diff options
154 files changed, 3992 insertions, 1600 deletions
diff --git a/.cirrus.yml b/.cirrus.yml index de0727cb09..ce7850a320 100644 --- a/.cirrus.yml +++ b/.cirrus.yml @@ -7,7 +7,7 @@ freebsd_12_task: cpu: 8 memory: 8G install_script: ASSUME_ALWAYS_YES=yes pkg bootstrap -f ; pkg install -y - bash bison curl cyrus-sasl git glib gmake gnutls gsed + bash curl cyrus-sasl git glib gmake gnutls gsed nettle perl5 pixman pkgconf png usbredir script: - mkdir build @@ -45,12 +45,15 @@ Aleksandar Markovic <aleksandar.qemu.devel@gmail.com> <amarkovic@wavecomp.com> Aleksandar Rikalo <aleksandar.rikalo@syrmia.com> <arikalo@wavecomp.com> Aleksandar Rikalo <aleksandar.rikalo@syrmia.com> <aleksandar.rikalo@rt-rk.com> Anthony Liguori <anthony@codemonkey.ws> Anthony Liguori <aliguori@us.ibm.com> +Filip Bozuta <filip.bozuta@syrmia.com> <filip.bozuta@rt-rk.com.com> +Frederic Konrad <konrad@adacore.com> <fred.konrad@greensocs.com> James Hogan <jhogan@kernel.org> <james.hogan@imgtec.com> Leif Lindholm <leif@nuviainc.com> <leif.lindholm@linaro.org> Paul Burton <pburton@wavecomp.com> <paul.burton@mips.com> Paul Burton <pburton@wavecomp.com> <paul.burton@imgtec.com> Paul Burton <pburton@wavecomp.com> <paul@archlinuxmips.org> Philippe Mathieu-Daudé <philmd@redhat.com> <f4bug@amsat.org> +Stefan Brankovic <stefan.brankovic@syrmia.com> <stefan.brankovic@rt-rk.com.com> Yongbok Kim <yongbok.kim@mips.com> <yongbok.kim@imgtec.com> # Also list preferred name forms where people have changed their diff --git a/.shippable.yml b/.shippable.yml index 2cce7b5689..10cf219bff 100644 --- a/.shippable.yml +++ b/.shippable.yml @@ -5,8 +5,8 @@ env: global: - LC_ALL=C matrix: - - IMAGE=debian-amd64 - TARGET_LIST=x86_64-softmmu,x86_64-linux-user + # - IMAGE=debian-amd64 + # TARGET_LIST=x86_64-softmmu,x86_64-linux-user - IMAGE=debian-win32-cross TARGET_LIST=arm-softmmu,i386-softmmu,lm32-softmmu - IMAGE=debian-win64-cross @@ -19,10 +19,10 @@ env: TARGET_LIST=aarch64-softmmu,aarch64-linux-user - IMAGE=debian-s390x-cross TARGET_LIST=s390x-softmmu,s390x-linux-user - - IMAGE=debian-mips-cross - TARGET_LIST=mips-softmmu,mipsel-linux-user - - IMAGE=debian-mips64el-cross - TARGET_LIST=mips64el-softmmu,mips64el-linux-user + # - IMAGE=debian-mips-cross + # TARGET_LIST=mips-softmmu,mipsel-linux-user + # - IMAGE=debian-mips64el-cross + # TARGET_LIST=mips64el-softmmu,mips64el-linux-user - IMAGE=debian-ppc64el-cross TARGET_LIST=ppc64-softmmu,ppc64-linux-user,ppc64abi32-linux-user build: diff --git a/.travis.yml b/.travis.yml index 564be50a3c..ec6367af1f 100644 --- a/.travis.yml +++ b/.travis.yml @@ -429,6 +429,7 @@ jobs: env: - TEST_CMD="make check check-tcg V=1" - CONFIG="--disable-containers --target-list=${MAIN_SOFTMMU_TARGETS}" + - UNRELIABLE=true - name: "[ppc64] GCC check-tcg" arch: ppc64le @@ -493,6 +494,7 @@ jobs: env: - TEST_CMD="make check check-tcg V=1" - CONFIG="--disable-containers --target-list=${MAIN_SOFTMMU_TARGETS},s390x-linux-user" + - UNRELIABLE=true script: - ( cd ${SRC_DIR} ; git submodule update --init roms/SLOF ) - BUILD_RC=0 && make -j${JOBS} || BUILD_RC=$? @@ -535,6 +537,7 @@ jobs: - TEST_CMD="make check-unit" - CONFIG="--disable-containers --disable-tcg --enable-kvm --disable-tools --host-cc=clang --cxx=clang++" + - UNRELIABLE=true # Release builds # The make-release script expect a QEMU version, so our tag must start with a 'v'. @@ -556,3 +559,5 @@ jobs: - mkdir -p release-build && cd release-build - ../configure ${BASE_CONFIG} ${CONFIG} || { cat config.log && exit 1; } - make install + allow_failures: + - env: UNRELIABLE=true diff --git a/MAINTAINERS b/MAINTAINERS index abe4d7ef8a..a922775e45 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1533,7 +1533,7 @@ F: hw/acpi/* F: hw/smbios/* F: hw/i386/acpi-build.[hc] F: hw/arm/virt-acpi-build.c -F: tests/qtest/bios-tables-test.c +F: tests/qtest/bios-tables-test* F: tests/qtest/acpi-utils.[hc] F: tests/data/acpi/ @@ -2330,6 +2330,7 @@ S: Maintained F: qtest.c F: accel/qtest.c F: tests/qtest/ +X: tests/qtest/bios-tables-test-allowed-diff.h Device Fuzzing M: Alexander Bulekov <alxndr@bu.edu> @@ -6809,8 +6809,11 @@ void bdrv_refresh_filename(BlockDriverState *bs) pstrcpy(bs->filename, sizeof(bs->filename), bs->exact_filename); } else { QString *json = qobject_to_json(QOBJECT(bs->full_open_options)); - snprintf(bs->filename, sizeof(bs->filename), "json:%s", - qstring_get_str(json)); + if (snprintf(bs->filename, sizeof(bs->filename), "json:%s", + qstring_get_str(json)) >= sizeof(bs->filename)) { + /* Give user a hint if we truncated things. */ + strcpy(bs->filename + sizeof(bs->filename) - 4, "..."); + } qobject_unref(json); } } diff --git a/block/nbd.c b/block/nbd.c index 4ac23c8f62..eed160c5cd 100644 --- a/block/nbd.c +++ b/block/nbd.c @@ -1984,6 +1984,7 @@ static void nbd_refresh_filename(BlockDriverState *bs) { BDRVNBDState *s = bs->opaque; const char *host = NULL, *port = NULL, *path = NULL; + size_t len = 0; if (s->saddr->type == SOCKET_ADDRESS_TYPE_INET) { const InetSocketAddress *inet = &s->saddr->u.inet; @@ -1996,17 +1997,21 @@ static void nbd_refresh_filename(BlockDriverState *bs) } /* else can't represent as pseudo-filename */ if (path && s->export) { - snprintf(bs->exact_filename, sizeof(bs->exact_filename), - "nbd+unix:///%s?socket=%s", s->export, path); + len = snprintf(bs->exact_filename, sizeof(bs->exact_filename), + "nbd+unix:///%s?socket=%s", s->export, path); } else if (path && !s->export) { - snprintf(bs->exact_filename, sizeof(bs->exact_filename), - "nbd+unix://?socket=%s", path); + len = snprintf(bs->exact_filename, sizeof(bs->exact_filename), + "nbd+unix://?socket=%s", path); } else if (host && s->export) { - snprintf(bs->exact_filename, sizeof(bs->exact_filename), - "nbd://%s:%s/%s", host, port, s->export); + len = snprintf(bs->exact_filename, sizeof(bs->exact_filename), + "nbd://%s:%s/%s", host, port, s->export); } else if (host && !s->export) { - snprintf(bs->exact_filename, sizeof(bs->exact_filename), - "nbd://%s:%s", host, port); + len = snprintf(bs->exact_filename, sizeof(bs->exact_filename), + "nbd://%s:%s", host, port); + } + if (len > sizeof(bs->exact_filename)) { + /* Name is too long to represent exactly, so leave it empty. */ + bs->exact_filename[0] = '\0'; } } diff --git a/chardev/char-socket.c b/chardev/char-socket.c index dd3d3ed8d6..afebeec5c3 100644 --- a/chardev/char-socket.c +++ b/chardev/char-socket.c @@ -175,15 +175,16 @@ static int tcp_chr_write(Chardev *chr, const uint8_t *buf, int len) if (ret < 0 && errno != EAGAIN) { if (tcp_chr_read_poll(chr) <= 0) { + /* Perform disconnect and return error. */ tcp_chr_disconnect_locked(chr); - return len; } /* else let the read handler finish it properly */ } return ret; } else { - /* XXX: indicate an error ? */ - return len; + /* Indicate an error. */ + errno = EIO; + return -1; } } @@ -7210,6 +7210,9 @@ if test "$vhost_crypto" = "yes" ; then fi if test "$vhost_vsock" = "yes" ; then echo "CONFIG_VHOST_VSOCK=y" >> $config_host_mak + if test "$vhost_user" = "yes" ; then + echo "CONFIG_VHOST_USER_VSOCK=y" >> $config_host_mak + fi fi if test "$vhost_kernel" = "yes" ; then echo "CONFIG_VHOST_KERNEL=y" >> $config_host_mak diff --git a/contrib/libvhost-user/libvhost-user.c b/contrib/libvhost-user/libvhost-user.c index 3bca996c62..d315db1396 100644 --- a/contrib/libvhost-user/libvhost-user.c +++ b/contrib/libvhost-user/libvhost-user.c @@ -137,6 +137,9 @@ vu_request_to_string(unsigned int req) REQ(VHOST_USER_SET_INFLIGHT_FD), REQ(VHOST_USER_GPU_SET_SOCKET), REQ(VHOST_USER_VRING_KICK), + REQ(VHOST_USER_GET_MAX_MEM_SLOTS), + REQ(VHOST_USER_ADD_MEM_REG), + REQ(VHOST_USER_REM_MEM_REG), REQ(VHOST_USER_MAX), }; #undef REQ @@ -266,7 +269,7 @@ have_userfault(void) static bool vu_message_read(VuDev *dev, int conn_fd, VhostUserMsg *vmsg) { - char control[CMSG_SPACE(VHOST_MEMORY_MAX_NREGIONS * sizeof(int))] = { }; + char control[CMSG_SPACE(VHOST_MEMORY_BASELINE_NREGIONS * sizeof(int))] = {}; struct iovec iov = { .iov_base = (char *)vmsg, .iov_len = VHOST_USER_HDR_SIZE, @@ -337,7 +340,7 @@ vu_message_write(VuDev *dev, int conn_fd, VhostUserMsg *vmsg) { int rc; uint8_t *p = (uint8_t *)vmsg; - char control[CMSG_SPACE(VHOST_MEMORY_MAX_NREGIONS * sizeof(int))] = { }; + char control[CMSG_SPACE(VHOST_MEMORY_BASELINE_NREGIONS * sizeof(int))] = {}; struct iovec iov = { .iov_base = (char *)vmsg, .iov_len = VHOST_USER_HDR_SIZE, @@ -350,7 +353,7 @@ vu_message_write(VuDev *dev, int conn_fd, VhostUserMsg *vmsg) struct cmsghdr *cmsg; memset(control, 0, sizeof(control)); - assert(vmsg->fd_num <= VHOST_MEMORY_MAX_NREGIONS); + assert(vmsg->fd_num <= VHOST_MEMORY_BASELINE_NREGIONS); if (vmsg->fd_num > 0) { size_t fdsize = vmsg->fd_num * sizeof(int); msg.msg_controllen = CMSG_SPACE(fdsize); @@ -495,6 +498,16 @@ static bool vu_get_features_exec(VuDev *dev, VhostUserMsg *vmsg) { vmsg->payload.u64 = + /* + * The following VIRTIO feature bits are supported by our virtqueue + * implementation: + */ + 1ULL << VIRTIO_F_NOTIFY_ON_EMPTY | + 1ULL << VIRTIO_RING_F_INDIRECT_DESC | + 1ULL << VIRTIO_RING_F_EVENT_IDX | + 1ULL << VIRTIO_F_VERSION_1 | + + /* vhost-user feature bits */ 1ULL << VHOST_F_LOG_ALL | 1ULL << VHOST_USER_F_PROTOCOL_FEATURES; @@ -584,6 +597,244 @@ map_ring(VuDev *dev, VuVirtq *vq) } static bool +generate_faults(VuDev *dev) { + int i; + for (i = 0; i < dev->nregions; i++) { + VuDevRegion *dev_region = &dev->regions[i]; + int ret; +#ifdef UFFDIO_REGISTER + /* + * We should already have an open ufd. Mark each memory + * range as ufd. + * Discard any mapping we have here; note I can't use MADV_REMOVE + * or fallocate to make the hole since I don't want to lose + * data that's already arrived in the shared process. + * TODO: How to do hugepage + */ + ret = madvise((void *)(uintptr_t)dev_region->mmap_addr, + dev_region->size + dev_region->mmap_offset, + MADV_DONTNEED); + if (ret) { + fprintf(stderr, + "%s: Failed to madvise(DONTNEED) region %d: %s\n", + __func__, i, strerror(errno)); + } + /* + * Turn off transparent hugepages so we dont get lose wakeups + * in neighbouring pages. + * TODO: Turn this backon later. + */ + ret = madvise((void *)(uintptr_t)dev_region->mmap_addr, + dev_region->size + dev_region->mmap_offset, + MADV_NOHUGEPAGE); + if (ret) { + /* + * Note: This can happen legally on kernels that are configured + * without madvise'able hugepages + */ + fprintf(stderr, + "%s: Failed to madvise(NOHUGEPAGE) region %d: %s\n", + __func__, i, strerror(errno)); + } + struct uffdio_register reg_struct; + reg_struct.range.start = (uintptr_t)dev_region->mmap_addr; + reg_struct.range.len = dev_region->size + dev_region->mmap_offset; + reg_struct.mode = UFFDIO_REGISTER_MODE_MISSING; + + if (ioctl(dev->postcopy_ufd, UFFDIO_REGISTER, ®_struct)) { + vu_panic(dev, "%s: Failed to userfault region %d " + "@%p + size:%zx offset: %zx: (ufd=%d)%s\n", + __func__, i, + dev_region->mmap_addr, + dev_region->size, dev_region->mmap_offset, + dev->postcopy_ufd, strerror(errno)); + return false; + } + if (!(reg_struct.ioctls & ((__u64)1 << _UFFDIO_COPY))) { + vu_panic(dev, "%s Region (%d) doesn't support COPY", + __func__, i); + return false; + } + DPRINT("%s: region %d: Registered userfault for %" + PRIx64 " + %" PRIx64 "\n", __func__, i, + (uint64_t)reg_struct.range.start, + (uint64_t)reg_struct.range.len); + /* Now it's registered we can let the client at it */ + if (mprotect((void *)(uintptr_t)dev_region->mmap_addr, + dev_region->size + dev_region->mmap_offset, + PROT_READ | PROT_WRITE)) { + vu_panic(dev, "failed to mprotect region %d for postcopy (%s)", + i, strerror(errno)); + return false; + } + /* TODO: Stash 'zero' support flags somewhere */ +#endif + } + + return true; +} + +static bool +vu_add_mem_reg(VuDev *dev, VhostUserMsg *vmsg) { + int i; + bool track_ramblocks = dev->postcopy_listening; + VhostUserMemoryRegion m = vmsg->payload.memreg.region, *msg_region = &m; + VuDevRegion *dev_region = &dev->regions[dev->nregions]; + void *mmap_addr; + + /* + * If we are in postcopy mode and we receive a u64 payload with a 0 value + * we know all the postcopy client bases have been recieved, and we + * should start generating faults. + */ + if (track_ramblocks && + vmsg->size == sizeof(vmsg->payload.u64) && + vmsg->payload.u64 == 0) { + (void)generate_faults(dev); + return false; + } + + DPRINT("Adding region: %d\n", dev->nregions); + DPRINT(" guest_phys_addr: 0x%016"PRIx64"\n", + msg_region->guest_phys_addr); + DPRINT(" memory_size: 0x%016"PRIx64"\n", + msg_region->memory_size); + DPRINT(" userspace_addr 0x%016"PRIx64"\n", + msg_region->userspace_addr); + DPRINT(" mmap_offset 0x%016"PRIx64"\n", + msg_region->mmap_offset); + + dev_region->gpa = msg_region->guest_phys_addr; + dev_region->size = msg_region->memory_size; + dev_region->qva = msg_region->userspace_addr; + dev_region->mmap_offset = msg_region->mmap_offset; + + /* + * We don't use offset argument of mmap() since the + * mapped address has to be page aligned, and we use huge + * pages. + */ + if (track_ramblocks) { + /* + * In postcopy we're using PROT_NONE here to catch anyone + * accessing it before we userfault. + */ + mmap_addr = mmap(0, dev_region->size + dev_region->mmap_offset, + PROT_NONE, MAP_SHARED, + vmsg->fds[0], 0); + } else { + mmap_addr = mmap(0, dev_region->size + dev_region->mmap_offset, + PROT_READ | PROT_WRITE, MAP_SHARED, vmsg->fds[0], + 0); + } + + if (mmap_addr == MAP_FAILED) { + vu_panic(dev, "region mmap error: %s", strerror(errno)); + } else { + dev_region->mmap_addr = (uint64_t)(uintptr_t)mmap_addr; + DPRINT(" mmap_addr: 0x%016"PRIx64"\n", + dev_region->mmap_addr); + } + + close(vmsg->fds[0]); + + if (track_ramblocks) { + /* + * Return the address to QEMU so that it can translate the ufd + * fault addresses back. + */ + msg_region->userspace_addr = (uintptr_t)(mmap_addr + + dev_region->mmap_offset); + + /* Send the message back to qemu with the addresses filled in. */ + vmsg->fd_num = 0; + if (!vu_send_reply(dev, dev->sock, vmsg)) { + vu_panic(dev, "failed to respond to add-mem-region for postcopy"); + return false; + } + + DPRINT("Successfully added new region in postcopy\n"); + dev->nregions++; + return false; + + } else { + for (i = 0; i < dev->max_queues; i++) { + if (dev->vq[i].vring.desc) { + if (map_ring(dev, &dev->vq[i])) { + vu_panic(dev, "remapping queue %d for new memory region", + i); + } + } + } + + DPRINT("Successfully added new region\n"); + dev->nregions++; + vmsg_set_reply_u64(vmsg, 0); + return true; + } +} + +static inline bool reg_equal(VuDevRegion *vudev_reg, + VhostUserMemoryRegion *msg_reg) +{ + if (vudev_reg->gpa == msg_reg->guest_phys_addr && + vudev_reg->qva == msg_reg->userspace_addr && + vudev_reg->size == msg_reg->memory_size) { + return true; + } + + return false; +} + +static bool +vu_rem_mem_reg(VuDev *dev, VhostUserMsg *vmsg) { + int i, j; + bool found = false; + VuDevRegion shadow_regions[VHOST_USER_MAX_RAM_SLOTS] = {}; + VhostUserMemoryRegion m = vmsg->payload.memreg.region, *msg_region = &m; + + DPRINT("Removing region:\n"); + DPRINT(" guest_phys_addr: 0x%016"PRIx64"\n", + msg_region->guest_phys_addr); + DPRINT(" memory_size: 0x%016"PRIx64"\n", + msg_region->memory_size); + DPRINT(" userspace_addr 0x%016"PRIx64"\n", + msg_region->userspace_addr); + DPRINT(" mmap_offset 0x%016"PRIx64"\n", + msg_region->mmap_offset); + + for (i = 0, j = 0; i < dev->nregions; i++) { + if (!reg_equal(&dev->regions[i], msg_region)) { + shadow_regions[j].gpa = dev->regions[i].gpa; + shadow_regions[j].size = dev->regions[i].size; + shadow_regions[j].qva = dev->regions[i].qva; + shadow_regions[j].mmap_offset = dev->regions[i].mmap_offset; + j++; + } else { + found = true; + VuDevRegion *r = &dev->regions[i]; + void *m = (void *) (uintptr_t) r->mmap_addr; + + if (m) { + munmap(m, r->size + r->mmap_offset); + } + } + } + + if (found) { + memcpy(dev->regions, shadow_regions, + sizeof(VuDevRegion) * VHOST_USER_MAX_RAM_SLOTS); + DPRINT("Successfully removed a region\n"); + dev->nregions--; + vmsg_set_reply_u64(vmsg, 0); + } else { + vu_panic(dev, "Specified region not found\n"); + } + + return true; +} + +static bool vu_set_mem_table_exec_postcopy(VuDev *dev, VhostUserMsg *vmsg) { int i; @@ -655,74 +906,7 @@ vu_set_mem_table_exec_postcopy(VuDev *dev, VhostUserMsg *vmsg) } /* OK, now we can go and register the memory and generate faults */ - for (i = 0; i < dev->nregions; i++) { - VuDevRegion *dev_region = &dev->regions[i]; - int ret; -#ifdef UFFDIO_REGISTER - /* We should already have an open ufd. Mark each memory - * range as ufd. - * Discard any mapping we have here; note I can't use MADV_REMOVE - * or fallocate to make the hole since I don't want to lose - * data that's already arrived in the shared process. - * TODO: How to do hugepage - */ - ret = madvise((void *)(uintptr_t)dev_region->mmap_addr, - dev_region->size + dev_region->mmap_offset, - MADV_DONTNEED); - if (ret) { - fprintf(stderr, - "%s: Failed to madvise(DONTNEED) region %d: %s\n", - __func__, i, strerror(errno)); - } - /* Turn off transparent hugepages so we dont get lose wakeups - * in neighbouring pages. - * TODO: Turn this backon later. - */ - ret = madvise((void *)(uintptr_t)dev_region->mmap_addr, - dev_region->size + dev_region->mmap_offset, - MADV_NOHUGEPAGE); - if (ret) { - /* Note: This can happen legally on kernels that are configured - * without madvise'able hugepages - */ - fprintf(stderr, - "%s: Failed to madvise(NOHUGEPAGE) region %d: %s\n", - __func__, i, strerror(errno)); - } - struct uffdio_register reg_struct; - reg_struct.range.start = (uintptr_t)dev_region->mmap_addr; - reg_struct.range.len = dev_region->size + dev_region->mmap_offset; - reg_struct.mode = UFFDIO_REGISTER_MODE_MISSING; - - if (ioctl(dev->postcopy_ufd, UFFDIO_REGISTER, ®_struct)) { - vu_panic(dev, "%s: Failed to userfault region %d " - "@%p + size:%zx offset: %zx: (ufd=%d)%s\n", - __func__, i, - dev_region->mmap_addr, - dev_region->size, dev_region->mmap_offset, - dev->postcopy_ufd, strerror(errno)); - return false; - } - if (!(reg_struct.ioctls & ((__u64)1 << _UFFDIO_COPY))) { - vu_panic(dev, "%s Region (%d) doesn't support COPY", - __func__, i); - return false; - } - DPRINT("%s: region %d: Registered userfault for %" - PRIx64 " + %" PRIx64 "\n", __func__, i, - (uint64_t)reg_struct.range.start, - (uint64_t)reg_struct.range.len); - /* Now it's registered we can let the client at it */ - if (mprotect((void *)(uintptr_t)dev_region->mmap_addr, - dev_region->size + dev_region->mmap_offset, - PROT_READ | PROT_WRITE)) { - vu_panic(dev, "failed to mprotect region %d for postcopy (%s)", - i, strerror(errno)); - return false; - } - /* TODO: Stash 'zero' support flags somewhere */ -#endif - } + (void)generate_faults(dev); return false; } @@ -1220,7 +1404,8 @@ vu_get_protocol_features_exec(VuDev *dev, VhostUserMsg *vmsg) 1ULL << VHOST_USER_PROTOCOL_F_SLAVE_REQ | 1ULL << VHOST_USER_PROTOCOL_F_HOST_NOTIFIER | 1ULL << VHOST_USER_PROTOCOL_F_SLAVE_SEND_FD | - 1ULL << VHOST_USER_PROTOCOL_F_REPLY_ACK; + 1ULL << VHOST_USER_PROTOCOL_F_REPLY_ACK | + 1ULL << VHOST_USER_PROTOCOL_F_CONFIGURE_MEM_SLOTS; if (have_userfault()) { features |= 1ULL << VHOST_USER_PROTOCOL_F_PAGEFAULT; @@ -1554,6 +1739,22 @@ vu_handle_vring_kick(VuDev *dev, VhostUserMsg *vmsg) return false; } +static bool vu_handle_get_max_memslots(VuDev *dev, VhostUserMsg *vmsg) +{ + vmsg->flags = VHOST_USER_REPLY_MASK | VHOST_USER_VERSION; + vmsg->size = sizeof(vmsg->payload.u64); + vmsg->payload.u64 = VHOST_USER_MAX_RAM_SLOTS; + vmsg->fd_num = 0; + + if (!vu_message_write(dev, dev->sock, vmsg)) { + vu_panic(dev, "Failed to send max ram slots: %s\n", strerror(errno)); + } + + DPRINT("u64: 0x%016"PRIx64"\n", (uint64_t) VHOST_USER_MAX_RAM_SLOTS); + + return false; +} + static bool vu_process_message(VuDev *dev, VhostUserMsg *vmsg) { @@ -1638,6 +1839,12 @@ vu_process_message(VuDev *dev, VhostUserMsg *vmsg) return vu_set_inflight_fd(dev, vmsg); case VHOST_USER_VRING_KICK: return vu_handle_vring_kick(dev, vmsg); + case VHOST_USER_GET_MAX_MEM_SLOTS: + return vu_handle_get_max_memslots(dev, vmsg); + case VHOST_USER_ADD_MEM_REG: + return vu_add_mem_reg(dev, vmsg); + case VHOST_USER_REM_MEM_REG: + return vu_rem_mem_reg(dev, vmsg); default: vmsg_close_fds(vmsg); vu_panic(dev, "Unhandled request: %d", vmsg->request); diff --git a/contrib/libvhost-user/libvhost-user.h b/contrib/libvhost-user/libvhost-user.h index f30394fab6..844c37c648 100644 --- a/contrib/libvhost-user/libvhost-user.h +++ b/contrib/libvhost-user/libvhost-user.h @@ -28,7 +28,13 @@ #define VIRTQUEUE_MAX_SIZE 1024 -#define VHOST_MEMORY_MAX_NREGIONS 8 +#define VHOST_MEMORY_BASELINE_NREGIONS 8 + +/* + * Set a reasonable maximum number of ram slots, which will be supported by + * any architecture. + */ +#define VHOST_USER_MAX_RAM_SLOTS 32 typedef enum VhostSetConfigType { VHOST_SET_CONFIG_TYPE_MASTER = 0, @@ -55,6 +61,7 @@ enum VhostUserProtocolFeature { VHOST_USER_PROTOCOL_F_HOST_NOTIFIER = 11, VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD = 12, VHOST_USER_PROTOCOL_F_INBAND_NOTIFICATIONS = 14, + VHOST_USER_PROTOCOL_F_CONFIGURE_MEM_SLOTS = 15, VHOST_USER_PROTOCOL_F_MAX }; @@ -97,6 +104,9 @@ typedef enum VhostUserRequest { VHOST_USER_SET_INFLIGHT_FD = 32, VHOST_USER_GPU_SET_SOCKET = 33, VHOST_USER_VRING_KICK = 35, + VHOST_USER_GET_MAX_MEM_SLOTS = 36, + VHOST_USER_ADD_MEM_REG = 37, + VHOST_USER_REM_MEM_REG = 38, VHOST_USER_MAX } VhostUserRequest; @@ -120,9 +130,14 @@ typedef struct VhostUserMemoryRegion { typedef struct VhostUserMemory { uint32_t nregions; uint32_t padding; - VhostUserMemoryRegion regions[VHOST_MEMORY_MAX_NREGIONS]; + VhostUserMemoryRegion regions[VHOST_MEMORY_BASELINE_NREGIONS]; } VhostUserMemory; +typedef struct VhostUserMemRegMsg { + uint32_t padding; + VhostUserMemoryRegion region; +} VhostUserMemRegMsg; + typedef struct VhostUserLog { uint64_t mmap_size; uint64_t mmap_offset; @@ -175,13 +190,14 @@ typedef struct VhostUserMsg { struct vhost_vring_state state; struct vhost_vring_addr addr; VhostUserMemory memory; + VhostUserMemRegMsg memreg; VhostUserLog log; VhostUserConfig config; VhostUserVringArea area; VhostUserInflight inflight; } payload; - int fds[VHOST_MEMORY_MAX_NREGIONS]; + int fds[VHOST_MEMORY_BASELINE_NREGIONS]; int fd_num; uint8_t *data; } VU_PACKED VhostUserMsg; @@ -359,7 +375,7 @@ typedef struct VuDevInflightInfo { struct VuDev { int sock; uint32_t nregions; - VuDevRegion regions[VHOST_MEMORY_MAX_NREGIONS]; + VuDevRegion regions[VHOST_USER_MAX_RAM_SLOTS]; VuVirtq *vq; VuDevInflightInfo inflight_info; int log_call_fd; diff --git a/contrib/vhost-user-blk/vhost-user-blk.c b/contrib/vhost-user-blk/vhost-user-blk.c index 6fd91c7e99..25eccd02b5 100644 --- a/contrib/vhost-user-blk/vhost-user-blk.c +++ b/contrib/vhost-user-blk/vhost-user-blk.c @@ -382,9 +382,7 @@ vub_get_features(VuDev *dev) 1ull << VIRTIO_BLK_F_DISCARD | 1ull << VIRTIO_BLK_F_WRITE_ZEROES | #endif - 1ull << VIRTIO_BLK_F_CONFIG_WCE | - 1ull << VIRTIO_F_VERSION_1 | - 1ull << VHOST_USER_F_PROTOCOL_FEATURES; + 1ull << VIRTIO_BLK_F_CONFIG_WCE; if (vdev_blk->enable_ro) { features |= 1ull << VIRTIO_BLK_F_RO; diff --git a/default-configs/unicore32-softmmu.mak b/default-configs/unicore32-softmmu.mak index 0bfce48c6d..899288e3d7 100644 --- a/default-configs/unicore32-softmmu.mak +++ b/default-configs/unicore32-softmmu.mak @@ -3,3 +3,4 @@ # Boards: # CONFIG_PUV3=y +CONFIG_SEMIHOSTING=y diff --git a/docs/interop/vhost-user.rst b/docs/interop/vhost-user.rst index 3b1b6602c7..688b7c6900 100644 --- a/docs/interop/vhost-user.rst +++ b/docs/interop/vhost-user.rst @@ -815,6 +815,7 @@ Protocol features #define VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD 12 #define VHOST_USER_PROTOCOL_F_RESET_DEVICE 13 #define VHOST_USER_PROTOCOL_F_INBAND_NOTIFICATIONS 14 + #define VHOST_USER_PROTOCOL_F_CONFIGURE_MEM_SLOTS 15 Master message types -------------------- @@ -1263,6 +1264,49 @@ Master message types The state.num field is currently reserved and must be set to 0. +``VHOST_USER_GET_MAX_MEM_SLOTS`` + :id: 36 + :equivalent ioctl: N/A + :slave payload: u64 + + When the ``VHOST_USER_PROTOCOL_F_CONFIGURE_MEM_SLOTS`` protocol + feature has been successfully negotiated, this message is submitted + by master to the slave. The slave should return the message with a + u64 payload containing the maximum number of memory slots for + QEMU to expose to the guest. The value returned by the backend + will be capped at the maximum number of ram slots which can be + supported by the target platform. + +``VHOST_USER_ADD_MEM_REG`` + :id: 37 + :equivalent ioctl: N/A + :slave payload: memory region + + When the ``VHOST_USER_PROTOCOL_F_CONFIGURE_MEM_SLOTS`` protocol + feature has been successfully negotiated, this message is submitted + by the master to the slave. The message payload contains a memory + region descriptor struct, describing a region of guest memory which + the slave device must map in. When the + ``VHOST_USER_PROTOCOL_F_CONFIGURE_MEM_SLOTS`` protocol feature has + been successfully negotiated, along with the + ``VHOST_USER_REM_MEM_REG`` message, this message is used to set and + update the memory tables of the slave device. + +``VHOST_USER_REM_MEM_REG`` + :id: 38 + :equivalent ioctl: N/A + :slave payload: memory region + + When the ``VHOST_USER_PROTOCOL_F_CONFIGURE_MEM_SLOTS`` protocol + feature has been successfully negotiated, this message is submitted + by the master to the slave. The message payload contains a memory + region descriptor struct, describing a region of guest memory which + the slave device must unmap. When the + ``VHOST_USER_PROTOCOL_F_CONFIGURE_MEM_SLOTS`` protocol feature has + been successfully negotiated, along with the + ``VHOST_USER_ADD_MEM_REG`` message, this message is used to set and + update the memory tables of the slave device. + Slave message types ------------------- diff --git a/docs/tools/qemu-img.rst b/docs/tools/qemu-img.rst index 69cd9a3037..7f0737488a 100644 --- a/docs/tools/qemu-img.rst +++ b/docs/tools/qemu-img.rst @@ -300,7 +300,7 @@ Command description: ``--disable`` to change *BITMAP* to stop recording future edits. - ``--merge`` to merge the contents of *SOURCE_BITMAP* into *BITMAP*. + ``--merge`` to merge the contents of the *SOURCE* bitmap into *BITMAP*. Additional options include ``-g`` which sets a non-default *GRANULARITY* for ``--add``, and ``-b`` and ``-F`` which select an @@ -1038,6 +1038,7 @@ int cpu_watchpoint_insert(CPUState *cpu, vaddr addr, vaddr len, int flags, CPUWatchpoint **watchpoint) { CPUWatchpoint *wp; + vaddr in_page; /* forbid ranges which are empty or run off the end of the address space */ if (len == 0 || (addr + len - 1) < addr) { @@ -1058,7 +1059,12 @@ int cpu_watchpoint_insert(CPUState *cpu, vaddr addr, vaddr len, QTAILQ_INSERT_TAIL(&cpu->watchpoints, wp, entry); } - tlb_flush_page(cpu, addr); + in_page = -(addr | TARGET_PAGE_MASK); + if (len <= in_page) { + tlb_flush_page(cpu, addr); + } else { + tlb_flush(cpu); + } if (watchpoint) *watchpoint = wp; diff --git a/hw/acpi/aml-build.c b/hw/acpi/aml-build.c index 3681ec6e3d..2cb7b991ef 100644 --- a/hw/acpi/aml-build.c +++ b/hw/acpi/aml-build.c @@ -26,6 +26,7 @@ #include "qemu/bitops.h" #include "sysemu/numa.h" #include "hw/boards.h" +#include "hw/acpi/tpm.h" static GArray *build_alloc_array(void) { @@ -1865,9 +1866,9 @@ void build_fadt(GArray *tbl, BIOSLinker *linker, const AcpiFadtData *f, } /* SLEEP_CONTROL_REG */ - build_append_gas(tbl, AML_AS_SYSTEM_MEMORY, 0 , 0, 0, 0); + build_append_gas_from_struct(tbl, &f->sleep_ctl); /* SLEEP_STATUS_REG */ - build_append_gas(tbl, AML_AS_SYSTEM_MEMORY, 0 , 0, 0, 0); + build_append_gas_from_struct(tbl, &f->sleep_sts); /* TODO: extra fields need to be added to support revisions above rev5 */ assert(f->rev == 5); @@ -1877,6 +1878,50 @@ build_hdr: "FACP", tbl->len - fadt_start, f->rev, oem_id, oem_table_id); } +void build_tpm2(GArray *table_data, BIOSLinker *linker, GArray *tcpalog) +{ + Acpi20TPM2 *tpm2_ptr = acpi_data_push(table_data, sizeof(AcpiTableHeader)); + unsigned log_addr_size = sizeof(tpm2_ptr->log_area_start_address); + unsigned log_addr_offset = + (char *)&tpm2_ptr->log_area_start_address - table_data->data; + uint8_t start_method_params[12] = {}; + TPMIf *tpmif = tpm_find(); + + /* platform class */ + build_append_int_noprefix(table_data, TPM2_ACPI_CLASS_CLIENT, 2); + /* reserved */ + build_append_int_noprefix(table_data, 0, 2); + if (TPM_IS_TIS_ISA(tpmif) || TPM_IS_TIS_SYSBUS(tpmif)) { + /* address of control area */ + build_append_int_noprefix(table_data, 0, 8); + /* start method */ + build_append_int_noprefix(table_data, TPM2_START_METHOD_MMIO, 4); + } else if (TPM_IS_CRB(tpmif)) { + build_append_int_noprefix(table_data, TPM_CRB_ADDR_CTRL, 8); + build_append_int_noprefix(table_data, TPM2_START_METHOD_CRB, 4); + } else { + g_warn_if_reached(); + } + + /* platform specific parameters */ + g_array_append_vals(table_data, &start_method_params, 12); + + /* log area minimum length */ + build_append_int_noprefix(table_data, TPM_LOG_AREA_MINIMUM_SIZE, 4); + + acpi_data_push(tcpalog, TPM_LOG_AREA_MINIMUM_SIZE); + bios_linker_loader_alloc(linker, ACPI_BUILD_TPMLOG_FILE, tcpalog, 1, + false); + + /* log area start address to be filled by Guest linker */ + build_append_int_noprefix(table_data, 0, 8); + bios_linker_loader_add_pointer(linker, ACPI_BUILD_TABLE_FILE, + log_addr_offset, log_addr_size, + ACPI_BUILD_TPMLOG_FILE, 0); + build_header(linker, table_data, + (void *)tpm2_ptr, "TPM2", sizeof(*tpm2_ptr), 4, NULL, NULL); +} + /* ACPI 5.0: 6.4.3.8.2 Serial Bus Connection Descriptors */ static Aml *aml_serial_bus_device(uint8_t serial_bus_type, uint8_t flags, uint16_t type_flags, diff --git a/hw/acpi/generic_event_device.c b/hw/acpi/generic_event_device.c index b1cbdd86b6..1cb34111e5 100644 --- a/hw/acpi/generic_event_device.c +++ b/hw/acpi/generic_event_device.c @@ -142,7 +142,7 @@ void build_ged_aml(Aml *table, const char *name, HotplugHandler *hotplug_dev, } /* Memory read by the GED _EVT AML dynamic method */ -static uint64_t ged_read(void *opaque, hwaddr addr, unsigned size) +static uint64_t ged_evt_read(void *opaque, hwaddr addr, unsigned size) { uint64_t val = 0; GEDState *ged_st = opaque; @@ -161,14 +161,14 @@ static uint64_t ged_read(void *opaque, hwaddr addr, unsigned size) } /* Nothing is expected to be written to the GED memory region */ -static void ged_write(void *opaque, hwaddr addr, uint64_t data, - unsigned int size) +static void ged_evt_write(void *opaque, hwaddr addr, uint64_t data, + unsigned int size) { } -static const MemoryRegionOps ged_ops = { - .read = ged_read, - .write = ged_write, +static const MemoryRegionOps ged_evt_ops = { + .read = ged_evt_read, + .write = ged_evt_write, .endianness = DEVICE_LITTLE_ENDIAN, .valid = { .min_access_size = 4, @@ -287,9 +287,9 @@ static void acpi_ged_initfn(Object *obj) SysBusDevice *sbd = SYS_BUS_DEVICE(obj); GEDState *ged_st = &s->ged_state; - memory_region_init_io(&ged_st->io, obj, &ged_ops, ged_st, + memory_region_init_io(&ged_st->evt, obj, &ged_evt_ops, ged_st, TYPE_ACPI_GED, ACPI_GED_EVT_SEL_LEN); - sysbus_init_mmio(sbd, &ged_st->io); + sysbus_init_mmio(sbd, &ged_st->evt); sysbus_init_irq(sbd, &s->irq); diff --git a/hw/acpi/nvdimm.c b/hw/acpi/nvdimm.c index 9316d12b70..8f7cc16add 100644 --- a/hw/acpi/nvdimm.c +++ b/hw/acpi/nvdimm.c @@ -28,6 +28,7 @@ #include "qemu/osdep.h" #include "qemu/uuid.h" +#include "qapi/error.h" #include "hw/acpi/acpi.h" #include "hw/acpi/aml-build.h" #include "hw/acpi/bios-linker-loader.h" @@ -1334,6 +1335,28 @@ static void nvdimm_build_ssdt(GArray *table_offsets, GArray *table_data, free_aml_allocator(); } +void nvdimm_build_srat(GArray *table_data) +{ + GSList *device_list = nvdimm_get_device_list(); + + for (; device_list; device_list = device_list->next) { + AcpiSratMemoryAffinity *numamem = NULL; + DeviceState *dev = device_list->data; + Object *obj = OBJECT(dev); + uint64_t addr, size; + int node; + + node = object_property_get_int(obj, PC_DIMM_NODE_PROP, &error_abort); + addr = object_property_get_uint(obj, PC_DIMM_ADDR_PROP, &error_abort); + size = object_property_get_uint(obj, PC_DIMM_SIZE_PROP, &error_abort); + + numamem = acpi_data_push(table_data, sizeof *numamem); + build_srat_memory(numamem, addr, size, node, + MEM_AFFINITY_ENABLED | MEM_AFFINITY_NON_VOLATILE); + } + g_slist_free(device_list); +} + void nvdimm_build_acpi(GArray *table_offsets, GArray *table_data, BIOSLinker *linker, NVDIMMState *state, uint32_t ram_slots) diff --git a/hw/arm/aspeed.c b/hw/arm/aspeed.c index 2c23297edf..62344ac6a3 100644 --- a/hw/arm/aspeed.c +++ b/hw/arm/aspeed.c @@ -262,7 +262,7 @@ static void aspeed_machine_init(MachineState *machine) bmc = g_new0(AspeedBoardState, 1); memory_region_init(&bmc->ram_container, NULL, "aspeed-ram-container", - UINT32_MAX); + 4 * GiB); memory_region_add_subregion(&bmc->ram_container, 0, machine->ram); object_initialize_child(OBJECT(machine), "soc", &bmc->soc, diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c index 1b0a584c7b..ca31f70f7f 100644 --- a/hw/arm/virt-acpi-build.c +++ b/hw/arm/virt-acpi-build.c @@ -41,12 +41,14 @@ #include "hw/acpi/pci.h" #include "hw/acpi/memory_hotplug.h" #include "hw/acpi/generic_event_device.h" +#include "hw/acpi/tpm.h" #include "hw/pci/pcie_host.h" #include "hw/pci/pci.h" #include "hw/arm/virt.h" #include "hw/mem/nvdimm.h" #include "sysemu/numa.h" #include "sysemu/reset.h" +#include "sysemu/tpm.h" #include "kvm_arm.h" #include "migration/vmstate.h" #include "hw/acpi/ghes.h" @@ -539,6 +541,10 @@ build_srat(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) } } + if (ms->nvdimms_state->is_enabled) { + nvdimm_build_srat(table_data); + } + if (ms->device_memory) { numamem = acpi_data_push(table_data, sizeof *numamem); build_srat_memory(numamem, ms->device_memory->base, @@ -844,6 +850,11 @@ void virt_acpi_build(VirtMachineState *vms, AcpiBuildTables *tables) build_iort(tables_blob, tables->linker, vms); } + if (tpm_get_version(tpm_find()) == TPM_VERSION_2_0) { + acpi_add_table(table_offsets, tables_blob); + build_tpm2(tables_blob, tables->linker, tables->tcpalog); + } + /* XSDT is pointed to by RSDP */ xsdt = tables_blob->len; build_xsdt(tables_blob, tables->linker, table_offsets, NULL, NULL); diff --git a/hw/block/vhost-user-blk.c b/hw/block/vhost-user-blk.c index 98941019a2..a00b854736 100644 --- a/hw/block/vhost-user-blk.c +++ b/hw/block/vhost-user-blk.c @@ -348,6 +348,19 @@ static void vhost_user_blk_disconnect(DeviceState *dev) vhost_dev_cleanup(&s->dev); } +static void vhost_user_blk_event(void *opaque, QEMUChrEvent event); + +static void vhost_user_blk_chr_closed_bh(void *opaque) +{ + DeviceState *dev = opaque; + VirtIODevice *vdev = VIRTIO_DEVICE(dev); + VHostUserBlk *s = VHOST_USER_BLK(vdev); + + vhost_user_blk_disconnect(dev); + qemu_chr_fe_set_handlers(&s->chardev, NULL, NULL, vhost_user_blk_event, + NULL, opaque, NULL, true); +} + static void vhost_user_blk_event(void *opaque, QEMUChrEvent event) { DeviceState *dev = opaque; @@ -362,7 +375,30 @@ static void vhost_user_blk_event(void *opaque, QEMUChrEvent event) } break; case CHR_EVENT_CLOSED: - vhost_user_blk_disconnect(dev); + /* + * A close event may happen during a read/write, but vhost + * code assumes the vhost_dev remains setup, so delay the + * stop & clear. There are two possible paths to hit this + * disconnect event: + * 1. When VM is in the RUN_STATE_PRELAUNCH state. The + * vhost_user_blk_device_realize() is a caller. + * 2. In tha main loop phase after VM start. + * + * For p2 the disconnect event will be delayed. We can't + * do the same for p1, because we are not running the loop + * at this moment. So just skip this step and perform + * disconnect in the caller function. + * + * TODO: maybe it is a good idea to make the same fix + * for other vhost-user devices. + */ + if (runstate_is_running()) { + AioContext *ctx = qemu_get_current_aio_context(); + + qemu_chr_fe_set_handlers(&s->chardev, NULL, NULL, NULL, NULL, + NULL, NULL, false); + aio_bh_schedule_oneshot(ctx, vhost_user_blk_chr_closed_bh, opaque); + } break; case CHR_EVENT_BREAK: case CHR_EVENT_MUX_IN: diff --git a/hw/char/parallel.c b/hw/char/parallel.c index 8dd67d1375..c0f34bf924 100644 --- a/hw/char/parallel.c +++ b/hw/char/parallel.c @@ -28,6 +28,7 @@ #include "qemu/module.h" #include "chardev/char-parallel.h" #include "chardev/char-fe.h" +#include "hw/acpi/aml-build.h" #include "hw/irq.h" #include "hw/isa/isa.h" #include "hw/qdev-properties.h" @@ -568,6 +569,25 @@ static void parallel_isa_realizefn(DeviceState *dev, Error **errp) s, "parallel"); } +static void parallel_isa_build_aml(ISADevice *isadev, Aml *scope) +{ + ISAParallelState *isa = ISA_PARALLEL(isadev); + Aml *dev; + Aml *crs; + + crs = aml_resource_template(); + aml_append(crs, aml_io(AML_DECODE16, isa->iobase, isa->iobase, 0x08, 0x08)); + aml_append(crs, aml_irq_no_flags(isa->isairq)); + + dev = aml_device("LPT%d", isa->index + 1); + aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0400"))); + aml_append(dev, aml_name_decl("_UID", aml_int(isa->index + 1))); + aml_append(dev, aml_name_decl("_STA", aml_int(0xf))); + aml_append(dev, aml_name_decl("_CRS", crs)); + + aml_append(scope, dev); +} + /* Memory mapped interface */ static uint64_t parallel_mm_readfn(void *opaque, hwaddr addr, unsigned size) { @@ -624,9 +644,11 @@ static Property parallel_isa_properties[] = { static void parallel_isa_class_initfn(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); + ISADeviceClass *isa = ISA_DEVICE_CLASS(klass); dc->realize = parallel_isa_realizefn; dc->vmsd = &vmstate_parallel_isa; + isa->build_aml = parallel_isa_build_aml; device_class_set_props(dc, parallel_isa_properties); set_bit(DEVICE_CATEGORY_INPUT, dc->categories); } diff --git a/hw/char/serial-isa.c b/hw/char/serial-isa.c index f9b6eed783..165e320e65 100644 --- a/hw/char/serial-isa.c +++ b/hw/char/serial-isa.c @@ -27,6 +27,7 @@ #include "qapi/error.h" #include "qemu/module.h" #include "sysemu/sysemu.h" +#include "hw/acpi/aml-build.h" #include "hw/char/serial.h" #include "hw/isa/isa.h" #include "hw/qdev-properties.h" @@ -81,6 +82,25 @@ static void serial_isa_realizefn(DeviceState *dev, Error **errp) isa_register_ioport(isadev, &s->io, isa->iobase); } +static void serial_isa_build_aml(ISADevice *isadev, Aml *scope) +{ + ISASerialState *isa = ISA_SERIAL(isadev); + Aml *dev; + Aml *crs; + + crs = aml_resource_template(); + aml_append(crs, aml_io(AML_DECODE16, isa->iobase, isa->iobase, 0x00, 0x08)); + aml_append(crs, aml_irq_no_flags(isa->isairq)); + + dev = aml_device("COM%d", isa->index + 1); + aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0501"))); + aml_append(dev, aml_name_decl("_UID", aml_int(isa->index + 1))); + aml_append(dev, aml_name_decl("_STA", aml_int(0xf))); + aml_append(dev, aml_name_decl("_CRS", crs)); + + aml_append(scope, dev); +} + static const VMStateDescription vmstate_isa_serial = { .name = "serial", .version_id = 3, @@ -103,9 +123,11 @@ static Property serial_isa_properties[] = { static void serial_isa_class_initfn(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); + ISADeviceClass *isa = ISA_DEVICE_CLASS(klass); dc->realize = serial_isa_realizefn; dc->vmsd = &vmstate_isa_serial; + isa->build_aml = serial_isa_build_aml; device_class_set_props(dc, serial_isa_properties); set_bit(DEVICE_CATEGORY_INPUT, dc->categories); } diff --git a/hw/core/machine.c b/hw/core/machine.c index 5460e62294..1d80ab0e1d 100644 --- a/hw/core/machine.c +++ b/hw/core/machine.c @@ -28,7 +28,9 @@ #include "hw/mem/nvdimm.h" #include "migration/vmstate.h" -GlobalProperty hw_compat_5_0[] = {}; +GlobalProperty hw_compat_5_0[] = { + { "virtio-balloon-device", "page-poison", "false" }, +}; const size_t hw_compat_5_0_len = G_N_ELEMENTS(hw_compat_5_0); GlobalProperty hw_compat_4_2[] = { diff --git a/hw/dma/puv3_dma.c b/hw/dma/puv3_dma.c index 5488d388a9..7fa979180f 100644 --- a/hw/dma/puv3_dma.c +++ b/hw/dma/puv3_dma.c @@ -15,6 +15,7 @@ #undef DEBUG_PUV3 #include "hw/unicore32/puv3.h" #include "qemu/module.h" +#include "qemu/log.h" #define PUV3_DMA_CH_NR (6) #define PUV3_DMA_CH_MASK (0xff) @@ -43,7 +44,9 @@ static uint64_t puv3_dma_read(void *opaque, hwaddr offset, ret = s->reg_CFG[PUV3_DMA_CH(offset)]; break; default: - DPRINTF("Bad offset 0x%x\n", offset); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad read offset 0x%"HWADDR_PRIx"\n", + __func__, offset); } DPRINTF("offset 0x%x, value 0x%x\n", offset, ret); @@ -62,7 +65,9 @@ static void puv3_dma_write(void *opaque, hwaddr offset, s->reg_CFG[PUV3_DMA_CH(offset)] = value; break; default: - DPRINTF("Bad offset 0x%x\n", offset); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad write offset 0x%"HWADDR_PRIx"\n", + __func__, offset); } DPRINTF("offset 0x%x, value 0x%x\n", offset, value); } diff --git a/hw/gpio/puv3_gpio.c b/hw/gpio/puv3_gpio.c index d19e342514..7362b6715f 100644 --- a/hw/gpio/puv3_gpio.c +++ b/hw/gpio/puv3_gpio.c @@ -15,6 +15,7 @@ #undef DEBUG_PUV3 #include "hw/unicore32/puv3.h" #include "qemu/module.h" +#include "qemu/log.h" #define TYPE_PUV3_GPIO "puv3_gpio" #define PUV3_GPIO(obj) OBJECT_CHECK(PUV3GPIOState, (obj), TYPE_PUV3_GPIO) @@ -47,7 +48,9 @@ static uint64_t puv3_gpio_read(void *opaque, hwaddr offset, ret = s->reg_GPIR; break; default: - DPRINTF("Bad offset 0x%x\n", offset); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad read offset 0x%"HWADDR_PRIx"\n", + __func__, offset); } DPRINTF("offset 0x%x, value 0x%x\n", offset, ret); @@ -68,14 +71,16 @@ static void puv3_gpio_write(void *opaque, hwaddr offset, if (s->reg_GPDR & value) { s->reg_GPLR |= value; } else { - DPRINTF("Write gpio input port error!"); + qemu_log_mask(LOG_GUEST_ERROR, "%s: Write gpio input port\n", + __func__); } break; case 0x0c: if (s->reg_GPDR & value) { s->reg_GPLR &= ~value; } else { - DPRINTF("Write gpio input port error!"); + qemu_log_mask(LOG_GUEST_ERROR, "%s: Write gpio input port\n", + __func__); } break; case 0x10: /* GRER */ @@ -86,7 +91,9 @@ static void puv3_gpio_write(void *opaque, hwaddr offset, s->reg_GPIR = value; break; default: - DPRINTF("Bad offset 0x%x\n", offset); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad write offset 0x%"HWADDR_PRIx"\n", + __func__, offset); } } diff --git a/hw/hppa/dino.c b/hw/hppa/dino.c index 2b1b38c58a..7290f23962 100644 --- a/hw/hppa/dino.c +++ b/hw/hppa/dino.c @@ -542,7 +542,7 @@ PCIBus *dino_init(MemoryRegion *addr_space, &s->parent_obj.data_mem); /* Dino PCI bus memory. */ - memory_region_init(&s->pci_mem, OBJECT(s), "pci-memory", 1ull << 32); + memory_region_init(&s->pci_mem, OBJECT(s), "pci-memory", 4 * GiB); b = pci_register_root_bus(dev, "pci", dino_set_irq, dino_pci_map_irq, s, &s->pci_mem, get_system_io(), @@ -561,7 +561,7 @@ PCIBus *dino_init(MemoryRegion *addr_space, } /* Set up PCI view of memory: Bus master address space. */ - memory_region_init(&s->bm, OBJECT(s), "bm-dino", 1ull << 32); + memory_region_init(&s->bm, OBJECT(s), "bm-dino", 4 * GiB); memory_region_init_alias(&s->bm_ram_alias, OBJECT(s), "bm-system", addr_space, 0, 0xf0000000 + DINO_MEM_CHUNK_SIZE); diff --git a/hw/i386/Makefile.objs b/hw/i386/Makefile.objs index 8ce1b26533..6abc74551a 100644 --- a/hw/i386/Makefile.objs +++ b/hw/i386/Makefile.objs @@ -16,4 +16,5 @@ obj-$(CONFIG_VMMOUSE) += vmmouse.o obj-$(CONFIG_PC) += port92.o obj-y += kvmvapic.o +obj-$(CONFIG_ACPI) += acpi-common.o obj-$(CONFIG_PC) += acpi-build.o diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c index dcdfbd8906..900f786d08 100644 --- a/hw/i386/acpi-build.c +++ b/hw/i386/acpi-build.c @@ -24,6 +24,7 @@ #include "qapi/error.h" #include "qapi/qmp/qnum.h" #include "acpi-build.h" +#include "acpi-common.h" #include "qemu/bitmap.h" #include "qemu/error-report.h" #include "hw/pci/pci.h" @@ -90,9 +91,6 @@ #define ACPI_BUILD_DPRINTF(fmt, ...) #endif -/* Default IOAPIC ID */ -#define ACPI_BUILD_IOAPIC_ID 0x0 - typedef struct AcpiPmInfo { bool s3_disabled; bool s4_disabled; @@ -328,125 +326,6 @@ build_facs(GArray *table_data) facs->length = cpu_to_le32(sizeof(*facs)); } -void pc_madt_cpu_entry(AcpiDeviceIf *adev, int uid, - const CPUArchIdList *apic_ids, GArray *entry) -{ - uint32_t apic_id = apic_ids->cpus[uid].arch_id; - - /* ACPI spec says that LAPIC entry for non present - * CPU may be omitted from MADT or it must be marked - * as disabled. However omitting non present CPU from - * MADT breaks hotplug on linux. So possible CPUs - * should be put in MADT but kept disabled. - */ - if (apic_id < 255) { - AcpiMadtProcessorApic *apic = acpi_data_push(entry, sizeof *apic); - - apic->type = ACPI_APIC_PROCESSOR; - apic->length = sizeof(*apic); - apic->processor_id = uid; - apic->local_apic_id = apic_id; - if (apic_ids->cpus[uid].cpu != NULL) { - apic->flags = cpu_to_le32(1); - } else { - apic->flags = cpu_to_le32(0); - } - } else { - AcpiMadtProcessorX2Apic *apic = acpi_data_push(entry, sizeof *apic); - - apic->type = ACPI_APIC_LOCAL_X2APIC; - apic->length = sizeof(*apic); - apic->uid = cpu_to_le32(uid); - apic->x2apic_id = cpu_to_le32(apic_id); - if (apic_ids->cpus[uid].cpu != NULL) { - apic->flags = cpu_to_le32(1); - } else { - apic->flags = cpu_to_le32(0); - } - } -} - -static void -build_madt(GArray *table_data, BIOSLinker *linker, PCMachineState *pcms) -{ - MachineClass *mc = MACHINE_GET_CLASS(pcms); - X86MachineState *x86ms = X86_MACHINE(pcms); - const CPUArchIdList *apic_ids = mc->possible_cpu_arch_ids(MACHINE(pcms)); - int madt_start = table_data->len; - AcpiDeviceIfClass *adevc = ACPI_DEVICE_IF_GET_CLASS(pcms->acpi_dev); - AcpiDeviceIf *adev = ACPI_DEVICE_IF(pcms->acpi_dev); - bool x2apic_mode = false; - - AcpiMultipleApicTable *madt; - AcpiMadtIoApic *io_apic; - AcpiMadtIntsrcovr *intsrcovr; - int i; - - madt = acpi_data_push(table_data, sizeof *madt); - madt->local_apic_address = cpu_to_le32(APIC_DEFAULT_ADDRESS); - madt->flags = cpu_to_le32(1); - - for (i = 0; i < apic_ids->len; i++) { - adevc->madt_cpu(adev, i, apic_ids, table_data); - if (apic_ids->cpus[i].arch_id > 254) { - x2apic_mode = true; - } - } - - io_apic = acpi_data_push(table_data, sizeof *io_apic); - io_apic->type = ACPI_APIC_IO; - io_apic->length = sizeof(*io_apic); - io_apic->io_apic_id = ACPI_BUILD_IOAPIC_ID; - io_apic->address = cpu_to_le32(IO_APIC_DEFAULT_ADDRESS); - io_apic->interrupt = cpu_to_le32(0); - - if (x86ms->apic_xrupt_override) { - intsrcovr = acpi_data_push(table_data, sizeof *intsrcovr); - intsrcovr->type = ACPI_APIC_XRUPT_OVERRIDE; - intsrcovr->length = sizeof(*intsrcovr); - intsrcovr->source = 0; - intsrcovr->gsi = cpu_to_le32(2); - intsrcovr->flags = cpu_to_le16(0); /* conforms to bus specifications */ - } - for (i = 1; i < 16; i++) { -#define ACPI_BUILD_PCI_IRQS ((1<<5) | (1<<9) | (1<<10) | (1<<11)) - if (!(ACPI_BUILD_PCI_IRQS & (1 << i))) { - /* No need for a INT source override structure. */ - continue; - } - intsrcovr = acpi_data_push(table_data, sizeof *intsrcovr); - intsrcovr->type = ACPI_APIC_XRUPT_OVERRIDE; - intsrcovr->length = sizeof(*intsrcovr); - intsrcovr->source = i; - intsrcovr->gsi = cpu_to_le32(i); - intsrcovr->flags = cpu_to_le16(0xd); /* active high, level triggered */ - } - - if (x2apic_mode) { - AcpiMadtLocalX2ApicNmi *local_nmi; - - local_nmi = acpi_data_push(table_data, sizeof *local_nmi); - local_nmi->type = ACPI_APIC_LOCAL_X2APIC_NMI; - local_nmi->length = sizeof(*local_nmi); - local_nmi->uid = 0xFFFFFFFF; /* all processors */ - local_nmi->flags = cpu_to_le16(0); - local_nmi->lint = 1; /* ACPI_LINT1 */ - } else { - AcpiMadtLocalNmi *local_nmi; - - local_nmi = acpi_data_push(table_data, sizeof *local_nmi); - local_nmi->type = ACPI_APIC_LOCAL_NMI; - local_nmi->length = sizeof(*local_nmi); - local_nmi->processor_id = 0xff; /* all processors */ - local_nmi->flags = cpu_to_le16(0); - local_nmi->lint = 1; /* ACPI_LINT1 */ - } - - build_header(linker, table_data, - (void *)(table_data->data + madt_start), "APIC", - table_data->len - madt_start, 1, NULL, NULL); -} - static void build_append_pcihp_notify_entry(Aml *method, int slot) { Aml *if_ctx; @@ -1138,22 +1017,6 @@ static Aml *build_fdc_device_aml(ISADevice *fdc) return dev; } -static Aml *build_rtc_device_aml(void) -{ - Aml *dev; - Aml *crs; - - dev = aml_device("RTC"); - aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0B00"))); - crs = aml_resource_template(); - aml_append(crs, aml_io(AML_DECODE16, 0x0070, 0x0070, 0x10, 0x02)); - aml_append(crs, aml_irq_no_flags(8)); - aml_append(crs, aml_io(AML_DECODE16, 0x0072, 0x0072, 0x02, 0x06)); - aml_append(dev, aml_name_decl("_CRS", crs)); - - return dev; -} - static Aml *build_kbd_device_aml(void) { Aml *dev; @@ -1190,87 +1053,6 @@ static Aml *build_mouse_device_aml(void) return dev; } -static Aml *build_lpt_device_aml(void) -{ - Aml *dev; - Aml *crs; - Aml *method; - Aml *if_ctx; - Aml *else_ctx; - Aml *zero = aml_int(0); - Aml *is_present = aml_local(0); - - dev = aml_device("LPT"); - aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0400"))); - - method = aml_method("_STA", 0, AML_NOTSERIALIZED); - aml_append(method, aml_store(aml_name("LPEN"), is_present)); - if_ctx = aml_if(aml_equal(is_present, zero)); - { - aml_append(if_ctx, aml_return(aml_int(0x00))); - } - aml_append(method, if_ctx); - else_ctx = aml_else(); - { - aml_append(else_ctx, aml_return(aml_int(0x0f))); - } - aml_append(method, else_ctx); - aml_append(dev, method); - - crs = aml_resource_template(); - aml_append(crs, aml_io(AML_DECODE16, 0x0378, 0x0378, 0x08, 0x08)); - aml_append(crs, aml_irq_no_flags(7)); - aml_append(dev, aml_name_decl("_CRS", crs)); - - return dev; -} - -static Aml *build_com_device_aml(uint8_t uid) -{ - Aml *dev; - Aml *crs; - Aml *method; - Aml *if_ctx; - Aml *else_ctx; - Aml *zero = aml_int(0); - Aml *is_present = aml_local(0); - const char *enabled_field = "CAEN"; - uint8_t irq = 4; - uint16_t io_port = 0x03F8; - - assert(uid == 1 || uid == 2); - if (uid == 2) { - enabled_field = "CBEN"; - irq = 3; - io_port = 0x02F8; - } - - dev = aml_device("COM%d", uid); - aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0501"))); - aml_append(dev, aml_name_decl("_UID", aml_int(uid))); - - method = aml_method("_STA", 0, AML_NOTSERIALIZED); - aml_append(method, aml_store(aml_name("%s", enabled_field), is_present)); - if_ctx = aml_if(aml_equal(is_present, zero)); - { - aml_append(if_ctx, aml_return(aml_int(0x00))); - } - aml_append(method, if_ctx); - else_ctx = aml_else(); - { - aml_append(else_ctx, aml_return(aml_int(0x0f))); - } - aml_append(method, else_ctx); - aml_append(dev, method); - - crs = aml_resource_template(); - aml_append(crs, aml_io(AML_DECODE16, io_port, io_port, 0x00, 0x08)); - aml_append(crs, aml_irq_no_flags(irq)); - aml_append(dev, aml_name_decl("_CRS", crs)); - - return dev; -} - static Aml *build_vmbus_device_aml(VMBusBridge *vmbus_bridge) { Aml *dev; @@ -1317,15 +1099,11 @@ static void build_isa_devices_aml(Aml *table) Aml *scope = aml_scope("_SB.PCI0.ISA"); Object *obj = object_resolve_path_type("", TYPE_ISA_BUS, &ambiguous); - aml_append(scope, build_rtc_device_aml()); aml_append(scope, build_kbd_device_aml()); aml_append(scope, build_mouse_device_aml()); if (fdc) { aml_append(scope, build_fdc_device_aml(fdc)); } - aml_append(scope, build_lpt_device_aml()); - aml_append(scope, build_com_device_aml(1)); - aml_append(scope, build_com_device_aml(2)); if (ambiguous) { error_report("Multiple ISA busses, unable to define IPMI ACPI data"); @@ -2338,36 +2116,6 @@ build_tpm_tcpa(GArray *table_data, BIOSLinker *linker, GArray *tcpalog) (void *)tcpa, "TCPA", sizeof(*tcpa), 2, NULL, NULL); } -static void -build_tpm2(GArray *table_data, BIOSLinker *linker, GArray *tcpalog) -{ - Acpi20TPM2 *tpm2_ptr = acpi_data_push(table_data, sizeof *tpm2_ptr); - unsigned log_addr_size = sizeof(tpm2_ptr->log_area_start_address); - unsigned log_addr_offset = - (char *)&tpm2_ptr->log_area_start_address - table_data->data; - - tpm2_ptr->platform_class = cpu_to_le16(TPM2_ACPI_CLASS_CLIENT); - if (TPM_IS_TIS_ISA(tpm_find())) { - tpm2_ptr->control_area_address = cpu_to_le64(0); - tpm2_ptr->start_method = cpu_to_le32(TPM2_START_METHOD_MMIO); - } else if (TPM_IS_CRB(tpm_find())) { - tpm2_ptr->control_area_address = cpu_to_le64(TPM_CRB_ADDR_CTRL); - tpm2_ptr->start_method = cpu_to_le32(TPM2_START_METHOD_CRB); - } else { - g_warn_if_reached(); - } - - tpm2_ptr->log_area_minimum_length = - cpu_to_le32(TPM_LOG_AREA_MINIMUM_SIZE); - - /* log area start address to be filled by Guest linker */ - bios_linker_loader_add_pointer(linker, ACPI_BUILD_TABLE_FILE, - log_addr_offset, log_addr_size, - ACPI_BUILD_TPMLOG_FILE, 0); - build_header(linker, table_data, - (void *)tpm2_ptr, "TPM2", sizeof(*tpm2_ptr), 4, NULL, NULL); -} - #define HOLE_640K_START (640 * KiB) #define HOLE_640K_END (1 * MiB) @@ -2471,6 +2219,11 @@ build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine) MEM_AFFINITY_ENABLED); } } + + if (machine->nvdimms_state->is_enabled) { + nvdimm_build_srat(table_data); + } + slots = (table_data->len - numa_start) / sizeof *numamem; for (; slots < pcms->numa_nodes + 2; slots++) { numamem = acpi_data_push(table_data, sizeof *numamem); @@ -2877,7 +2630,8 @@ void acpi_build(AcpiBuildTables *tables, MachineState *machine) aml_len += tables_blob->len - fadt; acpi_add_table(table_offsets, tables_blob); - build_madt(tables_blob, tables->linker, pcms); + acpi_build_madt(tables_blob, tables->linker, x86ms, + ACPI_DEVICE_IF(pcms->acpi_dev), true); vmgenid_dev = find_vmgenid_dev(); if (vmgenid_dev) { @@ -2891,10 +2645,10 @@ void acpi_build(AcpiBuildTables *tables, MachineState *machine) build_hpet(tables_blob, tables->linker); } if (misc.tpm_version != TPM_VERSION_UNSPEC) { - acpi_add_table(table_offsets, tables_blob); - build_tpm_tcpa(tables_blob, tables->linker, tables->tcpalog); - - if (misc.tpm_version == TPM_VERSION_2_0) { + if (misc.tpm_version == TPM_VERSION_1_2) { + acpi_add_table(table_offsets, tables_blob); + build_tpm_tcpa(tables_blob, tables->linker, tables->tcpalog); + } else { /* TPM_VERSION_2_0 */ acpi_add_table(table_offsets, tables_blob); build_tpm2(tables_blob, tables->linker, tables->tcpalog); } diff --git a/hw/i386/acpi-common.c b/hw/i386/acpi-common.c new file mode 100644 index 0000000000..ab9b00581a --- /dev/null +++ b/hw/i386/acpi-common.c @@ -0,0 +1,156 @@ +/* Support for generating ACPI tables and passing them to Guests + * + * Copyright (C) 2008-2010 Kevin O'Connor <kevin@koconnor.net> + * Copyright (C) 2006 Fabrice Bellard + * Copyright (C) 2013 Red Hat Inc + * + * Author: Michael S. Tsirkin <mst@redhat.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + + * You should have received a copy of the GNU General Public License along + * with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" + +#include "exec/memory.h" +#include "hw/acpi/acpi.h" +#include "hw/acpi/aml-build.h" +#include "hw/acpi/utils.h" +#include "hw/i386/pc.h" +#include "target/i386/cpu.h" + +#include "acpi-build.h" +#include "acpi-common.h" + +void pc_madt_cpu_entry(AcpiDeviceIf *adev, int uid, + const CPUArchIdList *apic_ids, GArray *entry) +{ + uint32_t apic_id = apic_ids->cpus[uid].arch_id; + + /* ACPI spec says that LAPIC entry for non present + * CPU may be omitted from MADT or it must be marked + * as disabled. However omitting non present CPU from + * MADT breaks hotplug on linux. So possible CPUs + * should be put in MADT but kept disabled. + */ + if (apic_id < 255) { + AcpiMadtProcessorApic *apic = acpi_data_push(entry, sizeof *apic); + + apic->type = ACPI_APIC_PROCESSOR; + apic->length = sizeof(*apic); + apic->processor_id = uid; + apic->local_apic_id = apic_id; + if (apic_ids->cpus[uid].cpu != NULL) { + apic->flags = cpu_to_le32(1); + } else { + apic->flags = cpu_to_le32(0); + } + } else { + AcpiMadtProcessorX2Apic *apic = acpi_data_push(entry, sizeof *apic); + + apic->type = ACPI_APIC_LOCAL_X2APIC; + apic->length = sizeof(*apic); + apic->uid = cpu_to_le32(uid); + apic->x2apic_id = cpu_to_le32(apic_id); + if (apic_ids->cpus[uid].cpu != NULL) { + apic->flags = cpu_to_le32(1); + } else { + apic->flags = cpu_to_le32(0); + } + } +} + +void acpi_build_madt(GArray *table_data, BIOSLinker *linker, + X86MachineState *x86ms, AcpiDeviceIf *adev, + bool has_pci) +{ + MachineClass *mc = MACHINE_GET_CLASS(x86ms); + const CPUArchIdList *apic_ids = mc->possible_cpu_arch_ids(MACHINE(x86ms)); + int madt_start = table_data->len; + AcpiDeviceIfClass *adevc = ACPI_DEVICE_IF_GET_CLASS(adev); + bool x2apic_mode = false; + + AcpiMultipleApicTable *madt; + AcpiMadtIoApic *io_apic; + AcpiMadtIntsrcovr *intsrcovr; + int i; + + madt = acpi_data_push(table_data, sizeof *madt); + madt->local_apic_address = cpu_to_le32(APIC_DEFAULT_ADDRESS); + madt->flags = cpu_to_le32(1); + + for (i = 0; i < apic_ids->len; i++) { + adevc->madt_cpu(adev, i, apic_ids, table_data); + if (apic_ids->cpus[i].arch_id > 254) { + x2apic_mode = true; + } + } + + io_apic = acpi_data_push(table_data, sizeof *io_apic); + io_apic->type = ACPI_APIC_IO; + io_apic->length = sizeof(*io_apic); + io_apic->io_apic_id = ACPI_BUILD_IOAPIC_ID; + io_apic->address = cpu_to_le32(IO_APIC_DEFAULT_ADDRESS); + io_apic->interrupt = cpu_to_le32(0); + + if (x86ms->apic_xrupt_override) { + intsrcovr = acpi_data_push(table_data, sizeof *intsrcovr); + intsrcovr->type = ACPI_APIC_XRUPT_OVERRIDE; + intsrcovr->length = sizeof(*intsrcovr); + intsrcovr->source = 0; + intsrcovr->gsi = cpu_to_le32(2); + intsrcovr->flags = cpu_to_le16(0); /* conforms to bus specifications */ + } + + if (has_pci) { + for (i = 1; i < 16; i++) { +#define ACPI_BUILD_PCI_IRQS ((1<<5) | (1<<9) | (1<<10) | (1<<11)) + if (!(ACPI_BUILD_PCI_IRQS & (1 << i))) { + /* No need for a INT source override structure. */ + continue; + } + intsrcovr = acpi_data_push(table_data, sizeof *intsrcovr); + intsrcovr->type = ACPI_APIC_XRUPT_OVERRIDE; + intsrcovr->length = sizeof(*intsrcovr); + intsrcovr->source = i; + intsrcovr->gsi = cpu_to_le32(i); + intsrcovr->flags = cpu_to_le16(0xd); /* active high, level triggered */ + } + } + + if (x2apic_mode) { + AcpiMadtLocalX2ApicNmi *local_nmi; + + local_nmi = acpi_data_push(table_data, sizeof *local_nmi); + local_nmi->type = ACPI_APIC_LOCAL_X2APIC_NMI; + local_nmi->length = sizeof(*local_nmi); + local_nmi->uid = 0xFFFFFFFF; /* all processors */ + local_nmi->flags = cpu_to_le16(0); + local_nmi->lint = 1; /* ACPI_LINT1 */ + } else { + AcpiMadtLocalNmi *local_nmi; + + local_nmi = acpi_data_push(table_data, sizeof *local_nmi); + local_nmi->type = ACPI_APIC_LOCAL_NMI; + local_nmi->length = sizeof(*local_nmi); + local_nmi->processor_id = 0xff; /* all processors */ + local_nmi->flags = cpu_to_le16(0); + local_nmi->lint = 1; /* ACPI_LINT1 */ + } + + build_header(linker, table_data, + (void *)(table_data->data + madt_start), "APIC", + table_data->len - madt_start, 1, NULL, NULL); +} + diff --git a/hw/i386/acpi-common.h b/hw/i386/acpi-common.h new file mode 100644 index 0000000000..9cac18dddf --- /dev/null +++ b/hw/i386/acpi-common.h @@ -0,0 +1,15 @@ +#ifndef HW_I386_ACPI_COMMON_H +#define HW_I386_ACPI_COMMON_H +#include "include/hw/acpi/acpi_dev_interface.h" + +#include "include/hw/acpi/bios-linker-loader.h" +#include "include/hw/i386/x86.h" + +/* Default IOAPIC ID */ +#define ACPI_BUILD_IOAPIC_ID 0x0 + +void acpi_build_madt(GArray *table_data, BIOSLinker *linker, + X86MachineState *x86ms, AcpiDeviceIf *adev, + bool has_pci); + +#endif diff --git a/hw/i386/xen/xen-hvm.c b/hw/i386/xen/xen-hvm.c index 041303a2fa..628bde5fac 100644 --- a/hw/i386/xen/xen-hvm.c +++ b/hw/i386/xen/xen-hvm.c @@ -9,6 +9,7 @@ */ #include "qemu/osdep.h" +#include "qemu/units.h" #include "cpu.h" #include "hw/pci/pci.h" @@ -231,7 +232,7 @@ static void xen_ram_init(PCMachineState *pcms, * Xen does not allocate the memory continuously, it keeps a * hole of the size computed above or passed in. */ - block_len = (1ULL << 32) + x86ms->above_4g_mem_size; + block_len = (4 * GiB) + x86ms->above_4g_mem_size; } memory_region_init_ram(&ram_memory, NULL, "xen.ram", block_len, &error_fatal); diff --git a/hw/intc/puv3_intc.c b/hw/intc/puv3_intc.c index e018955ce8..090d4839d1 100644 --- a/hw/intc/puv3_intc.c +++ b/hw/intc/puv3_intc.c @@ -16,6 +16,7 @@ #undef DEBUG_PUV3 #include "hw/unicore32/puv3.h" #include "qemu/module.h" +#include "qemu/log.h" #define TYPE_PUV3_INTC "puv3_intc" #define PUV3_INTC(obj) OBJECT_CHECK(PUV3INTCState, (obj), TYPE_PUV3_INTC) @@ -68,7 +69,9 @@ static uint64_t puv3_intc_read(void *opaque, hwaddr offset, ret = s->reg_ICPR; /* the same value with ICPR */ break; default: - DPRINTF("Bad offset %x\n", (int)offset); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad read offset 0x%"HWADDR_PRIx"\n", + __func__, offset); } DPRINTF("offset 0x%x, value 0x%x\n", offset, ret); return ret; @@ -88,7 +91,9 @@ static void puv3_intc_write(void *opaque, hwaddr offset, s->reg_ICMR = value; break; default: - DPRINTF("Bad offset 0x%x\n", (int)offset); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad write offset 0x%"HWADDR_PRIx"\n", + __func__, offset); return; } puv3_intc_update(s); diff --git a/hw/isa/apm.c b/hw/isa/apm.c index 6300b1ba7a..bce266b957 100644 --- a/hw/isa/apm.c +++ b/hw/isa/apm.c @@ -24,14 +24,8 @@ #include "hw/isa/apm.h" #include "hw/pci/pci.h" #include "migration/vmstate.h" +#include "trace.h" -//#define DEBUG - -#ifdef DEBUG -# define APM_DPRINTF(format, ...) printf(format, ## __VA_ARGS__) -#else -# define APM_DPRINTF(format, ...) do { } while (0) -#endif /* fixed I/O location */ #define APM_STS_IOPORT 0xb3 @@ -41,8 +35,8 @@ static void apm_ioport_writeb(void *opaque, hwaddr addr, uint64_t val, { APMState *apm = opaque; addr &= 1; - APM_DPRINTF("apm_ioport_writeb addr=0x%" HWADDR_PRIx - " val=0x%02" PRIx64 "\n", addr, val); + + trace_apm_io_write(addr, val); if (addr == 0) { apm->apmc = val; @@ -65,7 +59,8 @@ static uint64_t apm_ioport_readb(void *opaque, hwaddr addr, unsigned size) } else { val = apm->apms; } - APM_DPRINTF("apm_ioport_readb addr=0x%" HWADDR_PRIx " val=0x%02x\n", addr, val); + trace_apm_io_read(addr, val); + return val; } diff --git a/hw/isa/trace-events b/hw/isa/trace-events index 202f8938e7..3544c6213c 100644 --- a/hw/isa/trace-events +++ b/hw/isa/trace-events @@ -9,3 +9,7 @@ superio_create_ide(int id, uint16_t base, unsigned int irq) "id=%d, base 0x%03x, # pc87312.c pc87312_io_read(uint32_t addr, uint32_t val) "read addr=0x%x val=0x%x" pc87312_io_write(uint32_t addr, uint32_t val) "write addr=0x%x val=0x%x" + +# apm.c +apm_io_read(uint8_t addr, uint8_t val) "read addr=0x%x val=0x%02x" +apm_io_write(uint8_t addr, uint8_t val) "write addr=0x%x val=0x%02x" diff --git a/hw/misc/auxbus.c b/hw/misc/auxbus.c index f8e7b97971..06aabf20c5 100644 --- a/hw/misc/auxbus.c +++ b/hw/misc/auxbus.c @@ -196,7 +196,7 @@ AUXReply aux_request(AUXBus *bus, AUXCommand cmd, uint32_t address, } break; default: - DPRINTF("Not implemented!\n"); + qemu_log_mask(LOG_UNIMP, "AUX cmd=%u not implemented\n", cmd); return AUX_NACK; } diff --git a/hw/misc/puv3_pm.c b/hw/misc/puv3_pm.c index c213500d9c..8989d363cd 100644 --- a/hw/misc/puv3_pm.c +++ b/hw/misc/puv3_pm.c @@ -15,6 +15,7 @@ #undef DEBUG_PUV3 #include "hw/unicore32/puv3.h" #include "qemu/module.h" +#include "qemu/log.h" #define TYPE_PUV3_PM "puv3_pm" #define PUV3_PM(obj) OBJECT_CHECK(PUV3PMState, (obj), TYPE_PUV3_PM) @@ -73,7 +74,9 @@ static uint64_t puv3_pm_read(void *opaque, hwaddr offset, ret = 0x7; break; default: - DPRINTF("Bad offset 0x%x\n", offset); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad read offset 0x%"HWADDR_PRIx"\n", + __func__, offset); } DPRINTF("offset 0x%x, value 0x%x\n", offset, ret); @@ -105,7 +108,9 @@ static void puv3_pm_write(void *opaque, hwaddr offset, case 0x38: break; default: - DPRINTF("Bad offset 0x%x\n", offset); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad write offset 0x%"HWADDR_PRIx"\n", + __func__, offset); } DPRINTF("offset 0x%x, value 0x%x\n", offset, value); } diff --git a/hw/openrisc/openrisc_sim.c b/hw/openrisc/openrisc_sim.c index d08ce61811..02f5259e5e 100644 --- a/hw/openrisc/openrisc_sim.c +++ b/hw/openrisc/openrisc_sim.c @@ -134,6 +134,7 @@ static void openrisc_sim_init(MachineState *machine) int n; unsigned int smp_cpus = machine->smp.cpus; + assert(smp_cpus >= 1 && smp_cpus <= 2); for (n = 0; n < smp_cpus; n++) { cpu = OPENRISC_CPU(cpu_create(machine->cpu_type)); if (cpu == NULL) { diff --git a/hw/pci-host/i440fx.c b/hw/pci-host/i440fx.c index 0adbd77553..aefb416c8f 100644 --- a/hw/pci-host/i440fx.c +++ b/hw/pci-host/i440fx.c @@ -23,6 +23,7 @@ */ #include "qemu/osdep.h" +#include "qemu/units.h" #include "qemu/range.h" #include "hw/i386/pc.h" #include "hw/pci/pci.h" @@ -301,7 +302,7 @@ PCIBus *i440fx_init(const char *host_type, const char *pci_type, memory_region_set_enabled(&f->smram_region, true); /* smram, as seen by SMM CPUs */ - memory_region_init(&f->smram, OBJECT(d), "smram", 1ull << 32); + memory_region_init(&f->smram, OBJECT(d), "smram", 4 * GiB); memory_region_set_enabled(&f->smram, true); memory_region_init_alias(&f->low_smram, OBJECT(d), "smram-low", f->ram_memory, 0xa0000, 0x20000); diff --git a/hw/pci-host/prep.c b/hw/pci-host/prep.c index 1a02e9a670..88e2fc66a9 100644 --- a/hw/pci-host/prep.c +++ b/hw/pci-host/prep.c @@ -294,7 +294,7 @@ static void raven_pcihost_initfn(Object *obj) &s->pci_memory, &s->pci_io, 0, TYPE_PCI_BUS); /* Bus master address space */ - memory_region_init(&s->bm, obj, "bm-raven", UINT32_MAX); + memory_region_init(&s->bm, obj, "bm-raven", 4 * GiB); memory_region_init_alias(&s->bm_pci_memory_alias, obj, "bm-pci-memory", &s->pci_memory, 0, memory_region_size(&s->pci_memory)); diff --git a/hw/pci-host/q35.c b/hw/pci-host/q35.c index 352aeecfa7..b788f17b2c 100644 --- a/hw/pci-host/q35.c +++ b/hw/pci-host/q35.c @@ -589,7 +589,7 @@ static void mch_realize(PCIDevice *d, Error **errp) memory_region_set_enabled(&mch->open_high_smram, false); /* smram, as seen by SMM CPUs */ - memory_region_init(&mch->smram, OBJECT(mch), "smram", 1ull << 32); + memory_region_init(&mch->smram, OBJECT(mch), "smram", 4 * GiB); memory_region_set_enabled(&mch->smram, true); memory_region_init_alias(&mch->low_smram, OBJECT(mch), "smram-low", mch->ram_memory, MCH_HOST_BRIDGE_SMRAM_C_BASE, diff --git a/hw/pci-host/versatile.c b/hw/pci-host/versatile.c index cfb9a78ea6..8ddfb8772a 100644 --- a/hw/pci-host/versatile.c +++ b/hw/pci-host/versatile.c @@ -8,6 +8,7 @@ */ #include "qemu/osdep.h" +#include "qemu/units.h" #include "hw/sysbus.h" #include "migration/vmstate.h" #include "hw/irq.h" @@ -399,8 +400,8 @@ static void pci_vpb_realize(DeviceState *dev, Error **errp) pci_map_irq_fn mapfn; int i; - memory_region_init(&s->pci_io_space, OBJECT(s), "pci_io", 1ULL << 32); - memory_region_init(&s->pci_mem_space, OBJECT(s), "pci_mem", 1ULL << 32); + memory_region_init(&s->pci_io_space, OBJECT(s), "pci_io", 4 * GiB); + memory_region_init(&s->pci_mem_space, OBJECT(s), "pci_mem", 4 * GiB); pci_root_bus_new_inplace(&s->pci_bus, sizeof(s->pci_bus), dev, "pci", &s->pci_mem_space, &s->pci_io_space, diff --git a/hw/pci/msix.c b/hw/pci/msix.c index 2c7ead7667..67e34f34d6 100644 --- a/hw/pci/msix.c +++ b/hw/pci/msix.c @@ -200,6 +200,9 @@ static const MemoryRegionOps msix_table_mmio_ops = { .endianness = DEVICE_LITTLE_ENDIAN, .valid = { .min_access_size = 4, + .max_access_size = 8, + }, + .impl = { .max_access_size = 4, }, }; @@ -228,6 +231,9 @@ static const MemoryRegionOps msix_pba_mmio_ops = { .endianness = DEVICE_LITTLE_ENDIAN, .valid = { .min_access_size = 4, + .max_access_size = 8, + }, + .impl = { .max_access_size = 4, }, }; diff --git a/hw/pci/pci.c b/hw/pci/pci.c index 70c66965f5..a60cf3ae3b 100644 --- a/hw/pci/pci.c +++ b/hw/pci/pci.c @@ -1381,6 +1381,8 @@ uint32_t pci_default_read_config(PCIDevice *d, { uint32_t val = 0; + assert(address + len <= pci_config_size(d)); + if (pci_is_express_downstream_port(d) && ranges_overlap(address, len, d->exp.exp_cap + PCI_EXP_LNKSTA, 2)) { pcie_sync_bridge_lnk(d); @@ -1394,6 +1396,8 @@ void pci_default_write_config(PCIDevice *d, uint32_t addr, uint32_t val_in, int int i, was_irq_disabled = pci_irq_disabled(d); uint32_t val = val_in; + assert(addr + l <= pci_config_size(d)); + for (i = 0; i < l; val >>= 8, ++i) { uint8_t wmask = d->wmask[addr + i]; uint8_t w1cmask = d->w1cmask[addr + i]; @@ -1772,6 +1776,7 @@ static PciDeviceInfo *qmp_query_pci_device(PCIDevice *dev, PCIBus *bus, info->regions = qmp_query_pci_regions(dev); info->qdev_id = g_strdup(dev->qdev.id ? dev->qdev.id : ""); + info->irq_pin = dev->config[PCI_INTERRUPT_PIN]; if (dev->config[PCI_INTERRUPT_PIN] != 0) { info->has_irq = true; info->irq = dev->config[PCI_INTERRUPT_LINE]; @@ -1887,7 +1892,18 @@ PCIDevice *pci_nic_init_nofail(NICInfo *nd, PCIBus *rootbus, if (test_bit(DEVICE_CATEGORY_NETWORK, dc->categories) && dc->user_creatable) { const char *name = object_class_get_name(list->data); - g_ptr_array_add(pci_nic_models, (gpointer)name); + /* + * A network device might also be something else than a NIC, see + * e.g. the "rocker" device. Thus we have to look for the "netdev" + * property, too. Unfortunately, some devices like virtio-net only + * create this property during instance_init, so we have to create + * a temporary instance here to be able to check it. + */ + Object *obj = object_new_with_class(OBJECT_CLASS(dc)); + if (object_property_find(obj, "netdev", NULL)) { + g_ptr_array_add(pci_nic_models, (gpointer)name); + } + object_unref(obj); } next = list->next; g_slist_free_1(list); diff --git a/hw/pci/pci_bridge.c b/hw/pci/pci_bridge.c index 97967d12eb..3789c17edc 100644 --- a/hw/pci/pci_bridge.c +++ b/hw/pci/pci_bridge.c @@ -30,6 +30,7 @@ */ #include "qemu/osdep.h" +#include "qemu/units.h" #include "hw/pci/pci_bridge.h" #include "hw/pci/pci_bus.h" #include "qemu/module.h" @@ -381,7 +382,7 @@ void pci_bridge_initfn(PCIDevice *dev, const char *typename) memory_region_init(&br->address_space_mem, OBJECT(br), "pci_bridge_pci", UINT64_MAX); sec_bus->address_space_io = &br->address_space_io; memory_region_init(&br->address_space_io, OBJECT(br), "pci_bridge_io", - UINT32_MAX); + 4 * GiB); br->windows = pci_bridge_region_init(br); QLIST_INIT(&sec_bus->child); QLIST_INSERT_HEAD(&parent->child, sec_bus, sibling); @@ -422,14 +423,14 @@ int pci_bridge_qemu_reserve_cap_init(PCIDevice *dev, int cap_offset, } if (res_reserve.mem_non_pref != (uint64_t)-1 && - res_reserve.mem_non_pref >= (1ULL << 32)) { + res_reserve.mem_non_pref >= 4 * GiB) { error_setg(errp, "PCI resource reserve cap: mem-reserve must be less than 4G"); return -EINVAL; } if (res_reserve.mem_pref_32 != (uint64_t)-1 && - res_reserve.mem_pref_32 >= (1ULL << 32)) { + res_reserve.mem_pref_32 >= 4 * GiB) { error_setg(errp, "PCI resource reserve cap: pref32-reserve must be less than 4G"); return -EINVAL; diff --git a/hw/pci/pcie.c b/hw/pci/pcie.c index f50e10b8fb..5b9c022d91 100644 --- a/hw/pci/pcie.c +++ b/hw/pci/pcie.c @@ -407,6 +407,17 @@ static void pcie_cap_slot_plug_common(PCIDevice *hotplug_dev, DeviceState *dev, void pcie_cap_slot_pre_plug_cb(HotplugHandler *hotplug_dev, DeviceState *dev, Error **errp) { + PCIDevice *hotplug_pdev = PCI_DEVICE(hotplug_dev); + uint8_t *exp_cap = hotplug_pdev->config + hotplug_pdev->exp.exp_cap; + uint32_t sltcap = pci_get_word(exp_cap + PCI_EXP_SLTCAP); + + /* Check if hot-plug is disabled on the slot */ + if (dev->hotplugged && (sltcap & PCI_EXP_SLTCAP_HPC) == 0) { + error_setg(errp, "Hot-plug failed: unsupported by the port device '%s'", + DEVICE(hotplug_pdev)->id); + return; + } + pcie_cap_slot_plug_common(PCI_DEVICE(hotplug_dev), dev, errp); } @@ -415,7 +426,6 @@ void pcie_cap_slot_plug_cb(HotplugHandler *hotplug_dev, DeviceState *dev, { PCIDevice *hotplug_pdev = PCI_DEVICE(hotplug_dev); uint8_t *exp_cap = hotplug_pdev->config + hotplug_pdev->exp.exp_cap; - uint32_t sltcap = pci_get_word(exp_cap + PCI_EXP_SLTCAP); PCIDevice *pci_dev = PCI_DEVICE(dev); /* Don't send event when device is enabled during qemu machine creation: @@ -431,13 +441,6 @@ void pcie_cap_slot_plug_cb(HotplugHandler *hotplug_dev, DeviceState *dev, return; } - /* Check if hot-plug is disabled on the slot */ - if ((sltcap & PCI_EXP_SLTCAP_HPC) == 0) { - error_setg(errp, "Hot-plug failed: unsupported by the port device '%s'", - DEVICE(hotplug_pdev)->id); - return; - } - /* To enable multifunction hot-plug, we just ensure the function * 0 added last. When function 0 is added, we set the sltsta and * inform OS via event notification. diff --git a/hw/rtc/mc146818rtc.c b/hw/rtc/mc146818rtc.c index 9c30cbdcd7..1e9fa0f33f 100644 --- a/hw/rtc/mc146818rtc.c +++ b/hw/rtc/mc146818rtc.c @@ -27,6 +27,7 @@ #include "qemu/cutils.h" #include "qemu/module.h" #include "qemu/bcd.h" +#include "hw/acpi/aml-build.h" #include "hw/irq.h" #include "hw/qdev-properties.h" #include "qemu/timer.h" @@ -1007,13 +1008,36 @@ static void rtc_resetdev(DeviceState *d) } } +static void rtc_build_aml(ISADevice *isadev, Aml *scope) +{ + Aml *dev; + Aml *crs; + + /* + * Reserving 8 io ports here, following what physical hardware + * does, even though qemu only responds to the first two ports. + */ + crs = aml_resource_template(); + aml_append(crs, aml_io(AML_DECODE16, RTC_ISA_BASE, RTC_ISA_BASE, + 0x01, 0x08)); + aml_append(crs, aml_irq_no_flags(RTC_ISA_IRQ)); + + dev = aml_device("RTC"); + aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0B00"))); + aml_append(dev, aml_name_decl("_CRS", crs)); + + aml_append(scope, dev); +} + static void rtc_class_initfn(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); + ISADeviceClass *isa = ISA_DEVICE_CLASS(klass); dc->realize = rtc_realizefn; dc->reset = rtc_resetdev; dc->vmsd = &vmstate_rtc; + isa->build_aml = rtc_build_aml; device_class_set_props(dc, mc146818rtc_properties); } diff --git a/hw/semihosting/console.c b/hw/semihosting/console.c index 6346bd7f50..22e7827824 100644 --- a/hw/semihosting/console.c +++ b/hw/semihosting/console.c @@ -23,7 +23,6 @@ #include "exec/exec-all.h" #include "qemu/log.h" #include "chardev/char.h" -#include <pthread.h> #include "chardev/char-fe.h" #include "sysemu/sysemu.h" #include "qemu/main-loop.h" diff --git a/hw/timer/puv3_ost.c b/hw/timer/puv3_ost.c index 697519593b..f76b0bb1ca 100644 --- a/hw/timer/puv3_ost.c +++ b/hw/timer/puv3_ost.c @@ -14,6 +14,7 @@ #include "hw/irq.h" #include "hw/ptimer.h" #include "qemu/module.h" +#include "qemu/log.h" #undef DEBUG_PUV3 #include "hw/unicore32/puv3.h" @@ -52,7 +53,9 @@ static uint64_t puv3_ost_read(void *opaque, hwaddr offset, ret = s->reg_OIER; break; default: - DPRINTF("Bad offset %x\n", (int)offset); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad read offset 0x%"HWADDR_PRIx"\n", + __func__, offset); } DPRINTF("offset 0x%x, value 0x%x\n", offset, ret); return ret; @@ -88,7 +91,9 @@ static void puv3_ost_write(void *opaque, hwaddr offset, s->reg_OIER = value; break; default: - DPRINTF("Bad offset %x\n", (int)offset); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad write offset 0x%"HWADDR_PRIx"\n", + __func__, offset); } } diff --git a/hw/unicore32/puv3.c b/hw/unicore32/puv3.c index 7f9c0238fe..eacacb4249 100644 --- a/hw/unicore32/puv3.c +++ b/hw/unicore32/puv3.c @@ -16,8 +16,6 @@ #include "hw/boards.h" #include "hw/loader.h" #include "sysemu/qtest.h" - -#undef DEBUG_PUV3 #include "hw/unicore32/puv3.h" #include "hw/input/i8042.h" #include "hw/irq.h" diff --git a/hw/vfio/pci-quirks.c b/hw/vfio/pci-quirks.c index f2155ddb1d..d304c81148 100644 --- a/hw/vfio/pci-quirks.c +++ b/hw/vfio/pci-quirks.c @@ -11,6 +11,7 @@ */ #include "qemu/osdep.h" +#include "config-devices.h" #include "exec/memop.h" #include "qemu/units.h" #include "qemu/error-report.h" @@ -1567,18 +1568,6 @@ static int vfio_add_nv_gpudirect_cap(VFIOPCIDevice *vdev, Error **errp) return 0; } -int vfio_add_virt_caps(VFIOPCIDevice *vdev, Error **errp) -{ - int ret; - - ret = vfio_add_nv_gpudirect_cap(vdev, errp); - if (ret) { - return ret; - } - - return 0; -} - static void vfio_pci_nvlink2_get_tgt(Object *obj, Visitor *v, const char *name, void *opaque, Error **errp) @@ -1709,3 +1698,75 @@ free_exit: return ret; } + +/* + * The VMD endpoint provides a real PCIe domain to the guest and the guest + * kernel performs enumeration of the VMD sub-device domain. Guest transactions + * to VMD sub-devices go through MMU translation from guest addresses to + * physical addresses. When MMIO goes to an endpoint after being translated to + * physical addresses, the bridge rejects the transaction because the window + * has been programmed with guest addresses. + * + * VMD can use the Host Physical Address in order to correctly program the + * bridge windows in its PCIe domain. VMD device 28C0 has HPA shadow registers + * located at offset 0x2000 in MEMBAR2 (BAR 4). This quirk provides the HPA + * shadow registers in a vendor-specific capability register for devices + * without native support. The position of 0xE8-0xFF is in the reserved range + * of the VMD device capability space following the Power Management + * Capability. + */ +#define VMD_SHADOW_CAP_VER 1 +#define VMD_SHADOW_CAP_LEN 24 +static int vfio_add_vmd_shadow_cap(VFIOPCIDevice *vdev, Error **errp) +{ + uint8_t membar_phys[16]; + int ret, pos = 0xE8; + + if (!(vfio_pci_is(vdev, PCI_VENDOR_ID_INTEL, 0x201D) || + vfio_pci_is(vdev, PCI_VENDOR_ID_INTEL, 0x467F) || + vfio_pci_is(vdev, PCI_VENDOR_ID_INTEL, 0x4C3D) || + vfio_pci_is(vdev, PCI_VENDOR_ID_INTEL, 0x9A0B))) { + return 0; + } + + ret = pread(vdev->vbasedev.fd, membar_phys, 16, + vdev->config_offset + PCI_BASE_ADDRESS_2); + if (ret != 16) { + error_report("VMD %s cannot read MEMBARs (%d)", + vdev->vbasedev.name, ret); + return -EFAULT; + } + + ret = pci_add_capability(&vdev->pdev, PCI_CAP_ID_VNDR, pos, + VMD_SHADOW_CAP_LEN, errp); + if (ret < 0) { + error_prepend(errp, "Failed to add VMD MEMBAR Shadow cap: "); + return ret; + } + + memset(vdev->emulated_config_bits + pos, 0xFF, VMD_SHADOW_CAP_LEN); + pos += PCI_CAP_FLAGS; + pci_set_byte(vdev->pdev.config + pos++, VMD_SHADOW_CAP_LEN); + pci_set_byte(vdev->pdev.config + pos++, VMD_SHADOW_CAP_VER); + pci_set_long(vdev->pdev.config + pos, 0x53484457); /* SHDW */ + memcpy(vdev->pdev.config + pos + 4, membar_phys, 16); + + return 0; +} + +int vfio_add_virt_caps(VFIOPCIDevice *vdev, Error **errp) +{ + int ret; + + ret = vfio_add_nv_gpudirect_cap(vdev, errp); + if (ret) { + return ret; + } + + ret = vfio_add_vmd_shadow_cap(vdev, errp); + if (ret) { + return ret; + } + + return 0; +} diff --git a/hw/virtio/Makefile.objs b/hw/virtio/Makefile.objs index 4e4d39a0a4..13e75f171f 100644 --- a/hw/virtio/Makefile.objs +++ b/hw/virtio/Makefile.objs @@ -17,10 +17,12 @@ obj-$(CONFIG_VIRTIO_PMEM) += virtio-pmem.o common-obj-$(call land,$(CONFIG_VIRTIO_PMEM),$(CONFIG_VIRTIO_PCI)) += virtio-pmem-pci.o obj-$(call land,$(CONFIG_VHOST_USER_FS),$(CONFIG_VIRTIO_PCI)) += vhost-user-fs-pci.o obj-$(CONFIG_VIRTIO_IOMMU) += virtio-iommu.o -obj-$(CONFIG_VHOST_VSOCK) += vhost-vsock.o +obj-$(CONFIG_VHOST_VSOCK) += vhost-vsock-common.o vhost-vsock.o +obj-$(CONFIG_VHOST_USER_VSOCK) += vhost-vsock-common.o vhost-user-vsock.o ifeq ($(CONFIG_VIRTIO_PCI),y) obj-$(CONFIG_VHOST_VSOCK) += vhost-vsock-pci.o +obj-$(CONFIG_VHOST_USER_VSOCK) += vhost-user-vsock-pci.o obj-$(CONFIG_VHOST_USER_BLK) += vhost-user-blk-pci.o obj-$(CONFIG_VHOST_USER_INPUT) += vhost-user-input-pci.o obj-$(CONFIG_VHOST_USER_SCSI) += vhost-user-scsi-pci.o diff --git a/hw/virtio/trace-events b/hw/virtio/trace-events index e83500bee9..6427a0047d 100644 --- a/hw/virtio/trace-events +++ b/hw/virtio/trace-events @@ -5,7 +5,8 @@ vhost_commit(bool started, bool changed) "Started: %d Changed: %d" vhost_region_add_section(const char *name, uint64_t gpa, uint64_t size, uint64_t host) "%s: 0x%"PRIx64"+0x%"PRIx64" @ 0x%"PRIx64 vhost_region_add_section_merge(const char *name, uint64_t new_size, uint64_t gpa, uint64_t owr) "%s: size: 0x%"PRIx64 " gpa: 0x%"PRIx64 " owr: 0x%"PRIx64 vhost_region_add_section_aligned(const char *name, uint64_t gpa, uint64_t size, uint64_t host) "%s: 0x%"PRIx64"+0x%"PRIx64" @ 0x%"PRIx64 -vhost_section(const char *name, int r) "%s:%d" +vhost_section(const char *name) "%s" +vhost_reject_section(const char *name, int d) "%s:%d" vhost_iotlb_miss(void *dev, int step) "%p step %d" # vhost-user.c diff --git a/hw/virtio/vhost-user-vsock-pci.c b/hw/virtio/vhost-user-vsock-pci.c new file mode 100644 index 0000000000..0a6847e6fc --- /dev/null +++ b/hw/virtio/vhost-user-vsock-pci.c @@ -0,0 +1,84 @@ +/* + * Vhost-user vsock PCI Bindings + * + * Copyright 2020 Red Hat, Inc. + * + * 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 "virtio-pci.h" +#include "hw/qdev-properties.h" +#include "hw/virtio/vhost-user-vsock.h" + +typedef struct VHostUserVSockPCI VHostUserVSockPCI; + +/* + * vhost-user-vsock-pci: This extends VirtioPCIProxy. + */ +#define TYPE_VHOST_USER_VSOCK_PCI "vhost-user-vsock-pci-base" +#define VHOST_USER_VSOCK_PCI(obj) \ + OBJECT_CHECK(VHostUserVSockPCI, (obj), TYPE_VHOST_USER_VSOCK_PCI) + +struct VHostUserVSockPCI { + VirtIOPCIProxy parent_obj; + VHostUserVSock vdev; +}; + +/* vhost-user-vsock-pci */ + +static Property vhost_user_vsock_pci_properties[] = { + DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, 3), + DEFINE_PROP_END_OF_LIST(), +}; + +static void vhost_user_vsock_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) +{ + VHostUserVSockPCI *dev = VHOST_USER_VSOCK_PCI(vpci_dev); + DeviceState *vdev = DEVICE(&dev->vdev); + + qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus)); + object_property_set_bool(OBJECT(vdev), true, "realized", errp); +} + +static void vhost_user_vsock_pci_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass); + PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); + k->realize = vhost_user_vsock_pci_realize; + set_bit(DEVICE_CATEGORY_MISC, dc->categories); + device_class_set_props(dc, vhost_user_vsock_pci_properties); + pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET; + pcidev_k->device_id = PCI_DEVICE_ID_VIRTIO_VSOCK; + pcidev_k->revision = 0x00; + pcidev_k->class_id = PCI_CLASS_COMMUNICATION_OTHER; +} + +static void vhost_user_vsock_pci_instance_init(Object *obj) +{ + VHostUserVSockPCI *dev = VHOST_USER_VSOCK_PCI(obj); + + virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), + TYPE_VHOST_USER_VSOCK); +} + +static const VirtioPCIDeviceTypeInfo vhost_user_vsock_pci_info = { + .base_name = TYPE_VHOST_USER_VSOCK_PCI, + .generic_name = "vhost-user-vsock-pci", + .transitional_name = "vhost-user-vsock-pci-transitional", + .non_transitional_name = "vhost-user-vsock-pci-non-transitional", + .instance_size = sizeof(VHostUserVSockPCI), + .instance_init = vhost_user_vsock_pci_instance_init, + .class_init = vhost_user_vsock_pci_class_init, +}; + +static void virtio_pci_vhost_register(void) +{ + virtio_pci_types_register(&vhost_user_vsock_pci_info); +} + +type_init(virtio_pci_vhost_register) diff --git a/hw/virtio/vhost-user-vsock.c b/hw/virtio/vhost-user-vsock.c new file mode 100644 index 0000000000..3534a39d62 --- /dev/null +++ b/hw/virtio/vhost-user-vsock.c @@ -0,0 +1,181 @@ +/* + * Vhost-user vsock virtio device + * + * Copyright 2020 Red Hat, Inc. + * + * 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 "qapi/error.h" +#include "qemu/error-report.h" +#include "hw/qdev-properties.h" +#include "hw/virtio/vhost-user-vsock.h" + +static const int user_feature_bits[] = { + VIRTIO_F_VERSION_1, + VIRTIO_RING_F_INDIRECT_DESC, + VIRTIO_RING_F_EVENT_IDX, + VIRTIO_F_NOTIFY_ON_EMPTY, + VHOST_INVALID_FEATURE_BIT +}; + +static void vuv_get_config(VirtIODevice *vdev, uint8_t *config) +{ + VHostUserVSock *vsock = VHOST_USER_VSOCK(vdev); + + memcpy(config, &vsock->vsockcfg, sizeof(struct virtio_vsock_config)); +} + +static int vuv_handle_config_change(struct vhost_dev *dev) +{ + VHostUserVSock *vsock = VHOST_USER_VSOCK(dev->vdev); + int ret = vhost_dev_get_config(dev, (uint8_t *)&vsock->vsockcfg, + sizeof(struct virtio_vsock_config)); + if (ret < 0) { + error_report("get config space failed"); + return -1; + } + + virtio_notify_config(dev->vdev); + + return 0; +} + +const VhostDevConfigOps vsock_ops = { + .vhost_dev_config_notifier = vuv_handle_config_change, +}; + +static void vuv_set_status(VirtIODevice *vdev, uint8_t status) +{ + VHostVSockCommon *vvc = VHOST_VSOCK_COMMON(vdev); + bool should_start = status & VIRTIO_CONFIG_S_DRIVER_OK; + + if (!vdev->vm_running) { + should_start = false; + } + + if (vvc->vhost_dev.started == should_start) { + return; + } + + if (should_start) { + int ret = vhost_vsock_common_start(vdev); + if (ret < 0) { + return; + } + } else { + vhost_vsock_common_stop(vdev); + } +} + +static uint64_t vuv_get_features(VirtIODevice *vdev, + uint64_t features, + Error **errp) +{ + VHostVSockCommon *vvc = VHOST_VSOCK_COMMON(vdev); + + return vhost_get_features(&vvc->vhost_dev, user_feature_bits, features); +} + +static const VMStateDescription vuv_vmstate = { + .name = "vhost-user-vsock", + .unmigratable = 1, +}; + +static void vuv_device_realize(DeviceState *dev, Error **errp) +{ + VHostVSockCommon *vvc = VHOST_VSOCK_COMMON(dev); + VirtIODevice *vdev = VIRTIO_DEVICE(dev); + VHostUserVSock *vsock = VHOST_USER_VSOCK(dev); + int ret; + + if (!vsock->conf.chardev.chr) { + error_setg(errp, "missing chardev"); + return; + } + + if (!vhost_user_init(&vsock->vhost_user, &vsock->conf.chardev, errp)) { + return; + } + + vhost_vsock_common_realize(vdev, "vhost-user-vsock"); + + vhost_dev_set_config_notifier(&vvc->vhost_dev, &vsock_ops); + + ret = vhost_dev_init(&vvc->vhost_dev, &vsock->vhost_user, + VHOST_BACKEND_TYPE_USER, 0); + if (ret < 0) { + error_setg_errno(errp, -ret, "vhost_dev_init failed"); + goto err_virtio; + } + + ret = vhost_dev_get_config(&vvc->vhost_dev, (uint8_t *)&vsock->vsockcfg, + sizeof(struct virtio_vsock_config)); + if (ret < 0) { + error_setg_errno(errp, -ret, "get config space failed"); + goto err_vhost_dev; + } + + return; + +err_vhost_dev: + vhost_dev_cleanup(&vvc->vhost_dev); +err_virtio: + vhost_vsock_common_unrealize(vdev); + vhost_user_cleanup(&vsock->vhost_user); + return; +} + +static void vuv_device_unrealize(DeviceState *dev) +{ + VHostVSockCommon *vvc = VHOST_VSOCK_COMMON(dev); + VirtIODevice *vdev = VIRTIO_DEVICE(dev); + VHostUserVSock *vsock = VHOST_USER_VSOCK(dev); + + /* This will stop vhost backend if appropriate. */ + vuv_set_status(vdev, 0); + + vhost_dev_cleanup(&vvc->vhost_dev); + + vhost_vsock_common_unrealize(vdev); + + vhost_user_cleanup(&vsock->vhost_user); + +} + +static Property vuv_properties[] = { + DEFINE_PROP_CHR("chardev", VHostUserVSock, conf.chardev), + DEFINE_PROP_END_OF_LIST(), +}; + +static void vuv_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass); + + device_class_set_props(dc, vuv_properties); + dc->vmsd = &vuv_vmstate; + vdc->realize = vuv_device_realize; + vdc->unrealize = vuv_device_unrealize; + vdc->get_features = vuv_get_features; + vdc->get_config = vuv_get_config; + vdc->set_status = vuv_set_status; +} + +static const TypeInfo vuv_info = { + .name = TYPE_VHOST_USER_VSOCK, + .parent = TYPE_VHOST_VSOCK_COMMON, + .instance_size = sizeof(VHostUserVSock), + .class_init = vuv_class_init, +}; + +static void vuv_register_types(void) +{ + type_register_static(&vuv_info); +} + +type_init(vuv_register_types) diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c index ec21e8fbe8..4d6cd4e58a 100644 --- a/hw/virtio/vhost-user.c +++ b/hw/virtio/vhost-user.c @@ -35,11 +35,29 @@ #include <linux/userfaultfd.h> #endif -#define VHOST_MEMORY_MAX_NREGIONS 8 +#define VHOST_MEMORY_BASELINE_NREGIONS 8 #define VHOST_USER_F_PROTOCOL_FEATURES 30 #define VHOST_USER_SLAVE_MAX_FDS 8 /* + * Set maximum number of RAM slots supported to + * the maximum number supported by the target + * hardware plaform. + */ +#if defined(TARGET_X86) || defined(TARGET_X86_64) || \ + defined(TARGET_ARM) || defined(TARGET_ARM_64) +#include "hw/acpi/acpi.h" +#define VHOST_USER_MAX_RAM_SLOTS ACPI_MAX_RAM_SLOTS + +#elif defined(TARGET_PPC) || defined(TARGET_PPC_64) +#include "hw/ppc/spapr.h" +#define VHOST_USER_MAX_RAM_SLOTS SPAPR_MAX_RAM_SLOTS + +#else +#define VHOST_USER_MAX_RAM_SLOTS 512 +#endif + +/* * Maximum size of virtio device config space */ #define VHOST_USER_MAX_CONFIG_SIZE 256 @@ -59,6 +77,8 @@ enum VhostUserProtocolFeature { VHOST_USER_PROTOCOL_F_HOST_NOTIFIER = 11, VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD = 12, VHOST_USER_PROTOCOL_F_RESET_DEVICE = 13, + /* Feature 14 reserved for VHOST_USER_PROTOCOL_F_INBAND_NOTIFICATIONS. */ + VHOST_USER_PROTOCOL_F_CONFIGURE_MEM_SLOTS = 15, VHOST_USER_PROTOCOL_F_MAX }; @@ -100,6 +120,10 @@ typedef enum VhostUserRequest { VHOST_USER_SET_INFLIGHT_FD = 32, VHOST_USER_GPU_SET_SOCKET = 33, VHOST_USER_RESET_DEVICE = 34, + /* Message number 35 reserved for VHOST_USER_VRING_KICK. */ + VHOST_USER_GET_MAX_MEM_SLOTS = 36, + VHOST_USER_ADD_MEM_REG = 37, + VHOST_USER_REM_MEM_REG = 38, VHOST_USER_MAX } VhostUserRequest; @@ -121,9 +145,14 @@ typedef struct VhostUserMemoryRegion { typedef struct VhostUserMemory { uint32_t nregions; uint32_t padding; - VhostUserMemoryRegion regions[VHOST_MEMORY_MAX_NREGIONS]; + VhostUserMemoryRegion regions[VHOST_MEMORY_BASELINE_NREGIONS]; } VhostUserMemory; +typedef struct VhostUserMemRegMsg { + uint32_t padding; + VhostUserMemoryRegion region; +} VhostUserMemRegMsg; + typedef struct VhostUserLog { uint64_t mmap_size; uint64_t mmap_offset; @@ -182,6 +211,7 @@ typedef union { struct vhost_vring_state state; struct vhost_vring_addr addr; VhostUserMemory memory; + VhostUserMemRegMsg mem_reg; VhostUserLog log; struct vhost_iotlb_msg iotlb; VhostUserConfig config; @@ -210,7 +240,7 @@ struct vhost_user { int slave_fd; NotifierWithReturn postcopy_notifier; struct PostCopyFD postcopy_fd; - uint64_t postcopy_client_bases[VHOST_MEMORY_MAX_NREGIONS]; + uint64_t postcopy_client_bases[VHOST_USER_MAX_RAM_SLOTS]; /* Length of the region_rb and region_rb_offset arrays */ size_t region_rb_len; /* RAMBlock associated with a given region */ @@ -222,6 +252,16 @@ struct vhost_user { /* True once we've entered postcopy_listen */ bool postcopy_listen; + + /* Our current regions */ + int num_shadow_regions; + struct vhost_memory_region shadow_regions[VHOST_USER_MAX_RAM_SLOTS]; +}; + +struct scrub_regions { + struct vhost_memory_region *region; + int reg_idx; + int fd_idx; }; static bool ioeventfd_enabled(void) @@ -370,7 +410,7 @@ int vhost_user_gpu_set_socket(struct vhost_dev *dev, int fd) static int vhost_user_set_log_base(struct vhost_dev *dev, uint64_t base, struct vhost_log *log) { - int fds[VHOST_MEMORY_MAX_NREGIONS]; + int fds[VHOST_USER_MAX_RAM_SLOTS]; size_t fd_num = 0; bool shmfd = virtio_has_feature(dev->protocol_features, VHOST_USER_PROTOCOL_F_LOG_SHMFD); @@ -407,6 +447,27 @@ static int vhost_user_set_log_base(struct vhost_dev *dev, uint64_t base, return 0; } +static MemoryRegion *vhost_user_get_mr_data(uint64_t addr, ram_addr_t *offset, + int *fd) +{ + MemoryRegion *mr; + + assert((uintptr_t)addr == addr); + mr = memory_region_from_host((void *)(uintptr_t)addr, offset); + *fd = memory_region_get_fd(mr); + + return mr; +} + +static void vhost_user_fill_msg_region(VhostUserMemoryRegion *dst, + struct vhost_memory_region *src) +{ + assert(src != NULL && dst != NULL); + dst->userspace_addr = src->userspace_addr; + dst->memory_size = src->memory_size; + dst->guest_phys_addr = src->guest_phys_addr; +} + static int vhost_user_fill_set_mem_table_msg(struct vhost_user *u, struct vhost_dev *dev, VhostUserMsg *msg, @@ -417,19 +478,17 @@ static int vhost_user_fill_set_mem_table_msg(struct vhost_user *u, ram_addr_t offset; MemoryRegion *mr; struct vhost_memory_region *reg; + VhostUserMemoryRegion region_buffer; msg->hdr.request = VHOST_USER_SET_MEM_TABLE; for (i = 0; i < dev->mem->nregions; ++i) { reg = dev->mem->regions + i; - assert((uintptr_t)reg->userspace_addr == reg->userspace_addr); - mr = memory_region_from_host((void *)(uintptr_t)reg->userspace_addr, - &offset); - fd = memory_region_get_fd(mr); + mr = vhost_user_get_mr_data(reg->userspace_addr, &offset, &fd); if (fd > 0) { if (track_ramblocks) { - assert(*fd_num < VHOST_MEMORY_MAX_NREGIONS); + assert(*fd_num < VHOST_MEMORY_BASELINE_NREGIONS); trace_vhost_user_set_mem_table_withfd(*fd_num, mr->name, reg->memory_size, reg->guest_phys_addr, @@ -437,16 +496,12 @@ static int vhost_user_fill_set_mem_table_msg(struct vhost_user *u, offset); u->region_rb_offset[i] = offset; u->region_rb[i] = mr->ram_block; - } else if (*fd_num == VHOST_MEMORY_MAX_NREGIONS) { + } else if (*fd_num == VHOST_MEMORY_BASELINE_NREGIONS) { error_report("Failed preparing vhost-user memory table msg"); return -1; } - msg->payload.memory.regions[*fd_num].userspace_addr = - reg->userspace_addr; - msg->payload.memory.regions[*fd_num].memory_size = - reg->memory_size; - msg->payload.memory.regions[*fd_num].guest_phys_addr = - reg->guest_phys_addr; + vhost_user_fill_msg_region(®ion_buffer, reg); + msg->payload.memory.regions[*fd_num] = region_buffer; msg->payload.memory.regions[*fd_num].mmap_offset = offset; fds[(*fd_num)++] = fd; } else if (track_ramblocks) { @@ -470,11 +525,335 @@ static int vhost_user_fill_set_mem_table_msg(struct vhost_user *u, return 1; } +static inline bool reg_equal(struct vhost_memory_region *shadow_reg, + struct vhost_memory_region *vdev_reg) +{ + return shadow_reg->guest_phys_addr == vdev_reg->guest_phys_addr && + shadow_reg->userspace_addr == vdev_reg->userspace_addr && + shadow_reg->memory_size == vdev_reg->memory_size; +} + +static void scrub_shadow_regions(struct vhost_dev *dev, + struct scrub_regions *add_reg, + int *nr_add_reg, + struct scrub_regions *rem_reg, + int *nr_rem_reg, uint64_t *shadow_pcb, + bool track_ramblocks) +{ + struct vhost_user *u = dev->opaque; + bool found[VHOST_USER_MAX_RAM_SLOTS] = {}; + struct vhost_memory_region *reg, *shadow_reg; + int i, j, fd, add_idx = 0, rm_idx = 0, fd_num = 0; + ram_addr_t offset; + MemoryRegion *mr; + bool matching; + + /* + * Find memory regions present in our shadow state which are not in + * the device's current memory state. + * + * Mark regions in both the shadow and device state as "found". + */ + for (i = 0; i < u->num_shadow_regions; i++) { + shadow_reg = &u->shadow_regions[i]; + matching = false; + + for (j = 0; j < dev->mem->nregions; j++) { + reg = &dev->mem->regions[j]; + + mr = vhost_user_get_mr_data(reg->userspace_addr, &offset, &fd); + + if (reg_equal(shadow_reg, reg)) { + matching = true; + found[j] = true; + if (track_ramblocks) { + /* + * Reset postcopy client bases, region_rb, and + * region_rb_offset in case regions are removed. + */ + if (fd > 0) { + u->region_rb_offset[j] = offset; + u->region_rb[j] = mr->ram_block; + shadow_pcb[j] = u->postcopy_client_bases[i]; + } else { + u->region_rb_offset[j] = 0; + u->region_rb[j] = NULL; + } + } + break; + } + } + + /* + * If the region was not found in the current device memory state + * create an entry for it in the removed list. + */ + if (!matching) { + rem_reg[rm_idx].region = shadow_reg; + rem_reg[rm_idx++].reg_idx = i; + } + } + + /* + * For regions not marked "found", create entries in the added list. + * + * Note their indexes in the device memory state and the indexes of their + * file descriptors. + */ + for (i = 0; i < dev->mem->nregions; i++) { + reg = &dev->mem->regions[i]; + mr = vhost_user_get_mr_data(reg->userspace_addr, &offset, &fd); + if (fd > 0) { + ++fd_num; + } + + /* + * If the region was in both the shadow and device state we don't + * need to send a VHOST_USER_ADD_MEM_REG message for it. + */ + if (found[i]) { + continue; + } + + add_reg[add_idx].region = reg; + add_reg[add_idx].reg_idx = i; + add_reg[add_idx++].fd_idx = fd_num; + } + *nr_rem_reg = rm_idx; + *nr_add_reg = add_idx; + + return; +} + +static int send_remove_regions(struct vhost_dev *dev, + struct scrub_regions *remove_reg, + int nr_rem_reg, VhostUserMsg *msg, + bool reply_supported) +{ + struct vhost_user *u = dev->opaque; + struct vhost_memory_region *shadow_reg; + int i, fd, shadow_reg_idx, ret; + ram_addr_t offset; + VhostUserMemoryRegion region_buffer; + + /* + * The regions in remove_reg appear in the same order they do in the + * shadow table. Therefore we can minimize memory copies by iterating + * through remove_reg backwards. + */ + for (i = nr_rem_reg - 1; i >= 0; i--) { + shadow_reg = remove_reg[i].region; + shadow_reg_idx = remove_reg[i].reg_idx; + + vhost_user_get_mr_data(shadow_reg->userspace_addr, &offset, &fd); + + if (fd > 0) { + msg->hdr.request = VHOST_USER_REM_MEM_REG; + vhost_user_fill_msg_region(®ion_buffer, shadow_reg); + msg->payload.mem_reg.region = region_buffer; + + if (vhost_user_write(dev, msg, &fd, 1) < 0) { + return -1; + } + + if (reply_supported) { + ret = process_message_reply(dev, msg); + if (ret) { + return ret; + } + } + } + + /* + * At this point we know the backend has unmapped the region. It is now + * safe to remove it from the shadow table. + */ + memmove(&u->shadow_regions[shadow_reg_idx], + &u->shadow_regions[shadow_reg_idx + 1], + sizeof(struct vhost_memory_region) * + (u->num_shadow_regions - shadow_reg_idx)); + u->num_shadow_regions--; + } + + return 0; +} + +static int send_add_regions(struct vhost_dev *dev, + struct scrub_regions *add_reg, int nr_add_reg, + VhostUserMsg *msg, uint64_t *shadow_pcb, + bool reply_supported, bool track_ramblocks) +{ + struct vhost_user *u = dev->opaque; + int i, fd, ret, reg_idx, reg_fd_idx; + struct vhost_memory_region *reg; + MemoryRegion *mr; + ram_addr_t offset; + VhostUserMsg msg_reply; + VhostUserMemoryRegion region_buffer; + + for (i = 0; i < nr_add_reg; i++) { + reg = add_reg[i].region; + reg_idx = add_reg[i].reg_idx; + reg_fd_idx = add_reg[i].fd_idx; + + mr = vhost_user_get_mr_data(reg->userspace_addr, &offset, &fd); + + if (fd > 0) { + if (track_ramblocks) { + trace_vhost_user_set_mem_table_withfd(reg_fd_idx, mr->name, + reg->memory_size, + reg->guest_phys_addr, + reg->userspace_addr, + offset); + u->region_rb_offset[reg_idx] = offset; + u->region_rb[reg_idx] = mr->ram_block; + } + msg->hdr.request = VHOST_USER_ADD_MEM_REG; + vhost_user_fill_msg_region(®ion_buffer, reg); + msg->payload.mem_reg.region = region_buffer; + msg->payload.mem_reg.region.mmap_offset = offset; + + if (vhost_user_write(dev, msg, &fd, 1) < 0) { + return -1; + } + + if (track_ramblocks) { + uint64_t reply_gpa; + + if (vhost_user_read(dev, &msg_reply) < 0) { + return -1; + } + + reply_gpa = msg_reply.payload.mem_reg.region.guest_phys_addr; + + if (msg_reply.hdr.request != VHOST_USER_ADD_MEM_REG) { + error_report("%s: Received unexpected msg type." + "Expected %d received %d", __func__, + VHOST_USER_ADD_MEM_REG, + msg_reply.hdr.request); + return -1; + } + + /* + * We're using the same structure, just reusing one of the + * fields, so it should be the same size. + */ + if (msg_reply.hdr.size != msg->hdr.size) { + error_report("%s: Unexpected size for postcopy reply " + "%d vs %d", __func__, msg_reply.hdr.size, + msg->hdr.size); + return -1; + } + + /* Get the postcopy client base from the backend's reply. */ + if (reply_gpa == dev->mem->regions[reg_idx].guest_phys_addr) { + shadow_pcb[reg_idx] = + msg_reply.payload.mem_reg.region.userspace_addr; + trace_vhost_user_set_mem_table_postcopy( + msg_reply.payload.mem_reg.region.userspace_addr, + msg->payload.mem_reg.region.userspace_addr, + reg_fd_idx, reg_idx); + } else { + error_report("%s: invalid postcopy reply for region. " + "Got guest physical address %" PRIX64 ", expected " + "%" PRIX64, __func__, reply_gpa, + dev->mem->regions[reg_idx].guest_phys_addr); + return -1; + } + } else if (reply_supported) { + ret = process_message_reply(dev, msg); + if (ret) { + return ret; + } + } + } else if (track_ramblocks) { + u->region_rb_offset[reg_idx] = 0; + u->region_rb[reg_idx] = NULL; + } + + /* + * At this point, we know the backend has mapped in the new + * region, if the region has a valid file descriptor. + * + * The region should now be added to the shadow table. + */ + u->shadow_regions[u->num_shadow_regions].guest_phys_addr = + reg->guest_phys_addr; + u->shadow_regions[u->num_shadow_regions].userspace_addr = + reg->userspace_addr; + u->shadow_regions[u->num_shadow_regions].memory_size = + reg->memory_size; + u->num_shadow_regions++; + } + + return 0; +} + +static int vhost_user_add_remove_regions(struct vhost_dev *dev, + VhostUserMsg *msg, + bool reply_supported, + bool track_ramblocks) +{ + struct vhost_user *u = dev->opaque; + struct scrub_regions add_reg[VHOST_USER_MAX_RAM_SLOTS]; + struct scrub_regions rem_reg[VHOST_USER_MAX_RAM_SLOTS]; + uint64_t shadow_pcb[VHOST_USER_MAX_RAM_SLOTS] = {}; + int nr_add_reg, nr_rem_reg; + + msg->hdr.size = sizeof(msg->payload.mem_reg.padding) + + sizeof(VhostUserMemoryRegion); + + /* Find the regions which need to be removed or added. */ + scrub_shadow_regions(dev, add_reg, &nr_add_reg, rem_reg, &nr_rem_reg, + shadow_pcb, track_ramblocks); + + if (nr_rem_reg && send_remove_regions(dev, rem_reg, nr_rem_reg, msg, + reply_supported) < 0) + { + goto err; + } + + if (nr_add_reg && send_add_regions(dev, add_reg, nr_add_reg, msg, + shadow_pcb, reply_supported, track_ramblocks) < 0) + { + goto err; + } + + if (track_ramblocks) { + memcpy(u->postcopy_client_bases, shadow_pcb, + sizeof(uint64_t) * VHOST_USER_MAX_RAM_SLOTS); + /* + * Now we've registered this with the postcopy code, we ack to the + * client, because now we're in the position to be able to deal with + * any faults it generates. + */ + /* TODO: Use this for failure cases as well with a bad value. */ + msg->hdr.size = sizeof(msg->payload.u64); + msg->payload.u64 = 0; /* OK */ + + if (vhost_user_write(dev, msg, NULL, 0) < 0) { + return -1; + } + } + + return 0; + +err: + if (track_ramblocks) { + memcpy(u->postcopy_client_bases, shadow_pcb, + sizeof(uint64_t) * VHOST_USER_MAX_RAM_SLOTS); + } + + return -1; +} + static int vhost_user_set_mem_table_postcopy(struct vhost_dev *dev, - struct vhost_memory *mem) + struct vhost_memory *mem, + bool reply_supported, + bool config_mem_slots) { struct vhost_user *u = dev->opaque; - int fds[VHOST_MEMORY_MAX_NREGIONS]; + int fds[VHOST_MEMORY_BASELINE_NREGIONS]; size_t fd_num = 0; VhostUserMsg msg_reply; int region_i, msg_i; @@ -494,71 +873,84 @@ static int vhost_user_set_mem_table_postcopy(struct vhost_dev *dev, u->region_rb_len = dev->mem->nregions; } - if (vhost_user_fill_set_mem_table_msg(u, dev, &msg, fds, &fd_num, + if (config_mem_slots) { + if (vhost_user_add_remove_regions(dev, &msg, reply_supported, true) < 0) { - return -1; - } + return -1; + } + } else { + if (vhost_user_fill_set_mem_table_msg(u, dev, &msg, fds, &fd_num, + true) < 0) { + return -1; + } - if (vhost_user_write(dev, &msg, fds, fd_num) < 0) { - return -1; - } + if (vhost_user_write(dev, &msg, fds, fd_num) < 0) { + return -1; + } - if (vhost_user_read(dev, &msg_reply) < 0) { - return -1; - } + if (vhost_user_read(dev, &msg_reply) < 0) { + return -1; + } - if (msg_reply.hdr.request != VHOST_USER_SET_MEM_TABLE) { - error_report("%s: Received unexpected msg type." - "Expected %d received %d", __func__, - VHOST_USER_SET_MEM_TABLE, msg_reply.hdr.request); - return -1; - } - /* We're using the same structure, just reusing one of the - * fields, so it should be the same size. - */ - if (msg_reply.hdr.size != msg.hdr.size) { - error_report("%s: Unexpected size for postcopy reply " - "%d vs %d", __func__, msg_reply.hdr.size, msg.hdr.size); - return -1; - } - - memset(u->postcopy_client_bases, 0, - sizeof(uint64_t) * VHOST_MEMORY_MAX_NREGIONS); - - /* They're in the same order as the regions that were sent - * but some of the regions were skipped (above) if they - * didn't have fd's - */ - for (msg_i = 0, region_i = 0; - region_i < dev->mem->nregions; - region_i++) { - if (msg_i < fd_num && - msg_reply.payload.memory.regions[msg_i].guest_phys_addr == - dev->mem->regions[region_i].guest_phys_addr) { - u->postcopy_client_bases[region_i] = - msg_reply.payload.memory.regions[msg_i].userspace_addr; - trace_vhost_user_set_mem_table_postcopy( - msg_reply.payload.memory.regions[msg_i].userspace_addr, - msg.payload.memory.regions[msg_i].userspace_addr, - msg_i, region_i); - msg_i++; + if (msg_reply.hdr.request != VHOST_USER_SET_MEM_TABLE) { + error_report("%s: Received unexpected msg type." + "Expected %d received %d", __func__, + VHOST_USER_SET_MEM_TABLE, msg_reply.hdr.request); + return -1; + } + + /* + * We're using the same structure, just reusing one of the + * fields, so it should be the same size. + */ + if (msg_reply.hdr.size != msg.hdr.size) { + error_report("%s: Unexpected size for postcopy reply " + "%d vs %d", __func__, msg_reply.hdr.size, + msg.hdr.size); + return -1; + } + + memset(u->postcopy_client_bases, 0, + sizeof(uint64_t) * VHOST_USER_MAX_RAM_SLOTS); + + /* + * They're in the same order as the regions that were sent + * but some of the regions were skipped (above) if they + * didn't have fd's + */ + for (msg_i = 0, region_i = 0; + region_i < dev->mem->nregions; + region_i++) { + if (msg_i < fd_num && + msg_reply.payload.memory.regions[msg_i].guest_phys_addr == + dev->mem->regions[region_i].guest_phys_addr) { + u->postcopy_client_bases[region_i] = + msg_reply.payload.memory.regions[msg_i].userspace_addr; + trace_vhost_user_set_mem_table_postcopy( + msg_reply.payload.memory.regions[msg_i].userspace_addr, + msg.payload.memory.regions[msg_i].userspace_addr, + msg_i, region_i); + msg_i++; + } + } + if (msg_i != fd_num) { + error_report("%s: postcopy reply not fully consumed " + "%d vs %zd", + __func__, msg_i, fd_num); + return -1; + } + + /* + * Now we've registered this with the postcopy code, we ack to the + * client, because now we're in the position to be able to deal + * with any faults it generates. + */ + /* TODO: Use this for failure cases as well with a bad value. */ + msg.hdr.size = sizeof(msg.payload.u64); + msg.payload.u64 = 0; /* OK */ + if (vhost_user_write(dev, &msg, NULL, 0) < 0) { + return -1; } - } - if (msg_i != fd_num) { - error_report("%s: postcopy reply not fully consumed " - "%d vs %zd", - __func__, msg_i, fd_num); - return -1; - } - /* Now we've registered this with the postcopy code, we ack to the client, - * because now we're in the position to be able to deal with any faults - * it generates. - */ - /* TODO: Use this for failure cases as well with a bad value */ - msg.hdr.size = sizeof(msg.payload.u64); - msg.payload.u64 = 0; /* OK */ - if (vhost_user_write(dev, &msg, NULL, 0) < 0) { - return -1; } return 0; @@ -568,17 +960,22 @@ static int vhost_user_set_mem_table(struct vhost_dev *dev, struct vhost_memory *mem) { struct vhost_user *u = dev->opaque; - int fds[VHOST_MEMORY_MAX_NREGIONS]; + int fds[VHOST_MEMORY_BASELINE_NREGIONS]; size_t fd_num = 0; bool do_postcopy = u->postcopy_listen && u->postcopy_fd.handler; bool reply_supported = virtio_has_feature(dev->protocol_features, VHOST_USER_PROTOCOL_F_REPLY_ACK); + bool config_mem_slots = + virtio_has_feature(dev->protocol_features, + VHOST_USER_PROTOCOL_F_CONFIGURE_MEM_SLOTS); if (do_postcopy) { - /* Postcopy has enough differences that it's best done in it's own + /* + * Postcopy has enough differences that it's best done in it's own * version */ - return vhost_user_set_mem_table_postcopy(dev, mem); + return vhost_user_set_mem_table_postcopy(dev, mem, reply_supported, + config_mem_slots); } VhostUserMsg msg = { @@ -589,17 +986,23 @@ static int vhost_user_set_mem_table(struct vhost_dev *dev, msg.hdr.flags |= VHOST_USER_NEED_REPLY_MASK; } - if (vhost_user_fill_set_mem_table_msg(u, dev, &msg, fds, &fd_num, + if (config_mem_slots) { + if (vhost_user_add_remove_regions(dev, &msg, reply_supported, false) < 0) { - return -1; - } - - if (vhost_user_write(dev, &msg, fds, fd_num) < 0) { - return -1; - } + return -1; + } + } else { + if (vhost_user_fill_set_mem_table_msg(u, dev, &msg, fds, &fd_num, + false) < 0) { + return -1; + } + if (vhost_user_write(dev, &msg, fds, fd_num) < 0) { + return -1; + } - if (reply_supported) { - return process_message_reply(dev, &msg); + if (reply_supported) { + return process_message_reply(dev, &msg); + } } return 0; @@ -764,7 +1167,7 @@ static int vhost_set_vring_file(struct vhost_dev *dev, VhostUserRequest request, struct vhost_vring_file *file) { - int fds[VHOST_MEMORY_MAX_NREGIONS]; + int fds[VHOST_USER_MAX_RAM_SLOTS]; size_t fd_num = 0; VhostUserMsg msg = { .hdr.request = request, @@ -880,6 +1283,23 @@ static int vhost_user_set_owner(struct vhost_dev *dev) return 0; } +static int vhost_user_get_max_memslots(struct vhost_dev *dev, + uint64_t *max_memslots) +{ + uint64_t backend_max_memslots; + int err; + + err = vhost_user_get_u64(dev, VHOST_USER_GET_MAX_MEM_SLOTS, + &backend_max_memslots); + if (err < 0) { + return err; + } + + *max_memslots = backend_max_memslots; + + return 0; +} + static int vhost_user_reset_device(struct vhost_dev *dev) { VhostUserMsg msg = { @@ -1377,7 +1797,7 @@ static int vhost_user_postcopy_notifier(NotifierWithReturn *notifier, static int vhost_user_backend_init(struct vhost_dev *dev, void *opaque) { - uint64_t features, protocol_features; + uint64_t features, protocol_features, ram_slots; struct vhost_user *u; int err; @@ -1439,6 +1859,27 @@ static int vhost_user_backend_init(struct vhost_dev *dev, void *opaque) "slave-req protocol features."); return -1; } + + /* get max memory regions if backend supports configurable RAM slots */ + if (!virtio_has_feature(dev->protocol_features, + VHOST_USER_PROTOCOL_F_CONFIGURE_MEM_SLOTS)) { + u->user->memory_slots = VHOST_MEMORY_BASELINE_NREGIONS; + } else { + err = vhost_user_get_max_memslots(dev, &ram_slots); + if (err < 0) { + return err; + } + + if (ram_slots < u->user->memory_slots) { + error_report("The backend specified a max ram slots limit " + "of %" PRIu64", when the prior validated limit was %d. " + "This limit should never decrease.", ram_slots, + u->user->memory_slots); + return -1; + } + + u->user->memory_slots = MIN(ram_slots, VHOST_USER_MAX_RAM_SLOTS); + } } if (dev->migration_blocker == NULL && @@ -1504,7 +1945,9 @@ static int vhost_user_get_vq_index(struct vhost_dev *dev, int idx) static int vhost_user_memslots_limit(struct vhost_dev *dev) { - return VHOST_MEMORY_MAX_NREGIONS; + struct vhost_user *u = dev->opaque; + + return u->user->memory_slots; } static bool vhost_user_requires_shm_log(struct vhost_dev *dev) @@ -1545,13 +1988,9 @@ static bool vhost_user_can_merge(struct vhost_dev *dev, { ram_addr_t offset; int mfd, rfd; - MemoryRegion *mr; - - mr = memory_region_from_host((void *)(uintptr_t)start1, &offset); - mfd = memory_region_get_fd(mr); - mr = memory_region_from_host((void *)(uintptr_t)start2, &offset); - rfd = memory_region_get_fd(mr); + (void)vhost_user_get_mr_data(start1, &offset, &mfd); + (void)vhost_user_get_mr_data(start2, &offset, &rfd); return mfd == rfd; } @@ -1893,6 +2332,7 @@ bool vhost_user_init(VhostUserState *user, CharBackend *chr, Error **errp) return false; } user->chr = chr; + user->memory_slots = 0; return true; } diff --git a/hw/virtio/vhost-vsock-common.c b/hw/virtio/vhost-vsock-common.c new file mode 100644 index 0000000000..5b2ebf3496 --- /dev/null +++ b/hw/virtio/vhost-vsock-common.c @@ -0,0 +1,258 @@ +/* + * Parent class for vhost-vsock devices + * + * Copyright 2015-2020 Red Hat, Inc. + * + * 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 "standard-headers/linux/virtio_vsock.h" +#include "qapi/error.h" +#include "hw/virtio/virtio-access.h" +#include "qemu/error-report.h" +#include "hw/qdev-properties.h" +#include "hw/virtio/vhost-vsock.h" +#include "qemu/iov.h" +#include "monitor/monitor.h" + +int vhost_vsock_common_start(VirtIODevice *vdev) +{ + VHostVSockCommon *vvc = VHOST_VSOCK_COMMON(vdev); + BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev))); + VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus); + int ret; + int i; + + if (!k->set_guest_notifiers) { + error_report("binding does not support guest notifiers"); + return -ENOSYS; + } + + ret = vhost_dev_enable_notifiers(&vvc->vhost_dev, vdev); + if (ret < 0) { + error_report("Error enabling host notifiers: %d", -ret); + return ret; + } + + ret = k->set_guest_notifiers(qbus->parent, vvc->vhost_dev.nvqs, true); + if (ret < 0) { + error_report("Error binding guest notifier: %d", -ret); + goto err_host_notifiers; + } + + vvc->vhost_dev.acked_features = vdev->guest_features; + ret = vhost_dev_start(&vvc->vhost_dev, vdev); + if (ret < 0) { + error_report("Error starting vhost: %d", -ret); + goto err_guest_notifiers; + } + + /* + * guest_notifier_mask/pending not used yet, so just unmask + * everything here. virtio-pci will do the right thing by + * enabling/disabling irqfd. + */ + for (i = 0; i < vvc->vhost_dev.nvqs; i++) { + vhost_virtqueue_mask(&vvc->vhost_dev, vdev, i, false); + } + + return 0; + +err_guest_notifiers: + k->set_guest_notifiers(qbus->parent, vvc->vhost_dev.nvqs, false); +err_host_notifiers: + vhost_dev_disable_notifiers(&vvc->vhost_dev, vdev); + return ret; +} + +void vhost_vsock_common_stop(VirtIODevice *vdev) +{ + VHostVSockCommon *vvc = VHOST_VSOCK_COMMON(vdev); + BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev))); + VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus); + int ret; + + if (!k->set_guest_notifiers) { + return; + } + + vhost_dev_stop(&vvc->vhost_dev, vdev); + + ret = k->set_guest_notifiers(qbus->parent, vvc->vhost_dev.nvqs, false); + if (ret < 0) { + error_report("vhost guest notifier cleanup failed: %d", ret); + return; + } + + vhost_dev_disable_notifiers(&vvc->vhost_dev, vdev); +} + + +static void vhost_vsock_common_handle_output(VirtIODevice *vdev, VirtQueue *vq) +{ + /* Do nothing */ +} + +static void vhost_vsock_common_guest_notifier_mask(VirtIODevice *vdev, int idx, + bool mask) +{ + VHostVSockCommon *vvc = VHOST_VSOCK_COMMON(vdev); + + vhost_virtqueue_mask(&vvc->vhost_dev, vdev, idx, mask); +} + +static bool vhost_vsock_common_guest_notifier_pending(VirtIODevice *vdev, + int idx) +{ + VHostVSockCommon *vvc = VHOST_VSOCK_COMMON(vdev); + + return vhost_virtqueue_pending(&vvc->vhost_dev, idx); +} + +static void vhost_vsock_common_send_transport_reset(VHostVSockCommon *vvc) +{ + VirtQueueElement *elem; + VirtQueue *vq = vvc->event_vq; + struct virtio_vsock_event event = { + .id = cpu_to_le32(VIRTIO_VSOCK_EVENT_TRANSPORT_RESET), + }; + + elem = virtqueue_pop(vq, sizeof(VirtQueueElement)); + if (!elem) { + error_report("vhost-vsock missed transport reset event"); + return; + } + + if (elem->out_num) { + error_report("invalid vhost-vsock event virtqueue element with " + "out buffers"); + goto out; + } + + if (iov_from_buf(elem->in_sg, elem->in_num, 0, + &event, sizeof(event)) != sizeof(event)) { + error_report("vhost-vsock event virtqueue element is too short"); + goto out; + } + + virtqueue_push(vq, elem, sizeof(event)); + virtio_notify(VIRTIO_DEVICE(vvc), vq); + +out: + g_free(elem); +} + +static void vhost_vsock_common_post_load_timer_cleanup(VHostVSockCommon *vvc) +{ + if (!vvc->post_load_timer) { + return; + } + + timer_del(vvc->post_load_timer); + timer_free(vvc->post_load_timer); + vvc->post_load_timer = NULL; +} + +static void vhost_vsock_common_post_load_timer_cb(void *opaque) +{ + VHostVSockCommon *vvc = opaque; + + vhost_vsock_common_post_load_timer_cleanup(vvc); + vhost_vsock_common_send_transport_reset(vvc); +} + +int vhost_vsock_common_pre_save(void *opaque) +{ + VHostVSockCommon *vvc = opaque; + + /* + * At this point, backend must be stopped, otherwise + * it might keep writing to memory. + */ + assert(!vvc->vhost_dev.started); + + return 0; +} + +int vhost_vsock_common_post_load(void *opaque, int version_id) +{ + VHostVSockCommon *vvc = opaque; + VirtIODevice *vdev = VIRTIO_DEVICE(vvc); + + if (virtio_queue_get_addr(vdev, 2)) { + /* + * Defer transport reset event to a vm clock timer so that virtqueue + * changes happen after migration has completed. + */ + assert(!vvc->post_load_timer); + vvc->post_load_timer = + timer_new_ns(QEMU_CLOCK_VIRTUAL, + vhost_vsock_common_post_load_timer_cb, + vvc); + timer_mod(vvc->post_load_timer, 1); + } + return 0; +} + +void vhost_vsock_common_realize(VirtIODevice *vdev, const char *name) +{ + VHostVSockCommon *vvc = VHOST_VSOCK_COMMON(vdev); + + virtio_init(vdev, name, VIRTIO_ID_VSOCK, + sizeof(struct virtio_vsock_config)); + + /* Receive and transmit queues belong to vhost */ + vvc->recv_vq = virtio_add_queue(vdev, VHOST_VSOCK_QUEUE_SIZE, + vhost_vsock_common_handle_output); + vvc->trans_vq = virtio_add_queue(vdev, VHOST_VSOCK_QUEUE_SIZE, + vhost_vsock_common_handle_output); + + /* The event queue belongs to QEMU */ + vvc->event_vq = virtio_add_queue(vdev, VHOST_VSOCK_QUEUE_SIZE, + vhost_vsock_common_handle_output); + + vvc->vhost_dev.nvqs = ARRAY_SIZE(vvc->vhost_vqs); + vvc->vhost_dev.vqs = vvc->vhost_vqs; + + vvc->post_load_timer = NULL; +} + +void vhost_vsock_common_unrealize(VirtIODevice *vdev) +{ + VHostVSockCommon *vvc = VHOST_VSOCK_COMMON(vdev); + + vhost_vsock_common_post_load_timer_cleanup(vvc); + + virtio_delete_queue(vvc->recv_vq); + virtio_delete_queue(vvc->trans_vq); + virtio_delete_queue(vvc->event_vq); + virtio_cleanup(vdev); +} + +static void vhost_vsock_common_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass); + + set_bit(DEVICE_CATEGORY_MISC, dc->categories); + vdc->guest_notifier_mask = vhost_vsock_common_guest_notifier_mask; + vdc->guest_notifier_pending = vhost_vsock_common_guest_notifier_pending; +} + +static const TypeInfo vhost_vsock_common_info = { + .name = TYPE_VHOST_VSOCK_COMMON, + .parent = TYPE_VIRTIO_DEVICE, + .instance_size = sizeof(VHostVSockCommon), + .class_init = vhost_vsock_common_class_init, + .abstract = true, +}; + +static void vhost_vsock_common_register_types(void) +{ + type_register_static(&vhost_vsock_common_info); +} + +type_init(vhost_vsock_common_register_types) diff --git a/hw/virtio/vhost-vsock.c b/hw/virtio/vhost-vsock.c index 4a228f5168..c8f0699b4f 100644 --- a/hw/virtio/vhost-vsock.c +++ b/hw/virtio/vhost-vsock.c @@ -12,24 +12,14 @@ */ #include "qemu/osdep.h" -#include <sys/ioctl.h> #include "standard-headers/linux/virtio_vsock.h" #include "qapi/error.h" -#include "hw/virtio/virtio-bus.h" #include "hw/virtio/virtio-access.h" #include "qemu/error-report.h" #include "hw/qdev-properties.h" #include "hw/virtio/vhost-vsock.h" -#include "qemu/iov.h" -#include "qemu/module.h" #include "monitor/monitor.h" -enum { - VHOST_VSOCK_SAVEVM_VERSION = 0, - - VHOST_VSOCK_QUEUE_SIZE = 128, -}; - static void vhost_vsock_get_config(VirtIODevice *vdev, uint8_t *config) { VHostVSock *vsock = VHOST_VSOCK(vdev); @@ -39,16 +29,18 @@ static void vhost_vsock_get_config(VirtIODevice *vdev, uint8_t *config) memcpy(config, &vsockcfg, sizeof(vsockcfg)); } -static int vhost_vsock_set_guest_cid(VHostVSock *vsock) +static int vhost_vsock_set_guest_cid(VirtIODevice *vdev) { - const VhostOps *vhost_ops = vsock->vhost_dev.vhost_ops; + VHostVSockCommon *vvc = VHOST_VSOCK_COMMON(vdev); + VHostVSock *vsock = VHOST_VSOCK(vdev); + const VhostOps *vhost_ops = vvc->vhost_dev.vhost_ops; int ret; if (!vhost_ops->vhost_vsock_set_guest_cid) { return -ENOSYS; } - ret = vhost_ops->vhost_vsock_set_guest_cid(&vsock->vhost_dev, + ret = vhost_ops->vhost_vsock_set_guest_cid(&vvc->vhost_dev, vsock->conf.guest_cid); if (ret < 0) { return -errno; @@ -56,123 +48,58 @@ static int vhost_vsock_set_guest_cid(VHostVSock *vsock) return 0; } -static int vhost_vsock_set_running(VHostVSock *vsock, int start) +static int vhost_vsock_set_running(VirtIODevice *vdev, int start) { - const VhostOps *vhost_ops = vsock->vhost_dev.vhost_ops; + VHostVSockCommon *vvc = VHOST_VSOCK_COMMON(vdev); + const VhostOps *vhost_ops = vvc->vhost_dev.vhost_ops; int ret; if (!vhost_ops->vhost_vsock_set_running) { return -ENOSYS; } - ret = vhost_ops->vhost_vsock_set_running(&vsock->vhost_dev, start); + ret = vhost_ops->vhost_vsock_set_running(&vvc->vhost_dev, start); if (ret < 0) { return -errno; } return 0; } -static void vhost_vsock_start(VirtIODevice *vdev) -{ - VHostVSock *vsock = VHOST_VSOCK(vdev); - BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev))); - VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus); - int ret; - int i; - - if (!k->set_guest_notifiers) { - error_report("binding does not support guest notifiers"); - return; - } - - ret = vhost_dev_enable_notifiers(&vsock->vhost_dev, vdev); - if (ret < 0) { - error_report("Error enabling host notifiers: %d", -ret); - return; - } - - ret = k->set_guest_notifiers(qbus->parent, vsock->vhost_dev.nvqs, true); - if (ret < 0) { - error_report("Error binding guest notifier: %d", -ret); - goto err_host_notifiers; - } - - vsock->vhost_dev.acked_features = vdev->guest_features; - ret = vhost_dev_start(&vsock->vhost_dev, vdev); - if (ret < 0) { - error_report("Error starting vhost: %d", -ret); - goto err_guest_notifiers; - } - - ret = vhost_vsock_set_running(vsock, 1); - if (ret < 0) { - error_report("Error starting vhost vsock: %d", -ret); - goto err_dev_start; - } - - /* guest_notifier_mask/pending not used yet, so just unmask - * everything here. virtio-pci will do the right thing by - * enabling/disabling irqfd. - */ - for (i = 0; i < vsock->vhost_dev.nvqs; i++) { - vhost_virtqueue_mask(&vsock->vhost_dev, vdev, i, false); - } - - return; - -err_dev_start: - vhost_dev_stop(&vsock->vhost_dev, vdev); -err_guest_notifiers: - k->set_guest_notifiers(qbus->parent, vsock->vhost_dev.nvqs, false); -err_host_notifiers: - vhost_dev_disable_notifiers(&vsock->vhost_dev, vdev); -} - -static void vhost_vsock_stop(VirtIODevice *vdev) -{ - VHostVSock *vsock = VHOST_VSOCK(vdev); - BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev))); - VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus); - int ret; - - if (!k->set_guest_notifiers) { - return; - } - - ret = vhost_vsock_set_running(vsock, 0); - if (ret < 0) { - error_report("vhost vsock set running failed: %d", ret); - return; - } - - vhost_dev_stop(&vsock->vhost_dev, vdev); - - ret = k->set_guest_notifiers(qbus->parent, vsock->vhost_dev.nvqs, false); - if (ret < 0) { - error_report("vhost guest notifier cleanup failed: %d", ret); - return; - } - - vhost_dev_disable_notifiers(&vsock->vhost_dev, vdev); -} static void vhost_vsock_set_status(VirtIODevice *vdev, uint8_t status) { - VHostVSock *vsock = VHOST_VSOCK(vdev); + VHostVSockCommon *vvc = VHOST_VSOCK_COMMON(vdev); bool should_start = status & VIRTIO_CONFIG_S_DRIVER_OK; + int ret; if (!vdev->vm_running) { should_start = false; } - if (vsock->vhost_dev.started == should_start) { + if (vvc->vhost_dev.started == should_start) { return; } if (should_start) { - vhost_vsock_start(vdev); + ret = vhost_vsock_common_start(vdev); + if (ret < 0) { + return; + } + + ret = vhost_vsock_set_running(vdev, 1); + if (ret < 0) { + vhost_vsock_common_stop(vdev); + error_report("Error starting vhost vsock: %d", -ret); + return; + } } else { - vhost_vsock_stop(vdev); + ret = vhost_vsock_set_running(vdev, 0); + if (ret < 0) { + error_report("vhost vsock set running failed: %d", ret); + return; + } + + vhost_vsock_common_stop(vdev); } } @@ -184,108 +111,6 @@ static uint64_t vhost_vsock_get_features(VirtIODevice *vdev, return requested_features; } -static void vhost_vsock_handle_output(VirtIODevice *vdev, VirtQueue *vq) -{ - /* Do nothing */ -} - -static void vhost_vsock_guest_notifier_mask(VirtIODevice *vdev, int idx, - bool mask) -{ - VHostVSock *vsock = VHOST_VSOCK(vdev); - - vhost_virtqueue_mask(&vsock->vhost_dev, vdev, idx, mask); -} - -static bool vhost_vsock_guest_notifier_pending(VirtIODevice *vdev, int idx) -{ - VHostVSock *vsock = VHOST_VSOCK(vdev); - - return vhost_virtqueue_pending(&vsock->vhost_dev, idx); -} - -static void vhost_vsock_send_transport_reset(VHostVSock *vsock) -{ - VirtQueueElement *elem; - VirtQueue *vq = vsock->event_vq; - struct virtio_vsock_event event = { - .id = cpu_to_le32(VIRTIO_VSOCK_EVENT_TRANSPORT_RESET), - }; - - elem = virtqueue_pop(vq, sizeof(VirtQueueElement)); - if (!elem) { - error_report("vhost-vsock missed transport reset event"); - return; - } - - if (elem->out_num) { - error_report("invalid vhost-vsock event virtqueue element with " - "out buffers"); - goto out; - } - - if (iov_from_buf(elem->in_sg, elem->in_num, 0, - &event, sizeof(event)) != sizeof(event)) { - error_report("vhost-vsock event virtqueue element is too short"); - goto out; - } - - virtqueue_push(vq, elem, sizeof(event)); - virtio_notify(VIRTIO_DEVICE(vsock), vq); - -out: - g_free(elem); -} - -static void vhost_vsock_post_load_timer_cleanup(VHostVSock *vsock) -{ - if (!vsock->post_load_timer) { - return; - } - - timer_del(vsock->post_load_timer); - timer_free(vsock->post_load_timer); - vsock->post_load_timer = NULL; -} - -static void vhost_vsock_post_load_timer_cb(void *opaque) -{ - VHostVSock *vsock = opaque; - - vhost_vsock_post_load_timer_cleanup(vsock); - vhost_vsock_send_transport_reset(vsock); -} - -static int vhost_vsock_pre_save(void *opaque) -{ - VHostVSock *vsock = opaque; - - /* At this point, backend must be stopped, otherwise - * it might keep writing to memory. */ - assert(!vsock->vhost_dev.started); - - return 0; -} - -static int vhost_vsock_post_load(void *opaque, int version_id) -{ - VHostVSock *vsock = opaque; - VirtIODevice *vdev = VIRTIO_DEVICE(vsock); - - if (virtio_queue_get_addr(vdev, 2)) { - /* Defer transport reset event to a vm clock timer so that virtqueue - * changes happen after migration has completed. - */ - assert(!vsock->post_load_timer); - vsock->post_load_timer = - timer_new_ns(QEMU_CLOCK_VIRTUAL, - vhost_vsock_post_load_timer_cb, - vsock); - timer_mod(vsock->post_load_timer, 1); - } - return 0; -} - static const VMStateDescription vmstate_virtio_vhost_vsock = { .name = "virtio-vhost_vsock", .minimum_version_id = VHOST_VSOCK_SAVEVM_VERSION, @@ -294,12 +119,13 @@ static const VMStateDescription vmstate_virtio_vhost_vsock = { VMSTATE_VIRTIO_DEVICE, VMSTATE_END_OF_LIST() }, - .pre_save = vhost_vsock_pre_save, - .post_load = vhost_vsock_post_load, + .pre_save = vhost_vsock_common_pre_save, + .post_load = vhost_vsock_common_post_load, }; static void vhost_vsock_device_realize(DeviceState *dev, Error **errp) { + VHostVSockCommon *vvc = VHOST_VSOCK_COMMON(dev); VirtIODevice *vdev = VIRTIO_DEVICE(dev); VHostVSock *vsock = VHOST_VSOCK(dev); int vhostfd; @@ -331,46 +157,29 @@ static void vhost_vsock_device_realize(DeviceState *dev, Error **errp) } } - virtio_init(vdev, "vhost-vsock", VIRTIO_ID_VSOCK, - sizeof(struct virtio_vsock_config)); - - /* Receive and transmit queues belong to vhost */ - vsock->recv_vq = virtio_add_queue(vdev, VHOST_VSOCK_QUEUE_SIZE, - vhost_vsock_handle_output); - vsock->trans_vq = virtio_add_queue(vdev, VHOST_VSOCK_QUEUE_SIZE, - vhost_vsock_handle_output); + vhost_vsock_common_realize(vdev, "vhost-vsock"); - /* The event queue belongs to QEMU */ - vsock->event_vq = virtio_add_queue(vdev, VHOST_VSOCK_QUEUE_SIZE, - vhost_vsock_handle_output); - - vsock->vhost_dev.nvqs = ARRAY_SIZE(vsock->vhost_vqs); - vsock->vhost_dev.vqs = vsock->vhost_vqs; - ret = vhost_dev_init(&vsock->vhost_dev, (void *)(uintptr_t)vhostfd, + ret = vhost_dev_init(&vvc->vhost_dev, (void *)(uintptr_t)vhostfd, VHOST_BACKEND_TYPE_KERNEL, 0); if (ret < 0) { error_setg_errno(errp, -ret, "vhost-vsock: vhost_dev_init failed"); goto err_virtio; } - ret = vhost_vsock_set_guest_cid(vsock); + ret = vhost_vsock_set_guest_cid(vdev); if (ret < 0) { error_setg_errno(errp, -ret, "vhost-vsock: unable to set guest cid"); goto err_vhost_dev; } - vsock->post_load_timer = NULL; return; err_vhost_dev: - vhost_dev_cleanup(&vsock->vhost_dev); + vhost_dev_cleanup(&vvc->vhost_dev); /* vhost_dev_cleanup() closes the vhostfd passed to vhost_dev_init() */ vhostfd = -1; err_virtio: - virtio_delete_queue(vsock->recv_vq); - virtio_delete_queue(vsock->trans_vq); - virtio_delete_queue(vsock->event_vq); - virtio_cleanup(vdev); + vhost_vsock_common_unrealize(vdev); if (vhostfd >= 0) { close(vhostfd); } @@ -379,19 +188,14 @@ err_virtio: static void vhost_vsock_device_unrealize(DeviceState *dev) { + VHostVSockCommon *vvc = VHOST_VSOCK_COMMON(dev); VirtIODevice *vdev = VIRTIO_DEVICE(dev); - VHostVSock *vsock = VHOST_VSOCK(dev); - - vhost_vsock_post_load_timer_cleanup(vsock); /* This will stop vhost backend if appropriate. */ vhost_vsock_set_status(vdev, 0); - vhost_dev_cleanup(&vsock->vhost_dev); - virtio_delete_queue(vsock->recv_vq); - virtio_delete_queue(vsock->trans_vq); - virtio_delete_queue(vsock->event_vq); - virtio_cleanup(vdev); + vhost_dev_cleanup(&vvc->vhost_dev); + vhost_vsock_common_unrealize(vdev); } static Property vhost_vsock_properties[] = { @@ -407,19 +211,16 @@ static void vhost_vsock_class_init(ObjectClass *klass, void *data) device_class_set_props(dc, vhost_vsock_properties); dc->vmsd = &vmstate_virtio_vhost_vsock; - set_bit(DEVICE_CATEGORY_MISC, dc->categories); vdc->realize = vhost_vsock_device_realize; vdc->unrealize = vhost_vsock_device_unrealize; vdc->get_features = vhost_vsock_get_features; vdc->get_config = vhost_vsock_get_config; vdc->set_status = vhost_vsock_set_status; - vdc->guest_notifier_mask = vhost_vsock_guest_notifier_mask; - vdc->guest_notifier_pending = vhost_vsock_guest_notifier_pending; } static const TypeInfo vhost_vsock_info = { .name = TYPE_VHOST_VSOCK, - .parent = TYPE_VIRTIO_DEVICE, + .parent = TYPE_VHOST_VSOCK_COMMON, .instance_size = sizeof(VHostVSock), .class_init = vhost_vsock_class_init, }; diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c index aff98a0ede..5fd25fe520 100644 --- a/hw/virtio/vhost.c +++ b/hw/virtio/vhost.c @@ -27,6 +27,7 @@ #include "migration/blocker.h" #include "migration/qemu-file-types.h" #include "sysemu/dma.h" +#include "sysemu/tcg.h" #include "trace.h" /* enabled until disconnected backend stabilizes */ @@ -403,26 +404,50 @@ static int vhost_verify_ring_mappings(struct vhost_dev *dev, return r; } +/* + * vhost_section: identify sections needed for vhost access + * + * We only care about RAM sections here (where virtqueue and guest + * internals accessed by virtio might live). If we find one we still + * allow the backend to potentially filter it out of our list. + */ static bool vhost_section(struct vhost_dev *dev, MemoryRegionSection *section) { - bool result; - bool log_dirty = memory_region_get_dirty_log_mask(section->mr) & - ~(1 << DIRTY_MEMORY_MIGRATION); - result = memory_region_is_ram(section->mr) && - !memory_region_is_rom(section->mr); - - /* Vhost doesn't handle any block which is doing dirty-tracking other - * than migration; this typically fires on VGA areas. - */ - result &= !log_dirty; + MemoryRegion *mr = section->mr; + + if (memory_region_is_ram(mr) && !memory_region_is_rom(mr)) { + uint8_t dirty_mask = memory_region_get_dirty_log_mask(mr); + uint8_t handled_dirty; + + /* + * Kernel based vhost doesn't handle any block which is doing + * dirty-tracking other than migration for which it has + * specific logging support. However for TCG the kernel never + * gets involved anyway so we can also ignore it's + * self-modiying code detection flags. However a vhost-user + * client could still confuse a TCG guest if it re-writes + * executable memory that has already been translated. + */ + handled_dirty = (1 << DIRTY_MEMORY_MIGRATION) | + (1 << DIRTY_MEMORY_CODE); - if (result && dev->vhost_ops->vhost_backend_mem_section_filter) { - result &= - dev->vhost_ops->vhost_backend_mem_section_filter(dev, section); - } + if (dirty_mask & ~handled_dirty) { + trace_vhost_reject_section(mr->name, 1); + return false; + } + + if (dev->vhost_ops->vhost_backend_mem_section_filter && + !dev->vhost_ops->vhost_backend_mem_section_filter(dev, section)) { + trace_vhost_reject_section(mr->name, 2); + return false; + } - trace_vhost_section(section->mr->name, result); - return result; + trace_vhost_section(mr->name); + return true; + } else { + trace_vhost_reject_section(mr->name, 3); + return false; + } } static void vhost_begin(MemoryListener *listener) @@ -809,12 +834,12 @@ err_features: return r; } -static int vhost_migration_log(MemoryListener *listener, int enable) +static int vhost_migration_log(MemoryListener *listener, bool enable) { struct vhost_dev *dev = container_of(listener, struct vhost_dev, memory_listener); int r; - if (!!enable == dev->log_enabled) { + if (enable == dev->log_enabled) { return 0; } if (!dev->started) { diff --git a/hw/virtio/virtio-balloon.c b/hw/virtio/virtio-balloon.c index 065cd450f1..10507b2a43 100644 --- a/hw/virtio/virtio-balloon.c +++ b/hw/virtio/virtio-balloon.c @@ -321,6 +321,67 @@ static void balloon_stats_set_poll_interval(Object *obj, Visitor *v, balloon_stats_change_timer(s, 0); } +static void virtio_balloon_handle_report(VirtIODevice *vdev, VirtQueue *vq) +{ + VirtIOBalloon *dev = VIRTIO_BALLOON(vdev); + VirtQueueElement *elem; + + while ((elem = virtqueue_pop(vq, sizeof(VirtQueueElement)))) { + unsigned int i; + + /* + * When we discard the page it has the effect of removing the page + * from the hypervisor itself and causing it to be zeroed when it + * is returned to us. So we must not discard the page if it is + * accessible by another device or process, or if the guest is + * expecting it to retain a non-zero value. + */ + if (qemu_balloon_is_inhibited() || dev->poison_val) { + goto skip_element; + } + + for (i = 0; i < elem->in_num; i++) { + void *addr = elem->in_sg[i].iov_base; + size_t size = elem->in_sg[i].iov_len; + ram_addr_t ram_offset; + RAMBlock *rb; + + /* + * There is no need to check the memory section to see if + * it is ram/readonly/romd like there is for handle_output + * below. If the region is not meant to be written to then + * address_space_map will have allocated a bounce buffer + * and it will be freed in address_space_unmap and trigger + * and unassigned_mem_write before failing to copy over the + * buffer. If more than one bad descriptor is provided it + * will return NULL after the first bounce buffer and fail + * to map any resources. + */ + rb = qemu_ram_block_from_host(addr, false, &ram_offset); + if (!rb) { + trace_virtio_balloon_bad_addr(elem->in_addr[i]); + continue; + } + + /* + * For now we will simply ignore unaligned memory regions, or + * regions that overrun the end of the RAMBlock. + */ + if (!QEMU_IS_ALIGNED(ram_offset | size, qemu_ram_pagesize(rb)) || + (ram_offset + size) > qemu_ram_get_used_length(rb)) { + continue; + } + + ram_block_discard_range(rb, ram_offset, size); + } + +skip_element: + virtqueue_push(vq, elem, 0); + virtio_notify(vdev, vq); + g_free(elem); + } +} + static void virtio_balloon_handle_output(VirtIODevice *vdev, VirtQueue *vq) { VirtIOBalloon *s = VIRTIO_BALLOON(vdev); @@ -634,6 +695,7 @@ static void virtio_balloon_get_config(VirtIODevice *vdev, uint8_t *config_data) config.num_pages = cpu_to_le32(dev->num_pages); config.actual = cpu_to_le32(dev->actual); + config.poison_val = cpu_to_le32(dev->poison_val); if (dev->free_page_report_status == FREE_PAGE_REPORT_S_REQUESTED) { config.free_page_report_cmd_id = @@ -683,6 +745,14 @@ static ram_addr_t get_current_ram_size(void) return size; } +static bool virtio_balloon_page_poison_support(void *opaque) +{ + VirtIOBalloon *s = opaque; + VirtIODevice *vdev = VIRTIO_DEVICE(s); + + return virtio_vdev_has_feature(vdev, VIRTIO_BALLOON_F_PAGE_POISON); +} + static void virtio_balloon_set_config(VirtIODevice *vdev, const uint8_t *config_data) { @@ -697,6 +767,10 @@ static void virtio_balloon_set_config(VirtIODevice *vdev, qapi_event_send_balloon_change(vm_ram_size - ((ram_addr_t) dev->actual << VIRTIO_BALLOON_PFN_SHIFT)); } + dev->poison_val = 0; + if (virtio_balloon_page_poison_support(dev)) { + dev->poison_val = le32_to_cpu(config.poison_val); + } trace_virtio_balloon_set_config(dev->actual, oldactual); } @@ -755,6 +829,17 @@ static const VMStateDescription vmstate_virtio_balloon_free_page_report = { } }; +static const VMStateDescription vmstate_virtio_balloon_page_poison = { + .name = "vitio-balloon-device/page-poison", + .version_id = 1, + .minimum_version_id = 1, + .needed = virtio_balloon_page_poison_support, + .fields = (VMStateField[]) { + VMSTATE_UINT32(poison_val, VirtIOBalloon), + VMSTATE_END_OF_LIST() + } +}; + static const VMStateDescription vmstate_virtio_balloon_device = { .name = "virtio-balloon-device", .version_id = 1, @@ -767,6 +852,7 @@ static const VMStateDescription vmstate_virtio_balloon_device = { }, .subsections = (const VMStateDescription * []) { &vmstate_virtio_balloon_free_page_report, + &vmstate_virtio_balloon_page_poison, NULL } }; @@ -789,6 +875,13 @@ static void virtio_balloon_device_realize(DeviceState *dev, Error **errp) return; } + if (virtio_has_feature(s->host_features, VIRTIO_BALLOON_F_FREE_PAGE_HINT) && + !s->iothread) { + error_setg(errp, "'free-page-hint' requires 'iothread' to be set"); + virtio_cleanup(vdev); + return; + } + s->ivq = virtio_add_queue(vdev, 128, virtio_balloon_handle_output); s->dvq = virtio_add_queue(vdev, 128, virtio_balloon_handle_output); s->svq = virtio_add_queue(vdev, 128, virtio_balloon_receive_stats); @@ -797,25 +890,18 @@ static void virtio_balloon_device_realize(DeviceState *dev, Error **errp) VIRTIO_BALLOON_F_FREE_PAGE_HINT)) { s->free_page_vq = virtio_add_queue(vdev, VIRTQUEUE_MAX_SIZE, virtio_balloon_handle_free_page_vq); - s->free_page_report_status = FREE_PAGE_REPORT_S_STOP; - s->free_page_report_cmd_id = - VIRTIO_BALLOON_FREE_PAGE_REPORT_CMD_ID_MIN; - s->free_page_report_notify.notify = - virtio_balloon_free_page_report_notify; precopy_add_notifier(&s->free_page_report_notify); - if (s->iothread) { - object_ref(OBJECT(s->iothread)); - s->free_page_bh = aio_bh_new(iothread_get_aio_context(s->iothread), - virtio_ballloon_get_free_page_hints, s); - qemu_mutex_init(&s->free_page_lock); - qemu_cond_init(&s->free_page_cond); - s->block_iothread = false; - } else { - /* Simply disable this feature if the iothread wasn't created. */ - s->host_features &= ~(1 << VIRTIO_BALLOON_F_FREE_PAGE_HINT); - virtio_error(vdev, "iothread is missing"); - } + + object_ref(OBJECT(s->iothread)); + s->free_page_bh = aio_bh_new(iothread_get_aio_context(s->iothread), + virtio_ballloon_get_free_page_hints, s); } + + if (virtio_has_feature(s->host_features, VIRTIO_BALLOON_F_REPORTING)) { + s->reporting_vq = virtio_add_queue(vdev, 32, + virtio_balloon_handle_report); + } + reset_stats(s); } @@ -824,8 +910,9 @@ static void virtio_balloon_device_unrealize(DeviceState *dev) VirtIODevice *vdev = VIRTIO_DEVICE(dev); VirtIOBalloon *s = VIRTIO_BALLOON(dev); - if (virtio_balloon_free_page_support(s)) { + if (s->free_page_bh) { qemu_bh_delete(s->free_page_bh); + object_unref(OBJECT(s->iothread)); virtio_balloon_free_page_stop(s); precopy_remove_notifier(&s->free_page_report_notify); } @@ -838,6 +925,9 @@ static void virtio_balloon_device_unrealize(DeviceState *dev) if (s->free_page_vq) { virtio_delete_queue(s->free_page_vq); } + if (s->reporting_vq) { + virtio_delete_queue(s->reporting_vq); + } virtio_cleanup(vdev); } @@ -854,6 +944,8 @@ static void virtio_balloon_device_reset(VirtIODevice *vdev) g_free(s->stats_vq_elem); s->stats_vq_elem = NULL; } + + s->poison_val = 0; } static void virtio_balloon_set_status(VirtIODevice *vdev, uint8_t status) @@ -892,6 +984,11 @@ static void virtio_balloon_instance_init(Object *obj) { VirtIOBalloon *s = VIRTIO_BALLOON(obj); + qemu_mutex_init(&s->free_page_lock); + qemu_cond_init(&s->free_page_cond); + s->free_page_report_cmd_id = VIRTIO_BALLOON_FREE_PAGE_REPORT_CMD_ID_MIN; + s->free_page_report_notify.notify = virtio_balloon_free_page_report_notify; + object_property_add(obj, "guest-stats", "guest statistics", balloon_stats_get_all, NULL, NULL, s); @@ -916,6 +1013,10 @@ static Property virtio_balloon_properties[] = { VIRTIO_BALLOON_F_DEFLATE_ON_OOM, false), DEFINE_PROP_BIT("free-page-hint", VirtIOBalloon, host_features, VIRTIO_BALLOON_F_FREE_PAGE_HINT, false), + DEFINE_PROP_BIT("page-poison", VirtIOBalloon, host_features, + VIRTIO_BALLOON_F_PAGE_POISON, true), + DEFINE_PROP_BIT("free-page-reporting", VirtIOBalloon, host_features, + VIRTIO_BALLOON_F_REPORTING, false), /* QEMU 4.0 accidentally changed the config size even when free-page-hint * is disabled, resulting in QEMU 3.1 migration incompatibility. This * property retains this quirk for QEMU 4.1 machine types. diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c index d028c17c24..7bc8c1c056 100644 --- a/hw/virtio/virtio-pci.c +++ b/hw/virtio/virtio-pci.c @@ -1273,16 +1273,20 @@ static void virtio_pci_common_write(void *opaque, hwaddr addr, virtio_queue_set_vector(vdev, vdev->queue_sel, val); break; case VIRTIO_PCI_COMMON_Q_ENABLE: - virtio_queue_set_num(vdev, vdev->queue_sel, - proxy->vqs[vdev->queue_sel].num); - virtio_queue_set_rings(vdev, vdev->queue_sel, + if (val == 1) { + virtio_queue_set_num(vdev, vdev->queue_sel, + proxy->vqs[vdev->queue_sel].num); + virtio_queue_set_rings(vdev, vdev->queue_sel, ((uint64_t)proxy->vqs[vdev->queue_sel].desc[1]) << 32 | proxy->vqs[vdev->queue_sel].desc[0], ((uint64_t)proxy->vqs[vdev->queue_sel].avail[1]) << 32 | proxy->vqs[vdev->queue_sel].avail[0], ((uint64_t)proxy->vqs[vdev->queue_sel].used[1]) << 32 | proxy->vqs[vdev->queue_sel].used[0]); - proxy->vqs[vdev->queue_sel].enabled = 1; + proxy->vqs[vdev->queue_sel].enabled = 1; + } else { + virtio_error(vdev, "wrong value for queue_enable %"PRIx64, val); + } break; case VIRTIO_PCI_COMMON_Q_DESCLO: proxy->vqs[vdev->queue_sel].desc[0] = val; diff --git a/include/hw/acpi/acpi-defs.h b/include/hw/acpi/acpi-defs.h index c13327fa78..3be9ab5049 100644 --- a/include/hw/acpi/acpi-defs.h +++ b/include/hw/acpi/acpi-defs.h @@ -88,6 +88,8 @@ typedef struct AcpiFadtData { struct AcpiGenericAddress pm_tmr; /* PM_TMR_BLK */ struct AcpiGenericAddress gpe0_blk; /* GPE0_BLK */ struct AcpiGenericAddress reset_reg; /* RESET_REG */ + struct AcpiGenericAddress sleep_ctl; /* SLEEP_CONTROL_REG */ + struct AcpiGenericAddress sleep_sts; /* SLEEP_STATUS_REG */ uint8_t reset_val; /* RESET_VALUE */ uint8_t rev; /* Revision */ uint32_t flags; /* Flags */ diff --git a/include/hw/acpi/aml-build.h b/include/hw/acpi/aml-build.h index ed7c89309e..d27da03d64 100644 --- a/include/hw/acpi/aml-build.h +++ b/include/hw/acpi/aml-build.h @@ -437,4 +437,6 @@ void build_slit(GArray *table_data, BIOSLinker *linker, MachineState *ms); void build_fadt(GArray *tbl, BIOSLinker *linker, const AcpiFadtData *f, const char *oem_id, const char *oem_table_id); + +void build_tpm2(GArray *table_data, BIOSLinker *linker, GArray *tcpalog); #endif diff --git a/include/hw/acpi/generic_event_device.h b/include/hw/acpi/generic_event_device.h index 83917de024..90a9180db5 100644 --- a/include/hw/acpi/generic_event_device.h +++ b/include/hw/acpi/generic_event_device.h @@ -86,7 +86,7 @@ #define ACPI_GED_NVDIMM_HOTPLUG_EVT 0x4 typedef struct GEDState { - MemoryRegion io; + MemoryRegion evt; uint32_t sel; } GEDState; diff --git a/include/hw/mem/nvdimm.h b/include/hw/mem/nvdimm.h index a3c08955e8..b67a1aedf6 100644 --- a/include/hw/mem/nvdimm.h +++ b/include/hw/mem/nvdimm.h @@ -155,6 +155,7 @@ typedef struct NVDIMMState NVDIMMState; void nvdimm_init_acpi_state(NVDIMMState *state, MemoryRegion *io, struct AcpiGenericAddress dsm_io, FWCfgState *fw_cfg, Object *owner); +void nvdimm_build_srat(GArray *table_data); void nvdimm_build_acpi(GArray *table_offsets, GArray *table_data, BIOSLinker *linker, NVDIMMState *state, uint32_t ram_slots); diff --git a/include/hw/virtio/vhost-user-vsock.h b/include/hw/virtio/vhost-user-vsock.h new file mode 100644 index 0000000000..4e128a4b9f --- /dev/null +++ b/include/hw/virtio/vhost-user-vsock.h @@ -0,0 +1,36 @@ +/* + * Vhost-user vsock virtio device + * + * Copyright 2020 Red Hat, Inc. + * + * 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 _QEMU_VHOST_USER_VSOCK_H +#define _QEMU_VHOST_USER_VSOCK_H + +#include "hw/virtio/vhost-vsock-common.h" +#include "hw/virtio/vhost-user.h" +#include "standard-headers/linux/virtio_vsock.h" + +#define TYPE_VHOST_USER_VSOCK "vhost-user-vsock-device" +#define VHOST_USER_VSOCK(obj) \ + OBJECT_CHECK(VHostUserVSock, (obj), TYPE_VHOST_USER_VSOCK) + +typedef struct { + CharBackend chardev; +} VHostUserVSockConf; + +typedef struct { + /*< private >*/ + VHostVSockCommon parent; + VhostUserState vhost_user; + VHostUserVSockConf conf; + struct virtio_vsock_config vsockcfg; + + /*< public >*/ +} VHostUserVSock; + +#endif /* _QEMU_VHOST_USER_VSOCK_H */ diff --git a/include/hw/virtio/vhost-user.h b/include/hw/virtio/vhost-user.h index 811e325f42..a9abca3288 100644 --- a/include/hw/virtio/vhost-user.h +++ b/include/hw/virtio/vhost-user.h @@ -20,6 +20,7 @@ typedef struct VhostUserHostNotifier { typedef struct VhostUserState { CharBackend *chr; VhostUserHostNotifier notifier[VIRTIO_QUEUE_MAX]; + int memory_slots; } VhostUserState; bool vhost_user_init(VhostUserState *user, CharBackend *chr, Error **errp); diff --git a/include/hw/virtio/vhost-vsock-common.h b/include/hw/virtio/vhost-vsock-common.h new file mode 100644 index 0000000000..f8b4aaae00 --- /dev/null +++ b/include/hw/virtio/vhost-vsock-common.h @@ -0,0 +1,47 @@ +/* + * Parent class for vhost-vsock devices + * + * Copyright 2015-2020 Red Hat, Inc. + * + * 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 _QEMU_VHOST_VSOCK_COMMON_H +#define _QEMU_VHOST_VSOCK_COMMON_H + +#include "hw/virtio/virtio.h" +#include "hw/virtio/vhost.h" + +#define TYPE_VHOST_VSOCK_COMMON "vhost-vsock-common" +#define VHOST_VSOCK_COMMON(obj) \ + OBJECT_CHECK(VHostVSockCommon, (obj), TYPE_VHOST_VSOCK_COMMON) + +enum { + VHOST_VSOCK_SAVEVM_VERSION = 0, + + VHOST_VSOCK_QUEUE_SIZE = 128, +}; + +typedef struct { + VirtIODevice parent; + + struct vhost_virtqueue vhost_vqs[2]; + struct vhost_dev vhost_dev; + + VirtQueue *event_vq; + VirtQueue *recv_vq; + VirtQueue *trans_vq; + + QEMUTimer *post_load_timer; +} VHostVSockCommon; + +int vhost_vsock_common_start(VirtIODevice *vdev); +void vhost_vsock_common_stop(VirtIODevice *vdev); +int vhost_vsock_common_pre_save(void *opaque); +int vhost_vsock_common_post_load(void *opaque, int version_id); +void vhost_vsock_common_realize(VirtIODevice *vdev, const char *name); +void vhost_vsock_common_unrealize(VirtIODevice *vdev); + +#endif /* _QEMU_VHOST_VSOCK_COMMON_H */ diff --git a/include/hw/virtio/vhost-vsock.h b/include/hw/virtio/vhost-vsock.h index bc5a988ee5..8cbb7b90f9 100644 --- a/include/hw/virtio/vhost-vsock.h +++ b/include/hw/virtio/vhost-vsock.h @@ -14,8 +14,7 @@ #ifndef QEMU_VHOST_VSOCK_H #define QEMU_VHOST_VSOCK_H -#include "hw/virtio/virtio.h" -#include "hw/virtio/vhost.h" +#include "hw/virtio/vhost-vsock-common.h" #define TYPE_VHOST_VSOCK "vhost-vsock-device" #define VHOST_VSOCK(obj) \ @@ -28,14 +27,8 @@ typedef struct { typedef struct { /*< private >*/ - VirtIODevice parent; + VHostVSockCommon parent; VHostVSockConf conf; - struct vhost_virtqueue vhost_vqs[2]; - struct vhost_dev vhost_dev; - VirtQueue *event_vq; - VirtQueue *recv_vq; - VirtQueue *trans_vq; - QEMUTimer *post_load_timer; /*< public >*/ } VHostVSock; diff --git a/include/hw/virtio/virtio-balloon.h b/include/hw/virtio/virtio-balloon.h index d1c968d237..d49fef00ce 100644 --- a/include/hw/virtio/virtio-balloon.h +++ b/include/hw/virtio/virtio-balloon.h @@ -42,7 +42,7 @@ enum virtio_balloon_free_page_report_status { typedef struct VirtIOBalloon { VirtIODevice parent_obj; - VirtQueue *ivq, *dvq, *svq, *free_page_vq; + VirtQueue *ivq, *dvq, *svq, *free_page_vq, *reporting_vq; uint32_t free_page_report_status; uint32_t num_pages; uint32_t actual; @@ -70,6 +70,7 @@ typedef struct VirtIOBalloon { uint32_t host_features; bool qemu_4_0_config_size; + uint32_t poison_val; } VirtIOBalloon; #endif diff --git a/include/qemu/qemu-plugin.h b/include/qemu/qemu-plugin.h index 89ed579f55..bab8b0d4b3 100644 --- a/include/qemu/qemu-plugin.h +++ b/include/qemu/qemu-plugin.h @@ -12,6 +12,7 @@ #include <inttypes.h> #include <stdbool.h> +#include <stddef.h> /* * For best performance, build the plugin with -fvisibility=hidden so that diff --git a/include/sysemu/tpm.h b/include/sysemu/tpm.h index f37851b1aa..03fb25941c 100644 --- a/include/sysemu/tpm.h +++ b/include/sysemu/tpm.h @@ -50,6 +50,8 @@ typedef struct TPMIfClass { #define TPM_IS_TIS_ISA(chr) \ object_dynamic_cast(OBJECT(chr), TYPE_TPM_TIS_ISA) +#define TPM_IS_TIS_SYSBUS(chr) \ + object_dynamic_cast(OBJECT(chr), TYPE_TPM_TIS_SYSBUS) #define TPM_IS_CRB(chr) \ object_dynamic_cast(OBJECT(chr), TYPE_TPM_CRB) #define TPM_IS_SPAPR(chr) \ diff --git a/linux-user/elfload.c b/linux-user/elfload.c index ebc663ea0b..b5cb21384a 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -389,7 +389,7 @@ static bool init_guest_commpage(void) { void *want = g2h(ARM_COMMPAGE & -qemu_host_page_size); void *addr = mmap(want, qemu_host_page_size, PROT_READ | PROT_WRITE, - MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); if (addr == MAP_FAILED) { perror("Allocating guest commpage"); @@ -2101,9 +2101,54 @@ static void pgb_have_guest_base(const char *image_name, abi_ulong guest_loaddr, } } +/** + * pgd_find_hole_fallback: potential mmap address + * @guest_size: size of available space + * @brk: location of break + * @align: memory alignment + * + * This is a fallback method for finding a hole in the host address + * space if we don't have the benefit of being able to access + * /proc/self/map. It can potentially take a very long time as we can + * only dumbly iterate up the host address space seeing if the + * allocation would work. + */ +static uintptr_t pgd_find_hole_fallback(uintptr_t guest_size, uintptr_t brk, + long align, uintptr_t offset) +{ + uintptr_t base; + + /* Start (aligned) at the bottom and work our way up */ + base = ROUND_UP(mmap_min_addr, align); + + while (true) { + uintptr_t align_start, end; + align_start = ROUND_UP(base, align); + end = align_start + guest_size + offset; + + /* if brk is anywhere in the range give ourselves some room to grow. */ + if (align_start <= brk && brk < end) { + base = brk + (16 * MiB); + continue; + } else if (align_start + guest_size < align_start) { + /* we have run out of space */ + return -1; + } else { + int flags = MAP_ANONYMOUS | MAP_PRIVATE | MAP_NORESERVE | MAP_FIXED; + void * mmap_start = mmap((void *) align_start, guest_size, + PROT_NONE, flags, -1, 0); + if (mmap_start != MAP_FAILED) { + munmap((void *) align_start, guest_size); + return (uintptr_t) mmap_start + offset; + } + base += qemu_host_page_size; + } + } +} + /* Return value for guest_base, or -1 if no hole found. */ static uintptr_t pgb_find_hole(uintptr_t guest_loaddr, uintptr_t guest_size, - long align) + long align, uintptr_t offset) { GSList *maps, *iter; uintptr_t this_start, this_end, next_start, brk; @@ -2116,6 +2161,10 @@ static uintptr_t pgb_find_hole(uintptr_t guest_loaddr, uintptr_t guest_size, /* Read brk after we've read the maps, which will malloc. */ brk = (uintptr_t)sbrk(0); + if (!maps) { + return pgd_find_hole_fallback(guest_size, brk, align, offset); + } + /* The first hole is before the first map entry. */ this_start = mmap_min_addr; @@ -2125,7 +2174,7 @@ static uintptr_t pgb_find_hole(uintptr_t guest_loaddr, uintptr_t guest_size, this_end = ((MapInfo *)iter->data)->start; next_start = ((MapInfo *)iter->data)->end; - align_start = ROUND_UP(this_start, align); + align_start = ROUND_UP(this_start + offset, align); /* Skip holes that are too small. */ if (align_start >= this_end) { @@ -2175,6 +2224,7 @@ static void pgb_static(const char *image_name, abi_ulong orig_loaddr, { uintptr_t loaddr = orig_loaddr; uintptr_t hiaddr = orig_hiaddr; + uintptr_t offset = 0; uintptr_t addr; if (hiaddr != orig_hiaddr) { @@ -2188,18 +2238,19 @@ static void pgb_static(const char *image_name, abi_ulong orig_loaddr, if (ARM_COMMPAGE) { /* * Extend the allocation to include the commpage. - * For a 64-bit host, this is just 4GiB; for a 32-bit host, - * the address arithmetic will wrap around, but the difference - * will produce the correct allocation size. + * For a 64-bit host, this is just 4GiB; for a 32-bit host we + * need to ensure there is space bellow the guest_base so we + * can map the commpage in the place needed when the address + * arithmetic wraps around. */ if (sizeof(uintptr_t) == 8 || loaddr >= 0x80000000u) { - hiaddr = (uintptr_t)4 << 30; + hiaddr = (uintptr_t) 4 << 30; } else { - loaddr = ARM_COMMPAGE & -align; + offset = -(ARM_COMMPAGE & -align); } } - addr = pgb_find_hole(loaddr, hiaddr - loaddr, align); + addr = pgb_find_hole(loaddr, hiaddr - loaddr, align, offset); if (addr == -1) { /* * If ARM_COMMPAGE, there *might* be a non-consecutive allocation @@ -2234,7 +2285,7 @@ static void pgb_dynamic(const char *image_name, long align) * just above that, and maximises the positive guest addresses. */ commpage = ARM_COMMPAGE & -align; - addr = pgb_find_hole(commpage, -commpage, align); + addr = pgb_find_hole(commpage, -commpage, align, 0); assert(addr != -1); guest_base = addr; } diff --git a/linux-user/mmap.c b/linux-user/mmap.c index caab62909e..0019447892 100644 --- a/linux-user/mmap.c +++ b/linux-user/mmap.c @@ -467,7 +467,7 @@ abi_long target_mmap(abi_ulong start, abi_ulong len, int prot, * It can fail only on 64-bit host with 32-bit target. * On any other target/host host mmap() handles this error correctly. */ - if (!guest_range_valid(start, len)) { + if (end < start || !guest_range_valid(start, len)) { errno = ENOMEM; goto fail; } diff --git a/monitor/hmp-cmds.c b/monitor/hmp-cmds.c index 9c61e769ca..e03adf0d4d 100644 --- a/monitor/hmp-cmds.c +++ b/monitor/hmp-cmds.c @@ -688,7 +688,8 @@ static void hmp_info_pci_device(Monitor *mon, const PciDeviceInfo *dev) } if (dev->has_irq) { - monitor_printf(mon, " IRQ %" PRId64 ".\n", dev->irq); + monitor_printf(mon, " IRQ %" PRId64 ", pin %c\n", + dev->irq, (char)('A' + dev->irq_pin - 1)); } if (dev->has_pci_bridge) { diff --git a/nbd/server.c b/nbd/server.c index 02b1ed0801..20754e9ebc 100644 --- a/nbd/server.c +++ b/nbd/server.c @@ -217,7 +217,7 @@ nbd_negotiate_send_rep_verr(NBDClient *client, uint32_t type, msg = g_strdup_vprintf(fmt, va); len = strlen(msg); - assert(len < 4096); + assert(len < NBD_MAX_STRING_SIZE); trace_nbd_negotiate_send_rep_err(msg); ret = nbd_negotiate_send_rep_len(client, type, len, errp); if (ret < 0) { @@ -231,6 +231,19 @@ nbd_negotiate_send_rep_verr(NBDClient *client, uint32_t type, return 0; } +/* + * Return a malloc'd copy of @name suitable for use in an error reply. + */ +static char * +nbd_sanitize_name(const char *name) +{ + if (strnlen(name, 80) < 80) { + return g_strdup(name); + } + /* XXX Should we also try to sanitize any control characters? */ + return g_strdup_printf("%.80s...", name); +} + /* Send an error reply. * Return -errno on error, 0 on success. */ static int GCC_FMT_ATTR(4, 5) @@ -595,9 +608,11 @@ static int nbd_negotiate_handle_info(NBDClient *client, Error **errp) exp = nbd_export_find(name); if (!exp) { + g_autofree char *sane_name = nbd_sanitize_name(name); + return nbd_negotiate_send_rep_err(client, NBD_REP_ERR_UNKNOWN, errp, "export '%s' not present", - name); + sane_name); } /* Don't bother sending NBD_INFO_NAME unless client requested it */ @@ -995,8 +1010,10 @@ static int nbd_negotiate_meta_queries(NBDClient *client, meta->exp = nbd_export_find(export_name); if (meta->exp == NULL) { + g_autofree char *sane_name = nbd_sanitize_name(export_name); + return nbd_opt_drop(client, NBD_REP_ERR_UNKNOWN, errp, - "export '%s' not present", export_name); + "export '%s' not present", sane_name); } ret = nbd_opt_read(client, &nb_queries, sizeof(nb_queries), errp); @@ -1506,7 +1506,7 @@ static int net_param_nic(void *dummy, QemuOpts *opts, Error **errp) /* Create an ID if the user did not specify one */ nd_id = g_strdup(qemu_opts_id(opts)); if (!nd_id) { - nd_id = g_strdup_printf("__org.qemu.nic%i\n", idx); + nd_id = g_strdup_printf("__org.qemu.nic%i", idx); qemu_opts_set_id(opts, nd_id); } diff --git a/qapi/misc.json b/qapi/misc.json index 99b90ac80b..a5a0beb902 100644 --- a/qapi/misc.json +++ b/qapi/misc.json @@ -403,6 +403,8 @@ # # @irq: if an IRQ is assigned to the device, the IRQ number # +# @irq_pin: the IRQ pin, zero means no IRQ (since 5.1) +# # @qdev_id: the device name of the PCI device # # @pci_bridge: if the device is a PCI bridge, the bridge information @@ -417,8 +419,8 @@ { 'struct': 'PciDeviceInfo', 'data': {'bus': 'int', 'slot': 'int', 'function': 'int', 'class_info': 'PciDeviceClass', 'id': 'PciDeviceId', - '*irq': 'int', 'qdev_id': 'str', '*pci_bridge': 'PciBridgeInfo', - 'regions': ['PciMemoryRegion']} } + '*irq': 'int', 'irq_pin': 'int', 'qdev_id': 'str', + '*pci_bridge': 'PciBridgeInfo', 'regions': ['PciMemoryRegion'] }} ## # @PciInfo: diff --git a/scripts/clean-includes b/scripts/clean-includes index dd938daa3e..795b3bea31 100755 --- a/scripts/clean-includes +++ b/scripts/clean-includes @@ -123,6 +123,7 @@ for f in "$@"; do ;; *include/qemu/osdep.h | \ *include/qemu/compiler.h | \ + *include/qemu/qemu-plugin.h | \ *include/glib-compat.h | \ *include/sysemu/os-posix.h | \ *include/sysemu/os-win32.h | \ diff --git a/scripts/coverity-scan/coverity-scan.docker b/scripts/coverity-scan/coverity-scan.docker index efcf63224d..018c03de6d 100644 --- a/scripts/coverity-scan/coverity-scan.docker +++ b/scripts/coverity-scan/coverity-scan.docker @@ -19,7 +19,6 @@ FROM fedora:30 ENV PACKAGES \ alsa-lib-devel \ bc \ - bison \ brlapi-devel \ bzip2 \ bzip2-devel \ @@ -30,7 +29,6 @@ ENV PACKAGES \ dbus-daemon \ device-mapper-multipath-devel \ findutils \ - flex \ gcc \ gcc-c++ \ gettext \ diff --git a/scripts/decodetree.py b/scripts/decodetree.py index f9d204aa36..530d41ca62 100755 --- a/scripts/decodetree.py +++ b/scripts/decodetree.py @@ -31,7 +31,6 @@ variablewidth = False fields = {} arguments = {} formats = {} -patterns = [] allpatterns = [] anyextern = False @@ -51,23 +50,27 @@ def error_with_file(file, lineno, *args): global output_file global output_fd + prefix = '' + if file: + prefix += '{0}:'.format(file) if lineno: - r = '{0}:{1}: error:'.format(file, lineno) - elif input_file: - r = '{0}: error:'.format(file) - else: - r = 'error:' - for a in args: - r += ' ' + str(a) - r += '\n' - sys.stderr.write(r) + prefix += '{0}:'.format(lineno) + if prefix: + prefix += ' ' + print(prefix, end='error: ', file=sys.stderr) + print(*args, file=sys.stderr) + if output_file and output_fd: output_fd.close() os.remove(output_file) exit(1) +# end error_with_file + def error(lineno, *args): - error_with_file(input_file, lineno, args) + error_with_file(input_file, lineno, *args) +# end error + def output(*args): global output_fd @@ -120,6 +123,7 @@ def is_pow2(x): def ctz(x): """Return the number of times 2 factors into X.""" + assert x != 0 r = 0 while ((x >> r) & 1) == 0: r += 1 @@ -127,6 +131,8 @@ def ctz(x): def is_contiguous(bits): + if bits == 0: + return -1 shift = ctz(bits) if is_pow2((bits >> shift) + 1): return shift @@ -364,32 +370,99 @@ class Pattern(General): output(ind, 'u.f_', arg, '.', n, ' = ', f.str_extract(), ';\n') output(ind, 'if (', translate_prefix, '_', self.name, '(ctx, &u.f_', arg, ')) return true;\n') + + # Normal patterns do not have children. + def build_tree(self): + return + def prop_masks(self): + return + def prop_format(self): + return + def prop_width(self): + return + # end Pattern class MultiPattern(General): - """Class representing an overlapping set of instruction patterns""" + """Class representing a set of instruction patterns""" - def __init__(self, lineno, pats, fixb, fixm, udfm, w): + def __init__(self, lineno): self.file = input_file self.lineno = lineno - self.pats = pats + self.pats = [] self.base = None - self.fixedbits = fixb - self.fixedmask = fixm - self.undefmask = udfm - self.width = w + self.fixedbits = 0 + self.fixedmask = 0 + self.undefmask = 0 + self.width = None def __str__(self): - r = "{" - for p in self.pats: - r = r + ' ' + str(p) - return r + "}" + r = 'group' + if self.fixedbits is not None: + r += ' ' + str_match_bits(self.fixedbits, self.fixedmask) + return r def output_decl(self): for p in self.pats: p.output_decl() + def prop_masks(self): + global insnmask + + fixedmask = insnmask + undefmask = insnmask + + # Collect fixedmask/undefmask for all of the children. + for p in self.pats: + p.prop_masks() + fixedmask &= p.fixedmask + undefmask &= p.undefmask + + # Widen fixedmask until all fixedbits match + repeat = True + fixedbits = 0 + while repeat and fixedmask != 0: + fixedbits = None + for p in self.pats: + thisbits = p.fixedbits & fixedmask + if fixedbits is None: + fixedbits = thisbits + elif fixedbits != thisbits: + fixedmask &= ~(fixedbits ^ thisbits) + break + else: + repeat = False + + self.fixedbits = fixedbits + self.fixedmask = fixedmask + self.undefmask = undefmask + + def build_tree(self): + for p in self.pats: + p.build_tree() + + def prop_format(self): + for p in self.pats: + p.build_tree() + + def prop_width(self): + width = None + for p in self.pats: + p.prop_width() + if width is None: + width = p.width + elif width != p.width: + error_with_file(self.file, self.lineno, + 'width mismatch in patterns within braces') + self.width = width + +# end MultiPattern + + +class IncMultiPattern(MultiPattern): + """Class representing an overlapping set of instruction patterns""" + def output_code(self, i, extracted, outerbits, outermask): global translate_prefix ind = str_indent(i) @@ -406,7 +479,154 @@ class MultiPattern(General): output(ind, '}\n') else: p.output_code(i, extracted, p.fixedbits, p.fixedmask) -#end MultiPattern +#end IncMultiPattern + + +class Tree: + """Class representing a node in a decode tree""" + + def __init__(self, fm, tm): + self.fixedmask = fm + self.thismask = tm + self.subs = [] + self.base = None + + def str1(self, i): + ind = str_indent(i) + r = '{0}{1:08x}'.format(ind, self.fixedmask) + if self.format: + r += ' ' + self.format.name + r += ' [\n' + for (b, s) in self.subs: + r += '{0} {1:08x}:\n'.format(ind, b) + r += s.str1(i + 4) + '\n' + r += ind + ']' + return r + + def __str__(self): + return self.str1(0) + + def output_code(self, i, extracted, outerbits, outermask): + ind = str_indent(i) + + # If we identified all nodes below have the same format, + # extract the fields now. + if not extracted and self.base: + output(ind, self.base.extract_name(), + '(ctx, &u.f_', self.base.base.name, ', insn);\n') + extracted = True + + # Attempt to aid the compiler in producing compact switch statements. + # If the bits in the mask are contiguous, extract them. + sh = is_contiguous(self.thismask) + if sh > 0: + # Propagate SH down into the local functions. + def str_switch(b, sh=sh): + return '(insn >> {0}) & 0x{1:x}'.format(sh, b >> sh) + + def str_case(b, sh=sh): + return '0x{0:x}'.format(b >> sh) + else: + def str_switch(b): + return 'insn & 0x{0:08x}'.format(b) + + def str_case(b): + return '0x{0:08x}'.format(b) + + output(ind, 'switch (', str_switch(self.thismask), ') {\n') + for b, s in sorted(self.subs): + assert (self.thismask & ~s.fixedmask) == 0 + innermask = outermask | self.thismask + innerbits = outerbits | b + output(ind, 'case ', str_case(b), ':\n') + output(ind, ' /* ', + str_match_bits(innerbits, innermask), ' */\n') + s.output_code(i + 4, extracted, innerbits, innermask) + output(ind, ' return false;\n') + output(ind, '}\n') +# end Tree + + +class ExcMultiPattern(MultiPattern): + """Class representing a non-overlapping set of instruction patterns""" + + def output_code(self, i, extracted, outerbits, outermask): + # Defer everything to our decomposed Tree node + self.tree.output_code(i, extracted, outerbits, outermask) + + @staticmethod + def __build_tree(pats, outerbits, outermask): + # Find the intersection of all remaining fixedmask. + innermask = ~outermask & insnmask + for i in pats: + innermask &= i.fixedmask + + if innermask == 0: + # Edge condition: One pattern covers the entire insnmask + if len(pats) == 1: + t = Tree(outermask, innermask) + t.subs.append((0, pats[0])) + return t + + text = 'overlapping patterns:' + for p in pats: + text += '\n' + p.file + ':' + str(p.lineno) + ': ' + str(p) + error_with_file(pats[0].file, pats[0].lineno, text) + + fullmask = outermask | innermask + + # Sort each element of pats into the bin selected by the mask. + bins = {} + for i in pats: + fb = i.fixedbits & innermask + if fb in bins: + bins[fb].append(i) + else: + bins[fb] = [i] + + # We must recurse if any bin has more than one element or if + # the single element in the bin has not been fully matched. + t = Tree(fullmask, innermask) + + for b, l in bins.items(): + s = l[0] + if len(l) > 1 or s.fixedmask & ~fullmask != 0: + s = ExcMultiPattern.__build_tree(l, b | outerbits, fullmask) + t.subs.append((b, s)) + + return t + + def build_tree(self): + super().prop_format() + self.tree = self.__build_tree(self.pats, self.fixedbits, + self.fixedmask) + + @staticmethod + def __prop_format(tree): + """Propagate Format objects into the decode tree""" + + # Depth first search. + for (b, s) in tree.subs: + if isinstance(s, Tree): + ExcMultiPattern.__prop_format(s) + + # If all entries in SUBS have the same format, then + # propagate that into the tree. + f = None + for (b, s) in tree.subs: + if f is None: + f = s.base + if f is None: + return + if f is not s.base: + return + tree.base = f + + def prop_format(self): + super().prop_format() + self.__prop_format(self.tree) + +# end ExcMultiPattern def parse_field(lineno, name, toks): @@ -565,18 +785,19 @@ def infer_format(arg, fieldmask, flds, width): # end infer_format -def parse_generic(lineno, is_format, name, toks): +def parse_generic(lineno, parent_pat, name, toks): """Parse one instruction format from TOKS at LINENO""" global fields global arguments global formats - global patterns global allpatterns global re_ident global insnwidth global insnmask global variablewidth + is_format = parent_pat is None + fixedmask = 0 fixedbits = 0 undefmask = 0 @@ -727,7 +948,7 @@ def parse_generic(lineno, is_format, name, toks): error(lineno, 'field {0} not initialized'.format(f)) pat = Pattern(name, lineno, fmt, fixedbits, fixedmask, undefmask, fieldmask, flds, width) - patterns.append(pat) + parent_pat.pats.append(pat) allpatterns.append(pat) # Validate the masks that we have assembled. @@ -747,62 +968,16 @@ def parse_generic(lineno, is_format, name, toks): .format(allbits ^ insnmask)) # end parse_general -def build_multi_pattern(lineno, pats): - """Validate the Patterns going into a MultiPattern.""" - global patterns - global insnmask - - if len(pats) < 2: - error(lineno, 'less than two patterns within braces') - - fixedmask = insnmask - undefmask = insnmask - - # Collect fixed/undefmask for all of the children. - # Move the defining lineno back to that of the first child. - for p in pats: - fixedmask &= p.fixedmask - undefmask &= p.undefmask - if p.lineno < lineno: - lineno = p.lineno - - width = None - for p in pats: - if width is None: - width = p.width - elif width != p.width: - error(lineno, 'width mismatch in patterns within braces') - - repeat = True - while repeat: - if fixedmask == 0: - error(lineno, 'no overlap in patterns within braces') - fixedbits = None - for p in pats: - thisbits = p.fixedbits & fixedmask - if fixedbits is None: - fixedbits = thisbits - elif fixedbits != thisbits: - fixedmask &= ~(fixedbits ^ thisbits) - break - else: - repeat = False - mp = MultiPattern(lineno, pats, fixedbits, fixedmask, undefmask, width) - patterns.append(mp) -# end build_multi_pattern - -def parse_file(f): +def parse_file(f, parent_pat): """Parse all of the patterns within a file""" - global patterns - # Read all of the lines of the file. Concatenate lines # ending in backslash; discard empty lines and comments. toks = [] lineno = 0 nesting = 0 - saved_pats = [] + nesting_pats = [] for line in f: lineno += 1 @@ -846,17 +1021,23 @@ def parse_file(f): del toks[0] # End nesting? - if name == '}': - if nesting == 0: - error(start_lineno, 'mismatched close brace') + if name == '}' or name == ']': if len(toks) != 0: error(start_lineno, 'extra tokens after close brace') + + # Make sure { } and [ ] nest properly. + if (name == '}') != isinstance(parent_pat, IncMultiPattern): + error(lineno, 'mismatched close brace') + + try: + parent_pat = nesting_pats.pop() + except: + error(lineno, 'extra close brace') + nesting -= 2 if indent != nesting: - error(start_lineno, 'indentation ', indent, ' != ', nesting) - pats = patterns - patterns = saved_pats.pop() - build_multi_pattern(lineno, pats) + error(lineno, 'indentation ', indent, ' != ', nesting) + toks = [] continue @@ -865,11 +1046,18 @@ def parse_file(f): error(start_lineno, 'indentation ', indent, ' != ', nesting) # Start nesting? - if name == '{': + if name == '{' or name == '[': if len(toks) != 0: error(start_lineno, 'extra tokens after open brace') - saved_pats.append(patterns) - patterns = [] + + if name == '{': + nested_pat = IncMultiPattern(start_lineno) + else: + nested_pat = ExcMultiPattern(start_lineno) + parent_pat.pats.append(nested_pat) + nesting_pats.append(parent_pat) + parent_pat = nested_pat + nesting += 2 toks = [] continue @@ -880,113 +1068,14 @@ def parse_file(f): elif name[0] == '&': parse_arguments(start_lineno, name[1:], toks) elif name[0] == '@': - parse_generic(start_lineno, True, name[1:], toks) + parse_generic(start_lineno, None, name[1:], toks) else: - parse_generic(start_lineno, False, name, toks) + parse_generic(start_lineno, parent_pat, name, toks) toks = [] -# end parse_file - - -class Tree: - """Class representing a node in a decode tree""" - - def __init__(self, fm, tm): - self.fixedmask = fm - self.thismask = tm - self.subs = [] - self.base = None - def str1(self, i): - ind = str_indent(i) - r = '{0}{1:08x}'.format(ind, self.fixedmask) - if self.format: - r += ' ' + self.format.name - r += ' [\n' - for (b, s) in self.subs: - r += '{0} {1:08x}:\n'.format(ind, b) - r += s.str1(i + 4) + '\n' - r += ind + ']' - return r - - def __str__(self): - return self.str1(0) - - def output_code(self, i, extracted, outerbits, outermask): - ind = str_indent(i) - - # If we identified all nodes below have the same format, - # extract the fields now. - if not extracted and self.base: - output(ind, self.base.extract_name(), - '(ctx, &u.f_', self.base.base.name, ', insn);\n') - extracted = True - - # Attempt to aid the compiler in producing compact switch statements. - # If the bits in the mask are contiguous, extract them. - sh = is_contiguous(self.thismask) - if sh > 0: - # Propagate SH down into the local functions. - def str_switch(b, sh=sh): - return '(insn >> {0}) & 0x{1:x}'.format(sh, b >> sh) - - def str_case(b, sh=sh): - return '0x{0:x}'.format(b >> sh) - else: - def str_switch(b): - return 'insn & 0x{0:08x}'.format(b) - - def str_case(b): - return '0x{0:08x}'.format(b) - - output(ind, 'switch (', str_switch(self.thismask), ') {\n') - for b, s in sorted(self.subs): - assert (self.thismask & ~s.fixedmask) == 0 - innermask = outermask | self.thismask - innerbits = outerbits | b - output(ind, 'case ', str_case(b), ':\n') - output(ind, ' /* ', - str_match_bits(innerbits, innermask), ' */\n') - s.output_code(i + 4, extracted, innerbits, innermask) - output(ind, ' return false;\n') - output(ind, '}\n') -# end Tree - - -def build_tree(pats, outerbits, outermask): - # Find the intersection of all remaining fixedmask. - innermask = ~outermask & insnmask - for i in pats: - innermask &= i.fixedmask - - if innermask == 0: - text = 'overlapping patterns:' - for p in pats: - text += '\n' + p.file + ':' + str(p.lineno) + ': ' + str(p) - error_with_file(pats[0].file, pats[0].lineno, text) - - fullmask = outermask | innermask - - # Sort each element of pats into the bin selected by the mask. - bins = {} - for i in pats: - fb = i.fixedbits & innermask - if fb in bins: - bins[fb].append(i) - else: - bins[fb] = [i] - - # We must recurse if any bin has more than one element or if - # the single element in the bin has not been fully matched. - t = Tree(fullmask, innermask) - - for b, l in bins.items(): - s = l[0] - if len(l) > 1 or s.fixedmask & ~fullmask != 0: - s = build_tree(l, b | outerbits, fullmask) - t.subs.append((b, s)) - - return t -# end build_tree + if nesting != 0: + error(lineno, 'missing close brace') +# end parse_file class SizeTree: @@ -1130,28 +1219,6 @@ def build_size_tree(pats, width, outerbits, outermask): # end build_size_tree -def prop_format(tree): - """Propagate Format objects into the decode tree""" - - # Depth first search. - for (b, s) in tree.subs: - if isinstance(s, Tree): - prop_format(s) - - # If all entries in SUBS have the same format, then - # propagate that into the tree. - f = None - for (b, s) in tree.subs: - if f is None: - f = s.base - if f is None: - return - if f is not s.base: - return - tree.base = f -# end prop_format - - def prop_size(tree): """Propagate minimum widths up the decode size tree""" @@ -1172,7 +1239,6 @@ def prop_size(tree): def main(): global arguments global formats - global patterns global allpatterns global translate_scope global translate_prefix @@ -1219,19 +1285,30 @@ def main(): if len(args) < 1: error(0, 'missing input file') + + toppat = ExcMultiPattern(0) + for filename in args: input_file = filename f = open(filename, 'r') - parse_file(f) + parse_file(f, toppat) f.close() + # We do not want to compute masks for toppat, because those masks + # are used as a starting point for build_tree. For toppat, we must + # insist that decode begins from naught. + for i in toppat.pats: + i.prop_masks() + + toppat.build_tree() + toppat.prop_format() + if variablewidth: - stree = build_size_tree(patterns, 8, 0, 0) + for i in toppat.pats: + i.prop_width() + stree = build_size_tree(toppat.pats, 8, 0, 0) prop_size(stree) - dtree = build_tree(patterns, 0, 0) - prop_format(dtree) - if output_file: output_fd = open(output_file, 'w') else: @@ -1289,7 +1366,7 @@ def main(): f = arguments[n] output(i4, i4, f.struct_name(), ' f_', f.name, ';\n') output(i4, '} u;\n\n') - dtree.output_code(4, False, 0, 0) + toppat.output_code(4, False, 0, 0) output(i4, 'return false;\n') output('}\n') diff --git a/target/arm/t32.decode b/target/arm/t32.decode index c63082fc9c..c21a988f97 100644 --- a/target/arm/t32.decode +++ b/target/arm/t32.decode @@ -312,13 +312,13 @@ CLZ 1111 1010 1011 ---- 1111 .... 1000 .... @rdm &cps # Miscellaneous control - { + [ CLREX 1111 0011 1011 1111 1000 1111 0010 1111 DSB 1111 0011 1011 1111 1000 1111 0100 ---- DMB 1111 0011 1011 1111 1000 1111 0101 ---- ISB 1111 0011 1011 1111 1000 1111 0110 ---- SB 1111 0011 1011 1111 1000 1111 0111 0000 - } + ] # Note that the v7m insn overlaps both the normal and banked insn. { diff --git a/target/i386/cpu.c b/target/i386/cpu.c index 2d3b8d5dea..4fe97f9b41 100644 --- a/target/i386/cpu.c +++ b/target/i386/cpu.c @@ -6191,7 +6191,7 @@ static void x86_cpu_machine_done(Notifier *n, void *unused) if (smram) { cpu->smram = g_new(MemoryRegion, 1); memory_region_init_alias(cpu->smram, OBJECT(cpu), "smram", - smram, 0, 1ull << 32); + smram, 0, 4 * GiB); memory_region_set_enabled(cpu->smram, true); memory_region_add_subregion_overlap(cpu->cpu_as_root, 0, cpu->smram, 1); } diff --git a/target/mips/Makefile.objs b/target/mips/Makefile.objs index 91eb691833..b820b3b7bc 100644 --- a/target/mips/Makefile.objs +++ b/target/mips/Makefile.objs @@ -1,6 +1,6 @@ obj-y += translate.o cpu.o gdbstub.o helper.o obj-y += op_helper.o cp0_helper.o fpu_helper.o -obj-y += dsp_helper.o lmi_helper.o msa_helper.o +obj-y += dsp_helper.o lmmi_helper.o msa_helper.o obj-$(CONFIG_SOFTMMU) += mips-semi.o obj-$(CONFIG_SOFTMMU) += machine.o cp0_timer.o obj-$(CONFIG_KVM) += kvm.o diff --git a/target/mips/cpu.h b/target/mips/cpu.h index 94d01ea798..7cf7f5239f 100644 --- a/target/mips/cpu.h +++ b/target/mips/cpu.h @@ -198,8 +198,8 @@ typedef struct mips_def_t mips_def_t; * 3 Config3 WatchLo3 WatchHi * 4 Config4 WatchLo4 WatchHi * 5 Config5 WatchLo5 WatchHi - * 6 WatchLo6 WatchHi - * 7 WatchLo7 WatchHi + * 6 Config6 WatchLo6 WatchHi + * 7 Config7 WatchLo7 WatchHi * * * Register 20 Register 21 Register 22 Register 23 @@ -940,7 +940,35 @@ struct CPUMIPSState { #define CP0C5_UFR 2 #define CP0C5_NFExists 0 int32_t CP0_Config6; + int32_t CP0_Config6_rw_bitmask; +#define CP0C6_BPPASS 31 +#define CP0C6_KPOS 24 +#define CP0C6_KE 23 +#define CP0C6_VTLBONLY 22 +#define CP0C6_LASX 21 +#define CP0C6_SSEN 20 +#define CP0C6_DISDRTIME 19 +#define CP0C6_PIXNUEN 18 +#define CP0C6_SCRAND 17 +#define CP0C6_LLEXCEN 16 +#define CP0C6_DISVC 15 +#define CP0C6_VCLRU 14 +#define CP0C6_DCLRU 13 +#define CP0C6_PIXUEN 12 +#define CP0C6_DISBLKLYEN 11 +#define CP0C6_UMEMUALEN 10 +#define CP0C6_SFBEN 8 +#define CP0C6_FLTINT 7 +#define CP0C6_VLTINT 6 +#define CP0C6_DISBTB 5 +#define CP0C6_STPREFCTL 2 +#define CP0C6_INSTPREF 1 +#define CP0C6_DATAPREF 0 int32_t CP0_Config7; + int64_t CP0_Config7_rw_bitmask; +#define CP0C7_NAPCGEN 2 +#define CP0C7_UNIMUEN 1 +#define CP0C7_VFPUCGEN 0 uint64_t CP0_LLAddr; uint64_t CP0_MAAR[MIPS_MAAR_MAX]; int32_t CP0_MAARI; diff --git a/target/mips/fpu_helper.c b/target/mips/fpu_helper.c index 5287c86c61..7a3a61cab3 100644 --- a/target/mips/fpu_helper.c +++ b/target/mips/fpu_helper.c @@ -189,43 +189,48 @@ void helper_ctc1(CPUMIPSState *env, target_ulong arg1, uint32_t fs, uint32_t rt) } } -int ieee_ex_to_mips(int xcpt) +static inline int ieee_to_mips_xcpt(int ieee_xcpt) { - int ret = 0; - if (xcpt) { - if (xcpt & float_flag_invalid) { - ret |= FP_INVALID; - } - if (xcpt & float_flag_overflow) { - ret |= FP_OVERFLOW; - } - if (xcpt & float_flag_underflow) { - ret |= FP_UNDERFLOW; - } - if (xcpt & float_flag_divbyzero) { - ret |= FP_DIV0; - } - if (xcpt & float_flag_inexact) { - ret |= FP_INEXACT; - } + int mips_xcpt = 0; + + if (ieee_xcpt & float_flag_invalid) { + mips_xcpt |= FP_INVALID; + } + if (ieee_xcpt & float_flag_overflow) { + mips_xcpt |= FP_OVERFLOW; + } + if (ieee_xcpt & float_flag_underflow) { + mips_xcpt |= FP_UNDERFLOW; } - return ret; + if (ieee_xcpt & float_flag_divbyzero) { + mips_xcpt |= FP_DIV0; + } + if (ieee_xcpt & float_flag_inexact) { + mips_xcpt |= FP_INEXACT; + } + + return mips_xcpt; } static inline void update_fcr31(CPUMIPSState *env, uintptr_t pc) { - int tmp = ieee_ex_to_mips(get_float_exception_flags( - &env->active_fpu.fp_status)); + int ieee_exception_flags = get_float_exception_flags( + &env->active_fpu.fp_status); + int mips_exception_flags = 0; - SET_FP_CAUSE(env->active_fpu.fcr31, tmp); + if (ieee_exception_flags) { + mips_exception_flags = ieee_to_mips_xcpt(ieee_exception_flags); + } - if (tmp) { + SET_FP_CAUSE(env->active_fpu.fcr31, mips_exception_flags); + + if (mips_exception_flags) { set_float_exception_flags(0, &env->active_fpu.fp_status); - if (GET_FP_ENABLE(env->active_fpu.fcr31) & tmp) { + if (GET_FP_ENABLE(env->active_fpu.fcr31) & mips_exception_flags) { do_raise_exception(env, EXCP_FPE, pc); } else { - UPDATE_FP_FLAGS(env->active_fpu.fcr31, tmp); + UPDATE_FP_FLAGS(env->active_fpu.fcr31, mips_exception_flags); } } } @@ -1059,14 +1064,14 @@ uint32_t helper_float_recip1_s(CPUMIPSState *env, uint32_t fst0) uint64_t helper_float_recip1_ps(CPUMIPSState *env, uint64_t fdt0) { - uint32_t fst2; + uint32_t fstl2; uint32_t fsth2; - fst2 = float32_div(float32_one, fdt0 & 0XFFFFFFFF, - &env->active_fpu.fp_status); + fstl2 = float32_div(float32_one, fdt0 & 0XFFFFFFFF, + &env->active_fpu.fp_status); fsth2 = float32_div(float32_one, fdt0 >> 32, &env->active_fpu.fp_status); update_fcr31(env, GETPC()); - return ((uint64_t)fsth2 << 32) | fst2; + return ((uint64_t)fsth2 << 32) | fstl2; } uint64_t helper_float_rsqrt1_d(CPUMIPSState *env, uint64_t fdt0) @@ -1091,31 +1096,34 @@ uint32_t helper_float_rsqrt1_s(CPUMIPSState *env, uint32_t fst0) uint64_t helper_float_rsqrt1_ps(CPUMIPSState *env, uint64_t fdt0) { - uint32_t fst2; + uint32_t fstl2; uint32_t fsth2; - fst2 = float32_sqrt(fdt0 & 0XFFFFFFFF, &env->active_fpu.fp_status); + fstl2 = float32_sqrt(fdt0 & 0XFFFFFFFF, &env->active_fpu.fp_status); fsth2 = float32_sqrt(fdt0 >> 32, &env->active_fpu.fp_status); - fst2 = float32_div(float32_one, fst2, &env->active_fpu.fp_status); + fstl2 = float32_div(float32_one, fstl2, &env->active_fpu.fp_status); fsth2 = float32_div(float32_one, fsth2, &env->active_fpu.fp_status); update_fcr31(env, GETPC()); - return ((uint64_t)fsth2 << 32) | fst2; + return ((uint64_t)fsth2 << 32) | fstl2; } -#define FLOAT_RINT(name, bits) \ -uint ## bits ## _t helper_float_ ## name(CPUMIPSState *env, \ - uint ## bits ## _t fs) \ -{ \ - uint ## bits ## _t fdret; \ - \ - fdret = float ## bits ## _round_to_int(fs, &env->active_fpu.fp_status); \ - update_fcr31(env, GETPC()); \ - return fdret; \ +uint64_t helper_float_rint_d(CPUMIPSState *env, uint64_t fs) +{ + uint64_t fdret; + + fdret = float64_round_to_int(fs, &env->active_fpu.fp_status); + update_fcr31(env, GETPC()); + return fdret; } -FLOAT_RINT(rint_s, 32) -FLOAT_RINT(rint_d, 64) -#undef FLOAT_RINT +uint32_t helper_float_rint_s(CPUMIPSState *env, uint32_t fs) +{ + uint32_t fdret; + + fdret = float32_round_to_int(fs, &env->active_fpu.fp_status); + update_fcr31(env, GETPC()); + return fdret; +} #define FLOAT_CLASS_SIGNALING_NAN 0x001 #define FLOAT_CLASS_QUIET_NAN 0x002 @@ -1128,91 +1136,220 @@ FLOAT_RINT(rint_d, 64) #define FLOAT_CLASS_POSITIVE_SUBNORMAL 0x100 #define FLOAT_CLASS_POSITIVE_ZERO 0x200 -#define FLOAT_CLASS(name, bits) \ -uint ## bits ## _t float_ ## name(uint ## bits ## _t arg, \ - float_status *status) \ -{ \ - if (float ## bits ## _is_signaling_nan(arg, status)) { \ - return FLOAT_CLASS_SIGNALING_NAN; \ - } else if (float ## bits ## _is_quiet_nan(arg, status)) { \ - return FLOAT_CLASS_QUIET_NAN; \ - } else if (float ## bits ## _is_neg(arg)) { \ - if (float ## bits ## _is_infinity(arg)) { \ - return FLOAT_CLASS_NEGATIVE_INFINITY; \ - } else if (float ## bits ## _is_zero(arg)) { \ - return FLOAT_CLASS_NEGATIVE_ZERO; \ - } else if (float ## bits ## _is_zero_or_denormal(arg)) { \ - return FLOAT_CLASS_NEGATIVE_SUBNORMAL; \ - } else { \ - return FLOAT_CLASS_NEGATIVE_NORMAL; \ - } \ - } else { \ - if (float ## bits ## _is_infinity(arg)) { \ - return FLOAT_CLASS_POSITIVE_INFINITY; \ - } else if (float ## bits ## _is_zero(arg)) { \ - return FLOAT_CLASS_POSITIVE_ZERO; \ - } else if (float ## bits ## _is_zero_or_denormal(arg)) { \ - return FLOAT_CLASS_POSITIVE_SUBNORMAL; \ - } else { \ - return FLOAT_CLASS_POSITIVE_NORMAL; \ - } \ - } \ -} \ - \ -uint ## bits ## _t helper_float_ ## name(CPUMIPSState *env, \ - uint ## bits ## _t arg) \ -{ \ - return float_ ## name(arg, &env->active_fpu.fp_status); \ -} - -FLOAT_CLASS(class_s, 32) -FLOAT_CLASS(class_d, 64) -#undef FLOAT_CLASS +uint64_t float_class_d(uint64_t arg, float_status *status) +{ + if (float64_is_signaling_nan(arg, status)) { + return FLOAT_CLASS_SIGNALING_NAN; + } else if (float64_is_quiet_nan(arg, status)) { + return FLOAT_CLASS_QUIET_NAN; + } else if (float64_is_neg(arg)) { + if (float64_is_infinity(arg)) { + return FLOAT_CLASS_NEGATIVE_INFINITY; + } else if (float64_is_zero(arg)) { + return FLOAT_CLASS_NEGATIVE_ZERO; + } else if (float64_is_zero_or_denormal(arg)) { + return FLOAT_CLASS_NEGATIVE_SUBNORMAL; + } else { + return FLOAT_CLASS_NEGATIVE_NORMAL; + } + } else { + if (float64_is_infinity(arg)) { + return FLOAT_CLASS_POSITIVE_INFINITY; + } else if (float64_is_zero(arg)) { + return FLOAT_CLASS_POSITIVE_ZERO; + } else if (float64_is_zero_or_denormal(arg)) { + return FLOAT_CLASS_POSITIVE_SUBNORMAL; + } else { + return FLOAT_CLASS_POSITIVE_NORMAL; + } + } +} + +uint64_t helper_float_class_d(CPUMIPSState *env, uint64_t arg) +{ + return float_class_d(arg, &env->active_fpu.fp_status); +} + +uint32_t float_class_s(uint32_t arg, float_status *status) +{ + if (float32_is_signaling_nan(arg, status)) { + return FLOAT_CLASS_SIGNALING_NAN; + } else if (float32_is_quiet_nan(arg, status)) { + return FLOAT_CLASS_QUIET_NAN; + } else if (float32_is_neg(arg)) { + if (float32_is_infinity(arg)) { + return FLOAT_CLASS_NEGATIVE_INFINITY; + } else if (float32_is_zero(arg)) { + return FLOAT_CLASS_NEGATIVE_ZERO; + } else if (float32_is_zero_or_denormal(arg)) { + return FLOAT_CLASS_NEGATIVE_SUBNORMAL; + } else { + return FLOAT_CLASS_NEGATIVE_NORMAL; + } + } else { + if (float32_is_infinity(arg)) { + return FLOAT_CLASS_POSITIVE_INFINITY; + } else if (float32_is_zero(arg)) { + return FLOAT_CLASS_POSITIVE_ZERO; + } else if (float32_is_zero_or_denormal(arg)) { + return FLOAT_CLASS_POSITIVE_SUBNORMAL; + } else { + return FLOAT_CLASS_POSITIVE_NORMAL; + } + } +} + +uint32_t helper_float_class_s(CPUMIPSState *env, uint32_t arg) +{ + return float_class_s(arg, &env->active_fpu.fp_status); +} /* binary operations */ -#define FLOAT_BINOP(name) \ -uint64_t helper_float_ ## name ## _d(CPUMIPSState *env, \ - uint64_t fdt0, uint64_t fdt1) \ -{ \ - uint64_t dt2; \ - \ - dt2 = float64_ ## name(fdt0, fdt1, &env->active_fpu.fp_status);\ - update_fcr31(env, GETPC()); \ - return dt2; \ -} \ - \ -uint32_t helper_float_ ## name ## _s(CPUMIPSState *env, \ - uint32_t fst0, uint32_t fst1) \ -{ \ - uint32_t wt2; \ - \ - wt2 = float32_ ## name(fst0, fst1, &env->active_fpu.fp_status);\ - update_fcr31(env, GETPC()); \ - return wt2; \ -} \ - \ -uint64_t helper_float_ ## name ## _ps(CPUMIPSState *env, \ - uint64_t fdt0, \ - uint64_t fdt1) \ -{ \ - uint32_t fst0 = fdt0 & 0XFFFFFFFF; \ - uint32_t fsth0 = fdt0 >> 32; \ - uint32_t fst1 = fdt1 & 0XFFFFFFFF; \ - uint32_t fsth1 = fdt1 >> 32; \ - uint32_t wt2; \ - uint32_t wth2; \ - \ - wt2 = float32_ ## name(fst0, fst1, &env->active_fpu.fp_status); \ - wth2 = float32_ ## name(fsth0, fsth1, &env->active_fpu.fp_status); \ - update_fcr31(env, GETPC()); \ - return ((uint64_t)wth2 << 32) | wt2; \ -} - -FLOAT_BINOP(add) -FLOAT_BINOP(sub) -FLOAT_BINOP(mul) -FLOAT_BINOP(div) -#undef FLOAT_BINOP + +uint64_t helper_float_add_d(CPUMIPSState *env, + uint64_t fdt0, uint64_t fdt1) +{ + uint64_t dt2; + + dt2 = float64_add(fdt0, fdt1, &env->active_fpu.fp_status); + update_fcr31(env, GETPC()); + return dt2; +} + +uint32_t helper_float_add_s(CPUMIPSState *env, + uint32_t fst0, uint32_t fst1) +{ + uint32_t wt2; + + wt2 = float32_sub(fst0, fst1, &env->active_fpu.fp_status); + update_fcr31(env, GETPC()); + return wt2; +} + +uint64_t helper_float_add_ps(CPUMIPSState *env, + uint64_t fdt0, uint64_t fdt1) +{ + uint32_t fstl0 = fdt0 & 0XFFFFFFFF; + uint32_t fsth0 = fdt0 >> 32; + uint32_t fstl1 = fdt1 & 0XFFFFFFFF; + uint32_t fsth1 = fdt1 >> 32; + uint32_t wtl2; + uint32_t wth2; + + wtl2 = float32_add(fstl0, fstl1, &env->active_fpu.fp_status); + wth2 = float32_add(fsth0, fsth1, &env->active_fpu.fp_status); + update_fcr31(env, GETPC()); + return ((uint64_t)wth2 << 32) | wtl2; +} + +uint64_t helper_float_sub_d(CPUMIPSState *env, + uint64_t fdt0, uint64_t fdt1) +{ + uint64_t dt2; + + dt2 = float64_sub(fdt0, fdt1, &env->active_fpu.fp_status); + update_fcr31(env, GETPC()); + return dt2; +} + +uint32_t helper_float_sub_s(CPUMIPSState *env, + uint32_t fst0, uint32_t fst1) +{ + uint32_t wt2; + + wt2 = float32_sub(fst0, fst1, &env->active_fpu.fp_status); + update_fcr31(env, GETPC()); + return wt2; +} + +uint64_t helper_float_sub_ps(CPUMIPSState *env, + uint64_t fdt0, uint64_t fdt1) +{ + uint32_t fstl0 = fdt0 & 0XFFFFFFFF; + uint32_t fsth0 = fdt0 >> 32; + uint32_t fstl1 = fdt1 & 0XFFFFFFFF; + uint32_t fsth1 = fdt1 >> 32; + uint32_t wtl2; + uint32_t wth2; + + wtl2 = float32_sub(fstl0, fstl1, &env->active_fpu.fp_status); + wth2 = float32_sub(fsth0, fsth1, &env->active_fpu.fp_status); + update_fcr31(env, GETPC()); + return ((uint64_t)wth2 << 32) | wtl2; +} + +uint64_t helper_float_mul_d(CPUMIPSState *env, + uint64_t fdt0, uint64_t fdt1) +{ + uint64_t dt2; + + dt2 = float64_mul(fdt0, fdt1, &env->active_fpu.fp_status); + update_fcr31(env, GETPC()); + return dt2; +} + +uint32_t helper_float_mul_s(CPUMIPSState *env, + uint32_t fst0, uint32_t fst1) +{ + uint32_t wt2; + + wt2 = float32_mul(fst0, fst1, &env->active_fpu.fp_status); + update_fcr31(env, GETPC()); + return wt2; +} + +uint64_t helper_float_mul_ps(CPUMIPSState *env, + uint64_t fdt0, uint64_t fdt1) +{ + uint32_t fstl0 = fdt0 & 0XFFFFFFFF; + uint32_t fsth0 = fdt0 >> 32; + uint32_t fstl1 = fdt1 & 0XFFFFFFFF; + uint32_t fsth1 = fdt1 >> 32; + uint32_t wtl2; + uint32_t wth2; + + wtl2 = float32_mul(fstl0, fstl1, &env->active_fpu.fp_status); + wth2 = float32_mul(fsth0, fsth1, &env->active_fpu.fp_status); + update_fcr31(env, GETPC()); + return ((uint64_t)wth2 << 32) | wtl2; +} + +uint64_t helper_float_div_d(CPUMIPSState *env, + uint64_t fdt0, uint64_t fdt1) +{ + uint64_t dt2; + + dt2 = float64_div(fdt0, fdt1, &env->active_fpu.fp_status); + update_fcr31(env, GETPC()); + return dt2; +} + +uint32_t helper_float_div_s(CPUMIPSState *env, + uint32_t fst0, uint32_t fst1) +{ + uint32_t wt2; + + wt2 = float32_div(fst0, fst1, &env->active_fpu.fp_status); + update_fcr31(env, GETPC()); + return wt2; +} + +uint64_t helper_float_div_ps(CPUMIPSState *env, + uint64_t fdt0, uint64_t fdt1) +{ + uint32_t fstl0 = fdt0 & 0XFFFFFFFF; + uint32_t fsth0 = fdt0 >> 32; + uint32_t fstl1 = fdt1 & 0XFFFFFFFF; + uint32_t fsth1 = fdt1 >> 32; + uint32_t wtl2; + uint32_t wth2; + + wtl2 = float32_div(fstl0, fstl1, &env->active_fpu.fp_status); + wth2 = float32_div(fsth0, fsth1, &env->active_fpu.fp_status); + update_fcr31(env, GETPC()); + return ((uint64_t)wth2 << 32) | wtl2; +} + /* MIPS specific binary operations */ uint64_t helper_float_recip2_d(CPUMIPSState *env, uint64_t fdt0, uint64_t fdt2) @@ -1235,19 +1372,19 @@ uint32_t helper_float_recip2_s(CPUMIPSState *env, uint32_t fst0, uint32_t fst2) uint64_t helper_float_recip2_ps(CPUMIPSState *env, uint64_t fdt0, uint64_t fdt2) { - uint32_t fst0 = fdt0 & 0XFFFFFFFF; + uint32_t fstl0 = fdt0 & 0XFFFFFFFF; uint32_t fsth0 = fdt0 >> 32; - uint32_t fst2 = fdt2 & 0XFFFFFFFF; + uint32_t fstl2 = fdt2 & 0XFFFFFFFF; uint32_t fsth2 = fdt2 >> 32; - fst2 = float32_mul(fst0, fst2, &env->active_fpu.fp_status); + fstl2 = float32_mul(fstl0, fstl2, &env->active_fpu.fp_status); fsth2 = float32_mul(fsth0, fsth2, &env->active_fpu.fp_status); - fst2 = float32_chs(float32_sub(fst2, float32_one, + fstl2 = float32_chs(float32_sub(fstl2, float32_one, &env->active_fpu.fp_status)); fsth2 = float32_chs(float32_sub(fsth2, float32_one, &env->active_fpu.fp_status)); update_fcr31(env, GETPC()); - return ((uint64_t)fsth2 << 32) | fst2; + return ((uint64_t)fsth2 << 32) | fstl2; } uint64_t helper_float_rsqrt2_d(CPUMIPSState *env, uint64_t fdt0, uint64_t fdt2) @@ -1272,51 +1409,51 @@ uint32_t helper_float_rsqrt2_s(CPUMIPSState *env, uint32_t fst0, uint32_t fst2) uint64_t helper_float_rsqrt2_ps(CPUMIPSState *env, uint64_t fdt0, uint64_t fdt2) { - uint32_t fst0 = fdt0 & 0XFFFFFFFF; + uint32_t fstl0 = fdt0 & 0XFFFFFFFF; uint32_t fsth0 = fdt0 >> 32; - uint32_t fst2 = fdt2 & 0XFFFFFFFF; + uint32_t fstl2 = fdt2 & 0XFFFFFFFF; uint32_t fsth2 = fdt2 >> 32; - fst2 = float32_mul(fst0, fst2, &env->active_fpu.fp_status); + fstl2 = float32_mul(fstl0, fstl2, &env->active_fpu.fp_status); fsth2 = float32_mul(fsth0, fsth2, &env->active_fpu.fp_status); - fst2 = float32_sub(fst2, float32_one, &env->active_fpu.fp_status); + fstl2 = float32_sub(fstl2, float32_one, &env->active_fpu.fp_status); fsth2 = float32_sub(fsth2, float32_one, &env->active_fpu.fp_status); - fst2 = float32_chs(float32_div(fst2, FLOAT_TWO32, + fstl2 = float32_chs(float32_div(fstl2, FLOAT_TWO32, &env->active_fpu.fp_status)); fsth2 = float32_chs(float32_div(fsth2, FLOAT_TWO32, &env->active_fpu.fp_status)); update_fcr31(env, GETPC()); - return ((uint64_t)fsth2 << 32) | fst2; + return ((uint64_t)fsth2 << 32) | fstl2; } uint64_t helper_float_addr_ps(CPUMIPSState *env, uint64_t fdt0, uint64_t fdt1) { - uint32_t fst0 = fdt0 & 0XFFFFFFFF; + uint32_t fstl0 = fdt0 & 0XFFFFFFFF; uint32_t fsth0 = fdt0 >> 32; - uint32_t fst1 = fdt1 & 0XFFFFFFFF; + uint32_t fstl1 = fdt1 & 0XFFFFFFFF; uint32_t fsth1 = fdt1 >> 32; - uint32_t fst2; + uint32_t fstl2; uint32_t fsth2; - fst2 = float32_add(fst0, fsth0, &env->active_fpu.fp_status); - fsth2 = float32_add(fst1, fsth1, &env->active_fpu.fp_status); + fstl2 = float32_add(fstl0, fsth0, &env->active_fpu.fp_status); + fsth2 = float32_add(fstl1, fsth1, &env->active_fpu.fp_status); update_fcr31(env, GETPC()); - return ((uint64_t)fsth2 << 32) | fst2; + return ((uint64_t)fsth2 << 32) | fstl2; } uint64_t helper_float_mulr_ps(CPUMIPSState *env, uint64_t fdt0, uint64_t fdt1) { - uint32_t fst0 = fdt0 & 0XFFFFFFFF; + uint32_t fstl0 = fdt0 & 0XFFFFFFFF; uint32_t fsth0 = fdt0 >> 32; - uint32_t fst1 = fdt1 & 0XFFFFFFFF; + uint32_t fstl1 = fdt1 & 0XFFFFFFFF; uint32_t fsth1 = fdt1 >> 32; - uint32_t fst2; + uint32_t fstl2; uint32_t fsth2; - fst2 = float32_mul(fst0, fsth0, &env->active_fpu.fp_status); - fsth2 = float32_mul(fst1, fsth1, &env->active_fpu.fp_status); + fstl2 = float32_mul(fstl0, fsth0, &env->active_fpu.fp_status); + fsth2 = float32_mul(fstl1, fsth1, &env->active_fpu.fp_status); update_fcr31(env, GETPC()); - return ((uint64_t)fsth2 << 32) | fst2; + return ((uint64_t)fsth2 << 32) | fstl2; } #define FLOAT_MINMAX(name, bits, minmaxfunc) \ @@ -1344,60 +1481,171 @@ FLOAT_MINMAX(mina_d, 64, minnummag) #undef FLOAT_MINMAX /* ternary operations */ -#define UNFUSED_FMA(prefix, a, b, c, flags) \ -{ \ - a = prefix##_mul(a, b, &env->active_fpu.fp_status); \ - if ((flags) & float_muladd_negate_c) { \ - a = prefix##_sub(a, c, &env->active_fpu.fp_status); \ - } else { \ - a = prefix##_add(a, c, &env->active_fpu.fp_status); \ - } \ - if ((flags) & float_muladd_negate_result) { \ - a = prefix##_chs(a); \ - } \ -} - -/* FMA based operations */ -#define FLOAT_FMA(name, type) \ -uint64_t helper_float_ ## name ## _d(CPUMIPSState *env, \ - uint64_t fdt0, uint64_t fdt1, \ - uint64_t fdt2) \ -{ \ - UNFUSED_FMA(float64, fdt0, fdt1, fdt2, type); \ - update_fcr31(env, GETPC()); \ - return fdt0; \ -} \ - \ -uint32_t helper_float_ ## name ## _s(CPUMIPSState *env, \ - uint32_t fst0, uint32_t fst1, \ - uint32_t fst2) \ -{ \ - UNFUSED_FMA(float32, fst0, fst1, fst2, type); \ - update_fcr31(env, GETPC()); \ - return fst0; \ -} \ - \ -uint64_t helper_float_ ## name ## _ps(CPUMIPSState *env, \ - uint64_t fdt0, uint64_t fdt1, \ - uint64_t fdt2) \ -{ \ - uint32_t fst0 = fdt0 & 0XFFFFFFFF; \ - uint32_t fsth0 = fdt0 >> 32; \ - uint32_t fst1 = fdt1 & 0XFFFFFFFF; \ - uint32_t fsth1 = fdt1 >> 32; \ - uint32_t fst2 = fdt2 & 0XFFFFFFFF; \ - uint32_t fsth2 = fdt2 >> 32; \ - \ - UNFUSED_FMA(float32, fst0, fst1, fst2, type); \ - UNFUSED_FMA(float32, fsth0, fsth1, fsth2, type); \ - update_fcr31(env, GETPC()); \ - return ((uint64_t)fsth0 << 32) | fst0; \ -} -FLOAT_FMA(madd, 0) -FLOAT_FMA(msub, float_muladd_negate_c) -FLOAT_FMA(nmadd, float_muladd_negate_result) -FLOAT_FMA(nmsub, float_muladd_negate_result | float_muladd_negate_c) -#undef FLOAT_FMA + +uint64_t helper_float_madd_d(CPUMIPSState *env, uint64_t fst0, + uint64_t fst1, uint64_t fst2) +{ + fst0 = float64_mul(fst0, fst1, &env->active_fpu.fp_status); + fst0 = float64_add(fst0, fst2, &env->active_fpu.fp_status); + + update_fcr31(env, GETPC()); + return fst0; +} + +uint32_t helper_float_madd_s(CPUMIPSState *env, uint32_t fst0, + uint32_t fst1, uint32_t fst2) +{ + fst0 = float32_mul(fst0, fst1, &env->active_fpu.fp_status); + fst0 = float32_add(fst0, fst2, &env->active_fpu.fp_status); + + update_fcr31(env, GETPC()); + return fst0; +} + +uint64_t helper_float_madd_ps(CPUMIPSState *env, uint64_t fdt0, + uint64_t fdt1, uint64_t fdt2) +{ + uint32_t fstl0 = fdt0 & 0XFFFFFFFF; + uint32_t fsth0 = fdt0 >> 32; + uint32_t fstl1 = fdt1 & 0XFFFFFFFF; + uint32_t fsth1 = fdt1 >> 32; + uint32_t fstl2 = fdt2 & 0XFFFFFFFF; + uint32_t fsth2 = fdt2 >> 32; + + fstl0 = float32_mul(fstl0, fstl1, &env->active_fpu.fp_status); + fstl0 = float32_add(fstl0, fstl2, &env->active_fpu.fp_status); + fsth0 = float32_mul(fsth0, fsth1, &env->active_fpu.fp_status); + fsth0 = float32_add(fsth0, fsth2, &env->active_fpu.fp_status); + + update_fcr31(env, GETPC()); + return ((uint64_t)fsth0 << 32) | fstl0; +} + +uint64_t helper_float_msub_d(CPUMIPSState *env, uint64_t fst0, + uint64_t fst1, uint64_t fst2) +{ + fst0 = float64_mul(fst0, fst1, &env->active_fpu.fp_status); + fst0 = float64_sub(fst0, fst2, &env->active_fpu.fp_status); + + update_fcr31(env, GETPC()); + return fst0; +} + +uint32_t helper_float_msub_s(CPUMIPSState *env, uint32_t fst0, + uint32_t fst1, uint32_t fst2) +{ + fst0 = float32_mul(fst0, fst1, &env->active_fpu.fp_status); + fst0 = float32_sub(fst0, fst2, &env->active_fpu.fp_status); + + update_fcr31(env, GETPC()); + return fst0; +} + +uint64_t helper_float_msub_ps(CPUMIPSState *env, uint64_t fdt0, + uint64_t fdt1, uint64_t fdt2) +{ + uint32_t fstl0 = fdt0 & 0XFFFFFFFF; + uint32_t fsth0 = fdt0 >> 32; + uint32_t fstl1 = fdt1 & 0XFFFFFFFF; + uint32_t fsth1 = fdt1 >> 32; + uint32_t fstl2 = fdt2 & 0XFFFFFFFF; + uint32_t fsth2 = fdt2 >> 32; + + fstl0 = float32_mul(fstl0, fstl1, &env->active_fpu.fp_status); + fstl0 = float32_sub(fstl0, fstl2, &env->active_fpu.fp_status); + fsth0 = float32_mul(fsth0, fsth1, &env->active_fpu.fp_status); + fsth0 = float32_sub(fsth0, fsth2, &env->active_fpu.fp_status); + + update_fcr31(env, GETPC()); + return ((uint64_t)fsth0 << 32) | fstl0; +} + +uint64_t helper_float_nmadd_d(CPUMIPSState *env, uint64_t fst0, + uint64_t fst1, uint64_t fst2) +{ + fst0 = float64_mul(fst0, fst1, &env->active_fpu.fp_status); + fst0 = float64_add(fst0, fst2, &env->active_fpu.fp_status); + fst0 = float64_chs(fst0); + + update_fcr31(env, GETPC()); + return fst0; +} + +uint32_t helper_float_nmadd_s(CPUMIPSState *env, uint32_t fst0, + uint32_t fst1, uint32_t fst2) +{ + fst0 = float32_mul(fst0, fst1, &env->active_fpu.fp_status); + fst0 = float32_add(fst0, fst2, &env->active_fpu.fp_status); + fst0 = float32_chs(fst0); + + update_fcr31(env, GETPC()); + return fst0; +} + +uint64_t helper_float_nmadd_ps(CPUMIPSState *env, uint64_t fdt0, + uint64_t fdt1, uint64_t fdt2) +{ + uint32_t fstl0 = fdt0 & 0XFFFFFFFF; + uint32_t fsth0 = fdt0 >> 32; + uint32_t fstl1 = fdt1 & 0XFFFFFFFF; + uint32_t fsth1 = fdt1 >> 32; + uint32_t fstl2 = fdt2 & 0XFFFFFFFF; + uint32_t fsth2 = fdt2 >> 32; + + fstl0 = float32_mul(fstl0, fstl1, &env->active_fpu.fp_status); + fstl0 = float32_add(fstl0, fstl2, &env->active_fpu.fp_status); + fstl0 = float32_chs(fstl0); + fsth0 = float32_mul(fsth0, fsth1, &env->active_fpu.fp_status); + fsth0 = float32_add(fsth0, fsth2, &env->active_fpu.fp_status); + fsth0 = float32_chs(fsth0); + + update_fcr31(env, GETPC()); + return ((uint64_t)fsth0 << 32) | fstl0; +} + +uint64_t helper_float_nmsub_d(CPUMIPSState *env, uint64_t fst0, + uint64_t fst1, uint64_t fst2) +{ + fst0 = float64_mul(fst0, fst1, &env->active_fpu.fp_status); + fst0 = float64_sub(fst0, fst2, &env->active_fpu.fp_status); + fst0 = float64_chs(fst0); + + update_fcr31(env, GETPC()); + return fst0; +} + +uint32_t helper_float_nmsub_s(CPUMIPSState *env, uint32_t fst0, + uint32_t fst1, uint32_t fst2) +{ + fst0 = float32_mul(fst0, fst1, &env->active_fpu.fp_status); + fst0 = float32_sub(fst0, fst2, &env->active_fpu.fp_status); + fst0 = float32_chs(fst0); + + update_fcr31(env, GETPC()); + return fst0; +} + +uint64_t helper_float_nmsub_ps(CPUMIPSState *env, uint64_t fdt0, + uint64_t fdt1, uint64_t fdt2) +{ + uint32_t fstl0 = fdt0 & 0XFFFFFFFF; + uint32_t fsth0 = fdt0 >> 32; + uint32_t fstl1 = fdt1 & 0XFFFFFFFF; + uint32_t fsth1 = fdt1 >> 32; + uint32_t fstl2 = fdt2 & 0XFFFFFFFF; + uint32_t fsth2 = fdt2 >> 32; + + fstl0 = float32_mul(fstl0, fstl1, &env->active_fpu.fp_status); + fstl0 = float32_sub(fstl0, fstl2, &env->active_fpu.fp_status); + fstl0 = float32_chs(fstl0); + fsth0 = float32_mul(fsth0, fsth1, &env->active_fpu.fp_status); + fsth0 = float32_sub(fsth0, fsth2, &env->active_fpu.fp_status); + fsth0 = float32_chs(fsth0); + + update_fcr31(env, GETPC()); + return ((uint64_t)fsth0 << 32) | fstl0; +} + #define FLOAT_FMADDSUB(name, bits, muladd_arg) \ uint ## bits ## _t helper_float_ ## name(CPUMIPSState *env, \ diff --git a/target/mips/internal.h b/target/mips/internal.h index 1bf274b3ef..7f159a9230 100644 --- a/target/mips/internal.h +++ b/target/mips/internal.h @@ -36,7 +36,9 @@ struct mips_def_t { int32_t CP0_Config5; int32_t CP0_Config5_rw_bitmask; int32_t CP0_Config6; + int32_t CP0_Config6_rw_bitmask; int32_t CP0_Config7; + int32_t CP0_Config7_rw_bitmask; target_ulong CP0_LLAddr_rw_bitmask; int CP0_LLAddr_shift; int32_t SYNCI_Step; @@ -224,7 +226,6 @@ uint32_t float_class_s(uint32_t arg, float_status *fst); uint64_t float_class_d(uint64_t arg, float_status *fst); extern unsigned int ieee_rm[]; -int ieee_ex_to_mips(int xcpt); void update_pagemask(CPUMIPSState *env, target_ulong arg1, int32_t *pagemask); static inline void restore_rounding_mode(CPUMIPSState *env) diff --git a/target/mips/lmi_helper.c b/target/mips/lmmi_helper.c index 6c645cf679..6c645cf679 100644 --- a/target/mips/lmi_helper.c +++ b/target/mips/lmmi_helper.c diff --git a/target/mips/mips-defs.h b/target/mips/mips-defs.h index a831bb4384..0c129106c8 100644 --- a/target/mips/mips-defs.h +++ b/target/mips/mips-defs.h @@ -15,7 +15,7 @@ * ------------------------------------------------ */ /* - * bits 0-31: MIPS base instruction sets + * bits 0-23: MIPS base instruction sets */ #define ISA_MIPS1 0x0000000000000001ULL #define ISA_MIPS2 0x0000000000000002ULL @@ -34,30 +34,33 @@ #define ISA_MIPS64R6 0x0000000000004000ULL #define ISA_NANOMIPS32 0x0000000000008000ULL /* - * bits 32-47: MIPS ASEs + * bits 24-39: MIPS ASEs */ -#define ASE_MIPS16 0x0000000100000000ULL -#define ASE_MIPS3D 0x0000000200000000ULL -#define ASE_MDMX 0x0000000400000000ULL -#define ASE_DSP 0x0000000800000000ULL -#define ASE_DSP_R2 0x0000001000000000ULL -#define ASE_DSP_R3 0x0000002000000000ULL -#define ASE_MT 0x0000004000000000ULL -#define ASE_SMARTMIPS 0x0000008000000000ULL -#define ASE_MICROMIPS 0x0000010000000000ULL -#define ASE_MSA 0x0000020000000000ULL +#define ASE_MIPS16 0x0000000001000000ULL +#define ASE_MIPS3D 0x0000000002000000ULL +#define ASE_MDMX 0x0000000004000000ULL +#define ASE_DSP 0x0000000008000000ULL +#define ASE_DSP_R2 0x0000000010000000ULL +#define ASE_DSP_R3 0x0000000020000000ULL +#define ASE_MT 0x0000000040000000ULL +#define ASE_SMARTMIPS 0x0000000080000000ULL +#define ASE_MICROMIPS 0x0000000100000000ULL +#define ASE_MSA 0x0000000200000000ULL /* - * bits 48-55: vendor-specific base instruction sets + * bits 40-51: vendor-specific base instruction sets */ -#define INSN_LOONGSON2E 0x0001000000000000ULL -#define INSN_LOONGSON2F 0x0002000000000000ULL -#define INSN_VR54XX 0x0004000000000000ULL -#define INSN_R5900 0x0008000000000000ULL +#define INSN_VR54XX 0x0000010000000000ULL +#define INSN_R5900 0x0000020000000000ULL +#define INSN_LOONGSON2E 0x0000040000000000ULL +#define INSN_LOONGSON2F 0x0000080000000000ULL +#define INSN_LOONGSON3A 0x0000100000000000ULL /* - * bits 56-63: vendor-specific ASEs + * bits 52-63: vendor-specific ASEs */ -#define ASE_MMI 0x0100000000000000ULL -#define ASE_MXU 0x0200000000000000ULL +#define ASE_MMI 0x0010000000000000ULL +#define ASE_MXU 0x0020000000000000ULL +#define ASE_LMMI 0x0040000000000000ULL +#define ASE_LEXT 0x0080000000000000ULL /* MIPS CPU defines. */ #define CPU_MIPS1 (ISA_MIPS1) @@ -94,6 +97,8 @@ /* Wave Computing: "nanoMIPS" */ #define CPU_NANOMIPS32 (CPU_MIPS32R6 | ISA_NANOMIPS32) +#define CPU_LOONGSON3A (CPU_MIPS64R2 | INSN_LOONGSON3A) + /* * Strictly follow the architecture standard: * - Disallow "special" instruction handling for PMON/SPIM. diff --git a/target/mips/msa_helper.c b/target/mips/msa_helper.c index 3c7012c0b8..c3b271934a 100644 --- a/target/mips/msa_helper.c +++ b/target/mips/msa_helper.c @@ -5419,54 +5419,81 @@ static inline void check_msacsr_cause(CPUMIPSState *env, uintptr_t retaddr) #define CLEAR_IS_INEXACT 2 #define RECIPROCAL_INEXACT 4 -static inline int update_msacsr(CPUMIPSState *env, int action, int denormal) + +static inline int ieee_to_mips_xcpt_msa(int ieee_xcpt) { - int ieee_ex; + int mips_xcpt = 0; - int c; + if (ieee_xcpt & float_flag_invalid) { + mips_xcpt |= FP_INVALID; + } + if (ieee_xcpt & float_flag_overflow) { + mips_xcpt |= FP_OVERFLOW; + } + if (ieee_xcpt & float_flag_underflow) { + mips_xcpt |= FP_UNDERFLOW; + } + if (ieee_xcpt & float_flag_divbyzero) { + mips_xcpt |= FP_DIV0; + } + if (ieee_xcpt & float_flag_inexact) { + mips_xcpt |= FP_INEXACT; + } + + return mips_xcpt; +} + +static inline int update_msacsr(CPUMIPSState *env, int action, int denormal) +{ + int ieee_exception_flags; + int mips_exception_flags = 0; int cause; int enable; - ieee_ex = get_float_exception_flags(&env->active_tc.msa_fp_status); + ieee_exception_flags = get_float_exception_flags( + &env->active_tc.msa_fp_status); /* QEMU softfloat does not signal all underflow cases */ if (denormal) { - ieee_ex |= float_flag_underflow; + ieee_exception_flags |= float_flag_underflow; + } + if (ieee_exception_flags) { + mips_exception_flags = ieee_to_mips_xcpt_msa(ieee_exception_flags); } - - c = ieee_ex_to_mips(ieee_ex); enable = GET_FP_ENABLE(env->active_tc.msacsr) | FP_UNIMPLEMENTED; /* Set Inexact (I) when flushing inputs to zero */ - if ((ieee_ex & float_flag_input_denormal) && + if ((ieee_exception_flags & float_flag_input_denormal) && (env->active_tc.msacsr & MSACSR_FS_MASK) != 0) { if (action & CLEAR_IS_INEXACT) { - c &= ~FP_INEXACT; + mips_exception_flags &= ~FP_INEXACT; } else { - c |= FP_INEXACT; + mips_exception_flags |= FP_INEXACT; } } /* Set Inexact (I) and Underflow (U) when flushing outputs to zero */ - if ((ieee_ex & float_flag_output_denormal) && + if ((ieee_exception_flags & float_flag_output_denormal) && (env->active_tc.msacsr & MSACSR_FS_MASK) != 0) { - c |= FP_INEXACT; + mips_exception_flags |= FP_INEXACT; if (action & CLEAR_FS_UNDERFLOW) { - c &= ~FP_UNDERFLOW; + mips_exception_flags &= ~FP_UNDERFLOW; } else { - c |= FP_UNDERFLOW; + mips_exception_flags |= FP_UNDERFLOW; } } /* Set Inexact (I) when Overflow (O) is not enabled */ - if ((c & FP_OVERFLOW) != 0 && (enable & FP_OVERFLOW) == 0) { - c |= FP_INEXACT; + if ((mips_exception_flags & FP_OVERFLOW) != 0 && + (enable & FP_OVERFLOW) == 0) { + mips_exception_flags |= FP_INEXACT; } /* Clear Exact Underflow when Underflow (U) is not enabled */ - if ((c & FP_UNDERFLOW) != 0 && (enable & FP_UNDERFLOW) == 0 && - (c & FP_INEXACT) == 0) { - c &= ~FP_UNDERFLOW; + if ((mips_exception_flags & FP_UNDERFLOW) != 0 && + (enable & FP_UNDERFLOW) == 0 && + (mips_exception_flags & FP_INEXACT) == 0) { + mips_exception_flags &= ~FP_UNDERFLOW; } /* @@ -5474,11 +5501,11 @@ static inline int update_msacsr(CPUMIPSState *env, int action, int denormal) * divide by zero */ if ((action & RECIPROCAL_INEXACT) && - (c & (FP_INVALID | FP_DIV0)) == 0) { - c = FP_INEXACT; + (mips_exception_flags & (FP_INVALID | FP_DIV0)) == 0) { + mips_exception_flags = FP_INEXACT; } - cause = c & enable; /* all current enabled exceptions */ + cause = mips_exception_flags & enable; /* all current enabled exceptions */ if (cause == 0) { /* @@ -5486,7 +5513,7 @@ static inline int update_msacsr(CPUMIPSState *env, int action, int denormal) * with all current exceptions */ SET_FP_CAUSE(env->active_tc.msacsr, - (GET_FP_CAUSE(env->active_tc.msacsr) | c)); + (GET_FP_CAUSE(env->active_tc.msacsr) | mips_exception_flags)); } else { /* Current exceptions are enabled */ if ((env->active_tc.msacsr & MSACSR_NX_MASK) == 0) { @@ -5495,11 +5522,11 @@ static inline int update_msacsr(CPUMIPSState *env, int action, int denormal) * with all enabled exceptions */ SET_FP_CAUSE(env->active_tc.msacsr, - (GET_FP_CAUSE(env->active_tc.msacsr) | c)); + (GET_FP_CAUSE(env->active_tc.msacsr) | mips_exception_flags)); } } - return c; + return mips_exception_flags; } static inline int get_enabled_exceptions(const CPUMIPSState *env, int c) diff --git a/target/mips/translate.c b/target/mips/translate.c index 25b595a17d..2caf4cba5a 100644 --- a/target/mips/translate.c +++ b/target/mips/translate.c @@ -31206,7 +31206,9 @@ void cpu_state_reset(CPUMIPSState *env) env->CP0_Config5 = env->cpu_model->CP0_Config5; env->CP0_Config5_rw_bitmask = env->cpu_model->CP0_Config5_rw_bitmask; env->CP0_Config6 = env->cpu_model->CP0_Config6; + env->CP0_Config6_rw_bitmask = env->cpu_model->CP0_Config6_rw_bitmask; env->CP0_Config7 = env->cpu_model->CP0_Config7; + env->CP0_Config7_rw_bitmask = env->cpu_model->CP0_Config7_rw_bitmask; env->CP0_LLAddr_rw_bitmask = env->cpu_model->CP0_LLAddr_rw_bitmask << env->cpu_model->CP0_LLAddr_shift; env->CP0_LLAddr_shift = env->cpu_model->CP0_LLAddr_shift; diff --git a/target/mips/translate_init.inc.c b/target/mips/translate_init.inc.c index 6d145a905a..637caccd89 100644 --- a/target/mips/translate_init.inc.c +++ b/target/mips/translate_init.inc.c @@ -366,7 +366,7 @@ const mips_def_t mips_defs[] = }, { /* FIXME: - * Config3: CMGCR, PW, VZ, CTXTC, CDMM, TL + * Config3: VZ, CTXTC, CDMM, TL * Config4: MMUExtDef * Config5: MRP * FIR(FCR0): Has2008 @@ -380,10 +380,11 @@ const mips_def_t mips_defs[] = (2 << CP0C1_DS) | (4 << CP0C1_DL) | (3 << CP0C1_DA) | (1 << CP0C1_PC) | (1 << CP0C1_FP), .CP0_Config2 = MIPS_CONFIG2, - .CP0_Config3 = MIPS_CONFIG3 | (1U << CP0C3_M) | (1 << CP0C3_MSAP) | + .CP0_Config3 = MIPS_CONFIG3 | (1U << CP0C3_M) | + (1 << CP0C3_CMGCR) | (1 << CP0C3_MSAP) | (1 << CP0C3_BP) | (1 << CP0C3_BI) | (1 << CP0C3_SC) | - (1 << CP0C3_ULRI) | (1 << CP0C3_RXI) | (1 << CP0C3_LPA) | - (1 << CP0C3_VInt), + (1 << CP0C3_PW) | (1 << CP0C3_ULRI) | (1 << CP0C3_RXI) | + (1 << CP0C3_LPA) | (1 << CP0C3_VInt), .CP0_Config4 = MIPS_CONFIG4 | (1U << CP0C4_M) | (2 << CP0C4_IE) | (0x1c << CP0C4_KScrExist), .CP0_Config4_rw_bitmask = 0, @@ -802,6 +803,92 @@ const mips_def_t mips_defs[] = .mmu_type = MMU_TYPE_R4000, }, { + .name = "Loongson-3A1000", + .CP0_PRid = 0x6305, + /* 64KB I-cache and d-cache. 4 way with 32 bit cache line size. */ + .CP0_Config0 = MIPS_CONFIG0 | (0x1 << CP0C0_AR) | (0x2 << CP0C0_AT) | + (MMU_TYPE_R4000 << CP0C0_MT), + .CP0_Config1 = MIPS_CONFIG1 | (1 << CP0C1_FP) | (63 << CP0C1_MMU) | + (3 << CP0C1_IS) | (4 << CP0C1_IL) | (3 << CP0C1_IA) | + (3 << CP0C1_DS) | (4 << CP0C1_DL) | (3 << CP0C1_DA) | + (1 << CP0C1_PC) | (1 << CP0C1_WR) | (1 << CP0C1_EP), + .CP0_Config2 = MIPS_CONFIG2 | (7 << CP0C2_SS) | (4 << CP0C2_SL) | + (3 << CP0C2_SA), + .CP0_Config3 = MIPS_CONFIG3 | (1 << CP0C3_LPA), + .CP0_LLAddr_rw_bitmask = 0, + .SYNCI_Step = 32, + .CCRes = 2, + .CP0_Status_rw_bitmask = 0x74D8FFFF, + .CP0_PageGrain = (1 << CP0PG_ELPA), + .CP0_PageGrain_rw_bitmask = (1 << CP0PG_ELPA), + .CP1_fcr0 = (0x5 << FCR0_PRID) | (0x1 << FCR0_REV) | (0x1 << FCR0_F64) | + (0x1 << FCR0_PS) | (0x1 << FCR0_L) | (0x1 << FCR0_W) | + (0x1 << FCR0_D) | (0x1 << FCR0_S), + .CP1_fcr31 = 0, + .CP1_fcr31_rw_bitmask = 0xFF83FFFF, + .SEGBITS = 42, + .PABITS = 48, + .insn_flags = CPU_LOONGSON3A, + .mmu_type = MMU_TYPE_R4000, + }, + { + .name = "Loongson-3A4000", + .CP0_PRid = 0x14C000, + /* 64KB I-cache and d-cache. 4 way with 32 bit cache line size. */ + .CP0_Config0 = MIPS_CONFIG0 | (0x1 << CP0C0_AR) | (0x2 << CP0C0_AT) | + (MMU_TYPE_R4000 << CP0C0_MT), + .CP0_Config1 = MIPS_CONFIG1 | (1 << CP0C1_FP) | (63 << CP0C1_MMU) | + (2 << CP0C1_IS) | (5 << CP0C1_IL) | (3 << CP0C1_IA) | + (2 << CP0C1_DS) | (5 << CP0C1_DL) | (3 << CP0C1_DA) | + (1 << CP0C1_PC) | (1 << CP0C1_WR) | (1 << CP0C1_EP), + .CP0_Config2 = MIPS_CONFIG2 | (5 << CP0C2_SS) | (5 << CP0C2_SL) | + (15 << CP0C2_SA), + .CP0_Config3 = MIPS_CONFIG3 | (1U << CP0C3_M) | (1 << CP0C3_MSAP) | + (1 << CP0C3_BP) | (1 << CP0C3_BI) | (1 << CP0C3_ULRI) | + (1 << CP0C3_RXI) | (1 << CP0C3_LPA) | (1 << CP0C3_VInt), + .CP0_Config4 = MIPS_CONFIG4 | (1U << CP0C4_M) | (2 << CP0C4_IE) | + (1 << CP0C4_AE) | (0x1c << CP0C4_KScrExist), + .CP0_Config4_rw_bitmask = 0, + .CP0_Config5 = MIPS_CONFIG5 | (1 << CP0C5_CRCP) | (1 << CP0C5_NFExists), + .CP0_Config5_rw_bitmask = (1 << CP0C5_K) | (1 << CP0C5_CV) | + (1 << CP0C5_MSAEn) | (1 << CP0C5_UFE) | + (1 << CP0C5_FRE) | (1 << CP0C5_SBRI), + .CP0_Config6 = (1 << CP0C6_VCLRU) | (1 << CP0C6_DCLRU) | + (1 << CP0C6_SFBEN) | (1 << CP0C6_VLTINT) | + (1 << CP0C6_INSTPREF) | (1 << CP0C6_DATAPREF), + .CP0_Config6_rw_bitmask = (1 << CP0C6_BPPASS) | (0x3f << CP0C6_KPOS) | + (1 << CP0C6_KE) | (1 << CP0C6_VTLBONLY) | + (1 << CP0C6_LASX) | (1 << CP0C6_SSEN) | + (1 << CP0C6_DISDRTIME) | (1 << CP0C6_PIXNUEN) | + (1 << CP0C6_SCRAND) | (1 << CP0C6_LLEXCEN) | + (1 << CP0C6_DISVC) | (1 << CP0C6_VCLRU) | + (1 << CP0C6_DCLRU) | (1 << CP0C6_PIXUEN) | + (1 << CP0C6_DISBLKLYEN) | (1 << CP0C6_UMEMUALEN) | + (1 << CP0C6_SFBEN) | (1 << CP0C6_FLTINT) | + (1 << CP0C6_VLTINT) | (1 << CP0C6_DISBTB) | + (3 << CP0C6_STPREFCTL) | (1 << CP0C6_INSTPREF) | + (1 << CP0C6_DATAPREF), + .CP0_Config7 = 0, + .CP0_Config7_rw_bitmask = (1 << CP0C7_NAPCGEN) | (1 << CP0C7_UNIMUEN) | + (1 << CP0C7_VFPUCGEN), + .CP0_LLAddr_rw_bitmask = 1, + .SYNCI_Step = 16, + .CCRes = 2, + .CP0_Status_rw_bitmask = 0x7DDBFFFF, + .CP0_PageGrain = (1 << CP0PG_ELPA), + .CP0_PageGrain_rw_bitmask = (1U << CP0PG_RIE) | (1 << CP0PG_XIE) | + (1 << CP0PG_ELPA) | (1 << CP0PG_IEC), + .CP1_fcr0 = (0x5 << FCR0_PRID) | (0x1 << FCR0_REV) | (0x1 << FCR0_F64) | + (0x1 << FCR0_PS) | (0x1 << FCR0_L) | (0x1 << FCR0_W) | + (0x1 << FCR0_D) | (0x1 << FCR0_S), + .CP1_fcr31 = 0, + .CP1_fcr31_rw_bitmask = 0xFF83FFFF, + .SEGBITS = 48, + .PABITS = 48, + .insn_flags = CPU_LOONGSON3A, + .mmu_type = MMU_TYPE_R4000, + }, + { /* A generic CPU providing MIPS64 DSP R2 ASE features. FIXME: Eventually this should be replaced by a real CPU model. */ .name = "mips64dspr2", diff --git a/target/unicore32/helper.c b/target/unicore32/helper.c index 7d538e2144..54c26871fe 100644 --- a/target/unicore32/helper.c +++ b/target/unicore32/helper.c @@ -10,14 +10,11 @@ */ #include "qemu/osdep.h" +#include "qemu/log.h" #include "cpu.h" #include "exec/exec-all.h" -#include "exec/gdbstub.h" #include "exec/helper-proto.h" -#include "qemu/host-utils.h" -#ifndef CONFIG_USER_ONLY -#include "ui/console.h" -#endif +#include "hw/semihosting/console.h" #undef DEBUG_UC32 @@ -108,8 +105,9 @@ void helper_cp0_set(CPUUniCore32State *env, uint32_t val, uint32_t creg, } return; unrecognized: - DPRINTF("Wrong register (%d) or wrong operation (%d) in cp0_set!\n", - creg, cop); + qemu_log_mask(LOG_GUEST_ERROR, + "Wrong register (%d) or wrong operation (%d) in cp0_set!\n", + creg, cop); } uint32_t helper_cp0_get(CPUUniCore32State *env, uint32_t creg, uint32_t cop) @@ -155,63 +153,19 @@ uint32_t helper_cp0_get(CPUUniCore32State *env, uint32_t creg, uint32_t cop) } break; } - DPRINTF("Wrong register (%d) or wrong operation (%d) in cp0_set!\n", - creg, cop); + qemu_log_mask(LOG_GUEST_ERROR, + "Wrong register (%d) or wrong operation (%d) in cp0_set!\n", + creg, cop); return 0; } -#ifdef CONFIG_CURSES - -/* KEY_EVENT is defined in wincon.h and in curses.h. Avoid redefinition. */ -#undef KEY_EVENT -#include <curses.h> -#undef KEY_EVENT - -/* - * FIXME: - * 1. curses windows will be blank when switching back - * 2. backspace is not handled yet - */ -static void putc_on_screen(unsigned char ch) +void helper_cp1_putc(target_ulong regval) { - static WINDOW *localwin; - static int init; - - if (!init) { - /* Assume 80 * 30 screen to minimize the implementation */ - localwin = newwin(30, 80, 0, 0); - scrollok(localwin, TRUE); - init = TRUE; - } + const char c = regval; - if (isprint(ch)) { - wprintw(localwin, "%c", ch); - } else { - switch (ch) { - case '\n': - wprintw(localwin, "%c", ch); - break; - case '\r': - /* If '\r' is put before '\n', the curses window will destroy the - * last print line. And meanwhile, '\n' implifies '\r' inside. */ - break; - default: /* Not handled, so just print it hex code */ - wprintw(localwin, "-- 0x%x --", ch); - } - } - - wrefresh(localwin); -} -#else -#define putc_on_screen(c) do { } while (0) -#endif - -void helper_cp1_putc(target_ulong x) -{ - putc_on_screen((unsigned char)x); /* Output to screen */ - DPRINTF("%c", x); /* Output to stdout */ + qemu_semihosting_log_out(&c, sizeof(c)); } -#endif +#endif /* !CONFIG_USER_ONLY */ bool uc32_cpu_exec_interrupt(CPUState *cs, int interrupt_request) { diff --git a/tests/data/acpi/pc/DSDT b/tests/data/acpi/pc/DSDT Binary files differindex ad4b2d46cc..384a82dbb3 100644 --- a/tests/data/acpi/pc/DSDT +++ b/tests/data/acpi/pc/DSDT diff --git a/tests/data/acpi/pc/DSDT.acpihmat b/tests/data/acpi/pc/DSDT.acpihmat Binary files differindex eff7aadfab..47ddfdb027 100644 --- a/tests/data/acpi/pc/DSDT.acpihmat +++ b/tests/data/acpi/pc/DSDT.acpihmat diff --git a/tests/data/acpi/pc/DSDT.bridge b/tests/data/acpi/pc/DSDT.bridge Binary files differindex 92ae808e2e..d1e2fa9fb8 100644 --- a/tests/data/acpi/pc/DSDT.bridge +++ b/tests/data/acpi/pc/DSDT.bridge diff --git a/tests/data/acpi/pc/DSDT.cphp b/tests/data/acpi/pc/DSDT.cphp Binary files differindex f357235851..54f481faf1 100644 --- a/tests/data/acpi/pc/DSDT.cphp +++ b/tests/data/acpi/pc/DSDT.cphp diff --git a/tests/data/acpi/pc/DSDT.dimmpxm b/tests/data/acpi/pc/DSDT.dimmpxm Binary files differindex 7fa09463c1..5d98016ae5 100644 --- a/tests/data/acpi/pc/DSDT.dimmpxm +++ b/tests/data/acpi/pc/DSDT.dimmpxm diff --git a/tests/data/acpi/pc/DSDT.ipmikcs b/tests/data/acpi/pc/DSDT.ipmikcs Binary files differindex 469d13e1f6..57b7835874 100644 --- a/tests/data/acpi/pc/DSDT.ipmikcs +++ b/tests/data/acpi/pc/DSDT.ipmikcs diff --git a/tests/data/acpi/pc/DSDT.memhp b/tests/data/acpi/pc/DSDT.memhp Binary files differindex aee75bea27..8cb90ef14e 100644 --- a/tests/data/acpi/pc/DSDT.memhp +++ b/tests/data/acpi/pc/DSDT.memhp diff --git a/tests/data/acpi/pc/DSDT.numamem b/tests/data/acpi/pc/DSDT.numamem Binary files differindex 9a747f6f08..f194bc6394 100644 --- a/tests/data/acpi/pc/DSDT.numamem +++ b/tests/data/acpi/pc/DSDT.numamem diff --git a/tests/data/acpi/pc/SRAT.dimmpxm b/tests/data/acpi/pc/SRAT.dimmpxm Binary files differindex f5c0267ea2..5a13c61b90 100644 --- a/tests/data/acpi/pc/SRAT.dimmpxm +++ b/tests/data/acpi/pc/SRAT.dimmpxm diff --git a/tests/data/acpi/q35/DSDT b/tests/data/acpi/q35/DSDT Binary files differindex 9fa4d5a405..6a5e4dd85a 100644 --- a/tests/data/acpi/q35/DSDT +++ b/tests/data/acpi/q35/DSDT diff --git a/tests/data/acpi/q35/DSDT.acpihmat b/tests/data/acpi/q35/DSDT.acpihmat Binary files differindex 2d834a854c..c1dd7773f3 100644 --- a/tests/data/acpi/q35/DSDT.acpihmat +++ b/tests/data/acpi/q35/DSDT.acpihmat diff --git a/tests/data/acpi/q35/DSDT.bridge b/tests/data/acpi/q35/DSDT.bridge Binary files differindex b75122b24a..2ef1e894a3 100644 --- a/tests/data/acpi/q35/DSDT.bridge +++ b/tests/data/acpi/q35/DSDT.bridge diff --git a/tests/data/acpi/q35/DSDT.cphp b/tests/data/acpi/q35/DSDT.cphp Binary files differindex c59c19ff46..74e86176e5 100644 --- a/tests/data/acpi/q35/DSDT.cphp +++ b/tests/data/acpi/q35/DSDT.cphp diff --git a/tests/data/acpi/q35/DSDT.dimmpxm b/tests/data/acpi/q35/DSDT.dimmpxm Binary files differindex 9edc104ee6..4bf8e9d64b 100644 --- a/tests/data/acpi/q35/DSDT.dimmpxm +++ b/tests/data/acpi/q35/DSDT.dimmpxm diff --git a/tests/data/acpi/q35/DSDT.ipmibt b/tests/data/acpi/q35/DSDT.ipmibt Binary files differindex 3910e9b767..38723daef8 100644 --- a/tests/data/acpi/q35/DSDT.ipmibt +++ b/tests/data/acpi/q35/DSDT.ipmibt diff --git a/tests/data/acpi/q35/DSDT.memhp b/tests/data/acpi/q35/DSDT.memhp Binary files differindex 8461e984c9..98328d1c41 100644 --- a/tests/data/acpi/q35/DSDT.memhp +++ b/tests/data/acpi/q35/DSDT.memhp diff --git a/tests/data/acpi/q35/DSDT.mmio64 b/tests/data/acpi/q35/DSDT.mmio64 Binary files differindex fc0cc096ba..5916c0e9ce 100644 --- a/tests/data/acpi/q35/DSDT.mmio64 +++ b/tests/data/acpi/q35/DSDT.mmio64 diff --git a/tests/data/acpi/q35/DSDT.numamem b/tests/data/acpi/q35/DSDT.numamem Binary files differindex 498c843be1..cf3fde3449 100644 --- a/tests/data/acpi/q35/DSDT.numamem +++ b/tests/data/acpi/q35/DSDT.numamem diff --git a/tests/data/acpi/q35/DSDT.tis b/tests/data/acpi/q35/DSDT.tis Binary files differnew file mode 100644 index 0000000000..56b6fb0c32 --- /dev/null +++ b/tests/data/acpi/q35/DSDT.tis diff --git a/tests/data/acpi/q35/SRAT.dimmpxm b/tests/data/acpi/q35/SRAT.dimmpxm Binary files differindex f5c0267ea2..5a13c61b90 100644 --- a/tests/data/acpi/q35/SRAT.dimmpxm +++ b/tests/data/acpi/q35/SRAT.dimmpxm diff --git a/tests/data/acpi/q35/TPM2.tis b/tests/data/acpi/q35/TPM2.tis Binary files differnew file mode 100644 index 0000000000..7878a6e79a --- /dev/null +++ b/tests/data/acpi/q35/TPM2.tis diff --git a/tests/data/acpi/virt/SRAT.memhp b/tests/data/acpi/virt/SRAT.memhp Binary files differindex 1b57db2072..9a35adb40c 100644 --- a/tests/data/acpi/virt/SRAT.memhp +++ b/tests/data/acpi/virt/SRAT.memhp diff --git a/tests/decode/err_pattern_group_nest1.decode b/tests/decode/err_pattern_group_nest1.decode index 92e971c3c5..7d09891a1c 100644 --- a/tests/decode/err_pattern_group_nest1.decode +++ b/tests/decode/err_pattern_group_nest1.decode @@ -3,11 +3,12 @@ %sub1 0:8 %sub2 8:8 -%sub3 16:8 -%sub4 24:8 -# Groups with no overlap are supposed to fail +# Make sure braces are matched { - top 00000000 00000000 00000000 00000000 - sub4 ........ ........ ........ ........ %sub1 %sub2 %sub3 %sub4 + top 00000000 00000000 00000000 00000000 + [ + sub1 00000000 00000000 00000000 ........ %sub1 + sub2 00000000 00000000 ........ ........ %sub1 %sub2 + } } diff --git a/tests/decode/err_pattern_group_nest2.decode b/tests/decode/err_pattern_group_nest2.decode new file mode 100644 index 0000000000..c172239e9b --- /dev/null +++ b/tests/decode/err_pattern_group_nest2.decode @@ -0,0 +1,6 @@ +# This work is licensed under the terms of the GNU LGPL, version 2 or later. +# See the COPYING.LIB file in the top-level directory. + +# Make sure braces are matched +{ + [ diff --git a/tests/decode/err_pattern_group_nest3.decode b/tests/decode/err_pattern_group_nest3.decode new file mode 100644 index 0000000000..b085d01410 --- /dev/null +++ b/tests/decode/err_pattern_group_nest3.decode @@ -0,0 +1,14 @@ +# This work is licensed under the terms of the GNU LGPL, version 2 or later. +# See the COPYING.LIB file in the top-level directory. + +%sub1 0:8 +%sub2 8:8 + +# The exclusive group should error for overlap. +{ + top 00000000 00000000 00000000 00000000 + [ + sub1 00000000 00000000 00000000 ........ %sub1 + sub2 00000000 00000000 ........ ........ %sub1 %sub2 + ] +} diff --git a/tests/decode/succ_pattern_group_nest2.decode b/tests/decode/succ_pattern_group_nest2.decode new file mode 100644 index 0000000000..8d5ab4b2d3 --- /dev/null +++ b/tests/decode/succ_pattern_group_nest2.decode @@ -0,0 +1,13 @@ +# This work is licensed under the terms of the GNU LGPL, version 2 or later. +# See the COPYING.LIB file in the top-level directory. + +%sub1 0:8 +%sub2 8:8 +%sub3 16:8 +%sub4 24:8 + +# Group with complete overlap of the two patterns +{ + top 00000000 00000000 00000000 00000000 + sub4 ........ ........ ........ ........ %sub1 %sub2 %sub3 %sub4 +} diff --git a/tests/decode/succ_pattern_group_nest3.decode b/tests/decode/succ_pattern_group_nest3.decode new file mode 100644 index 0000000000..156249f090 --- /dev/null +++ b/tests/decode/succ_pattern_group_nest3.decode @@ -0,0 +1,11 @@ +# This work is licensed under the terms of the GNU LGPL, version 2 or later. +# See the COPYING.LIB file in the top-level directory. + +{ + [ + sub1 00000000 a:8 b:8 c:8 + sub2 00000001 a:8 b:8 c:8 + sub3 00000010 a:8 b:8 c:8 + ] + sub4 000000 d:2 a:8 b:8 c:8 +} diff --git a/tests/decode/succ_pattern_group_nest4.decode b/tests/decode/succ_pattern_group_nest4.decode new file mode 100644 index 0000000000..dc54a1d285 --- /dev/null +++ b/tests/decode/succ_pattern_group_nest4.decode @@ -0,0 +1,13 @@ +# This work is licensed under the terms of the GNU LGPL, version 2 or later. +# See the COPYING.LIB file in the top-level directory. + +# Verify deeper nesting, and a single element in the groups. +{ + [ + { + [ + sub1 00000000 a:8 b:8 c:8 + ] + } + ] +} diff --git a/tests/docker/Makefile.include b/tests/docker/Makefile.include index f32a95b488..3e3617816e 100644 --- a/tests/docker/Makefile.include +++ b/tests/docker/Makefile.include @@ -130,7 +130,7 @@ docker-image-debian-sparc64-cross: docker-image-debian10 docker-image-travis: NOUSER=1 # Specialist build images, sometimes very limited tools -docker-image-tricore-cross: docker-image-debian9 +docker-image-debian-tricore-cross: docker-image-debian9 docker-image-debian-arm64-test-cross: docker-image-debian11 # These images may be good enough for building tests but not for test builds diff --git a/tests/docker/dockerfiles/centos7.docker b/tests/docker/dockerfiles/centos7.docker index 9a2a2e515d..e197acdc3c 100644 --- a/tests/docker/dockerfiles/centos7.docker +++ b/tests/docker/dockerfiles/centos7.docker @@ -5,13 +5,11 @@ RUN yum -y update # Please keep this list sorted alphabetically ENV PACKAGES \ - bison \ bzip2 \ bzip2-devel \ ccache \ csnappy-devel \ dbus-daemon \ - flex \ gcc-c++ \ gcc \ gettext \ diff --git a/tests/docker/dockerfiles/centos8.docker b/tests/docker/dockerfiles/centos8.docker index bfa0d33c9c..9852c5b9ee 100644 --- a/tests/docker/dockerfiles/centos8.docker +++ b/tests/docker/dockerfiles/centos8.docker @@ -3,11 +3,9 @@ FROM centos:8.1.1911 RUN dnf -y update ENV PACKAGES \ SDL-devel \ - bison \ bzip2 \ bzip2-devel \ dbus-daemon \ - flex \ gcc \ gcc-c++ \ gettext \ diff --git a/tests/docker/dockerfiles/debian-xtensa-cross.docker b/tests/docker/dockerfiles/debian-xtensa-cross.docker index e6f93f65ee..beb73f46ba 100644 --- a/tests/docker/dockerfiles/debian-xtensa-cross.docker +++ b/tests/docker/dockerfiles/debian-xtensa-cross.docker @@ -11,11 +11,9 @@ RUN apt-get update && \ DEBIAN_FRONTEND=noninteractive apt install -yy eatmydata && \ DEBIAN_FRONTEND=noninteractive eatmydata \ apt-get install -y --no-install-recommends \ - bison \ build-essential \ ca-certificates \ curl \ - flex \ gettext \ git \ python3-minimal diff --git a/tests/docker/dockerfiles/debian10.docker b/tests/docker/dockerfiles/debian10.docker index 0769700a41..bcdff04ddf 100644 --- a/tests/docker/dockerfiles/debian10.docker +++ b/tests/docker/dockerfiles/debian10.docker @@ -18,12 +18,10 @@ RUN apt update && \ DEBIAN_FRONTEND=noninteractive eatmydata \ apt install -y --no-install-recommends \ bc \ - bison \ build-essential \ ca-certificates \ clang \ dbus \ - flex \ gdb-multiarch \ gettext \ git \ diff --git a/tests/docker/dockerfiles/debian9.docker b/tests/docker/dockerfiles/debian9.docker index 08cc970feb..0f0ebe530a 100644 --- a/tests/docker/dockerfiles/debian9.docker +++ b/tests/docker/dockerfiles/debian9.docker @@ -18,11 +18,9 @@ RUN apt update && \ DEBIAN_FRONTEND=noninteractive eatmydata \ apt install -y --no-install-recommends \ bc \ - bison \ build-essential \ ca-certificates \ clang \ - flex \ gdb-multiarch \ gettext \ git \ diff --git a/tests/docker/dockerfiles/fedora.docker b/tests/docker/dockerfiles/fedora.docker index 179575ecaa..92b6e11c8a 100644 --- a/tests/docker/dockerfiles/fedora.docker +++ b/tests/docker/dockerfiles/fedora.docker @@ -3,7 +3,6 @@ FROM fedora:30 # Please keep this list sorted alphabetically ENV PACKAGES \ bc \ - bison \ brlapi-devel \ bzip2 \ bzip2-devel \ @@ -13,7 +12,6 @@ ENV PACKAGES \ dbus-daemon \ device-mapper-multipath-devel \ findutils \ - flex \ gcc \ gcc-c++ \ gettext \ diff --git a/tests/docker/dockerfiles/ubuntu.docker b/tests/docker/dockerfiles/ubuntu.docker index eeb3b22bf2..161806e6b8 100644 --- a/tests/docker/dockerfiles/ubuntu.docker +++ b/tests/docker/dockerfiles/ubuntu.docker @@ -9,8 +9,8 @@ # system won't pick up that it has changed. # -FROM ubuntu:19.04 -ENV PACKAGES flex bison \ +FROM ubuntu:20.04 +ENV PACKAGES \ ccache \ clang \ dbus \ diff --git a/tests/docker/dockerfiles/ubuntu1804.docker b/tests/docker/dockerfiles/ubuntu1804.docker index f66b06f4cf..a10ea2850b 100644 --- a/tests/docker/dockerfiles/ubuntu1804.docker +++ b/tests/docker/dockerfiles/ubuntu1804.docker @@ -1,5 +1,5 @@ FROM ubuntu:18.04 -ENV PACKAGES flex bison \ +ENV PACKAGES \ ccache \ clang \ gcc \ diff --git a/tests/plugin/mem.c b/tests/plugin/mem.c index 878abf09d1..4725bd851d 100644 --- a/tests/plugin/mem.c +++ b/tests/plugin/mem.c @@ -28,7 +28,7 @@ static void plugin_exit(qemu_plugin_id_t id, void *p) g_string_printf(out, "mem accesses: %" PRIu64 "\n", mem_count); if (do_haddr) { - g_string_append_printf(out, "io accesses: %" PRIu64 "\n", mem_count); + g_string_append_printf(out, "io accesses: %" PRIu64 "\n", io_count); } qemu_plugin_outs(out->str); } diff --git a/tests/qemu-iotests/031.out b/tests/qemu-iotests/031.out index 5a4beda6a2..4b21d6a9ba 100644 --- a/tests/qemu-iotests/031.out +++ b/tests/qemu-iotests/031.out @@ -25,7 +25,7 @@ refcount_order 4 header_length 72 Header extension: -magic 0x12345678 +magic 0x12345678 (<unknown>) length 31 data 'This is a test header extension' @@ -53,7 +53,7 @@ refcount_order 4 header_length 72 Header extension: -magic 0x12345678 +magic 0x12345678 (<unknown>) length 31 data 'This is a test header extension' @@ -81,12 +81,12 @@ refcount_order 4 header_length 72 Header extension: -magic 0xe2792aca +magic 0xe2792aca (Backing format) length 11 data 'host_device' Header extension: -magic 0x12345678 +magic 0x12345678 (<unknown>) length 31 data 'This is a test header extension' @@ -116,12 +116,12 @@ refcount_order 4 header_length 112 Header extension: -magic 0x6803f857 +magic 0x6803f857 (Feature table) length 336 data <binary> Header extension: -magic 0x12345678 +magic 0x12345678 (<unknown>) length 31 data 'This is a test header extension' @@ -149,12 +149,12 @@ refcount_order 4 header_length 112 Header extension: -magic 0x6803f857 +magic 0x6803f857 (Feature table) length 336 data <binary> Header extension: -magic 0x12345678 +magic 0x12345678 (<unknown>) length 31 data 'This is a test header extension' @@ -182,17 +182,17 @@ refcount_order 4 header_length 112 Header extension: -magic 0xe2792aca +magic 0xe2792aca (Backing format) length 11 data 'host_device' Header extension: -magic 0x6803f857 +magic 0x6803f857 (Feature table) length 336 data <binary> Header extension: -magic 0x12345678 +magic 0x12345678 (<unknown>) length 31 data 'This is a test header extension' diff --git a/tests/qemu-iotests/036.out b/tests/qemu-iotests/036.out index e409acf60e..a9bed828e5 100644 --- a/tests/qemu-iotests/036.out +++ b/tests/qemu-iotests/036.out @@ -25,7 +25,7 @@ incompatible_features [] compatible_features [] autoclear_features [63] Header extension: -magic 0x6803f857 +magic 0x6803f857 (Feature table) length 336 data <binary> @@ -37,7 +37,7 @@ incompatible_features [] compatible_features [] autoclear_features [] Header extension: -magic 0x6803f857 +magic 0x6803f857 (Feature table) length 336 data <binary> diff --git a/tests/qemu-iotests/061.out b/tests/qemu-iotests/061.out index a51ad1b5ba..2f03cf045c 100644 --- a/tests/qemu-iotests/061.out +++ b/tests/qemu-iotests/061.out @@ -25,7 +25,7 @@ refcount_order 4 header_length 112 Header extension: -magic 0x6803f857 +magic 0x6803f857 (Feature table) length 336 data <binary> @@ -83,7 +83,7 @@ refcount_order 4 header_length 112 Header extension: -magic 0x6803f857 +magic 0x6803f857 (Feature table) length 336 data <binary> @@ -139,7 +139,7 @@ refcount_order 4 header_length 112 Header extension: -magic 0x6803f857 +magic 0x6803f857 (Feature table) length 336 data <binary> @@ -194,7 +194,7 @@ refcount_order 4 header_length 112 Header extension: -magic 0x6803f857 +magic 0x6803f857 (Feature table) length 336 data <binary> @@ -263,7 +263,7 @@ refcount_order 4 header_length 112 Header extension: -magic 0x6803f857 +magic 0x6803f857 (Feature table) length 336 data <binary> @@ -325,7 +325,7 @@ refcount_order 4 header_length 112 Header extension: -magic 0x6803f857 +magic 0x6803f857 (Feature table) length 336 data <binary> @@ -354,7 +354,7 @@ refcount_order 4 header_length 112 Header extension: -magic 0x6803f857 +magic 0x6803f857 (Feature table) length 336 data <binary> diff --git a/tests/qemu-iotests/143 b/tests/qemu-iotests/143 index f649b36195..d2349903b1 100755 --- a/tests/qemu-iotests/143 +++ b/tests/qemu-iotests/143 @@ -58,6 +58,10 @@ _send_qemu_cmd $QEMU_HANDLE \ $QEMU_IO_PROG -f raw -c quit \ "nbd+unix:///no_such_export?socket=$SOCK_DIR/nbd" 2>&1 \ | _filter_qemu_io | _filter_nbd +# Likewise, with longest possible name permitted in NBD protocol +$QEMU_IO_PROG -f raw -c quit \ + "nbd+unix:///$(printf %4096d 1 | tr ' ' a)?socket=$SOCK_DIR/nbd" 2>&1 \ + | _filter_qemu_io | _filter_nbd | sed 's/aaaa*aa/aa--aa/' _send_qemu_cmd $QEMU_HANDLE \ "{ 'execute': 'quit' }" \ diff --git a/tests/qemu-iotests/143.out b/tests/qemu-iotests/143.out index 1f4001c601..fc9c0a761f 100644 --- a/tests/qemu-iotests/143.out +++ b/tests/qemu-iotests/143.out @@ -5,6 +5,8 @@ QA output created by 143 {"return": {}} qemu-io: can't open device nbd+unix:///no_such_export?socket=SOCK_DIR/nbd: Requested export not available server reported: export 'no_such_export' not present +qemu-io: can't open device nbd+unix:///aa--aa1?socket=SOCK_DIR/nbd: Requested export not available +server reported: export 'aa--aa...' not present { 'execute': 'quit' } {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false, "reason": "host-qmp-quit"}} diff --git a/tests/qemu-iotests/194 b/tests/qemu-iotests/194 index 3fad7c6c1a..da7c4265ec 100755 --- a/tests/qemu-iotests/194 +++ b/tests/qemu-iotests/194 @@ -87,4 +87,14 @@ with iotests.FilePath('source.img') as source_img_path, \ iotests.log(dest_vm.qmp('nbd-server-stop')) break + iotests.log('Wait for migration completion on target...') + migr_events = (('MIGRATION', {'data': {'status': 'completed'}}), + ('MIGRATION', {'data': {'status': 'failed'}})) + event = dest_vm.events_wait(migr_events) + iotests.log(event, filters=[iotests.filter_qmp_event]) + + iotests.log('Check bitmaps on source:') iotests.log(source_vm.qmp('query-block')['return'][0]['dirty-bitmaps']) + + iotests.log('Check bitmaps on target:') + iotests.log(dest_vm.qmp('query-block')['return'][0]['dirty-bitmaps']) diff --git a/tests/qemu-iotests/194.out b/tests/qemu-iotests/194.out index dd60dcc14f..a51bdb2d4f 100644 --- a/tests/qemu-iotests/194.out +++ b/tests/qemu-iotests/194.out @@ -21,4 +21,9 @@ Gracefully ending the `drive-mirror` job on source... {"data": {"device": "mirror-job0", "len": 1073741824, "offset": 1073741824, "speed": 0, "type": "mirror"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} Stopping the NBD server on destination... {"return": {}} +Wait for migration completion on target... +{"data": {"status": "completed"}, "event": "MIGRATION", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} +Check bitmaps on source: +[{"busy": false, "count": 0, "granularity": 65536, "name": "bitmap0", "persistent": false, "recording": true, "status": "active"}] +Check bitmaps on target: [{"busy": false, "count": 0, "granularity": 65536, "name": "bitmap0", "persistent": false, "recording": true, "status": "active"}] diff --git a/tests/qemu-iotests/291 b/tests/qemu-iotests/291 index 3ca83b9cd1..404f8521f7 100755 --- a/tests/qemu-iotests/291 +++ b/tests/qemu-iotests/291 @@ -62,6 +62,8 @@ $QEMU_IO -c 'w 1M 1M' -f $IMGFMT "$TEST_IMG" | _filter_qemu_io $QEMU_IMG bitmap --disable -f $IMGFMT "$TEST_IMG" b1 $QEMU_IMG bitmap --enable -f $IMGFMT "$TEST_IMG" b2 $QEMU_IO -c 'w 2M 1M' -f $IMGFMT "$TEST_IMG" | _filter_qemu_io +echo "Check resulting qcow2 header extensions:" +$PYTHON qcow2.py "$TEST_IMG" dump-header-exts echo echo "=== Bitmap preservation not possible to non-qcow2 ===" @@ -77,7 +79,7 @@ echo # Only bitmaps from the active layer are copied $QEMU_IMG convert --bitmaps -O qcow2 "$TEST_IMG.orig" "$TEST_IMG" -$QEMU_IMG info "$TEST_IMG" | _filter_img_info --format-specific +_img_info --format-specific # But we can also merge in bitmaps from other layers. This test is a bit # contrived to cover more code paths, in reality, you could merge directly # into b0 without going through tmp @@ -87,7 +89,9 @@ $QEMU_IMG bitmap --add --merge b0 -b "$TEST_IMG.base" -F $IMGFMT \ $QEMU_IMG bitmap --merge tmp -f $IMGFMT "$TEST_IMG" b0 $QEMU_IMG bitmap --remove --image-opts \ driver=$IMGFMT,file.driver=file,file.filename="$TEST_IMG" tmp -$QEMU_IMG info "$TEST_IMG" | _filter_img_info --format-specific +_img_info --format-specific +echo "Check resulting qcow2 header extensions:" +$PYTHON qcow2.py "$TEST_IMG" dump-header-exts echo echo "=== Check bitmap contents ===" diff --git a/tests/qemu-iotests/291.out b/tests/qemu-iotests/291.out index 8c62017567..08bfaaaa6b 100644 --- a/tests/qemu-iotests/291.out +++ b/tests/qemu-iotests/291.out @@ -14,6 +14,25 @@ wrote 1048576/1048576 bytes at offset 1048576 1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) wrote 1048576/1048576 bytes at offset 2097152 1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +Check resulting qcow2 header extensions: +Header extension: +magic 0xe2792aca (Backing format) +length 5 +data 'qcow2' + +Header extension: +magic 0x6803f857 (Feature table) +length 336 +data <binary> + +Header extension: +magic 0x23852875 (Bitmaps) +length 24 +nb_bitmaps 2 +reserved32 0 +bitmap_directory_size 0x40 +bitmap_directory_offset 0x510000 + === Bitmap preservation not possible to non-qcow2 === @@ -24,7 +43,7 @@ qemu-img: Format driver 'raw' does not support bitmaps image: TEST_DIR/t.IMGFMT file format: IMGFMT virtual size: 10 MiB (10485760 bytes) -disk size: 4.39 MiB +cluster_size: 65536 Format specific information: compat: 1.1 compression type: zlib @@ -44,7 +63,7 @@ Format specific information: image: TEST_DIR/t.IMGFMT file format: IMGFMT virtual size: 10 MiB (10485760 bytes) -disk size: 4.48 MiB +cluster_size: 65536 Format specific information: compat: 1.1 compression type: zlib @@ -65,6 +84,20 @@ Format specific information: granularity: 65536 refcount bits: 16 corrupt: false +Check resulting qcow2 header extensions: +Header extension: +magic 0x6803f857 (Feature table) +length 336 +data <binary> + +Header extension: +magic 0x23852875 (Bitmaps) +length 24 +nb_bitmaps 3 +reserved32 0 +bitmap_directory_size 0x60 +bitmap_directory_offset 0x520000 + === Check bitmap contents === diff --git a/tests/qemu-iotests/qcow2.py b/tests/qemu-iotests/qcow2.py index 94a07b2f6f..8c187e9a72 100755 --- a/tests/qemu-iotests/qcow2.py +++ b/tests/qemu-iotests/qcow2.py @@ -1,181 +1,50 @@ #!/usr/bin/env python3 +# +# Manipulations with qcow2 image +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. +# import sys -import struct -import string - -class QcowHeaderExtension: - - def __init__(self, magic, length, data): - if length % 8 != 0: - padding = 8 - (length % 8) - data += b"\0" * padding - - self.magic = magic - self.length = length - self.data = data - - @classmethod - def create(cls, magic, data): - return QcowHeaderExtension(magic, len(data), data) - -class QcowHeader: - - uint32_t = 'I' - uint64_t = 'Q' - - fields = [ - # Version 2 header fields - [ uint32_t, '%#x', 'magic' ], - [ uint32_t, '%d', 'version' ], - [ uint64_t, '%#x', 'backing_file_offset' ], - [ uint32_t, '%#x', 'backing_file_size' ], - [ uint32_t, '%d', 'cluster_bits' ], - [ uint64_t, '%d', 'size' ], - [ uint32_t, '%d', 'crypt_method' ], - [ uint32_t, '%d', 'l1_size' ], - [ uint64_t, '%#x', 'l1_table_offset' ], - [ uint64_t, '%#x', 'refcount_table_offset' ], - [ uint32_t, '%d', 'refcount_table_clusters' ], - [ uint32_t, '%d', 'nb_snapshots' ], - [ uint64_t, '%#x', 'snapshot_offset' ], - - # Version 3 header fields - [ uint64_t, 'mask', 'incompatible_features' ], - [ uint64_t, 'mask', 'compatible_features' ], - [ uint64_t, 'mask', 'autoclear_features' ], - [ uint32_t, '%d', 'refcount_order' ], - [ uint32_t, '%d', 'header_length' ], - ]; - - fmt = '>' + ''.join(field[0] for field in fields) - - def __init__(self, fd): - - buf_size = struct.calcsize(QcowHeader.fmt) - - fd.seek(0) - buf = fd.read(buf_size) - - header = struct.unpack(QcowHeader.fmt, buf) - self.__dict__ = dict((field[2], header[i]) - for i, field in enumerate(QcowHeader.fields)) - - self.set_defaults() - self.cluster_size = 1 << self.cluster_bits - - fd.seek(self.header_length) - self.load_extensions(fd) - - if self.backing_file_offset: - fd.seek(self.backing_file_offset) - self.backing_file = fd.read(self.backing_file_size) - else: - self.backing_file = None - - def set_defaults(self): - if self.version == 2: - self.incompatible_features = 0 - self.compatible_features = 0 - self.autoclear_features = 0 - self.refcount_order = 4 - self.header_length = 72 - - def load_extensions(self, fd): - self.extensions = [] - - if self.backing_file_offset != 0: - end = min(self.cluster_size, self.backing_file_offset) - else: - end = self.cluster_size - - while fd.tell() < end: - (magic, length) = struct.unpack('>II', fd.read(8)) - if magic == 0: - break - else: - padded = (length + 7) & ~7 - data = fd.read(padded) - self.extensions.append(QcowHeaderExtension(magic, length, data)) - - def update_extensions(self, fd): - - fd.seek(self.header_length) - extensions = self.extensions - extensions.append(QcowHeaderExtension(0, 0, b"")) - for ex in extensions: - buf = struct.pack('>II', ex.magic, ex.length) - fd.write(buf) - fd.write(ex.data) - - if self.backing_file != None: - self.backing_file_offset = fd.tell() - fd.write(self.backing_file) - - if fd.tell() > self.cluster_size: - raise Exception("I think I just broke the image...") - - - def update(self, fd): - header_bytes = self.header_length - - self.update_extensions(fd) - - fd.seek(0) - header = tuple(self.__dict__[f] for t, p, f in QcowHeader.fields) - buf = struct.pack(QcowHeader.fmt, *header) - buf = buf[0:header_bytes-1] - fd.write(buf) - - def dump(self): - for f in QcowHeader.fields: - value = self.__dict__[f[2]] - if f[1] == 'mask': - bits = [] - for bit in range(64): - if value & (1 << bit): - bits.append(bit) - value_str = str(bits) - else: - value_str = f[1] % value - - print("%-25s" % f[2], value_str) - print("") - - def dump_extensions(self): - for ex in self.extensions: - data = ex.data[:ex.length] - if all(c in string.printable.encode('ascii') for c in data): - data = "'%s'" % data.decode('ascii') - else: - data = "<binary>" - - print("Header extension:") - print("%-25s %#x" % ("magic", ex.magic)) - print("%-25s %d" % ("length", ex.length)) - print("%-25s %s" % ("data", data)) - print("") +from qcow2_format import ( + QcowHeader, + QcowHeaderExtension +) def cmd_dump_header(fd): h = QcowHeader(fd) h.dump() + print() h.dump_extensions() + def cmd_dump_header_exts(fd): h = QcowHeader(fd) h.dump_extensions() + def cmd_set_header(fd, name, value): try: value = int(value, 0) - except: + except ValueError: print("'%s' is not a valid number" % value) sys.exit(1) fields = (field[2] for field in QcowHeader.fields) - if not name in fields: + if name not in fields: print("'%s' is not a known header field" % name) sys.exit(1) @@ -183,25 +52,29 @@ def cmd_set_header(fd, name, value): h.__dict__[name] = value h.update(fd) + def cmd_add_header_ext(fd, magic, data): try: magic = int(magic, 0) - except: + except ValueError: print("'%s' is not a valid magic number" % magic) sys.exit(1) h = QcowHeader(fd) - h.extensions.append(QcowHeaderExtension.create(magic, data.encode('ascii'))) + h.extensions.append(QcowHeaderExtension.create(magic, + data.encode('ascii'))) h.update(fd) + def cmd_add_header_ext_stdio(fd, magic): data = sys.stdin.read() cmd_add_header_ext(fd, magic, data) + def cmd_del_header_ext(fd, magic): try: magic = int(magic, 0) - except: + except ValueError: print("'%s' is not a valid magic number" % magic) sys.exit(1) @@ -219,12 +92,13 @@ def cmd_del_header_ext(fd, magic): h.update(fd) + def cmd_set_feature_bit(fd, group, bit): try: bit = int(bit, 0) if bit < 0 or bit >= 64: raise ValueError - except: + except ValueError: print("'%s' is not a valid bit number in range [0, 64)" % bit) sys.exit(1) @@ -236,21 +110,27 @@ def cmd_set_feature_bit(fd, group, bit): elif group == 'autoclear': h.autoclear_features |= 1 << bit else: - print("'%s' is not a valid group, try 'incompatible', 'compatible', or 'autoclear'" % group) + print("'%s' is not a valid group, try " + "'incompatible', 'compatible', or 'autoclear'" % group) sys.exit(1) h.update(fd) + cmds = [ - [ 'dump-header', cmd_dump_header, 0, 'Dump image header and header extensions' ], - [ 'dump-header-exts', cmd_dump_header_exts, 0, 'Dump image header extensions' ], - [ 'set-header', cmd_set_header, 2, 'Set a field in the header'], - [ 'add-header-ext', cmd_add_header_ext, 2, 'Add a header extension' ], - [ 'add-header-ext-stdio', cmd_add_header_ext_stdio, 1, 'Add a header extension, data from stdin' ], - [ 'del-header-ext', cmd_del_header_ext, 1, 'Delete a header extension' ], - [ 'set-feature-bit', cmd_set_feature_bit, 2, 'Set a feature bit'], + ['dump-header', cmd_dump_header, 0, + 'Dump image header and header extensions'], + ['dump-header-exts', cmd_dump_header_exts, 0, + 'Dump image header extensions'], + ['set-header', cmd_set_header, 2, 'Set a field in the header'], + ['add-header-ext', cmd_add_header_ext, 2, 'Add a header extension'], + ['add-header-ext-stdio', cmd_add_header_ext_stdio, 1, + 'Add a header extension, data from stdin'], + ['del-header-ext', cmd_del_header_ext, 1, 'Delete a header extension'], + ['set-feature-bit', cmd_set_feature_bit, 2, 'Set a feature bit'], ] + def main(filename, cmd, args): fd = open(filename, "r+b") try: @@ -267,6 +147,7 @@ def main(filename, cmd, args): finally: fd.close() + def usage(): print("Usage: %s <file> <cmd> [<arg>, ...]" % sys.argv[0]) print("") @@ -274,6 +155,7 @@ def usage(): for name, handler, num_args, desc in cmds: print(" %-20s - %s" % (name, desc)) + if __name__ == '__main__': if len(sys.argv) < 3: usage() diff --git a/tests/qemu-iotests/qcow2_format.py b/tests/qemu-iotests/qcow2_format.py new file mode 100644 index 0000000000..0f65fd161d --- /dev/null +++ b/tests/qemu-iotests/qcow2_format.py @@ -0,0 +1,286 @@ +# Library for manipulations with qcow2 image +# +# Copyright (c) 2020 Virtuozzo International GmbH. +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. +# + +import struct +import string + + +class Qcow2Field: + + def __init__(self, value): + self.value = value + + def __str__(self): + return str(self.value) + + +class Flags64(Qcow2Field): + + def __str__(self): + bits = [] + for bit in range(64): + if self.value & (1 << bit): + bits.append(bit) + return str(bits) + + +class Enum(Qcow2Field): + + def __str__(self): + return f'{self.value:#x} ({self.mapping.get(self.value, "<unknown>")})' + + +class Qcow2StructMeta(type): + + # Mapping from c types to python struct format + ctypes = { + 'u8': 'B', + 'u16': 'H', + 'u32': 'I', + 'u64': 'Q' + } + + def __init__(self, name, bases, attrs): + if 'fields' in attrs: + self.fmt = '>' + ''.join(self.ctypes[f[0]] for f in self.fields) + + +class Qcow2Struct(metaclass=Qcow2StructMeta): + + """Qcow2Struct: base class for qcow2 data structures + + Successors should define fields class variable, which is: list of tuples, + each of three elements: + - c-type (one of 'u8', 'u16', 'u32', 'u64') + - format (format_spec to use with .format() when dump or 'mask' to dump + bitmasks) + - field name + """ + + def __init__(self, fd=None, offset=None, data=None): + """ + Two variants: + 1. Specify data. fd and offset must be None. + 2. Specify fd and offset, data must be None. offset may be omitted + in this case, than current position of fd is used. + """ + if data is None: + assert fd is not None + buf_size = struct.calcsize(self.fmt) + if offset is not None: + fd.seek(offset) + data = fd.read(buf_size) + else: + assert fd is None and offset is None + + values = struct.unpack(self.fmt, data) + self.__dict__ = dict((field[2], values[i]) + for i, field in enumerate(self.fields)) + + def dump(self): + for f in self.fields: + value = self.__dict__[f[2]] + if isinstance(f[1], str): + value_str = f[1].format(value) + else: + value_str = str(f[1](value)) + + print('{:<25} {}'.format(f[2], value_str)) + + +class Qcow2BitmapExt(Qcow2Struct): + + fields = ( + ('u32', '{}', 'nb_bitmaps'), + ('u32', '{}', 'reserved32'), + ('u64', '{:#x}', 'bitmap_directory_size'), + ('u64', '{:#x}', 'bitmap_directory_offset') + ) + + +QCOW2_EXT_MAGIC_BITMAPS = 0x23852875 + + +class QcowHeaderExtension(Qcow2Struct): + + class Magic(Enum): + mapping = { + 0xe2792aca: 'Backing format', + 0x6803f857: 'Feature table', + 0x0537be77: 'Crypto header', + QCOW2_EXT_MAGIC_BITMAPS: 'Bitmaps', + 0x44415441: 'Data file' + } + + fields = ( + ('u32', Magic, 'magic'), + ('u32', '{}', 'length') + # length bytes of data follows + # then padding to next multiply of 8 + ) + + def __init__(self, magic=None, length=None, data=None, fd=None): + """ + Support both loading from fd and creation from user data. + For fd-based creation current position in a file will be used to read + the data. + + This should be somehow refactored and functionality should be moved to + superclass (to allow creation of any qcow2 struct), but then, fields + of variable length (data here) should be supported in base class + somehow. Note also, that we probably want to parse different + extensions. Should they be subclasses of this class, or how to do it + better? Should it be something like QAPI union with discriminator field + (magic here). So, it's a TODO. We'll see how to properly refactor this + when we have more qcow2 structures. + """ + if fd is None: + assert all(v is not None for v in (magic, length, data)) + self.magic = magic + self.length = length + if length % 8 != 0: + padding = 8 - (length % 8) + data += b'\0' * padding + self.data = data + else: + assert all(v is None for v in (magic, length, data)) + super().__init__(fd=fd) + padded = (self.length + 7) & ~7 + self.data = fd.read(padded) + assert self.data is not None + + if self.magic == QCOW2_EXT_MAGIC_BITMAPS: + self.obj = Qcow2BitmapExt(data=self.data) + else: + self.obj = None + + def dump(self): + super().dump() + + if self.obj is None: + data = self.data[:self.length] + if all(c in string.printable.encode('ascii') for c in data): + data = f"'{ data.decode('ascii') }'" + else: + data = '<binary>' + print(f'{"data":<25} {data}') + else: + self.obj.dump() + + @classmethod + def create(cls, magic, data): + return QcowHeaderExtension(magic, len(data), data) + + +class QcowHeader(Qcow2Struct): + + fields = ( + # Version 2 header fields + ('u32', '{:#x}', 'magic'), + ('u32', '{}', 'version'), + ('u64', '{:#x}', 'backing_file_offset'), + ('u32', '{:#x}', 'backing_file_size'), + ('u32', '{}', 'cluster_bits'), + ('u64', '{}', 'size'), + ('u32', '{}', 'crypt_method'), + ('u32', '{}', 'l1_size'), + ('u64', '{:#x}', 'l1_table_offset'), + ('u64', '{:#x}', 'refcount_table_offset'), + ('u32', '{}', 'refcount_table_clusters'), + ('u32', '{}', 'nb_snapshots'), + ('u64', '{:#x}', 'snapshot_offset'), + + # Version 3 header fields + ('u64', Flags64, 'incompatible_features'), + ('u64', Flags64, 'compatible_features'), + ('u64', Flags64, 'autoclear_features'), + ('u32', '{}', 'refcount_order'), + ('u32', '{}', 'header_length'), + ) + + def __init__(self, fd): + super().__init__(fd=fd, offset=0) + + self.set_defaults() + self.cluster_size = 1 << self.cluster_bits + + fd.seek(self.header_length) + self.load_extensions(fd) + + if self.backing_file_offset: + fd.seek(self.backing_file_offset) + self.backing_file = fd.read(self.backing_file_size) + else: + self.backing_file = None + + def set_defaults(self): + if self.version == 2: + self.incompatible_features = 0 + self.compatible_features = 0 + self.autoclear_features = 0 + self.refcount_order = 4 + self.header_length = 72 + + def load_extensions(self, fd): + self.extensions = [] + + if self.backing_file_offset != 0: + end = min(self.cluster_size, self.backing_file_offset) + else: + end = self.cluster_size + + while fd.tell() < end: + ext = QcowHeaderExtension(fd=fd) + if ext.magic == 0: + break + else: + self.extensions.append(ext) + + def update_extensions(self, fd): + + fd.seek(self.header_length) + extensions = self.extensions + extensions.append(QcowHeaderExtension(0, 0, b'')) + for ex in extensions: + buf = struct.pack('>II', ex.magic, ex.length) + fd.write(buf) + fd.write(ex.data) + + if self.backing_file is not None: + self.backing_file_offset = fd.tell() + fd.write(self.backing_file) + + if fd.tell() > self.cluster_size: + raise Exception('I think I just broke the image...') + + def update(self, fd): + header_bytes = self.header_length + + self.update_extensions(fd) + + fd.seek(0) + header = tuple(self.__dict__[f] for t, p, f in QcowHeader.fields) + buf = struct.pack(QcowHeader.fmt, *header) + buf = buf[0:header_bytes-1] + fd.write(buf) + + def dump_extensions(self): + for ex in self.extensions: + print('Header extension:') + ex.dump() + print() diff --git a/tests/qtest/Makefile.include b/tests/qtest/Makefile.include index 9e5a51d033..5023fa413d 100644 --- a/tests/qtest/Makefile.include +++ b/tests/qtest/Makefile.include @@ -262,6 +262,7 @@ tests/qtest/hd-geo-test$(EXESUF): tests/qtest/hd-geo-test.o $(libqos-obj-y) tests/qtest/boot-order-test$(EXESUF): tests/qtest/boot-order-test.o $(libqos-obj-y) tests/qtest/boot-serial-test$(EXESUF): tests/qtest/boot-serial-test.o $(libqos-obj-y) tests/qtest/bios-tables-test$(EXESUF): tests/qtest/bios-tables-test.o \ + tests/qtest/tpm-emu.o $(test-io-obj-y) \ tests/qtest/boot-sector.o tests/qtest/acpi-utils.o $(libqos-obj-y) tests/qtest/pxe-test$(EXESUF): tests/qtest/pxe-test.o tests/qtest/boot-sector.o $(libqos-obj-y) tests/qtest/microbit-test$(EXESUF): tests/qtest/microbit-test.o diff --git a/tests/qtest/bios-tables-test.c b/tests/qtest/bios-tables-test.c index c9843829b3..53f104a9c5 100644 --- a/tests/qtest/bios-tables-test.c +++ b/tests/qtest/bios-tables-test.c @@ -57,6 +57,9 @@ #include "qemu/bitmap.h" #include "acpi-utils.h" #include "boot-sector.h" +#include "tpm-emu.h" +#include "hw/acpi/tpm.h" + #define MACHINE_PC "pc" #define MACHINE_Q35 "q35" @@ -874,6 +877,60 @@ static void test_acpi_piix4_tcg_numamem(void) free_test_data(&data); } +uint64_t tpm_tis_base_addr; + +static void test_acpi_tcg_tpm(const char *machine, const char *tpm_if, + uint64_t base) +{ + gchar *tmp_dir_name = g_strdup_printf("qemu-test_acpi_%s_tcg_%s.XXXXXX", + machine, tpm_if); + char *tmp_path = g_dir_make_tmp(tmp_dir_name, NULL); + TestState test; + test_data data; + GThread *thread; + char *args, *variant = g_strdup_printf(".%s", tpm_if); + + tpm_tis_base_addr = base; + + module_call_init(MODULE_INIT_QOM); + + test.addr = g_new0(SocketAddress, 1); + test.addr->type = SOCKET_ADDRESS_TYPE_UNIX; + test.addr->u.q_unix.path = g_build_filename(tmp_path, "sock", NULL); + g_mutex_init(&test.data_mutex); + g_cond_init(&test.data_cond); + test.data_cond_signal = false; + + thread = g_thread_new(NULL, tpm_emu_ctrl_thread, &test); + tpm_emu_test_wait_cond(&test); + + memset(&data, 0, sizeof(data)); + data.machine = machine; + data.variant = variant; + + args = g_strdup_printf( + " -chardev socket,id=chr,path=%s" + " -tpmdev emulator,id=dev,chardev=chr" + " -device tpm-%s,tpmdev=dev", + test.addr->u.q_unix.path, tpm_if); + + test_acpi_one(args, &data); + + g_thread_join(thread); + g_unlink(test.addr->u.q_unix.path); + qapi_free_SocketAddress(test.addr); + g_rmdir(tmp_path); + g_free(variant); + g_free(tmp_path); + g_free(tmp_dir_name); + free_test_data(&data); +} + +static void test_acpi_q35_tcg_tpm_tis(void) +{ + test_acpi_tcg_tpm("q35", "tis", 0xFED40000); +} + static void test_acpi_tcg_dimm_pxm(const char *machine) { test_data data; @@ -1037,6 +1094,7 @@ int main(int argc, char *argv[]) return ret; } + qtest_add_func("acpi/q35/tpm-tis", test_acpi_q35_tcg_tpm_tis); qtest_add_func("acpi/piix4", test_acpi_piix4_tcg); qtest_add_func("acpi/piix4/bridge", test_acpi_piix4_tcg_bridge); qtest_add_func("acpi/q35", test_acpi_q35_tcg); diff --git a/tests/qtest/tpm-emu.c b/tests/qtest/tpm-emu.c index c43ac4aef8..298d0eec74 100644 --- a/tests/qtest/tpm-emu.c +++ b/tests/qtest/tpm-emu.c @@ -49,7 +49,6 @@ static void *tpm_emu_tpm_thread(void *data) s->tpm_msg->tag = be16_to_cpu(s->tpm_msg->tag); s->tpm_msg->len = be32_to_cpu(s->tpm_msg->len); g_assert_cmpint(s->tpm_msg->len, >=, minhlen); - g_assert_cmpint(s->tpm_msg->tag, ==, TPM2_ST_NO_SESSIONS); s->tpm_msg = g_realloc(s->tpm_msg, s->tpm_msg->len); qio_channel_read(ioc, (char *)&s->tpm_msg->code, diff --git a/tests/qtest/tpm-emu.h b/tests/qtest/tpm-emu.h index a4f1d64226..73f3bed0c4 100644 --- a/tests/qtest/tpm-emu.h +++ b/tests/qtest/tpm-emu.h @@ -16,6 +16,9 @@ #define TPM_RC_FAILURE 0x101 #define TPM2_ST_NO_SESSIONS 0x8001 +#include "qemu/sockets.h" +#include "io/channel.h" + struct tpm_hdr { uint16_t tag; uint32_t len; diff --git a/tests/tcg/arm/Makefile.target b/tests/tcg/arm/Makefile.target index 11c39c601e..3da09a38be 100644 --- a/tests/tcg/arm/Makefile.target +++ b/tests/tcg/arm/Makefile.target @@ -68,6 +68,8 @@ run-semiconsole-arm: semiconsole-arm run-plugin-semiconsole-arm-with-%: $(call skip-test, $<, "MANUAL ONLY") +ARM_TESTS += commpage + TESTS += $(ARM_TESTS) # On ARM Linux only supports 4k pages diff --git a/tests/tcg/arm/commpage.c b/tests/tcg/arm/commpage.c new file mode 100644 index 0000000000..c76e70cb8b --- /dev/null +++ b/tests/tcg/arm/commpage.c @@ -0,0 +1,61 @@ +/* + * Verify the COMMPAGE emulation + * + * The ARM commpage is a set of user space helper functions provided + * by the kernel in an effort to ease portability of user space code + * between different CPUs with potentially different capabilities. It + * is a 32 bit invention and similar to the vdso segment in many ways. + * + * The ABI is documented in the Linux kernel: + * Documentation/arm/kernel_userspace_helpers.rst + * + * Copyright (c) 2020 Linaro Ltd + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include <stdlib.h> +#include <stdio.h> +#include <stdint.h> + +#define ARM_COMMPAGE (0xffff0f00u) +#define ARM_KUSER_VERSION (*(int32_t *)(ARM_COMMPAGE + 0xfc)) +typedef void * (get_tls_fn)(void); +#define ARM_KUSER_GET_TLS (*(get_tls_fn *)(ARM_COMMPAGE + 0xe0)) +typedef int (cmpxchg_fn)(int oldval, int newval, volatile int *ptr); +#define ARM_KUSER_CMPXCHG (*(cmpxchg_fn *)(ARM_COMMPAGE + 0xc0)) +typedef void (dmb_fn)(void); +#define ARM_KUSER_DMB (*(dmb_fn *)(ARM_COMMPAGE + 0xa0)) +typedef int (cmpxchg64_fn)(const int64_t *oldval, + const int64_t *newval, + volatile int64_t *ptr); +#define ARM_KUSER_CMPXCHG64 (*(cmpxchg64_fn *)(ARM_COMMPAGE + 0x60)) + +#define fail_unless(x) \ + do { \ + if (!(x)) { \ + fprintf(stderr, "FAILED at %s:%d\n", __FILE__, __LINE__); \ + exit(EXIT_FAILURE); \ + } \ + } while (0) + + +int main(int argc, char *argv[argc]) +{ + void *kuser_tls; + int val = 1; + const int64_t oldval = 1, newval = 2; + int64_t val64 = 1; + + fail_unless(ARM_KUSER_VERSION == 0x5); + kuser_tls = ARM_KUSER_GET_TLS(); + printf("TLS = %p\n", kuser_tls); + fail_unless(kuser_tls != 0); + fail_unless(ARM_KUSER_CMPXCHG(1, 2, &val) == 0); + printf("val = %d\n", val); + /* this is a crash test, not checking an actual barrier occurs */ + ARM_KUSER_DMB(); + fail_unless(ARM_KUSER_CMPXCHG64(&oldval, &newval, &val64) == 0); + printf("val64 = %lld\n", val64); + return 0; +} diff --git a/tests/vm/fedora b/tests/vm/fedora index bd9c6cf295..a9195670f4 100755 --- a/tests/vm/fedora +++ b/tests/vm/fedora @@ -32,7 +32,6 @@ class FedoraVM(basevm.BaseVM): pkgs = [ # tools 'git-core', - 'flex', 'bison', 'gcc', 'binutils', 'make', # perl diff --git a/tests/vm/freebsd b/tests/vm/freebsd index 298967fe9c..f87db2b126 100755 --- a/tests/vm/freebsd +++ b/tests/vm/freebsd @@ -38,7 +38,6 @@ class FreeBSDVM(basevm.BaseVM): "bash", "gmake", "gsed", - "flex", "bison", # libs: crypto "gnutls", diff --git a/tests/vm/netbsd b/tests/vm/netbsd index b10c9d429d..cdac502dad 100755 --- a/tests/vm/netbsd +++ b/tests/vm/netbsd @@ -36,7 +36,6 @@ class NetBSDVM(basevm.BaseVM): "bash", "gmake", "gsed", - "flex", "bison", # libs: crypto "gnutls", diff --git a/tests/vm/openbsd b/tests/vm/openbsd index 0b705f4945..13e7f9a6d5 100755 --- a/tests/vm/openbsd +++ b/tests/vm/openbsd @@ -35,7 +35,6 @@ class OpenBSDVM(basevm.BaseVM): "bash", "gmake", "gsed", - "bison", # libs: usb "libusb1", diff --git a/tests/vm/ubuntu.i386 b/tests/vm/ubuntu.i386 index 1570775335..24527cc78c 100755 --- a/tests/vm/ubuntu.i386 +++ b/tests/vm/ubuntu.i386 @@ -52,7 +52,7 @@ class UbuntuX86VM(basevm.BaseVM): self.ssh_root_check("sed -ie s/^#\ deb-src/deb-src/g /etc/apt/sources.list") self.ssh_root_check("apt-get update") self.ssh_root_check("apt-get build-dep -y qemu") - self.ssh_root_check("apt-get install -y libfdt-dev flex bison language-pack-en") + self.ssh_root_check("apt-get install -y libfdt-dev language-pack-en") self.ssh_root("poweroff") self.wait() os.rename(img_tmp, img) |