diff options
151 files changed, 3544 insertions, 522 deletions
diff --git a/.gitlab-ci.d/buildtest.yml b/.gitlab-ci.d/buildtest.yml index 71d0f407ad..7e1cb0b3c2 100644 --- a/.gitlab-ci.d/buildtest.yml +++ b/.gitlab-ci.d/buildtest.yml @@ -100,6 +100,17 @@ avocado-system-debian: IMAGE: debian-amd64 MAKE_CHECK_ARGS: check-avocado +crash-test-debian: + extends: .native_test_job_template + needs: + - job: build-system-debian + artifacts: true + variables: + IMAGE: debian-amd64 + script: + - cd build + - scripts/device-crash-test -q ./qemu-system-i386 + build-system-fedora: extends: .native_build_job_template needs: @@ -134,6 +145,18 @@ avocado-system-fedora: IMAGE: fedora MAKE_CHECK_ARGS: check-avocado +crash-test-fedora: + extends: .native_test_job_template + needs: + - job: build-system-fedora + artifacts: true + variables: + IMAGE: fedora + script: + - cd build + - scripts/device-crash-test -q ./qemu-system-ppc + - scripts/device-crash-test -q ./qemu-system-riscv32 + build-system-centos: extends: .native_build_job_template needs: diff --git a/.gitlab-ci.d/cirrus.yml b/.gitlab-ci.d/cirrus.yml index d273a9e713..19e6c21401 100644 --- a/.gitlab-ci.d/cirrus.yml +++ b/.gitlab-ci.d/cirrus.yml @@ -89,3 +89,38 @@ x64-macos-11-base-build: PATH_EXTRA: /usr/local/opt/ccache/libexec:/usr/local/opt/gettext/bin PKG_CONFIG_PATH: /usr/local/opt/curl/lib/pkgconfig:/usr/local/opt/ncurses/lib/pkgconfig:/usr/local/opt/readline/lib/pkgconfig TEST_TARGETS: check-unit check-block check-qapi-schema check-softfloat check-qtest-x86_64 + + +# The following jobs run VM-based tests via KVM on a Linux-based Cirrus-CI job +.cirrus_kvm_job: + stage: build + image: registry.gitlab.com/libvirt/libvirt-ci/cirrus-run:master + needs: [] + timeout: 80m + allow_failure: true + script: + - sed -e "s|[@]CI_REPOSITORY_URL@|$CI_REPOSITORY_URL|g" + -e "s|[@]CI_COMMIT_REF_NAME@|$CI_COMMIT_REF_NAME|g" + -e "s|[@]CI_COMMIT_SHA@|$CI_COMMIT_SHA|g" + -e "s|[@]NAME@|$NAME|g" + -e "s|[@]CONFIGURE_ARGS@|$CONFIGURE_ARGS|g" + -e "s|[@]TEST_TARGETS@|$TEST_TARGETS|g" + <.gitlab-ci.d/cirrus/kvm-build.yml >.gitlab-ci.d/cirrus/$NAME.yml + - cat .gitlab-ci.d/cirrus/$NAME.yml + - cirrus-run -v --show-build-log always .gitlab-ci.d/cirrus/$NAME.yml + rules: + - when: manual + +x86-netbsd: + extends: .cirrus_kvm_job + variables: + NAME: netbsd + CONFIGURE_ARGS: --target-list=x86_64-softmmu,ppc64-softmmu,aarch64-softmmu + TEST_TARGETS: check + +x86-openbsd: + extends: .cirrus_kvm_job + variables: + NAME: openbsd + CONFIGURE_ARGS: --target-list=i386-softmmu,riscv64-softmmu,mips64-softmmu + TEST_TARGETS: check diff --git a/.gitlab-ci.d/cirrus/kvm-build.yml b/.gitlab-ci.d/cirrus/kvm-build.yml new file mode 100644 index 0000000000..4334fabf39 --- /dev/null +++ b/.gitlab-ci.d/cirrus/kvm-build.yml @@ -0,0 +1,31 @@ +container: + image: fedora:35 + cpu: 4 + memory: 8Gb + kvm: true + +env: + CIRRUS_CLONE_DEPTH: 1 + CI_REPOSITORY_URL: "@CI_REPOSITORY_URL@" + CI_COMMIT_REF_NAME: "@CI_COMMIT_REF_NAME@" + CI_COMMIT_SHA: "@CI_COMMIT_SHA@" + +@NAME@_task: + @NAME@_vm_cache: + folder: $HOME/.cache/qemu-vm + install_script: + - dnf update -y + - dnf install -y git make openssh-clients qemu-img qemu-system-x86 wget + clone_script: + - git clone --depth 100 "$CI_REPOSITORY_URL" . + - git fetch origin "$CI_COMMIT_REF_NAME" + - git reset --hard "$CI_COMMIT_SHA" + build_script: + - if [ -f $HOME/.cache/qemu-vm/images/@NAME@.img ]; then + make vm-build-@NAME@ J=$(getconf _NPROCESSORS_ONLN) + EXTRA_CONFIGURE_OPTS="@CONFIGURE_ARGS@" + BUILD_TARGET="@TEST_TARGETS@" ; + else + make vm-build-@NAME@ J=$(getconf _NPROCESSORS_ONLN) BUILD_TARGET=help + EXTRA_CONFIGURE_OPTS="--disable-system --disable-user --disable-tools" ; + fi diff --git a/.gitlab-ci.d/qemu-project.yml b/.gitlab-ci.d/qemu-project.yml index b3d79bc429..871262fe0e 100644 --- a/.gitlab-ci.d/qemu-project.yml +++ b/.gitlab-ci.d/qemu-project.yml @@ -11,3 +11,4 @@ include: - local: '/.gitlab-ci.d/static_checks.yml' - local: '/.gitlab-ci.d/custom-runners.yml' - local: '/.gitlab-ci.d/cirrus.yml' + - local: '/.gitlab-ci.d/windows.yml' diff --git a/.gitlab-ci.d/windows.yml b/.gitlab-ci.d/windows.yml new file mode 100644 index 0000000000..62dd9ed832 --- /dev/null +++ b/.gitlab-ci.d/windows.yml @@ -0,0 +1,98 @@ +.shared_msys2_builder: + tags: + - shared-windows + - windows + - windows-1809 + cache: + key: "${CI_JOB_NAME}-cache" + paths: + - ${CI_PROJECT_DIR}/msys64/var/cache + needs: [] + stage: build + timeout: 70m + before_script: + - If ( !(Test-Path -Path msys64\var\cache ) ) { + mkdir msys64\var\cache + } + - If ( !(Test-Path -Path msys64\var\cache\msys2.exe ) ) { + Invoke-WebRequest + "https://github.com/msys2/msys2-installer/releases/download/2021-07-25/msys2-base-x86_64-20210725.sfx.exe" + -outfile "msys64\var\cache\msys2.exe" + } + - msys64\var\cache\msys2.exe -y + - ((Get-Content -path .\msys64\etc\\post-install\\07-pacman-key.post -Raw) + -replace '--refresh-keys', '--version') | + Set-Content -Path ${CI_PROJECT_DIR}\msys64\etc\\post-install\\07-pacman-key.post + - .\msys64\usr\bin\bash -lc "sed -i 's/^CheckSpace/#CheckSpace/g' /etc/pacman.conf" + - .\msys64\usr\bin\bash -lc 'pacman --noconfirm -Syuu' # Core update + - .\msys64\usr\bin\bash -lc 'pacman --noconfirm -Syuu' # Normal update + - taskkill /F /FI "MODULES eq msys-2.0.dll" + +msys2-64bit: + extends: .shared_msys2_builder + script: + - .\msys64\usr\bin\bash -lc "pacman -Sy --noconfirm --needed + diffutils git grep make sed + mingw-w64-x86_64-capstone + mingw-w64-x86_64-curl + mingw-w64-x86_64-cyrus-sasl + mingw-w64-x86_64-gcc + mingw-w64-x86_64-glib2 + mingw-w64-x86_64-gnutls + mingw-w64-x86_64-libnfs + mingw-w64-x86_64-libpng + mingw-w64-x86_64-libssh + mingw-w64-x86_64-libtasn1 + mingw-w64-x86_64-libusb + mingw-w64-x86_64-libxml2 + mingw-w64-x86_64-nettle + mingw-w64-x86_64-ninja + mingw-w64-x86_64-pixman + mingw-w64-x86_64-pkgconf + mingw-w64-x86_64-python + mingw-w64-x86_64-SDL2 + mingw-w64-x86_64-SDL2_image + mingw-w64-x86_64-snappy + mingw-w64-x86_64-usbredir + mingw-w64-x86_64-zstd " + - $env:CHERE_INVOKING = 'yes' # Preserve the current working directory + - $env:MSYSTEM = 'MINGW64' # Start a 64 bit Mingw environment + - .\msys64\usr\bin\bash -lc './configure --target-list=x86_64-softmmu + --enable-capstone=system --without-default-devices' + - .\msys64\usr\bin\bash -lc "sed -i '/^ROMS=/d' build/config-host.mak" + - .\msys64\usr\bin\bash -lc 'make -j2' + - .\msys64\usr\bin\bash -lc 'make check' + +msys2-32bit: + extends: .shared_msys2_builder + script: + - .\msys64\usr\bin\bash -lc "pacman -Sy --noconfirm --needed + diffutils git grep make sed + mingw-w64-i686-capstone + mingw-w64-i686-curl + mingw-w64-i686-cyrus-sasl + mingw-w64-i686-gcc + mingw-w64-i686-glib2 + mingw-w64-i686-gnutls + mingw-w64-i686-gtk3 + mingw-w64-i686-libgcrypt + mingw-w64-i686-libjpeg-turbo + mingw-w64-i686-libssh + mingw-w64-i686-libtasn1 + mingw-w64-i686-libusb + mingw-w64-i686-libxml2 + mingw-w64-i686-lzo2 + mingw-w64-i686-ninja + mingw-w64-i686-pixman + mingw-w64-i686-pkgconf + mingw-w64-i686-python + mingw-w64-i686-snappy + mingw-w64-i686-usbredir " + - $env:CHERE_INVOKING = 'yes' # Preserve the current working directory + - $env:MSYSTEM = 'MINGW32' # Start a 32-bit MinG environment + - mkdir output + - cd output + - ..\msys64\usr\bin\bash -lc "../configure --target-list=ppc64-softmmu + --enable-capstone=system" + - ..\msys64\usr\bin\bash -lc 'make -j2' + - ..\msys64\usr\bin\bash -lc 'make check' diff --git a/.mailmap b/.mailmap index 8beb2f95ae..c45d1c5301 100644 --- a/.mailmap +++ b/.mailmap @@ -50,6 +50,7 @@ Aleksandar Rikalo <aleksandar.rikalo@syrmia.com> <arikalo@wavecomp.com> Aleksandar Rikalo <aleksandar.rikalo@syrmia.com> <aleksandar.rikalo@rt-rk.com> Alexander Graf <agraf@csgraf.de> <agraf@suse.de> Anthony Liguori <anthony@codemonkey.ws> Anthony Liguori <aliguori@us.ibm.com> +Christian Borntraeger <borntraeger@linux.ibm.com> <borntraeger@de.ibm.com> Filip Bozuta <filip.bozuta@syrmia.com> <filip.bozuta@rt-rk.com.com> Frederic Konrad <konrad@adacore.com> <fred.konrad@greensocs.com> Greg Kurz <groug@kaod.org> <gkurz@linux.vnet.ibm.com> diff --git a/MAINTAINERS b/MAINTAINERS index 7543eb4d59..9a8d1bdf72 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -393,7 +393,7 @@ F: target/ppc/kvm.c S390 KVM CPUs M: Halil Pasic <pasic@linux.ibm.com> -M: Christian Borntraeger <borntraeger@de.ibm.com> +M: Christian Borntraeger <borntraeger@linux.ibm.com> S: Supported F: target/s390x/kvm/ F: target/s390x/ioinst.[ch] @@ -1527,7 +1527,7 @@ S390 Machines ------------- S390 Virtio-ccw M: Halil Pasic <pasic@linux.ibm.com> -M: Christian Borntraeger <borntraeger@de.ibm.com> +M: Christian Borntraeger <borntraeger@linux.ibm.com> S: Supported F: hw/char/sclp*.[hc] F: hw/char/terminal3270.c @@ -1541,7 +1541,7 @@ T: git https://github.com/borntraeger/qemu.git s390-next L: qemu-s390x@nongnu.org S390-ccw boot -M: Christian Borntraeger <borntraeger@de.ibm.com> +M: Christian Borntraeger <borntraeger@linux.ibm.com> M: Thomas Huth <thuth@redhat.com> S: Supported F: hw/s390x/ipl.* @@ -1825,6 +1825,7 @@ F: hw/scsi/* F: tests/qtest/virtio-scsi-test.c F: tests/qtest/fuzz-virtio-scsi-test.c F: tests/qtest/am53c974-test.c +F: tests/qtest/fuzz-lsi53c895a-test.c T: git https://github.com/bonzini/qemu.git scsi-next SSI diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c index eecd8031cf..0e66ebb497 100644 --- a/accel/kvm/kvm-all.c +++ b/accel/kvm/kvm-all.c @@ -61,6 +61,10 @@ #endif #define PAGE_SIZE qemu_real_host_page_size +#ifndef KVM_GUESTDBG_BLOCKIRQ +#define KVM_GUESTDBG_BLOCKIRQ 0 +#endif + //#define DEBUG_KVM #ifdef DEBUG_KVM @@ -168,6 +172,8 @@ bool kvm_vm_attributes_allowed; bool kvm_direct_msi_allowed; bool kvm_ioeventfd_any_length_allowed; bool kvm_msi_use_devid; +bool kvm_has_guest_debug; +int kvm_sstep_flags; static bool kvm_immediate_exit; static hwaddr kvm_max_slot_size = ~0; @@ -2564,6 +2570,25 @@ static int kvm_init(MachineState *ms) kvm_ioeventfd_any_length_allowed = (kvm_check_extension(s, KVM_CAP_IOEVENTFD_ANY_LENGTH) > 0); +#ifdef KVM_CAP_SET_GUEST_DEBUG + kvm_has_guest_debug = + (kvm_check_extension(s, KVM_CAP_SET_GUEST_DEBUG) > 0); +#endif + + kvm_sstep_flags = 0; + if (kvm_has_guest_debug) { + kvm_sstep_flags = SSTEP_ENABLE; + +#if defined KVM_CAP_SET_GUEST_DEBUG2 + int guest_debug_flags = + kvm_check_extension(s, KVM_CAP_SET_GUEST_DEBUG2); + + if (guest_debug_flags & KVM_GUESTDBG_BLOCKIRQ) { + kvm_sstep_flags |= SSTEP_NOIRQ; + } +#endif + } + kvm_state = s; ret = kvm_arch_init(ms, s); @@ -3193,6 +3218,10 @@ int kvm_update_guest_debug(CPUState *cpu, unsigned long reinject_trap) if (cpu->singlestep_enabled) { data.dbg.control |= KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_SINGLESTEP; + + if (cpu->singlestep_enabled & SSTEP_NOIRQ) { + data.dbg.control |= KVM_GUESTDBG_BLOCKIRQ; + } } kvm_arch_update_guest_debug(cpu, &data.dbg); diff --git a/blockdev.c b/blockdev.c index b35072644e..0eb2823b1b 100644 --- a/blockdev.c +++ b/blockdev.c @@ -303,16 +303,6 @@ int drive_get_max_bus(BlockInterfaceType type) return max_bus; } -/* Get a block device. This should only be used for single-drive devices - (e.g. SD/Floppy/MTD). Multi-disk devices (scsi/ide) should use the - appropriate bus. */ -DriveInfo *drive_get_next(BlockInterfaceType type) -{ - static int next_block_unit[IF_COUNT]; - - return drive_get(type, 0, next_block_unit[type]++); -} - static void bdrv_format_print(void *opaque, const char *name) { qemu_printf(" %s", name); diff --git a/configure b/configure index 48c21775f3..5fae19858d 100755 --- a/configure +++ b/configure @@ -344,7 +344,6 @@ debug_stack_usage="no" crypto_afalg="no" tls_priority="NORMAL" tpm="$default_feature" -libssh="$default_feature" live_block_migration=${default_feature:-yes} numa="$default_feature" replication=${default_feature:-yes} @@ -626,7 +625,6 @@ fi case $targetos in MINGW32*) mingw32="yes" - supported_os="yes" plugins="no" pie="no" ;; @@ -668,7 +666,6 @@ SunOS) QEMU_CFLAGS="-D__EXTENSIONS__ $QEMU_CFLAGS" ;; Haiku) - haiku="yes" pie="no" QEMU_CFLAGS="-DB_USE_POSITIVE_POSIX_ERRORS -D_BSD_SOURCE -fPIC $QEMU_CFLAGS" ;; @@ -1078,10 +1075,6 @@ for opt do ;; --enable-tpm) tpm="yes" ;; - --disable-libssh) libssh="no" - ;; - --enable-libssh) libssh="yes" - ;; --disable-live-block-migration) live_block_migration="no" ;; --enable-live-block-migration) live_block_migration="yes" @@ -1448,7 +1441,6 @@ cat << EOF live-block-migration Block migration in the main migration stream coroutine-pool coroutine freelist (better performance) tpm TPM support - libssh ssh block device support numa libnuma support avx2 AVX2 optimization support avx512f AVX512F optimization support @@ -2562,21 +2554,6 @@ if test "$modules" = yes; then fi ########################################## -# libssh probe -if test "$libssh" != "no" ; then - if $pkg_config --exists "libssh >= 0.8.7"; then - libssh_cflags=$($pkg_config libssh --cflags) - libssh_libs=$($pkg_config libssh --libs) - libssh=yes - else - if test "$libssh" = "yes" ; then - error_exit "libssh required for --enable-libssh" - fi - libssh=no - fi -fi - -########################################## # TPM emulation is only on POSIX if test "$tpm" = ""; then @@ -3472,9 +3449,6 @@ fi if test "$solaris" = "yes" ; then echo "CONFIG_SOLARIS=y" >> $config_host_mak fi -if test "$haiku" = "yes" ; then - echo "CONFIG_HAIKU=y" >> $config_host_mak -fi if test "$static" = "yes" ; then echo "CONFIG_STATIC=y" >> $config_host_mak fi @@ -3636,12 +3610,6 @@ if test "$cmpxchg128" = "yes" ; then echo "CONFIG_CMPXCHG128=y" >> $config_host_mak fi -if test "$libssh" = "yes" ; then - echo "CONFIG_LIBSSH=y" >> $config_host_mak - echo "LIBSSH_CFLAGS=$libssh_cflags" >> $config_host_mak - echo "LIBSSH_LIBS=$libssh_libs" >> $config_host_mak -fi - if test "$live_block_migration" = "yes" ; then echo "CONFIG_LIVE_BLOCK_MIGRATION=y" >> $config_host_mak fi diff --git a/docs/system/arm/aspeed.rst b/docs/system/arm/aspeed.rst index cec87e3743..d8b102fa0a 100644 --- a/docs/system/arm/aspeed.rst +++ b/docs/system/arm/aspeed.rst @@ -14,6 +14,7 @@ AST2400 SoC based machines : - ``palmetto-bmc`` OpenPOWER Palmetto POWER8 BMC - ``quanta-q71l-bmc`` OpenBMC Quanta BMC +- ``supermicrox11-bmc`` Supermicro X11 BMC AST2500 SoC based machines : @@ -21,12 +22,16 @@ AST2500 SoC based machines : - ``romulus-bmc`` OpenPOWER Romulus POWER9 BMC - ``witherspoon-bmc`` OpenPOWER Witherspoon POWER9 BMC - ``sonorapass-bmc`` OCP SonoraPass BMC -- ``swift-bmc`` OpenPOWER Swift BMC POWER9 +- ``swift-bmc`` OpenPOWER Swift BMC POWER9 (to be removed in v7.0) +- ``fp5280g2-bmc`` Inspur FP5280G2 BMC +- ``g220a-bmc`` Bytedance G220A BMC AST2600 SoC based machines : - ``ast2600-evb`` Aspeed AST2600 Evaluation board (Cortex-A7) - ``tacoma-bmc`` OpenPOWER Witherspoon POWER9 AST2600 BMC +- ``rainier-bmc`` IBM Rainier POWER10 BMC +- ``fuji-bmc`` Facebook Fuji BMC Supported devices ----------------- @@ -51,13 +56,13 @@ Supported devices * Front LEDs (PCA9552 on I2C bus) * LPC Peripheral Controller (a subset of subdevices are supported) * Hash/Crypto Engine (HACE) - Hash support only. TODO: HMAC and RSA + * ADC Missing devices --------------- * Coprocessor support - * ADC (out of tree implementation) * PWM and Fan Controller * Slave GPIO Controller * Super I/O Controller @@ -73,16 +78,25 @@ Missing devices Boot options ------------ -The Aspeed machines can be started using the ``-kernel`` option to -load a Linux kernel or from a firmware. Images can be downloaded from -the OpenBMC jenkins : +The Aspeed machines can be started using the ``-kernel`` and ``-dtb`` options +to load a Linux kernel or from a firmware. Images can be downloaded from the +OpenBMC jenkins : - https://jenkins.openbmc.org/job/ci-openbmc/lastSuccessfulBuild/distro=ubuntu,label=docker-builder + https://jenkins.openbmc.org/job/ci-openbmc/lastSuccessfulBuild/ or directly from the OpenBMC GitHub release repository : https://github.com/openbmc/openbmc/releases +To boot a kernel directly from a Linux build tree: + +.. code-block:: bash + + $ qemu-system-arm -M ast2600-evb -nographic \ + -kernel arch/arm/boot/zImage \ + -dtb arch/arm/boot/dts/aspeed-ast2600-evb.dtb \ + -initrd rootfs.cpio + The image should be attached as an MTD drive. Run : .. code-block:: bash diff --git a/docs/system/i386/sgx.rst b/docs/system/i386/sgx.rst index f8fade5ac2..0f0a73f758 100644 --- a/docs/system/i386/sgx.rst +++ b/docs/system/i386/sgx.rst @@ -141,8 +141,7 @@ To launch a SGX guest: |qemu_system_x86| \\ -cpu host,+sgx-provisionkey \\ -object memory-backend-epc,id=mem1,size=64M,prealloc=on \\ - -object memory-backend-epc,id=mem2,size=28M \\ - -M sgx-epc.0.memdev=mem1,sgx-epc.1.memdev=mem2 + -M sgx-epc.0.memdev=mem1,sgx-epc.0.node=0 Utilizing SGX in the guest requires a kernel/OS with SGX support. The support can be determined in guest by:: @@ -152,8 +151,32 @@ The support can be determined in guest by:: and SGX epc info by:: $ dmesg | grep sgx - [ 1.242142] sgx: EPC section 0x180000000-0x181bfffff - [ 1.242319] sgx: EPC section 0x181c00000-0x1837fffff + [ 0.182807] sgx: EPC section 0x140000000-0x143ffffff + [ 0.183695] sgx: [Firmware Bug]: Unable to map EPC section to online node. Fallback to the NUMA node 0. + +To launch a SGX numa guest: + +.. parsed-literal:: + + |qemu_system_x86| \\ + -cpu host,+sgx-provisionkey \\ + -object memory-backend-ram,size=2G,host-nodes=0,policy=bind,id=node0 \\ + -object memory-backend-epc,id=mem0,size=64M,prealloc=on,host-nodes=0,policy=bind \\ + -numa node,nodeid=0,cpus=0-1,memdev=node0 \\ + -object memory-backend-ram,size=2G,host-nodes=1,policy=bind,id=node1 \\ + -object memory-backend-epc,id=mem1,size=28M,prealloc=on,host-nodes=1,policy=bind \\ + -numa node,nodeid=1,cpus=2-3,memdev=node1 \\ + -M sgx-epc.0.memdev=mem0,sgx-epc.0.node=0,sgx-epc.1.memdev=mem1,sgx-epc.1.node=1 + +and SGX epc numa info by:: + + $ dmesg | grep sgx + [ 0.369937] sgx: EPC section 0x180000000-0x183ffffff + [ 0.370259] sgx: EPC section 0x184000000-0x185bfffff + + $ dmesg | grep SRAT + [ 0.009981] ACPI: SRAT: Node 0 PXM 0 [mem 0x180000000-0x183ffffff] + [ 0.009982] ACPI: SRAT: Node 1 PXM 1 [mem 0x184000000-0x185bfffff] References ---------- diff --git a/dump/dump.c b/dump/dump.c index 662d0a62cd..a84d8b1598 100644 --- a/dump/dump.c +++ b/dump/dump.c @@ -1293,14 +1293,6 @@ static size_t get_len_buf_out(size_t page_size, uint32_t flag_compress) return 0; } -/* - * check if the page is all 0 - */ -static inline bool is_zero_page(const uint8_t *buf, size_t page_size) -{ - return buffer_is_zero(buf, page_size); -} - static void write_dump_pages(DumpState *s, Error **errp) { int ret = 0; @@ -1357,7 +1349,7 @@ static void write_dump_pages(DumpState *s, Error **errp) */ while (get_next_page(&block_iter, &pfn_iter, &buf, s)) { /* check zero page */ - if (is_zero_page(buf, s->dump_info.page_size)) { + if (buffer_is_zero(buf, s->dump_info.page_size)) { ret = write_cache(&page_desc, &pd_zero, sizeof(PageDescriptor), false); if (ret < 0) { diff --git a/gdbstub.c b/gdbstub.c index 141d7bc4ec..3c14c6a038 100644 --- a/gdbstub.c +++ b/gdbstub.c @@ -368,27 +368,10 @@ typedef struct GDBState { gdb_syscall_complete_cb current_syscall_cb; GString *str_buf; GByteArray *mem_buf; + int sstep_flags; + int supported_sstep_flags; } GDBState; -/* By default use no IRQs and no timers while single stepping so as to - * make single stepping like an ICE HW step. - */ -static int sstep_flags = SSTEP_ENABLE|SSTEP_NOIRQ|SSTEP_NOTIMER; - -/* Retrieves flags for single step mode. */ -static int get_sstep_flags(void) -{ - /* - * In replay mode all events written into the log should be replayed. - * That is why NOIRQ flag is removed in this mode. - */ - if (replay_mode != REPLAY_MODE_NONE) { - return SSTEP_ENABLE; - } else { - return sstep_flags; - } -} - static GDBState gdbserver_state; static void init_gdbserver_state(void) @@ -399,6 +382,29 @@ static void init_gdbserver_state(void) gdbserver_state.str_buf = g_string_new(NULL); gdbserver_state.mem_buf = g_byte_array_sized_new(MAX_PACKET_LENGTH); gdbserver_state.last_packet = g_byte_array_sized_new(MAX_PACKET_LENGTH + 4); + + /* + * In replay mode all events will come from the log and can't be + * suppressed otherwise we would break determinism. However as those + * events are tied to the number of executed instructions we won't see + * them occurring every time we single step. + */ + if (replay_mode != REPLAY_MODE_NONE) { + gdbserver_state.supported_sstep_flags = SSTEP_ENABLE; + } else if (kvm_enabled()) { + gdbserver_state.supported_sstep_flags = kvm_get_supported_sstep_flags(); + } else { + gdbserver_state.supported_sstep_flags = + SSTEP_ENABLE | SSTEP_NOIRQ | SSTEP_NOTIMER; + } + + /* + * By default use no IRQs and no timers while single stepping so as to + * make single stepping like an ICE HW step. + */ + gdbserver_state.sstep_flags = SSTEP_ENABLE | SSTEP_NOIRQ | SSTEP_NOTIMER; + gdbserver_state.sstep_flags &= gdbserver_state.supported_sstep_flags; + } #ifndef CONFIG_USER_ONLY @@ -505,7 +511,7 @@ static int gdb_continue_partial(char *newstates) CPU_FOREACH(cpu) { if (newstates[cpu->cpu_index] == 's') { trace_gdbstub_op_stepping(cpu->cpu_index); - cpu_single_step(cpu, sstep_flags); + cpu_single_step(cpu, gdbserver_state.sstep_flags); } } gdbserver_state.running_state = 1; @@ -524,7 +530,7 @@ static int gdb_continue_partial(char *newstates) break; /* nothing to do here */ case 's': trace_gdbstub_op_stepping(cpu->cpu_index); - cpu_single_step(cpu, get_sstep_flags()); + cpu_single_step(cpu, gdbserver_state.sstep_flags); cpu_resume(cpu); flag = 1; break; @@ -1883,7 +1889,7 @@ static void handle_step(GArray *params, void *user_ctx) gdb_set_cpu_pc((target_ulong)get_param(params, 0)->val_ull); } - cpu_single_step(gdbserver_state.c_cpu, get_sstep_flags()); + cpu_single_step(gdbserver_state.c_cpu, gdbserver_state.sstep_flags); gdb_continue(); } @@ -2017,24 +2023,44 @@ static void handle_v_commands(GArray *params, void *user_ctx) static void handle_query_qemu_sstepbits(GArray *params, void *user_ctx) { - g_string_printf(gdbserver_state.str_buf, "ENABLE=%x,NOIRQ=%x,NOTIMER=%x", - SSTEP_ENABLE, SSTEP_NOIRQ, SSTEP_NOTIMER); + g_string_printf(gdbserver_state.str_buf, "ENABLE=%x", SSTEP_ENABLE); + + if (gdbserver_state.supported_sstep_flags & SSTEP_NOIRQ) { + g_string_append_printf(gdbserver_state.str_buf, ",NOIRQ=%x", + SSTEP_NOIRQ); + } + + if (gdbserver_state.supported_sstep_flags & SSTEP_NOTIMER) { + g_string_append_printf(gdbserver_state.str_buf, ",NOTIMER=%x", + SSTEP_NOTIMER); + } + put_strbuf(); } static void handle_set_qemu_sstep(GArray *params, void *user_ctx) { + int new_sstep_flags; + if (!params->len) { return; } - sstep_flags = get_param(params, 0)->val_ul; + new_sstep_flags = get_param(params, 0)->val_ul; + + if (new_sstep_flags & ~gdbserver_state.supported_sstep_flags) { + put_packet("E22"); + return; + } + + gdbserver_state.sstep_flags = new_sstep_flags; put_packet("OK"); } static void handle_query_qemu_sstep(GArray *params, void *user_ctx) { - g_string_printf(gdbserver_state.str_buf, "0x%x", sstep_flags); + g_string_printf(gdbserver_state.str_buf, "0x%x", + gdbserver_state.sstep_flags); put_strbuf(); } @@ -3497,6 +3523,11 @@ int gdbserver_start(const char *device) return -1; } + if (kvm_enabled() && !kvm_supports_guest_debug()) { + error_report("gdbstub: KVM doesn't support guest debugging"); + return -1; + } + if (!device) return -1; if (strcmp(device, "none") != 0) { diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index 2d37d29f02..e652590943 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -27,6 +27,7 @@ config ARM_VIRT select DIMM select ACPI_HW_REDUCED select ACPI_APEI + select ACPI_VIOT config CHEETAH bool diff --git a/hw/arm/aspeed.c b/hw/arm/aspeed.c index a77f46b3ad..cf20ae0db5 100644 --- a/hw/arm/aspeed.c +++ b/hw/arm/aspeed.c @@ -284,12 +284,13 @@ static void write_boot_rom(DriveInfo *dinfo, hwaddr addr, size_t rom_size, } static void aspeed_board_init_flashes(AspeedSMCState *s, - const char *flashtype) + const char *flashtype, + int unit0) { int i ; for (i = 0; i < s->num_cs; ++i) { - DriveInfo *dinfo = drive_get_next(IF_MTD); + DriveInfo *dinfo = drive_get(IF_MTD, 0, unit0 + i); qemu_irq cs_line; DeviceState *dev; @@ -382,10 +383,12 @@ static void aspeed_machine_init(MachineState *machine) "max_ram", max_ram_size - machine->ram_size); memory_region_add_subregion(&bmc->ram_container, machine->ram_size, &bmc->max_ram); - aspeed_board_init_flashes(&bmc->soc.fmc, bmc->fmc_model ? - bmc->fmc_model : amc->fmc_model); - aspeed_board_init_flashes(&bmc->soc.spi[0], bmc->spi_model ? - bmc->spi_model : amc->spi_model); + aspeed_board_init_flashes(&bmc->soc.fmc, + bmc->fmc_model ? bmc->fmc_model : amc->fmc_model, + 0); + aspeed_board_init_flashes(&bmc->soc.spi[0], + bmc->spi_model ? bmc->spi_model : amc->spi_model, + bmc->soc.fmc.num_cs); /* Install first FMC flash content as a boot rom. */ if (drive0) { @@ -435,11 +438,13 @@ static void aspeed_machine_init(MachineState *machine) } for (i = 0; i < bmc->soc.sdhci.num_slots; i++) { - sdhci_attach_drive(&bmc->soc.sdhci.slots[i], drive_get_next(IF_SD)); + sdhci_attach_drive(&bmc->soc.sdhci.slots[i], + drive_get(IF_SD, 0, i)); } if (bmc->soc.emmc.num_slots) { - sdhci_attach_drive(&bmc->soc.emmc.slots[0], drive_get_next(IF_SD)); + sdhci_attach_drive(&bmc->soc.emmc.slots[0], + drive_get(IF_SD, 0, bmc->soc.sdhci.num_slots)); } arm_load_kernel(ARM_CPU(first_cpu), machine, &aspeed_board_binfo); diff --git a/hw/arm/boot.c b/hw/arm/boot.c index 74ad397b1f..399f8e837c 100644 --- a/hw/arm/boot.c +++ b/hw/arm/boot.c @@ -8,7 +8,6 @@ */ #include "qemu/osdep.h" -#include "qemu-common.h" #include "qemu/datadir.h" #include "qemu/error-report.h" #include "qapi/error.h" diff --git a/hw/arm/cubieboard.c b/hw/arm/cubieboard.c index 294ba5de6e..5e3372a3c7 100644 --- a/hw/arm/cubieboard.c +++ b/hw/arm/cubieboard.c @@ -81,7 +81,7 @@ static void cubieboard_init(MachineState *machine) } /* Retrieve SD bus */ - di = drive_get_next(IF_SD); + di = drive_get(IF_SD, 0, 0); blk = di ? blk_by_legacy_dinfo(di) : NULL; bus = qdev_get_child_bus(DEVICE(a10), "sd-bus"); diff --git a/hw/arm/digic_boards.c b/hw/arm/digic_boards.c index b771a3d8b7..4093af09cb 100644 --- a/hw/arm/digic_boards.c +++ b/hw/arm/digic_boards.c @@ -25,7 +25,6 @@ #include "qemu/osdep.h" #include "qapi/error.h" -#include "qemu-common.h" #include "qemu/datadir.h" #include "hw/boards.h" #include "qemu/error-report.h" diff --git a/hw/arm/highbank.c b/hw/arm/highbank.c index c3cb315dbc..4210894d81 100644 --- a/hw/arm/highbank.c +++ b/hw/arm/highbank.c @@ -18,7 +18,6 @@ */ #include "qemu/osdep.h" -#include "qemu-common.h" #include "qemu/datadir.h" #include "qapi/error.h" #include "hw/sysbus.h" diff --git a/hw/arm/imx25_pdk.c b/hw/arm/imx25_pdk.c index bd16acd4d9..6dff000163 100644 --- a/hw/arm/imx25_pdk.c +++ b/hw/arm/imx25_pdk.c @@ -123,7 +123,7 @@ static void imx25_pdk_init(MachineState *machine) DriveInfo *di; BlockBackend *blk; - di = drive_get_next(IF_SD); + di = drive_get(IF_SD, 0, i); blk = di ? blk_by_legacy_dinfo(di) : NULL; bus = qdev_get_child_bus(DEVICE(&s->soc.esdhc[i]), "sd-bus"); carddev = qdev_new(TYPE_SD_CARD); diff --git a/hw/arm/integratorcp.c b/hw/arm/integratorcp.c index 16e8985953..b109ece3ae 100644 --- a/hw/arm/integratorcp.c +++ b/hw/arm/integratorcp.c @@ -649,7 +649,7 @@ static void integratorcp_init(MachineState *machine) qdev_get_gpio_in_named(icp, ICP_GPIO_MMC_WPROT, 0)); qdev_connect_gpio_out_named(dev, "card-inserted", 0, qdev_get_gpio_in_named(icp, ICP_GPIO_MMC_CARDIN, 0)); - dinfo = drive_get_next(IF_SD); + dinfo = drive_get(IF_SD, 0, 0); if (dinfo) { DeviceState *card; diff --git a/hw/arm/mcimx6ul-evk.c b/hw/arm/mcimx6ul-evk.c index 77fae874b1..28b4886f48 100644 --- a/hw/arm/mcimx6ul-evk.c +++ b/hw/arm/mcimx6ul-evk.c @@ -52,7 +52,7 @@ static void mcimx6ul_evk_init(MachineState *machine) DriveInfo *di; BlockBackend *blk; - di = drive_get_next(IF_SD); + di = drive_get(IF_SD, 0, i); blk = di ? blk_by_legacy_dinfo(di) : NULL; bus = qdev_get_child_bus(DEVICE(&s->usdhc[i]), "sd-bus"); carddev = qdev_new(TYPE_SD_CARD); diff --git a/hw/arm/mcimx7d-sabre.c b/hw/arm/mcimx7d-sabre.c index 935d4b0f1c..50a5ecde31 100644 --- a/hw/arm/mcimx7d-sabre.c +++ b/hw/arm/mcimx7d-sabre.c @@ -52,7 +52,7 @@ static void mcimx7d_sabre_init(MachineState *machine) DriveInfo *di; BlockBackend *blk; - di = drive_get_next(IF_SD); + di = drive_get(IF_SD, 0, i); blk = di ? blk_by_legacy_dinfo(di) : NULL; bus = qdev_get_child_bus(DEVICE(&s->usdhc[i]), "sd-bus"); carddev = qdev_new(TYPE_SD_CARD); diff --git a/hw/arm/msf2-som.c b/hw/arm/msf2-som.c index 396e8b9913..d9f881690e 100644 --- a/hw/arm/msf2-som.c +++ b/hw/arm/msf2-som.c @@ -45,7 +45,7 @@ static void emcraft_sf2_s2s010_init(MachineState *machine) DeviceState *spi_flash; MSF2State *soc; MachineClass *mc = MACHINE_GET_CLASS(machine); - DriveInfo *dinfo = drive_get_next(IF_MTD); + DriveInfo *dinfo = drive_get(IF_MTD, 0, 0); qemu_irq cs_line; BusState *spi_bus; MemoryRegion *sysmem = get_system_memory(); diff --git a/hw/arm/npcm7xx_boards.c b/hw/arm/npcm7xx_boards.c index dec7d16ae5..0866d2f4f0 100644 --- a/hw/arm/npcm7xx_boards.c +++ b/hw/arm/npcm7xx_boards.c @@ -24,7 +24,6 @@ #include "hw/qdev-core.h" #include "hw/qdev-properties.h" #include "qapi/error.h" -#include "qemu-common.h" #include "qemu/datadir.h" #include "qemu/units.h" #include "sysemu/blockdev.h" @@ -84,9 +83,9 @@ static void npcm7xx_connect_dram(NPCM7xxState *soc, MemoryRegion *dram) &error_abort); } -static void sdhci_attach_drive(SDHCIState *sdhci) +static void sdhci_attach_drive(SDHCIState *sdhci, int unit) { - DriveInfo *di = drive_get_next(IF_SD); + DriveInfo *di = drive_get(IF_SD, 0, unit); BlockBackend *blk = di ? blk_by_legacy_dinfo(di) : NULL; BusState *bus = qdev_get_child_bus(DEVICE(sdhci), "sd-bus"); @@ -374,7 +373,7 @@ static void quanta_gbs_init(MachineState *machine) drive_get(IF_MTD, 0, 0)); quanta_gbs_i2c_init(soc); - sdhci_attach_drive(&soc->mmc.sdhci); + sdhci_attach_drive(&soc->mmc.sdhci, 0); npcm7xx_load_kernel(machine, soc); } diff --git a/hw/arm/orangepi.c b/hw/arm/orangepi.c index 0cf9895ce7..e796382236 100644 --- a/hw/arm/orangepi.c +++ b/hw/arm/orangepi.c @@ -85,7 +85,7 @@ static void orangepi_init(MachineState *machine) qdev_realize(DEVICE(h3), NULL, &error_abort); /* Retrieve SD bus */ - di = drive_get_next(IF_SD); + di = drive_get(IF_SD, 0, 0); blk = di ? blk_by_legacy_dinfo(di) : NULL; bus = qdev_get_child_bus(DEVICE(h3), "sd-bus"); diff --git a/hw/arm/raspi.c b/hw/arm/raspi.c index 146d35382b..b4dd6c1e99 100644 --- a/hw/arm/raspi.c +++ b/hw/arm/raspi.c @@ -284,7 +284,7 @@ static void raspi_machine_init(MachineState *machine) qdev_realize(DEVICE(&s->soc), NULL, &error_fatal); /* Create and plug in the SD cards */ - di = drive_get_next(IF_SD); + di = drive_get(IF_SD, 0, 0); blk = di ? blk_by_legacy_dinfo(di) : NULL; bus = qdev_get_child_bus(DEVICE(&s->soc), "sd-bus"); if (bus == NULL) { diff --git a/hw/arm/realview.c b/hw/arm/realview.c index 1c54316ba3..ddc70b54a5 100644 --- a/hw/arm/realview.c +++ b/hw/arm/realview.c @@ -237,7 +237,7 @@ static void realview_init(MachineState *machine, qemu_irq_invert(qdev_get_gpio_in(gpio2, 0))); qdev_connect_gpio_out_named(dev, "card-read-only", 0, mmc_irq[0]); qdev_connect_gpio_out_named(dev, "card-inserted", 0, mmc_irq[1]); - dinfo = drive_get_next(IF_SD); + dinfo = drive_get(IF_SD, 0, 0); if (dinfo) { DeviceState *card; diff --git a/hw/arm/sabrelite.c b/hw/arm/sabrelite.c index 553608e583..cce49aa25c 100644 --- a/hw/arm/sabrelite.c +++ b/hw/arm/sabrelite.c @@ -76,7 +76,7 @@ static void sabrelite_init(MachineState *machine) if (spi_bus) { DeviceState *flash_dev; qemu_irq cs_line; - DriveInfo *dinfo = drive_get_next(IF_MTD); + DriveInfo *dinfo = drive_get(IF_MTD, 0, 0); flash_dev = qdev_new("sst25vf016b"); if (dinfo) { diff --git a/hw/arm/sbsa-ref.c b/hw/arm/sbsa-ref.c index 358714bd3e..dd944553f7 100644 --- a/hw/arm/sbsa-ref.c +++ b/hw/arm/sbsa-ref.c @@ -18,7 +18,6 @@ */ #include "qemu/osdep.h" -#include "qemu-common.h" #include "qemu/datadir.h" #include "qapi/error.h" #include "qemu/error-report.h" diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index 78827ace6b..b6c8a5d609 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -10,6 +10,7 @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "hw/sysbus.h" +#include "hw/sd/sd.h" #include "hw/ssi/ssi.h" #include "hw/arm/boot.h" #include "qemu/timer.h" @@ -1157,6 +1158,9 @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) void *bus; DeviceState *sddev; DeviceState *ssddev; + DriveInfo *dinfo; + DeviceState *carddev; + BlockBackend *blk; /* * Some boards have both an OLED controller and SD card connected to @@ -1221,8 +1225,17 @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) * - Make the ssd0323 OLED controller chipselect active-low */ bus = qdev_get_child_bus(dev, "ssi"); - sddev = ssi_create_peripheral(bus, "ssi-sd"); + + dinfo = drive_get(IF_SD, 0, 0); + blk = dinfo ? blk_by_legacy_dinfo(dinfo) : NULL; + carddev = qdev_new(TYPE_SD_CARD); + qdev_prop_set_drive_err(carddev, "drive", blk, &error_fatal); + qdev_prop_set_bit(carddev, "spi", true); + qdev_realize_and_unref(carddev, + qdev_get_child_bus(sddev, "sd-bus"), + &error_fatal); + ssddev = ssi_create_peripheral(bus, "ssd0323"); gpio_out[GPIO_D][0] = qemu_irq_split( qdev_get_gpio_in_named(sddev, SSI_GPIO_CS, 0), diff --git a/hw/arm/stm32f405_soc.c b/hw/arm/stm32f405_soc.c index 0019b7f478..c07947d9f8 100644 --- a/hw/arm/stm32f405_soc.c +++ b/hw/arm/stm32f405_soc.c @@ -24,7 +24,6 @@ #include "qemu/osdep.h" #include "qapi/error.h" -#include "qemu-common.h" #include "exec/address-spaces.h" #include "sysemu/sysemu.h" #include "hw/arm/stm32f405_soc.h" diff --git a/hw/arm/versatilepb.c b/hw/arm/versatilepb.c index 575399c4fc..ecc1f6cf74 100644 --- a/hw/arm/versatilepb.c +++ b/hw/arm/versatilepb.c @@ -310,7 +310,7 @@ static void versatile_init(MachineState *machine, int board_id) qdev_connect_gpio_out(sysctl, 0, qdev_get_gpio_in(dev, 0)); dev = sysbus_create_varargs("pl181", 0x10005000, sic[22], sic[1], NULL); - dinfo = drive_get_next(IF_SD); + dinfo = drive_get(IF_SD, 0, 0); if (dinfo) { DeviceState *card; @@ -322,7 +322,7 @@ static void versatile_init(MachineState *machine, int board_id) } dev = sysbus_create_varargs("pl181", 0x1000b000, sic[23], sic[2], NULL); - dinfo = drive_get_next(IF_SD); + dinfo = drive_get(IF_SD, 0, 1); if (dinfo) { DeviceState *card; diff --git a/hw/arm/vexpress.c b/hw/arm/vexpress.c index 58481c0762..3e99b7918a 100644 --- a/hw/arm/vexpress.c +++ b/hw/arm/vexpress.c @@ -23,7 +23,6 @@ #include "qemu/osdep.h" #include "qapi/error.h" -#include "qemu-common.h" #include "qemu/datadir.h" #include "cpu.h" #include "hw/sysbus.h" @@ -625,7 +624,7 @@ static void vexpress_common_init(MachineState *machine) qdev_get_gpio_in(sysctl, ARM_SYSCTL_GPIO_MMC_WPROT)); qdev_connect_gpio_out_named(dev, "card-inserted", 0, qdev_get_gpio_in(sysctl, ARM_SYSCTL_GPIO_MMC_CARDIN)); - dinfo = drive_get_next(IF_SD); + dinfo = drive_get(IF_SD, 0, 0); if (dinfo) { DeviceState *card; @@ -657,7 +656,7 @@ static void vexpress_common_init(MachineState *machine) sysbus_create_simple("pl111", map[VE_CLCD], pic[14]); - dinfo = drive_get_next(IF_PFLASH); + dinfo = drive_get(IF_PFLASH, 0, 0); pflash0 = ve_pflash_cfi01_register(map[VE_NORFLASH0], "vexpress.flash0", dinfo); if (!pflash0) { @@ -673,7 +672,7 @@ static void vexpress_common_init(MachineState *machine) memory_region_add_subregion(sysmem, map[VE_NORFLASHALIAS], flashalias); } - dinfo = drive_get_next(IF_PFLASH); + dinfo = drive_get(IF_PFLASH, 0, 1); if (!ve_pflash_cfi01_register(map[VE_NORFLASH1], "vexpress.flash1", dinfo)) { error_report("vexpress: error registering flash 1"); diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c index 674f902652..d0f4867fdf 100644 --- a/hw/arm/virt-acpi-build.c +++ b/hw/arm/virt-acpi-build.c @@ -55,6 +55,7 @@ #include "kvm_arm.h" #include "migration/vmstate.h" #include "hw/acpi/ghes.h" +#include "hw/acpi/viot.h" #define ARM_SPI_BASE 32 @@ -1011,6 +1012,12 @@ void virt_acpi_build(VirtMachineState *vms, AcpiBuildTables *tables) } #endif + if (vms->iommu == VIRT_IOMMU_VIRTIO) { + acpi_add_table(table_offsets, tables_blob); + build_viot(ms, tables_blob, tables->linker, vms->virtio_iommu_bdf, + vms->oem_id, vms->oem_table_id); + } + /* XSDT is pointed to by RSDP */ xsdt = tables_blob->len; build_xsdt(tables_blob, tables->linker, table_offsets, vms->oem_id, diff --git a/hw/arm/virt.c b/hw/arm/virt.c index 30da05dfe0..6bce595aba 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -29,7 +29,6 @@ */ #include "qemu/osdep.h" -#include "qemu-common.h" #include "qemu/datadir.h" #include "qemu/units.h" #include "qemu/option.h" @@ -2494,6 +2493,11 @@ static void virt_machine_device_pre_plug_cb(HotplugHandler *hotplug_dev, hwaddr db_start = 0, db_end = 0; char *resv_prop_str; + if (vms->iommu != VIRT_IOMMU_NONE) { + error_setg(errp, "virt machine does not support multiple IOMMUs"); + return; + } + switch (vms->msi_controller) { case VIRT_MSI_CTRL_NONE: return; @@ -2513,8 +2517,9 @@ static void virt_machine_device_pre_plug_cb(HotplugHandler *hotplug_dev, db_start, db_end, VIRTIO_IOMMU_RESV_MEM_T_MSI); - qdev_prop_set_uint32(dev, "len-reserved-regions", 1); - qdev_prop_set_string(dev, "reserved-regions[0]", resv_prop_str); + object_property_set_uint(OBJECT(dev), "len-reserved-regions", 1, errp); + object_property_set_str(OBJECT(dev), "reserved-regions[0]", + resv_prop_str, errp); g_free(resv_prop_str); } } @@ -2614,16 +2619,10 @@ static HotplugHandler *virt_machine_get_hotplug_handler(MachineState *machine, MachineClass *mc = MACHINE_GET_CLASS(machine); if (device_is_dynamic_sysbus(mc, dev) || - (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM))) { + object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM) || + object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_IOMMU_PCI)) { return HOTPLUG_HANDLER(machine); } - if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_IOMMU_PCI)) { - VirtMachineState *vms = VIRT_MACHINE(machine); - - if (!vms->bootinfo.firmware_loaded || !virt_is_acpi_enabled(vms)) { - return HOTPLUG_HANDLER(machine); - } - } return NULL; } diff --git a/hw/arm/xilinx_zynq.c b/hw/arm/xilinx_zynq.c index 69c333e91b..50e7268396 100644 --- a/hw/arm/xilinx_zynq.c +++ b/hw/arm/xilinx_zynq.c @@ -125,9 +125,10 @@ static void gem_init(NICInfo *nd, uint32_t base, qemu_irq irq) sysbus_connect_irq(s, 0, irq); } -static inline void zynq_init_spi_flashes(uint32_t base_addr, qemu_irq irq, - bool is_qspi) +static inline int zynq_init_spi_flashes(uint32_t base_addr, qemu_irq irq, + bool is_qspi, int unit0) { + int unit = unit0; DeviceState *dev; SysBusDevice *busdev; SSIBus *spi; @@ -156,7 +157,7 @@ static inline void zynq_init_spi_flashes(uint32_t base_addr, qemu_irq irq, spi = (SSIBus *)qdev_get_child_bus(dev, bus_name); for (j = 0; j < num_ss; ++j) { - DriveInfo *dinfo = drive_get_next(IF_MTD); + DriveInfo *dinfo = drive_get(IF_MTD, 0, unit++); flash_dev = qdev_new("n25q128"); if (dinfo) { qdev_prop_set_drive_err(flash_dev, "drive", @@ -170,6 +171,7 @@ static inline void zynq_init_spi_flashes(uint32_t base_addr, qemu_irq irq, } } + return unit; } static void zynq_init(MachineState *machine) @@ -247,9 +249,9 @@ static void zynq_init(MachineState *machine) pic[n] = qdev_get_gpio_in(dev, n); } - zynq_init_spi_flashes(0xE0006000, pic[58-IRQ_OFFSET], false); - zynq_init_spi_flashes(0xE0007000, pic[81-IRQ_OFFSET], false); - zynq_init_spi_flashes(0xE000D000, pic[51-IRQ_OFFSET], true); + n = zynq_init_spi_flashes(0xE0006000, pic[58 - IRQ_OFFSET], false, 0); + n = zynq_init_spi_flashes(0xE0007000, pic[81 - IRQ_OFFSET], false, n); + n = zynq_init_spi_flashes(0xE000D000, pic[51 - IRQ_OFFSET], true, n); sysbus_create_simple(TYPE_CHIPIDEA, 0xE0002000, pic[53 - IRQ_OFFSET]); sysbus_create_simple(TYPE_CHIPIDEA, 0xE0003000, pic[76 - IRQ_OFFSET]); @@ -298,7 +300,7 @@ static void zynq_init(MachineState *machine) sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, hci_addr); sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, pic[hci_irq - IRQ_OFFSET]); - di = drive_get_next(IF_SD); + di = drive_get(IF_SD, 0, n); blk = di ? blk_by_legacy_dinfo(di) : NULL; carddev = qdev_new(TYPE_SD_CARD); qdev_prop_set_drive_err(carddev, "drive", blk, &error_fatal); diff --git a/hw/arm/xlnx-versal-virt.c b/hw/arm/xlnx-versal-virt.c index d2f55e29b6..0c5edc898e 100644 --- a/hw/arm/xlnx-versal-virt.c +++ b/hw/arm/xlnx-versal-virt.c @@ -669,7 +669,8 @@ static void versal_virt_init(MachineState *machine) /* Plugin SD cards. */ for (i = 0; i < ARRAY_SIZE(s->soc.pmc.iou.sd); i++) { - sd_plugin_card(&s->soc.pmc.iou.sd[i], drive_get_next(IF_SD)); + sd_plugin_card(&s->soc.pmc.iou.sd[i], + drive_get(IF_SD, 0, i)); } s->binfo.ram_size = machine->ram_size; diff --git a/hw/arm/xlnx-zcu102.c b/hw/arm/xlnx-zcu102.c index 3dc2b5e8ca..45eb19ab3b 100644 --- a/hw/arm/xlnx-zcu102.c +++ b/hw/arm/xlnx-zcu102.c @@ -169,7 +169,7 @@ static void xlnx_zcu102_init(MachineState *machine) /* Create and plug in the SD cards */ for (i = 0; i < XLNX_ZYNQMP_NUM_SDHCI; i++) { BusState *bus; - DriveInfo *di = drive_get_next(IF_SD); + DriveInfo *di = drive_get(IF_SD, 0, i); BlockBackend *blk = di ? blk_by_legacy_dinfo(di) : NULL; DeviceState *carddev; char *bus_name; @@ -190,7 +190,7 @@ static void xlnx_zcu102_init(MachineState *machine) BusState *spi_bus; DeviceState *flash_dev; qemu_irq cs_line; - DriveInfo *dinfo = drive_get_next(IF_MTD); + DriveInfo *dinfo = drive_get(IF_MTD, 0, i); gchar *bus_name = g_strdup_printf("spi%d", i); spi_bus = qdev_get_child_bus(DEVICE(&s->soc), bus_name); @@ -212,7 +212,7 @@ static void xlnx_zcu102_init(MachineState *machine) BusState *spi_bus; DeviceState *flash_dev; qemu_irq cs_line; - DriveInfo *dinfo = drive_get_next(IF_MTD); + DriveInfo *dinfo = drive_get(IF_MTD, 0, XLNX_ZYNQMP_NUM_SPIS + i); int bus = i / XLNX_ZYNQMP_NUM_QSPI_BUS_CS; gchar *bus_name = g_strdup_printf("qspi%d", bus); diff --git a/hw/char/stm32f2xx_usart.c b/hw/char/stm32f2xx_usart.c index 8df0832424..fde67f4f03 100644 --- a/hw/char/stm32f2xx_usart.c +++ b/hw/char/stm32f2xx_usart.c @@ -103,10 +103,11 @@ static uint64_t stm32f2xx_usart_read(void *opaque, hwaddr addr, return retvalue; case USART_DR: DB_PRINT("Value: 0x%" PRIx32 ", %c\n", s->usart_dr, (char) s->usart_dr); + retvalue = s->usart_dr & 0x3FF; s->usart_sr &= ~USART_SR_RXNE; qemu_chr_fe_accept_input(&s->chr); qemu_set_irq(s->irq, 0); - return s->usart_dr & 0x3FF; + return retvalue; case USART_BRR: return s->usart_brr; case USART_CR1: diff --git a/hw/core/numa.c b/hw/core/numa.c index e6050b2273..1aa05dcf42 100644 --- a/hw/core/numa.c +++ b/hw/core/numa.c @@ -784,9 +784,8 @@ static void numa_stat_memory_devices(NumaNodeMem node_mem[]) break; case MEMORY_DEVICE_INFO_KIND_SGX_EPC: se = value->u.sgx_epc.data; - /* TODO: once we support numa, assign to right node */ - node_mem[0].node_mem += se->size; - node_mem[0].node_plugged_mem += se->size; + node_mem[se->node].node_mem += se->size; + node_mem[se->node].node_plugged_mem = 0; break; default: g_assert_not_reached(); diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c index a99c6e4fe3..8383b83ee3 100644 --- a/hw/i386/acpi-build.c +++ b/hw/i386/acpi-build.c @@ -2068,6 +2068,8 @@ build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine) nvdimm_build_srat(table_data); } + sgx_epc_build_srat(table_data); + /* * TODO: this part is not in ACPI spec and current linux kernel boots fine * without these entries. But I recall there were issues the last time I diff --git a/hw/i386/sgx-epc.c b/hw/i386/sgx-epc.c index e508827e78..96b2940d75 100644 --- a/hw/i386/sgx-epc.c +++ b/hw/i386/sgx-epc.c @@ -21,6 +21,7 @@ static Property sgx_epc_properties[] = { DEFINE_PROP_UINT64(SGX_EPC_ADDR_PROP, SGXEPCDevice, addr, 0), + DEFINE_PROP_UINT32(SGX_EPC_NUMA_NODE_PROP, SGXEPCDevice, node, 0), DEFINE_PROP_LINK(SGX_EPC_MEMDEV_PROP, SGXEPCDevice, hostmem, TYPE_MEMORY_BACKEND_EPC, HostMemoryBackendEpc *), DEFINE_PROP_END_OF_LIST(), @@ -139,6 +140,8 @@ static void sgx_epc_md_fill_device_info(const MemoryDeviceState *md, se->memaddr = epc->addr; se->size = object_property_get_uint(OBJECT(epc), SGX_EPC_SIZE_PROP, NULL); + se->node = object_property_get_uint(OBJECT(epc), SGX_EPC_NUMA_NODE_PROP, + NULL); se->memdev = object_get_canonical_path(OBJECT(epc->hostmem)); info->u.sgx_epc.data = se; diff --git a/hw/i386/sgx-stub.c b/hw/i386/sgx-stub.c index c9b379e665..26833eb233 100644 --- a/hw/i386/sgx-stub.c +++ b/hw/i386/sgx-stub.c @@ -6,6 +6,10 @@ #include "qapi/error.h" #include "qapi/qapi-commands-misc-target.h" +void sgx_epc_build_srat(GArray *table_data) +{ +} + SGXInfo *qmp_query_sgx(Error **errp) { error_setg(errp, "SGX support is not compiled in"); diff --git a/hw/i386/sgx.c b/hw/i386/sgx.c index 8fef3dd8fa..5de5dd0893 100644 --- a/hw/i386/sgx.c +++ b/hw/i386/sgx.c @@ -23,6 +23,7 @@ #include "sysemu/hw_accel.h" #include "sysemu/reset.h" #include <sys/ioctl.h> +#include "hw/acpi/aml-build.h" #define SGX_MAX_EPC_SECTIONS 8 #define SGX_CPUID_EPC_INVALID 0x0 @@ -36,17 +37,59 @@ #define RETRY_NUM 2 +static int sgx_epc_device_list(Object *obj, void *opaque) +{ + GSList **list = opaque; + + if (object_dynamic_cast(obj, TYPE_SGX_EPC)) { + *list = g_slist_append(*list, DEVICE(obj)); + } + + object_child_foreach(obj, sgx_epc_device_list, opaque); + return 0; +} + +static GSList *sgx_epc_get_device_list(void) +{ + GSList *list = NULL; + + object_child_foreach(qdev_get_machine(), sgx_epc_device_list, &list); + return list; +} + +void sgx_epc_build_srat(GArray *table_data) +{ + GSList *device_list = sgx_epc_get_device_list(); + + for (; device_list; device_list = device_list->next) { + DeviceState *dev = device_list->data; + Object *obj = OBJECT(dev); + uint64_t addr, size; + int node; + + node = object_property_get_uint(obj, SGX_EPC_NUMA_NODE_PROP, + &error_abort); + addr = object_property_get_uint(obj, SGX_EPC_ADDR_PROP, &error_abort); + size = object_property_get_uint(obj, SGX_EPC_SIZE_PROP, &error_abort); + + build_srat_memory(table_data, addr, size, node, MEM_AFFINITY_ENABLED); + } + g_slist_free(device_list); +} + static uint64_t sgx_calc_section_metric(uint64_t low, uint64_t high) { return (low & MAKE_64BIT_MASK(12, 20)) + ((high & MAKE_64BIT_MASK(0, 20)) << 32); } -static uint64_t sgx_calc_host_epc_section_size(void) +static SGXEPCSectionList *sgx_calc_host_epc_sections(void) { + SGXEPCSectionList *head = NULL, **tail = &head; + SGXEPCSection *section; uint32_t i, type; uint32_t eax, ebx, ecx, edx; - uint64_t size = 0; + uint32_t j = 0; for (i = 0; i < SGX_MAX_EPC_SECTIONS; i++) { host_cpuid(0x12, i + 2, &eax, &ebx, &ecx, &edx); @@ -60,10 +103,13 @@ static uint64_t sgx_calc_host_epc_section_size(void) break; } - size += sgx_calc_section_metric(ecx, edx); + section = g_new0(SGXEPCSection, 1); + section->node = j++; + section->size = sgx_calc_section_metric(ecx, edx); + QAPI_LIST_APPEND(tail, section); } - return size; + return head; } static void sgx_epc_reset(void *opaque) @@ -127,13 +173,35 @@ SGXInfo *qmp_query_sgx_capabilities(Error **errp) info->sgx1 = eax & (1U << 0) ? true : false; info->sgx2 = eax & (1U << 1) ? true : false; - info->section_size = sgx_calc_host_epc_section_size(); + info->sections = sgx_calc_host_epc_sections(); close(fd); return info; } +static SGXEPCSectionList *sgx_get_epc_sections_list(void) +{ + GSList *device_list = sgx_epc_get_device_list(); + SGXEPCSectionList *head = NULL, **tail = &head; + SGXEPCSection *section; + + for (; device_list; device_list = device_list->next) { + DeviceState *dev = device_list->data; + Object *obj = OBJECT(dev); + + section = g_new0(SGXEPCSection, 1); + section->node = object_property_get_uint(obj, SGX_EPC_NUMA_NODE_PROP, + &error_abort); + section->size = object_property_get_uint(obj, SGX_EPC_SIZE_PROP, + &error_abort); + QAPI_LIST_APPEND(tail, section); + } + g_slist_free(device_list); + + return head; +} + SGXInfo *qmp_query_sgx(Error **errp) { SGXInfo *info = NULL; @@ -152,14 +220,13 @@ SGXInfo *qmp_query_sgx(Error **errp) return NULL; } - SGXEPCState *sgx_epc = &pcms->sgx_epc; info = g_new0(SGXInfo, 1); info->sgx = true; info->sgx1 = true; info->sgx2 = true; info->flc = true; - info->section_size = sgx_epc->size; + info->sections = sgx_get_epc_sections_list(); return info; } @@ -167,6 +234,7 @@ SGXInfo *qmp_query_sgx(Error **errp) void hmp_info_sgx(Monitor *mon, const QDict *qdict) { Error *err = NULL; + SGXEPCSectionList *section_list, *section; g_autoptr(SGXInfo) info = qmp_query_sgx(&err); if (err) { @@ -181,8 +249,14 @@ void hmp_info_sgx(Monitor *mon, const QDict *qdict) info->sgx2 ? "enabled" : "disabled"); monitor_printf(mon, "FLC support: %s\n", info->flc ? "enabled" : "disabled"); - monitor_printf(mon, "size: %" PRIu64 "\n", - info->section_size); + + section_list = info->sections; + for (section = section_list; section; section = section->next) { + monitor_printf(mon, "NUMA node #%" PRId64 ": ", + section->value->node); + monitor_printf(mon, "size=%" PRIu64 "\n", + section->value->size); + } } bool sgx_epc_get_section(int section_nr, uint64_t *addr, uint64_t *size) @@ -226,6 +300,9 @@ void pc_machine_init_sgx_epc(PCMachineState *pcms) /* set the memdev link with memory backend */ object_property_parse(obj, SGX_EPC_MEMDEV_PROP, list->value->memdev, &error_fatal); + /* set the numa node property for sgx epc object */ + object_property_set_uint(obj, SGX_EPC_NUMA_NODE_PROP, list->value->node, + &error_fatal); object_property_set_bool(obj, "realized", true, &error_fatal); object_unref(obj); } diff --git a/hw/intc/Kconfig b/hw/intc/Kconfig index 78aed93c45..010ded7eae 100644 --- a/hw/intc/Kconfig +++ b/hw/intc/Kconfig @@ -25,6 +25,11 @@ config APIC select MSI_NONBROKEN select I8259 +config ARM_GIC_TCG + bool + default y + depends on ARM_GIC && TCG + config ARM_GIC_KVM bool default y diff --git a/hw/intc/arm_gicv3.c b/hw/intc/arm_gicv3.c index 9f5f815db9..715df5421d 100644 --- a/hw/intc/arm_gicv3.c +++ b/hw/intc/arm_gicv3.c @@ -1,5 +1,5 @@ /* - * ARM Generic Interrupt Controller v3 + * ARM Generic Interrupt Controller v3 (emulation) * * Copyright (c) 2015 Huawei. * Copyright (c) 2016 Linaro Limited diff --git a/hw/intc/arm_gicv3_cpuif.c b/hw/intc/arm_gicv3_cpuif.c index 85fc369e55..d7e03d0cab 100644 --- a/hw/intc/arm_gicv3_cpuif.c +++ b/hw/intc/arm_gicv3_cpuif.c @@ -1,5 +1,5 @@ /* - * ARM Generic Interrupt Controller v3 + * ARM Generic Interrupt Controller v3 (emulation) * * Copyright (c) 2016 Linaro Limited * Written by Peter Maydell @@ -21,14 +21,6 @@ #include "hw/irq.h" #include "cpu.h" -void gicv3_set_gicv3state(CPUState *cpu, GICv3CPUState *s) -{ - ARMCPU *arm_cpu = ARM_CPU(cpu); - CPUARMState *env = &arm_cpu->env; - - env->gicv3state = (void *)s; -}; - static GICv3CPUState *icc_cs_from_env(CPUARMState *env) { return env->gicv3state; diff --git a/hw/intc/arm_gicv3_cpuif_common.c b/hw/intc/arm_gicv3_cpuif_common.c new file mode 100644 index 0000000000..ff1239f65d --- /dev/null +++ b/hw/intc/arm_gicv3_cpuif_common.c @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * ARM Generic Interrupt Controller v3 + * + * Copyright (c) 2016 Linaro Limited + * Written by Peter Maydell + * + * This code is licensed under the GPL, version 2 or (at your option) + * any later version. + */ + +#include "qemu/osdep.h" +#include "gicv3_internal.h" +#include "cpu.h" + +void gicv3_set_gicv3state(CPUState *cpu, GICv3CPUState *s) +{ + ARMCPU *arm_cpu = ARM_CPU(cpu); + CPUARMState *env = &arm_cpu->env; + + env->gicv3state = (void *)s; +}; diff --git a/hw/intc/arm_gicv3_its.c b/hw/intc/arm_gicv3_its.c index c929a9cb5c..b99e63d58f 100644 --- a/hw/intc/arm_gicv3_its.c +++ b/hw/intc/arm_gicv3_its.c @@ -274,21 +274,36 @@ static bool process_its_cmd(GICv3ITSState *s, uint64_t value, uint32_t offset, if (res != MEMTX_OK) { return result; } + } else { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid command attributes: " + "invalid dte: %"PRIx64" for %d (MEM_TX: %d)\n", + __func__, dte, devid, res); + return result; } - if ((devid > s->dt.maxids.max_devids) || !dte_valid || !ite_valid || - !cte_valid || (eventid > max_eventid)) { + + /* + * In this implementation, in case of guest errors we ignore the + * command and move onto the next command in the queue. + */ + if (devid > s->dt.maxids.max_devids) { qemu_log_mask(LOG_GUEST_ERROR, - "%s: invalid command attributes " - "devid %d or eventid %d or invalid dte %d or" - "invalid cte %d or invalid ite %d\n", - __func__, devid, eventid, dte_valid, cte_valid, - ite_valid); - /* - * in this implementation, in case of error - * we ignore this command and move onto the next - * command in the queue - */ + "%s: invalid command attributes: devid %d>%d", + __func__, devid, s->dt.maxids.max_devids); + + } else if (!dte_valid || !ite_valid || !cte_valid) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid command attributes: " + "dte: %s, ite: %s, cte: %s\n", + __func__, + dte_valid ? "valid" : "invalid", + ite_valid ? "valid" : "invalid", + cte_valid ? "valid" : "invalid"); + } else if (eventid > max_eventid) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid command attributes: eventid %d > %d\n", + __func__, eventid, max_eventid); } else { /* * Current implementation only supports rdbase == procnum diff --git a/hw/intc/meson.build b/hw/intc/meson.build index c89d2ca180..70080bc161 100644 --- a/hw/intc/meson.build +++ b/hw/intc/meson.build @@ -3,12 +3,14 @@ softmmu_ss.add(when: 'CONFIG_ARM_GIC', if_true: files( 'arm_gic.c', 'arm_gic_common.c', 'arm_gicv2m.c', - 'arm_gicv3.c', 'arm_gicv3_common.c', - 'arm_gicv3_dist.c', 'arm_gicv3_its_common.c', - 'arm_gicv3_redist.c', +)) +softmmu_ss.add(when: 'CONFIG_ARM_GIC_TCG', if_true: files( + 'arm_gicv3.c', + 'arm_gicv3_dist.c', 'arm_gicv3_its.c', + 'arm_gicv3_redist.c', )) softmmu_ss.add(when: 'CONFIG_ETRAXFS', if_true: files('etraxfs_pic.c')) softmmu_ss.add(when: 'CONFIG_HEATHROW_PIC', if_true: files('heathrow_pic.c')) @@ -25,7 +27,8 @@ softmmu_ss.add(when: 'CONFIG_XLNX_ZYNQMP_PMU', if_true: files('xlnx-pmu-iomod-in specific_ss.add(when: 'CONFIG_ALLWINNER_A10_PIC', if_true: files('allwinner-a10-pic.c')) specific_ss.add(when: 'CONFIG_APIC', if_true: files('apic.c', 'apic_common.c')) -specific_ss.add(when: 'CONFIG_ARM_GIC', if_true: files('arm_gicv3_cpuif.c')) +specific_ss.add(when: 'CONFIG_ARM_GIC', if_true: files('arm_gicv3_cpuif_common.c')) +specific_ss.add(when: 'CONFIG_ARM_GIC_TCG', if_true: files('arm_gicv3_cpuif.c')) specific_ss.add(when: 'CONFIG_ARM_GIC_KVM', if_true: files('arm_gic_kvm.c')) specific_ss.add(when: ['CONFIG_ARM_GIC_KVM', 'TARGET_AARCH64'], if_true: files('arm_gicv3_kvm.c', 'arm_gicv3_its_kvm.c')) specific_ss.add(when: 'CONFIG_ARM_V7M', if_true: files('armv7m_nvic.c')) diff --git a/hw/microblaze/petalogix_ml605_mmu.c b/hw/microblaze/petalogix_ml605_mmu.c index 159db6cbe2..a24fadddca 100644 --- a/hw/microblaze/petalogix_ml605_mmu.c +++ b/hw/microblaze/petalogix_ml605_mmu.c @@ -183,7 +183,7 @@ petalogix_ml605_init(MachineState *machine) spi = (SSIBus *)qdev_get_child_bus(dev, "spi"); for (i = 0; i < NUM_SPI_FLASHES; i++) { - DriveInfo *dinfo = drive_get_next(IF_MTD); + DriveInfo *dinfo = drive_get(IF_MTD, 0, i); qemu_irq cs_line; dev = qdev_new("n25q128"); diff --git a/hw/misc/sifive_u_otp.c b/hw/misc/sifive_u_otp.c index 52fdb750c0..6d5f84e6c2 100644 --- a/hw/misc/sifive_u_otp.c +++ b/hw/misc/sifive_u_otp.c @@ -209,9 +209,9 @@ static void sifive_u_otp_realize(DeviceState *dev, Error **errp) TYPE_SIFIVE_U_OTP, SIFIVE_U_OTP_REG_SIZE); sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->mmio); - dinfo = drive_get_next(IF_PFLASH); + dinfo = drive_get(IF_PFLASH, 0, 0); if (!dinfo) { - dinfo = drive_get_next(IF_NONE); + dinfo = drive_get(IF_NONE, 0, 0); if (dinfo) { warn_report("using \"-drive if=none\" for the OTP is deprecated, " "use \"-drive if=pflash\" instead."); diff --git a/hw/net/npcm7xx_emc.c b/hw/net/npcm7xx_emc.c index 7c892f820f..545b2b7410 100644 --- a/hw/net/npcm7xx_emc.c +++ b/hw/net/npcm7xx_emc.c @@ -284,6 +284,12 @@ static void emc_halt_rx(NPCM7xxEMCState *emc, uint32_t mista_flag) emc_set_mista(emc, mista_flag); } +static void emc_enable_rx_and_flush(NPCM7xxEMCState *emc) +{ + emc->rx_active = true; + qemu_flush_queued_packets(qemu_get_queue(emc->nic)); +} + static void emc_set_next_tx_descriptor(NPCM7xxEMCState *emc, const NPCM7xxEMCTxDesc *tx_desc, uint32_t desc_addr) @@ -581,13 +587,6 @@ static ssize_t emc_receive(NetClientState *nc, const uint8_t *buf, size_t len1) return len; } -static void emc_try_receive_next_packet(NPCM7xxEMCState *emc) -{ - if (emc_can_receive(qemu_get_queue(emc->nic))) { - qemu_flush_queued_packets(qemu_get_queue(emc->nic)); - } -} - static uint64_t npcm7xx_emc_read(void *opaque, hwaddr offset, unsigned size) { NPCM7xxEMCState *emc = opaque; @@ -703,7 +702,7 @@ static void npcm7xx_emc_write(void *opaque, hwaddr offset, emc->regs[REG_MGSTA] |= REG_MGSTA_RXHA; } if (value & REG_MCMDR_RXON) { - emc->rx_active = true; + emc_enable_rx_and_flush(emc); } else { emc_halt_rx(emc, 0); } @@ -739,8 +738,7 @@ static void npcm7xx_emc_write(void *opaque, hwaddr offset, break; case REG_RSDR: if (emc->regs[REG_MCMDR] & REG_MCMDR_RXON) { - emc->rx_active = true; - emc_try_receive_next_packet(emc); + emc_enable_rx_and_flush(emc); } break; case REG_MIIDA: diff --git a/hw/riscv/microchip_pfsoc.c b/hw/riscv/microchip_pfsoc.c index 57d779fb55..d1d065efbc 100644 --- a/hw/riscv/microchip_pfsoc.c +++ b/hw/riscv/microchip_pfsoc.c @@ -458,7 +458,7 @@ static void microchip_icicle_kit_machine_init(MachineState *machine) target_ulong firmware_end_addr, kernel_start_addr; uint64_t kernel_entry; uint32_t fdt_load_addr; - DriveInfo *dinfo = drive_get_next(IF_SD); + DriveInfo *dinfo = drive_get(IF_SD, 0, 0); /* Sanity check on RAM size */ if (machine->ram_size < mc->default_ram_size) { diff --git a/hw/riscv/sifive_u.c b/hw/riscv/sifive_u.c index 589ae72a59..aa74e67889 100644 --- a/hw/riscv/sifive_u.c +++ b/hw/riscv/sifive_u.c @@ -46,6 +46,7 @@ #include "hw/char/serial.h" #include "hw/cpu/cluster.h" #include "hw/misc/unimp.h" +#include "hw/sd/sd.h" #include "hw/ssi/ssi.h" #include "target/riscv/cpu.h" #include "hw/riscv/riscv_hart.h" @@ -536,7 +537,8 @@ static void sifive_u_machine_init(MachineState *machine) uint32_t fdt_load_addr; uint64_t kernel_entry; DriveInfo *dinfo; - DeviceState *flash_dev, *sd_dev; + BlockBackend *blk; + DeviceState *flash_dev, *sd_dev, *card_dev; qemu_irq flash_cs, sd_cs; /* Initialize SoC */ @@ -670,7 +672,7 @@ static void sifive_u_machine_init(MachineState *machine) /* Connect an SPI flash to SPI0 */ flash_dev = qdev_new("is25wp256"); - dinfo = drive_get_next(IF_MTD); + dinfo = drive_get(IF_MTD, 0, 0); if (dinfo) { qdev_prop_set_drive_err(flash_dev, "drive", blk_by_legacy_dinfo(dinfo), @@ -686,6 +688,15 @@ static void sifive_u_machine_init(MachineState *machine) sd_cs = qdev_get_gpio_in_named(sd_dev, SSI_GPIO_CS, 0); sysbus_connect_irq(SYS_BUS_DEVICE(&s->soc.spi2), 1, sd_cs); + + dinfo = drive_get(IF_SD, 0, 0); + blk = dinfo ? blk_by_legacy_dinfo(dinfo) : NULL; + card_dev = qdev_new(TYPE_SD_CARD); + qdev_prop_set_drive_err(card_dev, "drive", blk, &error_fatal); + qdev_prop_set_bit(card_dev, "spi", true); + qdev_realize_and_unref(card_dev, + qdev_get_child_bus(sd_dev, "sd-bus"), + &error_fatal); } static bool sifive_u_machine_get_start_in_flash(Object *obj, Error **errp) diff --git a/hw/s390x/s390-pci-bus.c b/hw/s390x/s390-pci-bus.c index 1b51a72838..01b58ebc70 100644 --- a/hw/s390x/s390-pci-bus.c +++ b/hw/s390x/s390-pci-bus.c @@ -782,6 +782,7 @@ static void s390_pci_init_default_group(void) resgrp->i = 128; resgrp->maxstbl = 128; resgrp->version = 0; + resgrp->dtsm = ZPCI_DTSM; } static void set_pbdev_info(S390PCIBusDevice *pbdev) diff --git a/hw/s390x/s390-pci-inst.c b/hw/s390x/s390-pci-inst.c index 1c8ad91175..6d400d4147 100644 --- a/hw/s390x/s390-pci-inst.c +++ b/hw/s390x/s390-pci-inst.c @@ -329,6 +329,7 @@ int clp_service_call(S390CPU *cpu, uint8_t r2, uintptr_t ra) stw_p(&resgrp->i, group->zpci_group.i); stw_p(&resgrp->maxstbl, group->zpci_group.maxstbl); resgrp->version = group->zpci_group.version; + resgrp->dtsm = group->zpci_group.dtsm; stw_p(&resgrp->hdr.rsp, CLP_RC_OK); break; } @@ -916,9 +917,10 @@ int pci_dereg_irqs(S390PCIBusDevice *pbdev) return 0; } -static int reg_ioat(CPUS390XState *env, S390PCIIOMMU *iommu, ZpciFib fib, +static int reg_ioat(CPUS390XState *env, S390PCIBusDevice *pbdev, ZpciFib fib, uintptr_t ra) { + S390PCIIOMMU *iommu = pbdev->iommu; uint64_t pba = ldq_p(&fib.pba); uint64_t pal = ldq_p(&fib.pal); uint64_t g_iota = ldq_p(&fib.iota); @@ -927,7 +929,7 @@ static int reg_ioat(CPUS390XState *env, S390PCIIOMMU *iommu, ZpciFib fib, pba &= ~0xfff; pal |= 0xfff; - if (pba > pal || pba < ZPCI_SDMA_ADDR || pal > ZPCI_EDMA_ADDR) { + if (pba > pal || pba < pbdev->zpci_fn.sdma || pal > pbdev->zpci_fn.edma) { s390_program_interrupt(env, PGM_OPERAND, ra); return -EINVAL; } @@ -1045,7 +1047,7 @@ static void fmb_update(void *opaque) sizeof(pbdev->fmb.last_update))) { return; } - timer_mod(pbdev->fmb_timer, t + DEFAULT_MUI); + timer_mod(pbdev->fmb_timer, t + pbdev->pci_group->zpci_group.mui); } int mpcifc_service_call(S390CPU *cpu, uint8_t r1, uint64_t fiba, uint8_t ar, @@ -1125,7 +1127,7 @@ int mpcifc_service_call(S390CPU *cpu, uint8_t r1, uint64_t fiba, uint8_t ar, } else if (pbdev->iommu->enabled) { cc = ZPCI_PCI_LS_ERR; s390_set_status_code(env, r1, ZPCI_MOD_ST_SEQUENCE); - } else if (reg_ioat(env, pbdev->iommu, fib, ra)) { + } else if (reg_ioat(env, pbdev, fib, ra)) { cc = ZPCI_PCI_LS_ERR; s390_set_status_code(env, r1, ZPCI_MOD_ST_INSUF_RES); } @@ -1150,7 +1152,7 @@ int mpcifc_service_call(S390CPU *cpu, uint8_t r1, uint64_t fiba, uint8_t ar, s390_set_status_code(env, r1, ZPCI_MOD_ST_SEQUENCE); } else { pci_dereg_ioat(pbdev->iommu); - if (reg_ioat(env, pbdev->iommu, fib, ra)) { + if (reg_ioat(env, pbdev, fib, ra)) { cc = ZPCI_PCI_LS_ERR; s390_set_status_code(env, r1, ZPCI_MOD_ST_INSUF_RES); } @@ -1203,7 +1205,8 @@ int mpcifc_service_call(S390CPU *cpu, uint8_t r1, uint64_t fiba, uint8_t ar, } pbdev->fmb_addr = fmb_addr; timer_mod(pbdev->fmb_timer, - qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) + DEFAULT_MUI); + qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) + + pbdev->pci_group->zpci_group.mui); break; } default: diff --git a/hw/s390x/s390-pci-vfio.c b/hw/s390x/s390-pci-vfio.c index 2a153fa8c9..6f80a47e29 100644 --- a/hw/s390x/s390-pci-vfio.c +++ b/hw/s390x/s390-pci-vfio.c @@ -160,6 +160,7 @@ static void s390_pci_read_group(S390PCIBusDevice *pbdev, resgrp->i = cap->noi; resgrp->maxstbl = cap->maxstbl; resgrp->version = cap->version; + resgrp->dtsm = ZPCI_DTSM; } } diff --git a/hw/scsi/lsi53c895a.c b/hw/scsi/lsi53c895a.c index 85e907a785..4c431adb77 100644 --- a/hw/scsi/lsi53c895a.c +++ b/hw/scsi/lsi53c895a.c @@ -621,8 +621,7 @@ static void lsi_do_dma(LSIState *s, int out) dma_addr_t addr; SCSIDevice *dev; - assert(s->current); - if (!s->current->dma_len) { + if (!s->current || !s->current->dma_len) { /* Wait until data is available. */ trace_lsi_do_dma_unavailable(); return; diff --git a/hw/sd/ssi-sd.c b/hw/sd/ssi-sd.c index e60854eeef..167c03b780 100644 --- a/hw/sd/ssi-sd.c +++ b/hw/sd/ssi-sd.c @@ -368,36 +368,9 @@ static const VMStateDescription vmstate_ssi_sd = { static void ssi_sd_realize(SSIPeripheral *d, Error **errp) { - ERRP_GUARD(); ssi_sd_state *s = SSI_SD(d); - DeviceState *carddev; - DriveInfo *dinfo; qbus_init(&s->sdbus, sizeof(s->sdbus), TYPE_SD_BUS, DEVICE(d), "sd-bus"); - - /* Create and plug in the sd card */ - /* FIXME use a qdev drive property instead of drive_get_next() */ - dinfo = drive_get_next(IF_SD); - carddev = qdev_new(TYPE_SD_CARD); - if (dinfo) { - if (!qdev_prop_set_drive_err(carddev, "drive", - blk_by_legacy_dinfo(dinfo), errp)) { - goto fail; - } - } - - if (!object_property_set_bool(OBJECT(carddev), "spi", true, errp)) { - goto fail; - } - - if (!qdev_realize_and_unref(carddev, BUS(&s->sdbus), errp)) { - goto fail; - } - - return; - -fail: - error_prepend(errp, "failed to init SD card: "); } static void ssi_sd_reset(DeviceState *dev) @@ -426,7 +399,7 @@ static void ssi_sd_class_init(ObjectClass *klass, void *data) k->cs_polarity = SSI_CS_LOW; dc->vmsd = &vmstate_ssi_sd; dc->reset = ssi_sd_reset; - /* Reason: init() method uses drive_get_next() */ + /* Reason: GPIO chip-select line should be wired up */ dc->user_creatable = false; } diff --git a/hw/sparc64/niagara.c b/hw/sparc64/niagara.c index f3e42d0326..ccad2c43a3 100644 --- a/hw/sparc64/niagara.c +++ b/hw/sparc64/niagara.c @@ -98,7 +98,7 @@ static void add_rom_or_fail(const char *file, const hwaddr addr) static void niagara_init(MachineState *machine) { NiagaraBoardState *s = g_new(NiagaraBoardState, 1); - DriveInfo *dinfo = drive_get_next(IF_PFLASH); + DriveInfo *dinfo = drive_get(IF_PFLASH, 0, 0); MemoryRegion *sysmem = get_system_memory(); /* init CPUs */ diff --git a/hw/virtio/trace-events b/hw/virtio/trace-events index 650e521e35..f7ad6be5fb 100644 --- a/hw/virtio/trace-events +++ b/hw/virtio/trace-events @@ -91,8 +91,7 @@ virtio_mmio_setting_irq(int level) "virtio_mmio setting IRQ %d" virtio_iommu_device_reset(void) "reset!" virtio_iommu_get_features(uint64_t features) "device supports features=0x%"PRIx64 virtio_iommu_device_status(uint8_t status) "driver status = %d" -virtio_iommu_get_config(uint64_t page_size_mask, uint64_t start, uint64_t end, uint32_t domain_range, uint32_t probe_size) "page_size_mask=0x%"PRIx64" start=0x%"PRIx64" end=0x%"PRIx64" domain_range=%d probe_size=0x%x" -virtio_iommu_set_config(uint64_t page_size_mask, uint64_t start, uint64_t end, uint32_t domain_range, uint32_t probe_size) "page_size_mask=0x%"PRIx64" start=0x%"PRIx64" end=0x%"PRIx64" domain_bits=%d probe_size=0x%x" +virtio_iommu_get_config(uint64_t page_size_mask, uint64_t start, uint64_t end, uint32_t domain_start, uint32_t domain_end, uint32_t probe_size) "page_size_mask=0x%"PRIx64" input range start=0x%"PRIx64" input range end=0x%"PRIx64" domain range start=%d domain range end=%d probe_size=0x%x" virtio_iommu_attach(uint32_t domain_id, uint32_t ep_id) "domain=%d endpoint=%d" virtio_iommu_detach(uint32_t domain_id, uint32_t ep_id) "domain=%d endpoint=%d" virtio_iommu_map(uint32_t domain_id, uint64_t virt_start, uint64_t virt_end, uint64_t phys_start, uint32_t flags) "domain=%d virt_start=0x%"PRIx64" virt_end=0x%"PRIx64 " phys_start=0x%"PRIx64" flags=%d" diff --git a/hw/virtio/virtio-iommu-pci.c b/hw/virtio/virtio-iommu-pci.c index a160ae6b41..6a1df7fe50 100644 --- a/hw/virtio/virtio-iommu-pci.c +++ b/hw/virtio/virtio-iommu-pci.c @@ -48,16 +48,8 @@ static void virtio_iommu_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) VirtIOIOMMU *s = VIRTIO_IOMMU(vdev); if (!qdev_get_machine_hotplug_handler(DEVICE(vpci_dev))) { - MachineClass *mc = MACHINE_GET_CLASS(qdev_get_machine()); - - error_setg(errp, - "%s machine fails to create iommu-map device tree bindings", - mc->name); - error_append_hint(errp, - "Check your machine implements a hotplug handler " - "for the virtio-iommu-pci device\n"); - error_append_hint(errp, "Check the guest is booted without FW or with " - "-no-acpi\n"); + error_setg(errp, "Check your machine implements a hotplug handler " + "for the virtio-iommu-pci device"); return; } for (int i = 0; i < s->nb_reserved_regions; i++) { diff --git a/hw/virtio/virtio-iommu.c b/hw/virtio/virtio-iommu.c index 1b23e8e18c..aa9c16a17b 100644 --- a/hw/virtio/virtio-iommu.c +++ b/hw/virtio/virtio-iommu.c @@ -822,27 +822,22 @@ unlock: static void virtio_iommu_get_config(VirtIODevice *vdev, uint8_t *config_data) { VirtIOIOMMU *dev = VIRTIO_IOMMU(vdev); - struct virtio_iommu_config *config = &dev->config; - - trace_virtio_iommu_get_config(config->page_size_mask, - config->input_range.start, - config->input_range.end, - config->domain_range.end, - config->probe_size); - memcpy(config_data, &dev->config, sizeof(struct virtio_iommu_config)); -} - -static void virtio_iommu_set_config(VirtIODevice *vdev, - const uint8_t *config_data) -{ - struct virtio_iommu_config config; - - memcpy(&config, config_data, sizeof(struct virtio_iommu_config)); - trace_virtio_iommu_set_config(config.page_size_mask, - config.input_range.start, - config.input_range.end, - config.domain_range.end, - config.probe_size); + struct virtio_iommu_config *dev_config = &dev->config; + struct virtio_iommu_config *out_config = (void *)config_data; + + out_config->page_size_mask = cpu_to_le64(dev_config->page_size_mask); + out_config->input_range.start = cpu_to_le64(dev_config->input_range.start); + out_config->input_range.end = cpu_to_le64(dev_config->input_range.end); + out_config->domain_range.start = cpu_to_le32(dev_config->domain_range.start); + out_config->domain_range.end = cpu_to_le32(dev_config->domain_range.end); + out_config->probe_size = cpu_to_le32(dev_config->probe_size); + + trace_virtio_iommu_get_config(dev_config->page_size_mask, + dev_config->input_range.start, + dev_config->input_range.end, + dev_config->domain_range.start, + dev_config->domain_range.end, + dev_config->probe_size); } static uint64_t virtio_iommu_get_features(VirtIODevice *vdev, uint64_t f, @@ -983,8 +978,8 @@ static void virtio_iommu_device_realize(DeviceState *dev, Error **errp) s->event_vq = virtio_add_queue(vdev, VIOMMU_DEFAULT_QUEUE_SIZE, NULL); s->config.page_size_mask = TARGET_PAGE_MASK; - s->config.input_range.end = -1UL; - s->config.domain_range.end = 32; + s->config.input_range.end = UINT64_MAX; + s->config.domain_range.end = UINT32_MAX; s->config.probe_size = VIOMMU_PROBE_SIZE; virtio_add_feature(&s->features, VIRTIO_RING_F_EVENT_IDX); @@ -1185,7 +1180,6 @@ static void virtio_iommu_class_init(ObjectClass *klass, void *data) vdc->unrealize = virtio_iommu_device_unrealize; vdc->reset = virtio_iommu_device_reset; vdc->get_config = virtio_iommu_get_config; - vdc->set_config = virtio_iommu_set_config; vdc->get_features = virtio_iommu_get_features; vdc->set_status = virtio_iommu_set_status; vdc->vmsd = &vmstate_virtio_iommu_device; diff --git a/include/hw/i386/microvm.h b/include/hw/i386/microvm.h index 4d9c732d4b..efcbd926fd 100644 --- a/include/hw/i386/microvm.h +++ b/include/hw/i386/microvm.h @@ -18,7 +18,6 @@ #ifndef HW_I386_MICROVM_H #define HW_I386_MICROVM_H -#include "qemu-common.h" #include "exec/hwaddr.h" #include "qemu/notify.h" diff --git a/include/hw/i386/sgx-epc.h b/include/hw/i386/sgx-epc.h index a6a65be854..581fac389a 100644 --- a/include/hw/i386/sgx-epc.h +++ b/include/hw/i386/sgx-epc.h @@ -25,6 +25,7 @@ #define SGX_EPC_ADDR_PROP "addr" #define SGX_EPC_SIZE_PROP "size" #define SGX_EPC_MEMDEV_PROP "memdev" +#define SGX_EPC_NUMA_NODE_PROP "node" /** * SGXEPCDevice: @@ -38,6 +39,7 @@ typedef struct SGXEPCDevice { /* public */ uint64_t addr; + uint32_t node; HostMemoryBackendEpc *hostmem; } SGXEPCDevice; @@ -56,6 +58,7 @@ typedef struct SGXEPCState { } SGXEPCState; bool sgx_epc_get_section(int section_nr, uint64_t *addr, uint64_t *size); +void sgx_epc_build_srat(GArray *table_data); static inline uint64_t sgx_epc_above_4g_end(SGXEPCState *sgx_epc) { diff --git a/include/hw/i386/x86.h b/include/hw/i386/x86.h index bb1cfb8896..a145a30370 100644 --- a/include/hw/i386/x86.h +++ b/include/hw/i386/x86.h @@ -17,7 +17,6 @@ #ifndef HW_I386_X86_H #define HW_I386_X86_H -#include "qemu-common.h" #include "exec/hwaddr.h" #include "qemu/notify.h" diff --git a/include/hw/pci/pci_bridge.h b/include/hw/pci/pci_bridge.h index a94d350034..30691a6e57 100644 --- a/include/hw/pci/pci_bridge.h +++ b/include/hw/pci/pci_bridge.h @@ -138,6 +138,7 @@ typedef struct PCIBridgeQemuCap { uint64_t mem_pref_64; /* Prefetchable memory to reserve (64-bit MMIO) */ } PCIBridgeQemuCap; +#define REDHAT_PCI_CAP_TYPE_OFFSET 3 #define REDHAT_PCI_CAP_RESOURCE_RESERVE 1 /* @@ -152,6 +153,13 @@ typedef struct PCIResReserve { uint64_t mem_pref_64; } PCIResReserve; +#define REDHAT_PCI_CAP_RES_RESERVE_BUS_RES 4 +#define REDHAT_PCI_CAP_RES_RESERVE_IO 8 +#define REDHAT_PCI_CAP_RES_RESERVE_MEM 16 +#define REDHAT_PCI_CAP_RES_RESERVE_PREF_MEM_32 20 +#define REDHAT_PCI_CAP_RES_RESERVE_PREF_MEM_64 24 +#define REDHAT_PCI_CAP_RES_RESERVE_CAP_SIZE 32 + int pci_bridge_qemu_reserve_cap_init(PCIDevice *dev, int cap_offset, PCIResReserve res_reserve, Error **errp); diff --git a/include/hw/s390x/s390-pci-bus.h b/include/hw/s390x/s390-pci-bus.h index aa891c178d..da3cde2bb4 100644 --- a/include/hw/s390x/s390-pci-bus.h +++ b/include/hw/s390x/s390-pci-bus.h @@ -37,6 +37,7 @@ #define ZPCI_MAX_UID 0xffff #define UID_UNDEFINED 0 #define UID_CHECKING_ENABLED 0x01 +#define ZPCI_DTSM 0x40 OBJECT_DECLARE_SIMPLE_TYPE(S390pciState, S390_PCI_HOST_BRIDGE) OBJECT_DECLARE_SIMPLE_TYPE(S390PCIBus, S390_PCI_BUS) @@ -313,7 +314,7 @@ typedef struct ZpciFmb { } ZpciFmb; QEMU_BUILD_BUG_MSG(offsetof(ZpciFmb, fmt0) != 48, "padding in ZpciFmb"); -#define ZPCI_DEFAULT_FN_GRP 0x20 +#define ZPCI_DEFAULT_FN_GRP 0xFF typedef struct S390PCIGroup { ClpRspQueryPciGrp zpci_group; int id; diff --git a/include/hw/s390x/s390-pci-clp.h b/include/hw/s390x/s390-pci-clp.h index 96b8e3f133..cc8c8662b8 100644 --- a/include/hw/s390x/s390-pci-clp.h +++ b/include/hw/s390x/s390-pci-clp.h @@ -163,7 +163,8 @@ typedef struct ClpRspQueryPciGrp { uint8_t fr; uint16_t maxstbl; uint16_t mui; - uint64_t reserved3; + uint8_t dtsm; + uint8_t reserved3[7]; uint64_t dasm; /* dma address space mask */ uint64_t msia; /* MSI address */ uint64_t reserved4; diff --git a/include/hw/virtio/virtio-gpu-bswap.h b/include/hw/virtio/virtio-gpu-bswap.h index e2bee8f595..5faac0d8d5 100644 --- a/include/hw/virtio/virtio-gpu-bswap.h +++ b/include/hw/virtio/virtio-gpu-bswap.h @@ -24,7 +24,6 @@ virtio_gpu_ctrl_hdr_bswap(struct virtio_gpu_ctrl_hdr *hdr) le32_to_cpus(&hdr->flags); le64_to_cpus(&hdr->fence_id); le32_to_cpus(&hdr->ctx_id); - le32_to_cpus(&hdr->padding); } static inline void diff --git a/include/migration/colo.h b/include/migration/colo.h index 768e1f04c3..5fbe1a6d5d 100644 --- a/include/migration/colo.h +++ b/include/migration/colo.h @@ -37,4 +37,5 @@ COLOMode get_colo_mode(void); void colo_do_failover(void); void colo_checkpoint_notify(void *opaque); +void colo_shutdown(void); #endif diff --git a/include/standard-headers/drm/drm_fourcc.h b/include/standard-headers/drm/drm_fourcc.h index 352b51fd0a..2c025cb4fe 100644 --- a/include/standard-headers/drm/drm_fourcc.h +++ b/include/standard-headers/drm/drm_fourcc.h @@ -103,6 +103,12 @@ extern "C" { /* 8 bpp Red */ #define DRM_FORMAT_R8 fourcc_code('R', '8', ' ', ' ') /* [7:0] R */ +/* 10 bpp Red */ +#define DRM_FORMAT_R10 fourcc_code('R', '1', '0', ' ') /* [15:0] x:R 6:10 little endian */ + +/* 12 bpp Red */ +#define DRM_FORMAT_R12 fourcc_code('R', '1', '2', ' ') /* [15:0] x:R 4:12 little endian */ + /* 16 bpp Red */ #define DRM_FORMAT_R16 fourcc_code('R', '1', '6', ' ') /* [15:0] R little endian */ @@ -372,6 +378,12 @@ extern "C" { #define DRM_FORMAT_RESERVED ((1ULL << 56) - 1) +#define fourcc_mod_get_vendor(modifier) \ + (((modifier) >> 56) & 0xff) + +#define fourcc_mod_is_vendor(modifier, vendor) \ + (fourcc_mod_get_vendor(modifier) == DRM_FORMAT_MOD_VENDOR_## vendor) + #define fourcc_mod_code(vendor, val) \ ((((uint64_t)DRM_FORMAT_MOD_VENDOR_## vendor) << 56) | ((val) & 0x00ffffffffffffffULL)) @@ -899,9 +911,9 @@ drm_fourcc_canonicalize_nvidia_format_mod(uint64_t modifier) /* * The top 4 bits (out of the 56 bits alloted for specifying vendor specific - * modifiers) denote the category for modifiers. Currently we have only two - * categories of modifiers ie AFBC and MISC. We can have a maximum of sixteen - * different categories. + * modifiers) denote the category for modifiers. Currently we have three + * categories of modifiers ie AFBC, MISC and AFRC. We can have a maximum of + * sixteen different categories. */ #define DRM_FORMAT_MOD_ARM_CODE(__type, __val) \ fourcc_mod_code(ARM, ((uint64_t)(__type) << 52) | ((__val) & 0x000fffffffffffffULL)) @@ -1017,6 +1029,109 @@ drm_fourcc_canonicalize_nvidia_format_mod(uint64_t modifier) #define AFBC_FORMAT_MOD_USM (1ULL << 12) /* + * Arm Fixed-Rate Compression (AFRC) modifiers + * + * AFRC is a proprietary fixed rate image compression protocol and format, + * designed to provide guaranteed bandwidth and memory footprint + * reductions in graphics and media use-cases. + * + * AFRC buffers consist of one or more planes, with the same components + * and meaning as an uncompressed buffer using the same pixel format. + * + * Within each plane, the pixel/luma/chroma values are grouped into + * "coding unit" blocks which are individually compressed to a + * fixed size (in bytes). All coding units within a given plane of a buffer + * store the same number of values, and have the same compressed size. + * + * The coding unit size is configurable, allowing different rates of compression. + * + * The start of each AFRC buffer plane must be aligned to an alignment granule which + * depends on the coding unit size. + * + * Coding Unit Size Plane Alignment + * ---------------- --------------- + * 16 bytes 1024 bytes + * 24 bytes 512 bytes + * 32 bytes 2048 bytes + * + * Coding units are grouped into paging tiles. AFRC buffer dimensions must be aligned + * to a multiple of the paging tile dimensions. + * The dimensions of each paging tile depend on whether the buffer is optimised for + * scanline (SCAN layout) or rotated (ROT layout) access. + * + * Layout Paging Tile Width Paging Tile Height + * ------ ----------------- ------------------ + * SCAN 16 coding units 4 coding units + * ROT 8 coding units 8 coding units + * + * The dimensions of each coding unit depend on the number of components + * in the compressed plane and whether the buffer is optimised for + * scanline (SCAN layout) or rotated (ROT layout) access. + * + * Number of Components in Plane Layout Coding Unit Width Coding Unit Height + * ----------------------------- --------- ----------------- ------------------ + * 1 SCAN 16 samples 4 samples + * Example: 16x4 luma samples in a 'Y' plane + * 16x4 chroma 'V' values, in the 'V' plane of a fully-planar YUV buffer + * ----------------------------- --------- ----------------- ------------------ + * 1 ROT 8 samples 8 samples + * Example: 8x8 luma samples in a 'Y' plane + * 8x8 chroma 'V' values, in the 'V' plane of a fully-planar YUV buffer + * ----------------------------- --------- ----------------- ------------------ + * 2 DONT CARE 8 samples 4 samples + * Example: 8x4 chroma pairs in the 'UV' plane of a semi-planar YUV buffer + * ----------------------------- --------- ----------------- ------------------ + * 3 DONT CARE 4 samples 4 samples + * Example: 4x4 pixels in an RGB buffer without alpha + * ----------------------------- --------- ----------------- ------------------ + * 4 DONT CARE 4 samples 4 samples + * Example: 4x4 pixels in an RGB buffer with alpha + */ + +#define DRM_FORMAT_MOD_ARM_TYPE_AFRC 0x02 + +#define DRM_FORMAT_MOD_ARM_AFRC(__afrc_mode) \ + DRM_FORMAT_MOD_ARM_CODE(DRM_FORMAT_MOD_ARM_TYPE_AFRC, __afrc_mode) + +/* + * AFRC coding unit size modifier. + * + * Indicates the number of bytes used to store each compressed coding unit for + * one or more planes in an AFRC encoded buffer. The coding unit size for chrominance + * is the same for both Cb and Cr, which may be stored in separate planes. + * + * AFRC_FORMAT_MOD_CU_SIZE_P0 indicates the number of bytes used to store + * each compressed coding unit in the first plane of the buffer. For RGBA buffers + * this is the only plane, while for semi-planar and fully-planar YUV buffers, + * this corresponds to the luma plane. + * + * AFRC_FORMAT_MOD_CU_SIZE_P12 indicates the number of bytes used to store + * each compressed coding unit in the second and third planes in the buffer. + * For semi-planar and fully-planar YUV buffers, this corresponds to the chroma plane(s). + * + * For single-plane buffers, AFRC_FORMAT_MOD_CU_SIZE_P0 must be specified + * and AFRC_FORMAT_MOD_CU_SIZE_P12 must be zero. + * For semi-planar and fully-planar buffers, both AFRC_FORMAT_MOD_CU_SIZE_P0 and + * AFRC_FORMAT_MOD_CU_SIZE_P12 must be specified. + */ +#define AFRC_FORMAT_MOD_CU_SIZE_MASK 0xf +#define AFRC_FORMAT_MOD_CU_SIZE_16 (1ULL) +#define AFRC_FORMAT_MOD_CU_SIZE_24 (2ULL) +#define AFRC_FORMAT_MOD_CU_SIZE_32 (3ULL) + +#define AFRC_FORMAT_MOD_CU_SIZE_P0(__afrc_cu_size) (__afrc_cu_size) +#define AFRC_FORMAT_MOD_CU_SIZE_P12(__afrc_cu_size) ((__afrc_cu_size) << 4) + +/* + * AFRC scanline memory layout. + * + * Indicates if the buffer uses the scanline-optimised layout + * for an AFRC encoded buffer, otherwise, it uses the rotation-optimised layout. + * The memory layout is the same for all planes. + */ +#define AFRC_FORMAT_MOD_LAYOUT_SCAN (1ULL << 8) + +/* * Arm 16x16 Block U-Interleaved modifier * * This is used by Arm Mali Utgard and Midgard GPUs. It divides the image diff --git a/include/standard-headers/linux/ethtool.h b/include/standard-headers/linux/ethtool.h index 053d3fafdf..688eb8dc39 100644 --- a/include/standard-headers/linux/ethtool.h +++ b/include/standard-headers/linux/ethtool.h @@ -603,6 +603,7 @@ enum ethtool_link_ext_state { ETHTOOL_LINK_EXT_STATE_CALIBRATION_FAILURE, ETHTOOL_LINK_EXT_STATE_POWER_BUDGET_EXCEEDED, ETHTOOL_LINK_EXT_STATE_OVERHEAT, + ETHTOOL_LINK_EXT_STATE_MODULE, }; /* More information in addition to ETHTOOL_LINK_EXT_STATE_AUTONEG. */ @@ -639,6 +640,8 @@ enum ethtool_link_ext_substate_link_logical_mismatch { enum ethtool_link_ext_substate_bad_signal_integrity { ETHTOOL_LINK_EXT_SUBSTATE_BSI_LARGE_NUMBER_OF_PHYSICAL_ERRORS = 1, ETHTOOL_LINK_EXT_SUBSTATE_BSI_UNSUPPORTED_RATE, + ETHTOOL_LINK_EXT_SUBSTATE_BSI_SERDES_REFERENCE_CLOCK_LOST, + ETHTOOL_LINK_EXT_SUBSTATE_BSI_SERDES_ALOS, }; /* More information in addition to ETHTOOL_LINK_EXT_STATE_CABLE_ISSUE. */ @@ -647,6 +650,11 @@ enum ethtool_link_ext_substate_cable_issue { ETHTOOL_LINK_EXT_SUBSTATE_CI_CABLE_TEST_FAILURE, }; +/* More information in addition to ETHTOOL_LINK_EXT_STATE_MODULE. */ +enum ethtool_link_ext_substate_module { + ETHTOOL_LINK_EXT_SUBSTATE_MODULE_CMIS_NOT_READY = 1, +}; + #define ETH_GSTRING_LEN 32 /** @@ -705,6 +713,29 @@ enum ethtool_stringset { }; /** + * enum ethtool_module_power_mode_policy - plug-in module power mode policy + * @ETHTOOL_MODULE_POWER_MODE_POLICY_HIGH: Module is always in high power mode. + * @ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO: Module is transitioned by the host + * to high power mode when the first port using it is put administratively + * up and to low power mode when the last port using it is put + * administratively down. + */ +enum ethtool_module_power_mode_policy { + ETHTOOL_MODULE_POWER_MODE_POLICY_HIGH = 1, + ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO, +}; + +/** + * enum ethtool_module_power_mode - plug-in module power mode + * @ETHTOOL_MODULE_POWER_MODE_LOW: Module is in low power mode. + * @ETHTOOL_MODULE_POWER_MODE_HIGH: Module is in high power mode. + */ +enum ethtool_module_power_mode { + ETHTOOL_MODULE_POWER_MODE_LOW = 1, + ETHTOOL_MODULE_POWER_MODE_HIGH, +}; + +/** * struct ethtool_gstrings - string set for data tagging * @cmd: Command number = %ETHTOOL_GSTRINGS * @string_set: String set ID; one of &enum ethtool_stringset diff --git a/include/standard-headers/linux/fuse.h b/include/standard-headers/linux/fuse.h index cce105bfba..23ea31708b 100644 --- a/include/standard-headers/linux/fuse.h +++ b/include/standard-headers/linux/fuse.h @@ -181,6 +181,9 @@ * - add FUSE_OPEN_KILL_SUIDGID * - extend fuse_setxattr_in, add FUSE_SETXATTR_EXT * - add FUSE_SETXATTR_ACL_KILL_SGID + * + * 7.34 + * - add FUSE_SYNCFS */ #ifndef _LINUX_FUSE_H @@ -212,7 +215,7 @@ #define FUSE_KERNEL_VERSION 7 /** Minor version number of this interface */ -#define FUSE_KERNEL_MINOR_VERSION 33 +#define FUSE_KERNEL_MINOR_VERSION 34 /** The node ID of the root inode */ #define FUSE_ROOT_ID 1 @@ -505,6 +508,7 @@ enum fuse_opcode { FUSE_COPY_FILE_RANGE = 47, FUSE_SETUPMAPPING = 48, FUSE_REMOVEMAPPING = 49, + FUSE_SYNCFS = 50, /* CUSE specific operations */ CUSE_INIT = 4096, @@ -967,4 +971,8 @@ struct fuse_removemapping_one { #define FUSE_REMOVEMAPPING_MAX_ENTRY \ (PAGE_SIZE / sizeof(struct fuse_removemapping_one)) +struct fuse_syncfs_in { + uint64_t padding; +}; + #endif /* _LINUX_FUSE_H */ diff --git a/include/standard-headers/linux/pci_regs.h b/include/standard-headers/linux/pci_regs.h index e709ae8235..ff6ccbc6ef 100644 --- a/include/standard-headers/linux/pci_regs.h +++ b/include/standard-headers/linux/pci_regs.h @@ -504,6 +504,12 @@ #define PCI_EXP_DEVCTL_URRE 0x0008 /* Unsupported Request Reporting En. */ #define PCI_EXP_DEVCTL_RELAX_EN 0x0010 /* Enable relaxed ordering */ #define PCI_EXP_DEVCTL_PAYLOAD 0x00e0 /* Max_Payload_Size */ +#define PCI_EXP_DEVCTL_PAYLOAD_128B 0x0000 /* 128 Bytes */ +#define PCI_EXP_DEVCTL_PAYLOAD_256B 0x0020 /* 256 Bytes */ +#define PCI_EXP_DEVCTL_PAYLOAD_512B 0x0040 /* 512 Bytes */ +#define PCI_EXP_DEVCTL_PAYLOAD_1024B 0x0060 /* 1024 Bytes */ +#define PCI_EXP_DEVCTL_PAYLOAD_2048B 0x0080 /* 2048 Bytes */ +#define PCI_EXP_DEVCTL_PAYLOAD_4096B 0x00a0 /* 4096 Bytes */ #define PCI_EXP_DEVCTL_EXT_TAG 0x0100 /* Extended Tag Field Enable */ #define PCI_EXP_DEVCTL_PHANTOM 0x0200 /* Phantom Functions Enable */ #define PCI_EXP_DEVCTL_AUX_PME 0x0400 /* Auxiliary Power PM Enable */ diff --git a/include/standard-headers/linux/virtio_gpu.h b/include/standard-headers/linux/virtio_gpu.h index 1357e4774e..2da48d3d4c 100644 --- a/include/standard-headers/linux/virtio_gpu.h +++ b/include/standard-headers/linux/virtio_gpu.h @@ -59,6 +59,11 @@ * VIRTIO_GPU_CMD_RESOURCE_CREATE_BLOB */ #define VIRTIO_GPU_F_RESOURCE_BLOB 3 +/* + * VIRTIO_GPU_CMD_CREATE_CONTEXT with + * context_init and multiple timelines + */ +#define VIRTIO_GPU_F_CONTEXT_INIT 4 enum virtio_gpu_ctrl_type { VIRTIO_GPU_UNDEFINED = 0, @@ -122,14 +127,20 @@ enum virtio_gpu_shm_id { VIRTIO_GPU_SHM_ID_HOST_VISIBLE = 1 }; -#define VIRTIO_GPU_FLAG_FENCE (1 << 0) +#define VIRTIO_GPU_FLAG_FENCE (1 << 0) +/* + * If the following flag is set, then ring_idx contains the index + * of the command ring that needs to used when creating the fence + */ +#define VIRTIO_GPU_FLAG_INFO_RING_IDX (1 << 1) struct virtio_gpu_ctrl_hdr { uint32_t type; uint32_t flags; uint64_t fence_id; uint32_t ctx_id; - uint32_t padding; + uint8_t ring_idx; + uint8_t padding[3]; }; /* data passed in the cursor vq */ @@ -269,10 +280,11 @@ struct virtio_gpu_resource_create_3d { }; /* VIRTIO_GPU_CMD_CTX_CREATE */ +#define VIRTIO_GPU_CONTEXT_INIT_CAPSET_ID_MASK 0x000000ff struct virtio_gpu_ctx_create { struct virtio_gpu_ctrl_hdr hdr; uint32_t nlen; - uint32_t padding; + uint32_t context_init; char debug_name[64]; }; diff --git a/include/standard-headers/linux/virtio_ids.h b/include/standard-headers/linux/virtio_ids.h index 4fe842c3a3..80d76b75bc 100644 --- a/include/standard-headers/linux/virtio_ids.h +++ b/include/standard-headers/linux/virtio_ids.h @@ -54,7 +54,31 @@ #define VIRTIO_ID_SOUND 25 /* virtio sound */ #define VIRTIO_ID_FS 26 /* virtio filesystem */ #define VIRTIO_ID_PMEM 27 /* virtio pmem */ +#define VIRTIO_ID_RPMB 28 /* virtio rpmb */ #define VIRTIO_ID_MAC80211_HWSIM 29 /* virtio mac80211-hwsim */ +#define VIRTIO_ID_VIDEO_ENCODER 30 /* virtio video encoder */ +#define VIRTIO_ID_VIDEO_DECODER 31 /* virtio video decoder */ +#define VIRTIO_ID_SCMI 32 /* virtio SCMI */ +#define VIRTIO_ID_NITRO_SEC_MOD 33 /* virtio nitro secure module*/ +#define VIRTIO_ID_I2C_ADAPTER 34 /* virtio i2c adapter */ +#define VIRTIO_ID_WATCHDOG 35 /* virtio watchdog */ +#define VIRTIO_ID_CAN 36 /* virtio can */ +#define VIRTIO_ID_DMABUF 37 /* virtio dmabuf */ +#define VIRTIO_ID_PARAM_SERV 38 /* virtio parameter server */ +#define VIRTIO_ID_AUDIO_POLICY 39 /* virtio audio policy */ #define VIRTIO_ID_BT 40 /* virtio bluetooth */ +#define VIRTIO_ID_GPIO 41 /* virtio gpio */ + +/* + * Virtio Transitional IDs + */ + +#define VIRTIO_TRANS_ID_NET 1000 /* transitional virtio net */ +#define VIRTIO_TRANS_ID_BLOCK 1001 /* transitional virtio block */ +#define VIRTIO_TRANS_ID_BALLOON 1002 /* transitional virtio balloon */ +#define VIRTIO_TRANS_ID_CONSOLE 1003 /* transitional virtio console */ +#define VIRTIO_TRANS_ID_SCSI 1004 /* transitional virtio SCSI */ +#define VIRTIO_TRANS_ID_RNG 1005 /* transitional virtio rng */ +#define VIRTIO_TRANS_ID_9P 1009 /* transitional virtio 9p console */ #endif /* _LINUX_VIRTIO_IDS_H */ diff --git a/include/standard-headers/linux/virtio_vsock.h b/include/standard-headers/linux/virtio_vsock.h index 3a23488e42..467e751b17 100644 --- a/include/standard-headers/linux/virtio_vsock.h +++ b/include/standard-headers/linux/virtio_vsock.h @@ -97,7 +97,8 @@ enum virtio_vsock_shutdown { /* VIRTIO_VSOCK_OP_RW flags values */ enum virtio_vsock_rw { - VIRTIO_VSOCK_SEQ_EOR = 1, + VIRTIO_VSOCK_SEQ_EOM = 1, + VIRTIO_VSOCK_SEQ_EOR = 2, }; #endif /* _LINUX_VIRTIO_VSOCK_H */ diff --git a/include/sysemu/blockdev.h b/include/sysemu/blockdev.h index 32c2d6023c..a750f99b79 100644 --- a/include/sysemu/blockdev.h +++ b/include/sysemu/blockdev.h @@ -50,7 +50,6 @@ void drive_check_orphaned(void); DriveInfo *drive_get_by_index(BlockInterfaceType type, int index); int drive_get_max_bus(BlockInterfaceType type); int drive_get_max_devs(BlockInterfaceType type); -DriveInfo *drive_get_next(BlockInterfaceType type); QemuOpts *drive_def(const char *optstr); QemuOpts *drive_add(BlockInterfaceType type, int index, const char *file, diff --git a/include/sysemu/kvm.h b/include/sysemu/kvm.h index 7b22aeb6ae..6eb39a088b 100644 --- a/include/sysemu/kvm.h +++ b/include/sysemu/kvm.h @@ -46,6 +46,8 @@ extern bool kvm_readonly_mem_allowed; extern bool kvm_direct_msi_allowed; extern bool kvm_ioeventfd_any_length_allowed; extern bool kvm_msi_use_devid; +extern bool kvm_has_guest_debug; +extern int kvm_sstep_flags; #define kvm_enabled() (kvm_allowed) /** @@ -167,6 +169,17 @@ extern bool kvm_msi_use_devid; */ #define kvm_msi_devid_required() (kvm_msi_use_devid) +/* + * Does KVM support guest debugging + */ +#define kvm_supports_guest_debug() (kvm_has_guest_debug) + +/* + * kvm_supported_sstep_flags + * Returns: SSTEP_* flags that KVM supports for guest debug + */ +#define kvm_get_supported_sstep_flags() (kvm_sstep_flags) + #else #define kvm_enabled() (0) @@ -184,6 +197,8 @@ extern bool kvm_msi_use_devid; #define kvm_direct_msi_enabled() (false) #define kvm_ioeventfd_any_length_enabled() (false) #define kvm_msi_devid_required() (false) +#define kvm_supports_guest_debug() (false) +#define kvm_get_supported_sstep_flags() (0) #endif /* CONFIG_KVM_IS_POSSIBLE */ diff --git a/linux-headers/asm-arm64/unistd.h b/linux-headers/asm-arm64/unistd.h index f83a70e07d..ce2ee8f1e3 100644 --- a/linux-headers/asm-arm64/unistd.h +++ b/linux-headers/asm-arm64/unistd.h @@ -20,5 +20,6 @@ #define __ARCH_WANT_SET_GET_RLIMIT #define __ARCH_WANT_TIME32_SYSCALLS #define __ARCH_WANT_SYS_CLONE3 +#define __ARCH_WANT_MEMFD_SECRET #include <asm-generic/unistd.h> diff --git a/linux-headers/asm-generic/unistd.h b/linux-headers/asm-generic/unistd.h index f211961ce1..4557a8b608 100644 --- a/linux-headers/asm-generic/unistd.h +++ b/linux-headers/asm-generic/unistd.h @@ -673,15 +673,15 @@ __SYSCALL(__NR_madvise, sys_madvise) #define __NR_remap_file_pages 234 __SYSCALL(__NR_remap_file_pages, sys_remap_file_pages) #define __NR_mbind 235 -__SC_COMP(__NR_mbind, sys_mbind, compat_sys_mbind) +__SYSCALL(__NR_mbind, sys_mbind) #define __NR_get_mempolicy 236 -__SC_COMP(__NR_get_mempolicy, sys_get_mempolicy, compat_sys_get_mempolicy) +__SYSCALL(__NR_get_mempolicy, sys_get_mempolicy) #define __NR_set_mempolicy 237 -__SC_COMP(__NR_set_mempolicy, sys_set_mempolicy, compat_sys_set_mempolicy) +__SYSCALL(__NR_set_mempolicy, sys_set_mempolicy) #define __NR_migrate_pages 238 -__SC_COMP(__NR_migrate_pages, sys_migrate_pages, compat_sys_migrate_pages) +__SYSCALL(__NR_migrate_pages, sys_migrate_pages) #define __NR_move_pages 239 -__SC_COMP(__NR_move_pages, sys_move_pages, compat_sys_move_pages) +__SYSCALL(__NR_move_pages, sys_move_pages) #endif #define __NR_rt_tgsigqueueinfo 240 @@ -873,8 +873,18 @@ __SYSCALL(__NR_landlock_add_rule, sys_landlock_add_rule) #define __NR_landlock_restrict_self 446 __SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self) +#ifdef __ARCH_WANT_MEMFD_SECRET +#define __NR_memfd_secret 447 +__SYSCALL(__NR_memfd_secret, sys_memfd_secret) +#endif +#define __NR_process_mrelease 448 +__SYSCALL(__NR_process_mrelease, sys_process_mrelease) + +#define __NR_futex_waitv 449 +__SYSCALL(__NR_futex_waitv, sys_futex_waitv) + #undef __NR_syscalls -#define __NR_syscalls 447 +#define __NR_syscalls 450 /* * 32 bit systems traditionally used different diff --git a/linux-headers/asm-mips/unistd_n32.h b/linux-headers/asm-mips/unistd_n32.h index 09cd297698..4b3e7ad1ec 100644 --- a/linux-headers/asm-mips/unistd_n32.h +++ b/linux-headers/asm-mips/unistd_n32.h @@ -376,5 +376,6 @@ #define __NR_landlock_create_ruleset (__NR_Linux + 444) #define __NR_landlock_add_rule (__NR_Linux + 445) #define __NR_landlock_restrict_self (__NR_Linux + 446) +#define __NR_process_mrelease (__NR_Linux + 448) #endif /* _ASM_UNISTD_N32_H */ diff --git a/linux-headers/asm-mips/unistd_n64.h b/linux-headers/asm-mips/unistd_n64.h index 780e0cead6..488d9298d9 100644 --- a/linux-headers/asm-mips/unistd_n64.h +++ b/linux-headers/asm-mips/unistd_n64.h @@ -352,5 +352,6 @@ #define __NR_landlock_create_ruleset (__NR_Linux + 444) #define __NR_landlock_add_rule (__NR_Linux + 445) #define __NR_landlock_restrict_self (__NR_Linux + 446) +#define __NR_process_mrelease (__NR_Linux + 448) #endif /* _ASM_UNISTD_N64_H */ diff --git a/linux-headers/asm-mips/unistd_o32.h b/linux-headers/asm-mips/unistd_o32.h index 06a2b3b55e..f47399870a 100644 --- a/linux-headers/asm-mips/unistd_o32.h +++ b/linux-headers/asm-mips/unistd_o32.h @@ -422,5 +422,6 @@ #define __NR_landlock_create_ruleset (__NR_Linux + 444) #define __NR_landlock_add_rule (__NR_Linux + 445) #define __NR_landlock_restrict_self (__NR_Linux + 446) +#define __NR_process_mrelease (__NR_Linux + 448) #endif /* _ASM_UNISTD_O32_H */ diff --git a/linux-headers/asm-powerpc/unistd_32.h b/linux-headers/asm-powerpc/unistd_32.h index cd5a8a41b2..11d54696dc 100644 --- a/linux-headers/asm-powerpc/unistd_32.h +++ b/linux-headers/asm-powerpc/unistd_32.h @@ -429,6 +429,7 @@ #define __NR_landlock_create_ruleset 444 #define __NR_landlock_add_rule 445 #define __NR_landlock_restrict_self 446 +#define __NR_process_mrelease 448 #endif /* _ASM_UNISTD_32_H */ diff --git a/linux-headers/asm-powerpc/unistd_64.h b/linux-headers/asm-powerpc/unistd_64.h index 8458effa8d..cf740bab13 100644 --- a/linux-headers/asm-powerpc/unistd_64.h +++ b/linux-headers/asm-powerpc/unistd_64.h @@ -401,6 +401,7 @@ #define __NR_landlock_create_ruleset 444 #define __NR_landlock_add_rule 445 #define __NR_landlock_restrict_self 446 +#define __NR_process_mrelease 448 #endif /* _ASM_UNISTD_64_H */ diff --git a/linux-headers/asm-s390/unistd_32.h b/linux-headers/asm-s390/unistd_32.h index 0c3cd299e4..8f97d98128 100644 --- a/linux-headers/asm-s390/unistd_32.h +++ b/linux-headers/asm-s390/unistd_32.h @@ -419,5 +419,6 @@ #define __NR_landlock_create_ruleset 444 #define __NR_landlock_add_rule 445 #define __NR_landlock_restrict_self 446 +#define __NR_process_mrelease 448 #endif /* _ASM_S390_UNISTD_32_H */ diff --git a/linux-headers/asm-s390/unistd_64.h b/linux-headers/asm-s390/unistd_64.h index 8dfc08b5e6..021ffc30e6 100644 --- a/linux-headers/asm-s390/unistd_64.h +++ b/linux-headers/asm-s390/unistd_64.h @@ -367,5 +367,6 @@ #define __NR_landlock_create_ruleset 444 #define __NR_landlock_add_rule 445 #define __NR_landlock_restrict_self 446 +#define __NR_process_mrelease 448 #endif /* _ASM_S390_UNISTD_64_H */ diff --git a/linux-headers/asm-x86/kvm.h b/linux-headers/asm-x86/kvm.h index a6c327f8ad..5a776a08f7 100644 --- a/linux-headers/asm-x86/kvm.h +++ b/linux-headers/asm-x86/kvm.h @@ -295,6 +295,7 @@ struct kvm_debug_exit_arch { #define KVM_GUESTDBG_USE_HW_BP 0x00020000 #define KVM_GUESTDBG_INJECT_DB 0x00040000 #define KVM_GUESTDBG_INJECT_BP 0x00080000 +#define KVM_GUESTDBG_BLOCKIRQ 0x00100000 /* for KVM_SET_GUEST_DEBUG */ struct kvm_guest_debug_arch { @@ -503,4 +504,8 @@ struct kvm_pmu_event_filter { #define KVM_PMU_EVENT_ALLOW 0 #define KVM_PMU_EVENT_DENY 1 +/* for KVM_{GET,SET,HAS}_DEVICE_ATTR */ +#define KVM_VCPU_TSC_CTRL 0 /* control group for the timestamp counter (TSC) */ +#define KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */ + #endif /* _ASM_X86_KVM_H */ diff --git a/linux-headers/asm-x86/unistd_32.h b/linux-headers/asm-x86/unistd_32.h index 66e96c0c68..9c9ffe312b 100644 --- a/linux-headers/asm-x86/unistd_32.h +++ b/linux-headers/asm-x86/unistd_32.h @@ -437,6 +437,9 @@ #define __NR_landlock_create_ruleset 444 #define __NR_landlock_add_rule 445 #define __NR_landlock_restrict_self 446 +#define __NR_memfd_secret 447 +#define __NR_process_mrelease 448 +#define __NR_futex_waitv 449 #endif /* _ASM_UNISTD_32_H */ diff --git a/linux-headers/asm-x86/unistd_64.h b/linux-headers/asm-x86/unistd_64.h index b8ff6f14ee..084f1eef9c 100644 --- a/linux-headers/asm-x86/unistd_64.h +++ b/linux-headers/asm-x86/unistd_64.h @@ -359,6 +359,9 @@ #define __NR_landlock_create_ruleset 444 #define __NR_landlock_add_rule 445 #define __NR_landlock_restrict_self 446 +#define __NR_memfd_secret 447 +#define __NR_process_mrelease 448 +#define __NR_futex_waitv 449 #endif /* _ASM_UNISTD_64_H */ diff --git a/linux-headers/asm-x86/unistd_x32.h b/linux-headers/asm-x86/unistd_x32.h index 06a1097c15..a2441affc2 100644 --- a/linux-headers/asm-x86/unistd_x32.h +++ b/linux-headers/asm-x86/unistd_x32.h @@ -312,6 +312,9 @@ #define __NR_landlock_create_ruleset (__X32_SYSCALL_BIT + 444) #define __NR_landlock_add_rule (__X32_SYSCALL_BIT + 445) #define __NR_landlock_restrict_self (__X32_SYSCALL_BIT + 446) +#define __NR_memfd_secret (__X32_SYSCALL_BIT + 447) +#define __NR_process_mrelease (__X32_SYSCALL_BIT + 448) +#define __NR_futex_waitv (__X32_SYSCALL_BIT + 449) #define __NR_rt_sigaction (__X32_SYSCALL_BIT + 512) #define __NR_rt_sigreturn (__X32_SYSCALL_BIT + 513) #define __NR_ioctl (__X32_SYSCALL_BIT + 514) diff --git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h index bcaf66cc4d..02c5e7b7bb 100644 --- a/linux-headers/linux/kvm.h +++ b/linux-headers/linux/kvm.h @@ -269,6 +269,7 @@ struct kvm_xen_exit { #define KVM_EXIT_AP_RESET_HOLD 32 #define KVM_EXIT_X86_BUS_LOCK 33 #define KVM_EXIT_XEN 34 +#define KVM_EXIT_RISCV_SBI 35 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -397,13 +398,23 @@ struct kvm_run { * "ndata" is correct, that new fields are enumerated in "flags", * and that each flag enumerates fields that are 64-bit aligned * and sized (so that ndata+internal.data[] is valid/accurate). + * + * Space beyond the defined fields may be used to store arbitrary + * debug information relating to the emulation failure. It is + * accounted for in "ndata" but the format is unspecified and is + * not represented in "flags". Any such information is *not* ABI! */ struct { __u32 suberror; __u32 ndata; __u64 flags; - __u8 insn_size; - __u8 insn_bytes[15]; + union { + struct { + __u8 insn_size; + __u8 insn_bytes[15]; + }; + }; + /* Arbitrary debug data may follow. */ } emulation_failure; /* KVM_EXIT_OSI */ struct { @@ -469,6 +480,13 @@ struct kvm_run { } msr; /* KVM_EXIT_XEN */ struct kvm_xen_exit xen; + /* KVM_EXIT_RISCV_SBI */ + struct { + unsigned long extension_id; + unsigned long function_id; + unsigned long args[6]; + unsigned long ret[2]; + } riscv_sbi; /* Fix the size of the union. */ char padding[256]; }; @@ -1223,11 +1241,16 @@ struct kvm_irqfd { /* Do not use 1, KVM_CHECK_EXTENSION returned it before we had flags. */ #define KVM_CLOCK_TSC_STABLE 2 +#define KVM_CLOCK_REALTIME (1 << 2) +#define KVM_CLOCK_HOST_TSC (1 << 3) struct kvm_clock_data { __u64 clock; __u32 flags; - __u32 pad[9]; + __u32 pad0; + __u64 realtime; + __u64 host_tsc; + __u32 pad[4]; }; /* For KVM_CAP_SW_TLB */ @@ -1965,7 +1988,9 @@ struct kvm_stats_header { #define KVM_STATS_TYPE_CUMULATIVE (0x0 << KVM_STATS_TYPE_SHIFT) #define KVM_STATS_TYPE_INSTANT (0x1 << KVM_STATS_TYPE_SHIFT) #define KVM_STATS_TYPE_PEAK (0x2 << KVM_STATS_TYPE_SHIFT) -#define KVM_STATS_TYPE_MAX KVM_STATS_TYPE_PEAK +#define KVM_STATS_TYPE_LINEAR_HIST (0x3 << KVM_STATS_TYPE_SHIFT) +#define KVM_STATS_TYPE_LOG_HIST (0x4 << KVM_STATS_TYPE_SHIFT) +#define KVM_STATS_TYPE_MAX KVM_STATS_TYPE_LOG_HIST #define KVM_STATS_UNIT_SHIFT 4 #define KVM_STATS_UNIT_MASK (0xF << KVM_STATS_UNIT_SHIFT) @@ -1988,8 +2013,9 @@ struct kvm_stats_header { * @size: The number of data items for this stats. * Every data item is of type __u64. * @offset: The offset of the stats to the start of stat structure in - * struture kvm or kvm_vcpu. - * @unused: Unused field for future usage. Always 0 for now. + * structure kvm or kvm_vcpu. + * @bucket_size: A parameter value used for histogram stats. It is only used + * for linear histogram stats, specifying the size of the bucket; * @name: The name string for the stats. Its size is indicated by the * &kvm_stats_header->name_size. */ @@ -1998,7 +2024,7 @@ struct kvm_stats_desc { __s16 exponent; __u16 size; __u32 offset; - __u32 unused; + __u32 bucket_size; char name[]; }; diff --git a/linux-user/aarch64/cpu_loop.c b/linux-user/aarch64/cpu_loop.c index 97e0728b67..f9f3473288 100644 --- a/linux-user/aarch64/cpu_loop.c +++ b/linux-user/aarch64/cpu_loop.c @@ -113,27 +113,35 @@ void cpu_loop(CPUARMState *env) break; case EXCP_PREFETCH_ABORT: case EXCP_DATA_ABORT: - /* We should only arrive here with EC in {DATAABORT, INSNABORT}. */ ec = syn_get_ec(env->exception.syndrome); - assert(ec == EC_DATAABORT || ec == EC_INSNABORT); - - /* Both EC have the same format for FSC, or close enough. */ - fsc = extract32(env->exception.syndrome, 0, 6); - switch (fsc) { - case 0x04 ... 0x07: /* Translation fault, level {0-3} */ - si_signo = TARGET_SIGSEGV; - si_code = TARGET_SEGV_MAPERR; + switch (ec) { + case EC_DATAABORT: + case EC_INSNABORT: + /* Both EC have the same format for FSC, or close enough. */ + fsc = extract32(env->exception.syndrome, 0, 6); + switch (fsc) { + case 0x04 ... 0x07: /* Translation fault, level {0-3} */ + si_signo = TARGET_SIGSEGV; + si_code = TARGET_SEGV_MAPERR; + break; + case 0x09 ... 0x0b: /* Access flag fault, level {1-3} */ + case 0x0d ... 0x0f: /* Permission fault, level {1-3} */ + si_signo = TARGET_SIGSEGV; + si_code = TARGET_SEGV_ACCERR; + break; + case 0x11: /* Synchronous Tag Check Fault */ + si_signo = TARGET_SIGSEGV; + si_code = TARGET_SEGV_MTESERR; + break; + case 0x21: /* Alignment fault */ + si_signo = TARGET_SIGBUS; + si_code = TARGET_BUS_ADRALN; + break; + default: + g_assert_not_reached(); + } break; - case 0x09 ... 0x0b: /* Access flag fault, level {1-3} */ - case 0x0d ... 0x0f: /* Permission fault, level {1-3} */ - si_signo = TARGET_SIGSEGV; - si_code = TARGET_SEGV_ACCERR; - break; - case 0x11: /* Synchronous Tag Check Fault */ - si_signo = TARGET_SIGSEGV; - si_code = TARGET_SEGV_MTESERR; - break; - case 0x21: /* Alignment fault */ + case EC_PCALIGNMENT: si_signo = TARGET_SIGBUS; si_code = TARGET_BUS_ADRALN; break; diff --git a/linux-user/hexagon/cpu_loop.c b/linux-user/hexagon/cpu_loop.c index 6b24cbaba9..e47f8348d5 100644 --- a/linux-user/hexagon/cpu_loop.c +++ b/linux-user/hexagon/cpu_loop.c @@ -19,6 +19,7 @@ */ #include "qemu/osdep.h" +#include "qemu-common.h" #include "qemu.h" #include "user-internals.h" #include "cpu_loop-common.h" diff --git a/meson.build b/meson.build index 96de1a6ef9..ae67ca28ab 100644 --- a/meson.build +++ b/meson.build @@ -874,11 +874,15 @@ if not get_option('glusterfs').auto() or have_block ''', dependencies: glusterfs) endif endif + libssh = not_found -if 'CONFIG_LIBSSH' in config_host - libssh = declare_dependency(compile_args: config_host['LIBSSH_CFLAGS'].split(), - link_args: config_host['LIBSSH_LIBS'].split()) +if not get_option('libssh').auto() or have_block + libssh = dependency('libssh', version: '>=0.8.7', + method: 'pkg-config', + required: get_option('libssh'), + kwargs: static_kwargs) endif + libbzip2 = not_found if not get_option('bzip2').auto() or have_block libbzip2 = cc.find_library('bz2', has_headers: ['bzlib.h'], @@ -1451,6 +1455,7 @@ config_host_data.set('CONFIG_EBPF', libbpf.found()) config_host_data.set('CONFIG_LIBDAXCTL', libdaxctl.found()) config_host_data.set('CONFIG_LIBISCSI', libiscsi.found()) config_host_data.set('CONFIG_LIBNFS', libnfs.found()) +config_host_data.set('CONFIG_LIBSSH', libssh.found()) config_host_data.set('CONFIG_LINUX_AIO', libaio.found()) config_host_data.set('CONFIG_LINUX_IO_URING', linux_io_uring.found()) config_host_data.set('CONFIG_LIBPMEM', libpmem.found()) @@ -3430,7 +3435,7 @@ endif summary_info += {'seccomp support': seccomp} summary_info += {'GlusterFS support': glusterfs} summary_info += {'TPM support': config_host.has_key('CONFIG_TPM')} -summary_info += {'libssh support': config_host.has_key('CONFIG_LIBSSH')} +summary_info += {'libssh support': libssh} summary_info += {'lzo support': lzo} summary_info += {'snappy support': snappy} summary_info += {'bzip2 support': libbzip2} diff --git a/meson_options.txt b/meson_options.txt index e392323732..4114bfcaa4 100644 --- a/meson_options.txt +++ b/meson_options.txt @@ -105,6 +105,8 @@ option('libdaxctl', type : 'feature', value : 'auto', description: 'libdaxctl support') option('libpmem', type : 'feature', value : 'auto', description: 'libpmem support') +option('libssh', type : 'feature', value : 'auto', + description: 'ssh block device support') option('libudev', type : 'feature', value : 'auto', description: 'Use libudev to enumerate host devices') option('libusb', type : 'feature', value : 'auto', diff --git a/migration/colo.c b/migration/colo.c index 2415325262..5f7071b3cd 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -530,7 +530,6 @@ static void colo_process_checkpoint(MigrationState *s) { QIOChannelBuffer *bioc; QEMUFile *fb = NULL; - int64_t current_time = qemu_clock_get_ms(QEMU_CLOCK_HOST); Error *local_err = NULL; int ret; @@ -578,8 +577,8 @@ static void colo_process_checkpoint(MigrationState *s) qemu_mutex_unlock_iothread(); trace_colo_vm_state_change("stop", "run"); - timer_mod(s->colo_delay_timer, - current_time + s->parameters.x_checkpoint_delay); + timer_mod(s->colo_delay_timer, qemu_clock_get_ms(QEMU_CLOCK_HOST) + + s->parameters.x_checkpoint_delay); while (s->state == MIGRATION_STATUS_COLO) { if (failover_get_state() != FAILOVER_STATUS_NONE) { @@ -667,8 +666,6 @@ void migrate_start_colo_process(MigrationState *s) colo_checkpoint_notify, s); qemu_sem_init(&s->colo_exit_sem, 0); - migrate_set_state(&s->state, MIGRATION_STATUS_ACTIVE, - MIGRATION_STATUS_COLO); colo_process_checkpoint(s); qemu_mutex_lock_iothread(); } @@ -683,8 +680,8 @@ static void colo_incoming_process_checkpoint(MigrationIncomingState *mis, qemu_mutex_lock_iothread(); vm_stop_force_state(RUN_STATE_COLO); - trace_colo_vm_state_change("run", "stop"); qemu_mutex_unlock_iothread(); + trace_colo_vm_state_change("run", "stop"); /* FIXME: This is unnecessary for periodic checkpoint mode */ colo_send_message(mis->to_src_file, COLO_MESSAGE_CHECKPOINT_REPLY, @@ -786,8 +783,8 @@ static void colo_incoming_process_checkpoint(MigrationIncomingState *mis, vmstate_loading = false; vm_start(); - trace_colo_vm_state_change("stop", "run"); qemu_mutex_unlock_iothread(); + trace_colo_vm_state_change("stop", "run"); if (failover_get_state() == FAILOVER_STATUS_RELAUNCH) { return; @@ -820,6 +817,26 @@ static void colo_wait_handle_message(MigrationIncomingState *mis, } } +void colo_shutdown(void) +{ + MigrationIncomingState *mis = NULL; + MigrationState *s = NULL; + + switch (get_colo_mode()) { + case COLO_MODE_PRIMARY: + s = migrate_get_current(); + qemu_event_set(&s->colo_checkpoint_event); + qemu_sem_post(&s->colo_exit_sem); + break; + case COLO_MODE_SECONDARY: + mis = migration_incoming_get_current(); + qemu_sem_post(&mis->colo_incoming_sem); + break; + default: + break; + } +} + void *colo_process_incoming_thread(void *opaque) { MigrationIncomingState *mis = opaque; @@ -870,8 +887,8 @@ void *colo_process_incoming_thread(void *opaque) abort(); #endif vm_start(); - trace_colo_vm_state_change("stop", "run"); qemu_mutex_unlock_iothread(); + trace_colo_vm_state_change("stop", "run"); colo_send_message(mis->to_src_file, COLO_MESSAGE_CHECKPOINT_READY, &local_err); diff --git a/migration/migration.c b/migration/migration.c index abaf6f9e3d..3de11ae921 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -226,6 +226,12 @@ void migration_cancel(const Error *error) void migration_shutdown(void) { /* + * When the QEMU main thread exit, the COLO thread + * may wait a semaphore. So, we should wakeup the + * COLO thread before migration shutdown. + */ + colo_shutdown(); + /* * Cancel the current migration - that will (eventually) * stop the migration using this structure */ @@ -990,6 +996,8 @@ static void populate_time_info(MigrationInfo *info, MigrationState *s) static void populate_ram_info(MigrationInfo *info, MigrationState *s) { + size_t page_size = qemu_target_page_size(); + info->has_ram = true; info->ram = g_malloc0(sizeof(*info->ram)); info->ram->transferred = ram_counters.transferred; @@ -998,12 +1006,11 @@ static void populate_ram_info(MigrationInfo *info, MigrationState *s) /* legacy value. It is not used anymore */ info->ram->skipped = 0; info->ram->normal = ram_counters.normal; - info->ram->normal_bytes = ram_counters.normal * - qemu_target_page_size(); + info->ram->normal_bytes = ram_counters.normal * page_size; info->ram->mbps = s->mbps; info->ram->dirty_sync_count = ram_counters.dirty_sync_count; info->ram->postcopy_requests = ram_counters.postcopy_requests; - info->ram->page_size = qemu_target_page_size(); + info->ram->page_size = page_size; info->ram->multifd_bytes = ram_counters.multifd_bytes; info->ram->pages_per_second = s->pages_per_second; @@ -3607,12 +3614,7 @@ static void migration_iteration_finish(MigrationState *s) migration_calculate_complete(s); runstate_set(RUN_STATE_POSTMIGRATE); break; - - case MIGRATION_STATUS_ACTIVE: - /* - * We should really assert here, but since it's during - * migration, let's try to reduce the usage of assertions. - */ + case MIGRATION_STATUS_COLO: if (!migrate_colo_enabled()) { error_report("%s: critical error: calling COLO code without " "COLO enabled", __func__); @@ -3622,6 +3624,12 @@ static void migration_iteration_finish(MigrationState *s) * Fixme: we will run VM in COLO no matter its old running state. * After exited COLO, we will keep running. */ + /* Fallthrough */ + case MIGRATION_STATUS_ACTIVE: + /* + * We should really assert here, but since it's during + * migration, let's try to reduce the usage of assertions. + */ s->vm_was_running = true; /* Fallthrough */ case MIGRATION_STATUS_FAILED: diff --git a/migration/multifd-zlib.c b/migration/multifd-zlib.c index ab4ba75d75..da6201704c 100644 --- a/migration/multifd-zlib.c +++ b/migration/multifd-zlib.c @@ -13,6 +13,7 @@ #include "qemu/osdep.h" #include <zlib.h> #include "qemu/rcu.h" +#include "exec/ramblock.h" #include "exec/target_page.h" #include "qapi/error.h" #include "migration.h" @@ -42,7 +43,6 @@ struct zlib_data { */ static int zlib_send_setup(MultiFDSendParams *p, Error **errp) { - uint32_t page_count = MULTIFD_PACKET_SIZE / qemu_target_page_size(); struct zlib_data *z = g_malloc0(sizeof(struct zlib_data)); z_stream *zs = &z->zs; @@ -54,9 +54,8 @@ static int zlib_send_setup(MultiFDSendParams *p, Error **errp) error_setg(errp, "multifd %d: deflate init failed", p->id); return -1; } - /* We will never have more than page_count pages */ - z->zbuff_len = page_count * qemu_target_page_size(); - z->zbuff_len *= 2; + /* To be safe, we reserve twice the size of the packet */ + z->zbuff_len = MULTIFD_PACKET_SIZE * 2; z->zbuff = g_try_malloc(z->zbuff_len); if (!z->zbuff) { deflateEnd(&z->zs); @@ -74,6 +73,7 @@ static int zlib_send_setup(MultiFDSendParams *p, Error **errp) * Close the channel and return memory. * * @p: Params for the channel that we are using + * @errp: pointer to an error */ static void zlib_send_cleanup(MultiFDSendParams *p, Error **errp) { @@ -95,27 +95,27 @@ static void zlib_send_cleanup(MultiFDSendParams *p, Error **errp) * Returns 0 for success or -1 for error * * @p: Params for the channel that we are using - * @used: number of pages used + * @errp: pointer to an error */ -static int zlib_send_prepare(MultiFDSendParams *p, uint32_t used, Error **errp) +static int zlib_send_prepare(MultiFDSendParams *p, Error **errp) { - struct iovec *iov = p->pages->iov; struct zlib_data *z = p->data; + size_t page_size = qemu_target_page_size(); z_stream *zs = &z->zs; uint32_t out_size = 0; int ret; uint32_t i; - for (i = 0; i < used; i++) { + for (i = 0; i < p->pages->num; i++) { uint32_t available = z->zbuff_len - out_size; int flush = Z_NO_FLUSH; - if (i == used - 1) { + if (i == p->pages->num - 1) { flush = Z_SYNC_FLUSH; } - zs->avail_in = iov[i].iov_len; - zs->next_in = iov[i].iov_base; + zs->avail_in = page_size; + zs->next_in = p->pages->block->host + p->pages->offset[i]; zs->avail_out = available; zs->next_out = z->zbuff + out_size; @@ -180,7 +180,6 @@ static int zlib_send_write(MultiFDSendParams *p, uint32_t used, Error **errp) */ static int zlib_recv_setup(MultiFDRecvParams *p, Error **errp) { - uint32_t page_count = MULTIFD_PACKET_SIZE / qemu_target_page_size(); struct zlib_data *z = g_malloc0(sizeof(struct zlib_data)); z_stream *zs = &z->zs; @@ -194,10 +193,8 @@ static int zlib_recv_setup(MultiFDRecvParams *p, Error **errp) error_setg(errp, "multifd %d: inflate init failed", p->id); return -1; } - /* We will never have more than page_count pages */ - z->zbuff_len = page_count * qemu_target_page_size(); - /* We know compression "could" use more space */ - z->zbuff_len *= 2; + /* To be safe, we reserve twice the size of the packet */ + z->zbuff_len = MULTIFD_PACKET_SIZE * 2; z->zbuff = g_try_malloc(z->zbuff_len); if (!z->zbuff) { inflateEnd(zs); @@ -234,17 +231,17 @@ static void zlib_recv_cleanup(MultiFDRecvParams *p) * Returns 0 for success or -1 for error * * @p: Params for the channel that we are using - * @used: number of pages used * @errp: pointer to an error */ -static int zlib_recv_pages(MultiFDRecvParams *p, uint32_t used, Error **errp) +static int zlib_recv_pages(MultiFDRecvParams *p, Error **errp) { struct zlib_data *z = p->data; + size_t page_size = qemu_target_page_size(); z_stream *zs = &z->zs; uint32_t in_size = p->next_packet_size; /* we measure the change of total_out */ uint32_t out_size = zs->total_out; - uint32_t expected_size = used * qemu_target_page_size(); + uint32_t expected_size = p->pages->num * qemu_target_page_size(); uint32_t flags = p->flags & MULTIFD_FLAG_COMPRESSION_MASK; int ret; int i; @@ -263,17 +260,16 @@ static int zlib_recv_pages(MultiFDRecvParams *p, uint32_t used, Error **errp) zs->avail_in = in_size; zs->next_in = z->zbuff; - for (i = 0; i < used; i++) { - struct iovec *iov = &p->pages->iov[i]; + for (i = 0; i < p->pages->num; i++) { int flush = Z_NO_FLUSH; unsigned long start = zs->total_out; - if (i == used - 1) { + if (i == p->pages->num - 1) { flush = Z_SYNC_FLUSH; } - zs->avail_out = iov->iov_len; - zs->next_out = iov->iov_base; + zs->avail_out = page_size; + zs->next_out = p->pages->block->host + p->pages->offset[i]; /* * Welcome to inflate semantics @@ -286,8 +282,8 @@ static int zlib_recv_pages(MultiFDRecvParams *p, uint32_t used, Error **errp) do { ret = inflate(zs, flush); } while (ret == Z_OK && zs->avail_in - && (zs->total_out - start) < iov->iov_len); - if (ret == Z_OK && (zs->total_out - start) < iov->iov_len) { + && (zs->total_out - start) < page_size); + if (ret == Z_OK && (zs->total_out - start) < page_size) { error_setg(errp, "multifd %d: inflate generated too few output", p->id); return -1; diff --git a/migration/multifd-zstd.c b/migration/multifd-zstd.c index 693bddf8c9..2d5b61106c 100644 --- a/migration/multifd-zstd.c +++ b/migration/multifd-zstd.c @@ -13,6 +13,7 @@ #include "qemu/osdep.h" #include <zstd.h> #include "qemu/rcu.h" +#include "exec/ramblock.h" #include "exec/target_page.h" #include "qapi/error.h" #include "migration.h" @@ -47,7 +48,6 @@ struct zstd_data { */ static int zstd_send_setup(MultiFDSendParams *p, Error **errp) { - uint32_t page_count = MULTIFD_PACKET_SIZE / qemu_target_page_size(); struct zstd_data *z = g_new0(struct zstd_data, 1); int res; @@ -67,9 +67,8 @@ static int zstd_send_setup(MultiFDSendParams *p, Error **errp) p->id, ZSTD_getErrorName(res)); return -1; } - /* We will never have more than page_count pages */ - z->zbuff_len = page_count * qemu_target_page_size(); - z->zbuff_len *= 2; + /* To be safe, we reserve twice the size of the packet */ + z->zbuff_len = MULTIFD_PACKET_SIZE * 2; z->zbuff = g_try_malloc(z->zbuff_len); if (!z->zbuff) { ZSTD_freeCStream(z->zcs); @@ -86,6 +85,7 @@ static int zstd_send_setup(MultiFDSendParams *p, Error **errp) * Close the channel and return memory. * * @p: Params for the channel that we are using + * @errp: pointer to an error */ static void zstd_send_cleanup(MultiFDSendParams *p, Error **errp) { @@ -108,12 +108,12 @@ static void zstd_send_cleanup(MultiFDSendParams *p, Error **errp) * Returns 0 for success or -1 for error * * @p: Params for the channel that we are using - * @used: number of pages used + * @errp: pointer to an error */ -static int zstd_send_prepare(MultiFDSendParams *p, uint32_t used, Error **errp) +static int zstd_send_prepare(MultiFDSendParams *p, Error **errp) { - struct iovec *iov = p->pages->iov; struct zstd_data *z = p->data; + size_t page_size = qemu_target_page_size(); int ret; uint32_t i; @@ -121,14 +121,14 @@ static int zstd_send_prepare(MultiFDSendParams *p, uint32_t used, Error **errp) z->out.size = z->zbuff_len; z->out.pos = 0; - for (i = 0; i < used; i++) { + for (i = 0; i < p->pages->num; i++) { ZSTD_EndDirective flush = ZSTD_e_continue; - if (i == used - 1) { + if (i == p->pages->num - 1) { flush = ZSTD_e_flush; } - z->in.src = iov[i].iov_base; - z->in.size = iov[i].iov_len; + z->in.src = p->pages->block->host + p->pages->offset[i]; + z->in.size = page_size; z->in.pos = 0; /* @@ -191,7 +191,6 @@ static int zstd_send_write(MultiFDSendParams *p, uint32_t used, Error **errp) */ static int zstd_recv_setup(MultiFDRecvParams *p, Error **errp) { - uint32_t page_count = MULTIFD_PACKET_SIZE / qemu_target_page_size(); struct zstd_data *z = g_new0(struct zstd_data, 1); int ret; @@ -212,10 +211,8 @@ static int zstd_recv_setup(MultiFDRecvParams *p, Error **errp) return -1; } - /* We will never have more than page_count pages */ - z->zbuff_len = page_count * qemu_target_page_size(); - /* We know compression "could" use more space */ - z->zbuff_len *= 2; + /* To be safe, we reserve twice the size of the packet */ + z->zbuff_len = MULTIFD_PACKET_SIZE * 2; z->zbuff = g_try_malloc(z->zbuff_len); if (!z->zbuff) { ZSTD_freeDStream(z->zds); @@ -254,14 +251,14 @@ static void zstd_recv_cleanup(MultiFDRecvParams *p) * Returns 0 for success or -1 for error * * @p: Params for the channel that we are using - * @used: number of pages used * @errp: pointer to an error */ -static int zstd_recv_pages(MultiFDRecvParams *p, uint32_t used, Error **errp) +static int zstd_recv_pages(MultiFDRecvParams *p, Error **errp) { uint32_t in_size = p->next_packet_size; uint32_t out_size = 0; - uint32_t expected_size = used * qemu_target_page_size(); + size_t page_size = qemu_target_page_size(); + uint32_t expected_size = p->pages->num * page_size; uint32_t flags = p->flags & MULTIFD_FLAG_COMPRESSION_MASK; struct zstd_data *z = p->data; int ret; @@ -282,11 +279,9 @@ static int zstd_recv_pages(MultiFDRecvParams *p, uint32_t used, Error **errp) z->in.size = in_size; z->in.pos = 0; - for (i = 0; i < used; i++) { - struct iovec *iov = &p->pages->iov[i]; - - z->out.dst = iov->iov_base; - z->out.size = iov->iov_len; + for (i = 0; i < p->pages->num; i++) { + z->out.dst = p->pages->block->host + p->pages->offset[i]; + z->out.size = page_size; z->out.pos = 0; /* @@ -300,8 +295,8 @@ static int zstd_recv_pages(MultiFDRecvParams *p, uint32_t used, Error **errp) do { ret = ZSTD_decompressStream(z->zds, &z->out, &z->in); } while (ret > 0 && (z->in.size - z->in.pos > 0) - && (z->out.pos < iov->iov_len)); - if (ret > 0 && (z->out.pos < iov->iov_len)) { + && (z->out.pos < page_size)); + if (ret > 0 && (z->out.pos < page_size)) { error_setg(errp, "multifd %d: decompressStream buffer too small", p->id); return -1; diff --git a/migration/multifd.c b/migration/multifd.c index 7c9deb1921..3242f688e5 100644 --- a/migration/multifd.c +++ b/migration/multifd.c @@ -66,6 +66,7 @@ static int nocomp_send_setup(MultiFDSendParams *p, Error **errp) * For no compression this function does nothing. * * @p: Params for the channel that we are using + * @errp: pointer to an error */ static void nocomp_send_cleanup(MultiFDSendParams *p, Error **errp) { @@ -81,13 +82,11 @@ static void nocomp_send_cleanup(MultiFDSendParams *p, Error **errp) * Returns 0 for success or -1 for error * * @p: Params for the channel that we are using - * @used: number of pages used * @errp: pointer to an error */ -static int nocomp_send_prepare(MultiFDSendParams *p, uint32_t used, - Error **errp) +static int nocomp_send_prepare(MultiFDSendParams *p, Error **errp) { - p->next_packet_size = used * qemu_target_page_size(); + p->next_packet_size = p->pages->num * qemu_target_page_size(); p->flags |= MULTIFD_FLAG_NOCOMP; return 0; } @@ -142,10 +141,9 @@ static void nocomp_recv_cleanup(MultiFDRecvParams *p) * Returns 0 for success or -1 for error * * @p: Params for the channel that we are using - * @used: number of pages used * @errp: pointer to an error */ -static int nocomp_recv_pages(MultiFDRecvParams *p, uint32_t used, Error **errp) +static int nocomp_recv_pages(MultiFDRecvParams *p, Error **errp) { uint32_t flags = p->flags & MULTIFD_FLAG_COMPRESSION_MASK; @@ -154,7 +152,7 @@ static int nocomp_recv_pages(MultiFDRecvParams *p, uint32_t used, Error **errp) p->id, flags, MULTIFD_FLAG_NOCOMP); return -1; } - return qio_channel_readv_all(p->c, p->pages->iov, used, errp); + return qio_channel_readv_all(p->c, p->pages->iov, p->pages->num, errp); } static MultiFDMethods multifd_nocomp_ops = { @@ -252,7 +250,7 @@ static MultiFDPages_t *multifd_pages_init(size_t size) static void multifd_pages_clear(MultiFDPages_t *pages) { - pages->used = 0; + pages->num = 0; pages->allocated = 0; pages->packet_num = 0; pages->block = NULL; @@ -270,7 +268,7 @@ static void multifd_send_fill_packet(MultiFDSendParams *p) packet->flags = cpu_to_be32(p->flags); packet->pages_alloc = cpu_to_be32(p->pages->allocated); - packet->pages_used = cpu_to_be32(p->pages->used); + packet->pages_used = cpu_to_be32(p->pages->num); packet->next_packet_size = cpu_to_be32(p->next_packet_size); packet->packet_num = cpu_to_be64(p->packet_num); @@ -278,7 +276,7 @@ static void multifd_send_fill_packet(MultiFDSendParams *p) strncpy(packet->ramblock, p->pages->block->idstr, 256); } - for (i = 0; i < p->pages->used; i++) { + for (i = 0; i < p->pages->num; i++) { /* there are architectures where ram_addr_t is 32 bit */ uint64_t temp = p->pages->offset[i]; @@ -289,7 +287,8 @@ static void multifd_send_fill_packet(MultiFDSendParams *p) static int multifd_recv_unfill_packet(MultiFDRecvParams *p, Error **errp) { MultiFDPacket_t *packet = p->packet; - uint32_t pages_max = MULTIFD_PACKET_SIZE / qemu_target_page_size(); + size_t page_size = qemu_target_page_size(); + uint32_t pages_max = MULTIFD_PACKET_SIZE / page_size; RAMBlock *block; int i; @@ -331,18 +330,18 @@ static int multifd_recv_unfill_packet(MultiFDRecvParams *p, Error **errp) p->pages = multifd_pages_init(packet->pages_alloc); } - p->pages->used = be32_to_cpu(packet->pages_used); - if (p->pages->used > packet->pages_alloc) { + p->pages->num = be32_to_cpu(packet->pages_used); + if (p->pages->num > packet->pages_alloc) { error_setg(errp, "multifd: received packet " "with %d pages and expected maximum pages are %d", - p->pages->used, packet->pages_alloc) ; + p->pages->num, packet->pages_alloc) ; return -1; } p->next_packet_size = be32_to_cpu(packet->next_packet_size); p->packet_num = be64_to_cpu(packet->packet_num); - if (p->pages->used == 0) { + if (p->pages->num == 0) { return 0; } @@ -355,17 +354,19 @@ static int multifd_recv_unfill_packet(MultiFDRecvParams *p, Error **errp) return -1; } - for (i = 0; i < p->pages->used; i++) { + p->pages->block = block; + for (i = 0; i < p->pages->num; i++) { uint64_t offset = be64_to_cpu(packet->offset[i]); - if (offset > (block->used_length - qemu_target_page_size())) { + if (offset > (block->used_length - page_size)) { error_setg(errp, "multifd: offset too long %" PRIu64 " (max " RAM_ADDR_FMT ")", offset, block->used_length); return -1; } + p->pages->offset[i] = offset; p->pages->iov[i].iov_base = block->host + offset; - p->pages->iov[i].iov_len = qemu_target_page_size(); + p->pages->iov[i].iov_len = page_size; } return 0; @@ -442,13 +443,13 @@ static int multifd_send_pages(QEMUFile *f) } qemu_mutex_unlock(&p->mutex); } - assert(!p->pages->used); + assert(!p->pages->num); assert(!p->pages->block); p->packet_num = multifd_send_state->packet_num++; multifd_send_state->pages = p->pages; p->pages = pages; - transferred = ((uint64_t) pages->used) * qemu_target_page_size() + transferred = ((uint64_t) pages->num) * qemu_target_page_size() + p->packet_len; qemu_file_update_transfer(f, transferred); ram_counters.multifd_bytes += transferred; @@ -468,12 +469,12 @@ int multifd_queue_page(QEMUFile *f, RAMBlock *block, ram_addr_t offset) } if (pages->block == block) { - pages->offset[pages->used] = offset; - pages->iov[pages->used].iov_base = block->host + offset; - pages->iov[pages->used].iov_len = qemu_target_page_size(); - pages->used++; + pages->offset[pages->num] = offset; + pages->iov[pages->num].iov_base = block->host + offset; + pages->iov[pages->num].iov_len = qemu_target_page_size(); + pages->num++; - if (pages->used < pages->allocated) { + if (pages->num < pages->allocated) { return 1; } } @@ -523,6 +524,9 @@ static void multifd_send_terminate_threads(Error *err) qemu_mutex_lock(&p->mutex); p->quit = true; qemu_sem_post(&p->sem); + if (p->c) { + qio_channel_shutdown(p->c, QIO_CHANNEL_SHUTDOWN_BOTH, NULL); + } qemu_mutex_unlock(&p->mutex); } } @@ -585,7 +589,7 @@ void multifd_send_sync_main(QEMUFile *f) if (!migrate_use_multifd()) { return; } - if (multifd_send_state->pages->used) { + if (multifd_send_state->pages->num) { if (multifd_send_pages(f) < 0) { error_report("%s: multifd_send_pages fail", __func__); return; @@ -627,7 +631,6 @@ static void *multifd_send_thread(void *opaque) MultiFDSendParams *p = opaque; Error *local_err = NULL; int ret = 0; - uint32_t flags = 0; trace_multifd_send_thread_start(p->id); rcu_register_thread(); @@ -648,13 +651,12 @@ static void *multifd_send_thread(void *opaque) qemu_mutex_lock(&p->mutex); if (p->pending_job) { - uint32_t used = p->pages->used; + uint32_t used = p->pages->num; uint64_t packet_num = p->packet_num; - flags = p->flags; + uint32_t flags = p->flags; if (used) { - ret = multifd_send_state->ops->send_prepare(p, used, - &local_err); + ret = multifd_send_state->ops->send_prepare(p, &local_err); if (ret != 0) { qemu_mutex_unlock(&p->mutex); break; @@ -664,7 +666,7 @@ static void *multifd_send_thread(void *opaque) p->flags = 0; p->num_packets++; p->num_pages += used; - p->pages->used = 0; + p->pages->num = 0; p->pages->block = NULL; qemu_mutex_unlock(&p->mutex); @@ -1090,7 +1092,7 @@ static void *multifd_recv_thread(void *opaque) break; } - used = p->pages->used; + used = p->pages->num; flags = p->flags; /* recv methods don't know how to handle the SYNC flag */ p->flags &= ~MULTIFD_FLAG_SYNC; @@ -1101,7 +1103,7 @@ static void *multifd_recv_thread(void *opaque) qemu_mutex_unlock(&p->mutex); if (used) { - ret = multifd_recv_state->ops->recv_pages(p, used, &local_err); + ret = multifd_recv_state->ops->recv_pages(p, &local_err); if (ret != 0) { break; } diff --git a/migration/multifd.h b/migration/multifd.h index 15c50ca0b2..e57adc783b 100644 --- a/migration/multifd.h +++ b/migration/multifd.h @@ -55,7 +55,7 @@ typedef struct { typedef struct { /* number of used pages */ - uint32_t used; + uint32_t num; /* number of allocated pages */ uint32_t allocated; /* global number of generated multifd packets */ @@ -159,7 +159,7 @@ typedef struct { /* Cleanup for sending side */ void (*send_cleanup)(MultiFDSendParams *p, Error **errp); /* Prepare the send packet */ - int (*send_prepare)(MultiFDSendParams *p, uint32_t used, Error **errp); + int (*send_prepare)(MultiFDSendParams *p, Error **errp); /* Write the send packet */ int (*send_write)(MultiFDSendParams *p, uint32_t used, Error **errp); /* Setup for receiving side */ @@ -167,7 +167,7 @@ typedef struct { /* Cleanup for receiving side */ void (*recv_cleanup)(MultiFDRecvParams *p); /* Read all pages */ - int (*recv_pages)(MultiFDRecvParams *p, uint32_t used, Error **errp); + int (*recv_pages)(MultiFDRecvParams *p, Error **errp); } MultiFDMethods; void multifd_register_ops(int method, MultiFDMethods *ops); diff --git a/migration/ram.c b/migration/ram.c index 863035d235..57efa67f20 100644 --- a/migration/ram.c +++ b/migration/ram.c @@ -81,11 +81,6 @@ /* 0x80 is reserved in migration.h start with 0x100 next */ #define RAM_SAVE_FLAG_COMPRESS_PAGE 0x100 -static inline bool is_zero_range(uint8_t *p, uint64_t size) -{ - return buffer_is_zero(p, size); -} - XBZRLECacheStats xbzrle_counters; /* struct contains XBZRLE cache and a static page @@ -1180,7 +1175,7 @@ static int save_zero_page_to_file(RAMState *rs, QEMUFile *file, uint8_t *p = block->host + offset; int len = 0; - if (is_zero_range(p, TARGET_PAGE_SIZE)) { + if (buffer_is_zero(p, TARGET_PAGE_SIZE)) { len += save_page_header(rs, file, block, offset | RAM_SAVE_FLAG_ZERO); qemu_put_byte(file, 0); len += 1; @@ -3367,7 +3362,7 @@ static inline void *colo_cache_from_block_offset(RAMBlock *block, */ void ram_handle_compressed(void *host, uint8_t ch, uint64_t size) { - if (ch != 0 || !is_zero_range(host, size)) { + if (ch != 0 || !buffer_is_zero(host, size)) { memset(host, ch, size); } } @@ -3918,7 +3913,6 @@ void colo_flush_ram_cache(void) unsigned long offset = 0; memory_global_dirty_log_sync(); - qemu_mutex_lock(&ram_state->bitmap_mutex); WITH_RCU_READ_LOCK_GUARD() { RAMBLOCK_FOREACH_NOT_IGNORED(block) { ramblock_sync_dirty_bitmap(ram_state, block); @@ -3954,7 +3948,6 @@ void colo_flush_ram_cache(void) } } trace_colo_flush_ram_cache_end(); - qemu_mutex_unlock(&ram_state->bitmap_mutex); } /** diff --git a/migration/savevm.c b/migration/savevm.c index d59e976d50..0bef031acb 100644 --- a/migration/savevm.c +++ b/migration/savevm.c @@ -1685,6 +1685,7 @@ static int loadvm_postcopy_handle_advise(MigrationIncomingState *mis, { PostcopyState ps = postcopy_state_set(POSTCOPY_INCOMING_ADVISE); uint64_t remote_pagesize_summary, local_pagesize_summary, remote_tps; + size_t page_size = qemu_target_page_size(); Error *local_err = NULL; trace_loadvm_postcopy_handle_advise(); @@ -1741,13 +1742,13 @@ static int loadvm_postcopy_handle_advise(MigrationIncomingState *mis, } remote_tps = qemu_get_be64(mis->from_src_file); - if (remote_tps != qemu_target_page_size()) { + if (remote_tps != page_size) { /* * Again, some differences could be dealt with, but for now keep it * simple. */ error_report("Postcopy needs matching target page sizes (s=%d d=%zd)", - (int)remote_tps, qemu_target_page_size()); + (int)remote_tps, page_size); return -1; } diff --git a/monitor/hmp-cmds.c b/monitor/hmp-cmds.c index 9c91bf93e9..2669156b28 100644 --- a/monitor/hmp-cmds.c +++ b/monitor/hmp-cmds.c @@ -1810,6 +1810,7 @@ void hmp_info_memory_devices(Monitor *mon, const QDict *qdict) se->id ? se->id : ""); monitor_printf(mon, " memaddr: 0x%" PRIx64 "\n", se->memaddr); monitor_printf(mon, " size: %" PRIu64 "\n", se->size); + monitor_printf(mon, " node: %" PRId64 "\n", se->node); monitor_printf(mon, " memdev: %s\n", se->memdev); break; default: diff --git a/qapi/machine.json b/qapi/machine.json index 067e3f5378..edeab6084b 100644 --- a/qapi/machine.json +++ b/qapi/machine.json @@ -867,7 +867,7 @@ # # @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 node/board the CPU belongs to (Since 4.1) +# @die-id: die number within socket the CPU belongs to (since 4.1) # @core-id: core number within die the CPU belongs to # @thread-id: thread number within core the CPU belongs to # @@ -1207,12 +1207,15 @@ # # @memdev: memory backend linked with device # +# @node: the numa node +# # Since: 6.2 ## { 'struct': 'SgxEPCDeviceInfo', 'data': { '*id': 'str', 'memaddr': 'size', 'size': 'size', + 'node': 'int', 'memdev': 'str' } } @@ -1285,10 +1288,15 @@ # # @memdev: memory backend linked with device # +# @node: the numa node +# # Since: 6.2 ## { 'struct': 'SgxEPC', - 'data': { 'memdev': 'str' } } + 'data': { 'memdev': 'str', + 'node': 'int' + } +} ## # @SgxEPCProperties: diff --git a/qapi/misc-target.json b/qapi/misc-target.json index 5aa2b95b7d..1022aa0184 100644 --- a/qapi/misc-target.json +++ b/qapi/misc-target.json @@ -338,6 +338,21 @@ ## +# @SGXEPCSection: +# +# Information about intel SGX EPC section info +# +# @node: the numa node +# +# @size: the size of epc section +# +# Since: 6.2 +## +{ 'struct': 'SGXEPCSection', + 'data': { 'node': 'int', + 'size': 'uint64'}} + +## # @SGXInfo: # # Information about intel Safe Guard eXtension (SGX) support @@ -350,7 +365,7 @@ # # @flc: true if FLC is supported # -# @section-size: The EPC section size for guest +# @sections: The EPC sections info for guest # # Since: 6.2 ## @@ -359,7 +374,7 @@ 'sgx1': 'bool', 'sgx2': 'bool', 'flc': 'bool', - 'section-size': 'uint64'}, + 'sections': ['SGXEPCSection']}, 'if': 'TARGET_I386' } ## diff --git a/qemu-options.hx b/qemu-options.hx index ae2c6dbbfc..489b58e151 100644 --- a/qemu-options.hx +++ b/qemu-options.hx @@ -127,11 +127,11 @@ SRST ERST DEF("M", HAS_ARG, QEMU_OPTION_M, - " sgx-epc.0.memdev=memid\n", + " sgx-epc.0.memdev=memid,sgx-epc.0.node=numaid\n", QEMU_ARCH_ALL) SRST -``sgx-epc.0.memdev=@var{memid}`` +``sgx-epc.0.memdev=@var{memid},sgx-epc.0.node=@var{numaid}`` Define an SGX EPC section. ERST diff --git a/scripts/entitlement.sh b/scripts/entitlement.sh index e2c956a3ac..0f412949ec 100755 --- a/scripts/entitlement.sh +++ b/scripts/entitlement.sh @@ -15,7 +15,7 @@ ENTITLEMENT="$4" if $in_place; then trap 'rm "$DST.tmp"' exit - cp -af "$SRC" "$DST.tmp" + cp -pPf "$SRC" "$DST.tmp" SRC="$DST.tmp" else cd "$MESON_INSTALL_DESTDIR_PREFIX" diff --git a/scripts/meson-buildoptions.sh b/scripts/meson-buildoptions.sh index 7a17ff4218..ae8f18edc2 100644 --- a/scripts/meson-buildoptions.sh +++ b/scripts/meson-buildoptions.sh @@ -53,6 +53,7 @@ meson_options_help() { printf "%s\n" ' libiscsi libiscsi userspace initiator' printf "%s\n" ' libnfs libnfs block device driver' printf "%s\n" ' libpmem libpmem support' + printf "%s\n" ' libssh ssh block device support' printf "%s\n" ' libudev Use libudev to enumerate host devices' printf "%s\n" ' libusb libusb support for USB passthrough' printf "%s\n" ' libxml2 libxml2 support for Parallels image format' @@ -177,6 +178,8 @@ _meson_option_parse() { --disable-libnfs) printf "%s" -Dlibnfs=disabled ;; --enable-libpmem) printf "%s" -Dlibpmem=enabled ;; --disable-libpmem) printf "%s" -Dlibpmem=disabled ;; + --enable-libssh) printf "%s" -Dlibssh=enabled ;; + --disable-libssh) printf "%s" -Dlibssh=disabled ;; --enable-libudev) printf "%s" -Dlibudev=enabled ;; --disable-libudev) printf "%s" -Dlibudev=disabled ;; --enable-libusb) printf "%s" -Dlibusb=enabled ;; diff --git a/target/arm/debug_helper.c b/target/arm/debug_helper.c index 2983e36dd3..32f3caec23 100644 --- a/target/arm/debug_helper.c +++ b/target/arm/debug_helper.c @@ -220,6 +220,7 @@ bool arm_debug_check_breakpoint(CPUState *cs) { ARMCPU *cpu = ARM_CPU(cs); CPUARMState *env = &cpu->env; + target_ulong pc; int n; /* @@ -231,6 +232,28 @@ bool arm_debug_check_breakpoint(CPUState *cs) return false; } + /* + * Single-step exceptions have priority over breakpoint exceptions. + * If single-step state is active-pending, suppress the bp. + */ + if (arm_singlestep_active(env) && !(env->pstate & PSTATE_SS)) { + return false; + } + + /* + * PC alignment faults have priority over breakpoint exceptions. + */ + pc = is_a64(env) ? env->pc : env->regs[15]; + if ((is_a64(env) || !env->thumb) && (pc & 3) != 0) { + return false; + } + + /* + * Instruction aborts have priority over breakpoint exceptions. + * TODO: We would need to look up the page for PC and verify that + * it is present and executable. + */ + for (n = 0; n < ARRAY_SIZE(env->cpu_breakpoint); n++) { if (bp_wp_matches(cpu, n, false)) { return true; diff --git a/target/arm/gdbstub.c b/target/arm/gdbstub.c index 134da0d0ae..ca1de47511 100644 --- a/target/arm/gdbstub.c +++ b/target/arm/gdbstub.c @@ -77,8 +77,13 @@ int arm_cpu_gdb_write_register(CPUState *cs, uint8_t *mem_buf, int n) tmp = ldl_p(mem_buf); - /* Mask out low bit of PC to workaround gdb bugs. This will probably - cause problems if we ever implement the Jazelle DBX extensions. */ + /* + * Mask out low bits of PC to workaround gdb bugs. + * This avoids an assert in thumb_tr_translate_insn, because it is + * architecturally impossible to misalign the pc. + * This will probably cause problems if we ever implement the + * Jazelle DBX extensions. + */ if (n == 15) { tmp &= ~1; } diff --git a/target/arm/helper.c b/target/arm/helper.c index 9b317899a6..db837d53bd 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -4519,18 +4519,18 @@ static uint64_t tlbi_aa64_range_get_length(CPUARMState *env, uint64_t exponent; uint64_t length; - num = extract64(value, 39, 4); + num = extract64(value, 39, 5); scale = extract64(value, 44, 2); page_size_granule = extract64(value, 46, 2); - page_shift = page_size_granule * 2 + 12; - if (page_size_granule == 0) { qemu_log_mask(LOG_GUEST_ERROR, "Invalid page size granule %d\n", page_size_granule); return 0; } + page_shift = (page_size_granule - 1) * 2 + 12; + exponent = (5 * scale) + 1; length = (num + 1) << (exponent + page_shift); diff --git a/target/arm/helper.h b/target/arm/helper.h index 448a86edfd..b463d9343b 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -47,6 +47,7 @@ DEF_HELPER_FLAGS_3(sel_flags, TCG_CALL_NO_RWG_SE, DEF_HELPER_2(exception_internal, void, env, i32) DEF_HELPER_4(exception_with_syndrome, void, env, i32, i32, i32) DEF_HELPER_2(exception_bkpt_insn, void, env, i32) +DEF_HELPER_2(exception_pc_alignment, noreturn, env, tl) DEF_HELPER_1(setend, void, env) DEF_HELPER_2(wfi, void, env, i32) DEF_HELPER_1(wfe, void, env) diff --git a/target/arm/machine.c b/target/arm/machine.c index c74d8c3f4b..135d2420b5 100644 --- a/target/arm/machine.c +++ b/target/arm/machine.c @@ -794,6 +794,16 @@ static int cpu_post_load(void *opaque, int version_id) return -1; } } + + /* + * Misaligned thumb pc is architecturally impossible. + * We have an assert in thumb_tr_translate_insn to verify this. + * Fail an incoming migrate to avoid this assert. + */ + if (!is_a64(env) && env->thumb && (env->regs[15] & 1)) { + return -1; + } + if (!kvm_enabled()) { pmu_op_finish(&cpu->env); } diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index f30f4130a2..8cde8e7243 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -282,4 +282,9 @@ static inline uint32_t syn_illegalstate(void) return (EC_ILLEGALSTATE << ARM_EL_EC_SHIFT) | ARM_EL_IL; } +static inline uint32_t syn_pcalignment(void) +{ + return (EC_PCALIGNMENT << ARM_EL_EC_SHIFT) | ARM_EL_IL; +} + #endif /* TARGET_ARM_SYNDROME_H */ diff --git a/target/arm/tlb_helper.c b/target/arm/tlb_helper.c index 12a934e924..b79004e0cc 100644 --- a/target/arm/tlb_helper.c +++ b/target/arm/tlb_helper.c @@ -9,6 +9,7 @@ #include "cpu.h" #include "internals.h" #include "exec/exec-all.h" +#include "exec/helper-proto.h" static inline uint32_t merge_syn_data_abort(uint32_t template_syn, unsigned int target_el, @@ -49,25 +50,11 @@ static inline uint32_t merge_syn_data_abort(uint32_t template_syn, return syn; } -static void QEMU_NORETURN arm_deliver_fault(ARMCPU *cpu, vaddr addr, - MMUAccessType access_type, - int mmu_idx, ARMMMUFaultInfo *fi) +static uint32_t compute_fsr_fsc(CPUARMState *env, ARMMMUFaultInfo *fi, + int target_el, int mmu_idx, uint32_t *ret_fsc) { - CPUARMState *env = &cpu->env; - int target_el; - bool same_el; - uint32_t syn, exc, fsr, fsc; ARMMMUIdx arm_mmu_idx = core_to_arm_mmu_idx(env, mmu_idx); - - target_el = exception_target_el(env); - if (fi->stage2) { - target_el = 2; - env->cp15.hpfar_el2 = extract64(fi->s2addr, 12, 47) << 4; - if (arm_is_secure_below_el3(env) && fi->s1ns) { - env->cp15.hpfar_el2 |= HPFAR_NS; - } - } - same_el = (arm_current_el(env) == target_el); + uint32_t fsr, fsc; if (target_el == 2 || arm_el_is_aa64(env, target_el) || arm_s1_regime_using_lpae_format(env, arm_mmu_idx)) { @@ -88,6 +75,31 @@ static void QEMU_NORETURN arm_deliver_fault(ARMCPU *cpu, vaddr addr, fsc = 0x3f; } + *ret_fsc = fsc; + return fsr; +} + +static void QEMU_NORETURN arm_deliver_fault(ARMCPU *cpu, vaddr addr, + MMUAccessType access_type, + int mmu_idx, ARMMMUFaultInfo *fi) +{ + CPUARMState *env = &cpu->env; + int target_el; + bool same_el; + uint32_t syn, exc, fsr, fsc; + + target_el = exception_target_el(env); + if (fi->stage2) { + target_el = 2; + env->cp15.hpfar_el2 = extract64(fi->s2addr, 12, 47) << 4; + if (arm_is_secure_below_el3(env) && fi->s1ns) { + env->cp15.hpfar_el2 |= HPFAR_NS; + } + } + same_el = (arm_current_el(env) == target_el); + + fsr = compute_fsr_fsc(env, fi, target_el, mmu_idx, &fsc); + if (access_type == MMU_INST_FETCH) { syn = syn_insn_abort(same_el, fi->ea, fi->s1ptw, fsc); exc = EXCP_PREFETCH_ABORT; @@ -123,6 +135,23 @@ void arm_cpu_do_unaligned_access(CPUState *cs, vaddr vaddr, arm_deliver_fault(cpu, vaddr, access_type, mmu_idx, &fi); } +void helper_exception_pc_alignment(CPUARMState *env, target_ulong pc) +{ + ARMMMUFaultInfo fi = { .type = ARMFault_Alignment }; + int target_el = exception_target_el(env); + int mmu_idx = cpu_mmu_index(env, true); + uint32_t fsc; + + env->exception.vaddress = pc; + + /* + * Note that the fsc is not applicable to this exception, + * since any syndrome is pcalignment not insn_abort. + */ + env->exception.fsr = compute_fsr_fsc(env, &fi, target_el, mmu_idx, &fsc); + raise_exception(env, EXCP_PREFETCH_ABORT, syn_pcalignment(), target_el); +} + #if !defined(CONFIG_USER_ONLY) /* diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index cec672f229..130a9ff8d5 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -14750,8 +14750,10 @@ static void aarch64_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu) { DisasContext *s = container_of(dcbase, DisasContext, base); CPUARMState *env = cpu->env_ptr; + uint64_t pc = s->base.pc_next; uint32_t insn; + /* Singlestep exceptions have the highest priority. */ if (s->ss_active && !s->pstate_ss) { /* Singlestep state is Active-pending. * If we're in this state at the start of a TB then either @@ -14766,13 +14768,28 @@ static void aarch64_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu) assert(s->base.num_insns == 1); gen_swstep_exception(s, 0, 0); s->base.is_jmp = DISAS_NORETURN; + s->base.pc_next = pc + 4; return; } - s->pc_curr = s->base.pc_next; - insn = arm_ldl_code(env, &s->base, s->base.pc_next, s->sctlr_b); + if (pc & 3) { + /* + * PC alignment fault. This has priority over the instruction abort + * that we would receive from a translation fault via arm_ldl_code. + * This should only be possible after an indirect branch, at the + * start of the TB. + */ + assert(s->base.num_insns == 1); + gen_helper_exception_pc_alignment(cpu_env, tcg_constant_tl(pc)); + s->base.is_jmp = DISAS_NORETURN; + s->base.pc_next = QEMU_ALIGN_UP(pc, 4); + return; + } + + s->pc_curr = pc; + insn = arm_ldl_code(env, &s->base, pc, s->sctlr_b); s->insn = insn; - s->base.pc_next += 4; + s->base.pc_next = pc + 4; s->fp_access_checked = false; s->sve_access_checked = false; diff --git a/target/arm/translate.c b/target/arm/translate.c index 98f5925928..0a3840d227 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -9502,7 +9502,7 @@ static void arm_tr_insn_start(DisasContextBase *dcbase, CPUState *cpu) dc->insn_start = tcg_last_op(); } -static bool arm_pre_translate_insn(DisasContext *dc) +static bool arm_check_kernelpage(DisasContext *dc) { #ifdef CONFIG_USER_ONLY /* Intercept jump to the magic kernel page. */ @@ -9514,7 +9514,11 @@ static bool arm_pre_translate_insn(DisasContext *dc) return true; } #endif + return false; +} +static bool arm_check_ss_active(DisasContext *dc) +{ if (dc->ss_active && !dc->pstate_ss) { /* Singlestep state is Active-pending. * If we're in this state at the start of a TB then either @@ -9548,17 +9552,38 @@ static void arm_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu) { DisasContext *dc = container_of(dcbase, DisasContext, base); CPUARMState *env = cpu->env_ptr; + uint32_t pc = dc->base.pc_next; unsigned int insn; - if (arm_pre_translate_insn(dc)) { - dc->base.pc_next += 4; + /* Singlestep exceptions have the highest priority. */ + if (arm_check_ss_active(dc)) { + dc->base.pc_next = pc + 4; return; } - dc->pc_curr = dc->base.pc_next; - insn = arm_ldl_code(env, &dc->base, dc->base.pc_next, dc->sctlr_b); + if (pc & 3) { + /* + * PC alignment fault. This has priority over the instruction abort + * that we would receive from a translation fault via arm_ldl_code + * (or the execution of the kernelpage entrypoint). This should only + * be possible after an indirect branch, at the start of the TB. + */ + assert(dc->base.num_insns == 1); + gen_helper_exception_pc_alignment(cpu_env, tcg_constant_tl(pc)); + dc->base.is_jmp = DISAS_NORETURN; + dc->base.pc_next = QEMU_ALIGN_UP(pc, 4); + return; + } + + if (arm_check_kernelpage(dc)) { + dc->base.pc_next = pc + 4; + return; + } + + dc->pc_curr = pc; + insn = arm_ldl_code(env, &dc->base, pc, dc->sctlr_b); dc->insn = insn; - dc->base.pc_next += 4; + dc->base.pc_next = pc + 4; disas_arm_insn(dc, insn); arm_post_translate_insn(dc); @@ -9617,25 +9642,28 @@ static void thumb_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu) { DisasContext *dc = container_of(dcbase, DisasContext, base); CPUARMState *env = cpu->env_ptr; + uint32_t pc = dc->base.pc_next; uint32_t insn; bool is_16bit; - if (arm_pre_translate_insn(dc)) { - dc->base.pc_next += 2; + /* Misaligned thumb PC is architecturally impossible. */ + assert((dc->base.pc_next & 1) == 0); + + if (arm_check_ss_active(dc) || arm_check_kernelpage(dc)) { + dc->base.pc_next = pc + 2; return; } - dc->pc_curr = dc->base.pc_next; - insn = arm_lduw_code(env, &dc->base, dc->base.pc_next, dc->sctlr_b); + dc->pc_curr = pc; + insn = arm_lduw_code(env, &dc->base, pc, dc->sctlr_b); is_16bit = thumb_insn_is_16bit(dc, dc->base.pc_next, insn); - dc->base.pc_next += 2; + pc += 2; if (!is_16bit) { - uint32_t insn2 = arm_lduw_code(env, &dc->base, dc->base.pc_next, - dc->sctlr_b); - + uint32_t insn2 = arm_lduw_code(env, &dc->base, pc, dc->sctlr_b); insn = insn << 16 | insn2; - dc->base.pc_next += 2; + pc += 2; } + dc->base.pc_next = pc; dc->insn = insn; if (dc->pstate_il) { diff --git a/target/hexagon/cpu.h b/target/hexagon/cpu.h index de121d950f..58a0d3870b 100644 --- a/target/hexagon/cpu.h +++ b/target/hexagon/cpu.h @@ -23,7 +23,6 @@ typedef struct CPUHexagonState CPUHexagonState; #include "fpu/softfloat-types.h" -#include "qemu-common.h" #include "exec/cpu-defs.h" #include "hex_regs.h" #include "mmvec/mmvec.h" diff --git a/target/i386/tcg/translate.c b/target/i386/tcg/translate.c index e9e1451540..05f9336c9b 100644 --- a/target/i386/tcg/translate.c +++ b/target/i386/tcg/translate.c @@ -3519,9 +3519,6 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b, case 0x171: /* shift xmm, im */ case 0x172: case 0x173: - if (b1 >= 2) { - goto unknown_op; - } val = x86_ldub_code(env, s); if (is_xmm) { tcg_gen_movi_tl(s->T0, val); @@ -3540,6 +3537,7 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b, offsetof(CPUX86State, mmx_t0.MMX_L(1))); op1_offset = offsetof(CPUX86State,mmx_t0); } + assert(b1 < 2); sse_fn_epp = sse_op_table2[((b - 1) & 3) * 8 + (((modrm >> 3)) & 7)][b1]; if (!sse_fn_epp) { @@ -3770,10 +3768,8 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b, rm = modrm & 7; reg = ((modrm >> 3) & 7) | REX_R(s); mod = (modrm >> 6) & 3; - if (b1 >= 2) { - goto unknown_op; - } + assert(b1 < 2); sse_fn_epp = sse_op_table6[b].op[b1]; if (!sse_fn_epp) { goto unknown_op; @@ -4200,10 +4196,8 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b, rm = modrm & 7; reg = ((modrm >> 3) & 7) | REX_R(s); mod = (modrm >> 6) & 3; - if (b1 >= 2) { - goto unknown_op; - } + assert(b1 < 2); sse_fn_eppi = sse_op_table7[b].op[b1]; if (!sse_fn_eppi) { goto unknown_op; diff --git a/target/rx/cpu.h b/target/rx/cpu.h index 4ac71aec37..657db84ef0 100644 --- a/target/rx/cpu.h +++ b/target/rx/cpu.h @@ -20,7 +20,6 @@ #define RX_CPU_H #include "qemu/bitops.h" -#include "qemu-common.h" #include "hw/registerfields.h" #include "cpu-qom.h" diff --git a/target/s390x/cpu.h b/target/s390x/cpu.h index ca3845d023..a75e559134 100644 --- a/target/s390x/cpu.h +++ b/target/s390x/cpu.h @@ -63,6 +63,8 @@ struct CPUS390XState { uint64_t etoken; /* etoken */ uint64_t etoken_extension; /* etoken extension */ + uint64_t diag318_info; + /* Fields up to this point are not cleared by initial CPU reset */ struct {} start_initial_reset_fields; @@ -118,8 +120,6 @@ struct CPUS390XState { uint16_t external_call_addr; DECLARE_BITMAP(emergency_signals, S390_MAX_CPUS); - uint64_t diag318_info; - #if !defined(CONFIG_USER_ONLY) uint64_t tlb_fill_tec; /* translation exception code during tlb_fill */ int tlb_fill_exc; /* exception number seen during tlb_fill */ diff --git a/target/s390x/kvm/kvm.c b/target/s390x/kvm/kvm.c index 5b1fdb55c4..6acf14d5ec 100644 --- a/target/s390x/kvm/kvm.c +++ b/target/s390x/kvm/kvm.c @@ -1585,6 +1585,10 @@ void kvm_s390_set_diag318(CPUState *cs, uint64_t diag318_info) env->diag318_info = diag318_info; cs->kvm_run->s.regs.diag318 = diag318_info; cs->kvm_run->kvm_dirty_regs |= KVM_SYNC_DIAG318; + /* + * diag 318 info is zeroed during a clear reset and + * diag 308 IPL subcodes. + */ } } diff --git a/tests/data/acpi/q35/DSDT.viot b/tests/data/acpi/q35/DSDT.viot new file mode 100644 index 0000000000..1c3b4da5cb --- /dev/null +++ b/tests/data/acpi/q35/DSDT.viot Binary files differdiff --git a/tests/data/acpi/q35/VIOT.viot b/tests/data/acpi/q35/VIOT.viot new file mode 100644 index 0000000000..9b179266cc --- /dev/null +++ b/tests/data/acpi/q35/VIOT.viot Binary files differdiff --git a/tests/data/acpi/virt/VIOT b/tests/data/acpi/virt/VIOT new file mode 100644 index 0000000000..921f40d88c --- /dev/null +++ b/tests/data/acpi/virt/VIOT Binary files differdiff --git a/tests/qtest/bios-tables-test.c b/tests/qtest/bios-tables-test.c index 258874167e..9a468e29eb 100644 --- a/tests/qtest/bios-tables-test.c +++ b/tests/qtest/bios-tables-test.c @@ -1465,6 +1465,43 @@ static void test_acpi_virt_tcg(void) free_test_data(&data); } +static void test_acpi_q35_viot(void) +{ + test_data data = { + .machine = MACHINE_Q35, + .variant = ".viot", + }; + + /* + * To keep things interesting, two buses bypass the IOMMU. + * VIOT should only describes the other two buses. + */ + test_acpi_one("-machine default_bus_bypass_iommu=on " + "-device virtio-iommu-pci " + "-device pxb-pcie,bus_nr=0x10,id=pcie.100,bus=pcie.0 " + "-device pxb-pcie,bus_nr=0x20,id=pcie.200,bus=pcie.0,bypass_iommu=on " + "-device pxb-pcie,bus_nr=0x30,id=pcie.300,bus=pcie.0", + &data); + free_test_data(&data); +} + +static void test_acpi_virt_viot(void) +{ + test_data data = { + .machine = "virt", + .tcg_only = true, + .uefi_fl1 = "pc-bios/edk2-aarch64-code.fd", + .uefi_fl2 = "pc-bios/edk2-arm-vars.fd", + .cd = "tests/data/uefi-boot-images/bios-tables-test.aarch64.iso.qcow2", + .ram_start = 0x40000000ULL, + .scan_len = 128ULL * 1024 * 1024, + }; + + test_acpi_one("-cpu cortex-a57 " + "-device virtio-iommu-pci", &data); + free_test_data(&data); +} + static void test_oem_fields(test_data *data) { int i; @@ -1639,6 +1676,7 @@ int main(int argc, char *argv[]) qtest_add_func("acpi/q35/kvm/xapic", test_acpi_q35_kvm_xapic); qtest_add_func("acpi/q35/kvm/dmar", test_acpi_q35_kvm_dmar); } + qtest_add_func("acpi/q35/viot", test_acpi_q35_viot); } else if (strcmp(arch, "aarch64") == 0) { if (has_tcg) { qtest_add_func("acpi/virt", test_acpi_virt_tcg); @@ -1646,6 +1684,7 @@ int main(int argc, char *argv[]) qtest_add_func("acpi/virt/memhp", test_acpi_virt_tcg_memhp); qtest_add_func("acpi/virt/pxb", test_acpi_virt_tcg_pxb); qtest_add_func("acpi/virt/oem-fields", test_acpi_oem_fields_virt); + qtest_add_func("acpi/virt/viot", test_acpi_virt_viot); } } ret = g_test_run(); diff --git a/tests/qtest/boot-serial-test.c b/tests/qtest/boot-serial-test.c index 83828ba270..4d8e1343bd 100644 --- a/tests/qtest/boot-serial-test.c +++ b/tests/qtest/boot-serial-test.c @@ -285,7 +285,8 @@ int main(int argc, char *argv[]) g_test_init(&argc, &argv, NULL); for (i = 0; tests[i].arch != NULL; i++) { - if (strcmp(arch, tests[i].arch) == 0) { + if (g_str_equal(arch, tests[i].arch) && + qtest_has_machine(tests[i].machine)) { char *name = g_strdup_printf("boot-serial/%s", tests[i].machine); qtest_add_data_func(name, &tests[i], test_machine); g_free(name); diff --git a/tests/qtest/cdrom-test.c b/tests/qtest/cdrom-test.c index 5af944a5fb..c1fcac5c45 100644 --- a/tests/qtest/cdrom-test.c +++ b/tests/qtest/cdrom-test.c @@ -109,9 +109,11 @@ static void test_cdrom_param(gconstpointer data) static void add_cdrom_param_tests(const char **machines) { while (*machines) { - char *testname = g_strdup_printf("cdrom/param/%s", *machines); - qtest_add_data_func(testname, *machines, test_cdrom_param); - g_free(testname); + if (qtest_has_machine(*machines)) { + char *testname = g_strdup_printf("cdrom/param/%s", *machines); + qtest_add_data_func(testname, *machines, test_cdrom_param); + g_free(testname); + } machines++; } } diff --git a/tests/qtest/fuzz-lsi53c895a-test.c b/tests/qtest/fuzz-lsi53c895a-test.c new file mode 100644 index 0000000000..ba5d468970 --- /dev/null +++ b/tests/qtest/fuzz-lsi53c895a-test.c @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * QTest fuzzer-generated testcase for LSI53C895A device + * + * Copyright (c) Red Hat + */ + +#include "qemu/osdep.h" +#include "libqos/libqtest.h" + +/* + * This used to trigger the assert in lsi_do_dma() + * https://bugs.launchpad.net/qemu/+bug/697510 + * https://bugs.launchpad.net/qemu/+bug/1905521 + * https://bugs.launchpad.net/qemu/+bug/1908515 + */ +static void test_lsi_do_dma_empty_queue(void) +{ + QTestState *s; + + s = qtest_init("-M q35 -nographic -monitor none -serial none " + "-drive if=none,id=drive0," + "file=null-co://,file.read-zeroes=on,format=raw " + "-device lsi53c895a,id=scsi0 " + "-device scsi-hd,drive=drive0," + "bus=scsi0.0,channel=0,scsi-id=0,lun=0"); + qtest_outl(s, 0xcf8, 0x80001814); + qtest_outl(s, 0xcfc, 0xe1068000); + qtest_outl(s, 0xcf8, 0x80001818); + qtest_outl(s, 0xcf8, 0x80001804); + qtest_outw(s, 0xcfc, 0x7); + qtest_outl(s, 0xcf8, 0x80002010); + + qtest_writeb(s, 0xe106802e, 0xff); /* Fill DSP bits 16-23 */ + qtest_writeb(s, 0xe106802f, 0xff); /* Fill DSP bits 24-31: trigger SCRIPT */ + + qtest_quit(s); +} + +int main(int argc, char **argv) +{ + const char *arch = qtest_get_arch(); + + g_test_init(&argc, &argv, NULL); + + if (strcmp(arch, "i386") == 0 || strcmp(arch, "x86_64") == 0) { + qtest_add_func("fuzz/lsi53c895a/lsi_do_dma_empty_queue", + test_lsi_do_dma_empty_queue); + } + + return g_test_run(); +} diff --git a/tests/qtest/libqos/libqtest.h b/tests/qtest/libqos/libqtest.h index 59e9271195..dff6b31cf0 100644 --- a/tests/qtest/libqos/libqtest.h +++ b/tests/qtest/libqos/libqtest.h @@ -711,6 +711,14 @@ void qtest_cb_for_every_machine(void (*cb)(const char *machine), bool skip_old_versioned); /** + * qtest_has_machine: + * @machine: The machine to look for + * + * Returns: true if the machine is available in the target binary. + */ +bool qtest_has_machine(const char *machine); + +/** * qtest_qmp_device_add_qdict: * @qts: QTestState instance to operate on * @drv: Name of the device that should be added diff --git a/tests/qtest/libqos/meson.build b/tests/qtest/libqos/meson.build index 4af1f04787..e988d15791 100644 --- a/tests/qtest/libqos/meson.build +++ b/tests/qtest/libqos/meson.build @@ -41,6 +41,7 @@ libqos_srcs = files('../libqtest.c', 'virtio-rng.c', 'virtio-scsi.c', 'virtio-serial.c', + 'virtio-iommu.c', # qgraph machines: 'aarch64-xlnx-zcu102-machine.c', diff --git a/tests/qtest/libqos/pci.c b/tests/qtest/libqos/pci.c index e1e96189c8..3a9076ae58 100644 --- a/tests/qtest/libqos/pci.c +++ b/tests/qtest/libqos/pci.c @@ -13,6 +13,8 @@ #include "qemu/osdep.h" #include "pci.h" +#include "hw/pci/pci.h" +#include "hw/pci/pci_bridge.h" #include "hw/pci/pci_regs.h" #include "qemu/host-utils.h" #include "qgraph.h" @@ -99,6 +101,123 @@ void qpci_device_init(QPCIDevice *dev, QPCIBus *bus, QPCIAddress *addr) g_assert(!addr->device_id || device_id == addr->device_id); } +static uint8_t qpci_find_resource_reserve_capability(QPCIDevice *dev) +{ + uint16_t device_id; + uint8_t cap = 0; + + if (qpci_config_readw(dev, PCI_VENDOR_ID) != PCI_VENDOR_ID_REDHAT) { + return 0; + } + + device_id = qpci_config_readw(dev, PCI_DEVICE_ID); + + if (device_id != PCI_DEVICE_ID_REDHAT_PCIE_RP && + device_id != PCI_DEVICE_ID_REDHAT_BRIDGE) { + return 0; + } + + do { + cap = qpci_find_capability(dev, PCI_CAP_ID_VNDR, cap); + } while (cap && + qpci_config_readb(dev, cap + REDHAT_PCI_CAP_TYPE_OFFSET) != + REDHAT_PCI_CAP_RESOURCE_RESERVE); + if (cap) { + uint8_t cap_len = qpci_config_readb(dev, cap + PCI_CAP_FLAGS); + if (cap_len < REDHAT_PCI_CAP_RES_RESERVE_CAP_SIZE) { + return 0; + } + } + return cap; +} + +static void qpci_secondary_buses_rec(QPCIBus *qbus, int bus, int *pci_bus) +{ + QPCIDevice *dev; + uint16_t class; + uint8_t pribus, secbus, subbus; + int index; + + for (index = 0; index < 32; index++) { + dev = qpci_device_find(qbus, QPCI_DEVFN(bus + index, 0)); + if (dev == NULL) { + continue; + } + class = qpci_config_readw(dev, PCI_CLASS_DEVICE); + if (class == PCI_CLASS_BRIDGE_PCI) { + qpci_config_writeb(dev, PCI_SECONDARY_BUS, 255); + qpci_config_writeb(dev, PCI_SUBORDINATE_BUS, 0); + } + g_free(dev); + } + + for (index = 0; index < 32; index++) { + dev = qpci_device_find(qbus, QPCI_DEVFN(bus + index, 0)); + if (dev == NULL) { + continue; + } + class = qpci_config_readw(dev, PCI_CLASS_DEVICE); + if (class != PCI_CLASS_BRIDGE_PCI) { + g_free(dev); + continue; + } + + pribus = qpci_config_readb(dev, PCI_PRIMARY_BUS); + if (pribus != bus) { + qpci_config_writeb(dev, PCI_PRIMARY_BUS, bus); + } + + secbus = qpci_config_readb(dev, PCI_SECONDARY_BUS); + (*pci_bus)++; + if (*pci_bus != secbus) { + secbus = *pci_bus; + qpci_config_writeb(dev, PCI_SECONDARY_BUS, secbus); + } + + subbus = qpci_config_readb(dev, PCI_SUBORDINATE_BUS); + qpci_config_writeb(dev, PCI_SUBORDINATE_BUS, 255); + + qpci_secondary_buses_rec(qbus, secbus << 5, pci_bus); + + if (subbus != *pci_bus) { + uint8_t res_bus = *pci_bus; + uint8_t cap = qpci_find_resource_reserve_capability(dev); + + if (cap) { + uint32_t tmp_res_bus; + + tmp_res_bus = qpci_config_readl(dev, cap + + REDHAT_PCI_CAP_RES_RESERVE_BUS_RES); + if (tmp_res_bus != (uint32_t)-1) { + res_bus = tmp_res_bus & 0xFF; + if ((uint8_t)(res_bus + secbus) < secbus || + (uint8_t)(res_bus + secbus) < res_bus) { + res_bus = 0; + } + if (secbus + res_bus > *pci_bus) { + res_bus = secbus + res_bus; + } + } + } + subbus = res_bus; + *pci_bus = res_bus; + } + + qpci_config_writeb(dev, PCI_SUBORDINATE_BUS, subbus); + g_free(dev); + } +} + +int qpci_secondary_buses_init(QPCIBus *bus) +{ + int last_bus = 0; + + qpci_secondary_buses_rec(bus, 0, &last_bus); + + return last_bus; +} + + void qpci_device_enable(QPCIDevice *dev) { uint16_t cmd; diff --git a/tests/qtest/libqos/pci.h b/tests/qtest/libqos/pci.h index ee64fdecbd..becb800f9e 100644 --- a/tests/qtest/libqos/pci.h +++ b/tests/qtest/libqos/pci.h @@ -81,6 +81,7 @@ void qpci_device_foreach(QPCIBus *bus, int vendor_id, int device_id, void *data); QPCIDevice *qpci_device_find(QPCIBus *bus, int devfn); void qpci_device_init(QPCIDevice *dev, QPCIBus *bus, QPCIAddress *addr); +int qpci_secondary_buses_init(QPCIBus *bus); bool qpci_has_buggy_msi(QPCIDevice *dev); bool qpci_check_buggy_msi(QPCIDevice *dev); diff --git a/tests/qtest/libqos/virtio-iommu.c b/tests/qtest/libqos/virtio-iommu.c new file mode 100644 index 0000000000..18cba4ca36 --- /dev/null +++ b/tests/qtest/libqos/virtio-iommu.c @@ -0,0 +1,126 @@ +/* + * libqos driver virtio-iommu-pci framework + * + * Copyright (c) 2021 Red Hat, Inc. + * + * Authors: + * Eric Auger <eric.auger@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or (at your + * option) any later version. See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "libqtest.h" +#include "qemu/module.h" +#include "qgraph.h" +#include "virtio-iommu.h" +#include "hw/virtio/virtio-iommu.h" + +static QGuestAllocator *alloc; + +/* virtio-iommu-device */ +static void *qvirtio_iommu_get_driver(QVirtioIOMMU *v_iommu, + const char *interface) +{ + if (!g_strcmp0(interface, "virtio-iommu")) { + return v_iommu; + } + if (!g_strcmp0(interface, "virtio")) { + return v_iommu->vdev; + } + + fprintf(stderr, "%s not present in virtio-iommu-device\n", interface); + g_assert_not_reached(); +} + +static void virtio_iommu_cleanup(QVirtioIOMMU *interface) +{ + qvirtqueue_cleanup(interface->vdev->bus, interface->vq, alloc); +} + +static void virtio_iommu_setup(QVirtioIOMMU *interface) +{ + QVirtioDevice *vdev = interface->vdev; + uint64_t features; + + features = qvirtio_get_features(vdev); + features &= ~(QVIRTIO_F_BAD_FEATURE | + (1ull << VIRTIO_RING_F_INDIRECT_DESC) | + (1ull << VIRTIO_RING_F_EVENT_IDX) | + (1ull << VIRTIO_IOMMU_F_BYPASS)); + qvirtio_set_features(vdev, features); + interface->vq = qvirtqueue_setup(interface->vdev, alloc, 0); + qvirtio_set_driver_ok(interface->vdev); +} + +/* virtio-iommu-pci */ +static void *qvirtio_iommu_pci_get_driver(void *object, const char *interface) +{ + QVirtioIOMMUPCI *v_iommu = object; + if (!g_strcmp0(interface, "pci-device")) { + return v_iommu->pci_vdev.pdev; + } + return qvirtio_iommu_get_driver(&v_iommu->iommu, interface); +} + +static void qvirtio_iommu_pci_destructor(QOSGraphObject *obj) +{ + QVirtioIOMMUPCI *iommu_pci = (QVirtioIOMMUPCI *) obj; + QVirtioIOMMU *interface = &iommu_pci->iommu; + QOSGraphObject *pci_vobj = &iommu_pci->pci_vdev.obj; + + virtio_iommu_cleanup(interface); + qvirtio_pci_destructor(pci_vobj); +} + +static void qvirtio_iommu_pci_start_hw(QOSGraphObject *obj) +{ + QVirtioIOMMUPCI *iommu_pci = (QVirtioIOMMUPCI *) obj; + QVirtioIOMMU *interface = &iommu_pci->iommu; + QOSGraphObject *pci_vobj = &iommu_pci->pci_vdev.obj; + + qvirtio_pci_start_hw(pci_vobj); + virtio_iommu_setup(interface); +} + + +static void *virtio_iommu_pci_create(void *pci_bus, QGuestAllocator *t_alloc, + void *addr) +{ + QVirtioIOMMUPCI *virtio_rpci = g_new0(QVirtioIOMMUPCI, 1); + QVirtioIOMMU *interface = &virtio_rpci->iommu; + QOSGraphObject *obj = &virtio_rpci->pci_vdev.obj; + + virtio_pci_init(&virtio_rpci->pci_vdev, pci_bus, addr); + interface->vdev = &virtio_rpci->pci_vdev.vdev; + alloc = t_alloc; + + obj->get_driver = qvirtio_iommu_pci_get_driver; + obj->start_hw = qvirtio_iommu_pci_start_hw; + obj->destructor = qvirtio_iommu_pci_destructor; + + return obj; +} + +static void virtio_iommu_register_nodes(void) +{ + QPCIAddress addr = { + .devfn = QPCI_DEVFN(4, 0), + }; + + QOSGraphEdgeOptions opts = { + .extra_device_opts = "addr=04.0", + }; + + /* virtio-iommu-pci */ + add_qpci_address(&opts, &addr); + qos_node_create_driver("virtio-iommu-pci", virtio_iommu_pci_create); + qos_node_consumes("virtio-iommu-pci", "pci-bus", &opts); + qos_node_produces("virtio-iommu-pci", "pci-device"); + qos_node_produces("virtio-iommu-pci", "virtio"); + qos_node_produces("virtio-iommu-pci", "virtio-iommu"); +} + +libqos_init(virtio_iommu_register_nodes); diff --git a/tests/qtest/libqos/virtio-iommu.h b/tests/qtest/libqos/virtio-iommu.h new file mode 100644 index 0000000000..d753761958 --- /dev/null +++ b/tests/qtest/libqos/virtio-iommu.h @@ -0,0 +1,40 @@ +/* + * libqos driver virtio-iommu-pci framework + * + * Copyright (c) 2021 Red Hat, Inc. + * + * Authors: + * Eric Auger <eric.auger@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or (at your + * option) any later version. See the COPYING file in the top-level directory. + * + */ + +#ifndef TESTS_LIBQOS_VIRTIO_IOMMU_H +#define TESTS_LIBQOS_VIRTIO_IOMMU_H + +#include "qgraph.h" +#include "virtio.h" +#include "virtio-pci.h" + +typedef struct QVirtioIOMMU QVirtioIOMMU; +typedef struct QVirtioIOMMUPCI QVirtioIOMMUPCI; +typedef struct QVirtioIOMMUDevice QVirtioIOMMUDevice; + +struct QVirtioIOMMU { + QVirtioDevice *vdev; + QVirtQueue *vq; +}; + +struct QVirtioIOMMUPCI { + QVirtioPCIDevice pci_vdev; + QVirtioIOMMU iommu; +}; + +struct QVirtioIOMMUDevice { + QOSGraphObject obj; + QVirtioIOMMU iommu; +}; + +#endif diff --git a/tests/qtest/libqtest.c b/tests/qtest/libqtest.c index 25aeea385b..65ed949685 100644 --- a/tests/qtest/libqtest.c +++ b/tests/qtest/libqtest.c @@ -1321,16 +1321,29 @@ static bool qtest_is_old_versioned_machine(const char *mname) return res; } -void qtest_cb_for_every_machine(void (*cb)(const char *machine), - bool skip_old_versioned) +struct MachInfo { + char *name; + char *alias; +}; + +/* + * Returns an array with pointers to the available machine names. + * The terminating entry has the name set to NULL. + */ +static struct MachInfo *qtest_get_machines(void) { + static struct MachInfo *machines; QDict *response, *minfo; QList *list; const QListEntry *p; QObject *qobj; QString *qstr; - const char *mname; QTestState *qts; + int idx; + + if (machines) { + return machines; + } qts = qtest_init("-machine none"); response = qtest_qmp(qts, "{ 'execute': 'query-machines' }"); @@ -1338,25 +1351,71 @@ void qtest_cb_for_every_machine(void (*cb)(const char *machine), list = qdict_get_qlist(response, "return"); g_assert(list); - for (p = qlist_first(list); p; p = qlist_next(p)) { + machines = g_new(struct MachInfo, qlist_size(list) + 1); + + for (p = qlist_first(list), idx = 0; p; p = qlist_next(p), idx++) { minfo = qobject_to(QDict, qlist_entry_obj(p)); g_assert(minfo); + qobj = qdict_get(minfo, "name"); g_assert(qobj); qstr = qobject_to(QString, qobj); g_assert(qstr); - mname = qstring_get_str(qstr); + machines[idx].name = g_strdup(qstring_get_str(qstr)); + + qobj = qdict_get(minfo, "alias"); + if (qobj) { /* The alias is optional */ + qstr = qobject_to(QString, qobj); + g_assert(qstr); + machines[idx].alias = g_strdup(qstring_get_str(qstr)); + } else { + machines[idx].alias = NULL; + } + } + + qtest_quit(qts); + qobject_unref(response); + + memset(&machines[idx], 0, sizeof(struct MachInfo)); /* Terminating entry */ + return machines; +} + +void qtest_cb_for_every_machine(void (*cb)(const char *machine), + bool skip_old_versioned) +{ + struct MachInfo *machines; + int i; + + machines = qtest_get_machines(); + + for (i = 0; machines[i].name != NULL; i++) { /* Ignore machines that cannot be used for qtests */ - if (!strncmp("xenfv", mname, 5) || g_str_equal("xenpv", mname)) { + if (!strncmp("xenfv", machines[i].name, 5) || + g_str_equal("xenpv", machines[i].name)) { continue; } - if (!skip_old_versioned || !qtest_is_old_versioned_machine(mname)) { - cb(mname); + if (!skip_old_versioned || + !qtest_is_old_versioned_machine(machines[i].name)) { + cb(machines[i].name); } } +} - qtest_quit(qts); - qobject_unref(response); +bool qtest_has_machine(const char *machine) +{ + struct MachInfo *machines; + int i; + + machines = qtest_get_machines(); + + for (i = 0; machines[i].name != NULL; i++) { + if (g_str_equal(machine, machines[i].name) || + (machines[i].alias && g_str_equal(machine, machines[i].alias))) { + return true; + } + } + + return false; } /* diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build index c9d8458062..ebeac59b3f 100644 --- a/tests/qtest/meson.build +++ b/tests/qtest/meson.build @@ -19,6 +19,7 @@ slow_qtests = { qtests_generic = \ (config_all_devices.has_key('CONFIG_MEGASAS_SCSI_PCI') ? ['fuzz-megasas-test'] : []) + \ + (config_all_devices.has_key('CONFIG_LSI_SCSI_PCI') ? ['fuzz-lsi53c895a-test'] : []) + \ (config_all_devices.has_key('CONFIG_VIRTIO_SCSI') ? ['fuzz-virtio-scsi-test'] : []) + \ (config_all_devices.has_key('CONFIG_SB16') ? ['fuzz-sb16-test'] : []) + \ (config_all_devices.has_key('CONFIG_SDHCI_PCI') ? ['fuzz-sdcard-test'] : []) + \ @@ -68,6 +69,10 @@ qtests_i386 = \ (config_all_devices.has_key('CONFIG_RTL8139_PCI') ? ['rtl8139-test'] : []) + \ (config_all_devices.has_key('CONFIG_E1000E_PCI_EXPRESS') ? ['fuzz-e1000e-test'] : []) + \ (config_all_devices.has_key('CONFIG_ESP_PCI') ? ['am53c974-test'] : []) + \ + (config_all_devices.has_key('CONFIG_VIRTIO_NET') and \ + 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', @@ -134,6 +139,7 @@ qtests_ppc = \ ['boot-order-test', 'prom-env-test', 'boot-serial-test'] \ qtests_ppc64 = \ + qtests_ppc + \ (config_all_devices.has_key('CONFIG_PSERIES') ? ['device-plug-test'] : []) + \ (config_all_devices.has_key('CONFIG_POWERNV') ? ['pnv-xscom-test'] : []) + \ (config_all_devices.has_key('CONFIG_PSERIES') ? ['rtas-test'] : []) + \ @@ -183,11 +189,10 @@ 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'] : []) + \ ['arm-cpu-features', 'numa-test', 'boot-serial-test', - 'xlnx-can-test', - 'fuzz-xlnx-dp-test', 'migration-test'] qtests_s390x = \ @@ -230,6 +235,7 @@ qos_test_ss.add( 'virtio-rng-test.c', 'virtio-scsi-test.c', 'virtio-serial-test.c', + 'virtio-iommu-test.c', 'vmxnet3-test.c', ) if have_virtfs diff --git a/tests/qtest/prom-env-test.c b/tests/qtest/prom-env-test.c index f41d80154a..bdbb01d8e5 100644 --- a/tests/qtest/prom-env-test.c +++ b/tests/qtest/prom-env-test.c @@ -71,9 +71,11 @@ static void add_tests(const char *machines[]) char *name; for (i = 0; machines[i] != NULL; i++) { - name = g_strdup_printf("prom-env/%s", machines[i]); - qtest_add_data_func(name, machines[i], test_machine); - g_free(name); + if (qtest_has_machine(machines[i])) { + name = g_strdup_printf("prom-env/%s", machines[i]); + qtest_add_data_func(name, machines[i], test_machine); + g_free(name); + } } } diff --git a/tests/qtest/virtio-iommu-test.c b/tests/qtest/virtio-iommu-test.c new file mode 100644 index 0000000000..47e68388a0 --- /dev/null +++ b/tests/qtest/virtio-iommu-test.c @@ -0,0 +1,326 @@ +/* + * QTest testcase for VirtIO IOMMU + * + * Copyright (c) 2021 Red Hat, Inc. + * + * Authors: + * Eric Auger <eric.auger@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or (at your + * option) any later version. See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "libqtest-single.h" +#include "qemu/module.h" +#include "libqos/qgraph.h" +#include "libqos/virtio-iommu.h" +#include "hw/virtio/virtio-iommu.h" + +#define PCI_SLOT_HP 0x06 +#define QVIRTIO_IOMMU_TIMEOUT_US (30 * 1000 * 1000) + +static QGuestAllocator *alloc; + +static void pci_config(void *obj, void *data, QGuestAllocator *t_alloc) +{ + QVirtioIOMMU *v_iommu = obj; + QVirtioDevice *dev = v_iommu->vdev; + uint64_t input_range_start = qvirtio_config_readq(dev, 8); + uint64_t input_range_end = qvirtio_config_readq(dev, 16); + uint32_t domain_range_start = qvirtio_config_readl(dev, 24); + uint32_t domain_range_end = qvirtio_config_readl(dev, 28); + + g_assert_cmpint(input_range_start, ==, 0); + g_assert_cmphex(input_range_end, ==, UINT64_MAX); + g_assert_cmpint(domain_range_start, ==, 0); + g_assert_cmpint(domain_range_end, ==, UINT32_MAX); +} + +static int read_tail_status(struct virtio_iommu_req_tail *buffer) +{ + int i; + + for (i = 0; i < 3; i++) { + g_assert_cmpint(buffer->reserved[i], ==, 0); + } + return buffer->status; +} + +/** + * send_attach_detach - Send an attach/detach command to the device + * @type: VIRTIO_IOMMU_T_ATTACH/VIRTIO_IOMMU_T_DETACH + * @domain: domain the endpoint is attached to + * @ep: endpoint + */ +static int send_attach_detach(QTestState *qts, QVirtioIOMMU *v_iommu, + uint8_t type, uint32_t domain, uint32_t ep) +{ + QVirtioDevice *dev = v_iommu->vdev; + QVirtQueue *vq = v_iommu->vq; + uint64_t ro_addr, wr_addr; + uint32_t free_head; + struct virtio_iommu_req_attach req = {}; /* same layout as detach */ + size_t ro_size = sizeof(req) - sizeof(struct virtio_iommu_req_tail); + size_t wr_size = sizeof(struct virtio_iommu_req_tail); + struct virtio_iommu_req_tail buffer; + int ret; + + req.head.type = type; + req.domain = cpu_to_le32(domain); + req.endpoint = cpu_to_le32(ep); + + ro_addr = guest_alloc(alloc, ro_size); + wr_addr = guest_alloc(alloc, wr_size); + + qtest_memwrite(qts, ro_addr, &req, ro_size); + free_head = qvirtqueue_add(qts, vq, ro_addr, ro_size, false, true); + qvirtqueue_add(qts, vq, wr_addr, wr_size, true, false); + qvirtqueue_kick(qts, dev, vq, free_head); + qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL, + QVIRTIO_IOMMU_TIMEOUT_US); + qtest_memread(qts, wr_addr, &buffer, wr_size); + ret = read_tail_status(&buffer); + guest_free(alloc, ro_addr); + guest_free(alloc, wr_addr); + return ret; +} + +/** + * send_map - Send a map command to the device + * @domain: domain the new mapping is attached to + * @virt_start: iova start + * @virt_end: iova end + * @phys_start: base physical address + * @flags: mapping flags + */ +static int send_map(QTestState *qts, QVirtioIOMMU *v_iommu, + uint32_t domain, uint64_t virt_start, uint64_t virt_end, + uint64_t phys_start, uint32_t flags) +{ + QVirtioDevice *dev = v_iommu->vdev; + QVirtQueue *vq = v_iommu->vq; + uint64_t ro_addr, wr_addr; + uint32_t free_head; + struct virtio_iommu_req_map req; + size_t ro_size = sizeof(req) - sizeof(struct virtio_iommu_req_tail); + size_t wr_size = sizeof(struct virtio_iommu_req_tail); + struct virtio_iommu_req_tail buffer; + int ret; + + req.head.type = VIRTIO_IOMMU_T_MAP; + req.domain = cpu_to_le32(domain); + req.virt_start = cpu_to_le64(virt_start); + req.virt_end = cpu_to_le64(virt_end); + req.phys_start = cpu_to_le64(phys_start); + req.flags = cpu_to_le32(flags); + + ro_addr = guest_alloc(alloc, ro_size); + wr_addr = guest_alloc(alloc, wr_size); + + qtest_memwrite(qts, ro_addr, &req, ro_size); + free_head = qvirtqueue_add(qts, vq, ro_addr, ro_size, false, true); + qvirtqueue_add(qts, vq, wr_addr, wr_size, true, false); + qvirtqueue_kick(qts, dev, vq, free_head); + qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL, + QVIRTIO_IOMMU_TIMEOUT_US); + qtest_memread(qts, wr_addr, &buffer, wr_size); + ret = read_tail_status(&buffer); + guest_free(alloc, ro_addr); + guest_free(alloc, wr_addr); + return ret; +} + +/** + * send_unmap - Send an unmap command to the device + * @domain: domain the new binding is attached to + * @virt_start: iova start + * @virt_end: iova end + */ +static int send_unmap(QTestState *qts, QVirtioIOMMU *v_iommu, + uint32_t domain, uint64_t virt_start, uint64_t virt_end) +{ + QVirtioDevice *dev = v_iommu->vdev; + QVirtQueue *vq = v_iommu->vq; + uint64_t ro_addr, wr_addr; + uint32_t free_head; + struct virtio_iommu_req_unmap req; + size_t ro_size = sizeof(req) - sizeof(struct virtio_iommu_req_tail); + size_t wr_size = sizeof(struct virtio_iommu_req_tail); + struct virtio_iommu_req_tail buffer; + int ret; + + req.head.type = VIRTIO_IOMMU_T_UNMAP; + req.domain = cpu_to_le32(domain); + req.virt_start = cpu_to_le64(virt_start); + req.virt_end = cpu_to_le64(virt_end); + + ro_addr = guest_alloc(alloc, ro_size); + wr_addr = guest_alloc(alloc, wr_size); + + qtest_memwrite(qts, ro_addr, &req, ro_size); + free_head = qvirtqueue_add(qts, vq, ro_addr, ro_size, false, true); + qvirtqueue_add(qts, vq, wr_addr, wr_size, true, false); + qvirtqueue_kick(qts, dev, vq, free_head); + qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL, + QVIRTIO_IOMMU_TIMEOUT_US); + qtest_memread(qts, wr_addr, &buffer, wr_size); + ret = read_tail_status(&buffer); + guest_free(alloc, ro_addr); + guest_free(alloc, wr_addr); + return ret; +} + +static void test_attach_detach(void *obj, void *data, QGuestAllocator *t_alloc) +{ + QVirtioIOMMU *v_iommu = obj; + QTestState *qts = global_qtest; + int ret; + + alloc = t_alloc; + + /* type, domain, ep */ + + /* attach ep0 to domain 0 */ + ret = send_attach_detach(qts, v_iommu, VIRTIO_IOMMU_T_ATTACH, 0, 0); + g_assert_cmpint(ret, ==, 0); + + /* attach a non existing device */ + ret = send_attach_detach(qts, v_iommu, VIRTIO_IOMMU_T_ATTACH, 0, 444); + g_assert_cmpint(ret, ==, VIRTIO_IOMMU_S_NOENT); + + /* detach a non existing device (1) */ + ret = send_attach_detach(qts, v_iommu, VIRTIO_IOMMU_T_DETACH, 0, 1); + g_assert_cmpint(ret, ==, VIRTIO_IOMMU_S_NOENT); + + /* move ep0 from domain 0 to domain 1 */ + ret = send_attach_detach(qts, v_iommu, VIRTIO_IOMMU_T_ATTACH, 1, 0); + g_assert_cmpint(ret, ==, 0); + + /* detach ep0 from domain 0 */ + ret = send_attach_detach(qts, v_iommu, VIRTIO_IOMMU_T_DETACH, 0, 0); + g_assert_cmpint(ret, ==, VIRTIO_IOMMU_S_INVAL); + + /* detach ep0 from domain 1 */ + ret = send_attach_detach(qts, v_iommu, VIRTIO_IOMMU_T_DETACH, 1, 0); + g_assert_cmpint(ret, ==, 0); + + ret = send_attach_detach(qts, v_iommu, VIRTIO_IOMMU_T_ATTACH, 1, 0); + g_assert_cmpint(ret, ==, 0); + ret = send_map(qts, v_iommu, 1, 0x0, 0xFFF, 0xa1000, + VIRTIO_IOMMU_MAP_F_READ); + g_assert_cmpint(ret, ==, 0); + ret = send_map(qts, v_iommu, 1, 0x2000, 0x2FFF, 0xb1000, + VIRTIO_IOMMU_MAP_F_READ); + g_assert_cmpint(ret, ==, 0); + ret = send_attach_detach(qts, v_iommu, VIRTIO_IOMMU_T_DETACH, 1, 0); + g_assert_cmpint(ret, ==, 0); +} + +/* Test map/unmap scenari documented in the spec */ +static void test_map_unmap(void *obj, void *data, QGuestAllocator *t_alloc) +{ + QVirtioIOMMU *v_iommu = obj; + QTestState *qts = global_qtest; + int ret; + + alloc = t_alloc; + + /* attach ep0 to domain 1 */ + ret = send_attach_detach(qts, v_iommu, VIRTIO_IOMMU_T_ATTACH, 1, 0); + g_assert_cmpint(ret, ==, 0); + + ret = send_map(qts, v_iommu, 0, 0, 0xFFF, 0xa1000, VIRTIO_IOMMU_MAP_F_READ); + g_assert_cmpint(ret, ==, VIRTIO_IOMMU_S_NOENT); + + /* domain, virt start, virt end, phys start, flags */ + ret = send_map(qts, v_iommu, 1, 0x0, 0xFFF, 0xa1000, VIRTIO_IOMMU_MAP_F_READ); + g_assert_cmpint(ret, ==, 0); + + /* send a new mapping overlapping the previous one */ + ret = send_map(qts, v_iommu, 1, 0, 0xFFFF, 0xb1000, VIRTIO_IOMMU_MAP_F_READ); + g_assert_cmpint(ret, ==, VIRTIO_IOMMU_S_INVAL); + + ret = send_unmap(qts, v_iommu, 4, 0x10, 0xFFF); + g_assert_cmpint(ret, ==, VIRTIO_IOMMU_S_NOENT); + + ret = send_unmap(qts, v_iommu, 1, 0x10, 0xFFF); + g_assert_cmpint(ret, ==, VIRTIO_IOMMU_S_RANGE); + + ret = send_unmap(qts, v_iommu, 1, 0, 0x1000); + g_assert_cmpint(ret, ==, 0); /* unmap everything */ + + /* Spec example sequence */ + + /* 1 */ + ret = send_unmap(qts, v_iommu, 1, 0, 4); + g_assert_cmpint(ret, ==, 0); /* doesn't unmap anything */ + + /* 2 */ + ret = send_map(qts, v_iommu, 1, 0, 9, 0xa1000, VIRTIO_IOMMU_MAP_F_READ); + g_assert_cmpint(ret, ==, 0); + ret = send_unmap(qts, v_iommu, 1, 0, 9); + g_assert_cmpint(ret, ==, 0); /* unmaps [0,9] */ + + /* 3 */ + ret = send_map(qts, v_iommu, 1, 0, 4, 0xb1000, VIRTIO_IOMMU_MAP_F_READ); + g_assert_cmpint(ret, ==, 0); + ret = send_map(qts, v_iommu, 1, 5, 9, 0xb2000, VIRTIO_IOMMU_MAP_F_READ); + g_assert_cmpint(ret, ==, 0); + ret = send_unmap(qts, v_iommu, 1, 0, 9); + g_assert_cmpint(ret, ==, 0); /* unmaps [0,4] and [5,9] */ + + /* 4 */ + ret = send_map(qts, v_iommu, 1, 0, 9, 0xc1000, VIRTIO_IOMMU_MAP_F_READ); + g_assert_cmpint(ret, ==, 0); + + ret = send_unmap(qts, v_iommu, 1, 0, 4); + g_assert_cmpint(ret, ==, VIRTIO_IOMMU_S_RANGE); /* doesn't unmap anything */ + + ret = send_unmap(qts, v_iommu, 1, 0, 10); + g_assert_cmpint(ret, ==, 0); + + /* 5 */ + ret = send_map(qts, v_iommu, 1, 0, 4, 0xd1000, VIRTIO_IOMMU_MAP_F_READ); + g_assert_cmpint(ret, ==, 0); + ret = send_map(qts, v_iommu, 1, 5, 9, 0xd2000, VIRTIO_IOMMU_MAP_F_READ); + g_assert_cmpint(ret, ==, 0); + ret = send_unmap(qts, v_iommu, 1, 0, 4); + g_assert_cmpint(ret, ==, 0); /* unmaps [0,4] */ + + ret = send_unmap(qts, v_iommu, 1, 5, 9); + g_assert_cmpint(ret, ==, 0); + + /* 6 */ + ret = send_map(qts, v_iommu, 1, 0, 4, 0xe2000, VIRTIO_IOMMU_MAP_F_READ); + g_assert_cmpint(ret, ==, 0); + ret = send_unmap(qts, v_iommu, 1, 0, 9); + g_assert_cmpint(ret, ==, 0); /* unmaps [0,4] */ + + /* 7 */ + ret = send_map(qts, v_iommu, 1, 0, 4, 0xf2000, VIRTIO_IOMMU_MAP_F_READ); + g_assert_cmpint(ret, ==, 0); + ret = send_map(qts, v_iommu, 1, 10, 14, 0xf3000, VIRTIO_IOMMU_MAP_F_READ); + g_assert_cmpint(ret, ==, 0); + ret = send_unmap(qts, v_iommu, 1, 0, 14); + g_assert_cmpint(ret, ==, 0); /* unmaps [0,4] and [10,14] */ + + ret = send_map(qts, v_iommu, 1, 10, 14, 0xf3000, VIRTIO_IOMMU_MAP_F_READ); + g_assert_cmpint(ret, ==, 0); + ret = send_map(qts, v_iommu, 1, 0, 4, 0xf2000, VIRTIO_IOMMU_MAP_F_READ); + g_assert_cmpint(ret, ==, 0); + ret = send_unmap(qts, v_iommu, 1, 0, 4); + g_assert_cmpint(ret, ==, 0); /* only unmaps [0,4] */ + ret = send_map(qts, v_iommu, 1, 10, 14, 0xf3000, VIRTIO_IOMMU_MAP_F_READ); + g_assert_cmpint(ret, ==, VIRTIO_IOMMU_S_INVAL); /* 10-14 still is mapped */ +} + +static void register_virtio_iommu_test(void) +{ + qos_add_test("config", "virtio-iommu", pci_config, NULL); + qos_add_test("attach_detach", "virtio-iommu", test_attach_detach, NULL); + qos_add_test("map_unmap", "virtio-iommu", test_map_unmap, NULL); +} + +libqos_init(register_virtio_iommu_test); diff --git a/tests/qtest/virtio-net-failover.c b/tests/qtest/virtio-net-failover.c new file mode 100644 index 0000000000..4b2ba8a106 --- /dev/null +++ b/tests/qtest/virtio-net-failover.c @@ -0,0 +1,1352 @@ +/* + * QTest testcase for virtio-net failover + * + * See docs/system/virtio-net-failover.rst + * + * Copyright (c) 2021 Red Hat, Inc. + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ +#include "qemu/osdep.h" +#include "libqos/libqtest.h" +#include "libqos/pci.h" +#include "libqos/pci-pc.h" +#include "qapi/qmp/qdict.h" +#include "qapi/qmp/qlist.h" +#include "qapi/qmp/qjson.h" +#include "libqos/malloc-pc.h" +#include "libqos/virtio-pci.h" +#include "hw/pci/pci.h" + +#define ACPI_PCIHP_ADDR_ICH9 0x0cc0 +#define PCI_EJ_BASE 0x0008 +#define PCI_SEL_BASE 0x0010 + +#define BASE_MACHINE "-M q35 -nodefaults " \ + "-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 " + +#define MAC_PRIMARY0 "52:54:00:11:11:11" +#define MAC_STANDBY0 "52:54:00:22:22:22" +#define MAC_PRIMARY1 "52:54:00:33:33:33" +#define MAC_STANDBY1 "52:54:00:44:44:44" + +static QGuestAllocator guest_malloc; +static QPCIBus *pcibus; + +static QTestState *machine_start(const char *args, int numbus) +{ + QTestState *qts; + QPCIDevice *dev; + int bus; + + qts = qtest_init(args); + + pc_alloc_init(&guest_malloc, qts, 0); + pcibus = qpci_new_pc(qts, &guest_malloc); + g_assert(qpci_secondary_buses_init(pcibus) == numbus); + + for (bus = 1; bus <= numbus; bus++) { + dev = qpci_device_find(pcibus, QPCI_DEVFN(bus, 0)); + g_assert_nonnull(dev); + + qpci_device_enable(dev); + qpci_iomap(dev, 4, NULL); + + g_free(dev); + } + + return qts; +} + +static void machine_stop(QTestState *qts) +{ + qpci_free_pc(pcibus); + alloc_destroy(&guest_malloc); + qtest_quit(qts); +} + +static void test_error_id(void) +{ + QTestState *qts; + QDict *resp; + QDict *err; + + qts = machine_start(BASE_MACHINE + "-device virtio-net,bus=root0,id=standby0,failover=on", + 2); + + resp = qtest_qmp(qts, "{'execute': 'device_add'," + "'arguments': {" + "'driver': 'virtio-net'," + "'bus': 'root1'," + "'failover_pair_id': 'standby0'" + "} }"); + g_assert(qdict_haskey(resp, "error")); + + err = qdict_get_qdict(resp, "error"); + g_assert(qdict_haskey(err, "desc")); + + g_assert_cmpstr(qdict_get_str(err, "desc"), ==, + "Device with failover_pair_id needs to have id"); + + qobject_unref(resp); + + machine_stop(qts); +} + +static void test_error_pcie(void) +{ + QTestState *qts; + QDict *resp; + QDict *err; + + qts = machine_start(BASE_MACHINE + "-device virtio-net,bus=root0,id=standby0,failover=on", + 2); + + resp = qtest_qmp(qts, "{'execute': 'device_add'," + "'arguments': {" + "'driver': 'virtio-net'," + "'id': 'primary0'," + "'bus': 'pcie.0'," + "'failover_pair_id': 'standby0'" + "} }"); + g_assert(qdict_haskey(resp, "error")); + + err = qdict_get_qdict(resp, "error"); + g_assert(qdict_haskey(err, "desc")); + + g_assert_cmpstr(qdict_get_str(err, "desc"), ==, + "Bus 'pcie.0' does not support hotplugging"); + + qobject_unref(resp); + + machine_stop(qts); +} + +static QDict *find_device(QDict *bus, const char *name) +{ + const QObject *obj; + QList *devices; + QList *list; + + devices = qdict_get_qlist(bus, "devices"); + if (devices == NULL) { + return NULL; + } + + list = qlist_copy(devices); + while ((obj = qlist_pop(list))) { + QDict *device; + + device = qobject_to(QDict, obj); + + if (qdict_haskey(device, "pci_bridge")) { + QDict *bridge; + QDict *bridge_device; + + bridge = qdict_get_qdict(device, "pci_bridge"); + + if (qdict_haskey(bridge, "devices")) { + bridge_device = find_device(bridge, name); + if (bridge_device) { + qobject_unref(device); + qobject_unref(list); + return bridge_device; + } + } + } + + if (!qdict_haskey(device, "qdev_id")) { + qobject_unref(device); + continue; + } + + if (strcmp(qdict_get_str(device, "qdev_id"), name) == 0) { + qobject_unref(list); + return device; + } + qobject_unref(device); + } + qobject_unref(list); + + return NULL; +} + +static QDict *get_bus(QTestState *qts, int num) +{ + QObject *obj; + QDict *resp; + QList *ret; + + resp = qtest_qmp(qts, "{ 'execute': 'query-pci' }"); + g_assert(qdict_haskey(resp, "return")); + + ret = qdict_get_qlist(resp, "return"); + g_assert_nonnull(ret); + + while ((obj = qlist_pop(ret))) { + QDict *bus; + + bus = qobject_to(QDict, obj); + if (!qdict_haskey(bus, "bus")) { + qobject_unref(bus); + continue; + } + if (qdict_get_int(bus, "bus") == num) { + qobject_unref(resp); + return bus; + } + qobject_ref(bus); + } + qobject_unref(resp); + + return NULL; +} + +static char *get_mac(QTestState *qts, const char *name) +{ + QDict *resp; + char *mac; + + resp = qtest_qmp(qts, "{ 'execute': 'qom-get', " + "'arguments': { " + "'path': %s, " + "'property': 'mac' } }", name); + + g_assert(qdict_haskey(resp, "return")); + + mac = g_strdup(qdict_get_str(resp, "return")); + + qobject_unref(resp); + + return mac; +} + +static void check_one_card(QTestState *qts, bool present, + const char *id, const char *mac) +{ + QDict *device; + QDict *bus; + char *addr; + + bus = get_bus(qts, 0); + device = find_device(bus, id); + if (present) { + char *path; + + g_assert_nonnull(device); + qobject_unref(device); + + path = g_strdup_printf("/machine/peripheral/%s", id); + addr = get_mac(qts, path); + g_free(path); + g_assert_cmpstr(mac, ==, addr); + g_free(addr); + } else { + g_assert_null(device); + } + + qobject_unref(bus); +} + +static void test_on(void) +{ + QTestState *qts; + + qts = machine_start(BASE_MACHINE + "-netdev user,id=hs0 " + "-device virtio-net,bus=root0,id=standby0," + "failover=on,netdev=hs0,mac="MAC_STANDBY0" " + "-device virtio-net,bus=root1,id=primary0," + "failover_pair_id=standby0,netdev=hs1,mac="MAC_PRIMARY0, + 2); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, false, "primary0", MAC_PRIMARY0); + + machine_stop(qts); +} + +static void test_on_mismatch(void) +{ + QTestState *qts; + + qts = machine_start(BASE_MACHINE + "-netdev user,id=hs0 " + "-device virtio-net,bus=root0,id=standby0," + "failover=on,netdev=hs0,mac="MAC_STANDBY0" " + "-netdev user,id=hs1 " + "-device virtio-net,bus=root1,id=primary0," + "failover_pair_id=standby1,netdev=hs1,mac="MAC_PRIMARY0, + 2); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, true, "primary0", MAC_PRIMARY0); + + machine_stop(qts); +} + +static void test_off(void) +{ + QTestState *qts; + + qts = machine_start(BASE_MACHINE + "-netdev user,id=hs0 " + "-device virtio-net,bus=root0,id=standby0," + "failover=off,netdev=hs0,mac="MAC_STANDBY0" " + "-netdev user,id=hs1 " + "-device virtio-net,bus=root1,id=primary0," + "failover_pair_id=standby0,netdev=hs1,mac="MAC_PRIMARY0, + 2); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, true, "primary0", MAC_PRIMARY0); + + machine_stop(qts); +} + +static QDict *get_failover_negociated_event(QTestState *qts) +{ + QDict *resp; + QDict *data; + + resp = qtest_qmp_eventwait_ref(qts, "FAILOVER_NEGOTIATED"); + g_assert(qdict_haskey(resp, "data")); + + data = qdict_get_qdict(resp, "data"); + g_assert(qdict_haskey(data, "device-id")); + qobject_ref(data); + qobject_unref(resp); + + return data; +} + +static QVirtioPCIDevice *start_virtio_net(QTestState *qts, int bus, int slot, + const char *id) +{ + QVirtioPCIDevice *dev; + uint64_t features; + QPCIAddress addr; + QDict *resp; + + addr.devfn = QPCI_DEVFN((bus << 5) + slot, 0); + dev = virtio_pci_new(pcibus, &addr); + g_assert_nonnull(dev); + qvirtio_pci_device_enable(dev); + qvirtio_start_device(&dev->vdev); + features = qvirtio_get_features(&dev->vdev); + features = features & ~(QVIRTIO_F_BAD_FEATURE | + (1ull << VIRTIO_RING_F_INDIRECT_DESC) | + (1ull << VIRTIO_RING_F_EVENT_IDX)); + qvirtio_set_features(&dev->vdev, features); + qvirtio_set_driver_ok(&dev->vdev); + + resp = get_failover_negociated_event(qts); + g_assert_cmpstr(qdict_get_str(resp, "device-id"), ==, id); + qobject_unref(resp); + + return dev; +} + +static void test_enabled(void) +{ + QTestState *qts; + QVirtioPCIDevice *vdev; + + qts = machine_start(BASE_MACHINE + "-netdev user,id=hs0 " + "-device virtio-net,bus=root0,id=standby0," + "failover=on,netdev=hs0,mac="MAC_STANDBY0" " + "-netdev user,id=hs1 " + "-device virtio-net,bus=root1,id=primary0," + "failover_pair_id=standby0,netdev=hs1,mac="MAC_PRIMARY0" ", + 2); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, false, "primary0", MAC_PRIMARY0); + + vdev = start_virtio_net(qts, 1, 0, "standby0"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, true, "primary0", MAC_PRIMARY0); + + qos_object_destroy((QOSGraphObject *)vdev); + machine_stop(qts); +} + +static void test_hotplug_1(void) +{ + QTestState *qts; + QVirtioPCIDevice *vdev; + + qts = machine_start(BASE_MACHINE + "-netdev user,id=hs0 " + "-device virtio-net,bus=root0,id=standby0," + "failover=on,netdev=hs0,mac="MAC_STANDBY0" " + "-netdev user,id=hs1 ", 2); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, false, "primary0", MAC_PRIMARY0); + + vdev = start_virtio_net(qts, 1, 0, "standby0"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, false, "primary0", MAC_PRIMARY0); + + qtest_qmp_device_add(qts, "virtio-net", "primary0", + "{'bus': 'root1'," + "'failover_pair_id': 'standby0'," + "'netdev': 'hs1'," + "'mac': '"MAC_PRIMARY0"'}"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, true, "primary0", MAC_PRIMARY0); + + qos_object_destroy((QOSGraphObject *)vdev); + machine_stop(qts); +} + +static void test_hotplug_1_reverse(void) +{ + QTestState *qts; + QVirtioPCIDevice *vdev; + + qts = machine_start(BASE_MACHINE + "-netdev user,id=hs0 " + "-netdev user,id=hs1 " + "-device virtio-net,bus=root1,id=primary0," + "failover_pair_id=standby0,netdev=hs1,mac="MAC_PRIMARY0" ", + 2); + + check_one_card(qts, false, "standby0", MAC_STANDBY0); + check_one_card(qts, true, "primary0", MAC_PRIMARY0); + + qtest_qmp_device_add(qts, "virtio-net", "standby0", + "{'bus': 'root0'," + "'failover': 'on'," + "'netdev': 'hs0'," + "'mac': '"MAC_STANDBY0"'}"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, true, "primary0", MAC_PRIMARY0); + + vdev = start_virtio_net(qts, 1, 0, "standby0"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, true, "primary0", MAC_PRIMARY0); + + qos_object_destroy((QOSGraphObject *)vdev); + machine_stop(qts); +} + +static void test_hotplug_2(void) +{ + QTestState *qts; + QVirtioPCIDevice *vdev; + + qts = machine_start(BASE_MACHINE + "-netdev user,id=hs0 " + "-netdev user,id=hs1 ", + 2); + + check_one_card(qts, false, "standby0", MAC_STANDBY0); + check_one_card(qts, false, "primary0", MAC_PRIMARY0); + + qtest_qmp_device_add(qts, "virtio-net", "standby0", + "{'bus': 'root0'," + "'failover': 'on'," + "'netdev': 'hs0'," + "'mac': '"MAC_STANDBY0"'}"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, false, "primary0", MAC_PRIMARY0); + + vdev = start_virtio_net(qts, 1, 0, "standby0"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, false, "primary0", MAC_PRIMARY0); + + qtest_qmp_device_add(qts, "virtio-net", "primary0", + "{'bus': 'root1'," + "'failover_pair_id': 'standby0'," + "'netdev': 'hs1'," + "'mac': '"MAC_PRIMARY0"'}"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, true, "primary0", MAC_PRIMARY0); + + qos_object_destroy((QOSGraphObject *)vdev); + machine_stop(qts); +} + +static void test_hotplug_2_reverse(void) +{ + QTestState *qts; + QVirtioPCIDevice *vdev; + + qts = machine_start(BASE_MACHINE + "-netdev user,id=hs0 " + "-netdev user,id=hs1 ", + 2); + + check_one_card(qts, false, "standby0", MAC_STANDBY0); + check_one_card(qts, false, "primary0", MAC_PRIMARY0); + + qtest_qmp_device_add(qts, "virtio-net", "primary0", + "{'bus': 'root1'," + "'failover_pair_id': 'standby0'," + "'netdev': 'hs1'," + "'mac': '"MAC_PRIMARY0"'}"); + + check_one_card(qts, false, "standby0", MAC_STANDBY0); + check_one_card(qts, true, "primary0", MAC_PRIMARY0); + + qtest_qmp_device_add(qts, "virtio-net", "standby0", + "{'bus': 'root0'," + "'failover': 'on'," + "'netdev': 'hs0'," + "'rombar': 0," + "'romfile': ''," + "'mac': '"MAC_STANDBY0"'}"); + + /* + * XXX: sounds like a bug: + * The primary should be hidden until the virtio-net driver + * negotiates the VIRTIO_NET_F_STANDBY feature by start_virtio_net() + */ + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, true, "primary0", MAC_PRIMARY0); + + vdev = start_virtio_net(qts, 1, 0, "standby0"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, true, "primary0", MAC_PRIMARY0); + + qos_object_destroy((QOSGraphObject *)vdev); + machine_stop(qts); +} + +static QDict *migrate_status(QTestState *qts) +{ + QDict *resp, *ret; + + resp = qtest_qmp(qts, "{ 'execute': 'query-migrate' }"); + g_assert(qdict_haskey(resp, "return")); + + ret = qdict_get_qdict(resp, "return"); + g_assert(qdict_haskey(ret, "status")); + qobject_ref(ret); + qobject_unref(resp); + + return ret; +} + +static QDict *get_unplug_primary_event(QTestState *qts) +{ + QDict *resp; + QDict *data; + + resp = qtest_qmp_eventwait_ref(qts, "UNPLUG_PRIMARY"); + g_assert(qdict_haskey(resp, "data")); + + data = qdict_get_qdict(resp, "data"); + g_assert(qdict_haskey(data, "device-id")); + qobject_ref(data); + qobject_unref(resp); + + return data; +} + +static void test_migrate_out(gconstpointer opaque) +{ + QTestState *qts; + QDict *resp, *args, *ret; + g_autofree gchar *uri = g_strdup_printf("exec: cat > %s", (gchar *)opaque); + const gchar *status; + QVirtioPCIDevice *vdev; + + qts = machine_start(BASE_MACHINE + "-netdev user,id=hs0 " + "-netdev user,id=hs1 ", + 2); + + check_one_card(qts, false, "standby0", MAC_STANDBY0); + check_one_card(qts, false, "primary0", MAC_PRIMARY0); + + qtest_qmp_device_add(qts, "virtio-net", "standby0", + "{'bus': 'root0'," + "'failover': 'on'," + "'netdev': 'hs0'," + "'mac': '"MAC_STANDBY0"'}"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, false, "primary0", MAC_PRIMARY0); + + vdev = start_virtio_net(qts, 1, 0, "standby0"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, false, "primary0", MAC_PRIMARY0); + + qtest_qmp_device_add(qts, "virtio-net", "primary0", + "{'bus': 'root1'," + "'failover_pair_id': 'standby0'," + "'netdev': 'hs1'," + "'rombar': 0," + "'romfile': ''," + "'mac': '"MAC_PRIMARY0"'}"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, true, "primary0", MAC_PRIMARY0); + + args = qdict_from_jsonf_nofail("{}"); + g_assert_nonnull(args); + qdict_put_str(args, "uri", uri); + + resp = qtest_qmp(qts, "{ 'execute': 'migrate', 'arguments': %p}", args); + g_assert(qdict_haskey(resp, "return")); + qobject_unref(resp); + + /* the event is sent when QEMU asks the OS to unplug the card */ + resp = get_unplug_primary_event(qts); + g_assert_cmpstr(qdict_get_str(resp, "device-id"), ==, "primary0"); + qobject_unref(resp); + + /* wait the end of the migration setup phase */ + while (true) { + ret = migrate_status(qts); + + status = qdict_get_str(ret, "status"); + if (strcmp(status, "wait-unplug") == 0) { + qobject_unref(ret); + break; + } + + /* The migration must not start if the card is not ejected */ + g_assert_cmpstr(status, !=, "active"); + g_assert_cmpstr(status, !=, "completed"); + g_assert_cmpstr(status, !=, "failed"); + g_assert_cmpstr(status, !=, "cancelling"); + g_assert_cmpstr(status, !=, "cancelled"); + + qobject_unref(ret); + } + + if (g_test_slow()) { + /* check we stay in wait-unplug while the card is not ejected */ + for (int i = 0; i < 5; i++) { + sleep(1); + ret = migrate_status(qts); + status = qdict_get_str(ret, "status"); + g_assert_cmpstr(status, ==, "wait-unplug"); + qobject_unref(ret); + } + } + + /* OS unplugs the cards, QEMU can move from wait-unplug state */ + qtest_outl(qts, ACPI_PCIHP_ADDR_ICH9 + PCI_EJ_BASE, 1); + + while (true) { + ret = migrate_status(qts); + + status = qdict_get_str(ret, "status"); + if (strcmp(status, "completed") == 0) { + qobject_unref(ret); + break; + } + g_assert_cmpstr(status, !=, "failed"); + g_assert_cmpstr(status, !=, "cancelling"); + g_assert_cmpstr(status, !=, "cancelled"); + qobject_unref(ret); + } + + qtest_qmp_eventwait(qts, "STOP"); + + /* + * in fact, the card is ejected from the point of view of kernel + * but not really from QEMU to be able to hotplug it back if + * migration fails. So we can't check that: + * check_one_card(qts, true, "standby0", MAC_STANDBY0); + * check_one_card(qts, false, "primary0", MAC_PRIMARY0); + */ + + qos_object_destroy((QOSGraphObject *)vdev); + machine_stop(qts); +} + +static QDict *get_migration_event(QTestState *qts) +{ + QDict *resp; + QDict *data; + + resp = qtest_qmp_eventwait_ref(qts, "MIGRATION"); + g_assert(qdict_haskey(resp, "data")); + + data = qdict_get_qdict(resp, "data"); + g_assert(qdict_haskey(data, "status")); + qobject_ref(data); + qobject_unref(resp); + + return data; +} + +static void test_migrate_in(gconstpointer opaque) +{ + QTestState *qts; + QDict *resp, *args, *ret; + g_autofree gchar *uri = g_strdup_printf("exec: cat %s", (gchar *)opaque); + + qts = machine_start(BASE_MACHINE + "-netdev user,id=hs0 " + "-netdev user,id=hs1 " + "-incoming defer ", + 2); + + check_one_card(qts, false, "standby0", MAC_STANDBY0); + check_one_card(qts, false, "primary0", MAC_PRIMARY0); + + qtest_qmp_device_add(qts, "virtio-net", "standby0", + "{'bus': 'root0'," + "'failover': 'on'," + "'netdev': 'hs0'," + "'mac': '"MAC_STANDBY0"'}"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, false, "primary0", MAC_PRIMARY0); + + qtest_qmp_device_add(qts, "virtio-net", "primary0", + "{'bus': 'root1'," + "'failover_pair_id': 'standby0'," + "'netdev': 'hs1'," + "'rombar': 0," + "'romfile': ''," + "'mac': '"MAC_PRIMARY0"'}"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, false, "primary0", MAC_PRIMARY0); + + args = qdict_from_jsonf_nofail("{}"); + g_assert_nonnull(args); + qdict_put_str(args, "uri", uri); + + resp = qtest_qmp(qts, "{ 'execute': 'migrate-incoming', 'arguments': %p}", + args); + g_assert(qdict_haskey(resp, "return")); + qobject_unref(resp); + + resp = get_migration_event(qts); + g_assert_cmpstr(qdict_get_str(resp, "status"), ==, "setup"); + qobject_unref(resp); + + resp = get_failover_negociated_event(qts); + g_assert_cmpstr(qdict_get_str(resp, "device-id"), ==, "standby0"); + qobject_unref(resp); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, true, "primary0", MAC_PRIMARY0); + + qtest_qmp_eventwait(qts, "RESUME"); + + ret = migrate_status(qts); + g_assert_cmpstr(qdict_get_str(ret, "status"), ==, "completed"); + qobject_unref(ret); + + machine_stop(qts); +} + +static void test_migrate_abort_wait_unplug(gconstpointer opaque) +{ + QTestState *qts; + QDict *resp, *args, *ret; + g_autofree gchar *uri = g_strdup_printf("exec: cat > %s", (gchar *)opaque); + const gchar *status; + QVirtioPCIDevice *vdev; + + qts = machine_start(BASE_MACHINE + "-netdev user,id=hs0 " + "-netdev user,id=hs1 ", + 2); + + check_one_card(qts, false, "standby0", MAC_STANDBY0); + check_one_card(qts, false, "primary0", MAC_PRIMARY0); + + qtest_qmp_device_add(qts, "virtio-net", "standby0", + "{'bus': 'root0'," + "'failover': 'on'," + "'netdev': 'hs0'," + "'mac': '"MAC_STANDBY0"'}"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, false, "primary0", MAC_PRIMARY0); + + vdev = start_virtio_net(qts, 1, 0, "standby0"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, false, "primary0", MAC_PRIMARY0); + + qtest_qmp_device_add(qts, "virtio-net", "primary0", + "{'bus': 'root1'," + "'failover_pair_id': 'standby0'," + "'netdev': 'hs1'," + "'rombar': 0," + "'romfile': ''," + "'mac': '"MAC_PRIMARY0"'}"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, true, "primary0", MAC_PRIMARY0); + + args = qdict_from_jsonf_nofail("{}"); + g_assert_nonnull(args); + qdict_put_str(args, "uri", uri); + + resp = qtest_qmp(qts, "{ 'execute': 'migrate', 'arguments': %p}", args); + g_assert(qdict_haskey(resp, "return")); + qobject_unref(resp); + + /* the event is sent when QEMU asks the OS to unplug the card */ + resp = get_unplug_primary_event(qts); + g_assert_cmpstr(qdict_get_str(resp, "device-id"), ==, "primary0"); + qobject_unref(resp); + + resp = qtest_qmp(qts, "{ 'execute': 'migrate_cancel' }"); + g_assert(qdict_haskey(resp, "return")); + qobject_unref(resp); + + /* migration has been cancelled while the unplug was in progress */ + + /* while the card is not ejected, we must be in "cancelling" state */ + ret = migrate_status(qts); + + status = qdict_get_str(ret, "status"); + g_assert_cmpstr(status, ==, "cancelling"); + qobject_unref(ret); + + /* OS unplugs the cards, QEMU can move from wait-unplug state */ + qtest_outl(qts, ACPI_PCIHP_ADDR_ICH9 + PCI_EJ_BASE, 1); + + while (true) { + ret = migrate_status(qts); + + status = qdict_get_str(ret, "status"); + if (strcmp(status, "cancelled") == 0) { + qobject_unref(ret); + break; + } + g_assert_cmpstr(status, !=, "failed"); + g_assert_cmpstr(status, !=, "active"); + qobject_unref(ret); + } + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, true, "primary0", MAC_PRIMARY0); + + qos_object_destroy((QOSGraphObject *)vdev); + machine_stop(qts); +} + +static void test_migrate_abort_active(gconstpointer opaque) +{ + QTestState *qts; + QDict *resp, *args, *ret; + g_autofree gchar *uri = g_strdup_printf("exec: cat > %s", (gchar *)opaque); + const gchar *status; + QVirtioPCIDevice *vdev; + + qts = machine_start(BASE_MACHINE + "-netdev user,id=hs0 " + "-netdev user,id=hs1 ", + 2); + + check_one_card(qts, false, "standby0", MAC_STANDBY0); + check_one_card(qts, false, "primary0", MAC_PRIMARY0); + + qtest_qmp_device_add(qts, "virtio-net", "standby0", + "{'bus': 'root0'," + "'failover': 'on'," + "'netdev': 'hs0'," + "'mac': '"MAC_STANDBY0"'}"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, false, "primary0", MAC_PRIMARY0); + + vdev = start_virtio_net(qts, 1, 0, "standby0"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, false, "primary0", MAC_PRIMARY0); + + qtest_qmp_device_add(qts, "virtio-net", "primary0", + "{'bus': 'root1'," + "'failover_pair_id': 'standby0'," + "'netdev': 'hs1'," + "'rombar': 0," + "'romfile': ''," + "'mac': '"MAC_PRIMARY0"'}"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, true, "primary0", MAC_PRIMARY0); + + args = qdict_from_jsonf_nofail("{}"); + g_assert_nonnull(args); + qdict_put_str(args, "uri", uri); + + resp = qtest_qmp(qts, "{ 'execute': 'migrate', 'arguments': %p}", args); + g_assert(qdict_haskey(resp, "return")); + qobject_unref(resp); + + /* the event is sent when QEMU asks the OS to unplug the card */ + resp = get_unplug_primary_event(qts); + g_assert_cmpstr(qdict_get_str(resp, "device-id"), ==, "primary0"); + qobject_unref(resp); + + /* OS unplugs the cards, QEMU can move from wait-unplug state */ + qtest_outl(qts, ACPI_PCIHP_ADDR_ICH9 + PCI_EJ_BASE, 1); + + while (true) { + ret = migrate_status(qts); + + status = qdict_get_str(ret, "status"); + if (strcmp(status, "wait-unplug") != 0) { + qobject_unref(ret); + break; + } + g_assert_cmpstr(status, !=, "failed"); + qobject_unref(ret); + } + + resp = qtest_qmp(qts, "{ 'execute': 'migrate_cancel' }"); + g_assert(qdict_haskey(resp, "return")); + qobject_unref(resp); + + while (true) { + ret = migrate_status(qts); + + status = qdict_get_str(ret, "status"); + if (strcmp(status, "cancelled") == 0) { + qobject_unref(ret); + break; + } + g_assert_cmpstr(status, !=, "failed"); + g_assert_cmpstr(status, !=, "active"); + qobject_unref(ret); + } + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, true, "primary0", MAC_PRIMARY0); + + qos_object_destroy((QOSGraphObject *)vdev); + machine_stop(qts); +} + +static void test_migrate_abort_timeout(gconstpointer opaque) +{ + QTestState *qts; + QDict *resp, *args, *ret; + g_autofree gchar *uri = g_strdup_printf("exec: cat > %s", (gchar *)opaque); + const gchar *status; + int total; + QVirtioPCIDevice *vdev; + + qts = machine_start(BASE_MACHINE + "-netdev user,id=hs0 " + "-netdev user,id=hs1 ", + 2); + + check_one_card(qts, false, "standby0", MAC_STANDBY0); + check_one_card(qts, false, "primary0", MAC_PRIMARY0); + + qtest_qmp_device_add(qts, "virtio-net", "standby0", + "{'bus': 'root0'," + "'failover': 'on'," + "'netdev': 'hs0'," + "'mac': '"MAC_STANDBY0"'}"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, false, "primary0", MAC_PRIMARY0); + + vdev = start_virtio_net(qts, 1, 0, "standby0"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, false, "primary0", MAC_PRIMARY0); + + qtest_qmp_device_add(qts, "virtio-net", "primary0", + "{'bus': 'root1'," + "'failover_pair_id': 'standby0'," + "'netdev': 'hs1'," + "'rombar': 0," + "'romfile': ''," + "'mac': '"MAC_PRIMARY0"'}"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, true, "primary0", MAC_PRIMARY0); + + args = qdict_from_jsonf_nofail("{}"); + g_assert_nonnull(args); + qdict_put_str(args, "uri", uri); + + resp = qtest_qmp(qts, "{ 'execute': 'migrate', 'arguments': %p}", args); + g_assert(qdict_haskey(resp, "return")); + qobject_unref(resp); + + /* the event is sent when QEMU asks the OS to unplug the card */ + resp = get_unplug_primary_event(qts); + g_assert_cmpstr(qdict_get_str(resp, "device-id"), ==, "primary0"); + qobject_unref(resp); + + resp = qtest_qmp(qts, "{ 'execute': 'migrate_cancel' }"); + g_assert(qdict_haskey(resp, "return")); + qobject_unref(resp); + + /* migration has been cancelled while the unplug was in progress */ + + /* while the card is not ejected, we must be in "cancelling" state */ + + total = 0; + while (true) { + ret = migrate_status(qts); + + status = qdict_get_str(ret, "status"); + if (strcmp(status, "cancelled") == 0) { + qobject_unref(ret); + break; + } + g_assert_cmpstr(status, ==, "cancelling"); + g_assert(qdict_haskey(ret, "total-time")); + total = qdict_get_int(ret, "total-time"); + qobject_unref(ret); + } + + /* + * migration timeout in this case is 30 seconds + * check we exit on the timeout (ms) + */ + g_assert_cmpint(total, >, 30000); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, true, "primary0", MAC_PRIMARY0); + + qos_object_destroy((QOSGraphObject *)vdev); + machine_stop(qts); +} + +static void test_multi_out(gconstpointer opaque) +{ + QTestState *qts; + QDict *resp, *args, *ret; + g_autofree gchar *uri = g_strdup_printf("exec: cat > %s", (gchar *)opaque); + const gchar *status, *expected; + QVirtioPCIDevice *vdev0, *vdev1; + + qts = machine_start(BASE_MACHINE + "-device pcie-root-port,id=root2,addr=0x3,bus=pcie.0,chassis=3 " + "-device pcie-root-port,id=root3,addr=0x4,bus=pcie.0,chassis=4 " + "-netdev user,id=hs0 " + "-netdev user,id=hs1 " + "-netdev user,id=hs2 " + "-netdev user,id=hs3 ", + 4); + + check_one_card(qts, false, "standby0", MAC_STANDBY0); + check_one_card(qts, false, "primary0", MAC_PRIMARY0); + check_one_card(qts, false, "standby1", MAC_STANDBY1); + check_one_card(qts, false, "primary1", MAC_PRIMARY1); + + qtest_qmp_device_add(qts, "virtio-net", "standby0", + "{'bus': 'root0'," + "'failover': 'on'," + "'netdev': 'hs0'," + "'mac': '"MAC_STANDBY0"'}"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, false, "primary0", MAC_PRIMARY0); + check_one_card(qts, false, "standby1", MAC_STANDBY1); + check_one_card(qts, false, "primary1", MAC_PRIMARY1); + + qtest_qmp_device_add(qts, "virtio-net", "primary0", + "{'bus': 'root1'," + "'failover_pair_id': 'standby0'," + "'netdev': 'hs1'," + "'rombar': 0," + "'romfile': ''," + "'mac': '"MAC_PRIMARY0"'}"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, false, "primary0", MAC_PRIMARY0); + check_one_card(qts, false, "standby1", MAC_STANDBY1); + check_one_card(qts, false, "primary1", MAC_PRIMARY1); + + vdev0 = start_virtio_net(qts, 1, 0, "standby0"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, true, "primary0", MAC_PRIMARY0); + check_one_card(qts, false, "standby1", MAC_STANDBY1); + check_one_card(qts, false, "primary1", MAC_PRIMARY1); + + qtest_qmp_device_add(qts, "virtio-net", "standby1", + "{'bus': 'root2'," + "'failover': 'on'," + "'netdev': 'hs2'," + "'mac': '"MAC_STANDBY1"'}"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, true, "primary0", MAC_PRIMARY0); + check_one_card(qts, true, "standby1", MAC_STANDBY1); + check_one_card(qts, false, "primary1", MAC_PRIMARY1); + + qtest_qmp_device_add(qts, "virtio-net", "primary1", + "{'bus': 'root3'," + "'failover_pair_id': 'standby1'," + "'netdev': 'hs3'," + "'rombar': 0," + "'romfile': ''," + "'mac': '"MAC_PRIMARY1"'}"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, true, "primary0", MAC_PRIMARY0); + check_one_card(qts, true, "standby1", MAC_STANDBY1); + check_one_card(qts, false, "primary1", MAC_PRIMARY1); + + vdev1 = start_virtio_net(qts, 3, 0, "standby1"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, true, "primary0", MAC_PRIMARY0); + check_one_card(qts, true, "standby1", MAC_STANDBY1); + check_one_card(qts, true, "primary1", MAC_PRIMARY1); + + args = qdict_from_jsonf_nofail("{}"); + g_assert_nonnull(args); + qdict_put_str(args, "uri", uri); + + resp = qtest_qmp(qts, "{ 'execute': 'migrate', 'arguments': %p}", args); + g_assert(qdict_haskey(resp, "return")); + qobject_unref(resp); + + /* the event is sent when QEMU asks the OS to unplug the card */ + resp = get_unplug_primary_event(qts); + if (strcmp(qdict_get_str(resp, "device-id"), "primary0") == 0) { + expected = "primary1"; + } else if (strcmp(qdict_get_str(resp, "device-id"), "primary1") == 0) { + expected = "primary0"; + } else { + g_assert_not_reached(); + } + qobject_unref(resp); + + resp = get_unplug_primary_event(qts); + g_assert_cmpstr(qdict_get_str(resp, "device-id"), ==, expected); + qobject_unref(resp); + + /* wait the end of the migration setup phase */ + while (true) { + ret = migrate_status(qts); + + status = qdict_get_str(ret, "status"); + if (strcmp(status, "wait-unplug") == 0) { + qobject_unref(ret); + break; + } + + /* The migration must not start if the card is not ejected */ + g_assert_cmpstr(status, !=, "active"); + g_assert_cmpstr(status, !=, "completed"); + g_assert_cmpstr(status, !=, "failed"); + g_assert_cmpstr(status, !=, "cancelling"); + g_assert_cmpstr(status, !=, "cancelled"); + + qobject_unref(ret); + } + + /* OS unplugs primary1, but we must wait the second */ + qtest_outl(qts, ACPI_PCIHP_ADDR_ICH9 + PCI_EJ_BASE, 1); + + ret = migrate_status(qts); + status = qdict_get_str(ret, "status"); + g_assert_cmpstr(status, ==, "wait-unplug"); + qobject_unref(ret); + + if (g_test_slow()) { + /* check we stay in wait-unplug while the card is not ejected */ + for (int i = 0; i < 5; i++) { + sleep(1); + ret = migrate_status(qts); + status = qdict_get_str(ret, "status"); + g_assert_cmpstr(status, ==, "wait-unplug"); + qobject_unref(ret); + } + } + + /* OS unplugs primary0, QEMU can move from wait-unplug state */ + qtest_outl(qts, ACPI_PCIHP_ADDR_ICH9 + PCI_SEL_BASE, 2); + qtest_outl(qts, ACPI_PCIHP_ADDR_ICH9 + PCI_EJ_BASE, 1); + + while (true) { + ret = migrate_status(qts); + + status = qdict_get_str(ret, "status"); + if (strcmp(status, "completed") == 0) { + qobject_unref(ret); + break; + } + g_assert_cmpstr(status, !=, "failed"); + g_assert_cmpstr(status, !=, "cancelling"); + g_assert_cmpstr(status, !=, "cancelled"); + qobject_unref(ret); + } + + qtest_qmp_eventwait(qts, "STOP"); + + qos_object_destroy((QOSGraphObject *)vdev0); + qos_object_destroy((QOSGraphObject *)vdev1); + machine_stop(qts); +} + +static void test_multi_in(gconstpointer opaque) +{ + QTestState *qts; + QDict *resp, *args, *ret; + g_autofree gchar *uri = g_strdup_printf("exec: cat %s", (gchar *)opaque); + + qts = machine_start(BASE_MACHINE + "-device pcie-root-port,id=root2,addr=0x3,bus=pcie.0,chassis=3 " + "-device pcie-root-port,id=root3,addr=0x4,bus=pcie.0,chassis=4 " + "-netdev user,id=hs0 " + "-netdev user,id=hs1 " + "-netdev user,id=hs2 " + "-netdev user,id=hs3 " + "-incoming defer ", + 4); + + check_one_card(qts, false, "standby0", MAC_STANDBY0); + check_one_card(qts, false, "primary0", MAC_PRIMARY0); + check_one_card(qts, false, "standby1", MAC_STANDBY1); + check_one_card(qts, false, "primary1", MAC_PRIMARY1); + + qtest_qmp_device_add(qts, "virtio-net", "standby0", + "{'bus': 'root0'," + "'failover': 'on'," + "'netdev': 'hs0'," + "'mac': '"MAC_STANDBY0"'}"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, false, "primary0", MAC_PRIMARY0); + check_one_card(qts, false, "standby1", MAC_STANDBY1); + check_one_card(qts, false, "primary1", MAC_PRIMARY1); + + qtest_qmp_device_add(qts, "virtio-net", "primary0", + "{'bus': 'root1'," + "'failover_pair_id': 'standby0'," + "'netdev': 'hs1'," + "'rombar': 0," + "'romfile': ''," + "'mac': '"MAC_PRIMARY0"'}"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, false, "primary0", MAC_PRIMARY0); + check_one_card(qts, false, "standby1", MAC_STANDBY1); + check_one_card(qts, false, "primary1", MAC_PRIMARY1); + + qtest_qmp_device_add(qts, "virtio-net", "standby1", + "{'bus': 'root2'," + "'failover': 'on'," + "'netdev': 'hs2'," + "'mac': '"MAC_STANDBY1"'}"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, false, "primary0", MAC_PRIMARY0); + check_one_card(qts, true, "standby1", MAC_STANDBY1); + check_one_card(qts, false, "primary1", MAC_PRIMARY1); + + qtest_qmp_device_add(qts, "virtio-net", "primary1", + "{'bus': 'root3'," + "'failover_pair_id': 'standby1'," + "'netdev': 'hs3'," + "'rombar': 0," + "'romfile': ''," + "'mac': '"MAC_PRIMARY1"'}"); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, false, "primary0", MAC_PRIMARY0); + check_one_card(qts, true, "standby1", MAC_STANDBY1); + check_one_card(qts, false, "primary1", MAC_PRIMARY1); + + args = qdict_from_jsonf_nofail("{}"); + g_assert_nonnull(args); + qdict_put_str(args, "uri", uri); + + resp = qtest_qmp(qts, "{ 'execute': 'migrate-incoming', 'arguments': %p}", + args); + g_assert(qdict_haskey(resp, "return")); + qobject_unref(resp); + + resp = get_migration_event(qts); + g_assert_cmpstr(qdict_get_str(resp, "status"), ==, "setup"); + qobject_unref(resp); + + resp = get_failover_negociated_event(qts); + g_assert_cmpstr(qdict_get_str(resp, "device-id"), ==, "standby0"); + qobject_unref(resp); + + resp = get_failover_negociated_event(qts); + g_assert_cmpstr(qdict_get_str(resp, "device-id"), ==, "standby1"); + qobject_unref(resp); + + check_one_card(qts, true, "standby0", MAC_STANDBY0); + check_one_card(qts, true, "primary0", MAC_PRIMARY0); + check_one_card(qts, true, "standby1", MAC_STANDBY1); + check_one_card(qts, true, "primary1", MAC_PRIMARY1); + + qtest_qmp_eventwait(qts, "RESUME"); + + ret = migrate_status(qts); + g_assert_cmpstr(qdict_get_str(ret, "status"), ==, "completed"); + qobject_unref(ret); + + machine_stop(qts); +} + +int main(int argc, char **argv) +{ + const gchar *tmpdir = g_get_tmp_dir(); + gchar *tmpfile = g_strdup_printf("%s/failover_test_migrate-%u-%u", + tmpdir, getpid(), g_test_rand_int()); + int ret; + + g_test_init(&argc, &argv, NULL); + + qtest_add_func("failover-virtio-net/params/error/id", test_error_id); + qtest_add_func("failover-virtio-net/params/error/pcie", test_error_pcie); + qtest_add_func("failover-virtio-net/params/on", test_on); + qtest_add_func("failover-virtio-net/params/on_mismatch", + test_on_mismatch); + qtest_add_func("failover-virtio-net/params/off", test_off); + qtest_add_func("failover-virtio-net/params/enabled", test_enabled); + qtest_add_func("failover-virtio-net/hotplug_1", test_hotplug_1); + qtest_add_func("failover-virtio-net/hotplug_1_reverse", + test_hotplug_1_reverse); + qtest_add_func("failover-virtio-net/hotplug_2", test_hotplug_2); + qtest_add_func("failover-virtio-net/hotplug_2_reverse", + test_hotplug_2_reverse); + qtest_add_data_func("failover-virtio-net/migrate/out", tmpfile, + test_migrate_out); + qtest_add_data_func("failover-virtio-net/migrate/in", tmpfile, + test_migrate_in); + qtest_add_data_func("failover-virtio-net/migrate/abort/wait-unplug", + tmpfile, test_migrate_abort_wait_unplug); + qtest_add_data_func("failover-virtio-net/migrate/abort/active", tmpfile, + test_migrate_abort_active); + if (g_test_slow()) { + qtest_add_data_func("failover-virtio-net/migrate/abort/timeout", + tmpfile, test_migrate_abort_timeout); + } + qtest_add_data_func("failover-virtio-net/multi/out", + tmpfile, test_multi_out); + qtest_add_data_func("failover-virtio-net/multi/in", + tmpfile, test_multi_in); + + ret = g_test_run(); + + unlink(tmpfile); + g_free(tmpfile); + + return ret; +} diff --git a/tests/tcg/aarch64/Makefile.target b/tests/tcg/aarch64/Makefile.target index 2c05c90d17..1d967901bd 100644 --- a/tests/tcg/aarch64/Makefile.target +++ b/tests/tcg/aarch64/Makefile.target @@ -8,8 +8,8 @@ VPATH += $(ARM_SRC) AARCH64_SRC=$(SRC_PATH)/tests/tcg/aarch64 VPATH += $(AARCH64_SRC) -# Float-convert Tests -AARCH64_TESTS=fcvt +# Base architecture tests +AARCH64_TESTS=fcvt pcalign-a64 fcvt: LDFLAGS+=-lm diff --git a/tests/tcg/aarch64/pcalign-a64.c b/tests/tcg/aarch64/pcalign-a64.c new file mode 100644 index 0000000000..6b9277f919 --- /dev/null +++ b/tests/tcg/aarch64/pcalign-a64.c @@ -0,0 +1,37 @@ +/* Test PC misalignment exception */ + +#include <assert.h> +#include <signal.h> +#include <stdlib.h> +#include <stdio.h> + +static void *expected; + +static void sigbus(int sig, siginfo_t *info, void *vuc) +{ + assert(info->si_code == BUS_ADRALN); + assert(info->si_addr == expected); + exit(EXIT_SUCCESS); +} + +int main() +{ + void *tmp; + + struct sigaction sa = { + .sa_sigaction = sigbus, + .sa_flags = SA_SIGINFO + }; + + if (sigaction(SIGBUS, &sa, NULL) < 0) { + perror("sigaction"); + return EXIT_FAILURE; + } + + asm volatile("adr %0, 1f + 1\n\t" + "str %0, %1\n\t" + "br %0\n" + "1:" + : "=&r"(tmp), "=m"(expected)); + abort(); +} diff --git a/tests/tcg/arm/Makefile.target b/tests/tcg/arm/Makefile.target index 5ab59ed6ce..f509d823d4 100644 --- a/tests/tcg/arm/Makefile.target +++ b/tests/tcg/arm/Makefile.target @@ -29,6 +29,10 @@ run-fcvt: fcvt $(call run-test,fcvt,$(QEMU) $<,"$< on $(TARGET_NAME)") $(call diff-out,fcvt,$(ARM_SRC)/fcvt.ref) +# PC alignment test +ARM_TESTS += pcalign-a32 +pcalign-a32: CFLAGS+=-marm + ifeq ($(CONFIG_ARM_COMPATIBLE_SEMIHOSTING),y) # Semihosting smoke test for linux-user diff --git a/tests/tcg/arm/pcalign-a32.c b/tests/tcg/arm/pcalign-a32.c new file mode 100644 index 0000000000..3c9c8cc97b --- /dev/null +++ b/tests/tcg/arm/pcalign-a32.c @@ -0,0 +1,46 @@ +/* Test PC misalignment exception */ + +#ifdef __thumb__ +#error "This test must be compiled for ARM" +#endif + +#include <assert.h> +#include <signal.h> +#include <stdlib.h> +#include <stdio.h> + +static void *expected; + +static void sigbus(int sig, siginfo_t *info, void *vuc) +{ + assert(info->si_code == BUS_ADRALN); + assert(info->si_addr == expected); + exit(EXIT_SUCCESS); +} + +int main() +{ + void *tmp; + + struct sigaction sa = { + .sa_sigaction = sigbus, + .sa_flags = SA_SIGINFO + }; + + if (sigaction(SIGBUS, &sa, NULL) < 0) { + perror("sigaction"); + return EXIT_FAILURE; + } + + asm volatile("adr %0, 1f + 2\n\t" + "str %0, %1\n\t" + "bx %0\n" + "1:" + : "=&r"(tmp), "=m"(expected)); + + /* + * From v8, it is CONSTRAINED UNPREDICTABLE whether BXWritePC aligns + * the address or not. If so, we can legitimately fall through. + */ + return EXIT_SUCCESS; +} |