadlock.patch [bz#2100106] +- kvm-virtio-iommu-Add-an-assert-check-in-translate-routin.patch [bz#2100106] +- kvm-virtio-iommu-Fix-the-partial-copy-of-probe-request.patch [bz#2100106] +- kvm-virtio-iommu-Fix-migration-regression.patch [bz#2100106] +- kvm-pc-bios-s390-ccw-virtio-Introduce-a-macro-for-the-DA.patch [bz#2098077] +- kvm-pc-bios-s390-ccw-bootmap-Improve-the-guessing-logic-.patch [bz#2098077] +- kvm-pc-bios-s390-ccw-virtio-blkdev-Simplify-fix-virtio_i.patch [bz#2098077] +- kvm-pc-bios-s390-ccw-virtio-blkdev-Remove-virtio_assume_.patch [bz#2098077] +- kvm-pc-bios-s390-ccw-virtio-Set-missing-status-bits-whil.patch [bz#2098077] +- kvm-pc-bios-s390-ccw-virtio-Read-device-config-after-fea.patch [bz#2098077] +- kvm-pc-bios-s390-ccw-virtio-Beautify-the-code-for-readin.patch [bz#2098077] +- kvm-pc-bios-s390-ccw-Split-virtio-scsi-code-from-virtio_.patch [bz#2098077] +- kvm-pc-bios-s390-ccw-virtio-blkdev-Request-the-right-fea.patch [bz#2098077] +- kvm-pc-bios-s390-ccw-netboot.mak-Ignore-Clang-s-warnings.patch [bz#2098077] +- kvm-hw-block-fdc-Prevent-end-of-track-overrun-CVE-2021-3.patch [bz#1951522] +- kvm-tests-qtest-fdc-test-Add-a-regression-test-for-CVE-2.patch [bz#1951522] +- Resolves: bz#2100106 + (Fix virtio-iommu/vfio bypass) +- Resolves: bz#2098077 + (virtio-blk: Can't boot fresh installation from used virtio-blk dasd disk under certain conditions) +- Resolves: bz#1951522 + (CVE-2021-3507 qemu-kvm: QEMU: fdc: heap buffer overflow in DMA read data transfers [rhel-9.0]) + +* Tue Jul 05 2022 Camilla Conte - 7.0.0-8 +- kvm-tests-avocado-update-aarch64_virt-test-to-exercise-c.patch [bz#2060839] +- kvm-RHEL-only-tests-avocado-Switch-aarch64-tests-from-a5.patch [bz#2060839] +- kvm-RHEL-only-AArch64-Drop-unsupported-CPU-types.patch [bz#2060839] +- kvm-target-i386-deprecate-CPUs-older-than-x86_64-v2-ABI.patch [bz#2060839] +- kvm-target-s390x-deprecate-CPUs-older-than-z14.patch [bz#2060839] +- kvm-target-arm-deprecate-named-CPU-models.patch [bz#2060839] +- kvm-meson.build-Fix-docker-test-build-alpine-when-includ.patch [bz#1968509] +- kvm-QIOChannel-Add-flags-on-io_writev-and-introduce-io_f.patch [bz#1968509] +- kvm-QIOChannelSocket-Implement-io_writev-zero-copy-flag-.patch [bz#1968509] +- kvm-migration-Add-zero-copy-send-parameter-for-QMP-HMP-f.patch [bz#1968509] +- kvm-migration-Add-migrate_use_tls-helper.patch [bz#1968509] +- kvm-multifd-multifd_send_sync_main-now-returns-negative-.patch [bz#1968509] +- kvm-multifd-Send-header-packet-without-flags-if-zero-cop.patch [bz#1968509] +- kvm-multifd-Implement-zero-copy-write-in-multifd-migrati.patch [bz#1968509] +- kvm-QIOChannelSocket-Introduce-assert-and-reduce-ifdefs-.patch [bz#1968509] +- kvm-QIOChannelSocket-Fix-zero-copy-send-so-socket-flush-.patch [bz#1968509] +- kvm-migration-Change-zero_copy_send-from-migration-param.patch [bz#1968509] +- kvm-migration-Allow-migrate-recover-to-run-multiple-time.patch [bz#2096143] +- Resolves: bz#2060839 + (Consider deprecating CPU models like "kvm64" / "qemu64" on RHEL 9) +- Resolves: bz#1968509 + (Use MSG_ZEROCOPY on QEMU Live Migration) +- Resolves: bz#2096143 + (The migration port is not released if use it again for recovering postcopy migration) + +* Mon Jun 27 2022 Miroslav Rezanina - 7.0.0-7 +- kvm-coroutine-ucontext-use-QEMU_DEFINE_STATIC_CO_TLS.patch [bz#1952483] +- kvm-coroutine-use-QEMU_DEFINE_STATIC_CO_TLS.patch [bz#1952483] +- kvm-coroutine-win32-use-QEMU_DEFINE_STATIC_CO_TLS.patch [bz#1952483] +- kvm-Enable-virtio-iommu-pci-on-x86_64.patch [bz#2094252] +- kvm-linux-aio-fix-unbalanced-plugged-counter-in-laio_io_.patch [bz#2092788] +- kvm-linux-aio-explain-why-max-batch-is-checked-in-laio_i.patch [bz#2092788] +- Resolves: bz#1952483 + (RFE: QEMU's coroutines fail with CFLAGS=-flto on non-x86_64 architectures) +- Resolves: bz#2094252 + (Compile the virtio-iommu device on x86_64) +- Resolves: bz#2092788 + (Stalled IO Operations in VM) + +* Mon Jun 13 2022 Miroslav Rezanina - 7.0.0-6 +- kvm-Introduce-event-loop-base-abstract-class.patch [bz#2031024] +- kvm-util-main-loop-Introduce-the-main-loop-into-QOM.patch [bz#2031024] +- kvm-util-event-loop-base-Introduce-options-to-set-the-th.patch [bz#2031024] +- kvm-qcow2-Improve-refcount-structure-rebuilding.patch [bz#2072379] +- kvm-iotests-108-Test-new-refcount-rebuild-algorithm.patch [bz#2072379] +- kvm-qcow2-Add-errp-to-rebuild_refcount_structure.patch [bz#2072379] +- kvm-iotests-108-Fix-when-missing-user_allow_other.patch [bz#2072379] +- kvm-virtio-net-setup-vhost_dev-and-notifiers-for-cvq-onl.patch [bz#2070804] +- kvm-virtio-net-align-ctrl_vq-index-for-non-mq-guest-for-.patch [bz#2070804] +- kvm-vhost-vdpa-fix-improper-cleanup-in-net_init_vhost_vd.patch [bz#2070804] +- kvm-vhost-net-fix-improper-cleanup-in-vhost_net_start.patch [bz#2070804] +- kvm-vhost-vdpa-backend-feature-should-set-only-once.patch [bz#2070804] +- kvm-vhost-vdpa-change-name-and-polarity-for-vhost_vdpa_o.patch [bz#2070804] +- kvm-virtio-net-don-t-handle-mq-request-in-userspace-hand.patch [bz#2070804] +- kvm-Revert-globally-limit-the-maximum-number-of-CPUs.patch [bz#2094270] +- kvm-vfio-common-remove-spurious-warning-on-vfio_listener.patch [bz#2086262] +- Resolves: bz#2031024 + (Add support for fixing thread pool size [QEMU]) +- Resolves: bz#2072379 + (Fail to rebuild the reference count tables of qcow2 image on host block devices (e.g. LVs)) +- Resolves: bz#2070804 + (PXE boot crash qemu when using multiqueue vDPA) +- Resolves: bz#2094270 + (Do not set the hard vCPU limit to the soft vCPU limit in downstream qemu-kvm anymore) +- Resolves: bz#2086262 + ([Win11][tpm]vfio_listener_region_del received unaligned region) + +* Mon May 30 2022 Miroslav Rezanina - 7.0.0-5 +- kvm-qemu-nbd-Pass-max-connections-to-blockdev-layer.patch [bz#1708300] +- kvm-nbd-server-Allow-MULTI_CONN-for-shared-writable-expo.patch [bz#1708300] +- Resolves: bz#1708300 + (RFE: qemu-nbd vs NBD_FLAG_CAN_MULTI_CONN) + +* Thu May 19 2022 Miroslav Rezanina - 7.0.0-4 +- kvm-qapi-machine.json-Add-cluster-id.patch [bz#2041823] +- kvm-qtest-numa-test-Specify-CPU-topology-in-aarch64_numa.patch [bz#2041823] +- kvm-hw-arm-virt-Consider-SMP-configuration-in-CPU-topolo.patch [bz#2041823] +- kvm-qtest-numa-test-Correct-CPU-and-NUMA-association-in-.patch [bz#2041823] +- kvm-hw-arm-virt-Fix-CPU-s-default-NUMA-node-ID.patch [bz#2041823] +- kvm-hw-acpi-aml-build-Use-existing-CPU-topology-to-build.patch [bz#2041823] +- kvm-coroutine-Rename-qemu_coroutine_inc-dec_pool_size.patch [bz#2079938] +- kvm-coroutine-Revert-to-constant-batch-size.patch [bz#2079938] +- kvm-virtio-scsi-fix-ctrl-and-event-handler-functions-in-.patch [bz#2079347] +- kvm-virtio-scsi-don-t-waste-CPU-polling-the-event-virtqu.patch [bz#2079347] +- kvm-virtio-scsi-clean-up-virtio_scsi_handle_event_vq.patch [bz#2079347] +- kvm-virtio-scsi-clean-up-virtio_scsi_handle_ctrl_vq.patch [bz#2079347] +- kvm-virtio-scsi-clean-up-virtio_scsi_handle_cmd_vq.patch [bz#2079347] +- kvm-virtio-scsi-move-request-related-items-from-.h-to-.c.patch [bz#2079347] +- kvm-Revert-virtio-scsi-Reject-scsi-cd-if-data-plane-enab.patch [bz#1995710] +- kvm-migration-Fix-operator-type.patch [bz#2064530] +- Resolves: bz#2041823 + ([aarch64][numa] When there are at least 6 Numa nodes serial log shows 'arch topology borken') +- Resolves: bz#2079938 + (qemu coredump when boot with multi disks (qemu) failed to set up stack guard page: Cannot allocate memory) +- Resolves: bz#2079347 + (Guest boot blocked when scsi disks using same iothread and 100% CPU consumption) +- Resolves: bz#1995710 + (RFE: Allow virtio-scsi CD-ROM media change with IOThreads) +- Resolves: bz#2064530 + (Rebuild qemu-kvm with clang-14) + +* Thu May 12 2022 Miroslav Rezanina - 7.0.0-3 +- kvm-hw-arm-virt-Remove-the-dtb-kaslr-seed-machine-option.patch [bz#2046029] +- kvm-hw-arm-virt-Fix-missing-initialization-in-instance-c.patch [bz#2046029] +- kvm-Enable-virtio-iommu-pci-on-aarch64.patch [bz#1477099] +- kvm-sysemu-tpm-Add-a-stub-function-for-TPM_IS_CRB.patch [bz#2037612] +- kvm-vfio-common-remove-spurious-tpm-crb-cmd-misalignment.patch [bz#2037612] +- Resolves: bz#2046029 + ([WRB] New machine type property - dtb-kaslr-seed) +- Resolves: bz#1477099 + (virtio-iommu (including ACPI, VHOST/VFIO integration, migration support)) +- Resolves: bz#2037612 + ([Win11][tpm][QL41112 PF] vfio_listener_region_add received unaligned region) + +* Fri May 06 2022 Miroslav Rezanina - 7.0.0-2 +- kvm-configs-devices-aarch64-softmmu-Enable-CONFIG_VIRTIO.patch [bz#2044162] +- kvm-target-ppc-cpu-models-Fix-ppc_cpu_aliases-list-for-R.patch [bz#2081022] +- Resolves: bz#2044162 + ([RHEL9.1] Enable virtio-mem as tech-preview on ARM64 QEMU) +- Resolves: bz#2081022 + (Build regression on ppc64le with c9s qemu-kvm 7.0.0-1 changes) + +* Wed Apr 20 2022 Miroslav Rezanina - 7.0.0-1 +- Rebase to QEMU 7.0.0 [bz#2064757] +- Do not build ssh block driver anymore [bz#2064500] +- Removed hpet and parallel port support [bz#2065042] +- Compatibility support [bz#2064782 bz#2064771] +- Resolves: bz#2064757 + (Rebase to QEMU 7.0.0) +- Resolves: bz#2064500 + (Install qemu-kvm-6.2.0-11.el9_0.1 failed as conflict with qemu-kvm-block-ssh-6.2.0-11.el9_0.1) +- Resolves: bz#2065042 + (Remove upstream-only devices from the qemu-kvm binary) +- Resolves: bz#2064782 + (Update machine type compatibility for QEMU 7.0.0 update [s390x]) +- Resolves: bz#2064771 + (Update machine type compatibility for QEMU 7.0.0 update [x86_64]) + +* Thu Apr 14 2022 Miroslav Rezanina - 6.2.0-13 +- kvm-RHEL-disable-seqpacket-for-vhost-vsock-device-in-rhe.patch [bz#2065589] +- Resolves: bz#2065589 + (RHEL 9.0 guest with vsock device migration failed from RHEL 9.0 > RHEL 8.6 [rhel-9.1.0]) + +* Mon Mar 21 2022 Miroslav Rezanina - 6.2.0-12 +- kvm-RHEL-mark-old-machine-types-as-deprecated.patch [bz#2062813] +- kvm-hw-virtio-vdpa-Fix-leak-of-host-notifier-memory-regi.patch [bz#2062828] +- kvm-spec-Fix-obsolete-for-spice-subpackages.patch [bz#2062819 bz#2062817] +- kvm-spec-Obsolete-old-usb-redir-subpackage.patch [bz#2062819] +- kvm-spec-Obsolete-ssh-driver.patch [bz#2062817] +- Resolves: bz#2062828 + ([virtual network][rhel9][vDPA] qemu crash after hot unplug vdpa device [rhel-9.1.0]) +- Resolves: bz#2062819 + (Broken upgrade path due to qemu-kvm-hw-usbredir rename [rhel-9.1.0]) +- Resolves: bz#2062817 + (Missing qemu-kvm-block-ssh obsolete breaks upgrade path [rhel-9.1.0]) +- Resolves: bz#2062813 + (Mark all RHEL-8 and earlier machine types as deprecated [rhel-9.1.0]) * Tue Mar 01 2022 Miroslav Rezanina - 6.2.0-11 - kvm-spec-Remove-qemu-virtiofsd.patch [bz#2055284]