From d9dd6a665da53e499de7ac6c64eaa159df33d407 Mon Sep 17 00:00:00 2001 From: Miroslav Rezanina Date: Tue, 4 Apr 2023 08:34:43 -0400 Subject: [PATCH] Branch synchronization with RHEL 8.8.0 --- .gitignore | 5 +- 0004-Initial-redhat-build.patch | 313 -------- 0005-Enable-disable-devices-for-RHEL.patch | 642 ---------------- ...Machine-type-related-general-changes.patch | 619 --------------- 0007-Add-aarch64-machine-types.patch | 352 --------- 0008-Add-ppc64-machine-types.patch | 528 ------------- 0009-Add-s390x-machine-types.patch | 186 ----- 0010-Add-x86_64-machine-types.patch | 714 ------------------ 0011-Enable-make-check.patch | 186 ----- ...mber-of-devices-that-can-be-assigned.patch | 104 --- ...Add-support-statement-to-help-output.patch | 55 -- ...lly-limit-the-maximum-number-of-CPUs.patch | 45 -- ...documentation-instead-of-qemu-system.patch | 61 -- ...ct-scsi-cd-if-data-plane-enabled-RHE.patch | 66 -- ...e-at-least-64kiB-pages-for-downstrea.patch | 60 -- ...on-warning-when-opening-v2-images-rw.patch | 77 -- ...oduce-RHEL-9.0.0-hw-compat-structure.patch | 135 ---- ...90x-machine-type-compatibility-for-r.patch | 38 - ...ve-s3-s4-suspend-disabling-to-compat.patch | 70 -- README.rst | 19 - gating.yaml | 9 - kvm-Enable-virtio-iommu-pci-on-aarch64.patch | 41 - kvm-Enable-virtio-iommu-pci-on-x86_64.patch | 41 - ...oduce-event-loop-base-abstract-class.patch | 503 ------------ kvm-KVM-keep-track-of-running-ioctls.patch | 82 ++ ...y-AArch64-Drop-unsupported-CPU-types.patch | 237 ------ ...avocado-Switch-aarch64-tests-from-a5.patch | 95 --- ...lly-limit-the-maximum-number-of-CPUs.patch | 58 -- ...vert-migration-Simplify-unqueue_page.patch | 134 ---- ...si-Reject-scsi-cd-if-data-plane-enab.patch | 51 -- ...el-introduce-accelerator-blocker-API.patch | 349 +++++++++ ...aio-wait-switch-to-smp_mb__after_rmw.patch | 50 ++ ...wait_kick-add-missing-memory-barrier.patch | 86 +++ ...sage-of-barriers-in-the-polling-case.patch | 66 ++ ...documentation-of-the-memory-barriers.patch | 111 +++ ...mirror-Do-not-wait-for-active-writes.patch | 153 ++++ ...r-Drop-mirror_wait_for_any_operation.patch | 76 ++ ...rror-Fix-NULL-s-job-in-active-writes.patch | 75 ++ ...aarch64-softmmu-Enable-CONFIG_VIRTIO.patch | 41 - ...ame-qemu_coroutine_inc-dec_pool_size.patch | 101 --- ...outine-Revert-to-constant-batch-size.patch | 138 ---- ...ontext-use-QEMU_DEFINE_STATIC_CO_TLS.patch | 132 ---- ...outine-use-QEMU_DEFINE_STATIC_CO_TLS.patch | 139 ---- ...-win32-use-QEMU_DEFINE_STATIC_CO_TLS.patch | 99 --- ...ent-dma_blk_cb-vs-dma_aio_cancel-rac.patch | 127 ++++ kvm-edu-add-smp_mb__after_rmw.patch | 61 ++ ...d-Use-existing-CPU-topology-to-build.patch | 179 ----- ...ider-SMP-configuration-in-CPU-topolo.patch | 74 -- ...-virt-Fix-CPU-s-default-NUMA-node-ID.patch | 88 --- ...missing-initialization-in-instance-c.patch | 56 -- ...ve-the-dtb-kaslr-seed-machine-option.patch | 76 -- ...virtio-Replace-g_memdup-by-g_memdup2.patch | 95 --- ...port-for-MSG_PEEK-for-socket-channel.patch | 367 +++++++++ kvm-kvm-Atomic-memslot-updates.patch | 290 +++++++ ...on-t-use-perror-without-useful-errno.patch | 62 -- kvm-meson-create-have_vhost_-variables.patch | 154 ---- ...ave_vhost_-variables-to-pick-sources.patch | 213 ------ ...docker-test-build-alpine-when-includ.patch | 87 --- kvm-migration-Fix-operator-type.patch | 47 -- kvm-migration-Read-state-once.patch | 76 ++ ...magic-value-for-deciding-the-mapping.patch | 296 ++++++++ ...es-before-compressing-them-with-zlib.patch | 142 ---- ...-MULTI_CONN-for-shared-writable-expo.patch | 381 ---------- ...-netboot.mak-Ignore-Clang-s-warnings.patch | 78 -- kvm-physmem-add-missing-memory-barrier.patch | 55 ++ kvm-qapi-machine.json-Add-cluster-id.patch | 126 ---- ...qatomic-add-smp_mb__before-after_rmw.patch | 177 +++++ ...tical-corruption-in-store_bitmap-err.patch | 67 ++ ...coroutine-lock-add-smp_mb__after_rmw.patch | 75 ++ ...Report-errors-while-closing-the-imag.patch | 70 ++ ...Report-errors-while-closing-the-imag.patch | 67 ++ ...t-qemu-img-bitmap-commit-exit-code-o.patch | 166 ++++ ...ss-max-connections-to-blockdev-layer.patch | 92 --- ...posix-cleanup-fix-document-QemuEvent.patch | 146 ++++ ...win32-cleanup-fix-document-QemuEvent.patch | 162 ++++ ...Correct-CPU-and-NUMA-association-in-.patch | 100 --- ...Specify-CPU-topology-in-aarch64_numa.patch | 68 -- ...-second-pass-when-mappings-exhausted.patch | 114 +++ kvm-s390x-pci-coalesce-unmap-operations.patch | 125 +++ ...ISM-passthrough-devices-on-shutdown-.patch | 147 ++++ ...-DMA-aperture-to-be-bound-by-vfio-DM.patch | 91 +++ ...otect-req-aiocb-with-AioContext-lock.patch | 176 +++++ ...m-Add-a-stub-function-for-TPM_IS_CRB.patch | 54 -- ...arget-arm-deprecate-named-CPU-models.patch | 129 ---- ...recate-CPUs-older-than-x86_64-v2-ABI.patch | 273 ------- ...odels-Fix-ppc_cpu_aliases-list-for-R.patch | 48 -- ...h_dump-Fix-memory-corruption-in-s390.patch | 50 ++ ...-s390x-deprecate-CPUs-older-than-z14.patch | 194 ----- ...date-aarch64_virt-test-to-exercise-c.patch | 157 ---- ...base-Introduce-options-to-set-the-th.patch | 385 ---------- ...oop-Introduce-the-main-loop-into-QOM.patch | 233 ------ kvm-vdpa-Add-device-migration-blocker.patch | 106 --- ...-Add-x-svq-to-NetdevVhostVDPAOptions.patch | 223 ------ ...compiler-to-squash-reads-to-used-idx.patch | 65 -- ...ffer-CVQ-support-on-shadow-virtqueue.patch | 323 -------- ...t-vhost_vdpa_dma_map-and-unmap-calls.patch | 84 --- ...-features-part-from-vhost_vdpa_get_m.patch | 108 --- kvm-vdpa-manual-forward-CVQ-buffers.patch | 166 ---- ...ve-spurious-tpm-crb-cmd-misalignment.patch | 114 --- ...ve-spurious-warning-on-vfio_listener.patch | 78 -- kvm-vhost-Add-SVQDescState.patch | 135 ---- ...vhost-Add-svq-avail_handler-callback.patch | 164 ---- ...heck-for-queue-full-at-vhost_svq_add.patch | 134 ---- ...-vhost_svq_add-from-VirtQueueElement.patch | 138 ---- kvm-vhost-Expose-vhost_svq_add.patch | 73 -- ...Fix-device-s-used-descriptor-dequeue.patch | 83 -- ...Fix-element-in-vhost_svq_add-failure.patch | 68 -- ...vhost_svq_kick-call-to-vhost_svq_add.patch | 61 -- kvm-vhost-Reorder-vhost_svq_kick.patch | 88 --- ...k-descriptor-chain-in-private-at-SVQ.patch | 123 --- ...rack-number-of-descs-in-SVQDescState.patch | 81 -- kvm-vhost-add-vhost_svq_poll.patch | 92 --- kvm-vhost-add-vhost_svq_push_elem.patch | 83 -- ...iptor-translation-to-vhost_svq_vring.patch | 120 --- ...dd-stubs-for-when-no-virtio-net-devi.patch | 87 --- ...-an-assert-check-in-translate-routin.patch | 46 -- ...-bypass-mode-support-to-assigned-dev.patch | 250 ------ ...irtio-iommu-Fix-migration-regression.patch | 54 -- ...ix-the-partial-copy-of-probe-request.patch | 67 -- ...Use-recursive-lock-to-avoid-deadlock.patch | 141 ---- kvm-virtio-net-Expose-MAC_TABLE_ENTRIES.patch | 69 -- ...rtio-net-Expose-ctrl-virtqueue-logic.patch | 169 ----- ...i-clean-up-virtio_scsi_handle_cmd_vq.patch | 77 -- ...-clean-up-virtio_scsi_handle_ctrl_vq.patch | 65 -- ...clean-up-virtio_scsi_handle_event_vq.patch | 62 -- ...t-waste-CPU-polling-the-event-virtqu.patch | 103 --- ...ctrl-and-event-handler-functions-in-.patch | 119 --- ...-request-related-items-from-.h-to-.c.patch | 168 ----- ...t-SCSI-devices-from-main-loop-thread.patch | 337 +++++++++ modules-load.conf | 4 - qemu-kvm.spec | 121 ++- rpminspect.yaml | 11 - tests_data_acpi_virt_SSDT | Bin 0 -> 736 bytes 133 files changed, 4414 insertions(+), 13884 deletions(-) delete mode 100644 0004-Initial-redhat-build.patch delete mode 100644 0005-Enable-disable-devices-for-RHEL.patch delete mode 100644 0006-Machine-type-related-general-changes.patch delete mode 100644 0007-Add-aarch64-machine-types.patch delete mode 100644 0008-Add-ppc64-machine-types.patch delete mode 100644 0009-Add-s390x-machine-types.patch delete mode 100644 0010-Add-x86_64-machine-types.patch delete mode 100644 0011-Enable-make-check.patch delete mode 100644 0012-vfio-cap-number-of-devices-that-can-be-assigned.patch delete mode 100644 0013-Add-support-statement-to-help-output.patch delete mode 100644 0014-globally-limit-the-maximum-number-of-CPUs.patch delete mode 100644 0015-Use-qemu-kvm-in-documentation-instead-of-qemu-system.patch delete mode 100644 0016-virtio-scsi-Reject-scsi-cd-if-data-plane-enabled-RHE.patch delete mode 100644 0017-BZ1653590-Require-at-least-64kiB-pages-for-downstrea.patch delete mode 100644 0018-qcow2-Deprecation-warning-when-opening-v2-images-rw.patch delete mode 100644 0019-WRB-Introduce-RHEL-9.0.0-hw-compat-structure.patch delete mode 100644 0020-redhat-Update-s390x-machine-type-compatibility-for-r.patch delete mode 100644 0021-pc-Move-s3-s4-suspend-disabling-to-compat.patch delete mode 100644 README.rst delete mode 100644 gating.yaml delete mode 100644 kvm-Enable-virtio-iommu-pci-on-aarch64.patch delete mode 100644 kvm-Enable-virtio-iommu-pci-on-x86_64.patch delete mode 100644 kvm-Introduce-event-loop-base-abstract-class.patch create mode 100644 kvm-KVM-keep-track-of-running-ioctls.patch delete mode 100644 kvm-RHEL-only-AArch64-Drop-unsupported-CPU-types.patch delete mode 100644 kvm-RHEL-only-tests-avocado-Switch-aarch64-tests-from-a5.patch delete mode 100644 kvm-Revert-globally-limit-the-maximum-number-of-CPUs.patch delete mode 100644 kvm-Revert-migration-Simplify-unqueue_page.patch delete mode 100644 kvm-Revert-virtio-scsi-Reject-scsi-cd-if-data-plane-enab.patch create mode 100644 kvm-accel-introduce-accelerator-blocker-API.patch create mode 100644 kvm-aio-wait-switch-to-smp_mb__after_rmw.patch create mode 100644 kvm-aio_wait_kick-add-missing-memory-barrier.patch create mode 100644 kvm-async-clarify-usage-of-barriers-in-the-polling-case.patch create mode 100644 kvm-async-update-documentation-of-the-memory-barriers.patch create mode 100644 kvm-block-mirror-Do-not-wait-for-active-writes.patch create mode 100644 kvm-block-mirror-Drop-mirror_wait_for_any_operation.patch create mode 100644 kvm-block-mirror-Fix-NULL-s-job-in-active-writes.patch delete mode 100644 kvm-configs-devices-aarch64-softmmu-Enable-CONFIG_VIRTIO.patch delete mode 100644 kvm-coroutine-Rename-qemu_coroutine_inc-dec_pool_size.patch delete mode 100644 kvm-coroutine-Revert-to-constant-batch-size.patch delete mode 100644 kvm-coroutine-ucontext-use-QEMU_DEFINE_STATIC_CO_TLS.patch delete mode 100644 kvm-coroutine-use-QEMU_DEFINE_STATIC_CO_TLS.patch delete mode 100644 kvm-coroutine-win32-use-QEMU_DEFINE_STATIC_CO_TLS.patch create mode 100644 kvm-dma-helpers-prevent-dma_blk_cb-vs-dma_aio_cancel-rac.patch create mode 100644 kvm-edu-add-smp_mb__after_rmw.patch delete mode 100644 kvm-hw-acpi-aml-build-Use-existing-CPU-topology-to-build.patch delete mode 100644 kvm-hw-arm-virt-Consider-SMP-configuration-in-CPU-topolo.patch delete mode 100644 kvm-hw-arm-virt-Fix-CPU-s-default-NUMA-node-ID.patch delete mode 100644 kvm-hw-arm-virt-Fix-missing-initialization-in-instance-c.patch delete mode 100644 kvm-hw-arm-virt-Remove-the-dtb-kaslr-seed-machine-option.patch delete mode 100644 kvm-hw-virtio-Replace-g_memdup-by-g_memdup2.patch create mode 100644 kvm-io-Add-support-for-MSG_PEEK-for-socket-channel.patch create mode 100644 kvm-kvm-Atomic-memslot-updates.patch delete mode 100644 kvm-kvm-don-t-use-perror-without-useful-errno.patch delete mode 100644 kvm-meson-create-have_vhost_-variables.patch delete mode 100644 kvm-meson-use-have_vhost_-variables-to-pick-sources.patch delete mode 100644 kvm-meson.build-Fix-docker-test-build-alpine-when-includ.patch delete mode 100644 kvm-migration-Fix-operator-type.patch create mode 100644 kvm-migration-Read-state-once.patch create mode 100644 kvm-migration-check-magic-value-for-deciding-the-mapping.patch delete mode 100644 kvm-multifd-Copy-pages-before-compressing-them-with-zlib.patch delete mode 100644 kvm-nbd-server-Allow-MULTI_CONN-for-shared-writable-expo.patch delete mode 100644 kvm-pc-bios-s390-ccw-netboot.mak-Ignore-Clang-s-warnings.patch create mode 100644 kvm-physmem-add-missing-memory-barrier.patch delete mode 100644 kvm-qapi-machine.json-Add-cluster-id.patch create mode 100644 kvm-qatomic-add-smp_mb__before-after_rmw.patch create mode 100644 kvm-qcow2-Fix-theoretical-corruption-in-store_bitmap-err.patch create mode 100644 kvm-qemu-coroutine-lock-add-smp_mb__after_rmw.patch create mode 100644 kvm-qemu-img-bitmap-Report-errors-while-closing-the-imag.patch create mode 100644 kvm-qemu-img-commit-Report-errors-while-closing-the-imag.patch create mode 100644 kvm-qemu-iotests-Test-qemu-img-bitmap-commit-exit-code-o.patch delete mode 100644 kvm-qemu-nbd-Pass-max-connections-to-blockdev-layer.patch create mode 100644 kvm-qemu-thread-posix-cleanup-fix-document-QemuEvent.patch create mode 100644 kvm-qemu-thread-win32-cleanup-fix-document-QemuEvent.patch delete mode 100644 kvm-qtest-numa-test-Correct-CPU-and-NUMA-association-in-.patch delete mode 100644 kvm-qtest-numa-test-Specify-CPU-topology-in-aarch64_numa.patch create mode 100644 kvm-s390x-pci-RPCIT-second-pass-when-mappings-exhausted.patch create mode 100644 kvm-s390x-pci-coalesce-unmap-operations.patch create mode 100644 kvm-s390x-pci-reset-ISM-passthrough-devices-on-shutdown-.patch create mode 100644 kvm-s390x-pci-shrink-DMA-aperture-to-be-bound-by-vfio-DM.patch create mode 100644 kvm-scsi-protect-req-aiocb-with-AioContext-lock.patch delete mode 100644 kvm-sysemu-tpm-Add-a-stub-function-for-TPM_IS_CRB.patch delete mode 100644 kvm-target-arm-deprecate-named-CPU-models.patch delete mode 100644 kvm-target-i386-deprecate-CPUs-older-than-x86_64-v2-ABI.patch delete mode 100644 kvm-target-ppc-cpu-models-Fix-ppc_cpu_aliases-list-for-R.patch create mode 100644 kvm-target-s390x-arch_dump-Fix-memory-corruption-in-s390.patch delete mode 100644 kvm-target-s390x-deprecate-CPUs-older-than-z14.patch delete mode 100644 kvm-tests-avocado-update-aarch64_virt-test-to-exercise-c.patch delete mode 100644 kvm-util-event-loop-base-Introduce-options-to-set-the-th.patch delete mode 100644 kvm-util-main-loop-Introduce-the-main-loop-into-QOM.patch delete mode 100644 kvm-vdpa-Add-device-migration-blocker.patch delete mode 100644 kvm-vdpa-Add-x-svq-to-NetdevVhostVDPAOptions.patch delete mode 100644 kvm-vdpa-Avoid-compiler-to-squash-reads-to-used-idx.patch delete mode 100644 kvm-vdpa-Buffer-CVQ-support-on-shadow-virtqueue.patch delete mode 100644 kvm-vdpa-Export-vhost_vdpa_dma_map-and-unmap-calls.patch delete mode 100644 kvm-vdpa-Extract-get-features-part-from-vhost_vdpa_get_m.patch delete mode 100644 kvm-vdpa-manual-forward-CVQ-buffers.patch delete mode 100644 kvm-vfio-common-remove-spurious-tpm-crb-cmd-misalignment.patch delete mode 100644 kvm-vfio-common-remove-spurious-warning-on-vfio_listener.patch delete mode 100644 kvm-vhost-Add-SVQDescState.patch delete mode 100644 kvm-vhost-Add-svq-avail_handler-callback.patch delete mode 100644 kvm-vhost-Check-for-queue-full-at-vhost_svq_add.patch delete mode 100644 kvm-vhost-Decouple-vhost_svq_add-from-VirtQueueElement.patch delete mode 100644 kvm-vhost-Expose-vhost_svq_add.patch delete mode 100644 kvm-vhost-Fix-device-s-used-descriptor-dequeue.patch delete mode 100644 kvm-vhost-Fix-element-in-vhost_svq_add-failure.patch delete mode 100644 kvm-vhost-Move-vhost_svq_kick-call-to-vhost_svq_add.patch delete mode 100644 kvm-vhost-Reorder-vhost_svq_kick.patch delete mode 100644 kvm-vhost-Track-descriptor-chain-in-private-at-SVQ.patch delete mode 100644 kvm-vhost-Track-number-of-descs-in-SVQDescState.patch delete mode 100644 kvm-vhost-add-vhost_svq_poll.patch delete mode 100644 kvm-vhost-add-vhost_svq_push_elem.patch delete mode 100644 kvm-vhost-move-descriptor-translation-to-vhost_svq_vring.patch delete mode 100644 kvm-vhost-net-vdpa-add-stubs-for-when-no-virtio-net-devi.patch delete mode 100644 kvm-virtio-iommu-Add-an-assert-check-in-translate-routin.patch delete mode 100644 kvm-virtio-iommu-Add-bypass-mode-support-to-assigned-dev.patch delete mode 100644 kvm-virtio-iommu-Fix-migration-regression.patch delete mode 100644 kvm-virtio-iommu-Fix-the-partial-copy-of-probe-request.patch delete mode 100644 kvm-virtio-iommu-Use-recursive-lock-to-avoid-deadlock.patch delete mode 100644 kvm-virtio-net-Expose-MAC_TABLE_ENTRIES.patch delete mode 100644 kvm-virtio-net-Expose-ctrl-virtqueue-logic.patch delete mode 100644 kvm-virtio-scsi-clean-up-virtio_scsi_handle_cmd_vq.patch delete mode 100644 kvm-virtio-scsi-clean-up-virtio_scsi_handle_ctrl_vq.patch delete mode 100644 kvm-virtio-scsi-clean-up-virtio_scsi_handle_event_vq.patch delete mode 100644 kvm-virtio-scsi-don-t-waste-CPU-polling-the-event-virtqu.patch delete mode 100644 kvm-virtio-scsi-fix-ctrl-and-event-handler-functions-in-.patch delete mode 100644 kvm-virtio-scsi-move-request-related-items-from-.h-to-.c.patch create mode 100644 kvm-virtio-scsi-reset-SCSI-devices-from-main-loop-thread.patch delete mode 100644 modules-load.conf delete mode 100644 rpminspect.yaml create mode 100644 tests_data_acpi_virt_SSDT diff --git a/.gitignore b/.gitignore index 3305db8..ad51880 100644 --- a/.gitignore +++ b/.gitignore @@ -1,2 +1,5 @@ -SOURCES/qemu-6.2.0.tar.xz +/qemu-5.2.0-rc2.tar.xz +/qemu-5.2.0.tar.xz +/qemu-6.0.0.tar.xz /qemu-6.2.0.tar.xz +SOURCES/qemu-6.2.0.tar.xz diff --git a/0004-Initial-redhat-build.patch b/0004-Initial-redhat-build.patch deleted file mode 100644 index 94cf91c..0000000 --- a/0004-Initial-redhat-build.patch +++ /dev/null @@ -1,313 +0,0 @@ -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/0005-Enable-disable-devices-for-RHEL.patch b/0005-Enable-disable-devices-for-RHEL.patch deleted file mode 100644 index 1ffbe97..0000000 --- a/0005-Enable-disable-devices-for-RHEL.patch +++ /dev/null @@ -1,642 +0,0 @@ -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/0006-Machine-type-related-general-changes.patch b/0006-Machine-type-related-general-changes.patch deleted file mode 100644 index c3b08a4..0000000 --- a/0006-Machine-type-related-general-changes.patch +++ /dev/null @@ -1,619 +0,0 @@ -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/0007-Add-aarch64-machine-types.patch b/0007-Add-aarch64-machine-types.patch deleted file mode 100644 index 3c44b11..0000000 --- a/0007-Add-aarch64-machine-types.patch +++ /dev/null @@ -1,352 +0,0 @@ -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/0008-Add-ppc64-machine-types.patch b/0008-Add-ppc64-machine-types.patch deleted file mode 100644 index 860e803..0000000 --- a/0008-Add-ppc64-machine-types.patch +++ /dev/null @@ -1,528 +0,0 @@ -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/0009-Add-s390x-machine-types.patch b/0009-Add-s390x-machine-types.patch deleted file mode 100644 index 2d8b554..0000000 --- a/0009-Add-s390x-machine-types.patch +++ /dev/null @@ -1,186 +0,0 @@ -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/0010-Add-x86_64-machine-types.patch b/0010-Add-x86_64-machine-types.patch deleted file mode 100644 index 7c48967..0000000 --- a/0010-Add-x86_64-machine-types.patch +++ /dev/null @@ -1,714 +0,0 @@ -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/0011-Enable-make-check.patch b/0011-Enable-make-check.patch deleted file mode 100644 index 832b38d..0000000 --- a/0011-Enable-make-check.patch +++ /dev/null @@ -1,186 +0,0 @@ -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/0012-vfio-cap-number-of-devices-that-can-be-assigned.patch b/0012-vfio-cap-number-of-devices-that-can-be-assigned.patch deleted file mode 100644 index c9e42b2..0000000 --- a/0012-vfio-cap-number-of-devices-that-can-be-assigned.patch +++ /dev/null @@ -1,104 +0,0 @@ -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/0013-Add-support-statement-to-help-output.patch b/0013-Add-support-statement-to-help-output.patch deleted file mode 100644 index 4826ea4..0000000 --- a/0013-Add-support-statement-to-help-output.patch +++ /dev/null @@ -1,55 +0,0 @@ -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/0014-globally-limit-the-maximum-number-of-CPUs.patch b/0014-globally-limit-the-maximum-number-of-CPUs.patch deleted file mode 100644 index 6764a84..0000000 --- a/0014-globally-limit-the-maximum-number-of-CPUs.patch +++ /dev/null @@ -1,45 +0,0 @@ -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/0015-Use-qemu-kvm-in-documentation-instead-of-qemu-system.patch b/0015-Use-qemu-kvm-in-documentation-instead-of-qemu-system.patch deleted file mode 100644 index 722484d..0000000 --- a/0015-Use-qemu-kvm-in-documentation-instead-of-qemu-system.patch +++ /dev/null @@ -1,61 +0,0 @@ -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/0016-virtio-scsi-Reject-scsi-cd-if-data-plane-enabled-RHE.patch b/0016-virtio-scsi-Reject-scsi-cd-if-data-plane-enabled-RHE.patch deleted file mode 100644 index 9f08024..0000000 --- a/0016-virtio-scsi-Reject-scsi-cd-if-data-plane-enabled-RHE.patch +++ /dev/null @@ -1,66 +0,0 @@ -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/0017-BZ1653590-Require-at-least-64kiB-pages-for-downstrea.patch b/0017-BZ1653590-Require-at-least-64kiB-pages-for-downstrea.patch deleted file mode 100644 index 2bc687c..0000000 --- a/0017-BZ1653590-Require-at-least-64kiB-pages-for-downstrea.patch +++ /dev/null @@ -1,60 +0,0 @@ -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/0018-qcow2-Deprecation-warning-when-opening-v2-images-rw.patch b/0018-qcow2-Deprecation-warning-when-opening-v2-images-rw.patch deleted file mode 100644 index d7401d5..0000000 --- a/0018-qcow2-Deprecation-warning-when-opening-v2-images-rw.patch +++ /dev/null @@ -1,77 +0,0 @@ -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/0019-WRB-Introduce-RHEL-9.0.0-hw-compat-structure.patch b/0019-WRB-Introduce-RHEL-9.0.0-hw-compat-structure.patch deleted file mode 100644 index 285cd6b..0000000 --- a/0019-WRB-Introduce-RHEL-9.0.0-hw-compat-structure.patch +++ /dev/null @@ -1,135 +0,0 @@ -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/0020-redhat-Update-s390x-machine-type-compatibility-for-r.patch b/0020-redhat-Update-s390x-machine-type-compatibility-for-r.patch deleted file mode 100644 index d3b91d0..0000000 --- a/0020-redhat-Update-s390x-machine-type-compatibility-for-r.patch +++ /dev/null @@ -1,38 +0,0 @@ -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/0021-pc-Move-s3-s4-suspend-disabling-to-compat.patch b/0021-pc-Move-s3-s4-suspend-disabling-to-compat.patch deleted file mode 100644 index f9535a8..0000000 --- a/0021-pc-Move-s3-s4-suspend-disabling-to-compat.patch +++ /dev/null @@ -1,70 +0,0 @@ -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/README.rst b/README.rst deleted file mode 100644 index 15f93e6..0000000 --- a/README.rst +++ /dev/null @@ -1,19 +0,0 @@ -=================== -qemu-kvm development -=================== - -qemu-kvm is maintained in a `source tree`_ rather than directly in dist-git. -This provides way to develope using regular source code structure and provides -way to generate SRPM and build using koji service. In addition, local build using -CentOS 9 Stream specific configuration. - -Developers deliver all changes to source-git using merge request. Only maintainers -will be pushing changes sent to source-git to dist-git. - -Each release in dist-git is tagged in the source repository so you can easily -check out the source tree for a build. The tags are in the format -name-version-release, but note release doesn't contain the dist tag since the -source can be built in different build roots (Fedora, CentOS, etc.) - -.. _source tree: https://gitlab.com/redhat/centos-stream/src/qemu-kvm - diff --git a/gating.yaml b/gating.yaml deleted file mode 100644 index 8d17eb8..0000000 --- a/gating.yaml +++ /dev/null @@ -1,9 +0,0 @@ -# recipients: kvmqe-ci, yfu ---- !Policy -product_versions: - - rhel-9 -decision_context: osci_compose_gate -subject_type: brew-build -rules: - - !PassingTestCaseRule {test_case_name: kvm-ci.qemu-kvm.x86_64-intel.brew-build.gating.tier1.functional} - - !PassingTestCaseRule {test_case_name: kvm-ci.qemu-kvm.x86_64-amd.brew-build.gating.tier1.functional} diff --git a/kvm-Enable-virtio-iommu-pci-on-aarch64.patch b/kvm-Enable-virtio-iommu-pci-on-aarch64.patch deleted file mode 100644 index 3aafd3c..0000000 --- a/kvm-Enable-virtio-iommu-pci-on-aarch64.patch +++ /dev/null @@ -1,41 +0,0 @@ -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/kvm-Enable-virtio-iommu-pci-on-x86_64.patch b/kvm-Enable-virtio-iommu-pci-on-x86_64.patch deleted file mode 100644 index 2eb24df..0000000 --- a/kvm-Enable-virtio-iommu-pci-on-x86_64.patch +++ /dev/null @@ -1,41 +0,0 @@ -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/kvm-Introduce-event-loop-base-abstract-class.patch b/kvm-Introduce-event-loop-base-abstract-class.patch deleted file mode 100644 index 9f987ea..0000000 --- a/kvm-Introduce-event-loop-base-abstract-class.patch +++ /dev/null @@ -1,503 +0,0 @@ -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/kvm-KVM-keep-track-of-running-ioctls.patch b/kvm-KVM-keep-track-of-running-ioctls.patch new file mode 100644 index 0000000..8fad887 --- /dev/null +++ b/kvm-KVM-keep-track-of-running-ioctls.patch @@ -0,0 +1,82 @@ +From 9bacf8c4104ff3cff2e0e2c2179ec4fda633167f Mon Sep 17 00:00:00 2001 +From: Emanuele Giuseppe Esposito +Date: Mon, 16 Jan 2023 07:51:08 -0500 +Subject: [PATCH 05/11] KVM: keep track of running ioctls + +RH-Author: Emanuele Giuseppe Esposito +RH-MergeRequest: 247: accel: introduce accelerator blocker API +RH-Bugzilla: 2161188 +RH-Acked-by: David Hildenbrand +RH-Acked-by: Vitaly Kuznetsov +RH-Acked-by: Miroslav Rezanina +RH-Commit: [2/3] 357508389e2a0fd996206b406e9e235e50b5f0b6 + +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2161188 + +commit a27dd2de68f37ba96fe164a42121daa5f0750afc +Author: Emanuele Giuseppe Esposito +Date: Fri Nov 11 10:47:57 2022 -0500 + + KVM: keep track of running ioctls + + Using the new accel-blocker API, mark where ioctls are being called + in KVM. Next, we will implement the critical section that will take + care of performing memslots modifications atomically, therefore + preventing any new ioctl from running and allowing the running ones + to finish. + + Signed-off-by: David Hildenbrand + Signed-off-by: Emanuele Giuseppe Esposito + Message-Id: <20221111154758.1372674-3-eesposit@redhat.com> + Signed-off-by: Paolo Bonzini + +Signed-off-by: Emanuele Giuseppe Esposito +--- + accel/kvm/kvm-all.c | 7 +++++++ + 1 file changed, 7 insertions(+) + +diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c +index 8f2a53438f..221aadfda7 100644 +--- a/accel/kvm/kvm-all.c ++++ b/accel/kvm/kvm-all.c +@@ -2337,6 +2337,7 @@ static int kvm_init(MachineState *ms) + assert(TARGET_PAGE_SIZE <= qemu_real_host_page_size); + + s->sigmask_len = 8; ++ accel_blocker_init(); + + #ifdef KVM_CAP_SET_GUEST_DEBUG + QTAILQ_INIT(&s->kvm_sw_breakpoints); +@@ -3018,7 +3019,9 @@ int kvm_vm_ioctl(KVMState *s, int type, ...) + va_end(ap); + + trace_kvm_vm_ioctl(type, arg); ++ accel_ioctl_begin(); + ret = ioctl(s->vmfd, type, arg); ++ accel_ioctl_end(); + if (ret == -1) { + ret = -errno; + } +@@ -3036,7 +3039,9 @@ int kvm_vcpu_ioctl(CPUState *cpu, int type, ...) + va_end(ap); + + trace_kvm_vcpu_ioctl(cpu->cpu_index, type, arg); ++ accel_cpu_ioctl_begin(cpu); + ret = ioctl(cpu->kvm_fd, type, arg); ++ accel_cpu_ioctl_end(cpu); + if (ret == -1) { + ret = -errno; + } +@@ -3054,7 +3059,9 @@ int kvm_device_ioctl(int fd, int type, ...) + va_end(ap); + + trace_kvm_device_ioctl(fd, type, arg); ++ accel_ioctl_begin(); + ret = ioctl(fd, type, arg); ++ accel_ioctl_end(); + if (ret == -1) { + ret = -errno; + } +-- +2.37.3 + diff --git a/kvm-RHEL-only-AArch64-Drop-unsupported-CPU-types.patch b/kvm-RHEL-only-AArch64-Drop-unsupported-CPU-types.patch deleted file mode 100644 index 8a0aeb0..0000000 --- a/kvm-RHEL-only-AArch64-Drop-unsupported-CPU-types.patch +++ /dev/null @@ -1,237 +0,0 @@ -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/kvm-RHEL-only-tests-avocado-Switch-aarch64-tests-from-a5.patch b/kvm-RHEL-only-tests-avocado-Switch-aarch64-tests-from-a5.patch deleted file mode 100644 index a1cc4c7..0000000 --- a/kvm-RHEL-only-tests-avocado-Switch-aarch64-tests-from-a5.patch +++ /dev/null @@ -1,95 +0,0 @@ -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/kvm-Revert-globally-limit-the-maximum-number-of-CPUs.patch b/kvm-Revert-globally-limit-the-maximum-number-of-CPUs.patch deleted file mode 100644 index 7740d0b..0000000 --- a/kvm-Revert-globally-limit-the-maximum-number-of-CPUs.patch +++ /dev/null @@ -1,58 +0,0 @@ -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/kvm-Revert-migration-Simplify-unqueue_page.patch b/kvm-Revert-migration-Simplify-unqueue_page.patch deleted file mode 100644 index f5c97f6..0000000 --- a/kvm-Revert-migration-Simplify-unqueue_page.patch +++ /dev/null @@ -1,134 +0,0 @@ -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/kvm-Revert-virtio-scsi-Reject-scsi-cd-if-data-plane-enab.patch b/kvm-Revert-virtio-scsi-Reject-scsi-cd-if-data-plane-enab.patch deleted file mode 100644 index e8eb35d..0000000 --- a/kvm-Revert-virtio-scsi-Reject-scsi-cd-if-data-plane-enab.patch +++ /dev/null @@ -1,51 +0,0 @@ -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/kvm-accel-introduce-accelerator-blocker-API.patch b/kvm-accel-introduce-accelerator-blocker-API.patch new file mode 100644 index 0000000..7db7fd2 --- /dev/null +++ b/kvm-accel-introduce-accelerator-blocker-API.patch @@ -0,0 +1,349 @@ +From a5e7bb1f7a88efb5574266a76e80fd7604d19921 Mon Sep 17 00:00:00 2001 +From: Emanuele Giuseppe Esposito +Date: Mon, 16 Jan 2023 07:49:59 -0500 +Subject: [PATCH 04/11] accel: introduce accelerator blocker API +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Emanuele Giuseppe Esposito +RH-MergeRequest: 247: accel: introduce accelerator blocker API +RH-Bugzilla: 2161188 +RH-Acked-by: David Hildenbrand +RH-Acked-by: Vitaly Kuznetsov +RH-Acked-by: Miroslav Rezanina +RH-Commit: [1/3] 9d3d7f9554974a79042c915763288cce07aef135 + +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2161188 + +commit bd688fc93120fb3e28aa70e3dfdf567ccc1e0bc1 +Author: Emanuele Giuseppe Esposito +Date: Fri Nov 11 10:47:56 2022 -0500 + + accel: introduce accelerator blocker API + + This API allows the accelerators to prevent vcpus from issuing + new ioctls while execting a critical section marked with the + accel_ioctl_inhibit_begin/end functions. + + Note that all functions submitting ioctls must mark where the + ioctl is being called with accel_{cpu_}ioctl_begin/end(). + + This API requires the caller to always hold the BQL. + API documentation is in sysemu/accel-blocker.h + + Internally, it uses a QemuLockCnt together with a per-CPU QemuLockCnt + (to minimize cache line bouncing) to keep avoid that new ioctls + run when the critical section starts, and a QemuEvent to wait + that all running ioctls finish. + + Signed-off-by: Emanuele Giuseppe Esposito + Reviewed-by: Philippe Mathieu-Daudé + Message-Id: <20221111154758.1372674-2-eesposit@redhat.com> + Signed-off-by: Paolo Bonzini + +Conflicts: + util/meson.build: files are missing in rhel 8.8.0 + namely int128.c, memalign.c and interval-tree.c + +Signed-off-by: Emanuele Giuseppe Esposito +--- + accel/accel-blocker.c | 154 +++++++++++++++++++++++++++++++++ + accel/meson.build | 2 +- + hw/core/cpu-common.c | 2 + + include/hw/core/cpu.h | 3 + + include/sysemu/accel-blocker.h | 56 ++++++++++++ + util/meson.build | 2 +- + 6 files changed, 217 insertions(+), 2 deletions(-) + create mode 100644 accel/accel-blocker.c + create mode 100644 include/sysemu/accel-blocker.h + +diff --git a/accel/accel-blocker.c b/accel/accel-blocker.c +new file mode 100644 +index 0000000000..1e7f423462 +--- /dev/null ++++ b/accel/accel-blocker.c +@@ -0,0 +1,154 @@ ++/* ++ * Lock to inhibit accelerator ioctls ++ * ++ * Copyright (c) 2022 Red Hat Inc. ++ * ++ * Author: Emanuele Giuseppe Esposito ++ * ++ * Permission is hereby granted, free of charge, to any person obtaining a copy ++ * of this software and associated documentation files (the "Software"), to deal ++ * in the Software without restriction, including without limitation the rights ++ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell ++ * copies of the Software, and to permit persons to whom the Software is ++ * furnished to do so, subject to the following conditions: ++ * ++ * The above copyright notice and this permission notice shall be included in ++ * all copies or substantial portions of the Software. ++ * ++ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR ++ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, ++ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL ++ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER ++ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, ++ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN ++ * THE SOFTWARE. ++ */ ++ ++#include "qemu/osdep.h" ++#include "qemu/thread.h" ++#include "qemu/main-loop.h" ++#include "hw/core/cpu.h" ++#include "sysemu/accel-blocker.h" ++ ++static QemuLockCnt accel_in_ioctl_lock; ++static QemuEvent accel_in_ioctl_event; ++ ++void accel_blocker_init(void) ++{ ++ qemu_lockcnt_init(&accel_in_ioctl_lock); ++ qemu_event_init(&accel_in_ioctl_event, false); ++} ++ ++void accel_ioctl_begin(void) ++{ ++ if (likely(qemu_mutex_iothread_locked())) { ++ return; ++ } ++ ++ /* block if lock is taken in kvm_ioctl_inhibit_begin() */ ++ qemu_lockcnt_inc(&accel_in_ioctl_lock); ++} ++ ++void accel_ioctl_end(void) ++{ ++ if (likely(qemu_mutex_iothread_locked())) { ++ return; ++ } ++ ++ qemu_lockcnt_dec(&accel_in_ioctl_lock); ++ /* change event to SET. If event was BUSY, wake up all waiters */ ++ qemu_event_set(&accel_in_ioctl_event); ++} ++ ++void accel_cpu_ioctl_begin(CPUState *cpu) ++{ ++ if (unlikely(qemu_mutex_iothread_locked())) { ++ return; ++ } ++ ++ /* block if lock is taken in kvm_ioctl_inhibit_begin() */ ++ qemu_lockcnt_inc(&cpu->in_ioctl_lock); ++} ++ ++void accel_cpu_ioctl_end(CPUState *cpu) ++{ ++ if (unlikely(qemu_mutex_iothread_locked())) { ++ return; ++ } ++ ++ qemu_lockcnt_dec(&cpu->in_ioctl_lock); ++ /* change event to SET. If event was BUSY, wake up all waiters */ ++ qemu_event_set(&accel_in_ioctl_event); ++} ++ ++static bool accel_has_to_wait(void) ++{ ++ CPUState *cpu; ++ bool needs_to_wait = false; ++ ++ CPU_FOREACH(cpu) { ++ if (qemu_lockcnt_count(&cpu->in_ioctl_lock)) { ++ /* exit the ioctl, if vcpu is running it */ ++ qemu_cpu_kick(cpu); ++ needs_to_wait = true; ++ } ++ } ++ ++ return needs_to_wait || qemu_lockcnt_count(&accel_in_ioctl_lock); ++} ++ ++void accel_ioctl_inhibit_begin(void) ++{ ++ CPUState *cpu; ++ ++ /* ++ * We allow to inhibit only when holding the BQL, so we can identify ++ * when an inhibitor wants to issue an ioctl easily. ++ */ ++ g_assert(qemu_mutex_iothread_locked()); ++ ++ /* Block further invocations of the ioctls outside the BQL. */ ++ CPU_FOREACH(cpu) { ++ qemu_lockcnt_lock(&cpu->in_ioctl_lock); ++ } ++ qemu_lockcnt_lock(&accel_in_ioctl_lock); ++ ++ /* Keep waiting until there are running ioctls */ ++ while (true) { ++ ++ /* Reset event to FREE. */ ++ qemu_event_reset(&accel_in_ioctl_event); ++ ++ if (accel_has_to_wait()) { ++ /* ++ * If event is still FREE, and there are ioctls still in progress, ++ * wait. ++ * ++ * If an ioctl finishes before qemu_event_wait(), it will change ++ * the event state to SET. This will prevent qemu_event_wait() from ++ * blocking, but it's not a problem because if other ioctls are ++ * still running the loop will iterate once more and reset the event ++ * status to FREE so that it can wait properly. ++ * ++ * If an ioctls finishes while qemu_event_wait() is blocking, then ++ * it will be waken up, but also here the while loop makes sure ++ * to re-enter the wait if there are other running ioctls. ++ */ ++ qemu_event_wait(&accel_in_ioctl_event); ++ } else { ++ /* No ioctl is running */ ++ return; ++ } ++ } ++} ++ ++void accel_ioctl_inhibit_end(void) ++{ ++ CPUState *cpu; ++ ++ qemu_lockcnt_unlock(&accel_in_ioctl_lock); ++ CPU_FOREACH(cpu) { ++ qemu_lockcnt_unlock(&cpu->in_ioctl_lock); ++ } ++} ++ +diff --git a/accel/meson.build b/accel/meson.build +index dfd808d2c8..801b4d44e8 100644 +--- a/accel/meson.build ++++ b/accel/meson.build +@@ -1,4 +1,4 @@ +-specific_ss.add(files('accel-common.c')) ++specific_ss.add(files('accel-common.c', 'accel-blocker.c')) + softmmu_ss.add(files('accel-softmmu.c')) + user_ss.add(files('accel-user.c')) + +diff --git a/hw/core/cpu-common.c b/hw/core/cpu-common.c +index 9e3241b430..b6e83acf0a 100644 +--- a/hw/core/cpu-common.c ++++ b/hw/core/cpu-common.c +@@ -238,6 +238,7 @@ static void cpu_common_initfn(Object *obj) + cpu->nr_threads = 1; + + qemu_mutex_init(&cpu->work_mutex); ++ qemu_lockcnt_init(&cpu->in_ioctl_lock); + QSIMPLEQ_INIT(&cpu->work_list); + QTAILQ_INIT(&cpu->breakpoints); + QTAILQ_INIT(&cpu->watchpoints); +@@ -249,6 +250,7 @@ static void cpu_common_finalize(Object *obj) + { + CPUState *cpu = CPU(obj); + ++ qemu_lockcnt_destroy(&cpu->in_ioctl_lock); + qemu_mutex_destroy(&cpu->work_mutex); + } + +diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h +index e948e81f1a..49d9c73f97 100644 +--- a/include/hw/core/cpu.h ++++ b/include/hw/core/cpu.h +@@ -383,6 +383,9 @@ struct CPUState { + uint32_t kvm_fetch_index; + uint64_t dirty_pages; + ++ /* Use by accel-block: CPU is executing an ioctl() */ ++ QemuLockCnt in_ioctl_lock; ++ + /* Used for events with 'vcpu' and *without* the 'disabled' properties */ + DECLARE_BITMAP(trace_dstate_delayed, CPU_TRACE_DSTATE_MAX_EVENTS); + DECLARE_BITMAP(trace_dstate, CPU_TRACE_DSTATE_MAX_EVENTS); +diff --git a/include/sysemu/accel-blocker.h b/include/sysemu/accel-blocker.h +new file mode 100644 +index 0000000000..72020529ef +--- /dev/null ++++ b/include/sysemu/accel-blocker.h +@@ -0,0 +1,56 @@ ++/* ++ * Accelerator blocking API, to prevent new ioctls from starting and wait the ++ * running ones finish. ++ * This mechanism differs from pause/resume_all_vcpus() in that it does not ++ * release the BQL. ++ * ++ * Copyright (c) 2022 Red Hat Inc. ++ * ++ * Author: Emanuele Giuseppe Esposito ++ * ++ * This work is licensed under the terms of the GNU GPL, version 2 or later. ++ * See the COPYING file in the top-level directory. ++ */ ++#ifndef ACCEL_BLOCKER_H ++#define ACCEL_BLOCKER_H ++ ++#include "qemu/osdep.h" ++#include "sysemu/cpus.h" ++ ++extern void accel_blocker_init(void); ++ ++/* ++ * accel_{cpu_}ioctl_begin/end: ++ * Mark when ioctl is about to run or just finished. ++ * ++ * accel_{cpu_}ioctl_begin will block after accel_ioctl_inhibit_begin() is ++ * called, preventing new ioctls to run. They will continue only after ++ * accel_ioctl_inibith_end(). ++ */ ++extern void accel_ioctl_begin(void); ++extern void accel_ioctl_end(void); ++extern void accel_cpu_ioctl_begin(CPUState *cpu); ++extern void accel_cpu_ioctl_end(CPUState *cpu); ++ ++/* ++ * accel_ioctl_inhibit_begin: start critical section ++ * ++ * This function makes sure that: ++ * 1) incoming accel_{cpu_}ioctl_begin() calls block ++ * 2) wait that all ioctls that were already running reach ++ * accel_{cpu_}ioctl_end(), kicking vcpus if necessary. ++ * ++ * This allows the caller to access shared data or perform operations without ++ * worrying of concurrent vcpus accesses. ++ */ ++extern void accel_ioctl_inhibit_begin(void); ++ ++/* ++ * accel_ioctl_inhibit_end: end critical section started by ++ * accel_ioctl_inhibit_begin() ++ * ++ * This function allows blocked accel_{cpu_}ioctl_begin() to continue. ++ */ ++extern void accel_ioctl_inhibit_end(void); ++ ++#endif /* ACCEL_BLOCKER_H */ +diff --git a/util/meson.build b/util/meson.build +index 05b593055a..b5f153b0e8 100644 +--- a/util/meson.build ++++ b/util/meson.build +@@ -48,6 +48,7 @@ util_ss.add(files('transactions.c')) + util_ss.add(when: 'CONFIG_POSIX', if_true: files('drm.c')) + util_ss.add(files('guest-random.c')) + util_ss.add(files('yank.c')) ++util_ss.add(files('lockcnt.c')) + + if have_user + util_ss.add(files('selfmap.c')) +@@ -69,7 +70,6 @@ if have_block + util_ss.add(files('hexdump.c')) + util_ss.add(files('iova-tree.c')) + util_ss.add(files('iov.c', 'qemu-sockets.c', 'uri.c')) +- util_ss.add(files('lockcnt.c')) + util_ss.add(files('main-loop.c')) + util_ss.add(files('nvdimm-utils.c')) + util_ss.add(files('qemu-coroutine.c', 'qemu-coroutine-lock.c', 'qemu-coroutine-io.c')) +-- +2.37.3 + diff --git a/kvm-aio-wait-switch-to-smp_mb__after_rmw.patch b/kvm-aio-wait-switch-to-smp_mb__after_rmw.patch new file mode 100644 index 0000000..e3b79cf --- /dev/null +++ b/kvm-aio-wait-switch-to-smp_mb__after_rmw.patch @@ -0,0 +1,50 @@ +From 953c5c0982b61b0a3f8f03452844b5487eb22fc7 Mon Sep 17 00:00:00 2001 +From: Emanuele Giuseppe Esposito +Date: Thu, 9 Mar 2023 08:13:17 -0500 +Subject: [PATCH 06/13] aio-wait: switch to smp_mb__after_rmw() + +RH-Author: Emanuele Giuseppe Esposito +RH-MergeRequest: 263: qatomic: add smp_mb__before/after_rmw() +RH-Bugzilla: 2168472 +RH-Acked-by: Cornelia Huck +RH-Acked-by: Eric Auger +RH-Acked-by: Paolo Bonzini +RH-Acked-by: David Hildenbrand +RH-Commit: [6/10] 9f30f97754139ffd18d36b2350f9ed4e59ac496e + +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2168472 + +commit b532526a07ef3b903ead2e055fe6cc87b41057a3 +Author: Paolo Bonzini +Date: Fri Mar 3 11:03:52 2023 +0100 + + aio-wait: switch to smp_mb__after_rmw() + + The barrier comes after an atomic increment, so it is enough to use + smp_mb__after_rmw(); this avoids a double barrier on x86 systems. + + Reviewed-by: Richard Henderson + Reviewed-by: David Hildenbrand + Signed-off-by: Paolo Bonzini + +Signed-off-by: Emanuele Giuseppe Esposito +--- + include/block/aio-wait.h | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/include/block/aio-wait.h b/include/block/aio-wait.h +index 54840f8622..03b6394c78 100644 +--- a/include/block/aio-wait.h ++++ b/include/block/aio-wait.h +@@ -82,7 +82,7 @@ extern AioWait global_aio_wait; + /* Increment wait_->num_waiters before evaluating cond. */ \ + qatomic_inc(&wait_->num_waiters); \ + /* Paired with smp_mb in aio_wait_kick(). */ \ +- smp_mb(); \ ++ smp_mb__after_rmw(); \ + if (ctx_ && in_aio_context_home_thread(ctx_)) { \ + while ((cond)) { \ + aio_poll(ctx_, true); \ +-- +2.37.3 + diff --git a/kvm-aio_wait_kick-add-missing-memory-barrier.patch b/kvm-aio_wait_kick-add-missing-memory-barrier.patch new file mode 100644 index 0000000..9a9ae00 --- /dev/null +++ b/kvm-aio_wait_kick-add-missing-memory-barrier.patch @@ -0,0 +1,86 @@ +From d7eae0ff4c7f7f7bf10f10272adf7c6971c0db9b Mon Sep 17 00:00:00 2001 +From: Emanuele Giuseppe Esposito +Date: Thu, 9 Mar 2023 09:26:35 -0500 +Subject: [PATCH 01/13] aio_wait_kick: add missing memory barrier + +RH-Author: Emanuele Giuseppe Esposito +RH-MergeRequest: 263: qatomic: add smp_mb__before/after_rmw() +RH-Bugzilla: 2168472 +RH-Acked-by: Cornelia Huck +RH-Acked-by: Eric Auger +RH-Acked-by: Paolo Bonzini +RH-Acked-by: David Hildenbrand +RH-Commit: [1/10] eb774aee79864052e14e706d931e52e7bd1162c8 + +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2168472 + +commit 7455ff1aa01564cc175db5b2373e610503ad4411 +Author: Emanuele Giuseppe Esposito +Date: Tue May 24 13:30:54 2022 -0400 + + aio_wait_kick: add missing memory barrier + + It seems that aio_wait_kick always required a memory barrier + or atomic operation in the caller, but nobody actually + took care of doing it. + + Let's put the barrier in the function instead, and pair it + with another one in AIO_WAIT_WHILE. Read aio_wait_kick() + comment for further explanation. + + Suggested-by: Paolo Bonzini + Signed-off-by: Emanuele Giuseppe Esposito + Message-Id: <20220524173054.12651-1-eesposit@redhat.com> + Reviewed-by: Vladimir Sementsov-Ogievskiy + Reviewed-by: Stefan Hajnoczi + Signed-off-by: Kevin Wolf + +Signed-off-by: Emanuele Giuseppe Esposito +--- + include/block/aio-wait.h | 2 ++ + util/aio-wait.c | 16 +++++++++++++++- + 2 files changed, 17 insertions(+), 1 deletion(-) + +diff --git a/include/block/aio-wait.h b/include/block/aio-wait.h +index b39eefb38d..54840f8622 100644 +--- a/include/block/aio-wait.h ++++ b/include/block/aio-wait.h +@@ -81,6 +81,8 @@ extern AioWait global_aio_wait; + AioContext *ctx_ = (ctx); \ + /* Increment wait_->num_waiters before evaluating cond. */ \ + qatomic_inc(&wait_->num_waiters); \ ++ /* Paired with smp_mb in aio_wait_kick(). */ \ ++ smp_mb(); \ + if (ctx_ && in_aio_context_home_thread(ctx_)) { \ + while ((cond)) { \ + aio_poll(ctx_, true); \ +diff --git a/util/aio-wait.c b/util/aio-wait.c +index bdb3d3af22..98c5accd29 100644 +--- a/util/aio-wait.c ++++ b/util/aio-wait.c +@@ -35,7 +35,21 @@ static void dummy_bh_cb(void *opaque) + + void aio_wait_kick(void) + { +- /* The barrier (or an atomic op) is in the caller. */ ++ /* ++ * Paired with smp_mb in AIO_WAIT_WHILE. Here we have: ++ * write(condition); ++ * aio_wait_kick() { ++ * smp_mb(); ++ * read(num_waiters); ++ * } ++ * ++ * And in AIO_WAIT_WHILE: ++ * write(num_waiters); ++ * smp_mb(); ++ * read(condition); ++ */ ++ smp_mb(); ++ + if (qatomic_read(&global_aio_wait.num_waiters)) { + aio_bh_schedule_oneshot(qemu_get_aio_context(), dummy_bh_cb, NULL); + } +-- +2.37.3 + diff --git a/kvm-async-clarify-usage-of-barriers-in-the-polling-case.patch b/kvm-async-clarify-usage-of-barriers-in-the-polling-case.patch new file mode 100644 index 0000000..5338a8d --- /dev/null +++ b/kvm-async-clarify-usage-of-barriers-in-the-polling-case.patch @@ -0,0 +1,66 @@ +From 187eb7a418af93375e42298d06e231e2bec3cf00 Mon Sep 17 00:00:00 2001 +From: Emanuele Giuseppe Esposito +Date: Thu, 9 Mar 2023 08:15:42 -0500 +Subject: [PATCH 10/13] async: clarify usage of barriers in the polling case + +RH-Author: Emanuele Giuseppe Esposito +RH-MergeRequest: 263: qatomic: add smp_mb__before/after_rmw() +RH-Bugzilla: 2168472 +RH-Acked-by: Cornelia Huck +RH-Acked-by: Eric Auger +RH-Acked-by: Paolo Bonzini +RH-Acked-by: David Hildenbrand +RH-Commit: [10/10] 3be07ccc6137a0336becfe63a818d9cbadb38e9c + +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2168472 + +commit 6229438cca037d42f44a96d38feb15cb102a444f +Author: Paolo Bonzini +Date: Mon Mar 6 10:43:52 2023 +0100 + + async: clarify usage of barriers in the polling case + + Explain that aio_context_notifier_poll() relies on + aio_notify_accept() to catch all the memory writes that were + done before ctx->notified was set to true. + + Reviewed-by: Richard Henderson + Reviewed-by: Stefan Hajnoczi + Signed-off-by: Paolo Bonzini + +Signed-off-by: Emanuele Giuseppe Esposito +--- + util/async.c | 10 ++++++++-- + 1 file changed, 8 insertions(+), 2 deletions(-) + +diff --git a/util/async.c b/util/async.c +index 795fe699b6..2a63bf90f2 100644 +--- a/util/async.c ++++ b/util/async.c +@@ -463,8 +463,9 @@ void aio_notify_accept(AioContext *ctx) + qatomic_set(&ctx->notified, false); + + /* +- * Write ctx->notified before reading e.g. bh->flags. Pairs with smp_wmb +- * in aio_notify. ++ * Order reads of ctx->notified (in aio_context_notifier_poll()) and the ++ * above clearing of ctx->notified before reads of e.g. bh->flags. Pairs ++ * with smp_wmb() in aio_notify. + */ + smp_mb(); + } +@@ -487,6 +488,11 @@ static bool aio_context_notifier_poll(void *opaque) + EventNotifier *e = opaque; + AioContext *ctx = container_of(e, AioContext, notifier); + ++ /* ++ * No need for load-acquire because we just want to kick the ++ * event loop. aio_notify_accept() takes care of synchronizing ++ * the event loop with the producers. ++ */ + return qatomic_read(&ctx->notified); + } + +-- +2.37.3 + diff --git a/kvm-async-update-documentation-of-the-memory-barriers.patch b/kvm-async-update-documentation-of-the-memory-barriers.patch new file mode 100644 index 0000000..aea20ea --- /dev/null +++ b/kvm-async-update-documentation-of-the-memory-barriers.patch @@ -0,0 +1,111 @@ +From ea3856bb545d19499602830cdc3076d83a981e7a Mon Sep 17 00:00:00 2001 +From: Emanuele Giuseppe Esposito +Date: Thu, 9 Mar 2023 08:15:36 -0500 +Subject: [PATCH 09/13] async: update documentation of the memory barriers + +RH-Author: Emanuele Giuseppe Esposito +RH-MergeRequest: 263: qatomic: add smp_mb__before/after_rmw() +RH-Bugzilla: 2168472 +RH-Acked-by: Cornelia Huck +RH-Acked-by: Eric Auger +RH-Acked-by: Paolo Bonzini +RH-Acked-by: David Hildenbrand +RH-Commit: [9/10] d471da2acf7a107cf75f3327c5e8d7456307160e + +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2168472 + +commit 8dd48650b43dfde4ebea34191ac267e474bcc29e +Author: Paolo Bonzini +Date: Mon Mar 6 10:15:06 2023 +0100 + + async: update documentation of the memory barriers + + Ever since commit 8c6b0356b539 ("util/async: make bh_aio_poll() O(1)", + 2020-02-22), synchronization between qemu_bh_schedule() and aio_bh_poll() + is happening when the bottom half is enqueued in the bh_list; not + when the flags are set. Update the documentation to match. + + Reviewed-by: Stefan Hajnoczi + Signed-off-by: Paolo Bonzini + +Signed-off-by: Emanuele Giuseppe Esposito +--- + util/async.c | 33 +++++++++++++++++++-------------- + 1 file changed, 19 insertions(+), 14 deletions(-) + +diff --git a/util/async.c b/util/async.c +index 6f6717a34b..795fe699b6 100644 +--- a/util/async.c ++++ b/util/async.c +@@ -71,14 +71,21 @@ static void aio_bh_enqueue(QEMUBH *bh, unsigned new_flags) + unsigned old_flags; + + /* +- * The memory barrier implicit in qatomic_fetch_or makes sure that: +- * 1. idle & any writes needed by the callback are done before the +- * locations are read in the aio_bh_poll. +- * 2. ctx is loaded before the callback has a chance to execute and bh +- * could be freed. ++ * Synchronizes with atomic_fetch_and() in aio_bh_dequeue(), ensuring that ++ * insertion starts after BH_PENDING is set. + */ + old_flags = qatomic_fetch_or(&bh->flags, BH_PENDING | new_flags); ++ + if (!(old_flags & BH_PENDING)) { ++ /* ++ * At this point the bottom half becomes visible to aio_bh_poll(). ++ * This insertion thus synchronizes with QSLIST_MOVE_ATOMIC in ++ * aio_bh_poll(), ensuring that: ++ * 1. any writes needed by the callback are visible from the callback ++ * after aio_bh_dequeue() returns bh. ++ * 2. ctx is loaded before the callback has a chance to execute and bh ++ * could be freed. ++ */ + QSLIST_INSERT_HEAD_ATOMIC(&ctx->bh_list, bh, next); + } + +@@ -97,11 +104,8 @@ static QEMUBH *aio_bh_dequeue(BHList *head, unsigned *flags) + QSLIST_REMOVE_HEAD(head, next); + + /* +- * The qatomic_and is paired with aio_bh_enqueue(). The implicit memory +- * barrier ensures that the callback sees all writes done by the scheduling +- * thread. It also ensures that the scheduling thread sees the cleared +- * flag before bh->cb has run, and thus will call aio_notify again if +- * necessary. ++ * Synchronizes with qatomic_fetch_or() in aio_bh_enqueue(), ensuring that ++ * the removal finishes before BH_PENDING is reset. + */ + *flags = qatomic_fetch_and(&bh->flags, + ~(BH_PENDING | BH_SCHEDULED | BH_IDLE)); +@@ -148,6 +152,7 @@ int aio_bh_poll(AioContext *ctx) + BHListSlice *s; + int ret = 0; + ++ /* Synchronizes with QSLIST_INSERT_HEAD_ATOMIC in aio_bh_enqueue(). */ + QSLIST_MOVE_ATOMIC(&slice.bh_list, &ctx->bh_list); + QSIMPLEQ_INSERT_TAIL(&ctx->bh_slice_list, &slice, next); + +@@ -437,15 +442,15 @@ LuringState *aio_get_linux_io_uring(AioContext *ctx) + void aio_notify(AioContext *ctx) + { + /* +- * Write e.g. bh->flags before writing ctx->notified. Pairs with smp_mb in +- * aio_notify_accept. ++ * Write e.g. ctx->bh_list before writing ctx->notified. Pairs with ++ * smp_mb() in aio_notify_accept(). + */ + smp_wmb(); + qatomic_set(&ctx->notified, true); + + /* +- * Write ctx->notified before reading ctx->notify_me. Pairs +- * with smp_mb in aio_ctx_prepare or aio_poll. ++ * Write ctx->notified (and also ctx->bh_list) before reading ctx->notify_me. ++ * Pairs with smp_mb() in aio_ctx_prepare or aio_poll. + */ + smp_mb(); + if (qatomic_read(&ctx->notify_me)) { +-- +2.37.3 + diff --git a/kvm-block-mirror-Do-not-wait-for-active-writes.patch b/kvm-block-mirror-Do-not-wait-for-active-writes.patch new file mode 100644 index 0000000..1756d88 --- /dev/null +++ b/kvm-block-mirror-Do-not-wait-for-active-writes.patch @@ -0,0 +1,153 @@ +From 192f956f2b0761f270070555f8feb1f0544e5558 Mon Sep 17 00:00:00 2001 +From: Hanna Reitz +Date: Wed, 9 Nov 2022 17:54:48 +0100 +Subject: [PATCH 01/11] block/mirror: Do not wait for active writes + +RH-Author: Hanna Czenczek +RH-MergeRequest: 246: block/mirror: Make active mirror progress even under full load +RH-Bugzilla: 2125119 +RH-Acked-by: Emanuele Giuseppe Esposito +RH-Acked-by: Stefan Hajnoczi +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Kevin Wolf +RH-Commit: [1/3] 652d1e55b954f13eaec2c86f58735d4942837e16 + +Waiting for all active writes to settle before daring to create a +background copying operation means that we will never do background +operations while the guest does anything (in write-blocking mode), and +therefore cannot converge. Yes, we also will not diverge, but actually +converging would be even nicer. + +It is unclear why we did decide to wait for all active writes to settle +before creating a background operation, but it just does not seem +necessary. Active writes will put themselves into the in_flight bitmap +and thus properly block actually conflicting background requests. + +It is important for active requests to wait on overlapping background +requests, which we do in active_write_prepare(). However, so far it was +not documented why it is important. Add such documentation now, and +also to the other call of mirror_wait_on_conflicts(), so that it becomes +more clear why and when requests need to actively wait for other +requests to settle. + +Another thing to note is that of course we need to ensure that there are +no active requests when the job completes, but that is done by virtue of +the BDS being drained anyway, so there cannot be any active requests at +that point. + +With this change, we will need to explicitly keep track of how many +bytes are in flight in active requests so that +job_progress_set_remaining() in mirror_run() can set the correct number +of remaining bytes. + +Buglink: https://bugzilla.redhat.com/show_bug.cgi?id=2123297 +Signed-off-by: Hanna Reitz +Message-Id: <20221109165452.67927-2-hreitz@redhat.com> +Reviewed-by: Kevin Wolf +Signed-off-by: Kevin Wolf +(cherry picked from commit d69a879bdf1aed586478eaa161ee064fe1b92f1a) +Signed-off-by: Hanna Czenczek +--- + block/mirror.c | 37 ++++++++++++++++++++++++++++++------- + 1 file changed, 30 insertions(+), 7 deletions(-) + +diff --git a/block/mirror.c b/block/mirror.c +index efec2c7674..282f428cb7 100644 +--- a/block/mirror.c ++++ b/block/mirror.c +@@ -81,6 +81,7 @@ typedef struct MirrorBlockJob { + int max_iov; + bool initial_zeroing_ongoing; + int in_active_write_counter; ++ int64_t active_write_bytes_in_flight; + bool prepared; + bool in_drain; + } MirrorBlockJob; +@@ -493,6 +494,13 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s) + } + bdrv_dirty_bitmap_unlock(s->dirty_bitmap); + ++ /* ++ * Wait for concurrent requests to @offset. The next loop will limit the ++ * copied area based on in_flight_bitmap so we only copy an area that does ++ * not overlap with concurrent in-flight requests. Still, we would like to ++ * copy something, so wait until there are at least no more requests to the ++ * very beginning of the area. ++ */ + mirror_wait_on_conflicts(NULL, s, offset, 1); + + job_pause_point(&s->common.job); +@@ -993,12 +1001,6 @@ static int coroutine_fn mirror_run(Job *job, Error **errp) + int64_t cnt, delta; + bool should_complete; + +- /* Do not start passive operations while there are active +- * writes in progress */ +- while (s->in_active_write_counter) { +- mirror_wait_for_any_operation(s, true); +- } +- + if (s->ret < 0) { + ret = s->ret; + goto immediate_exit; +@@ -1015,7 +1017,9 @@ static int coroutine_fn mirror_run(Job *job, Error **errp) + /* cnt is the number of dirty bytes remaining and s->bytes_in_flight is + * the number of bytes currently being processed; together those are + * the current remaining operation length */ +- job_progress_set_remaining(&s->common.job, s->bytes_in_flight + cnt); ++ job_progress_set_remaining(&s->common.job, ++ s->bytes_in_flight + cnt + ++ s->active_write_bytes_in_flight); + + /* Note that even when no rate limit is applied we need to yield + * periodically with no pending I/O so that bdrv_drain_all() returns. +@@ -1073,6 +1077,10 @@ static int coroutine_fn mirror_run(Job *job, Error **errp) + + s->in_drain = true; + bdrv_drained_begin(bs); ++ ++ /* Must be zero because we are drained */ ++ assert(s->in_active_write_counter == 0); ++ + cnt = bdrv_get_dirty_count(s->dirty_bitmap); + if (cnt > 0 || mirror_flush(s) < 0) { + bdrv_drained_end(bs); +@@ -1306,6 +1314,7 @@ do_sync_target_write(MirrorBlockJob *job, MirrorMethod method, + } + + job_progress_increase_remaining(&job->common.job, bytes); ++ job->active_write_bytes_in_flight += bytes; + + switch (method) { + case MIRROR_METHOD_COPY: +@@ -1327,6 +1336,7 @@ do_sync_target_write(MirrorBlockJob *job, MirrorMethod method, + abort(); + } + ++ job->active_write_bytes_in_flight -= bytes; + if (ret >= 0) { + job_progress_update(&job->common.job, bytes); + } else { +@@ -1375,6 +1385,19 @@ static MirrorOp *coroutine_fn active_write_prepare(MirrorBlockJob *s, + + s->in_active_write_counter++; + ++ /* ++ * Wait for concurrent requests affecting the area. If there are already ++ * running requests that are copying off now-to-be stale data in the area, ++ * we must wait for them to finish before we begin writing fresh data to the ++ * target so that the write operations appear in the correct order. ++ * Note that background requests (see mirror_iteration()) in contrast only ++ * wait for conflicting requests at the start of the dirty area, and then ++ * (based on the in_flight_bitmap) truncate the area to copy so it will not ++ * conflict with any requests beyond that. For active writes, however, we ++ * cannot truncate that area. The request from our parent must be blocked ++ * until the area is copied in full. Therefore, we must wait for the whole ++ * area to become free of concurrent requests. ++ */ + mirror_wait_on_conflicts(op, s, offset, bytes); + + bitmap_set(s->in_flight_bitmap, start_chunk, end_chunk - start_chunk); +-- +2.37.3 + diff --git a/kvm-block-mirror-Drop-mirror_wait_for_any_operation.patch b/kvm-block-mirror-Drop-mirror_wait_for_any_operation.patch new file mode 100644 index 0000000..457788e --- /dev/null +++ b/kvm-block-mirror-Drop-mirror_wait_for_any_operation.patch @@ -0,0 +1,76 @@ +From 57c79ed20cb73aa9aa4dd7487379b85ea3f936f6 Mon Sep 17 00:00:00 2001 +From: Hanna Reitz +Date: Wed, 9 Nov 2022 17:54:49 +0100 +Subject: [PATCH 02/11] block/mirror: Drop mirror_wait_for_any_operation() + +RH-Author: Hanna Czenczek +RH-MergeRequest: 246: block/mirror: Make active mirror progress even under full load +RH-Bugzilla: 2125119 +RH-Acked-by: Emanuele Giuseppe Esposito +RH-Acked-by: Stefan Hajnoczi +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Kevin Wolf +RH-Commit: [2/3] dec37883bcc491441ae08d9592d1ec26a47765c0 + +mirror_wait_for_free_in_flight_slot() is the only remaining user of +mirror_wait_for_any_operation(), so inline the latter into the former. + +Signed-off-by: Hanna Reitz +Message-Id: <20221109165452.67927-3-hreitz@redhat.com> +Reviewed-by: Kevin Wolf +Signed-off-by: Kevin Wolf +(cherry picked from commit eb994912993077f178ccb43b20e422ecf9ae4ac7) +Signed-off-by: Hanna Czenczek +--- + block/mirror.c | 21 ++++++++------------- + 1 file changed, 8 insertions(+), 13 deletions(-) + +diff --git a/block/mirror.c b/block/mirror.c +index 282f428cb7..6b02555ad7 100644 +--- a/block/mirror.c ++++ b/block/mirror.c +@@ -304,19 +304,21 @@ static int mirror_cow_align(MirrorBlockJob *s, int64_t *offset, + } + + static inline void coroutine_fn +-mirror_wait_for_any_operation(MirrorBlockJob *s, bool active) ++mirror_wait_for_free_in_flight_slot(MirrorBlockJob *s) + { + MirrorOp *op; + + QTAILQ_FOREACH(op, &s->ops_in_flight, next) { +- /* Do not wait on pseudo ops, because it may in turn wait on ++ /* ++ * Do not wait on pseudo ops, because it may in turn wait on + * some other operation to start, which may in fact be the + * caller of this function. Since there is only one pseudo op + * at any given time, we will always find some real operation +- * to wait on. */ +- if (!op->is_pseudo_op && op->is_in_flight && +- op->is_active_write == active) +- { ++ * to wait on. ++ * Also, do not wait on active operations, because they do not ++ * use up in-flight slots. ++ */ ++ if (!op->is_pseudo_op && op->is_in_flight && !op->is_active_write) { + qemu_co_queue_wait(&op->waiting_requests, NULL); + return; + } +@@ -324,13 +326,6 @@ mirror_wait_for_any_operation(MirrorBlockJob *s, bool active) + abort(); + } + +-static inline void coroutine_fn +-mirror_wait_for_free_in_flight_slot(MirrorBlockJob *s) +-{ +- /* Only non-active operations use up in-flight slots */ +- mirror_wait_for_any_operation(s, false); +-} +- + /* Perform a mirror copy operation. + * + * *op->bytes_handled is set to the number of bytes copied after and +-- +2.37.3 + diff --git a/kvm-block-mirror-Fix-NULL-s-job-in-active-writes.patch b/kvm-block-mirror-Fix-NULL-s-job-in-active-writes.patch new file mode 100644 index 0000000..b353bd1 --- /dev/null +++ b/kvm-block-mirror-Fix-NULL-s-job-in-active-writes.patch @@ -0,0 +1,75 @@ +From b1f5aa5a342a25dc558ee9d435fed0643fe5155f Mon Sep 17 00:00:00 2001 +From: Hanna Reitz +Date: Wed, 9 Nov 2022 17:54:50 +0100 +Subject: [PATCH 03/11] block/mirror: Fix NULL s->job in active writes + +RH-Author: Hanna Czenczek +RH-MergeRequest: 246: block/mirror: Make active mirror progress even under full load +RH-Bugzilla: 2125119 +RH-Acked-by: Emanuele Giuseppe Esposito +RH-Acked-by: Stefan Hajnoczi +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Kevin Wolf +RH-Commit: [3/3] 49d7ebd15667151a6e14228a8260cfdd0aa27a78 + +There is a small gap in mirror_start_job() before putting the mirror +filter node into the block graph (bdrv_append() call) and the actual job +being created. Before the job is created, MirrorBDSOpaque.job is NULL. + +It is possible that requests come in when bdrv_drained_end() is called, +and those requests would see MirrorBDSOpaque.job == NULL. Have our +filter node handle that case gracefully. + +Signed-off-by: Hanna Reitz +Message-Id: <20221109165452.67927-4-hreitz@redhat.com> +Reviewed-by: Kevin Wolf +Signed-off-by: Kevin Wolf +(cherry picked from commit da93d5c84e56e6b4e84aa8e98b6b984c9b6bb528) +Signed-off-by: Hanna Czenczek +--- + block/mirror.c | 20 ++++++++++++-------- + 1 file changed, 12 insertions(+), 8 deletions(-) + +diff --git a/block/mirror.c b/block/mirror.c +index 6b02555ad7..50289fca49 100644 +--- a/block/mirror.c ++++ b/block/mirror.c +@@ -1438,11 +1438,13 @@ static int coroutine_fn bdrv_mirror_top_do_write(BlockDriverState *bs, + MirrorOp *op = NULL; + MirrorBDSOpaque *s = bs->opaque; + int ret = 0; +- bool copy_to_target; ++ bool copy_to_target = false; + +- copy_to_target = s->job->ret >= 0 && +- !job_is_cancelled(&s->job->common.job) && +- s->job->copy_mode == MIRROR_COPY_MODE_WRITE_BLOCKING; ++ if (s->job) { ++ copy_to_target = s->job->ret >= 0 && ++ !job_is_cancelled(&s->job->common.job) && ++ s->job->copy_mode == MIRROR_COPY_MODE_WRITE_BLOCKING; ++ } + + if (copy_to_target) { + op = active_write_prepare(s->job, offset, bytes); +@@ -1487,11 +1489,13 @@ static int coroutine_fn bdrv_mirror_top_pwritev(BlockDriverState *bs, + QEMUIOVector bounce_qiov; + void *bounce_buf; + int ret = 0; +- bool copy_to_target; ++ bool copy_to_target = false; + +- copy_to_target = s->job->ret >= 0 && +- !job_is_cancelled(&s->job->common.job) && +- s->job->copy_mode == MIRROR_COPY_MODE_WRITE_BLOCKING; ++ if (s->job) { ++ copy_to_target = s->job->ret >= 0 && ++ !job_is_cancelled(&s->job->common.job) && ++ s->job->copy_mode == MIRROR_COPY_MODE_WRITE_BLOCKING; ++ } + + if (copy_to_target) { + /* The guest might concurrently modify the data to write; but +-- +2.37.3 + diff --git a/kvm-configs-devices-aarch64-softmmu-Enable-CONFIG_VIRTIO.patch b/kvm-configs-devices-aarch64-softmmu-Enable-CONFIG_VIRTIO.patch deleted file mode 100644 index a948e57..0000000 --- a/kvm-configs-devices-aarch64-softmmu-Enable-CONFIG_VIRTIO.patch +++ /dev/null @@ -1,41 +0,0 @@ -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/kvm-coroutine-Rename-qemu_coroutine_inc-dec_pool_size.patch b/kvm-coroutine-Rename-qemu_coroutine_inc-dec_pool_size.patch deleted file mode 100644 index c1f3683..0000000 --- a/kvm-coroutine-Rename-qemu_coroutine_inc-dec_pool_size.patch +++ /dev/null @@ -1,101 +0,0 @@ -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/kvm-coroutine-Revert-to-constant-batch-size.patch b/kvm-coroutine-Revert-to-constant-batch-size.patch deleted file mode 100644 index 2973510..0000000 --- a/kvm-coroutine-Revert-to-constant-batch-size.patch +++ /dev/null @@ -1,138 +0,0 @@ -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/kvm-coroutine-ucontext-use-QEMU_DEFINE_STATIC_CO_TLS.patch b/kvm-coroutine-ucontext-use-QEMU_DEFINE_STATIC_CO_TLS.patch deleted file mode 100644 index 963cf04..0000000 --- a/kvm-coroutine-ucontext-use-QEMU_DEFINE_STATIC_CO_TLS.patch +++ /dev/null @@ -1,132 +0,0 @@ -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/kvm-coroutine-use-QEMU_DEFINE_STATIC_CO_TLS.patch b/kvm-coroutine-use-QEMU_DEFINE_STATIC_CO_TLS.patch deleted file mode 100644 index 9d0f811..0000000 --- a/kvm-coroutine-use-QEMU_DEFINE_STATIC_CO_TLS.patch +++ /dev/null @@ -1,139 +0,0 @@ -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/kvm-coroutine-win32-use-QEMU_DEFINE_STATIC_CO_TLS.patch b/kvm-coroutine-win32-use-QEMU_DEFINE_STATIC_CO_TLS.patch deleted file mode 100644 index 1665319..0000000 --- a/kvm-coroutine-win32-use-QEMU_DEFINE_STATIC_CO_TLS.patch +++ /dev/null @@ -1,99 +0,0 @@ -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/kvm-dma-helpers-prevent-dma_blk_cb-vs-dma_aio_cancel-rac.patch b/kvm-dma-helpers-prevent-dma_blk_cb-vs-dma_aio_cancel-rac.patch new file mode 100644 index 0000000..4be5d14 --- /dev/null +++ b/kvm-dma-helpers-prevent-dma_blk_cb-vs-dma_aio_cancel-rac.patch @@ -0,0 +1,127 @@ +From 103608465b8bd2edf7f9aaef5c3c93309ccf9ec2 Mon Sep 17 00:00:00 2001 +From: Stefan Hajnoczi +Date: Tue, 21 Feb 2023 16:22:17 -0500 +Subject: [PATCH 12/13] dma-helpers: prevent dma_blk_cb() vs dma_aio_cancel() + race + +RH-Author: Stefan Hajnoczi +RH-MergeRequest: 264: scsi: protect req->aiocb with AioContext lock +RH-Bugzilla: 2090990 +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Kevin Wolf +RH-Commit: [2/3] 14f5835093ba8c5111f3ada2fe87730371aca733 + +dma_blk_cb() only takes the AioContext lock around ->io_func(). That +means the rest of dma_blk_cb() is not protected. In particular, the +DMAAIOCB field accesses happen outside the lock. + +There is a race when the main loop thread holds the AioContext lock and +invokes scsi_device_purge_requests() -> bdrv_aio_cancel() -> +dma_aio_cancel() while an IOThread executes dma_blk_cb(). The dbs->acb +field determines how cancellation proceeds. If dma_aio_cancel() sees +dbs->acb == NULL while dma_blk_cb() is still running, the request can be +completed twice (-ECANCELED and the actual return value). + +The following assertion can occur with virtio-scsi when an IOThread is +used: + + ../hw/scsi/scsi-disk.c:368: scsi_dma_complete: Assertion `r->req.aiocb != NULL' failed. + +Fix the race by holding the AioContext across dma_blk_cb(). Now +dma_aio_cancel() under the AioContext lock will not see +inconsistent/intermediate states. + +Cc: Paolo Bonzini +Reviewed-by: Eric Blake +Signed-off-by: Stefan Hajnoczi +Message-Id: <20230221212218.1378734-3-stefanha@redhat.com> +Signed-off-by: Kevin Wolf +(cherry picked from commit abfcd2760b3e70727bbc0792221b8b98a733dc32) +Signed-off-by: Stefan Hajnoczi +--- + hw/scsi/scsi-disk.c | 4 +--- + softmmu/dma-helpers.c | 12 +++++++----- + 2 files changed, 8 insertions(+), 8 deletions(-) + +diff --git a/hw/scsi/scsi-disk.c b/hw/scsi/scsi-disk.c +index 179ce22c4a..c8109a673e 100644 +--- a/hw/scsi/scsi-disk.c ++++ b/hw/scsi/scsi-disk.c +@@ -351,13 +351,12 @@ done: + scsi_req_unref(&r->req); + } + ++/* Called with AioContext lock held */ + static void scsi_dma_complete(void *opaque, int ret) + { + SCSIDiskReq *r = (SCSIDiskReq *)opaque; + SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, r->req.dev); + +- aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk)); +- + assert(r->req.aiocb != NULL); + r->req.aiocb = NULL; + +@@ -367,7 +366,6 @@ static void scsi_dma_complete(void *opaque, int ret) + block_acct_done(blk_get_stats(s->qdev.conf.blk), &r->acct); + } + scsi_dma_complete_noio(r, ret); +- aio_context_release(blk_get_aio_context(s->qdev.conf.blk)); + } + + static void scsi_read_complete_noio(SCSIDiskReq *r, int ret) +diff --git a/softmmu/dma-helpers.c b/softmmu/dma-helpers.c +index 7d766a5e89..42af18719a 100644 +--- a/softmmu/dma-helpers.c ++++ b/softmmu/dma-helpers.c +@@ -127,17 +127,19 @@ static void dma_complete(DMAAIOCB *dbs, int ret) + static void dma_blk_cb(void *opaque, int ret) + { + DMAAIOCB *dbs = (DMAAIOCB *)opaque; ++ AioContext *ctx = dbs->ctx; + dma_addr_t cur_addr, cur_len; + void *mem; + + trace_dma_blk_cb(dbs, ret); + ++ aio_context_acquire(ctx); + dbs->acb = NULL; + dbs->offset += dbs->iov.size; + + if (dbs->sg_cur_index == dbs->sg->nsg || ret < 0) { + dma_complete(dbs, ret); +- return; ++ goto out; + } + dma_blk_unmap(dbs); + +@@ -177,9 +179,9 @@ static void dma_blk_cb(void *opaque, int ret) + + if (dbs->iov.size == 0) { + trace_dma_map_wait(dbs); +- dbs->bh = aio_bh_new(dbs->ctx, reschedule_dma, dbs); ++ dbs->bh = aio_bh_new(ctx, reschedule_dma, dbs); + cpu_register_map_client(dbs->bh); +- return; ++ goto out; + } + + if (!QEMU_IS_ALIGNED(dbs->iov.size, dbs->align)) { +@@ -187,11 +189,11 @@ static void dma_blk_cb(void *opaque, int ret) + QEMU_ALIGN_DOWN(dbs->iov.size, dbs->align)); + } + +- aio_context_acquire(dbs->ctx); + dbs->acb = dbs->io_func(dbs->offset, &dbs->iov, + dma_blk_cb, dbs, dbs->io_func_opaque); +- aio_context_release(dbs->ctx); + assert(dbs->acb); ++out: ++ aio_context_release(ctx); + } + + static void dma_aio_cancel(BlockAIOCB *acb) +-- +2.37.3 + diff --git a/kvm-edu-add-smp_mb__after_rmw.patch b/kvm-edu-add-smp_mb__after_rmw.patch new file mode 100644 index 0000000..eea0eea --- /dev/null +++ b/kvm-edu-add-smp_mb__after_rmw.patch @@ -0,0 +1,61 @@ +From 7693449b235bbab6d32a1b87fa1d0e101c786f3b Mon Sep 17 00:00:00 2001 +From: Emanuele Giuseppe Esposito +Date: Thu, 9 Mar 2023 08:11:14 -0500 +Subject: [PATCH 05/13] edu: add smp_mb__after_rmw() + +RH-Author: Emanuele Giuseppe Esposito +RH-MergeRequest: 263: qatomic: add smp_mb__before/after_rmw() +RH-Bugzilla: 2168472 +RH-Acked-by: Cornelia Huck +RH-Acked-by: Eric Auger +RH-Acked-by: Paolo Bonzini +RH-Acked-by: David Hildenbrand +RH-Commit: [5/10] 300901290e08b253b1278eedc39cd07c1e202b96 + +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2168472 + +commit 2482aeea4195ad84cf3d4e5b15b28ec5b420ed5a +Author: Paolo Bonzini +Date: Thu Mar 2 11:16:13 2023 +0100 + + edu: add smp_mb__after_rmw() + + Ensure ordering between clearing the COMPUTING flag and checking + IRQFACT, and between setting the IRQFACT flag and checking + COMPUTING. This ensures that no wakeups are lost. + + Reviewed-by: Richard Henderson + Reviewed-by: David Hildenbrand + Signed-off-by: Paolo Bonzini + +Signed-off-by: Emanuele Giuseppe Esposito +--- + hw/misc/edu.c | 5 +++++ + 1 file changed, 5 insertions(+) + +diff --git a/hw/misc/edu.c b/hw/misc/edu.c +index e935c418d4..a1f8bc77e7 100644 +--- a/hw/misc/edu.c ++++ b/hw/misc/edu.c +@@ -267,6 +267,8 @@ static void edu_mmio_write(void *opaque, hwaddr addr, uint64_t val, + case 0x20: + if (val & EDU_STATUS_IRQFACT) { + qatomic_or(&edu->status, EDU_STATUS_IRQFACT); ++ /* Order check of the COMPUTING flag after setting IRQFACT. */ ++ smp_mb__after_rmw(); + } else { + qatomic_and(&edu->status, ~EDU_STATUS_IRQFACT); + } +@@ -349,6 +351,9 @@ static void *edu_fact_thread(void *opaque) + qemu_mutex_unlock(&edu->thr_mutex); + qatomic_and(&edu->status, ~EDU_STATUS_COMPUTING); + ++ /* Clear COMPUTING flag before checking IRQFACT. */ ++ smp_mb__after_rmw(); ++ + if (qatomic_read(&edu->status) & EDU_STATUS_IRQFACT) { + qemu_mutex_lock_iothread(); + edu_raise_irq(edu, FACT_IRQ); +-- +2.37.3 + diff --git a/kvm-hw-acpi-aml-build-Use-existing-CPU-topology-to-build.patch b/kvm-hw-acpi-aml-build-Use-existing-CPU-topology-to-build.patch deleted file mode 100644 index 2795dcd..0000000 --- a/kvm-hw-acpi-aml-build-Use-existing-CPU-topology-to-build.patch +++ /dev/null @@ -1,179 +0,0 @@ -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/kvm-hw-arm-virt-Consider-SMP-configuration-in-CPU-topolo.patch b/kvm-hw-arm-virt-Consider-SMP-configuration-in-CPU-topolo.patch deleted file mode 100644 index 240aead..0000000 --- a/kvm-hw-arm-virt-Consider-SMP-configuration-in-CPU-topolo.patch +++ /dev/null @@ -1,74 +0,0 @@ -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/kvm-hw-arm-virt-Fix-CPU-s-default-NUMA-node-ID.patch b/kvm-hw-arm-virt-Fix-CPU-s-default-NUMA-node-ID.patch deleted file mode 100644 index 6b60b70..0000000 --- a/kvm-hw-arm-virt-Fix-CPU-s-default-NUMA-node-ID.patch +++ /dev/null @@ -1,88 +0,0 @@ -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/kvm-hw-arm-virt-Fix-missing-initialization-in-instance-c.patch b/kvm-hw-arm-virt-Fix-missing-initialization-in-instance-c.patch deleted file mode 100644 index 78b9ee0..0000000 --- a/kvm-hw-arm-virt-Fix-missing-initialization-in-instance-c.patch +++ /dev/null @@ -1,56 +0,0 @@ -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/kvm-hw-arm-virt-Remove-the-dtb-kaslr-seed-machine-option.patch b/kvm-hw-arm-virt-Remove-the-dtb-kaslr-seed-machine-option.patch deleted file mode 100644 index 10af6c0..0000000 --- a/kvm-hw-arm-virt-Remove-the-dtb-kaslr-seed-machine-option.patch +++ /dev/null @@ -1,76 +0,0 @@ -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/kvm-hw-virtio-Replace-g_memdup-by-g_memdup2.patch b/kvm-hw-virtio-Replace-g_memdup-by-g_memdup2.patch deleted file mode 100644 index 44897ac..0000000 --- a/kvm-hw-virtio-Replace-g_memdup-by-g_memdup2.patch +++ /dev/null @@ -1,95 +0,0 @@ -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/kvm-io-Add-support-for-MSG_PEEK-for-socket-channel.patch b/kvm-io-Add-support-for-MSG_PEEK-for-socket-channel.patch new file mode 100644 index 0000000..6f2cc3f --- /dev/null +++ b/kvm-io-Add-support-for-MSG_PEEK-for-socket-channel.patch @@ -0,0 +1,367 @@ +From 88b5e059462a72ca758d84c0d4d0895a03baac50 Mon Sep 17 00:00:00 2001 +From: "manish.mishra" +Date: Tue, 20 Dec 2022 18:44:17 +0000 +Subject: [PATCH 1/3] io: Add support for MSG_PEEK for socket channel +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Peter Xu +RH-MergeRequest: 258: migration: Fix multifd crash due to channel disorder +RH-Bugzilla: 2137740 +RH-Acked-by: quintela1 +RH-Acked-by: Leonardo Brás +RH-Acked-by: Dr. David Alan Gilbert +RH-Commit: [1/2] 04fc6fae358599b8509f5355469d2e8720f01903 + +Conflicts: + io/channel-null.c + migration/channel-block.c + + Because these two files do not exist in rhel8.8 tree, dropping the + changes. + +MSG_PEEK peeks at the channel, The data is treated as unread and +the next read shall still return this data. This support is +currently added only for socket class. Extra parameter 'flags' +is added to io_readv calls to pass extra read flags like MSG_PEEK. + +Reviewed-by: Peter Xu +Reviewed-by: Daniel P. Berrange +Reviewed-by: Juan Quintela +Suggested-by: Daniel P. Berrange +Signed-off-by: manish.mishra +Signed-off-by: Juan Quintela +(cherry picked from commit 84615a19ddf2bfb38d7b3a0d487d2397ee55e4f3) +Signed-off-by: Peter Xu +--- + chardev/char-socket.c | 4 ++-- + include/io/channel.h | 6 ++++++ + io/channel-buffer.c | 1 + + io/channel-command.c | 1 + + io/channel-file.c | 1 + + io/channel-socket.c | 19 ++++++++++++++++++- + io/channel-tls.c | 1 + + io/channel-websock.c | 1 + + io/channel.c | 16 ++++++++++++---- + migration/rdma.c | 1 + + scsi/qemu-pr-helper.c | 2 +- + tests/qtest/tpm-emu.c | 2 +- + tests/unit/test-io-channel-socket.c | 1 + + util/vhost-user-server.c | 2 +- + 14 files changed, 48 insertions(+), 10 deletions(-) + +diff --git a/chardev/char-socket.c b/chardev/char-socket.c +index 836cfa0bc2..4cdf79e0c2 100644 +--- a/chardev/char-socket.c ++++ b/chardev/char-socket.c +@@ -339,11 +339,11 @@ static ssize_t tcp_chr_recv(Chardev *chr, char *buf, size_t len) + if (qio_channel_has_feature(s->ioc, QIO_CHANNEL_FEATURE_FD_PASS)) { + ret = qio_channel_readv_full(s->ioc, &iov, 1, + &msgfds, &msgfds_num, +- NULL); ++ 0, NULL); + } else { + ret = qio_channel_readv_full(s->ioc, &iov, 1, + NULL, NULL, +- NULL); ++ 0, NULL); + } + + if (ret == QIO_CHANNEL_ERR_BLOCK) { +diff --git a/include/io/channel.h b/include/io/channel.h +index c680ee7480..716235d496 100644 +--- a/include/io/channel.h ++++ b/include/io/channel.h +@@ -34,6 +34,8 @@ OBJECT_DECLARE_TYPE(QIOChannel, QIOChannelClass, + + #define QIO_CHANNEL_WRITE_FLAG_ZERO_COPY 0x1 + ++#define QIO_CHANNEL_READ_FLAG_MSG_PEEK 0x1 ++ + typedef enum QIOChannelFeature QIOChannelFeature; + + enum QIOChannelFeature { +@@ -41,6 +43,7 @@ enum QIOChannelFeature { + QIO_CHANNEL_FEATURE_SHUTDOWN, + QIO_CHANNEL_FEATURE_LISTEN, + QIO_CHANNEL_FEATURE_WRITE_ZERO_COPY, ++ QIO_CHANNEL_FEATURE_READ_MSG_PEEK, + }; + + +@@ -114,6 +117,7 @@ struct QIOChannelClass { + size_t niov, + int **fds, + size_t *nfds, ++ int flags, + Error **errp); + int (*io_close)(QIOChannel *ioc, + Error **errp); +@@ -188,6 +192,7 @@ void qio_channel_set_name(QIOChannel *ioc, + * @niov: the length of the @iov array + * @fds: pointer to an array that will received file handles + * @nfds: pointer filled with number of elements in @fds on return ++ * @flags: read flags (QIO_CHANNEL_READ_FLAG_*) + * @errp: pointer to a NULL-initialized error object + * + * Read data from the IO channel, storing it in the +@@ -224,6 +229,7 @@ ssize_t qio_channel_readv_full(QIOChannel *ioc, + size_t niov, + int **fds, + size_t *nfds, ++ int flags, + Error **errp); + + +diff --git a/io/channel-buffer.c b/io/channel-buffer.c +index bf52011be2..8096180f85 100644 +--- a/io/channel-buffer.c ++++ b/io/channel-buffer.c +@@ -54,6 +54,7 @@ static ssize_t qio_channel_buffer_readv(QIOChannel *ioc, + size_t niov, + int **fds, + size_t *nfds, ++ int flags, + Error **errp) + { + QIOChannelBuffer *bioc = QIO_CHANNEL_BUFFER(ioc); +diff --git a/io/channel-command.c b/io/channel-command.c +index 5ff1691bad..2834413b3a 100644 +--- a/io/channel-command.c ++++ b/io/channel-command.c +@@ -230,6 +230,7 @@ static ssize_t qio_channel_command_readv(QIOChannel *ioc, + size_t niov, + int **fds, + size_t *nfds, ++ int flags, + Error **errp) + { + QIOChannelCommand *cioc = QIO_CHANNEL_COMMAND(ioc); +diff --git a/io/channel-file.c b/io/channel-file.c +index 348a48545e..490f0e5d84 100644 +--- a/io/channel-file.c ++++ b/io/channel-file.c +@@ -86,6 +86,7 @@ static ssize_t qio_channel_file_readv(QIOChannel *ioc, + size_t niov, + int **fds, + size_t *nfds, ++ int flags, + Error **errp) + { + QIOChannelFile *fioc = QIO_CHANNEL_FILE(ioc); +diff --git a/io/channel-socket.c b/io/channel-socket.c +index 6010ad7017..ca8b180b69 100644 +--- a/io/channel-socket.c ++++ b/io/channel-socket.c +@@ -174,6 +174,9 @@ int qio_channel_socket_connect_sync(QIOChannelSocket *ioc, + } + #endif + ++ qio_channel_set_feature(QIO_CHANNEL(ioc), ++ QIO_CHANNEL_FEATURE_READ_MSG_PEEK); ++ + return 0; + } + +@@ -407,6 +410,9 @@ qio_channel_socket_accept(QIOChannelSocket *ioc, + } + #endif /* WIN32 */ + ++ qio_channel_set_feature(QIO_CHANNEL(cioc), ++ QIO_CHANNEL_FEATURE_READ_MSG_PEEK); ++ + trace_qio_channel_socket_accept_complete(ioc, cioc, cioc->fd); + return cioc; + +@@ -497,6 +503,7 @@ static ssize_t qio_channel_socket_readv(QIOChannel *ioc, + size_t niov, + int **fds, + size_t *nfds, ++ int flags, + Error **errp) + { + QIOChannelSocket *sioc = QIO_CHANNEL_SOCKET(ioc); +@@ -518,6 +525,10 @@ static ssize_t qio_channel_socket_readv(QIOChannel *ioc, + + } + ++ if (flags & QIO_CHANNEL_READ_FLAG_MSG_PEEK) { ++ sflags |= MSG_PEEK; ++ } ++ + retry: + ret = recvmsg(sioc->fd, &msg, sflags); + if (ret < 0) { +@@ -625,11 +636,17 @@ static ssize_t qio_channel_socket_readv(QIOChannel *ioc, + size_t niov, + int **fds, + size_t *nfds, ++ int flags, + Error **errp) + { + QIOChannelSocket *sioc = QIO_CHANNEL_SOCKET(ioc); + ssize_t done = 0; + ssize_t i; ++ int sflags = 0; ++ ++ if (flags & QIO_CHANNEL_READ_FLAG_MSG_PEEK) { ++ sflags |= MSG_PEEK; ++ } + + for (i = 0; i < niov; i++) { + ssize_t ret; +@@ -637,7 +654,7 @@ static ssize_t qio_channel_socket_readv(QIOChannel *ioc, + ret = recv(sioc->fd, + iov[i].iov_base, + iov[i].iov_len, +- 0); ++ sflags); + if (ret < 0) { + if (errno == EAGAIN) { + if (done) { +diff --git a/io/channel-tls.c b/io/channel-tls.c +index 4ce890a538..c730cb8ec5 100644 +--- a/io/channel-tls.c ++++ b/io/channel-tls.c +@@ -260,6 +260,7 @@ static ssize_t qio_channel_tls_readv(QIOChannel *ioc, + size_t niov, + int **fds, + size_t *nfds, ++ int flags, + Error **errp) + { + QIOChannelTLS *tioc = QIO_CHANNEL_TLS(ioc); +diff --git a/io/channel-websock.c b/io/channel-websock.c +index 035dd6075b..13c94f2afe 100644 +--- a/io/channel-websock.c ++++ b/io/channel-websock.c +@@ -1081,6 +1081,7 @@ static ssize_t qio_channel_websock_readv(QIOChannel *ioc, + size_t niov, + int **fds, + size_t *nfds, ++ int flags, + Error **errp) + { + QIOChannelWebsock *wioc = QIO_CHANNEL_WEBSOCK(ioc); +diff --git a/io/channel.c b/io/channel.c +index 0640941ac5..a8c7f11649 100644 +--- a/io/channel.c ++++ b/io/channel.c +@@ -52,6 +52,7 @@ ssize_t qio_channel_readv_full(QIOChannel *ioc, + size_t niov, + int **fds, + size_t *nfds, ++ int flags, + Error **errp) + { + QIOChannelClass *klass = QIO_CHANNEL_GET_CLASS(ioc); +@@ -63,7 +64,14 @@ ssize_t qio_channel_readv_full(QIOChannel *ioc, + return -1; + } + +- return klass->io_readv(ioc, iov, niov, fds, nfds, errp); ++ if ((flags & QIO_CHANNEL_READ_FLAG_MSG_PEEK) && ++ !qio_channel_has_feature(ioc, QIO_CHANNEL_FEATURE_READ_MSG_PEEK)) { ++ error_setg_errno(errp, EINVAL, ++ "Channel does not support peek read"); ++ return -1; ++ } ++ ++ return klass->io_readv(ioc, iov, niov, fds, nfds, flags, errp); + } + + +@@ -146,7 +154,7 @@ int qio_channel_readv_full_all_eof(QIOChannel *ioc, + while ((nlocal_iov > 0) || local_fds) { + ssize_t len; + len = qio_channel_readv_full(ioc, local_iov, nlocal_iov, local_fds, +- local_nfds, errp); ++ local_nfds, 0, errp); + if (len == QIO_CHANNEL_ERR_BLOCK) { + if (qemu_in_coroutine()) { + qio_channel_yield(ioc, G_IO_IN); +@@ -284,7 +292,7 @@ ssize_t qio_channel_readv(QIOChannel *ioc, + size_t niov, + Error **errp) + { +- return qio_channel_readv_full(ioc, iov, niov, NULL, NULL, errp); ++ return qio_channel_readv_full(ioc, iov, niov, NULL, NULL, 0, errp); + } + + +@@ -303,7 +311,7 @@ ssize_t qio_channel_read(QIOChannel *ioc, + Error **errp) + { + struct iovec iov = { .iov_base = buf, .iov_len = buflen }; +- return qio_channel_readv_full(ioc, &iov, 1, NULL, NULL, errp); ++ return qio_channel_readv_full(ioc, &iov, 1, NULL, NULL, 0, errp); + } + + +diff --git a/migration/rdma.c b/migration/rdma.c +index 54acd2000e..dcf98bd7f8 100644 +--- a/migration/rdma.c ++++ b/migration/rdma.c +@@ -2917,6 +2917,7 @@ static ssize_t qio_channel_rdma_readv(QIOChannel *ioc, + size_t niov, + int **fds, + size_t *nfds, ++ int flags, + Error **errp) + { + QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(ioc); +diff --git a/scsi/qemu-pr-helper.c b/scsi/qemu-pr-helper.c +index f281daeced..12ec8e9368 100644 +--- a/scsi/qemu-pr-helper.c ++++ b/scsi/qemu-pr-helper.c +@@ -612,7 +612,7 @@ static int coroutine_fn prh_read(PRHelperClient *client, void *buf, int sz, + iov.iov_base = buf; + iov.iov_len = sz; + n_read = qio_channel_readv_full(QIO_CHANNEL(client->ioc), &iov, 1, +- &fds, &nfds, errp); ++ &fds, &nfds, 0, errp); + + if (n_read == QIO_CHANNEL_ERR_BLOCK) { + qio_channel_yield(QIO_CHANNEL(client->ioc), G_IO_IN); +diff --git a/tests/qtest/tpm-emu.c b/tests/qtest/tpm-emu.c +index 2994d1cf42..3cf1acaf7d 100644 +--- a/tests/qtest/tpm-emu.c ++++ b/tests/qtest/tpm-emu.c +@@ -106,7 +106,7 @@ void *tpm_emu_ctrl_thread(void *data) + int *pfd = NULL; + size_t nfd = 0; + +- qio_channel_readv_full(ioc, &iov, 1, &pfd, &nfd, &error_abort); ++ qio_channel_readv_full(ioc, &iov, 1, &pfd, &nfd, 0, &error_abort); + cmd = be32_to_cpu(cmd); + g_assert_cmpint(cmd, ==, CMD_SET_DATAFD); + g_assert_cmpint(nfd, ==, 1); +diff --git a/tests/unit/test-io-channel-socket.c b/tests/unit/test-io-channel-socket.c +index 6713886d02..de2930f203 100644 +--- a/tests/unit/test-io-channel-socket.c ++++ b/tests/unit/test-io-channel-socket.c +@@ -452,6 +452,7 @@ static void test_io_channel_unix_fd_pass(void) + G_N_ELEMENTS(iorecv), + &fdrecv, + &nfdrecv, ++ 0, + &error_abort); + + g_assert(nfdrecv == G_N_ELEMENTS(fdsend)); +diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c +index 783d847a6d..e6a9ef72b7 100644 +--- a/util/vhost-user-server.c ++++ b/util/vhost-user-server.c +@@ -102,7 +102,7 @@ vu_message_read(VuDev *vu_dev, int conn_fd, VhostUserMsg *vmsg) + * qio_channel_readv_full may have short reads, keeping calling it + * until getting VHOST_USER_HDR_SIZE or 0 bytes in total + */ +- rc = qio_channel_readv_full(ioc, &iov, 1, &fds, &nfds, &local_err); ++ rc = qio_channel_readv_full(ioc, &iov, 1, &fds, &nfds, 0, &local_err); + if (rc < 0) { + if (rc == QIO_CHANNEL_ERR_BLOCK) { + assert(local_err == NULL); +-- +2.37.3 + diff --git a/kvm-kvm-Atomic-memslot-updates.patch b/kvm-kvm-Atomic-memslot-updates.patch new file mode 100644 index 0000000..d97a2c9 --- /dev/null +++ b/kvm-kvm-Atomic-memslot-updates.patch @@ -0,0 +1,290 @@ +From 93ec857c46911b95ed8e3abc6a9d432ae847c084 Mon Sep 17 00:00:00 2001 +From: Emanuele Giuseppe Esposito +Date: Mon, 16 Jan 2023 07:51:56 -0500 +Subject: [PATCH 06/11] kvm: Atomic memslot updates + +RH-Author: Emanuele Giuseppe Esposito +RH-MergeRequest: 247: accel: introduce accelerator blocker API +RH-Bugzilla: 2161188 +RH-Acked-by: David Hildenbrand +RH-Acked-by: Vitaly Kuznetsov +RH-Acked-by: Miroslav Rezanina +RH-Commit: [3/3] 520e41c0f58066a7381a5f6b32b81bc01cce51c0 + +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2161188 + +commit f39b7d2b96e3e73c01bb678cd096f7baf0b9ab39 +Author: David Hildenbrand +Date: Fri Nov 11 10:47:58 2022 -0500 + + kvm: Atomic memslot updates + + If we update an existing memslot (e.g., resize, split), we temporarily + remove the memslot to re-add it immediately afterwards. These updates + are not atomic, especially not for KVM VCPU threads, such that we can + get spurious faults. + + Let's inhibit most KVM ioctls while performing relevant updates, such + that we can perform the update just as if it would happen atomically + without additional kernel support. + + We capture the add/del changes and apply them in the notifier commit + stage instead. There, we can check for overlaps and perform the ioctl + inhibiting only if really required (-> overlap). + + To keep things simple we don't perform additional checks that wouldn't + actually result in an overlap -- such as !RAM memory regions in some + cases (see kvm_set_phys_mem()). + + To minimize cache-line bouncing, use a separate indicator + (in_ioctl_lock) per CPU. Also, make sure to hold the kvm_slots_lock + while performing both actions (removing+re-adding). + + We have to wait until all IOCTLs were exited and block new ones from + getting executed. + + This approach cannot result in a deadlock as long as the inhibitor does + not hold any locks that might hinder an IOCTL from getting finished and + exited - something fairly unusual. The inhibitor will always hold the BQL. + + AFAIKs, one possible candidate would be userfaultfd. If a page cannot be + placed (e.g., during postcopy), because we're waiting for a lock, or if the + userfaultfd thread cannot process a fault, because it is waiting for a + lock, there could be a deadlock. However, the BQL is not applicable here, + because any other guest memory access while holding the BQL would already + result in a deadlock. + + Nothing else in the kernel should block forever and wait for userspace + intervention. + + Note: pause_all_vcpus()/resume_all_vcpus() or + start_exclusive()/end_exclusive() cannot be used, as they either drop + the BQL or require to be called without the BQL - something inhibitors + cannot handle. We need a low-level locking mechanism that is + deadlock-free even when not releasing the BQL. + + Signed-off-by: David Hildenbrand + Signed-off-by: Emanuele Giuseppe Esposito + Tested-by: Emanuele Giuseppe Esposito + Message-Id: <20221111154758.1372674-4-eesposit@redhat.com> + Signed-off-by: Paolo Bonzini + +Conflicts: + accel/kvm/kvm-all.c: include "sysemu/dirtylimit.h" is missing in + rhel 8.8.0 + +Signed-off-by: Emanuele Giuseppe Esposito +--- + accel/kvm/kvm-all.c | 101 ++++++++++++++++++++++++++++++++++----- + include/sysemu/kvm_int.h | 8 ++++ + 2 files changed, 98 insertions(+), 11 deletions(-) + +diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c +index 221aadfda7..3b7bc39823 100644 +--- a/accel/kvm/kvm-all.c ++++ b/accel/kvm/kvm-all.c +@@ -31,6 +31,7 @@ + #include "sysemu/kvm_int.h" + #include "sysemu/runstate.h" + #include "sysemu/cpus.h" ++#include "sysemu/accel-blocker.h" + #include "qemu/bswap.h" + #include "exec/memory.h" + #include "exec/ram_addr.h" +@@ -45,6 +46,7 @@ + #include "qemu/guest-random.h" + #include "sysemu/hw_accel.h" + #include "kvm-cpus.h" ++#include "qemu/range.h" + + #include "hw/boards.h" + +@@ -1334,6 +1336,7 @@ void kvm_set_max_memslot_size(hwaddr max_slot_size) + kvm_max_slot_size = max_slot_size; + } + ++/* Called with KVMMemoryListener.slots_lock held */ + static void kvm_set_phys_mem(KVMMemoryListener *kml, + MemoryRegionSection *section, bool add) + { +@@ -1368,14 +1371,12 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml, + ram = memory_region_get_ram_ptr(mr) + mr_offset; + ram_start_offset = memory_region_get_ram_addr(mr) + mr_offset; + +- kvm_slots_lock(); +- + if (!add) { + do { + slot_size = MIN(kvm_max_slot_size, size); + mem = kvm_lookup_matching_slot(kml, start_addr, slot_size); + if (!mem) { +- goto out; ++ return; + } + if (mem->flags & KVM_MEM_LOG_DIRTY_PAGES) { + /* +@@ -1413,7 +1414,7 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml, + start_addr += slot_size; + size -= slot_size; + } while (size); +- goto out; ++ return; + } + + /* register the new slot */ +@@ -1438,9 +1439,6 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml, + ram += slot_size; + size -= slot_size; + } while (size); +- +-out: +- kvm_slots_unlock(); + } + + static void *kvm_dirty_ring_reaper_thread(void *data) +@@ -1492,18 +1490,95 @@ static void kvm_region_add(MemoryListener *listener, + MemoryRegionSection *section) + { + KVMMemoryListener *kml = container_of(listener, KVMMemoryListener, listener); ++ KVMMemoryUpdate *update; ++ ++ update = g_new0(KVMMemoryUpdate, 1); ++ update->section = *section; + +- memory_region_ref(section->mr); +- kvm_set_phys_mem(kml, section, true); ++ QSIMPLEQ_INSERT_TAIL(&kml->transaction_add, update, next); + } + + static void kvm_region_del(MemoryListener *listener, + MemoryRegionSection *section) + { + KVMMemoryListener *kml = container_of(listener, KVMMemoryListener, listener); ++ KVMMemoryUpdate *update; ++ ++ update = g_new0(KVMMemoryUpdate, 1); ++ update->section = *section; ++ ++ QSIMPLEQ_INSERT_TAIL(&kml->transaction_del, update, next); ++} ++ ++static void kvm_region_commit(MemoryListener *listener) ++{ ++ KVMMemoryListener *kml = container_of(listener, KVMMemoryListener, ++ listener); ++ KVMMemoryUpdate *u1, *u2; ++ bool need_inhibit = false; ++ ++ if (QSIMPLEQ_EMPTY(&kml->transaction_add) && ++ QSIMPLEQ_EMPTY(&kml->transaction_del)) { ++ return; ++ } ++ ++ /* ++ * We have to be careful when regions to add overlap with ranges to remove. ++ * We have to simulate atomic KVM memslot updates by making sure no ioctl() ++ * is currently active. ++ * ++ * The lists are order by addresses, so it's easy to find overlaps. ++ */ ++ u1 = QSIMPLEQ_FIRST(&kml->transaction_del); ++ u2 = QSIMPLEQ_FIRST(&kml->transaction_add); ++ while (u1 && u2) { ++ Range r1, r2; ++ ++ range_init_nofail(&r1, u1->section.offset_within_address_space, ++ int128_get64(u1->section.size)); ++ range_init_nofail(&r2, u2->section.offset_within_address_space, ++ int128_get64(u2->section.size)); ++ ++ if (range_overlaps_range(&r1, &r2)) { ++ need_inhibit = true; ++ break; ++ } ++ if (range_lob(&r1) < range_lob(&r2)) { ++ u1 = QSIMPLEQ_NEXT(u1, next); ++ } else { ++ u2 = QSIMPLEQ_NEXT(u2, next); ++ } ++ } ++ ++ kvm_slots_lock(); ++ if (need_inhibit) { ++ accel_ioctl_inhibit_begin(); ++ } ++ ++ /* Remove all memslots before adding the new ones. */ ++ while (!QSIMPLEQ_EMPTY(&kml->transaction_del)) { ++ u1 = QSIMPLEQ_FIRST(&kml->transaction_del); ++ QSIMPLEQ_REMOVE_HEAD(&kml->transaction_del, next); + +- kvm_set_phys_mem(kml, section, false); +- memory_region_unref(section->mr); ++ kvm_set_phys_mem(kml, &u1->section, false); ++ memory_region_unref(u1->section.mr); ++ ++ g_free(u1); ++ } ++ while (!QSIMPLEQ_EMPTY(&kml->transaction_add)) { ++ u1 = QSIMPLEQ_FIRST(&kml->transaction_add); ++ QSIMPLEQ_REMOVE_HEAD(&kml->transaction_add, next); ++ ++ memory_region_ref(u1->section.mr); ++ kvm_set_phys_mem(kml, &u1->section, true); ++ ++ g_free(u1); ++ } ++ ++ if (need_inhibit) { ++ accel_ioctl_inhibit_end(); ++ } ++ kvm_slots_unlock(); + } + + static void kvm_log_sync(MemoryListener *listener, +@@ -1647,8 +1722,12 @@ void kvm_memory_listener_register(KVMState *s, KVMMemoryListener *kml, + kml->slots[i].slot = i; + } + ++ QSIMPLEQ_INIT(&kml->transaction_add); ++ QSIMPLEQ_INIT(&kml->transaction_del); ++ + kml->listener.region_add = kvm_region_add; + kml->listener.region_del = kvm_region_del; ++ kml->listener.commit = kvm_region_commit; + kml->listener.log_start = kvm_log_start; + kml->listener.log_stop = kvm_log_stop; + kml->listener.priority = 10; +diff --git a/include/sysemu/kvm_int.h b/include/sysemu/kvm_int.h +index 1f5487d9b7..7e18c0a3c0 100644 +--- a/include/sysemu/kvm_int.h ++++ b/include/sysemu/kvm_int.h +@@ -11,6 +11,7 @@ + + #include "exec/memory.h" + #include "qemu/accel.h" ++#include "qemu/queue.h" + #include "sysemu/kvm.h" + + typedef struct KVMSlot +@@ -30,10 +31,17 @@ typedef struct KVMSlot + ram_addr_t ram_start_offset; + } KVMSlot; + ++typedef struct KVMMemoryUpdate { ++ QSIMPLEQ_ENTRY(KVMMemoryUpdate) next; ++ MemoryRegionSection section; ++} KVMMemoryUpdate; ++ + typedef struct KVMMemoryListener { + MemoryListener listener; + KVMSlot *slots; + int as_id; ++ QSIMPLEQ_HEAD(, KVMMemoryUpdate) transaction_add; ++ QSIMPLEQ_HEAD(, KVMMemoryUpdate) transaction_del; + } KVMMemoryListener; + + void kvm_memory_listener_register(KVMState *s, KVMMemoryListener *kml, +-- +2.37.3 + diff --git a/kvm-kvm-don-t-use-perror-without-useful-errno.patch b/kvm-kvm-don-t-use-perror-without-useful-errno.patch deleted file mode 100644 index a78c089..0000000 --- a/kvm-kvm-don-t-use-perror-without-useful-errno.patch +++ /dev/null @@ -1,62 +0,0 @@ -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/kvm-meson-create-have_vhost_-variables.patch b/kvm-meson-create-have_vhost_-variables.patch deleted file mode 100644 index fcae620..0000000 --- a/kvm-meson-create-have_vhost_-variables.patch +++ /dev/null @@ -1,154 +0,0 @@ -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/kvm-meson-use-have_vhost_-variables-to-pick-sources.patch b/kvm-meson-use-have_vhost_-variables-to-pick-sources.patch deleted file mode 100644 index 99d86c1..0000000 --- a/kvm-meson-use-have_vhost_-variables-to-pick-sources.patch +++ /dev/null @@ -1,213 +0,0 @@ -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/kvm-meson.build-Fix-docker-test-build-alpine-when-includ.patch b/kvm-meson.build-Fix-docker-test-build-alpine-when-includ.patch deleted file mode 100644 index 0da63bf..0000000 --- a/kvm-meson.build-Fix-docker-test-build-alpine-when-includ.patch +++ /dev/null @@ -1,87 +0,0 @@ -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/kvm-migration-Fix-operator-type.patch b/kvm-migration-Fix-operator-type.patch deleted file mode 100644 index f6a462a..0000000 --- a/kvm-migration-Fix-operator-type.patch +++ /dev/null @@ -1,47 +0,0 @@ -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/kvm-migration-Read-state-once.patch b/kvm-migration-Read-state-once.patch new file mode 100644 index 0000000..63fd047 --- /dev/null +++ b/kvm-migration-Read-state-once.patch @@ -0,0 +1,76 @@ +From 34eae2d7ef928a7e0e10cc30fe76839c005998eb Mon Sep 17 00:00:00 2001 +From: "Dr. David Alan Gilbert" +Date: Wed, 13 Apr 2022 12:33:29 +0100 +Subject: [PATCH 07/11] migration: Read state once + +RH-Author: Dr. David Alan Gilbert +RH-MergeRequest: 249: migration: Read state once +RH-Bugzilla: 2074205 +RH-Acked-by: Peter Xu +RH-Acked-by: Laszlo Ersek +RH-Acked-by: Jon Maloy +RH-Acked-by: quintela1 +RH-Commit: [1/1] 9aa47b492a646fce4e66ebd9b7d7a85286d16051 + +The 'status' field for the migration is updated normally using +an atomic operation from the migration thread. +Most readers of it aren't that careful, and in most cases it doesn't +matter. + +In query_migrate->fill_source_migration_info the 'state' +is read twice; the first time to decide which state fields to fill in, +and then secondly to copy the state to the status field; that can end up +with a status that's inconsistent; e.g. setting up the fields +for 'setup' and then having an 'active' status. In that case +libvirt gets upset by the lack of ram info. +The symptom is: + libvirt.libvirtError: internal error: migration was active, but no RAM info was set + +Read the state exactly once in fill_source_migration_info. + +This is a possible fix for: +https://bugzilla.redhat.com/show_bug.cgi?id=2074205 + +Signed-off-by: Dr. David Alan Gilbert +Message-Id: <20220413113329.103696-1-dgilbert@redhat.com> +Reviewed-by: Juan Quintela +Reviewed-by: Peter Xu +Signed-off-by: Dr. David Alan Gilbert +(cherry picked from commit 552de79bfdd5e9e53847eb3c6d6e4cd898a4370e) +--- + migration/migration.c | 5 +++-- + 1 file changed, 3 insertions(+), 2 deletions(-) + +diff --git a/migration/migration.c b/migration/migration.c +index 51e6726dac..d8b24a2c91 100644 +--- a/migration/migration.c ++++ b/migration/migration.c +@@ -1071,6 +1071,7 @@ static void populate_disk_info(MigrationInfo *info) + static void fill_source_migration_info(MigrationInfo *info) + { + MigrationState *s = migrate_get_current(); ++ int state = qatomic_read(&s->state); + GSList *cur_blocker = migration_blockers; + + info->blocked_reasons = NULL; +@@ -1090,7 +1091,7 @@ static void fill_source_migration_info(MigrationInfo *info) + } + info->has_blocked_reasons = info->blocked_reasons != NULL; + +- switch (s->state) { ++ switch (state) { + case MIGRATION_STATUS_NONE: + /* no migration has happened ever */ + /* do not overwrite destination migration status */ +@@ -1135,7 +1136,7 @@ static void fill_source_migration_info(MigrationInfo *info) + info->has_status = true; + break; + } +- info->status = s->state; ++ info->status = state; + } + + typedef enum WriteTrackingSupport { +-- +2.37.3 + diff --git a/kvm-migration-check-magic-value-for-deciding-the-mapping.patch b/kvm-migration-check-magic-value-for-deciding-the-mapping.patch new file mode 100644 index 0000000..7838333 --- /dev/null +++ b/kvm-migration-check-magic-value-for-deciding-the-mapping.patch @@ -0,0 +1,296 @@ +From f21a343af4b4d0c6e5181ae0abd0f6280dc8296c Mon Sep 17 00:00:00 2001 +From: "manish.mishra" +Date: Tue, 20 Dec 2022 18:44:18 +0000 +Subject: [PATCH 2/3] migration: check magic value for deciding the mapping of + channels +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Peter Xu +RH-MergeRequest: 258: migration: Fix multifd crash due to channel disorder +RH-Bugzilla: 2137740 +RH-Acked-by: quintela1 +RH-Acked-by: Leonardo Brás +RH-Acked-by: Dr. David Alan Gilbert +RH-Commit: [2/2] f97bebef3d3e372cfd660e5ddb6cffba791840d2 + +Conflicts: + migration/migration.c + migration/multifd.c + migration/postcopy-ram.c + migration/postcopy-ram.h + + There're a bunch of conflicts due to missing upstream patches on + e.g. on qemufile reworks, postcopy preempt. We don't plan to have + preempt in rhel8 at all, probably the same as the rest. + +Current logic assumes that channel connections on the destination side are +always established in the same order as the source and the first one will +always be the main channel followed by the multifid or post-copy +preemption channel. This may not be always true, as even if a channel has a +connection established on the source side it can be in the pending state on +the destination side and a newer connection can be established first. +Basically causing out of order mapping of channels on the destination side. +Currently, all channels except post-copy preempt send a magic number, this +patch uses that magic number to decide the type of channel. This logic is +applicable only for precopy(multifd) live migration, as mentioned, the +post-copy preempt channel does not send any magic number. Also, tls live +migrations already does tls handshake before creating other channels, so +this issue is not possible with tls, hence this logic is avoided for tls +live migrations. This patch uses read peek to check the magic number of +channels so that current data/control stream management remains +un-effected. + +Reviewed-by: Peter Xu +Reviewed-by: Daniel P. Berrange +Reviewed-by: Juan Quintela +Suggested-by: Daniel P. Berrange +Signed-off-by: manish.mishra +Signed-off-by: Juan Quintela +(cherry picked from commit 6720c2b32725e6ac404f22851a0ecd0a71d0cbe2) +Signed-off-by: Peter Xu +--- + migration/channel.c | 45 ++++++++++++++++++++++++++++++++++++++ + migration/channel.h | 5 +++++ + migration/migration.c | 51 +++++++++++++++++++++++++++++++------------ + migration/multifd.c | 19 ++++++++-------- + migration/multifd.h | 2 +- + 5 files changed, 98 insertions(+), 24 deletions(-) + +diff --git a/migration/channel.c b/migration/channel.c +index 086b5c0d8b..ee308fef23 100644 +--- a/migration/channel.c ++++ b/migration/channel.c +@@ -98,3 +98,48 @@ void migration_channel_connect(MigrationState *s, + g_free(s->hostname); + error_free(error); + } ++ ++ ++/** ++ * @migration_channel_read_peek - Peek at migration channel, without ++ * actually removing it from channel buffer. ++ * ++ * @ioc: the channel object ++ * @buf: the memory region to read data into ++ * @buflen: the number of bytes to read in @buf ++ * @errp: pointer to a NULL-initialized error object ++ * ++ * Returns 0 if successful, returns -1 and sets @errp if fails. ++ */ ++int migration_channel_read_peek(QIOChannel *ioc, ++ const char *buf, ++ const size_t buflen, ++ Error **errp) ++{ ++ ssize_t len = 0; ++ struct iovec iov = { .iov_base = (char *)buf, .iov_len = buflen }; ++ ++ while (true) { ++ len = qio_channel_readv_full(ioc, &iov, 1, NULL, NULL, ++ QIO_CHANNEL_READ_FLAG_MSG_PEEK, errp); ++ ++ if (len <= 0 && len != QIO_CHANNEL_ERR_BLOCK) { ++ error_setg(errp, ++ "Failed to peek at channel"); ++ return -1; ++ } ++ ++ if (len == buflen) { ++ break; ++ } ++ ++ /* 1ms sleep. */ ++ if (qemu_in_coroutine()) { ++ qemu_co_sleep_ns(QEMU_CLOCK_REALTIME, 1000000); ++ } else { ++ g_usleep(1000); ++ } ++ } ++ ++ return 0; ++} +diff --git a/migration/channel.h b/migration/channel.h +index 67a461c28a..5bdb8208a7 100644 +--- a/migration/channel.h ++++ b/migration/channel.h +@@ -24,4 +24,9 @@ void migration_channel_connect(MigrationState *s, + QIOChannel *ioc, + const char *hostname, + Error *error_in); ++ ++int migration_channel_read_peek(QIOChannel *ioc, ++ const char *buf, ++ const size_t buflen, ++ Error **errp); + #endif +diff --git a/migration/migration.c b/migration/migration.c +index d8b24a2c91..0885549de0 100644 +--- a/migration/migration.c ++++ b/migration/migration.c +@@ -32,6 +32,7 @@ + #include "savevm.h" + #include "qemu-file-channel.h" + #include "qemu-file.h" ++#include "channel.h" + #include "migration/vmstate.h" + #include "block/block.h" + #include "qapi/error.h" +@@ -637,10 +638,6 @@ static bool migration_incoming_setup(QEMUFile *f, Error **errp) + { + MigrationIncomingState *mis = migration_incoming_get_current(); + +- if (multifd_load_setup(errp) != 0) { +- return false; +- } +- + if (!mis->from_src_file) { + mis->from_src_file = f; + } +@@ -701,10 +698,42 @@ void migration_fd_process_incoming(QEMUFile *f, Error **errp) + void migration_ioc_process_incoming(QIOChannel *ioc, Error **errp) + { + MigrationIncomingState *mis = migration_incoming_get_current(); ++ bool default_channel = true; ++ uint32_t channel_magic = 0; + Error *local_err = NULL; +- bool start_migration; ++ int ret = 0; + +- if (!mis->from_src_file) { ++ if (migrate_use_multifd() && !migrate_postcopy_ram() && ++ qio_channel_has_feature(ioc, QIO_CHANNEL_FEATURE_READ_MSG_PEEK)) { ++ /* ++ * With multiple channels, it is possible that we receive channels ++ * out of order on destination side, causing incorrect mapping of ++ * source channels on destination side. Check channel MAGIC to ++ * decide type of channel. Please note this is best effort, postcopy ++ * preempt channel does not send any magic number so avoid it for ++ * postcopy live migration. Also tls live migration already does ++ * tls handshake while initializing main channel so with tls this ++ * issue is not possible. ++ */ ++ ret = migration_channel_read_peek(ioc, (void *)&channel_magic, ++ sizeof(channel_magic), &local_err); ++ ++ if (ret != 0) { ++ error_propagate(errp, local_err); ++ return; ++ } ++ ++ default_channel = (channel_magic == cpu_to_be32(QEMU_VM_FILE_MAGIC)); ++ } else { ++ default_channel = !mis->from_src_file; ++ } ++ ++ if (multifd_load_setup(errp) != 0) { ++ error_setg(errp, "Failed to setup multifd channels"); ++ return; ++ } ++ ++ if (default_channel) { + /* The first connection (multifd may have multiple) */ + QEMUFile *f = qemu_fopen_channel_input(ioc); + +@@ -716,23 +745,17 @@ void migration_ioc_process_incoming(QIOChannel *ioc, Error **errp) + if (!migration_incoming_setup(f, errp)) { + return; + } +- +- /* +- * Common migration only needs one channel, so we can start +- * right now. Multifd needs more than one channel, we wait. +- */ +- start_migration = !migrate_use_multifd(); + } else { + /* Multiple connections */ + assert(migrate_use_multifd()); +- start_migration = multifd_recv_new_channel(ioc, &local_err); ++ multifd_recv_new_channel(ioc, &local_err); + if (local_err) { + error_propagate(errp, local_err); + return; + } + } + +- if (start_migration) { ++ if (migration_has_all_channels()) { + migration_incoming_process(); + } + } +diff --git a/migration/multifd.c b/migration/multifd.c +index 7c16523e6b..75ac052d2f 100644 +--- a/migration/multifd.c ++++ b/migration/multifd.c +@@ -1183,9 +1183,14 @@ int multifd_load_setup(Error **errp) + uint32_t page_count = MULTIFD_PACKET_SIZE / qemu_target_page_size(); + uint8_t i; + +- if (!migrate_use_multifd()) { ++ /* ++ * Return successfully if multiFD recv state is already initialised ++ * or multiFD is not enabled. ++ */ ++ if (multifd_recv_state || !migrate_use_multifd()) { + return 0; + } ++ + if (!migrate_multifd_is_allowed()) { + error_setg(errp, "multifd is not supported by current protocol"); + return -1; +@@ -1244,11 +1249,9 @@ bool multifd_recv_all_channels_created(void) + + /* + * Try to receive all multifd channels to get ready for the migration. +- * - Return true and do not set @errp when correctly receiving all channels; +- * - Return false and do not set @errp when correctly receiving the current one; +- * - Return false and set @errp when failing to receive the current channel. ++ * Sets @errp when failing to receive the current channel. + */ +-bool multifd_recv_new_channel(QIOChannel *ioc, Error **errp) ++void multifd_recv_new_channel(QIOChannel *ioc, Error **errp) + { + MultiFDRecvParams *p; + Error *local_err = NULL; +@@ -1261,7 +1264,7 @@ bool multifd_recv_new_channel(QIOChannel *ioc, Error **errp) + "failed to receive packet" + " via multifd channel %d: ", + qatomic_read(&multifd_recv_state->count)); +- return false; ++ return; + } + trace_multifd_recv_new_channel(id); + +@@ -1271,7 +1274,7 @@ bool multifd_recv_new_channel(QIOChannel *ioc, Error **errp) + id); + multifd_recv_terminate_threads(local_err); + error_propagate(errp, local_err); +- return false; ++ return; + } + p->c = ioc; + object_ref(OBJECT(ioc)); +@@ -1282,6 +1285,4 @@ bool multifd_recv_new_channel(QIOChannel *ioc, Error **errp) + qemu_thread_create(&p->thread, p->name, multifd_recv_thread, p, + QEMU_THREAD_JOINABLE); + qatomic_inc(&multifd_recv_state->count); +- return qatomic_read(&multifd_recv_state->count) == +- migrate_multifd_channels(); + } +diff --git a/migration/multifd.h b/migration/multifd.h +index 11d5e273e6..9c0a2a0701 100644 +--- a/migration/multifd.h ++++ b/migration/multifd.h +@@ -20,7 +20,7 @@ void multifd_save_cleanup(void); + int multifd_load_setup(Error **errp); + 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_new_channel(QIOChannel *ioc, Error **errp); + void multifd_recv_sync_main(void); + int multifd_send_sync_main(QEMUFile *f); + int multifd_queue_page(QEMUFile *f, RAMBlock *block, ram_addr_t offset); +-- +2.37.3 + diff --git a/kvm-multifd-Copy-pages-before-compressing-them-with-zlib.patch b/kvm-multifd-Copy-pages-before-compressing-them-with-zlib.patch deleted file mode 100644 index ea89a9f..0000000 --- a/kvm-multifd-Copy-pages-before-compressing-them-with-zlib.patch +++ /dev/null @@ -1,142 +0,0 @@ -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/kvm-nbd-server-Allow-MULTI_CONN-for-shared-writable-expo.patch b/kvm-nbd-server-Allow-MULTI_CONN-for-shared-writable-expo.patch deleted file mode 100644 index 56abcb1..0000000 --- a/kvm-nbd-server-Allow-MULTI_CONN-for-shared-writable-expo.patch +++ /dev/null @@ -1,381 +0,0 @@ -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/kvm-pc-bios-s390-ccw-netboot.mak-Ignore-Clang-s-warnings.patch b/kvm-pc-bios-s390-ccw-netboot.mak-Ignore-Clang-s-warnings.patch deleted file mode 100644 index 00601aa..0000000 --- a/kvm-pc-bios-s390-ccw-netboot.mak-Ignore-Clang-s-warnings.patch +++ /dev/null @@ -1,78 +0,0 @@ -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/kvm-physmem-add-missing-memory-barrier.patch b/kvm-physmem-add-missing-memory-barrier.patch new file mode 100644 index 0000000..f6a2137 --- /dev/null +++ b/kvm-physmem-add-missing-memory-barrier.patch @@ -0,0 +1,55 @@ +From 01c09f31978154f0d2fd699621ae958a8c3ea2a5 Mon Sep 17 00:00:00 2001 +From: Emanuele Giuseppe Esposito +Date: Thu, 9 Mar 2023 08:15:24 -0500 +Subject: [PATCH 08/13] physmem: add missing memory barrier + +RH-Author: Emanuele Giuseppe Esposito +RH-MergeRequest: 263: qatomic: add smp_mb__before/after_rmw() +RH-Bugzilla: 2168472 +RH-Acked-by: Cornelia Huck +RH-Acked-by: Eric Auger +RH-Acked-by: Paolo Bonzini +RH-Acked-by: David Hildenbrand +RH-Commit: [8/10] f6a9659f7cf40b78de6e85e4a7c06842273aa770 + +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2168472 + +commit 33828ca11da08436e1b32f3e79dabce3061a0427 +Author: Paolo Bonzini +Date: Fri Mar 3 14:36:32 2023 +0100 + + physmem: add missing memory barrier + + Reviewed-by: Richard Henderson + Reviewed-by: David Hildenbrand + Signed-off-by: Paolo Bonzini + +Signed-off-by: Emanuele Giuseppe Esposito +--- + softmmu/physmem.c | 3 +++ + 1 file changed, 3 insertions(+) + +diff --git a/softmmu/physmem.c b/softmmu/physmem.c +index 4d0ef5f92f..2b96fad302 100644 +--- a/softmmu/physmem.c ++++ b/softmmu/physmem.c +@@ -3087,6 +3087,8 @@ void cpu_register_map_client(QEMUBH *bh) + qemu_mutex_lock(&map_client_list_lock); + client->bh = bh; + QLIST_INSERT_HEAD(&map_client_list, client, link); ++ /* Write map_client_list before reading in_use. */ ++ smp_mb(); + if (!qatomic_read(&bounce.in_use)) { + cpu_notify_map_clients_locked(); + } +@@ -3279,6 +3281,7 @@ void address_space_unmap(AddressSpace *as, void *buffer, hwaddr len, + qemu_vfree(bounce.buffer); + bounce.buffer = NULL; + memory_region_unref(bounce.mr); ++ /* Clear in_use before reading map_client_list. */ + qatomic_mb_set(&bounce.in_use, false); + cpu_notify_map_clients(); + } +-- +2.37.3 + diff --git a/kvm-qapi-machine.json-Add-cluster-id.patch b/kvm-qapi-machine.json-Add-cluster-id.patch deleted file mode 100644 index 2b2a22a..0000000 --- a/kvm-qapi-machine.json-Add-cluster-id.patch +++ /dev/null @@ -1,126 +0,0 @@ -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/kvm-qatomic-add-smp_mb__before-after_rmw.patch b/kvm-qatomic-add-smp_mb__before-after_rmw.patch new file mode 100644 index 0000000..3992f4e --- /dev/null +++ b/kvm-qatomic-add-smp_mb__before-after_rmw.patch @@ -0,0 +1,177 @@ +From e7d0e29d1962092af58d0445439671a6e1d91f71 Mon Sep 17 00:00:00 2001 +From: Emanuele Giuseppe Esposito +Date: Thu, 9 Mar 2023 08:10:33 -0500 +Subject: [PATCH 02/13] qatomic: add smp_mb__before/after_rmw() + +RH-Author: Emanuele Giuseppe Esposito +RH-MergeRequest: 263: qatomic: add smp_mb__before/after_rmw() +RH-Bugzilla: 2168472 +RH-Acked-by: Cornelia Huck +RH-Acked-by: Eric Auger +RH-Acked-by: Paolo Bonzini +RH-Acked-by: David Hildenbrand +RH-Commit: [2/10] 1f87eb3157abcf23f020881cedce42f76497f348 + +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2168472 + +commit ff00bed1897c3d27adc5b0cec6f6eeb5a7d13176 +Author: Paolo Bonzini +Date: Thu Mar 2 11:10:56 2023 +0100 + + qatomic: add smp_mb__before/after_rmw() + + On ARM, seqcst loads and stores (which QEMU does not use) are compiled + respectively as LDAR and STLR instructions. Even though LDAR is + also used for load-acquire operations, it also waits for all STLRs to + leave the store buffer. Thus, LDAR and STLR alone are load-acquire + and store-release operations, but LDAR also provides store-against-load + ordering as long as the previous store is a STLR. + + Compare this to ARMv7, where store-release is DMB+STR and load-acquire + is LDR+DMB, but an additional DMB is needed between store-seqcst and + load-seqcst (e.g. DMB+STR+DMB+LDR+DMB); or with x86, where MOV provides + load-acquire and store-release semantics and the two can be reordered. + + Likewise, on ARM sequentially consistent read-modify-write operations only + need to use LDAXR and STLXR respectively for the load and the store, while + on x86 they need to use the stronger LOCK prefix. + + In a strange twist of events, however, the _stronger_ semantics + of the ARM instructions can end up causing bugs on ARM, not on x86. + The problems occur when seqcst atomics are mixed with relaxed atomics. + + QEMU's atomics try to bridge the Linux API (that most of the developers + are familiar with) and the C11 API, and the two have a substantial + difference: + + - in Linux, strongly-ordered atomics such as atomic_add_return() affect + the global ordering of _all_ memory operations, including for example + READ_ONCE()/WRITE_ONCE() + + - in C11, sequentially consistent atomics (except for seq-cst fences) + only affect the ordering of sequentially consistent operations. + In particular, since relaxed loads are done with LDR on ARM, they are + not ordered against seqcst stores (which are done with STLR). + + QEMU implements high-level synchronization primitives with the idea that + the primitives contain the necessary memory barriers, and the callers can + use relaxed atomics (qatomic_read/qatomic_set) or even regular accesses. + This is very much incompatible with the C11 view that seqcst accesses + are only ordered against other seqcst accesses, and requires using seqcst + fences as in the following example: + + qatomic_set(&y, 1); qatomic_set(&x, 1); + smp_mb(); smp_mb(); + ... qatomic_read(&x) ... ... qatomic_read(&y) ... + + When a qatomic_*() read-modify write operation is used instead of one + or both stores, developers that are more familiar with the Linux API may + be tempted to omit the smp_mb(), which will work on x86 but not on ARM. + + This nasty difference between Linux and C11 read-modify-write operations + has already caused issues in util/async.c and more are being found. + Provide something similar to Linux smp_mb__before/after_atomic(); this + has the double function of documenting clearly why there is a memory + barrier, and avoiding a double barrier on x86 and s390x systems. + + The new macro can already be put to use in qatomic_mb_set(). + + Reviewed-by: Richard Henderson + Reviewed-by: David Hildenbrand + Signed-off-by: Paolo Bonzini + +Signed-off-by: Emanuele Giuseppe Esposito +--- + docs/devel/atomics.rst | 26 +++++++++++++++++++++----- + include/qemu/atomic.h | 17 ++++++++++++++++- + 2 files changed, 37 insertions(+), 6 deletions(-) + +diff --git a/docs/devel/atomics.rst b/docs/devel/atomics.rst +index 52baa0736d..10fbfc58bb 100644 +--- a/docs/devel/atomics.rst ++++ b/docs/devel/atomics.rst +@@ -25,7 +25,8 @@ provides macros that fall in three camps: + + - weak atomic access and manual memory barriers: ``qatomic_read()``, + ``qatomic_set()``, ``smp_rmb()``, ``smp_wmb()``, ``smp_mb()``, +- ``smp_mb_acquire()``, ``smp_mb_release()``, ``smp_read_barrier_depends()``; ++ ``smp_mb_acquire()``, ``smp_mb_release()``, ``smp_read_barrier_depends()``, ++ ``smp_mb__before_rmw()``, ``smp_mb__after_rmw()``; + + - sequentially consistent atomic access: everything else. + +@@ -470,7 +471,7 @@ and memory barriers, and the equivalents in QEMU: + sequential consistency. + + - in QEMU, ``qatomic_read()`` and ``qatomic_set()`` do not participate in +- the total ordering enforced by sequentially-consistent operations. ++ the ordering enforced by read-modify-write operations. + This is because QEMU uses the C11 memory model. The following example + is correct in Linux but not in QEMU: + +@@ -486,9 +487,24 @@ and memory barriers, and the equivalents in QEMU: + because the read of ``y`` can be moved (by either the processor or the + compiler) before the write of ``x``. + +- Fixing this requires an ``smp_mb()`` memory barrier between the write +- of ``x`` and the read of ``y``. In the common case where only one thread +- writes ``x``, it is also possible to write it like this: ++ Fixing this requires a full memory barrier between the write of ``x`` and ++ the read of ``y``. QEMU provides ``smp_mb__before_rmw()`` and ++ ``smp_mb__after_rmw()``; they act both as an optimization, ++ avoiding the memory barrier on processors where it is unnecessary, ++ and as a clarification of this corner case of the C11 memory model: ++ ++ +--------------------------------+ ++ | QEMU (correct) | ++ +================================+ ++ | :: | ++ | | ++ | a = qatomic_fetch_add(&x, 2);| ++ | smp_mb__after_rmw(); | ++ | b = qatomic_read(&y); | ++ +--------------------------------+ ++ ++ In the common case where only one thread writes ``x``, it is also possible ++ to write it like this: + + +--------------------------------+ + | QEMU (correct) | +diff --git a/include/qemu/atomic.h b/include/qemu/atomic.h +index 112a29910b..7855443cab 100644 +--- a/include/qemu/atomic.h ++++ b/include/qemu/atomic.h +@@ -243,6 +243,20 @@ + #define smp_wmb() smp_mb_release() + #define smp_rmb() smp_mb_acquire() + ++/* ++ * SEQ_CST is weaker than the older __sync_* builtins and Linux ++ * kernel read-modify-write atomics. Provide a macro to obtain ++ * the same semantics. ++ */ ++#if !defined(QEMU_SANITIZE_THREAD) && \ ++ (defined(__i386__) || defined(__x86_64__) || defined(__s390x__)) ++# define smp_mb__before_rmw() signal_barrier() ++# define smp_mb__after_rmw() signal_barrier() ++#else ++# define smp_mb__before_rmw() smp_mb() ++# define smp_mb__after_rmw() smp_mb() ++#endif ++ + /* qatomic_mb_read/set semantics map Java volatile variables. They are + * less expensive on some platforms (notably POWER) than fully + * sequentially consistent operations. +@@ -257,7 +271,8 @@ + #if !defined(__SANITIZE_THREAD__) && \ + (defined(__i386__) || defined(__x86_64__) || defined(__s390x__)) + /* This is more efficient than a store plus a fence. */ +-# define qatomic_mb_set(ptr, i) ((void)qatomic_xchg(ptr, i)) ++# define qatomic_mb_set(ptr, i) \ ++ ({ (void)qatomic_xchg(ptr, i); smp_mb__after_rmw(); }) + #else + # define qatomic_mb_set(ptr, i) \ + ({ qatomic_store_release(ptr, i); smp_mb(); }) +-- +2.37.3 + diff --git a/kvm-qcow2-Fix-theoretical-corruption-in-store_bitmap-err.patch b/kvm-qcow2-Fix-theoretical-corruption-in-store_bitmap-err.patch new file mode 100644 index 0000000..a57bf63 --- /dev/null +++ b/kvm-qcow2-Fix-theoretical-corruption-in-store_bitmap-err.patch @@ -0,0 +1,67 @@ +From 06c73c4b57dd1f47f819d719a63eb39fbe799304 Mon Sep 17 00:00:00 2001 +From: Kevin Wolf +Date: Thu, 12 Jan 2023 20:14:51 +0100 +Subject: [PATCH 1/4] qcow2: Fix theoretical corruption in store_bitmap() error + path +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Kevin Wolf +RH-MergeRequest: 251: qemu-img: Fix exit code for errors closing the image +RH-Bugzilla: 2147617 +RH-Acked-by: Hanna Czenczek +RH-Acked-by: Stefan Hajnoczi +RH-Acked-by: Stefano Garzarella +RH-Commit: [1/4] d0a26bed7b16db41e7baee1f8f2b3ae54e52dd52 + +In order to write the bitmap table to the image file, it is converted to +big endian. If the write fails, it is passed to clear_bitmap_table() to +free all of the clusters it had allocated before. However, if we don't +convert it back to native endianness first, we'll free things at a wrong +offset. + +In practical terms, the offsets will be so high that we won't actually +free any allocated clusters, but just run into an error, but in theory +this can cause image corruption. + +Cc: qemu-stable@nongnu.org +Signed-off-by: Kevin Wolf +Message-Id: <20230112191454.169353-2-kwolf@redhat.com> +Reviewed-by: Hanna Czenczek +Reviewed-by: Philippe Mathieu-Daudé +Signed-off-by: Kevin Wolf +(cherry picked from commit b03dd9613bcf8fe948581b2b3585510cb525c382) +Signed-off-by: Kevin Wolf +--- + block/qcow2-bitmap.c | 5 +++-- + 1 file changed, 3 insertions(+), 2 deletions(-) + +diff --git a/block/qcow2-bitmap.c b/block/qcow2-bitmap.c +index 8fb4731551..869069415c 100644 +--- a/block/qcow2-bitmap.c ++++ b/block/qcow2-bitmap.c +@@ -115,7 +115,7 @@ static int update_header_sync(BlockDriverState *bs) + return bdrv_flush(bs->file->bs); + } + +-static inline void bitmap_table_to_be(uint64_t *bitmap_table, size_t size) ++static inline void bitmap_table_bswap_be(uint64_t *bitmap_table, size_t size) + { + size_t i; + +@@ -1401,9 +1401,10 @@ static int store_bitmap(BlockDriverState *bs, Qcow2Bitmap *bm, Error **errp) + goto fail; + } + +- bitmap_table_to_be(tb, tb_size); ++ bitmap_table_bswap_be(tb, tb_size); + ret = bdrv_pwrite(bs->file, tb_offset, tb, tb_size * sizeof(tb[0])); + if (ret < 0) { ++ bitmap_table_bswap_be(tb, tb_size); + error_setg_errno(errp, -ret, "Failed to write bitmap '%s' to file", + bm_name); + goto fail; +-- +2.37.3 + diff --git a/kvm-qemu-coroutine-lock-add-smp_mb__after_rmw.patch b/kvm-qemu-coroutine-lock-add-smp_mb__after_rmw.patch new file mode 100644 index 0000000..95933af --- /dev/null +++ b/kvm-qemu-coroutine-lock-add-smp_mb__after_rmw.patch @@ -0,0 +1,75 @@ +From 2f03293910f3ac559f37d45c95325ae29638003a Mon Sep 17 00:00:00 2001 +From: Emanuele Giuseppe Esposito +Date: Thu, 9 Mar 2023 08:15:14 -0500 +Subject: [PATCH 07/13] qemu-coroutine-lock: add smp_mb__after_rmw() + +RH-Author: Emanuele Giuseppe Esposito +RH-MergeRequest: 263: qatomic: add smp_mb__before/after_rmw() +RH-Bugzilla: 2168472 +RH-Acked-by: Cornelia Huck +RH-Acked-by: Eric Auger +RH-Acked-by: Paolo Bonzini +RH-Acked-by: David Hildenbrand +RH-Commit: [7/10] 9cf1b6d3b0dd154489e75ad54a3000ea58983960 + +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2168472 + +commit e3a3b6ec8169eab2feb241b4982585001512cd55 +Author: Paolo Bonzini +Date: Fri Mar 3 10:52:59 2023 +0100 + + qemu-coroutine-lock: add smp_mb__after_rmw() + + mutex->from_push and mutex->handoff in qemu-coroutine-lock implement + the familiar pattern: + + write a write b + smp_mb() smp_mb() + read b read a + + The memory barrier is required by the C memory model even after a + SEQ_CST read-modify-write operation such as QSLIST_INSERT_HEAD_ATOMIC. + Add it and avoid the unclear qatomic_mb_read() operation. + + Reviewed-by: Richard Henderson + Reviewed-by: David Hildenbrand + Signed-off-by: Paolo Bonzini + +Signed-off-by: Emanuele Giuseppe Esposito +--- + util/qemu-coroutine-lock.c | 9 ++++++++- + 1 file changed, 8 insertions(+), 1 deletion(-) + +diff --git a/util/qemu-coroutine-lock.c b/util/qemu-coroutine-lock.c +index 2669403839..a03ed0e664 100644 +--- a/util/qemu-coroutine-lock.c ++++ b/util/qemu-coroutine-lock.c +@@ -206,10 +206,16 @@ static void coroutine_fn qemu_co_mutex_lock_slowpath(AioContext *ctx, + trace_qemu_co_mutex_lock_entry(mutex, self); + push_waiter(mutex, &w); + ++ /* ++ * Add waiter before reading mutex->handoff. Pairs with qatomic_mb_set ++ * in qemu_co_mutex_unlock. ++ */ ++ smp_mb__after_rmw(); ++ + /* This is the "Responsibility Hand-Off" protocol; a lock() picks from + * a concurrent unlock() the responsibility of waking somebody up. + */ +- old_handoff = qatomic_mb_read(&mutex->handoff); ++ old_handoff = qatomic_read(&mutex->handoff); + if (old_handoff && + has_waiters(mutex) && + qatomic_cmpxchg(&mutex->handoff, old_handoff, 0) == old_handoff) { +@@ -308,6 +314,7 @@ void coroutine_fn qemu_co_mutex_unlock(CoMutex *mutex) + } + + our_handoff = mutex->sequence; ++ /* Set handoff before checking for waiters. */ + qatomic_mb_set(&mutex->handoff, our_handoff); + if (!has_waiters(mutex)) { + /* The concurrent lock has not added itself yet, so it +-- +2.37.3 + diff --git a/kvm-qemu-img-bitmap-Report-errors-while-closing-the-imag.patch b/kvm-qemu-img-bitmap-Report-errors-while-closing-the-imag.patch new file mode 100644 index 0000000..ae9850e --- /dev/null +++ b/kvm-qemu-img-bitmap-Report-errors-while-closing-the-imag.patch @@ -0,0 +1,70 @@ +From 648193b48d8aeaded90fd657e3610d8040f505fc Mon Sep 17 00:00:00 2001 +From: Kevin Wolf +Date: Thu, 12 Jan 2023 20:14:53 +0100 +Subject: [PATCH 3/4] qemu-img bitmap: Report errors while closing the image +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Kevin Wolf +RH-MergeRequest: 251: qemu-img: Fix exit code for errors closing the image +RH-Bugzilla: 2147617 +RH-Acked-by: Hanna Czenczek +RH-Acked-by: Stefan Hajnoczi +RH-Acked-by: Stefano Garzarella +RH-Commit: [3/4] 8e13e09564718a0badd03af84f036246a46a0eba + +blk_unref() can't report any errors that happen while closing the image. +For example, if qcow2 hits an -ENOSPC error while writing out dirty +bitmaps when it's closed, it prints error messages to stderr, but +'qemu-img bitmap' won't see any error return value and will therefore +look successful with exit code 0. + +In order to fix this, manually inactivate the image first before calling +blk_unref(). This already performs the operations that would be most +likely to fail while closing the image, but it can still return errors. + +Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1330 +Signed-off-by: Kevin Wolf +Message-Id: <20230112191454.169353-4-kwolf@redhat.com> +Reviewed-by: Hanna Czenczek +Reviewed-by: Philippe Mathieu-Daudé +Signed-off-by: Kevin Wolf +(cherry picked from commit c5e477110dcb8ef4642dce399777c3dee68fa96c) +Signed-off-by: Kevin Wolf +--- + qemu-img.c | 11 +++++++++++ + 1 file changed, 11 insertions(+) + +diff --git a/qemu-img.c b/qemu-img.c +index 18833f7d69..7d035c0c7f 100644 +--- a/qemu-img.c ++++ b/qemu-img.c +@@ -4622,6 +4622,7 @@ static int img_bitmap(int argc, char **argv) + QSIMPLEQ_HEAD(, ImgBitmapAction) actions; + ImgBitmapAction *act, *act_next; + const char *op; ++ int inactivate_ret; + + QSIMPLEQ_INIT(&actions); + +@@ -4806,6 +4807,16 @@ static int img_bitmap(int argc, char **argv) + ret = 0; + + out: ++ /* ++ * Manually inactivate the images first because this way we can know whether ++ * an error occurred. blk_unref() doesn't tell us about failures. ++ */ ++ inactivate_ret = bdrv_inactivate_all(); ++ if (inactivate_ret < 0) { ++ error_report("Error while closing the image: %s", strerror(-inactivate_ret)); ++ ret = 1; ++ } ++ + blk_unref(src); + blk_unref(blk); + qemu_opts_del(opts); +-- +2.37.3 + diff --git a/kvm-qemu-img-commit-Report-errors-while-closing-the-imag.patch b/kvm-qemu-img-commit-Report-errors-while-closing-the-imag.patch new file mode 100644 index 0000000..32d3d9d --- /dev/null +++ b/kvm-qemu-img-commit-Report-errors-while-closing-the-imag.patch @@ -0,0 +1,67 @@ +From 2396df7fe527567e8e78761ef24ea1057ef6fa48 Mon Sep 17 00:00:00 2001 +From: Kevin Wolf +Date: Thu, 12 Jan 2023 20:14:52 +0100 +Subject: [PATCH 2/4] qemu-img commit: Report errors while closing the image + +RH-Author: Kevin Wolf +RH-MergeRequest: 251: qemu-img: Fix exit code for errors closing the image +RH-Bugzilla: 2147617 +RH-Acked-by: Hanna Czenczek +RH-Acked-by: Stefan Hajnoczi +RH-Acked-by: Stefano Garzarella +RH-Commit: [2/4] 28f95bf76d1d63e2b0bed0c2ba5206bd3e5ea4f8 + +blk_unref() can't report any errors that happen while closing the image. +For example, if qcow2 hits an -ENOSPC error while writing out dirty +bitmaps when it's closed, it prints error messages to stderr, but +'qemu-img commit' won't see any error return value and will therefore +look successful with exit code 0. + +In order to fix this, manually inactivate the image first before calling +blk_unref(). This already performs the operations that would be most +likely to fail while closing the image, but it can still return errors. + +Signed-off-by: Kevin Wolf +Message-Id: <20230112191454.169353-3-kwolf@redhat.com> +Reviewed-by: Hanna Czenczek +Signed-off-by: Kevin Wolf +(cherry picked from commit 44efba2d713aca076c411594d0c1a2b99155eeb3) +Signed-off-by: Kevin Wolf +--- + qemu-img.c | 13 +++++++++++++ + 1 file changed, 13 insertions(+) + +diff --git a/qemu-img.c b/qemu-img.c +index f036a1d428..18833f7d69 100644 +--- a/qemu-img.c ++++ b/qemu-img.c +@@ -443,6 +443,11 @@ static BlockBackend *img_open(bool image_opts, + blk = img_open_file(filename, NULL, fmt, flags, writethrough, quiet, + force_share); + } ++ ++ if (blk) { ++ blk_set_force_allow_inactivate(blk); ++ } ++ + return blk; + } + +@@ -1110,6 +1115,14 @@ unref_backing: + done: + qemu_progress_end(); + ++ /* ++ * Manually inactivate the image first because this way we can know whether ++ * an error occurred. blk_unref() doesn't tell us about failures. ++ */ ++ ret = bdrv_inactivate_all(); ++ if (ret < 0 && !local_err) { ++ error_setg_errno(&local_err, -ret, "Error while closing the image"); ++ } + blk_unref(blk); + + if (local_err) { +-- +2.37.3 + diff --git a/kvm-qemu-iotests-Test-qemu-img-bitmap-commit-exit-code-o.patch b/kvm-qemu-iotests-Test-qemu-img-bitmap-commit-exit-code-o.patch new file mode 100644 index 0000000..31e60a3 --- /dev/null +++ b/kvm-qemu-iotests-Test-qemu-img-bitmap-commit-exit-code-o.patch @@ -0,0 +1,166 @@ +From 7c6faae20638f58681df223e0ca44e0a6cb60d2d Mon Sep 17 00:00:00 2001 +From: Kevin Wolf +Date: Thu, 12 Jan 2023 20:14:54 +0100 +Subject: [PATCH 4/4] qemu-iotests: Test qemu-img bitmap/commit exit code on + error + +RH-Author: Kevin Wolf +RH-MergeRequest: 251: qemu-img: Fix exit code for errors closing the image +RH-Bugzilla: 2147617 +RH-Acked-by: Hanna Czenczek +RH-Acked-by: Stefan Hajnoczi +RH-Acked-by: Stefano Garzarella +RH-Commit: [4/4] fb2f9de98ddd2ee1d745119e4f15272ef44e0aae + +This tests that when an error happens while writing back bitmaps to the +image file in qcow2_inactivate(), 'qemu-img bitmap/commit' actually +return an error value in their exit code instead of making the operation +look successful to scripts. + +Signed-off-by: Kevin Wolf +Message-Id: <20230112191454.169353-5-kwolf@redhat.com> +Reviewed-by: Hanna Czenczek +Signed-off-by: Kevin Wolf +(cherry picked from commit 07a4e1f8e5418f36424cd57d5d061b090a238c65) +Signed-off-by: Kevin Wolf +--- + .../qemu-iotests/tests/qemu-img-close-errors | 96 +++++++++++++++++++ + .../tests/qemu-img-close-errors.out | 23 +++++ + 2 files changed, 119 insertions(+) + create mode 100755 tests/qemu-iotests/tests/qemu-img-close-errors + create mode 100644 tests/qemu-iotests/tests/qemu-img-close-errors.out + +diff --git a/tests/qemu-iotests/tests/qemu-img-close-errors b/tests/qemu-iotests/tests/qemu-img-close-errors +new file mode 100755 +index 0000000000..50bfb6cfa2 +--- /dev/null ++++ b/tests/qemu-iotests/tests/qemu-img-close-errors +@@ -0,0 +1,96 @@ ++#!/usr/bin/env bash ++# group: rw auto quick ++# ++# Check that errors while closing the image, in particular writing back dirty ++# bitmaps, is correctly reported with a failing qemu-img exit code. ++# ++# Copyright (C) 2023 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 . ++# ++ ++# creator ++owner=kwolf@redhat.com ++ ++seq="$(basename $0)" ++echo "QA output created by $seq" ++ ++status=1 # failure is the default! ++ ++_cleanup() ++{ ++ _cleanup_test_img ++} ++trap "_cleanup; exit \$status" 0 1 2 3 15 ++ ++# get standard environment, filters and checks ++cd .. ++. ./common.rc ++. ./common.filter ++ ++_supported_fmt qcow2 ++_supported_proto file ++_supported_os Linux ++ ++size=1G ++ ++# The error we are going to use is ENOSPC. Depending on how many bitmaps we ++# create in the backing file (and therefore increase the used up space), we get ++# failures in different places. With a low number, only merging the bitmap ++# fails, whereas with a higher number, already 'qemu-img commit' fails. ++for max_bitmap in 6 7; do ++ echo ++ echo "=== Test with $max_bitmap bitmaps ===" ++ ++ TEST_IMG="$TEST_IMG.base" _make_test_img -q $size ++ for i in $(seq 1 $max_bitmap); do ++ $QEMU_IMG bitmap --add "$TEST_IMG.base" "stale-bitmap-$i" ++ done ++ ++ # Simulate a block device of 128 MB by resizing the image file accordingly ++ # and then enforcing the size with the raw driver ++ $QEMU_IO -f raw -c "truncate 128M" "$TEST_IMG.base" ++ BASE_JSON='json:{ ++ "driver": "qcow2", ++ "file": { ++ "driver": "raw", ++ "size": 134217728, ++ "file": { ++ "driver": "file", ++ "filename":"'"$TEST_IMG.base"'" ++ } ++ } ++ }' ++ ++ _make_test_img -q -b "$BASE_JSON" -F $IMGFMT ++ $QEMU_IMG bitmap --add "$TEST_IMG" "good-bitmap" ++ ++ $QEMU_IO -c 'write 0 126m' "$TEST_IMG" | _filter_qemu_io ++ ++ $QEMU_IMG commit -d "$TEST_IMG" 2>&1 | _filter_generated_node_ids ++ echo "qemu-img commit exit code: ${PIPESTATUS[0]}" ++ ++ $QEMU_IMG bitmap --add "$BASE_JSON" "good-bitmap" ++ echo "qemu-img bitmap --add exit code: $?" ++ ++ $QEMU_IMG bitmap --merge "good-bitmap" -b "$TEST_IMG" "$BASE_JSON" \ ++ "good-bitmap" 2>&1 | _filter_generated_node_ids ++ echo "qemu-img bitmap --merge exit code: ${PIPESTATUS[0]}" ++done ++ ++# success, all done ++echo "*** done" ++rm -f $seq.full ++status=0 ++ +diff --git a/tests/qemu-iotests/tests/qemu-img-close-errors.out b/tests/qemu-iotests/tests/qemu-img-close-errors.out +new file mode 100644 +index 0000000000..1bfe88f176 +--- /dev/null ++++ b/tests/qemu-iotests/tests/qemu-img-close-errors.out +@@ -0,0 +1,23 @@ ++QA output created by qemu-img-close-errors ++ ++=== Test with 6 bitmaps === ++wrote 132120576/132120576 bytes at offset 0 ++126 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ++Image committed. ++qemu-img commit exit code: 0 ++qemu-img bitmap --add exit code: 0 ++qemu-img: Lost persistent bitmaps during inactivation of node 'NODE_NAME': Failed to write bitmap 'good-bitmap' to file: No space left on device ++qemu-img: Error while closing the image: Invalid argument ++qemu-img: Lost persistent bitmaps during inactivation of node 'NODE_NAME': Failed to write bitmap 'good-bitmap' to file: No space left on device ++qemu-img bitmap --merge exit code: 1 ++ ++=== Test with 7 bitmaps === ++wrote 132120576/132120576 bytes at offset 0 ++126 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ++qemu-img: Lost persistent bitmaps during inactivation of node 'NODE_NAME': Failed to write bitmap 'stale-bitmap-7' to file: No space left on device ++qemu-img: Lost persistent bitmaps during inactivation of node 'NODE_NAME': Failed to write bitmap 'stale-bitmap-7' to file: No space left on device ++qemu-img: Error while closing the image: Invalid argument ++qemu-img commit exit code: 1 ++qemu-img bitmap --add exit code: 0 ++qemu-img bitmap --merge exit code: 0 ++*** done +-- +2.37.3 + diff --git a/kvm-qemu-nbd-Pass-max-connections-to-blockdev-layer.patch b/kvm-qemu-nbd-Pass-max-connections-to-blockdev-layer.patch deleted file mode 100644 index 9acff58..0000000 --- a/kvm-qemu-nbd-Pass-max-connections-to-blockdev-layer.patch +++ /dev/null @@ -1,92 +0,0 @@ -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/kvm-qemu-thread-posix-cleanup-fix-document-QemuEvent.patch b/kvm-qemu-thread-posix-cleanup-fix-document-QemuEvent.patch new file mode 100644 index 0000000..0051baf --- /dev/null +++ b/kvm-qemu-thread-posix-cleanup-fix-document-QemuEvent.patch @@ -0,0 +1,146 @@ +From d46ca52c3f42add549bd3790a41d06594821334e Mon Sep 17 00:00:00 2001 +From: Emanuele Giuseppe Esposito +Date: Thu, 9 Mar 2023 08:10:57 -0500 +Subject: [PATCH 03/13] qemu-thread-posix: cleanup, fix, document QemuEvent + +RH-Author: Emanuele Giuseppe Esposito +RH-MergeRequest: 263: qatomic: add smp_mb__before/after_rmw() +RH-Bugzilla: 2168472 +RH-Acked-by: Cornelia Huck +RH-Acked-by: Eric Auger +RH-Acked-by: Paolo Bonzini +RH-Acked-by: David Hildenbrand +RH-Commit: [3/10] 746070c4d78c7f0a9ac4456d9aee69475acb8964 + +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2168472 + +commit 9586a1329f5dce6c1d7f4de53cf0536644d7e593 +Author: Paolo Bonzini +Date: Thu Mar 2 11:19:52 2023 +0100 + + qemu-thread-posix: cleanup, fix, document QemuEvent + + QemuEvent is currently broken on ARM due to missing memory barriers + after qatomic_*(). Apart from adding the memory barrier, a closer look + reveals some unpaired memory barriers too. Document more clearly what + is going on. + + Reviewed-by: Richard Henderson + Reviewed-by: David Hildenbrand + Signed-off-by: Paolo Bonzini + +Signed-off-by: Emanuele Giuseppe Esposito +--- + util/qemu-thread-posix.c | 69 ++++++++++++++++++++++++++++------------ + 1 file changed, 49 insertions(+), 20 deletions(-) + +diff --git a/util/qemu-thread-posix.c b/util/qemu-thread-posix.c +index e1225b63bd..dd3b6d4670 100644 +--- a/util/qemu-thread-posix.c ++++ b/util/qemu-thread-posix.c +@@ -430,13 +430,21 @@ void qemu_event_destroy(QemuEvent *ev) + + void qemu_event_set(QemuEvent *ev) + { +- /* qemu_event_set has release semantics, but because it *loads* ++ assert(ev->initialized); ++ ++ /* ++ * Pairs with both qemu_event_reset() and qemu_event_wait(). ++ * ++ * qemu_event_set has release semantics, but because it *loads* + * ev->value we need a full memory barrier here. + */ +- assert(ev->initialized); + smp_mb(); + if (qatomic_read(&ev->value) != EV_SET) { +- if (qatomic_xchg(&ev->value, EV_SET) == EV_BUSY) { ++ int old = qatomic_xchg(&ev->value, EV_SET); ++ ++ /* Pairs with memory barrier in kernel futex_wait system call. */ ++ smp_mb__after_rmw(); ++ if (old == EV_BUSY) { + /* There were waiters, wake them up. */ + qemu_futex_wake(ev, INT_MAX); + } +@@ -445,18 +453,19 @@ void qemu_event_set(QemuEvent *ev) + + void qemu_event_reset(QemuEvent *ev) + { +- unsigned value; +- + assert(ev->initialized); +- value = qatomic_read(&ev->value); +- smp_mb_acquire(); +- if (value == EV_SET) { +- /* +- * If there was a concurrent reset (or even reset+wait), +- * do nothing. Otherwise change EV_SET->EV_FREE. +- */ +- qatomic_or(&ev->value, EV_FREE); +- } ++ ++ /* ++ * If there was a concurrent reset (or even reset+wait), ++ * do nothing. Otherwise change EV_SET->EV_FREE. ++ */ ++ qatomic_or(&ev->value, EV_FREE); ++ ++ /* ++ * Order reset before checking the condition in the caller. ++ * Pairs with the first memory barrier in qemu_event_set(). ++ */ ++ smp_mb__after_rmw(); + } + + void qemu_event_wait(QemuEvent *ev) +@@ -464,20 +473,40 @@ void qemu_event_wait(QemuEvent *ev) + unsigned value; + + assert(ev->initialized); +- value = qatomic_read(&ev->value); +- smp_mb_acquire(); ++ ++ /* ++ * qemu_event_wait must synchronize with qemu_event_set even if it does ++ * not go down the slow path, so this load-acquire is needed that ++ * synchronizes with the first memory barrier in qemu_event_set(). ++ * ++ * If we do go down the slow path, there is no requirement at all: we ++ * might miss a qemu_event_set() here but ultimately the memory barrier in ++ * qemu_futex_wait() will ensure the check is done correctly. ++ */ ++ value = qatomic_load_acquire(&ev->value); + if (value != EV_SET) { + if (value == EV_FREE) { + /* +- * Leave the event reset and tell qemu_event_set that there +- * are waiters. No need to retry, because there cannot be +- * a concurrent busy->free transition. After the CAS, the +- * event will be either set or busy. ++ * Leave the event reset and tell qemu_event_set that there are ++ * waiters. No need to retry, because there cannot be a concurrent ++ * busy->free transition. After the CAS, the event will be either ++ * set or busy. ++ * ++ * This cmpxchg doesn't have particular ordering requirements if it ++ * succeeds (moving the store earlier can only cause qemu_event_set() ++ * to issue _more_ wakeups), the failing case needs acquire semantics ++ * like the load above. + */ + if (qatomic_cmpxchg(&ev->value, EV_FREE, EV_BUSY) == EV_SET) { + return; + } + } ++ ++ /* ++ * This is the final check for a concurrent set, so it does need ++ * a smp_mb() pairing with the second barrier of qemu_event_set(). ++ * The barrier is inside the FUTEX_WAIT system call. ++ */ + qemu_futex_wait(ev, EV_BUSY); + } + } +-- +2.37.3 + diff --git a/kvm-qemu-thread-win32-cleanup-fix-document-QemuEvent.patch b/kvm-qemu-thread-win32-cleanup-fix-document-QemuEvent.patch new file mode 100644 index 0000000..3b63378 --- /dev/null +++ b/kvm-qemu-thread-win32-cleanup-fix-document-QemuEvent.patch @@ -0,0 +1,162 @@ +From fa730378c42567e77eaf3e70983108f31f9001b9 Mon Sep 17 00:00:00 2001 +From: Emanuele Giuseppe Esposito +Date: Thu, 9 Mar 2023 08:11:05 -0500 +Subject: [PATCH 04/13] qemu-thread-win32: cleanup, fix, document QemuEvent + +RH-Author: Emanuele Giuseppe Esposito +RH-MergeRequest: 263: qatomic: add smp_mb__before/after_rmw() +RH-Bugzilla: 2168472 +RH-Acked-by: Cornelia Huck +RH-Acked-by: Eric Auger +RH-Acked-by: Paolo Bonzini +RH-Acked-by: David Hildenbrand +RH-Commit: [4/10] 43d5bd903b460d4c3c5793a456820e8c5c8521d9 + +Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2168472 + +commit 6c5df4b48f0c52a61342ecb307a43f4c2a3565c4 +Author: Paolo Bonzini +Date: Thu Mar 2 11:22:50 2023 +0100 + + qemu-thread-win32: cleanup, fix, document QemuEvent + + QemuEvent is currently broken on ARM due to missing memory barriers + after qatomic_*(). Apart from adding the memory barrier, a closer look + reveals some unpaired memory barriers that are not really needed and + complicated the functions unnecessarily. Also, it is relying on + a memory barrier in ResetEvent(); the barrier _ought_ to be there + but there is really no documentation about it, so make it explicit. + + Reviewed-by: Richard Henderson + Reviewed-by: David Hildenbrand + Signed-off-by: Paolo Bonzini + +Signed-off-by: Emanuele Giuseppe Esposito +--- + util/qemu-thread-win32.c | 82 +++++++++++++++++++++++++++------------- + 1 file changed, 56 insertions(+), 26 deletions(-) + +diff --git a/util/qemu-thread-win32.c b/util/qemu-thread-win32.c +index 52eb19f351..c10249bc2e 100644 +--- a/util/qemu-thread-win32.c ++++ b/util/qemu-thread-win32.c +@@ -246,12 +246,20 @@ void qemu_event_destroy(QemuEvent *ev) + void qemu_event_set(QemuEvent *ev) + { + assert(ev->initialized); +- /* qemu_event_set has release semantics, but because it *loads* ++ ++ /* ++ * Pairs with both qemu_event_reset() and qemu_event_wait(). ++ * ++ * qemu_event_set has release semantics, but because it *loads* + * ev->value we need a full memory barrier here. + */ + smp_mb(); + if (qatomic_read(&ev->value) != EV_SET) { +- if (qatomic_xchg(&ev->value, EV_SET) == EV_BUSY) { ++ int old = qatomic_xchg(&ev->value, EV_SET); ++ ++ /* Pairs with memory barrier after ResetEvent. */ ++ smp_mb__after_rmw(); ++ if (old == EV_BUSY) { + /* There were waiters, wake them up. */ + SetEvent(ev->event); + } +@@ -260,17 +268,19 @@ void qemu_event_set(QemuEvent *ev) + + void qemu_event_reset(QemuEvent *ev) + { +- unsigned value; +- + assert(ev->initialized); +- value = qatomic_read(&ev->value); +- smp_mb_acquire(); +- if (value == EV_SET) { +- /* If there was a concurrent reset (or even reset+wait), +- * do nothing. Otherwise change EV_SET->EV_FREE. +- */ +- qatomic_or(&ev->value, EV_FREE); +- } ++ ++ /* ++ * If there was a concurrent reset (or even reset+wait), ++ * do nothing. Otherwise change EV_SET->EV_FREE. ++ */ ++ qatomic_or(&ev->value, EV_FREE); ++ ++ /* ++ * Order reset before checking the condition in the caller. ++ * Pairs with the first memory barrier in qemu_event_set(). ++ */ ++ smp_mb__after_rmw(); + } + + void qemu_event_wait(QemuEvent *ev) +@@ -278,29 +288,49 @@ void qemu_event_wait(QemuEvent *ev) + unsigned value; + + assert(ev->initialized); +- value = qatomic_read(&ev->value); +- smp_mb_acquire(); ++ ++ /* ++ * qemu_event_wait must synchronize with qemu_event_set even if it does ++ * not go down the slow path, so this load-acquire is needed that ++ * synchronizes with the first memory barrier in qemu_event_set(). ++ * ++ * If we do go down the slow path, there is no requirement at all: we ++ * might miss a qemu_event_set() here but ultimately the memory barrier in ++ * qemu_futex_wait() will ensure the check is done correctly. ++ */ ++ value = qatomic_load_acquire(&ev->value); + if (value != EV_SET) { + if (value == EV_FREE) { +- /* qemu_event_set is not yet going to call SetEvent, but we are +- * going to do another check for EV_SET below when setting EV_BUSY. +- * At that point it is safe to call WaitForSingleObject. ++ /* ++ * Here the underlying kernel event is reset, but qemu_event_set is ++ * not yet going to call SetEvent. However, there will be another ++ * check for EV_SET below when setting EV_BUSY. At that point it ++ * is safe to call WaitForSingleObject. + */ + ResetEvent(ev->event); + +- /* Tell qemu_event_set that there are waiters. No need to retry +- * because there cannot be a concurrent busy->free transition. +- * After the CAS, the event will be either set or busy. ++ /* ++ * It is not clear whether ResetEvent provides this barrier; kernel ++ * APIs (KeResetEvent/KeClearEvent) do not. Better safe than sorry! ++ */ ++ smp_mb(); ++ ++ /* ++ * Leave the event reset and tell qemu_event_set that there are ++ * waiters. No need to retry, because there cannot be a concurrent ++ * busy->free transition. After the CAS, the event will be either ++ * set or busy. + */ + if (qatomic_cmpxchg(&ev->value, EV_FREE, EV_BUSY) == EV_SET) { +- value = EV_SET; +- } else { +- value = EV_BUSY; ++ return; + } + } +- if (value == EV_BUSY) { +- WaitForSingleObject(ev->event, INFINITE); +- } ++ ++ /* ++ * ev->value is now EV_BUSY. Since we didn't observe EV_SET, ++ * qemu_event_set() must observe EV_BUSY and call SetEvent(). ++ */ ++ WaitForSingleObject(ev->event, INFINITE); + } + } + +-- +2.37.3 + diff --git a/kvm-qtest-numa-test-Correct-CPU-and-NUMA-association-in-.patch b/kvm-qtest-numa-test-Correct-CPU-and-NUMA-association-in-.patch deleted file mode 100644 index 9c2ac99..0000000 --- a/kvm-qtest-numa-test-Correct-CPU-and-NUMA-association-in-.patch +++ /dev/null @@ -1,100 +0,0 @@ -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/kvm-qtest-numa-test-Specify-CPU-topology-in-aarch64_numa.patch b/kvm-qtest-numa-test-Specify-CPU-topology-in-aarch64_numa.patch deleted file mode 100644 index a87abc0..0000000 --- a/kvm-qtest-numa-test-Specify-CPU-topology-in-aarch64_numa.patch +++ /dev/null @@ -1,68 +0,0 @@ -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/kvm-s390x-pci-RPCIT-second-pass-when-mappings-exhausted.patch b/kvm-s390x-pci-RPCIT-second-pass-when-mappings-exhausted.patch new file mode 100644 index 0000000..2e90869 --- /dev/null +++ b/kvm-s390x-pci-RPCIT-second-pass-when-mappings-exhausted.patch @@ -0,0 +1,114 @@ +From 2f0febd6813c4ad7f52e43afb3ecce7aef3557e6 Mon Sep 17 00:00:00 2001 +From: Matthew Rosato +Date: Fri, 28 Oct 2022 15:47:56 -0400 +Subject: [PATCH 08/11] s390x/pci: RPCIT second pass when mappings exhausted +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Cédric Le Goater +RH-MergeRequest: 250: s390x/pci: reset ISM passthrough devices on shutdown and system reset +RH-Bugzilla: 2163713 +RH-Acked-by: Thomas Huth +RH-Acked-by: Cornelia Huck +RH-Acked-by: Miroslav Rezanina +RH-Commit: [1/4] 0b4500b9247725b1ef0b290bb85392300a618cac + +If we encounter a new mapping while the number of available DMA entries +in vfio is 0, we are currently skipping that mapping which is a problem +if we manage to free up DMA space after that within the same RPCIT -- +we will return to the guest with CC0 and have not mapped everything +within the specified range. This issue was uncovered while testing +changes to the s390 linux kernel iommu/dma code, where a different +usage pattern was employed (new mappings start at the end of the +aperture and work back towards the front, making us far more likely +to encounter new mappings before invalidated mappings during a +global refresh). + +Fix this by tracking whether any mappings were skipped due to vfio +DMA limit hitting 0; when this occurs, we still continue the range +and unmap/map anything we can - then we must re-run the range again +to pickup anything that was missed. This must occur in a loop until +all requests are satisfied (success) or we detect that we are still +unable to complete all mappings (return ZPCI_RPCIT_ST_INSUFF_RES). + +Link: https://lore.kernel.org/linux-s390/20221019144435.369902-1-schnelle@linux.ibm.com/ +Fixes: 37fa32de70 ("s390x/pci: Honor DMA limits set by vfio") +Reported-by: Niklas Schnelle +Signed-off-by: Matthew Rosato +Message-Id: <20221028194758.204007-2-mjrosato@linux.ibm.com> +Reviewed-by: Eric Farman +Signed-off-by: Thomas Huth +(cherry picked from commit 4a8d21ba50fc8625c3bd51dab903872952f95718) +Signed-off-by: Cédric Le Goater +--- + hw/s390x/s390-pci-inst.c | 29 ++++++++++++++++++++++------- + 1 file changed, 22 insertions(+), 7 deletions(-) + +diff --git a/hw/s390x/s390-pci-inst.c b/hw/s390x/s390-pci-inst.c +index 20a9bcc7af..7cc4bcf850 100644 +--- a/hw/s390x/s390-pci-inst.c ++++ b/hw/s390x/s390-pci-inst.c +@@ -677,8 +677,9 @@ int rpcit_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2, uintptr_t ra) + S390PCIBusDevice *pbdev; + S390PCIIOMMU *iommu; + S390IOTLBEntry entry; +- hwaddr start, end; ++ hwaddr start, end, sstart; + uint32_t dma_avail; ++ bool again; + + if (env->psw.mask & PSW_MASK_PSTATE) { + s390_program_interrupt(env, PGM_PRIVILEGED, ra); +@@ -691,7 +692,7 @@ int rpcit_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2, uintptr_t ra) + } + + fh = env->regs[r1] >> 32; +- start = env->regs[r2]; ++ sstart = start = env->regs[r2]; + end = start + env->regs[r2 + 1]; + + pbdev = s390_pci_find_dev_by_fh(s390_get_phb(), fh); +@@ -732,6 +733,9 @@ int rpcit_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2, uintptr_t ra) + goto err; + } + ++ retry: ++ start = sstart; ++ again = false; + while (start < end) { + error = s390_guest_io_table_walk(iommu->g_iota, start, &entry); + if (error) { +@@ -739,13 +743,24 @@ int rpcit_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2, uintptr_t ra) + } + + start += entry.len; +- while (entry.iova < start && entry.iova < end && +- (dma_avail > 0 || entry.perm == IOMMU_NONE)) { +- dma_avail = s390_pci_update_iotlb(iommu, &entry); +- entry.iova += TARGET_PAGE_SIZE; +- entry.translated_addr += TARGET_PAGE_SIZE; ++ while (entry.iova < start && entry.iova < end) { ++ if (dma_avail > 0 || entry.perm == IOMMU_NONE) { ++ dma_avail = s390_pci_update_iotlb(iommu, &entry); ++ entry.iova += TARGET_PAGE_SIZE; ++ entry.translated_addr += TARGET_PAGE_SIZE; ++ } else { ++ /* ++ * We are unable to make a new mapping at this time, continue ++ * on and hopefully free up more space. Then attempt another ++ * pass. ++ */ ++ again = true; ++ break; ++ } + } + } ++ if (again && dma_avail > 0) ++ goto retry; + err: + if (error) { + pbdev->state = ZPCI_FS_ERROR; +-- +2.37.3 + diff --git a/kvm-s390x-pci-coalesce-unmap-operations.patch b/kvm-s390x-pci-coalesce-unmap-operations.patch new file mode 100644 index 0000000..baa0a9c --- /dev/null +++ b/kvm-s390x-pci-coalesce-unmap-operations.patch @@ -0,0 +1,125 @@ +From b972c5a2763a91024725c147cf1691ed8e180c7c Mon Sep 17 00:00:00 2001 +From: Matthew Rosato +Date: Fri, 28 Oct 2022 15:47:57 -0400 +Subject: [PATCH 09/11] s390x/pci: coalesce unmap operations +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Cédric Le Goater +RH-MergeRequest: 250: s390x/pci: reset ISM passthrough devices on shutdown and system reset +RH-Bugzilla: 2163713 +RH-Acked-by: Thomas Huth +RH-Acked-by: Cornelia Huck +RH-Acked-by: Miroslav Rezanina +RH-Commit: [2/4] 7b5ee38eca565f5a7cbede4b9883ba3a508fb46c + +Currently, each unmapped page is handled as an individual iommu +region notification. Attempt to group contiguous unmap operations +into fewer notifications to reduce overhead. + +Signed-off-by: Matthew Rosato +Message-Id: <20221028194758.204007-3-mjrosato@linux.ibm.com> +Reviewed-by: Eric Farman +Signed-off-by: Thomas Huth +(cherry picked from commit ef536007c3301bbd6a787e4c2210ea289adaa6f0) +Signed-off-by: Cédric Le Goater +--- + hw/s390x/s390-pci-inst.c | 51 ++++++++++++++++++++++++++++++++++++++++ + 1 file changed, 51 insertions(+) + +diff --git a/hw/s390x/s390-pci-inst.c b/hw/s390x/s390-pci-inst.c +index 7cc4bcf850..66e764f901 100644 +--- a/hw/s390x/s390-pci-inst.c ++++ b/hw/s390x/s390-pci-inst.c +@@ -640,6 +640,8 @@ static uint32_t s390_pci_update_iotlb(S390PCIIOMMU *iommu, + } + g_hash_table_remove(iommu->iotlb, &entry->iova); + inc_dma_avail(iommu); ++ /* Don't notify the iommu yet, maybe we can bundle contiguous unmaps */ ++ goto out; + } else { + if (cache) { + if (cache->perm == entry->perm && +@@ -663,15 +665,44 @@ static uint32_t s390_pci_update_iotlb(S390PCIIOMMU *iommu, + dec_dma_avail(iommu); + } + ++ /* ++ * All associated iotlb entries have already been cleared, trigger the ++ * unmaps. ++ */ + memory_region_notify_iommu(&iommu->iommu_mr, 0, event); + + out: + return iommu->dma_limit ? iommu->dma_limit->avail : 1; + } + ++static void s390_pci_batch_unmap(S390PCIIOMMU *iommu, uint64_t iova, ++ uint64_t len) ++{ ++ uint64_t remain = len, start = iova, end = start + len - 1, mask, size; ++ IOMMUTLBEvent event = { ++ .type = IOMMU_NOTIFIER_UNMAP, ++ .entry = { ++ .target_as = &address_space_memory, ++ .translated_addr = 0, ++ .perm = IOMMU_NONE, ++ }, ++ }; ++ ++ while (remain >= TARGET_PAGE_SIZE) { ++ mask = dma_aligned_pow2_mask(start, end, 64); ++ size = mask + 1; ++ event.entry.iova = start; ++ event.entry.addr_mask = mask; ++ memory_region_notify_iommu(&iommu->iommu_mr, 0, event); ++ start += size; ++ remain -= size; ++ } ++} ++ + int rpcit_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2, uintptr_t ra) + { + CPUS390XState *env = &cpu->env; ++ uint64_t iova, coalesce = 0; + uint32_t fh; + uint16_t error = 0; + S390PCIBusDevice *pbdev; +@@ -742,6 +773,21 @@ int rpcit_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2, uintptr_t ra) + break; + } + ++ /* ++ * If this is an unmap of a PTE, let's try to coalesce multiple unmaps ++ * into as few notifier events as possible. ++ */ ++ if (entry.perm == IOMMU_NONE && entry.len == TARGET_PAGE_SIZE) { ++ if (coalesce == 0) { ++ iova = entry.iova; ++ } ++ coalesce += entry.len; ++ } else if (coalesce > 0) { ++ /* Unleash the coalesced unmap before processing a new map */ ++ s390_pci_batch_unmap(iommu, iova, coalesce); ++ coalesce = 0; ++ } ++ + start += entry.len; + while (entry.iova < start && entry.iova < end) { + if (dma_avail > 0 || entry.perm == IOMMU_NONE) { +@@ -759,6 +805,11 @@ int rpcit_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2, uintptr_t ra) + } + } + } ++ if (coalesce) { ++ /* Unleash the coalesced unmap before finishing rpcit */ ++ s390_pci_batch_unmap(iommu, iova, coalesce); ++ coalesce = 0; ++ } + if (again && dma_avail > 0) + goto retry; + err: +-- +2.37.3 + diff --git a/kvm-s390x-pci-reset-ISM-passthrough-devices-on-shutdown-.patch b/kvm-s390x-pci-reset-ISM-passthrough-devices-on-shutdown-.patch new file mode 100644 index 0000000..215c5dd --- /dev/null +++ b/kvm-s390x-pci-reset-ISM-passthrough-devices-on-shutdown-.patch @@ -0,0 +1,147 @@ +From 9ec96a236be84e34b16681e658d3910fc3877a44 Mon Sep 17 00:00:00 2001 +From: Matthew Rosato +Date: Fri, 9 Dec 2022 14:57:00 -0500 +Subject: [PATCH 11/11] s390x/pci: reset ISM passthrough devices on shutdown + and system reset +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Cédric Le Goater +RH-MergeRequest: 250: s390x/pci: reset ISM passthrough devices on shutdown and system reset +RH-Bugzilla: 2163713 +RH-Acked-by: Thomas Huth +RH-Acked-by: Cornelia Huck +RH-Acked-by: Miroslav Rezanina +RH-Commit: [4/4] c857d022c7c2f43cdeb66c4f6acfd9272c925b35 + +ISM device firmware stores unique state information that can +can cause a wholesale unmap of the associated IOMMU (e.g. when +we get a termination signal for QEMU) to trigger firmware errors +because firmware believes we are attempting to invalidate entries +that are still in-use by the guest OS (when in fact that guest is +in the process of being terminated or rebooted). +To alleviate this, register both a shutdown notifier (for unexpected +termination cases e.g. virsh destroy) as well as a reset callback +(for cases like guest OS reboot). For each of these scenarios, trigger +PCI device reset; this is enough to indicate to firmware that the IOMMU +is no longer in-use by the guest OS, making it safe to invalidate any +associated IOMMU entries. + +Fixes: 15d0e7942d3b ("s390x/pci: don't fence interpreted devices without MSI-X") +Signed-off-by: Matthew Rosato +Message-Id: <20221209195700.263824-1-mjrosato@linux.ibm.com> +Reviewed-by: Eric Farman +[thuth: Adjusted the hunk in s390-pci-vfio.c due to different context] +Signed-off-by: Thomas Huth +(cherry picked from commit 03451953c79e6b31f7860ee0c35b28e181d573c1) +Signed-off-by: Cédric Le Goater +--- + hw/s390x/s390-pci-bus.c | 28 ++++++++++++++++++++++++++++ + hw/s390x/s390-pci-vfio.c | 2 ++ + include/hw/s390x/s390-pci-bus.h | 5 +++++ + 3 files changed, 35 insertions(+) + +diff --git a/hw/s390x/s390-pci-bus.c b/hw/s390x/s390-pci-bus.c +index d8b1e44a02..2d92848b0f 100644 +--- a/hw/s390x/s390-pci-bus.c ++++ b/hw/s390x/s390-pci-bus.c +@@ -24,6 +24,8 @@ + #include "hw/pci/msi.h" + #include "qemu/error-report.h" + #include "qemu/module.h" ++#include "sysemu/reset.h" ++#include "sysemu/runstate.h" + + #ifndef DEBUG_S390PCI_BUS + #define DEBUG_S390PCI_BUS 0 +@@ -150,10 +152,30 @@ out: + psccb->header.response_code = cpu_to_be16(rc); + } + ++static void s390_pci_shutdown_notifier(Notifier *n, void *opaque) ++{ ++ S390PCIBusDevice *pbdev = container_of(n, S390PCIBusDevice, ++ shutdown_notifier); ++ ++ pci_device_reset(pbdev->pdev); ++} ++ ++static void s390_pci_reset_cb(void *opaque) ++{ ++ S390PCIBusDevice *pbdev = opaque; ++ ++ pci_device_reset(pbdev->pdev); ++} ++ + static void s390_pci_perform_unplug(S390PCIBusDevice *pbdev) + { + HotplugHandler *hotplug_ctrl; + ++ if (pbdev->pft == ZPCI_PFT_ISM) { ++ notifier_remove(&pbdev->shutdown_notifier); ++ qemu_unregister_reset(s390_pci_reset_cb, pbdev); ++ } ++ + /* Unplug the PCI device */ + if (pbdev->pdev) { + DeviceState *pdev = DEVICE(pbdev->pdev); +@@ -1111,6 +1133,12 @@ static void s390_pcihost_plug(HotplugHandler *hotplug_dev, DeviceState *dev, + pbdev->fh |= FH_SHM_VFIO; + pbdev->forwarding_assist = false; + } ++ /* Register shutdown notifier and reset callback for ISM devices */ ++ if (pbdev->pft == ZPCI_PFT_ISM) { ++ pbdev->shutdown_notifier.notify = s390_pci_shutdown_notifier; ++ qemu_register_shutdown_notifier(&pbdev->shutdown_notifier); ++ qemu_register_reset(s390_pci_reset_cb, pbdev); ++ } + } else { + pbdev->fh |= FH_SHM_EMUL; + /* Always intercept emulated devices */ +diff --git a/hw/s390x/s390-pci-vfio.c b/hw/s390x/s390-pci-vfio.c +index 99806e2a84..69af35f4fe 100644 +--- a/hw/s390x/s390-pci-vfio.c ++++ b/hw/s390x/s390-pci-vfio.c +@@ -124,6 +124,8 @@ static void s390_pci_read_base(S390PCIBusDevice *pbdev, + /* The following values remain 0 until we support other FMB formats */ + pbdev->zpci_fn.fmbl = 0; + pbdev->zpci_fn.pft = 0; ++ /* Store function type separately for type-specific behavior */ ++ pbdev->pft = cap->pft; + + /* + * If appropriate, reduce the size of the supported DMA aperture reported +diff --git a/include/hw/s390x/s390-pci-bus.h b/include/hw/s390x/s390-pci-bus.h +index 1c46e3a269..e0a9f9385b 100644 +--- a/include/hw/s390x/s390-pci-bus.h ++++ b/include/hw/s390x/s390-pci-bus.h +@@ -39,6 +39,9 @@ + #define UID_CHECKING_ENABLED 0x01 + #define ZPCI_DTSM 0x40 + ++/* zPCI Function Types */ ++#define ZPCI_PFT_ISM 5 ++ + OBJECT_DECLARE_SIMPLE_TYPE(S390pciState, S390_PCI_HOST_BRIDGE) + OBJECT_DECLARE_SIMPLE_TYPE(S390PCIBus, S390_PCI_BUS) + OBJECT_DECLARE_SIMPLE_TYPE(S390PCIBusDevice, S390_PCI_DEVICE) +@@ -344,6 +347,7 @@ struct S390PCIBusDevice { + uint16_t noi; + uint16_t maxstbl; + uint8_t sum; ++ uint8_t pft; + S390PCIGroup *pci_group; + ClpRspQueryPci zpci_fn; + S390MsixInfo msix; +@@ -352,6 +356,7 @@ struct S390PCIBusDevice { + MemoryRegion msix_notify_mr; + IndAddr *summary_ind; + IndAddr *indicator; ++ Notifier shutdown_notifier; + bool pci_unplug_request_processed; + bool unplug_requested; + bool interp; +-- +2.37.3 + diff --git a/kvm-s390x-pci-shrink-DMA-aperture-to-be-bound-by-vfio-DM.patch b/kvm-s390x-pci-shrink-DMA-aperture-to-be-bound-by-vfio-DM.patch new file mode 100644 index 0000000..e1df69f --- /dev/null +++ b/kvm-s390x-pci-shrink-DMA-aperture-to-be-bound-by-vfio-DM.patch @@ -0,0 +1,91 @@ +From a0b6c21b555566eb6bc38643269d14c82dfd0226 Mon Sep 17 00:00:00 2001 +From: Matthew Rosato +Date: Fri, 28 Oct 2022 15:47:58 -0400 +Subject: [PATCH 10/11] s390x/pci: shrink DMA aperture to be bound by vfio DMA + limit +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Cédric Le Goater +RH-MergeRequest: 250: s390x/pci: reset ISM passthrough devices on shutdown and system reset +RH-Bugzilla: 2163713 +RH-Acked-by: Thomas Huth +RH-Acked-by: Cornelia Huck +RH-Acked-by: Miroslav Rezanina +RH-Commit: [3/4] aa241dd250ad5e696b67c87dddc31ee5aaee9c0e + +Currently, s390x-pci performs accounting against the vfio DMA +limit and triggers the guest to clean up mappings when the limit +is reached. Let's go a step further and also limit the size of +the supported DMA aperture reported to the guest based upon the +initial vfio DMA limit reported for the container (if less than +than the size reported by the firmware/host zPCI layer). This +avoids processing sections of the guest DMA table during global +refresh that, for common use cases, will never be used anway, and +makes exhausting the vfio DMA limit due to mismatch between guest +aperture size and host limit far less likely and more indicitive +of an error. + +Signed-off-by: Matthew Rosato +Message-Id: <20221028194758.204007-4-mjrosato@linux.ibm.com> +Reviewed-by: Eric Farman +Signed-off-by: Thomas Huth +(cherry picked from commit df202e3ff3fccb49868e08f20d0bda86cb953fbe) +Signed-off-by: Cédric Le Goater +--- + hw/s390x/s390-pci-vfio.c | 11 +++++++++++ + include/hw/s390x/s390-pci-bus.h | 1 + + 2 files changed, 12 insertions(+) + +diff --git a/hw/s390x/s390-pci-vfio.c b/hw/s390x/s390-pci-vfio.c +index 2aefa508a0..99806e2a84 100644 +--- a/hw/s390x/s390-pci-vfio.c ++++ b/hw/s390x/s390-pci-vfio.c +@@ -84,6 +84,7 @@ S390PCIDMACount *s390_pci_start_dma_count(S390pciState *s, + cnt->users = 1; + cnt->avail = avail; + QTAILQ_INSERT_TAIL(&s->zpci_dma_limit, cnt, link); ++ pbdev->iommu->max_dma_limit = avail; + return cnt; + } + +@@ -103,6 +104,7 @@ static void s390_pci_read_base(S390PCIBusDevice *pbdev, + struct vfio_info_cap_header *hdr; + struct vfio_device_info_cap_zpci_base *cap; + VFIOPCIDevice *vpci = container_of(pbdev->pdev, VFIOPCIDevice, pdev); ++ uint64_t vfio_size; + + hdr = vfio_get_device_info_cap(info, VFIO_DEVICE_INFO_CAP_ZPCI_BASE); + +@@ -122,6 +124,15 @@ static void s390_pci_read_base(S390PCIBusDevice *pbdev, + /* The following values remain 0 until we support other FMB formats */ + pbdev->zpci_fn.fmbl = 0; + pbdev->zpci_fn.pft = 0; ++ ++ /* ++ * If appropriate, reduce the size of the supported DMA aperture reported ++ * to the guest based upon the vfio DMA limit. ++ */ ++ vfio_size = pbdev->iommu->max_dma_limit << TARGET_PAGE_BITS; ++ if (vfio_size < (cap->end_dma - cap->start_dma + 1)) { ++ pbdev->zpci_fn.edma = cap->start_dma + vfio_size - 1; ++ } + } + + static bool get_host_fh(S390PCIBusDevice *pbdev, struct vfio_device_info *info, +diff --git a/include/hw/s390x/s390-pci-bus.h b/include/hw/s390x/s390-pci-bus.h +index 0605fcea24..1c46e3a269 100644 +--- a/include/hw/s390x/s390-pci-bus.h ++++ b/include/hw/s390x/s390-pci-bus.h +@@ -278,6 +278,7 @@ struct S390PCIIOMMU { + uint64_t g_iota; + uint64_t pba; + uint64_t pal; ++ uint64_t max_dma_limit; + GHashTable *iotlb; + S390PCIDMACount *dma_limit; + }; +-- +2.37.3 + diff --git a/kvm-scsi-protect-req-aiocb-with-AioContext-lock.patch b/kvm-scsi-protect-req-aiocb-with-AioContext-lock.patch new file mode 100644 index 0000000..1343855 --- /dev/null +++ b/kvm-scsi-protect-req-aiocb-with-AioContext-lock.patch @@ -0,0 +1,176 @@ +From df836ee4b4e2a69cca5042a3a9daf2c41dc2aa58 Mon Sep 17 00:00:00 2001 +From: Stefan Hajnoczi +Date: Tue, 21 Feb 2023 16:22:16 -0500 +Subject: [PATCH 11/13] scsi: protect req->aiocb with AioContext lock + +RH-Author: Stefan Hajnoczi +RH-MergeRequest: 264: scsi: protect req->aiocb with AioContext lock +RH-Bugzilla: 2090990 +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Kevin Wolf +RH-Commit: [1/3] e6a6d4109713e0fd6d6c515535c66196fea98688 + +If requests are being processed in the IOThread when a SCSIDevice is +unplugged, scsi_device_purge_requests() -> scsi_req_cancel_async() races +with I/O completion callbacks. Both threads load and store req->aiocb. +This can lead to assert(r->req.aiocb == NULL) failures and undefined +behavior. + +Protect r->req.aiocb with the AioContext lock to prevent the race. + +Reviewed-by: Eric Blake +Reviewed-by: Kevin Wolf +Signed-off-by: Stefan Hajnoczi +Message-Id: <20230221212218.1378734-2-stefanha@redhat.com> +Signed-off-by: Kevin Wolf +(cherry picked from commit 7b7fc3d0102dafe8eb44802493036a526e921a71) +Signed-off-by: Stefan Hajnoczi +--- + hw/scsi/scsi-disk.c | 23 ++++++++++++++++------- + hw/scsi/scsi-generic.c | 11 ++++++----- + 2 files changed, 22 insertions(+), 12 deletions(-) + +diff --git a/hw/scsi/scsi-disk.c b/hw/scsi/scsi-disk.c +index d4914178ea..179ce22c4a 100644 +--- a/hw/scsi/scsi-disk.c ++++ b/hw/scsi/scsi-disk.c +@@ -270,9 +270,11 @@ static void scsi_aio_complete(void *opaque, int ret) + SCSIDiskReq *r = (SCSIDiskReq *)opaque; + SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, r->req.dev); + ++ aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk)); ++ + assert(r->req.aiocb != NULL); + r->req.aiocb = NULL; +- aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk)); ++ + if (scsi_disk_req_check_error(r, ret, true)) { + goto done; + } +@@ -354,10 +356,11 @@ static void scsi_dma_complete(void *opaque, int ret) + SCSIDiskReq *r = (SCSIDiskReq *)opaque; + SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, r->req.dev); + ++ aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk)); ++ + assert(r->req.aiocb != NULL); + r->req.aiocb = NULL; + +- aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk)); + if (ret < 0) { + block_acct_failed(blk_get_stats(s->qdev.conf.blk), &r->acct); + } else { +@@ -390,10 +393,11 @@ static void scsi_read_complete(void *opaque, int ret) + SCSIDiskReq *r = (SCSIDiskReq *)opaque; + SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, r->req.dev); + ++ aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk)); ++ + assert(r->req.aiocb != NULL); + r->req.aiocb = NULL; + +- aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk)); + if (ret < 0) { + block_acct_failed(blk_get_stats(s->qdev.conf.blk), &r->acct); + } else { +@@ -443,10 +447,11 @@ static void scsi_do_read_cb(void *opaque, int ret) + SCSIDiskReq *r = (SCSIDiskReq *)opaque; + SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, r->req.dev); + ++ aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk)); ++ + assert (r->req.aiocb != NULL); + r->req.aiocb = NULL; + +- aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk)); + if (ret < 0) { + block_acct_failed(blk_get_stats(s->qdev.conf.blk), &r->acct); + } else { +@@ -527,10 +532,11 @@ static void scsi_write_complete(void * opaque, int ret) + SCSIDiskReq *r = (SCSIDiskReq *)opaque; + SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, r->req.dev); + ++ aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk)); ++ + assert (r->req.aiocb != NULL); + r->req.aiocb = NULL; + +- aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk)); + if (ret < 0) { + block_acct_failed(blk_get_stats(s->qdev.conf.blk), &r->acct); + } else { +@@ -1659,10 +1665,11 @@ static void scsi_unmap_complete(void *opaque, int ret) + SCSIDiskReq *r = data->r; + SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, r->req.dev); + ++ aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk)); ++ + assert(r->req.aiocb != NULL); + r->req.aiocb = NULL; + +- aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk)); + if (scsi_disk_req_check_error(r, ret, true)) { + scsi_req_unref(&r->req); + g_free(data); +@@ -1738,9 +1745,11 @@ static void scsi_write_same_complete(void *opaque, int ret) + SCSIDiskReq *r = data->r; + SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, r->req.dev); + ++ aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk)); ++ + assert(r->req.aiocb != NULL); + r->req.aiocb = NULL; +- aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk)); ++ + if (scsi_disk_req_check_error(r, ret, true)) { + goto done; + } +diff --git a/hw/scsi/scsi-generic.c b/hw/scsi/scsi-generic.c +index 3742899839..a1a40df64b 100644 +--- a/hw/scsi/scsi-generic.c ++++ b/hw/scsi/scsi-generic.c +@@ -111,10 +111,11 @@ static void scsi_command_complete(void *opaque, int ret) + SCSIGenericReq *r = (SCSIGenericReq *)opaque; + SCSIDevice *s = r->req.dev; + ++ aio_context_acquire(blk_get_aio_context(s->conf.blk)); ++ + assert(r->req.aiocb != NULL); + r->req.aiocb = NULL; + +- aio_context_acquire(blk_get_aio_context(s->conf.blk)); + scsi_command_complete_noio(r, ret); + aio_context_release(blk_get_aio_context(s->conf.blk)); + } +@@ -269,11 +270,11 @@ static void scsi_read_complete(void * opaque, int ret) + SCSIDevice *s = r->req.dev; + int len; + ++ aio_context_acquire(blk_get_aio_context(s->conf.blk)); ++ + assert(r->req.aiocb != NULL); + r->req.aiocb = NULL; + +- aio_context_acquire(blk_get_aio_context(s->conf.blk)); +- + if (ret || r->req.io_canceled) { + scsi_command_complete_noio(r, ret); + goto done; +@@ -387,11 +388,11 @@ static void scsi_write_complete(void * opaque, int ret) + + trace_scsi_generic_write_complete(ret); + ++ aio_context_acquire(blk_get_aio_context(s->conf.blk)); ++ + assert(r->req.aiocb != NULL); + r->req.aiocb = NULL; + +- aio_context_acquire(blk_get_aio_context(s->conf.blk)); +- + if (ret || r->req.io_canceled) { + scsi_command_complete_noio(r, ret); + goto done; +-- +2.37.3 + diff --git a/kvm-sysemu-tpm-Add-a-stub-function-for-TPM_IS_CRB.patch b/kvm-sysemu-tpm-Add-a-stub-function-for-TPM_IS_CRB.patch deleted file mode 100644 index 8fd2e16..0000000 --- a/kvm-sysemu-tpm-Add-a-stub-function-for-TPM_IS_CRB.patch +++ /dev/null @@ -1,54 +0,0 @@ -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/kvm-target-arm-deprecate-named-CPU-models.patch b/kvm-target-arm-deprecate-named-CPU-models.patch deleted file mode 100644 index dbe8d24..0000000 --- a/kvm-target-arm-deprecate-named-CPU-models.patch +++ /dev/null @@ -1,129 +0,0 @@ -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/kvm-target-i386-deprecate-CPUs-older-than-x86_64-v2-ABI.patch b/kvm-target-i386-deprecate-CPUs-older-than-x86_64-v2-ABI.patch deleted file mode 100644 index d63bfdb..0000000 --- a/kvm-target-i386-deprecate-CPUs-older-than-x86_64-v2-ABI.patch +++ /dev/null @@ -1,273 +0,0 @@ -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/kvm-target-ppc-cpu-models-Fix-ppc_cpu_aliases-list-for-R.patch b/kvm-target-ppc-cpu-models-Fix-ppc_cpu_aliases-list-for-R.patch deleted file mode 100644 index c940cdb..0000000 --- a/kvm-target-ppc-cpu-models-Fix-ppc_cpu_aliases-list-for-R.patch +++ /dev/null @@ -1,48 +0,0 @@ -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/kvm-target-s390x-arch_dump-Fix-memory-corruption-in-s390.patch b/kvm-target-s390x-arch_dump-Fix-memory-corruption-in-s390.patch new file mode 100644 index 0000000..188c6bf --- /dev/null +++ b/kvm-target-s390x-arch_dump-Fix-memory-corruption-in-s390.patch @@ -0,0 +1,50 @@ +From e1870dec813fa6f8482f4f27b7a9bef8c1584b6b Mon Sep 17 00:00:00 2001 +From: Thomas Huth +Date: Tue, 14 Feb 2023 14:48:37 +0100 +Subject: [PATCH 3/3] target/s390x/arch_dump: Fix memory corruption in + s390x_write_elf64_notes() +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +RH-Author: Thomas Huth +RH-MergeRequest: 260: target/s390x/arch_dump: Fix memory corruption in s390x_write_elf64_notes() +RH-Bugzilla: 2168187 +RH-Acked-by: David Hildenbrand +RH-Acked-by: Cédric Le Goater +RH-Acked-by: Cornelia Huck +RH-Commit: [1/1] 67b71ed720a1f03d5bda9119969ea95fc4a6106d + +Bugzilla: https://bugzilla.redhat.com/2168187 +Upstream-Status: Posted (and reviewed, but not merged yet) + +"note_size" can be smaller than sizeof(note), so unconditionally calling +memset(notep, 0, sizeof(note)) could cause a memory corruption here in +case notep has been allocated dynamically, thus let's use note_size as +length argument for memset() instead. + +Fixes: 113d8f4e95 ("s390x: pv: Add dump support") +Message-Id: <20230214141056.680969-1-thuth@redhat.com> +Reviewed-by: Janosch Frank +Reviewed-by: Philippe Mathieu-Daudé +Signed-off-by: Thomas Huth +--- + target/s390x/arch_dump.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/target/s390x/arch_dump.c b/target/s390x/arch_dump.c +index a2329141e8..a7c44ba49d 100644 +--- a/target/s390x/arch_dump.c ++++ b/target/s390x/arch_dump.c +@@ -248,7 +248,7 @@ static int s390x_write_elf64_notes(const char *note_name, + notep = g_malloc(note_size); + } + +- memset(notep, 0, sizeof(note)); ++ memset(notep, 0, note_size); + + /* Setup note header data */ + notep->hdr.n_descsz = cpu_to_be32(content_size); +-- +2.37.3 + diff --git a/kvm-target-s390x-deprecate-CPUs-older-than-z14.patch b/kvm-target-s390x-deprecate-CPUs-older-than-z14.patch deleted file mode 100644 index 212900d..0000000 --- a/kvm-target-s390x-deprecate-CPUs-older-than-z14.patch +++ /dev/null @@ -1,194 +0,0 @@ -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/kvm-tests-avocado-update-aarch64_virt-test-to-exercise-c.patch b/kvm-tests-avocado-update-aarch64_virt-test-to-exercise-c.patch deleted file mode 100644 index 4fcf786..0000000 --- a/kvm-tests-avocado-update-aarch64_virt-test-to-exercise-c.patch +++ /dev/null @@ -1,157 +0,0 @@ -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/kvm-util-event-loop-base-Introduce-options-to-set-the-th.patch b/kvm-util-event-loop-base-Introduce-options-to-set-the-th.patch deleted file mode 100644 index 77929a6..0000000 --- a/kvm-util-event-loop-base-Introduce-options-to-set-the-th.patch +++ /dev/null @@ -1,385 +0,0 @@ -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/kvm-util-main-loop-Introduce-the-main-loop-into-QOM.patch b/kvm-util-main-loop-Introduce-the-main-loop-into-QOM.patch deleted file mode 100644 index 2104424..0000000 --- a/kvm-util-main-loop-Introduce-the-main-loop-into-QOM.patch +++ /dev/null @@ -1,233 +0,0 @@ -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/kvm-vdpa-Add-device-migration-blocker.patch b/kvm-vdpa-Add-device-migration-blocker.patch deleted file mode 100644 index 1b83c98..0000000 --- a/kvm-vdpa-Add-device-migration-blocker.patch +++ /dev/null @@ -1,106 +0,0 @@ -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/kvm-vdpa-Add-x-svq-to-NetdevVhostVDPAOptions.patch b/kvm-vdpa-Add-x-svq-to-NetdevVhostVDPAOptions.patch deleted file mode 100644 index 8a7b600..0000000 --- a/kvm-vdpa-Add-x-svq-to-NetdevVhostVDPAOptions.patch +++ /dev/null @@ -1,223 +0,0 @@ -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/kvm-vdpa-Avoid-compiler-to-squash-reads-to-used-idx.patch b/kvm-vdpa-Avoid-compiler-to-squash-reads-to-used-idx.patch deleted file mode 100644 index acd45e0..0000000 --- a/kvm-vdpa-Avoid-compiler-to-squash-reads-to-used-idx.patch +++ /dev/null @@ -1,65 +0,0 @@ -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/kvm-vdpa-Buffer-CVQ-support-on-shadow-virtqueue.patch b/kvm-vdpa-Buffer-CVQ-support-on-shadow-virtqueue.patch deleted file mode 100644 index 243aec8..0000000 --- a/kvm-vdpa-Buffer-CVQ-support-on-shadow-virtqueue.patch +++ /dev/null @@ -1,323 +0,0 @@ -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/kvm-vdpa-Export-vhost_vdpa_dma_map-and-unmap-calls.patch b/kvm-vdpa-Export-vhost_vdpa_dma_map-and-unmap-calls.patch deleted file mode 100644 index d6e72ac..0000000 --- a/kvm-vdpa-Export-vhost_vdpa_dma_map-and-unmap-calls.patch +++ /dev/null @@ -1,84 +0,0 @@ -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/kvm-vdpa-Extract-get-features-part-from-vhost_vdpa_get_m.patch b/kvm-vdpa-Extract-get-features-part-from-vhost_vdpa_get_m.patch deleted file mode 100644 index 44e97af..0000000 --- a/kvm-vdpa-Extract-get-features-part-from-vhost_vdpa_get_m.patch +++ /dev/null @@ -1,108 +0,0 @@ -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/kvm-vdpa-manual-forward-CVQ-buffers.patch b/kvm-vdpa-manual-forward-CVQ-buffers.patch deleted file mode 100644 index 61909ff..0000000 --- a/kvm-vdpa-manual-forward-CVQ-buffers.patch +++ /dev/null @@ -1,166 +0,0 @@ -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/kvm-vfio-common-remove-spurious-tpm-crb-cmd-misalignment.patch b/kvm-vfio-common-remove-spurious-tpm-crb-cmd-misalignment.patch deleted file mode 100644 index 26083c1..0000000 --- a/kvm-vfio-common-remove-spurious-tpm-crb-cmd-misalignment.patch +++ /dev/null @@ -1,114 +0,0 @@ -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/kvm-vfio-common-remove-spurious-warning-on-vfio_listener.patch b/kvm-vfio-common-remove-spurious-warning-on-vfio_listener.patch deleted file mode 100644 index 7e644c5..0000000 --- a/kvm-vfio-common-remove-spurious-warning-on-vfio_listener.patch +++ /dev/null @@ -1,78 +0,0 @@ -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/kvm-vhost-Add-SVQDescState.patch b/kvm-vhost-Add-SVQDescState.patch deleted file mode 100644 index b1ea4bb..0000000 --- a/kvm-vhost-Add-SVQDescState.patch +++ /dev/null @@ -1,135 +0,0 @@ -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/kvm-vhost-Add-svq-avail_handler-callback.patch b/kvm-vhost-Add-svq-avail_handler-callback.patch deleted file mode 100644 index a8b585d..0000000 --- a/kvm-vhost-Add-svq-avail_handler-callback.patch +++ /dev/null @@ -1,164 +0,0 @@ -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/kvm-vhost-Check-for-queue-full-at-vhost_svq_add.patch b/kvm-vhost-Check-for-queue-full-at-vhost_svq_add.patch deleted file mode 100644 index 9b09d42..0000000 --- a/kvm-vhost-Check-for-queue-full-at-vhost_svq_add.patch +++ /dev/null @@ -1,134 +0,0 @@ -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/kvm-vhost-Decouple-vhost_svq_add-from-VirtQueueElement.patch b/kvm-vhost-Decouple-vhost_svq_add-from-VirtQueueElement.patch deleted file mode 100644 index 6755aad..0000000 --- a/kvm-vhost-Decouple-vhost_svq_add-from-VirtQueueElement.patch +++ /dev/null @@ -1,138 +0,0 @@ -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/kvm-vhost-Expose-vhost_svq_add.patch b/kvm-vhost-Expose-vhost_svq_add.patch deleted file mode 100644 index 70dc774..0000000 --- a/kvm-vhost-Expose-vhost_svq_add.patch +++ /dev/null @@ -1,73 +0,0 @@ -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/kvm-vhost-Fix-device-s-used-descriptor-dequeue.patch b/kvm-vhost-Fix-device-s-used-descriptor-dequeue.patch deleted file mode 100644 index f149c05..0000000 --- a/kvm-vhost-Fix-device-s-used-descriptor-dequeue.patch +++ /dev/null @@ -1,83 +0,0 @@ -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/kvm-vhost-Fix-element-in-vhost_svq_add-failure.patch b/kvm-vhost-Fix-element-in-vhost_svq_add-failure.patch deleted file mode 100644 index 51eb700..0000000 --- a/kvm-vhost-Fix-element-in-vhost_svq_add-failure.patch +++ /dev/null @@ -1,68 +0,0 @@ -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/kvm-vhost-Move-vhost_svq_kick-call-to-vhost_svq_add.patch b/kvm-vhost-Move-vhost_svq_kick-call-to-vhost_svq_add.patch deleted file mode 100644 index 513d7b4..0000000 --- a/kvm-vhost-Move-vhost_svq_kick-call-to-vhost_svq_add.patch +++ /dev/null @@ -1,61 +0,0 @@ -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/kvm-vhost-Reorder-vhost_svq_kick.patch b/kvm-vhost-Reorder-vhost_svq_kick.patch deleted file mode 100644 index f61f3c3..0000000 --- a/kvm-vhost-Reorder-vhost_svq_kick.patch +++ /dev/null @@ -1,88 +0,0 @@ -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/kvm-vhost-Track-descriptor-chain-in-private-at-SVQ.patch b/kvm-vhost-Track-descriptor-chain-in-private-at-SVQ.patch deleted file mode 100644 index 31bfccc..0000000 --- a/kvm-vhost-Track-descriptor-chain-in-private-at-SVQ.patch +++ /dev/null @@ -1,123 +0,0 @@ -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/kvm-vhost-Track-number-of-descs-in-SVQDescState.patch b/kvm-vhost-Track-number-of-descs-in-SVQDescState.patch deleted file mode 100644 index 6a2e147..0000000 --- a/kvm-vhost-Track-number-of-descs-in-SVQDescState.patch +++ /dev/null @@ -1,81 +0,0 @@ -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/kvm-vhost-add-vhost_svq_poll.patch b/kvm-vhost-add-vhost_svq_poll.patch deleted file mode 100644 index fa27e5e..0000000 --- a/kvm-vhost-add-vhost_svq_poll.patch +++ /dev/null @@ -1,92 +0,0 @@ -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/kvm-vhost-add-vhost_svq_push_elem.patch b/kvm-vhost-add-vhost_svq_push_elem.patch deleted file mode 100644 index 2a9ec40..0000000 --- a/kvm-vhost-add-vhost_svq_push_elem.patch +++ /dev/null @@ -1,83 +0,0 @@ -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/kvm-vhost-move-descriptor-translation-to-vhost_svq_vring.patch b/kvm-vhost-move-descriptor-translation-to-vhost_svq_vring.patch deleted file mode 100644 index 08bcaf2..0000000 --- a/kvm-vhost-move-descriptor-translation-to-vhost_svq_vring.patch +++ /dev/null @@ -1,120 +0,0 @@ -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/kvm-vhost-net-vdpa-add-stubs-for-when-no-virtio-net-devi.patch b/kvm-vhost-net-vdpa-add-stubs-for-when-no-virtio-net-devi.patch deleted file mode 100644 index 31677fd..0000000 --- a/kvm-vhost-net-vdpa-add-stubs-for-when-no-virtio-net-devi.patch +++ /dev/null @@ -1,87 +0,0 @@ -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/kvm-virtio-iommu-Add-an-assert-check-in-translate-routin.patch b/kvm-virtio-iommu-Add-an-assert-check-in-translate-routin.patch deleted file mode 100644 index 2a72cc7..0000000 --- a/kvm-virtio-iommu-Add-an-assert-check-in-translate-routin.patch +++ /dev/null @@ -1,46 +0,0 @@ -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/kvm-virtio-iommu-Add-bypass-mode-support-to-assigned-dev.patch b/kvm-virtio-iommu-Add-bypass-mode-support-to-assigned-dev.patch deleted file mode 100644 index 3352666..0000000 --- a/kvm-virtio-iommu-Add-bypass-mode-support-to-assigned-dev.patch +++ /dev/null @@ -1,250 +0,0 @@ -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/kvm-virtio-iommu-Fix-migration-regression.patch b/kvm-virtio-iommu-Fix-migration-regression.patch deleted file mode 100644 index f5ae4d6..0000000 --- a/kvm-virtio-iommu-Fix-migration-regression.patch +++ /dev/null @@ -1,54 +0,0 @@ -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/kvm-virtio-iommu-Fix-the-partial-copy-of-probe-request.patch b/kvm-virtio-iommu-Fix-the-partial-copy-of-probe-request.patch deleted file mode 100644 index 7747bfe..0000000 --- a/kvm-virtio-iommu-Fix-the-partial-copy-of-probe-request.patch +++ /dev/null @@ -1,67 +0,0 @@ -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/kvm-virtio-iommu-Use-recursive-lock-to-avoid-deadlock.patch b/kvm-virtio-iommu-Use-recursive-lock-to-avoid-deadlock.patch deleted file mode 100644 index df961b0..0000000 --- a/kvm-virtio-iommu-Use-recursive-lock-to-avoid-deadlock.patch +++ /dev/null @@ -1,141 +0,0 @@ -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/kvm-virtio-net-Expose-MAC_TABLE_ENTRIES.patch b/kvm-virtio-net-Expose-MAC_TABLE_ENTRIES.patch deleted file mode 100644 index 4ae4cc4..0000000 --- a/kvm-virtio-net-Expose-MAC_TABLE_ENTRIES.patch +++ /dev/null @@ -1,69 +0,0 @@ -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/kvm-virtio-net-Expose-ctrl-virtqueue-logic.patch b/kvm-virtio-net-Expose-ctrl-virtqueue-logic.patch deleted file mode 100644 index b4b9012..0000000 --- a/kvm-virtio-net-Expose-ctrl-virtqueue-logic.patch +++ /dev/null @@ -1,169 +0,0 @@ -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/kvm-virtio-scsi-clean-up-virtio_scsi_handle_cmd_vq.patch b/kvm-virtio-scsi-clean-up-virtio_scsi_handle_cmd_vq.patch deleted file mode 100644 index 897e04c..0000000 --- a/kvm-virtio-scsi-clean-up-virtio_scsi_handle_cmd_vq.patch +++ /dev/null @@ -1,77 +0,0 @@ -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/kvm-virtio-scsi-clean-up-virtio_scsi_handle_ctrl_vq.patch b/kvm-virtio-scsi-clean-up-virtio_scsi_handle_ctrl_vq.patch deleted file mode 100644 index 30f012f..0000000 --- a/kvm-virtio-scsi-clean-up-virtio_scsi_handle_ctrl_vq.patch +++ /dev/null @@ -1,65 +0,0 @@ -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/kvm-virtio-scsi-clean-up-virtio_scsi_handle_event_vq.patch b/kvm-virtio-scsi-clean-up-virtio_scsi_handle_event_vq.patch deleted file mode 100644 index bfdd39b..0000000 --- a/kvm-virtio-scsi-clean-up-virtio_scsi_handle_event_vq.patch +++ /dev/null @@ -1,62 +0,0 @@ -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/kvm-virtio-scsi-don-t-waste-CPU-polling-the-event-virtqu.patch b/kvm-virtio-scsi-don-t-waste-CPU-polling-the-event-virtqu.patch deleted file mode 100644 index 5ba11a2..0000000 --- a/kvm-virtio-scsi-don-t-waste-CPU-polling-the-event-virtqu.patch +++ /dev/null @@ -1,103 +0,0 @@ -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/kvm-virtio-scsi-fix-ctrl-and-event-handler-functions-in-.patch b/kvm-virtio-scsi-fix-ctrl-and-event-handler-functions-in-.patch deleted file mode 100644 index 1f22ba0..0000000 --- a/kvm-virtio-scsi-fix-ctrl-and-event-handler-functions-in-.patch +++ /dev/null @@ -1,119 +0,0 @@ -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/kvm-virtio-scsi-move-request-related-items-from-.h-to-.c.patch b/kvm-virtio-scsi-move-request-related-items-from-.h-to-.c.patch deleted file mode 100644 index 8487f5c..0000000 --- a/kvm-virtio-scsi-move-request-related-items-from-.h-to-.c.patch +++ /dev/null @@ -1,168 +0,0 @@ -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/kvm-virtio-scsi-reset-SCSI-devices-from-main-loop-thread.patch b/kvm-virtio-scsi-reset-SCSI-devices-from-main-loop-thread.patch new file mode 100644 index 0000000..9325d69 --- /dev/null +++ b/kvm-virtio-scsi-reset-SCSI-devices-from-main-loop-thread.patch @@ -0,0 +1,337 @@ +From 31e9e3691789469b93a75d0221387bab3e526094 Mon Sep 17 00:00:00 2001 +From: Stefan Hajnoczi +Date: Tue, 21 Feb 2023 16:22:18 -0500 +Subject: [PATCH 13/13] virtio-scsi: reset SCSI devices from main loop thread + +RH-Author: Stefan Hajnoczi +RH-MergeRequest: 264: scsi: protect req->aiocb with AioContext lock +RH-Bugzilla: 2090990 +RH-Acked-by: Stefano Garzarella +RH-Acked-by: Miroslav Rezanina +RH-Acked-by: Kevin Wolf +RH-Commit: [3/3] 30d7c2bd868efa6694992e75ace22fb48aef161b + +When an IOThread is configured, the ctrl virtqueue is processed in the +IOThread. TMFs that reset SCSI devices are currently called directly +from the IOThread and trigger an assertion failure in blk_drain() from +the following call stack: + +virtio_scsi_handle_ctrl_req -> virtio_scsi_do_tmf -> device_code_reset +-> scsi_disk_reset -> scsi_device_purge_requests -> blk_drain + + ../block/block-backend.c:1780: void blk_drain(BlockBackend *): Assertion `qemu_in_main_thread()' failed. + +The blk_drain() function is not designed to be called from an IOThread +because it needs the Big QEMU Lock (BQL). + +This patch defers TMFs that reset SCSI devices to a Bottom Half (BH) +that runs in the main loop thread under the BQL. This way it's safe to +call blk_drain() and the assertion failure is avoided. + +Introduce s->tmf_bh_list for tracking TMF requests that have been +deferred to the BH. When the BH runs it will grab the entire list and +process all requests. Care must be taken to clear the list when the +virtio-scsi device is reset or unrealized. Otherwise deferred TMF +requests could execute later and lead to use-after-free or other +undefined behavior. + +The s->resetting counter that's used by TMFs that reset SCSI devices is +accessed from multiple threads. This patch makes that explicit by using +atomic accessor functions. With this patch applied the counter is only +modified by the main loop thread under the BQL but can be read by any +thread. + +Reported-by: Qing Wang +Cc: Paolo Bonzini +Reviewed-by: Eric Blake +Signed-off-by: Stefan Hajnoczi +Message-Id: <20230221212218.1378734-4-stefanha@redhat.com> +Signed-off-by: Kevin Wolf +(cherry picked from commit be2c42b97c3a3a395b2f05bad1b6c7de20ecf2a5) +Signed-off-by: Stefan Hajnoczi + +Conflicts: +- hw/scsi/virtio-scsi.c + - VirtIOSCSIReq is defined in include/hw/virtio/virtio-scsi.h + downstream instead of hw/scsi/virtio-scsi.c because commit + 3dc584abeef0 ("virtio-scsi: move request-related items from .h to + .c") is missing. Update the struct fields in virtio-scsi.h + downstream. + + - Use qbus_reset_all() downstream instead of bus_cold_reset() because + commit 4a5fc890b1d3 ("scsi: Use device_cold_reset() and + bus_cold_reset()") is missing. + + - Drop GLOBAL_STATE_CODE() because these macros don't exist + downstream. They are assertions/documentation and can be removed + without affecting the code. +--- + hw/scsi/virtio-scsi.c | 155 +++++++++++++++++++++++++------- + include/hw/virtio/virtio-scsi.h | 21 +++-- + 2 files changed, 139 insertions(+), 37 deletions(-) + +diff --git a/hw/scsi/virtio-scsi.c b/hw/scsi/virtio-scsi.c +index a35257c35a..ef19a9bcd0 100644 +--- a/hw/scsi/virtio-scsi.c ++++ b/hw/scsi/virtio-scsi.c +@@ -256,6 +256,118 @@ static inline void virtio_scsi_ctx_check(VirtIOSCSI *s, SCSIDevice *d) + } + } + ++static void virtio_scsi_do_one_tmf_bh(VirtIOSCSIReq *req) ++{ ++ VirtIOSCSI *s = req->dev; ++ SCSIDevice *d = virtio_scsi_device_get(s, req->req.tmf.lun); ++ BusChild *kid; ++ int target; ++ ++ switch (req->req.tmf.subtype) { ++ case VIRTIO_SCSI_T_TMF_LOGICAL_UNIT_RESET: ++ if (!d) { ++ req->resp.tmf.response = VIRTIO_SCSI_S_BAD_TARGET; ++ goto out; ++ } ++ if (d->lun != virtio_scsi_get_lun(req->req.tmf.lun)) { ++ req->resp.tmf.response = VIRTIO_SCSI_S_INCORRECT_LUN; ++ goto out; ++ } ++ qatomic_inc(&s->resetting); ++ qdev_reset_all(&d->qdev); ++ qatomic_dec(&s->resetting); ++ break; ++ ++ case VIRTIO_SCSI_T_TMF_I_T_NEXUS_RESET: ++ target = req->req.tmf.lun[1]; ++ qatomic_inc(&s->resetting); ++ ++ rcu_read_lock(); ++ QTAILQ_FOREACH_RCU(kid, &s->bus.qbus.children, sibling) { ++ SCSIDevice *d1 = SCSI_DEVICE(kid->child); ++ if (d1->channel == 0 && d1->id == target) { ++ qdev_reset_all(&d1->qdev); ++ } ++ } ++ rcu_read_unlock(); ++ ++ qatomic_dec(&s->resetting); ++ break; ++ ++ default: ++ g_assert_not_reached(); ++ break; ++ } ++ ++out: ++ object_unref(OBJECT(d)); ++ ++ virtio_scsi_acquire(s); ++ virtio_scsi_complete_req(req); ++ virtio_scsi_release(s); ++} ++ ++/* Some TMFs must be processed from the main loop thread */ ++static void virtio_scsi_do_tmf_bh(void *opaque) ++{ ++ VirtIOSCSI *s = opaque; ++ QTAILQ_HEAD(, VirtIOSCSIReq) reqs = QTAILQ_HEAD_INITIALIZER(reqs); ++ VirtIOSCSIReq *req; ++ VirtIOSCSIReq *tmp; ++ ++ virtio_scsi_acquire(s); ++ ++ QTAILQ_FOREACH_SAFE(req, &s->tmf_bh_list, next, tmp) { ++ QTAILQ_REMOVE(&s->tmf_bh_list, req, next); ++ QTAILQ_INSERT_TAIL(&reqs, req, next); ++ } ++ ++ qemu_bh_delete(s->tmf_bh); ++ s->tmf_bh = NULL; ++ ++ virtio_scsi_release(s); ++ ++ QTAILQ_FOREACH_SAFE(req, &reqs, next, tmp) { ++ QTAILQ_REMOVE(&reqs, req, next); ++ virtio_scsi_do_one_tmf_bh(req); ++ } ++} ++ ++static void virtio_scsi_reset_tmf_bh(VirtIOSCSI *s) ++{ ++ VirtIOSCSIReq *req; ++ VirtIOSCSIReq *tmp; ++ ++ virtio_scsi_acquire(s); ++ ++ if (s->tmf_bh) { ++ qemu_bh_delete(s->tmf_bh); ++ s->tmf_bh = NULL; ++ } ++ ++ QTAILQ_FOREACH_SAFE(req, &s->tmf_bh_list, next, tmp) { ++ QTAILQ_REMOVE(&s->tmf_bh_list, req, next); ++ ++ /* SAM-6 6.3.2 Hard reset */ ++ req->resp.tmf.response = VIRTIO_SCSI_S_TARGET_FAILURE; ++ virtio_scsi_complete_req(req); ++ } ++ ++ virtio_scsi_release(s); ++} ++ ++static void virtio_scsi_defer_tmf_to_bh(VirtIOSCSIReq *req) ++{ ++ VirtIOSCSI *s = req->dev; ++ ++ QTAILQ_INSERT_TAIL(&s->tmf_bh_list, req, next); ++ ++ if (!s->tmf_bh) { ++ s->tmf_bh = qemu_bh_new(virtio_scsi_do_tmf_bh, s); ++ qemu_bh_schedule(s->tmf_bh); ++ } ++} ++ + /* Return 0 if the request is ready to be completed and return to guest; + * -EINPROGRESS if the request is submitted and will be completed later, in the + * case of async cancellation. */ +@@ -263,8 +375,6 @@ static int virtio_scsi_do_tmf(VirtIOSCSI *s, VirtIOSCSIReq *req) + { + SCSIDevice *d = virtio_scsi_device_get(s, req->req.tmf.lun); + SCSIRequest *r, *next; +- BusChild *kid; +- int target; + int ret = 0; + + virtio_scsi_ctx_check(s, d); +@@ -321,15 +431,9 @@ static int virtio_scsi_do_tmf(VirtIOSCSI *s, VirtIOSCSIReq *req) + break; + + case VIRTIO_SCSI_T_TMF_LOGICAL_UNIT_RESET: +- if (!d) { +- goto fail; +- } +- if (d->lun != virtio_scsi_get_lun(req->req.tmf.lun)) { +- goto incorrect_lun; +- } +- s->resetting++; +- qdev_reset_all(&d->qdev); +- s->resetting--; ++ case VIRTIO_SCSI_T_TMF_I_T_NEXUS_RESET: ++ virtio_scsi_defer_tmf_to_bh(req); ++ ret = -EINPROGRESS; + break; + + case VIRTIO_SCSI_T_TMF_ABORT_TASK_SET: +@@ -372,22 +476,6 @@ static int virtio_scsi_do_tmf(VirtIOSCSI *s, VirtIOSCSIReq *req) + } + break; + +- case VIRTIO_SCSI_T_TMF_I_T_NEXUS_RESET: +- target = req->req.tmf.lun[1]; +- s->resetting++; +- +- rcu_read_lock(); +- QTAILQ_FOREACH_RCU(kid, &s->bus.qbus.children, sibling) { +- SCSIDevice *d1 = SCSI_DEVICE(kid->child); +- if (d1->channel == 0 && d1->id == target) { +- qdev_reset_all(&d1->qdev); +- } +- } +- rcu_read_unlock(); +- +- s->resetting--; +- break; +- + case VIRTIO_SCSI_T_TMF_CLEAR_ACA: + default: + req->resp.tmf.response = VIRTIO_SCSI_S_FUNCTION_REJECTED; +@@ -603,7 +691,7 @@ static void virtio_scsi_request_cancelled(SCSIRequest *r) + if (!req) { + return; + } +- if (req->dev->resetting) { ++ if (qatomic_read(&req->dev->resetting)) { + req->resp.cmd.response = VIRTIO_SCSI_S_RESET; + } else { + req->resp.cmd.response = VIRTIO_SCSI_S_ABORTED; +@@ -784,9 +872,12 @@ static void virtio_scsi_reset(VirtIODevice *vdev) + VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(vdev); + + assert(!s->dataplane_started); +- s->resetting++; ++ ++ virtio_scsi_reset_tmf_bh(s); ++ ++ qatomic_inc(&s->resetting); + qbus_reset_all(BUS(&s->bus)); +- s->resetting--; ++ qatomic_dec(&s->resetting); + + vs->sense_size = VIRTIO_SCSI_SENSE_DEFAULT_SIZE; + vs->cdb_size = VIRTIO_SCSI_CDB_DEFAULT_SIZE; +@@ -1018,6 +1109,8 @@ static void virtio_scsi_device_realize(DeviceState *dev, Error **errp) + VirtIOSCSI *s = VIRTIO_SCSI(dev); + Error *err = NULL; + ++ QTAILQ_INIT(&s->tmf_bh_list); ++ + virtio_scsi_common_realize(dev, + virtio_scsi_handle_ctrl, + virtio_scsi_handle_event, +@@ -1055,6 +1148,8 @@ static void virtio_scsi_device_unrealize(DeviceState *dev) + { + VirtIOSCSI *s = VIRTIO_SCSI(dev); + ++ virtio_scsi_reset_tmf_bh(s); ++ + qbus_set_hotplug_handler(BUS(&s->bus), NULL); + virtio_scsi_common_unrealize(dev); + } +diff --git a/include/hw/virtio/virtio-scsi.h b/include/hw/virtio/virtio-scsi.h +index 543681bc18..b0e36f25aa 100644 +--- a/include/hw/virtio/virtio-scsi.h ++++ b/include/hw/virtio/virtio-scsi.h +@@ -77,13 +77,22 @@ struct VirtIOSCSICommon { + VirtQueue **cmd_vqs; + }; + ++struct VirtIOSCSIReq; ++ + struct VirtIOSCSI { + VirtIOSCSICommon parent_obj; + + SCSIBus bus; +- int resetting; ++ int resetting; /* written from main loop thread, read from any thread */ + bool events_dropped; + ++ /* ++ * TMFs deferred to main loop BH. These fields are protected by ++ * virtio_scsi_acquire(). ++ */ ++ QEMUBH *tmf_bh; ++ QTAILQ_HEAD(, VirtIOSCSIReq) tmf_bh_list; ++ + /* Fields for dataplane below */ + AioContext *ctx; /* one iothread per virtio-scsi-pci for now */ + +@@ -106,13 +115,11 @@ typedef struct VirtIOSCSIReq { + QEMUSGList qsgl; + QEMUIOVector resp_iov; + +- union { +- /* Used for two-stage request submission */ +- QTAILQ_ENTRY(VirtIOSCSIReq) next; ++ /* Used for two-stage request submission and TMFs deferred to BH */ ++ QTAILQ_ENTRY(VirtIOSCSIReq) next; + +- /* Used for cancellation of request during TMFs */ +- int remaining; +- }; ++ /* Used for cancellation of request during TMFs */ ++ int remaining; + + SCSIRequest *sreq; + size_t resp_size; +-- +2.37.3 + diff --git a/modules-load.conf b/modules-load.conf deleted file mode 100644 index 45b477d..0000000 --- a/modules-load.conf +++ /dev/null @@ -1,4 +0,0 @@ -# When using SELinux in libvirt, automatic loading of the kvm.ko kernel -# module might not work when qemu-kvm tries to access /dev/kvm - thus we -# simply always load this module during the boot process already. -kvm diff --git a/qemu-kvm.spec b/qemu-kvm.spec index f22b861..b2f9cff 100644 --- a/qemu-kvm.spec +++ b/qemu-kvm.spec @@ -83,7 +83,7 @@ Obsoletes: %1-rhev <= %{epoch}:%{version}-%{release} Summary: QEMU is a machine emulator and virtualizer Name: qemu-kvm Version: 6.2.0 -Release: 28%{?rcrel}%{?dist} +Release: 32%{?rcrel}%{?dist} # Epoch because we pushed a qemu-1.0 package. AIUI this can't ever be dropped Epoch: 15 License: GPLv2 and GPLv2+ and CC-BY @@ -590,6 +590,68 @@ Patch224: kvm-hw-display-qxl-Avoid-buffer-overrun-in-qxl_phys2virt.patch Patch225: kvm-hw-display-qxl-Assert-memory-slot-fits-in-preallocat.patch # For bz#2155448 - RHEL8.8 - KVM: s390: pv: don't allow userspace to set the clock under PV - QEMU part Patch226: kvm-s390x-tod-kvm-don-t-save-restore-the-TOD-in-PV-guest.patch +# For bz#2125119 - Mirror job with "copy-mode":"write-blocking" that used for storage migration can't converge under heavy I/O +Patch227: kvm-block-mirror-Do-not-wait-for-active-writes.patch +# For bz#2125119 - Mirror job with "copy-mode":"write-blocking" that used for storage migration can't converge under heavy I/O +Patch228: kvm-block-mirror-Drop-mirror_wait_for_any_operation.patch +# For bz#2125119 - Mirror job with "copy-mode":"write-blocking" that used for storage migration can't converge under heavy I/O +Patch229: kvm-block-mirror-Fix-NULL-s-job-in-active-writes.patch +# For bz#2161188 - SVM: non atomic memslot updates cause boot failure with seabios and cpu-pm=on +Patch230: kvm-accel-introduce-accelerator-blocker-API.patch +# For bz#2161188 - SVM: non atomic memslot updates cause boot failure with seabios and cpu-pm=on +Patch231: kvm-KVM-keep-track-of-running-ioctls.patch +# For bz#2161188 - SVM: non atomic memslot updates cause boot failure with seabios and cpu-pm=on +Patch232: kvm-kvm-Atomic-memslot-updates.patch +# For bz#2074205 - while live-migrating many instances concurrently, libvirt sometimes return internal error: migration was active, but no RAM info was set +Patch233: kvm-migration-Read-state-once.patch +# For bz#2163713 - [s390x] VM fails to start with ISM passed through +Patch234: kvm-s390x-pci-RPCIT-second-pass-when-mappings-exhausted.patch +# For bz#2163713 - [s390x] VM fails to start with ISM passed through +Patch235: kvm-s390x-pci-coalesce-unmap-operations.patch +# For bz#2163713 - [s390x] VM fails to start with ISM passed through +Patch236: kvm-s390x-pci-shrink-DMA-aperture-to-be-bound-by-vfio-DM.patch +# For bz#2163713 - [s390x] VM fails to start with ISM passed through +Patch237: kvm-s390x-pci-reset-ISM-passthrough-devices-on-shutdown-.patch +# For bz#2147617 - qemu-img finishes successfully while having errors in commit or bitmaps operations +Patch238: kvm-qcow2-Fix-theoretical-corruption-in-store_bitmap-err.patch +# For bz#2147617 - qemu-img finishes successfully while having errors in commit or bitmaps operations +Patch239: kvm-qemu-img-commit-Report-errors-while-closing-the-imag.patch +# For bz#2147617 - qemu-img finishes successfully while having errors in commit or bitmaps operations +Patch240: kvm-qemu-img-bitmap-Report-errors-while-closing-the-imag.patch +# For bz#2147617 - qemu-img finishes successfully while having errors in commit or bitmaps operations +Patch241: kvm-qemu-iotests-Test-qemu-img-bitmap-commit-exit-code-o.patch +# For bz#2137740 - Multifd migration fails under a weak network/socket ordering race +Patch242: kvm-io-Add-support-for-MSG_PEEK-for-socket-channel.patch +# For bz#2137740 - Multifd migration fails under a weak network/socket ordering race +Patch243: kvm-migration-check-magic-value-for-deciding-the-mapping.patch +# For bz#2168187 - [s390x] qemu-kvm coredumps when SE crashes +Patch244: kvm-target-s390x-arch_dump-Fix-memory-corruption-in-s390.patch +# For bz#2168472 - Guest hangs when starting or rebooting +Patch245: kvm-aio_wait_kick-add-missing-memory-barrier.patch +# For bz#2168472 - Guest hangs when starting or rebooting +Patch246: kvm-qatomic-add-smp_mb__before-after_rmw.patch +# For bz#2168472 - Guest hangs when starting or rebooting +Patch247: kvm-qemu-thread-posix-cleanup-fix-document-QemuEvent.patch +# For bz#2168472 - Guest hangs when starting or rebooting +Patch248: kvm-qemu-thread-win32-cleanup-fix-document-QemuEvent.patch +# For bz#2168472 - Guest hangs when starting or rebooting +Patch249: kvm-edu-add-smp_mb__after_rmw.patch +# For bz#2168472 - Guest hangs when starting or rebooting +Patch250: kvm-aio-wait-switch-to-smp_mb__after_rmw.patch +# For bz#2168472 - Guest hangs when starting or rebooting +Patch251: kvm-qemu-coroutine-lock-add-smp_mb__after_rmw.patch +# For bz#2168472 - Guest hangs when starting or rebooting +Patch252: kvm-physmem-add-missing-memory-barrier.patch +# For bz#2168472 - Guest hangs when starting or rebooting +Patch253: kvm-async-update-documentation-of-the-memory-barriers.patch +# For bz#2168472 - Guest hangs when starting or rebooting +Patch254: kvm-async-clarify-usage-of-barriers-in-the-polling-case.patch +# For bz#2090990 - qemu crash with error scsi_req_unref(SCSIRequest *): Assertion `req->refcount > 0' failed or scsi_dma_complete(void *, int): Assertion `r->req.aiocb != NULL' failed [8.7.0] +Patch255: kvm-scsi-protect-req-aiocb-with-AioContext-lock.patch +# For bz#2090990 - qemu crash with error scsi_req_unref(SCSIRequest *): Assertion `req->refcount > 0' failed or scsi_dma_complete(void *, int): Assertion `r->req.aiocb != NULL' failed [8.7.0] +Patch256: kvm-dma-helpers-prevent-dma_blk_cb-vs-dma_aio_cancel-rac.patch +# For bz#2090990 - qemu crash with error scsi_req_unref(SCSIRequest *): Assertion `req->refcount > 0' failed or scsi_dma_complete(void *, int): Assertion `r->req.aiocb != NULL' failed [8.7.0] +Patch257: kvm-virtio-scsi-reset-SCSI-devices-from-main-loop-thread.patch BuildRequires: wget BuildRequires: rpm-build @@ -1759,6 +1821,63 @@ sh %{_sysconfdir}/sysconfig/modules/kvm.modules &> /dev/null || : %changelog +* Mon Mar 13 2023 Jon Maloy - 6.2.0-32.el8_8 +- kvm-aio_wait_kick-add-missing-memory-barrier.patch [bz#2168472] +- kvm-qatomic-add-smp_mb__before-after_rmw.patch [bz#2168472] +- kvm-qemu-thread-posix-cleanup-fix-document-QemuEvent.patch [bz#2168472] +- kvm-qemu-thread-win32-cleanup-fix-document-QemuEvent.patch [bz#2168472] +- kvm-edu-add-smp_mb__after_rmw.patch [bz#2168472] +- kvm-aio-wait-switch-to-smp_mb__after_rmw.patch [bz#2168472] +- kvm-qemu-coroutine-lock-add-smp_mb__after_rmw.patch [bz#2168472] +- kvm-physmem-add-missing-memory-barrier.patch [bz#2168472] +- kvm-async-update-documentation-of-the-memory-barriers.patch [bz#2168472] +- kvm-async-clarify-usage-of-barriers-in-the-polling-case.patch [bz#2168472] +- kvm-scsi-protect-req-aiocb-with-AioContext-lock.patch [bz#2090990] +- kvm-dma-helpers-prevent-dma_blk_cb-vs-dma_aio_cancel-rac.patch [bz#2090990] +- kvm-virtio-scsi-reset-SCSI-devices-from-main-loop-thread.patch [bz#2090990] +- Resolves: bz#2168472 + (Guest hangs when starting or rebooting) +- Resolves: bz#2090990 + (qemu crash with error scsi_req_unref(SCSIRequest *): Assertion `req->refcount > 0' failed or scsi_dma_complete(void *, int): Assertion `r->req.aiocb != NULL' failed [8.7.0]) + +* Wed Feb 15 2023 Jon Maloy - 6.2.0-31 +- kvm-io-Add-support-for-MSG_PEEK-for-socket-channel.patch [bz#2137740] +- kvm-migration-check-magic-value-for-deciding-the-mapping.patch [bz#2137740] +- kvm-target-s390x-arch_dump-Fix-memory-corruption-in-s390.patch [bz#2168187] +- Resolves: bz#2137740 + (Multifd migration fails under a weak network/socket ordering race) +- Resolves: bz#2168187 + ([s390x] qemu-kvm coredumps when SE crashes) + +* Mon Feb 13 2023 Jon Maloy - 6.2.0-30 +- kvm-qcow2-Fix-theoretical-corruption-in-store_bitmap-err.patch [bz#2147617] +- kvm-qemu-img-commit-Report-errors-while-closing-the-imag.patch [bz#2147617] +- kvm-qemu-img-bitmap-Report-errors-while-closing-the-imag.patch [bz#2147617] +- kvm-qemu-iotests-Test-qemu-img-bitmap-commit-exit-code-o.patch [bz#2147617] +- Resolves: bz#2147617 + (qemu-img finishes successfully while having errors in commit or bitmaps operations) + +* Fri Jan 27 2023 Jon Maloy - 6.2.0-29 +- kvm-block-mirror-Do-not-wait-for-active-writes.patch [bz#2125119] +- kvm-block-mirror-Drop-mirror_wait_for_any_operation.patch [bz#2125119] +- kvm-block-mirror-Fix-NULL-s-job-in-active-writes.patch [bz#2125119] +- kvm-accel-introduce-accelerator-blocker-API.patch [bz#2161188] +- kvm-KVM-keep-track-of-running-ioctls.patch [bz#2161188] +- kvm-kvm-Atomic-memslot-updates.patch [bz#2161188] +- kvm-migration-Read-state-once.patch [bz#2074205] +- kvm-s390x-pci-RPCIT-second-pass-when-mappings-exhausted.patch [bz#2163713] +- kvm-s390x-pci-coalesce-unmap-operations.patch [bz#2163713] +- kvm-s390x-pci-shrink-DMA-aperture-to-be-bound-by-vfio-DM.patch [bz#2163713] +- kvm-s390x-pci-reset-ISM-passthrough-devices-on-shutdown-.patch [bz#2163713] +- Resolves: bz#2125119 + (Mirror job with "copy-mode":"write-blocking" that used for storage migration can't converge under heavy I/O) +- Resolves: bz#2161188 + (SVM: non atomic memslot updates cause boot failure with seabios and cpu-pm=on) +- Resolves: bz#2074205 + (while live-migrating many instances concurrently, libvirt sometimes return internal error: migration was active, but no RAM info was set) +- Resolves: bz#2163713 + ([s390x] VM fails to start with ISM passed through) + * Wed Jan 04 2023 Jon Maloy - 6.2.0-28 - kvm-s390x-tod-kvm-don-t-save-restore-the-TOD-in-PV-guest.patch [bz#2155448] - Resolves: bz#2155448 diff --git a/rpminspect.yaml b/rpminspect.yaml deleted file mode 100644 index 889796d..0000000 --- a/rpminspect.yaml +++ /dev/null @@ -1,11 +0,0 @@ ---- -elf: - exclude_path: (.*s390-ccw.img.*)|(.*s390-netboot.img.*) -inspections: - badfuncs: off -annocheck: - - hardened: --skip-cf-protection --skip-property-note --ignore-unknown --verbose - - rhel-policy: --skip-cf-protection --skip-property-note --ignore-unknown --verbose - ignore: - - /usr/share/qemu-kvm/s390-ccw.img - - /usr/share/qemu-kvm/s390-netboot.img diff --git a/tests_data_acpi_virt_SSDT b/tests_data_acpi_virt_SSDT new file mode 100644 index 0000000000000000000000000000000000000000..375d7b6fc85a484f492a26ccd355c205f2c34473 GIT binary patch literal 736 zcmZWnF^JPp82;0gYnryuv=ve6ky!_O9Yk@A=!SHy6V5FNJ%-&%O8V`fj)#OzB2uGw|c}i-+q^1^MKw z_VHcygYT}d#t$oR)3T7e5LPP=#O$kq8(w=B4B#{vxe%s8(#DyVKR7Unu8X2Ru zu>3T5IpLGR@r15fP5^vzWXMNT3lV0eDx%=gIA z5)JvVL=50yh<*6jkA~!l$Ftx$MH~RHMeidlrF>7Z^kjq~kM_qC;7rSwprofvRkPDv zOSNnuBWwg`Fr&*6Fic^K!HGB}_rwKC(IHrnEXmT^8?<~qjw^HGH nl43HK9Wu^ho1!~0$|p*~zX9-x4PM>g?0-1R;a8+qKg)jr(Nxg^ literal 0 HcmV?d00001