diff options
61 files changed, 722 insertions, 404 deletions
diff --git a/.cirrus.yml b/.cirrus.yml index 2e45b3254f..62a9b57530 100644 --- a/.cirrus.yml +++ b/.cirrus.yml @@ -18,6 +18,7 @@ freebsd_12_task: - gmake -j$(sysctl -n hw.ncpu) check V=1 macos_task: + timeout_in: 90m osx_instance: image: catalina-base install_script: @@ -32,6 +33,7 @@ macos_task: - gmake check V=1 macos_xcode_task: + timeout_in: 90m osx_instance: # this is an alias for the latest Xcode image: catalina-xcode diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml index 9a8b375188..d0173e82b1 100644 --- a/.gitlab-ci.yml +++ b/.gitlab-ci.yml @@ -247,6 +247,15 @@ build-user: CONFIGURE_ARGS: --disable-tools --disable-system MAKE_CHECK_ARGS: check-tcg +# Only build the softmmu targets we have check-tcg tests for +build-some-softmmu: + <<: *native_build_job_definition + variables: + IMAGE: debian-all-test-cross + CONFIGURE_ARGS: --disable-tools --enable-debug-tcg + TARGETS: xtensa-softmmu arm-softmmu aarch64-softmmu alpha-softmmu + MAKE_CHECK_ARGS: check-tcg + # Run check-tcg against linux-user (with plugins) # we skip sparc64-linux-user until it has been fixed somewhat # we skip cris-linux-user as it doesn't use the common run loop @@ -258,6 +267,14 @@ build-user-plugins: MAKE_CHECK_ARGS: check-tcg timeout: 1h 30m +build-some-softmmu-plugins: + <<: *native_build_job_definition + variables: + IMAGE: debian-all-test-cross + CONFIGURE_ARGS: --disable-tools --disable-user --enable-plugins --enable-debug-tcg + TARGETS: xtensa-softmmu arm-softmmu aarch64-softmmu alpha-softmmu + MAKE_CHECK_ARGS: check-tcg + build-clang: <<: *native_build_job_definition variables: @@ -398,6 +415,24 @@ check-crypto-only-gnutls: IMAGE: centos7 MAKE_CHECK_ARGS: check +# We don't need to exercise every backend with every front-end +build-trace-multi-user: + <<: *native_build_job_definition + variables: + IMAGE: ubuntu2004 + CONFIGURE_ARGS: --enable-trace-backends=log,simple,syslog --disable-system + +build-trace-ftrace-system: + <<: *native_build_job_definition + variables: + IMAGE: ubuntu2004 + CONFIGURE_ARGS: --enable-trace-backends=ftrace --target-list=x86_64-softmmu + +build-trace-ust-system: + <<: *native_build_job_definition + variables: + IMAGE: ubuntu2004 + CONFIGURE_ARGS: --enable-trace-backends=ust --target-list=x86_64-softmmu check-patch: stage: build diff --git a/.travis.yml b/.travis.yml index a3d78171ca..1f80bdb624 100644 --- a/.travis.yml +++ b/.travis.yml @@ -232,25 +232,6 @@ jobs: - TEST_CMD="" - # We don't need to exercise every backend with every front-end - - name: "GCC trace log,simple,syslog (user)" - env: - - CONFIG="--enable-trace-backends=log,simple,syslog --disable-system" - - TEST_CMD="" - - - - name: "GCC trace ftrace (x86_64-softmmu)" - env: - - CONFIG="--enable-trace-backends=ftrace --target-list=x86_64-softmmu" - - TEST_CMD="" - - - - name: "GCC trace ust (x86_64-softmmu)" - env: - - CONFIG="--enable-trace-backends=ust --target-list=x86_64-softmmu" - - TEST_CMD="" - - # Using newer GCC with sanitizers - name: "GCC9 with sanitizers (softmmu)" dist: bionic @@ -301,32 +282,6 @@ jobs: - ${SRC_DIR}/configure ${CONFIG} --extra-cflags="-g3 -O0 -fsanitize=thread" || { cat config.log meson-logs/meson-log.txt && exit 1; } - # Run check-tcg against linux-user - - name: "GCC check-tcg (user)" - env: - - CONFIG="--disable-system --enable-debug-tcg" - - TEST_BUILD_CMD="make build-tcg" - - TEST_CMD="make check-tcg" - - CACHE_NAME="${TRAVIS_BRANCH}-linux-gcc-debug-tcg" - - - # Run check-tcg against softmmu targets - - name: "GCC check-tcg (some-softmmu)" - env: - - CONFIG="--enable-debug-tcg --target-list=xtensa-softmmu,arm-softmmu,aarch64-softmmu,alpha-softmmu" - - TEST_BUILD_CMD="make build-tcg" - - TEST_CMD="make check-tcg" - - CACHE_NAME="${TRAVIS_BRANCH}-linux-gcc-debug-tcg" - - - # Run check-tcg against softmmu targets (with plugins) - - name: "GCC plugins check-tcg (some-softmmu)" - env: - - CONFIG="--enable-plugins --enable-debug-tcg --target-list=xtensa-softmmu,arm-softmmu,aarch64-softmmu,alpha-softmmu" - - TEST_BUILD_CMD="make build-tcg" - - TEST_CMD="make check-tcg" - - CACHE_NAME="${TRAVIS_BRANCH}-linux-gcc-debug-tcg" - - name: "[aarch64] GCC check-tcg" arch: arm64 dist: focal diff --git a/MAINTAINERS b/MAINTAINERS index 2e018a0c1d..68bc160f41 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -158,6 +158,7 @@ F: disas/arm.c F: disas/arm-a64.cc F: disas/libvixl/ F: docs/system/target-arm.rst +F: docs/system/arm/cpu-features.rst ARM SMMU M: Eric Auger <eric.auger@redhat.com> @@ -558,7 +559,7 @@ S: Maintained F: hw/*/allwinner-h3* F: include/hw/*/allwinner-h3* F: hw/arm/orangepi.c -F: docs/system/orangepi.rst +F: docs/system/arm/orangepi.rst ARM PrimeCell and CMSDK devices M: Peter Maydell <peter.maydell@linaro.org> @@ -762,6 +763,7 @@ F: include/hw/*/npcm7xx* F: tests/qtest/npcm7xx* F: pc-bios/npcm7xx_bootrom.bin F: roms/vbootrom +F: docs/system/arm/nuvoton.rst nSeries M: Andrzej Zaborowski <balrogg@gmail.com> @@ -801,6 +803,7 @@ F: hw/arm/raspi_platform.h F: hw/*/bcm283* F: include/hw/arm/raspi* F: include/hw/*/bcm283* +F: docs/system/arm/raspi.rst Real View M: Peter Maydell <peter.maydell@linaro.org> @@ -855,6 +858,7 @@ R: Leif Lindholm <leif@nuviainc.com> L: qemu-arm@nongnu.org S: Maintained F: hw/arm/sbsa-ref.c +F: docs/system/arm/sbsa.rst Sharp SL-5500 (Collie) PDA M: Peter Maydell <peter.maydell@linaro.org> @@ -999,6 +1003,7 @@ F: include/hw/*/*aspeed* F: include/hw/misc/pca9552*.h F: hw/net/ftgmac100.c F: include/hw/net/ftgmac100.h +F: docs/system/arm/aspeed.rst NRF51 M: Joel Stanley <joel@jms.id.au> @@ -1603,6 +1608,7 @@ L: qemu-arm@nongnu.org S: Maintained F: hw/*/omap* F: include/hw/arm/omap.h +F: docs/system/arm/sx1.rst IPack M: Alberto Garcia <berto@igalia.com> @@ -1882,6 +1888,7 @@ M: Klaus Jensen <its@irrelevant.dk> L: qemu-block@nongnu.org S: Supported F: hw/block/nvme* +F: include/block/nvme.h F: tests/qtest/nvme-test.c F: docs/specs/nvme.txt T: git git://git.infradead.org/qemu-nvme.git nvme-next @@ -2972,6 +2979,7 @@ R: Fam Zheng <fam@euphon.net> L: qemu-block@nongnu.org S: Supported F: block/nvme* +F: include/block/nvme.h T: git https://github.com/stefanha/qemu.git block Bootdevice diff --git a/VERSION b/VERSION index f01420afbd..e9b9829697 100644 --- a/VERSION +++ b/VERSION @@ -1 +1 @@ -5.1.92 +5.1.93 diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c index 9ef5daf4c5..baaa54249d 100644 --- a/accel/kvm/kvm-all.c +++ b/accel/kvm/kvm-all.c @@ -2239,8 +2239,10 @@ static int kvm_init(MachineState *ms) kvm_memory_listener_register(s, &s->memory_listener, &address_space_memory, 0); - memory_listener_register(&kvm_io_listener, - &address_space_io); + if (kvm_eventfds_allowed) { + memory_listener_register(&kvm_io_listener, + &address_space_io); + } memory_listener_register(&kvm_coalesced_pio_listener, &address_space_io); diff --git a/block/nvme.c b/block/nvme.c index 739a0a700c..a06a188d53 100644 --- a/block/nvme.c +++ b/block/nvme.c @@ -41,6 +41,16 @@ typedef struct BDRVNVMeState BDRVNVMeState; +/* Same index is used for queues and IRQs */ +#define INDEX_ADMIN 0 +#define INDEX_IO(n) (1 + n) + +/* This driver shares a single MSIX IRQ for the admin and I/O queues */ +enum { + MSIX_SHARED_IRQ_IDX = 0, + MSIX_IRQ_COUNT = 1 +}; + typedef struct { int32_t head, tail; uint8_t *queue; @@ -81,18 +91,10 @@ typedef struct { QEMUBH *completion_bh; } NVMeQueuePair; -#define INDEX_ADMIN 0 -#define INDEX_IO(n) (1 + n) - -/* This driver shares a single MSIX IRQ for the admin and I/O queues */ -enum { - MSIX_SHARED_IRQ_IDX = 0, - MSIX_IRQ_COUNT = 1 -}; - struct BDRVNVMeState { AioContext *aio_context; QEMUVFIOState *vfio; + void *bar0_wo_map; /* Memory mapped registers */ volatile struct { uint32_t sq_tail; @@ -103,7 +105,7 @@ struct BDRVNVMeState { * [1..]: io queues. */ NVMeQueuePair **queues; - int nr_queues; + unsigned queue_count; size_t page_size; /* How many uint32_t elements does each doorbell entry take. */ size_t doorbell_scale; @@ -159,28 +161,32 @@ static QemuOptsList runtime_opts = { }, }; -static void nvme_init_queue(BDRVNVMeState *s, NVMeQueue *q, - int nentries, int entry_bytes, Error **errp) +/* Returns true on success, false on failure. */ +static bool nvme_init_queue(BDRVNVMeState *s, NVMeQueue *q, + unsigned nentries, size_t entry_bytes, Error **errp) { size_t bytes; int r; - bytes = ROUND_UP(nentries * entry_bytes, s->page_size); + bytes = ROUND_UP(nentries * entry_bytes, qemu_real_host_page_size); q->head = q->tail = 0; - q->queue = qemu_try_memalign(s->page_size, bytes); + q->queue = qemu_try_memalign(qemu_real_host_page_size, bytes); if (!q->queue) { error_setg(errp, "Cannot allocate queue"); - return; + return false; } memset(q->queue, 0, bytes); r = qemu_vfio_dma_map(s->vfio, q->queue, bytes, false, &q->iova); if (r) { error_setg(errp, "Cannot map queue"); + return false; } + return true; } static void nvme_free_queue_pair(NVMeQueuePair *q) { + trace_nvme_free_queue_pair(q->index, q); if (q->completion_bh) { qemu_bh_delete(q->completion_bh); } @@ -204,31 +210,33 @@ static void nvme_free_req_queue_cb(void *opaque) static NVMeQueuePair *nvme_create_queue_pair(BDRVNVMeState *s, AioContext *aio_context, - int idx, int size, + unsigned idx, size_t size, Error **errp) { int i, r; - Error *local_err = NULL; NVMeQueuePair *q; uint64_t prp_list_iova; + size_t bytes; q = g_try_new0(NVMeQueuePair, 1); if (!q) { return NULL; } - q->prp_list_pages = qemu_try_memalign(s->page_size, - s->page_size * NVME_NUM_REQS); + trace_nvme_create_queue_pair(idx, q, size, aio_context, + event_notifier_get_fd(s->irq_notifier)); + bytes = QEMU_ALIGN_UP(s->page_size * NVME_NUM_REQS, + qemu_real_host_page_size); + q->prp_list_pages = qemu_try_memalign(qemu_real_host_page_size, bytes); if (!q->prp_list_pages) { goto fail; } - memset(q->prp_list_pages, 0, s->page_size * NVME_NUM_REQS); + memset(q->prp_list_pages, 0, bytes); qemu_mutex_init(&q->lock); q->s = s; q->index = idx; qemu_co_queue_init(&q->free_req_queue); q->completion_bh = aio_bh_new(aio_context, nvme_process_completion_bh, q); - r = qemu_vfio_dma_map(s->vfio, q->prp_list_pages, - s->page_size * NVME_NUM_REQS, + r = qemu_vfio_dma_map(s->vfio, q->prp_list_pages, bytes, false, &prp_list_iova); if (r) { goto fail; @@ -243,16 +251,12 @@ static NVMeQueuePair *nvme_create_queue_pair(BDRVNVMeState *s, req->prp_list_iova = prp_list_iova + i * s->page_size; } - nvme_init_queue(s, &q->sq, size, NVME_SQ_ENTRY_BYTES, &local_err); - if (local_err) { - error_propagate(errp, local_err); + if (!nvme_init_queue(s, &q->sq, size, NVME_SQ_ENTRY_BYTES, errp)) { goto fail; } q->sq.doorbell = &s->doorbells[idx * s->doorbell_scale].sq_tail; - nvme_init_queue(s, &q->cq, size, NVME_CQ_ENTRY_BYTES, &local_err); - if (local_err) { - error_propagate(errp, local_err); + if (!nvme_init_queue(s, &q->cq, size, NVME_CQ_ENTRY_BYTES, errp)) { goto fail; } q->cq.doorbell = &s->doorbells[idx * s->doorbell_scale].cq_head; @@ -292,7 +296,7 @@ static NVMeRequest *nvme_get_free_req(NVMeQueuePair *q) while (q->free_req_head == -1) { if (qemu_in_coroutine()) { - trace_nvme_free_req_queue_wait(q); + trace_nvme_free_req_queue_wait(q->s, q->index); qemu_co_queue_wait(&q->free_req_queue, &q->lock); } else { qemu_mutex_unlock(&q->lock); @@ -399,8 +403,8 @@ static bool nvme_process_completion(NVMeQueuePair *q) } cid = le16_to_cpu(c->cid); if (cid == 0 || cid > NVME_QUEUE_SIZE) { - fprintf(stderr, "Unexpected CID in completion queue: %" PRIu32 "\n", - cid); + warn_report("NVMe: Unexpected CID in completion queue: %"PRIu32", " + "queue size: %u", cid, NVME_QUEUE_SIZE); continue; } trace_nvme_complete_command(s, q->index, cid); @@ -465,7 +469,7 @@ static void nvme_submit_command(NVMeQueuePair *q, NVMeRequest *req, assert(!req->cb); req->cb = cb; req->opaque = opaque; - cmd->cid = cpu_to_le32(req->cid); + cmd->cid = cpu_to_le16(req->cid); trace_nvme_submit_command(q->s, q->index, req->cid); nvme_trace_command(cmd); @@ -479,16 +483,17 @@ static void nvme_submit_command(NVMeQueuePair *q, NVMeRequest *req, qemu_mutex_unlock(&q->lock); } -static void nvme_cmd_sync_cb(void *opaque, int ret) +static void nvme_admin_cmd_sync_cb(void *opaque, int ret) { int *pret = opaque; *pret = ret; aio_wait_kick(); } -static int nvme_cmd_sync(BlockDriverState *bs, NVMeQueuePair *q, - NvmeCmd *cmd) +static int nvme_admin_cmd_sync(BlockDriverState *bs, NvmeCmd *cmd) { + BDRVNVMeState *s = bs->opaque; + NVMeQueuePair *q = s->queues[INDEX_ADMIN]; AioContext *aio_context = bdrv_get_aio_context(bs); NVMeRequest *req; int ret = -EINPROGRESS; @@ -496,15 +501,17 @@ static int nvme_cmd_sync(BlockDriverState *bs, NVMeQueuePair *q, if (!req) { return -EBUSY; } - nvme_submit_command(q, req, cmd, nvme_cmd_sync_cb, &ret); + nvme_submit_command(q, req, cmd, nvme_admin_cmd_sync_cb, &ret); AIO_WAIT_WHILE(aio_context, ret == -EINPROGRESS); return ret; } -static void nvme_identify(BlockDriverState *bs, int namespace, Error **errp) +/* Returns true on success, false on failure. */ +static bool nvme_identify(BlockDriverState *bs, int namespace, Error **errp) { BDRVNVMeState *s = bs->opaque; + bool ret = false; union { NvmeIdCtrl ctrl; NvmeIdNs ns; @@ -517,21 +524,22 @@ static void nvme_identify(BlockDriverState *bs, int namespace, Error **errp) .opcode = NVME_ADM_CMD_IDENTIFY, .cdw10 = cpu_to_le32(0x1), }; + size_t id_size = QEMU_ALIGN_UP(sizeof(*id), qemu_real_host_page_size); - id = qemu_try_memalign(s->page_size, sizeof(*id)); + id = qemu_try_memalign(qemu_real_host_page_size, id_size); if (!id) { error_setg(errp, "Cannot allocate buffer for identify response"); goto out; } - r = qemu_vfio_dma_map(s->vfio, id, sizeof(*id), true, &iova); + r = qemu_vfio_dma_map(s->vfio, id, id_size, true, &iova); if (r) { error_setg(errp, "Cannot map buffer for DMA"); goto out; } - memset(id, 0, sizeof(*id)); + memset(id, 0, id_size); cmd.dptr.prp1 = cpu_to_le64(iova); - if (nvme_cmd_sync(bs, s->queues[INDEX_ADMIN], &cmd)) { + if (nvme_admin_cmd_sync(bs, &cmd)) { error_setg(errp, "Failed to identify controller"); goto out; } @@ -551,10 +559,10 @@ static void nvme_identify(BlockDriverState *bs, int namespace, Error **errp) s->supports_write_zeroes = !!(oncs & NVME_ONCS_WRITE_ZEROES); s->supports_discard = !!(oncs & NVME_ONCS_DSM); - memset(id, 0, sizeof(*id)); + memset(id, 0, id_size); cmd.cdw10 = 0; cmd.nsid = cpu_to_le32(namespace); - if (nvme_cmd_sync(bs, s->queues[INDEX_ADMIN], &cmd)) { + if (nvme_admin_cmd_sync(bs, &cmd)) { error_setg(errp, "Failed to identify namespace"); goto out; } @@ -581,10 +589,13 @@ static void nvme_identify(BlockDriverState *bs, int namespace, Error **errp) goto out; } + ret = true; s->blkshift = lbaf->ds; out: qemu_vfio_dma_unmap(s->vfio, id); qemu_vfree(id); + + return ret; } static bool nvme_poll_queue(NVMeQueuePair *q) @@ -594,6 +605,7 @@ static bool nvme_poll_queue(NVMeQueuePair *q) const size_t cqe_offset = q->cq.head * NVME_CQ_ENTRY_BYTES; NvmeCqe *cqe = (NvmeCqe *)&q->cq.queue[cqe_offset]; + trace_nvme_poll_queue(q->s, q->index); /* * Do an early check for completions. q->lock isn't needed because * nvme_process_completion() only runs in the event loop thread and @@ -618,7 +630,7 @@ static bool nvme_poll_queues(BDRVNVMeState *s) bool progress = false; int i; - for (i = 0; i < s->nr_queues; i++) { + for (i = 0; i < s->queue_count; i++) { if (nvme_poll_queue(s->queues[i])) { progress = true; } @@ -639,11 +651,12 @@ static void nvme_handle_event(EventNotifier *n) static bool nvme_add_io_queue(BlockDriverState *bs, Error **errp) { BDRVNVMeState *s = bs->opaque; - int n = s->nr_queues; + unsigned n = s->queue_count; NVMeQueuePair *q; NvmeCmd cmd; - int queue_size = NVME_QUEUE_SIZE; + unsigned queue_size = NVME_QUEUE_SIZE; + assert(n <= UINT16_MAX); q = nvme_create_queue_pair(s, bdrv_get_aio_context(bs), n, queue_size, errp); if (!q) { @@ -652,26 +665,26 @@ static bool nvme_add_io_queue(BlockDriverState *bs, Error **errp) cmd = (NvmeCmd) { .opcode = NVME_ADM_CMD_CREATE_CQ, .dptr.prp1 = cpu_to_le64(q->cq.iova), - .cdw10 = cpu_to_le32(((queue_size - 1) << 16) | (n & 0xFFFF)), - .cdw11 = cpu_to_le32(0x3), + .cdw10 = cpu_to_le32(((queue_size - 1) << 16) | n), + .cdw11 = cpu_to_le32(NVME_CQ_IEN | NVME_CQ_PC), }; - if (nvme_cmd_sync(bs, s->queues[INDEX_ADMIN], &cmd)) { - error_setg(errp, "Failed to create CQ io queue [%d]", n); + if (nvme_admin_cmd_sync(bs, &cmd)) { + error_setg(errp, "Failed to create CQ io queue [%u]", n); goto out_error; } cmd = (NvmeCmd) { .opcode = NVME_ADM_CMD_CREATE_SQ, .dptr.prp1 = cpu_to_le64(q->sq.iova), - .cdw10 = cpu_to_le32(((queue_size - 1) << 16) | (n & 0xFFFF)), - .cdw11 = cpu_to_le32(0x1 | (n << 16)), + .cdw10 = cpu_to_le32(((queue_size - 1) << 16) | n), + .cdw11 = cpu_to_le32(NVME_SQ_PC | (n << 16)), }; - if (nvme_cmd_sync(bs, s->queues[INDEX_ADMIN], &cmd)) { - error_setg(errp, "Failed to create SQ io queue [%d]", n); + if (nvme_admin_cmd_sync(bs, &cmd)) { + error_setg(errp, "Failed to create SQ io queue [%u]", n); goto out_error; } s->queues = g_renew(NVMeQueuePair *, s->queues, n + 1); s->queues[n] = q; - s->nr_queues++; + s->queue_count++; return true; out_error: nvme_free_queue_pair(q); @@ -684,7 +697,6 @@ static bool nvme_poll_cb(void *opaque) BDRVNVMeState *s = container_of(e, BDRVNVMeState, irq_notifier[MSIX_SHARED_IRQ_IDX]); - trace_nvme_poll_cb(s); return nvme_poll_queues(s); } @@ -692,12 +704,12 @@ static int nvme_init(BlockDriverState *bs, const char *device, int namespace, Error **errp) { BDRVNVMeState *s = bs->opaque; + NVMeQueuePair *q; AioContext *aio_context = bdrv_get_aio_context(bs); int ret; uint64_t cap; uint64_t timeout_ms; uint64_t deadline, now; - Error *local_err = NULL; volatile NvmeBar *regs = NULL; qemu_co_mutex_init(&s->dma_map_lock); @@ -727,15 +739,29 @@ static int nvme_init(BlockDriverState *bs, const char *device, int namespace, * Initialization". */ cap = le64_to_cpu(regs->cap); + trace_nvme_controller_capability_raw(cap); + trace_nvme_controller_capability("Maximum Queue Entries Supported", + 1 + NVME_CAP_MQES(cap)); + trace_nvme_controller_capability("Contiguous Queues Required", + NVME_CAP_CQR(cap)); + trace_nvme_controller_capability("Doorbell Stride", + 2 << (2 + NVME_CAP_DSTRD(cap))); + trace_nvme_controller_capability("Subsystem Reset Supported", + NVME_CAP_NSSRS(cap)); + trace_nvme_controller_capability("Memory Page Size Minimum", + 1 << (12 + NVME_CAP_MPSMIN(cap))); + trace_nvme_controller_capability("Memory Page Size Maximum", + 1 << (12 + NVME_CAP_MPSMAX(cap))); if (!NVME_CAP_CSS(cap)) { error_setg(errp, "Device doesn't support NVMe command set"); ret = -EINVAL; goto out; } - s->page_size = MAX(4096, 1 << NVME_CAP_MPSMIN(cap)); + s->page_size = 1u << (12 + NVME_CAP_MPSMIN(cap)); s->doorbell_scale = (4 << NVME_CAP_DSTRD(cap)) / sizeof(uint32_t); bs->bl.opt_mem_alignment = s->page_size; + bs->bl.request_alignment = s->page_size; timeout_ms = MIN(500 * NVME_CAP_TO(cap), 30000); /* Reset device to get a clean state. */ @@ -752,8 +778,10 @@ static int nvme_init(BlockDriverState *bs, const char *device, int namespace, } } - s->doorbells = qemu_vfio_pci_map_bar(s->vfio, 0, sizeof(NvmeBar), - NVME_DOORBELL_SIZE, PROT_WRITE, errp); + s->bar0_wo_map = qemu_vfio_pci_map_bar(s->vfio, 0, 0, + sizeof(NvmeBar) + NVME_DOORBELL_SIZE, + PROT_WRITE, errp); + s->doorbells = (void *)((uintptr_t)s->bar0_wo_map + sizeof(NvmeBar)); if (!s->doorbells) { ret = -EINVAL; goto out; @@ -761,19 +789,18 @@ static int nvme_init(BlockDriverState *bs, const char *device, int namespace, /* Set up admin queue. */ s->queues = g_new(NVMeQueuePair *, 1); - s->queues[INDEX_ADMIN] = nvme_create_queue_pair(s, aio_context, 0, - NVME_QUEUE_SIZE, - errp); - if (!s->queues[INDEX_ADMIN]) { + q = nvme_create_queue_pair(s, aio_context, 0, NVME_QUEUE_SIZE, errp); + if (!q) { ret = -EINVAL; goto out; } - s->nr_queues = 1; - QEMU_BUILD_BUG_ON(NVME_QUEUE_SIZE & 0xF000); - regs->aqa = cpu_to_le32((NVME_QUEUE_SIZE << AQA_ACQS_SHIFT) | - (NVME_QUEUE_SIZE << AQA_ASQS_SHIFT)); - regs->asq = cpu_to_le64(s->queues[INDEX_ADMIN]->sq.iova); - regs->acq = cpu_to_le64(s->queues[INDEX_ADMIN]->cq.iova); + s->queues[INDEX_ADMIN] = q; + s->queue_count = 1; + QEMU_BUILD_BUG_ON((NVME_QUEUE_SIZE - 1) & 0xF000); + regs->aqa = cpu_to_le32(((NVME_QUEUE_SIZE - 1) << AQA_ACQS_SHIFT) | + ((NVME_QUEUE_SIZE - 1) << AQA_ASQS_SHIFT)); + regs->asq = cpu_to_le64(q->sq.iova); + regs->acq = cpu_to_le64(q->cq.iova); /* After setting up all control registers we can enable device now. */ regs->cc = cpu_to_le32((ctz32(NVME_CQ_ENTRY_BYTES) << CC_IOCQES_SHIFT) | @@ -801,9 +828,7 @@ static int nvme_init(BlockDriverState *bs, const char *device, int namespace, &s->irq_notifier[MSIX_SHARED_IRQ_IDX], false, nvme_handle_event, nvme_poll_cb); - nvme_identify(bs, namespace, &local_err); - if (local_err) { - error_propagate(errp, local_err); + if (!nvme_identify(bs, namespace, errp)) { ret = -EIO; goto out; } @@ -869,7 +894,7 @@ static int nvme_enable_disable_write_cache(BlockDriverState *bs, bool enable, .cdw11 = cpu_to_le32(enable ? 0x01 : 0x00), }; - ret = nvme_cmd_sync(bs, s->queues[INDEX_ADMIN], &cmd); + ret = nvme_admin_cmd_sync(bs, &cmd); if (ret) { error_setg(errp, "Failed to configure NVMe write cache"); } @@ -878,10 +903,9 @@ static int nvme_enable_disable_write_cache(BlockDriverState *bs, bool enable, static void nvme_close(BlockDriverState *bs) { - int i; BDRVNVMeState *s = bs->opaque; - for (i = 0; i < s->nr_queues; ++i) { + for (unsigned i = 0; i < s->queue_count; ++i) { nvme_free_queue_pair(s->queues[i]); } g_free(s->queues); @@ -889,8 +913,8 @@ static void nvme_close(BlockDriverState *bs) &s->irq_notifier[MSIX_SHARED_IRQ_IDX], false, NULL, NULL); event_notifier_cleanup(&s->irq_notifier[MSIX_SHARED_IRQ_IDX]); - qemu_vfio_pci_unmap_bar(s->vfio, 0, (void *)s->doorbells, - sizeof(NvmeBar), NVME_DOORBELL_SIZE); + qemu_vfio_pci_unmap_bar(s->vfio, 0, s->bar0_wo_map, + 0, sizeof(NvmeBar) + NVME_DOORBELL_SIZE); qemu_vfio_close(s->vfio); g_free(s->device); @@ -994,11 +1018,12 @@ static coroutine_fn int nvme_cmd_map_qiov(BlockDriverState *bs, NvmeCmd *cmd, for (i = 0; i < qiov->niov; ++i) { bool retry = true; uint64_t iova; + size_t len = QEMU_ALIGN_UP(qiov->iov[i].iov_len, + qemu_real_host_page_size); try_map: r = qemu_vfio_dma_map(s->vfio, qiov->iov[i].iov_base, - qiov->iov[i].iov_len, - true, &iova); + len, true, &iova); if (r == -ENOMEM && retry) { retry = false; trace_nvme_dma_flush_queue_wait(s); @@ -1106,7 +1131,7 @@ static coroutine_fn int nvme_co_prw_aligned(BlockDriverState *bs, }; trace_nvme_prw_aligned(s, is_write, offset, bytes, flags, qiov->niov); - assert(s->nr_queues > 1); + assert(s->queue_count > 1); req = nvme_get_free_req(ioq); assert(req); @@ -1142,8 +1167,9 @@ static inline bool nvme_qiov_aligned(BlockDriverState *bs, BDRVNVMeState *s = bs->opaque; for (i = 0; i < qiov->niov; ++i) { - if (!QEMU_PTR_IS_ALIGNED(qiov->iov[i].iov_base, s->page_size) || - !QEMU_IS_ALIGNED(qiov->iov[i].iov_len, s->page_size)) { + if (!QEMU_PTR_IS_ALIGNED(qiov->iov[i].iov_base, + qemu_real_host_page_size) || + !QEMU_IS_ALIGNED(qiov->iov[i].iov_len, qemu_real_host_page_size)) { trace_nvme_qiov_unaligned(qiov, i, qiov->iov[i].iov_base, qiov->iov[i].iov_len, s->page_size); return false; @@ -1159,7 +1185,7 @@ static int nvme_co_prw(BlockDriverState *bs, uint64_t offset, uint64_t bytes, int r; uint8_t *buf = NULL; QEMUIOVector local_qiov; - + size_t len = QEMU_ALIGN_UP(bytes, qemu_real_host_page_size); assert(QEMU_IS_ALIGNED(offset, s->page_size)); assert(QEMU_IS_ALIGNED(bytes, s->page_size)); assert(bytes <= s->max_transfer); @@ -1169,7 +1195,7 @@ static int nvme_co_prw(BlockDriverState *bs, uint64_t offset, uint64_t bytes, } s->stats.unaligned_accesses++; trace_nvme_prw_buffered(s, offset, bytes, qiov->niov, is_write); - buf = qemu_try_memalign(s->page_size, bytes); + buf = qemu_try_memalign(qemu_real_host_page_size, len); if (!buf) { return -ENOMEM; @@ -1216,7 +1242,7 @@ static coroutine_fn int nvme_co_flush(BlockDriverState *bs) .ret = -EINPROGRESS, }; - assert(s->nr_queues > 1); + assert(s->queue_count > 1); req = nvme_get_free_req(ioq); assert(req); nvme_submit_command(ioq, req, &cmd, nvme_rw_cb, &data); @@ -1268,7 +1294,7 @@ static coroutine_fn int nvme_co_pwrite_zeroes(BlockDriverState *bs, cmd.cdw12 = cpu_to_le32(cdw12); trace_nvme_write_zeroes(s, offset, bytes, flags); - assert(s->nr_queues > 1); + assert(s->queue_count > 1); req = nvme_get_free_req(ioq); assert(req); @@ -1311,7 +1337,7 @@ static int coroutine_fn nvme_co_pdiscard(BlockDriverState *bs, return -ENOTSUP; } - assert(s->nr_queues > 1); + assert(s->queue_count > 1); buf = qemu_try_memalign(s->page_size, s->page_size); if (!buf) { @@ -1391,7 +1417,7 @@ static void nvme_detach_aio_context(BlockDriverState *bs) { BDRVNVMeState *s = bs->opaque; - for (int i = 0; i < s->nr_queues; i++) { + for (unsigned i = 0; i < s->queue_count; i++) { NVMeQueuePair *q = s->queues[i]; qemu_bh_delete(q->completion_bh); @@ -1412,7 +1438,7 @@ static void nvme_attach_aio_context(BlockDriverState *bs, aio_set_event_notifier(new_context, &s->irq_notifier[MSIX_SHARED_IRQ_IDX], false, nvme_handle_event, nvme_poll_cb); - for (int i = 0; i < s->nr_queues; i++) { + for (unsigned i = 0; i < s->queue_count; i++) { NVMeQueuePair *q = s->queues[i]; q->completion_bh = @@ -1429,11 +1455,10 @@ static void nvme_aio_plug(BlockDriverState *bs) static void nvme_aio_unplug(BlockDriverState *bs) { - int i; BDRVNVMeState *s = bs->opaque; assert(s->plugged); s->plugged = false; - for (i = INDEX_IO(0); i < s->nr_queues; i++) { + for (unsigned i = INDEX_IO(0); i < s->queue_count; i++) { NVMeQueuePair *q = s->queues[i]; qemu_mutex_lock(&q->lock); nvme_kick(q); diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index 485b4cb92e..bd0597842f 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -2010,14 +2010,17 @@ static int zero_in_l2_slice(BlockDriverState *bs, uint64_t offset, continue; } + /* First update L2 entries */ qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_slice); - if (unmap) { - qcow2_free_any_cluster(bs, old_l2_entry, QCOW2_DISCARD_REQUEST); - } set_l2_entry(s, l2_slice, l2_index + i, new_l2_entry); if (has_subclusters(s)) { set_l2_bitmap(s, l2_slice, l2_index + i, new_l2_bitmap); } + + /* Then decrease the refcount */ + if (unmap) { + qcow2_free_any_cluster(bs, old_l2_entry, QCOW2_DISCARD_REQUEST); + } } qcow2_cache_put(s->l2_table_cache, (void **) &l2_slice); diff --git a/block/trace-events b/block/trace-events index 0e351c3fa3..8368f4acb0 100644 --- a/block/trace-events +++ b/block/trace-events @@ -134,25 +134,29 @@ qed_aio_write_postfill(void *s, void *acb, uint64_t start, size_t len, uint64_t qed_aio_write_main(void *s, void *acb, int ret, uint64_t offset, size_t len) "s %p acb %p ret %d offset %"PRIu64" len %zu" # nvme.c -nvme_kick(void *s, int queue) "s %p queue %d" +nvme_controller_capability_raw(uint64_t value) "0x%08"PRIx64 +nvme_controller_capability(const char *desc, uint64_t value) "%s: %"PRIu64 +nvme_kick(void *s, unsigned q_index) "s %p q #%u" nvme_dma_flush_queue_wait(void *s) "s %p" nvme_error(int cmd_specific, int sq_head, int sqid, int cid, int status) "cmd_specific %d sq_head %d sqid %d cid %d status 0x%x" -nvme_process_completion(void *s, int index, int inflight) "s %p queue %d inflight %d" -nvme_process_completion_queue_plugged(void *s, int index) "s %p queue %d" -nvme_complete_command(void *s, int index, int cid) "s %p queue %d cid %d" -nvme_submit_command(void *s, int index, int cid) "s %p queue %d cid %d" +nvme_process_completion(void *s, unsigned q_index, int inflight) "s %p q #%u inflight %d" +nvme_process_completion_queue_plugged(void *s, unsigned q_index) "s %p q #%u" +nvme_complete_command(void *s, unsigned q_index, int cid) "s %p q #%u cid %d" +nvme_submit_command(void *s, unsigned q_index, int cid) "s %p q #%u cid %d" nvme_submit_command_raw(int c0, int c1, int c2, int c3, int c4, int c5, int c6, int c7) "%02x %02x %02x %02x %02x %02x %02x %02x" nvme_handle_event(void *s) "s %p" -nvme_poll_cb(void *s) "s %p" -nvme_prw_aligned(void *s, int is_write, uint64_t offset, uint64_t bytes, int flags, int niov) "s %p is_write %d offset %"PRId64" bytes %"PRId64" flags %d niov %d" -nvme_write_zeroes(void *s, uint64_t offset, uint64_t bytes, int flags) "s %p offset %"PRId64" bytes %"PRId64" flags %d" +nvme_poll_queue(void *s, unsigned q_index) "s %p q #%u" +nvme_prw_aligned(void *s, int is_write, uint64_t offset, uint64_t bytes, int flags, int niov) "s %p is_write %d offset 0x%"PRIx64" bytes %"PRId64" flags %d niov %d" +nvme_write_zeroes(void *s, uint64_t offset, uint64_t bytes, int flags) "s %p offset 0x%"PRIx64" bytes %"PRId64" flags %d" nvme_qiov_unaligned(const void *qiov, int n, void *base, size_t size, int align) "qiov %p n %d base %p size 0x%zx align 0x%x" -nvme_prw_buffered(void *s, uint64_t offset, uint64_t bytes, int niov, int is_write) "s %p offset %"PRId64" bytes %"PRId64" niov %d is_write %d" -nvme_rw_done(void *s, int is_write, uint64_t offset, uint64_t bytes, int ret) "s %p is_write %d offset %"PRId64" bytes %"PRId64" ret %d" -nvme_dsm(void *s, uint64_t offset, uint64_t bytes) "s %p offset %"PRId64" bytes %"PRId64"" -nvme_dsm_done(void *s, uint64_t offset, uint64_t bytes, int ret) "s %p offset %"PRId64" bytes %"PRId64" ret %d" +nvme_prw_buffered(void *s, uint64_t offset, uint64_t bytes, int niov, int is_write) "s %p offset 0x%"PRIx64" bytes %"PRId64" niov %d is_write %d" +nvme_rw_done(void *s, int is_write, uint64_t offset, uint64_t bytes, int ret) "s %p is_write %d offset 0x%"PRIx64" bytes %"PRId64" ret %d" +nvme_dsm(void *s, uint64_t offset, uint64_t bytes) "s %p offset 0x%"PRIx64" bytes %"PRId64"" +nvme_dsm_done(void *s, uint64_t offset, uint64_t bytes, int ret) "s %p offset 0x%"PRIx64" bytes %"PRId64" ret %d" nvme_dma_map_flush(void *s) "s %p" -nvme_free_req_queue_wait(void *q) "q %p" +nvme_free_req_queue_wait(void *s, unsigned q_index) "s %p q #%u" +nvme_create_queue_pair(unsigned q_index, void *q, unsigned size, void *aio_context, int fd) "index %u q %p size %u aioctx %p fd %d" +nvme_free_queue_pair(unsigned q_index, void *q) "index %u q %p" nvme_cmd_map_qiov(void *s, void *cmd, void *req, void *qiov, int entries) "s %p cmd %p req %p qiov %p entries %d" nvme_cmd_map_qiov_pages(void *s, int i, uint64_t page) "s %p page[%d] 0x%"PRIx64 nvme_cmd_map_qiov_iov(void *s, int i, void *page, int pages) "s %p iov[%d] %p pages %d" diff --git a/docs/meson.build b/docs/meson.build index bf8204a08f..ebd85d59f9 100644 --- a/docs/meson.build +++ b/docs/meson.build @@ -60,6 +60,7 @@ if build_docs 'tools': { 'qemu-img.1': (have_tools ? 'man1' : ''), 'qemu-nbd.8': (have_tools ? 'man8' : ''), + 'qemu-pr-helper.8': (have_tools ? 'man8' : ''), 'qemu-trace-stap.1': (config_host.has_key('CONFIG_TRACE_SYSTEMTAP') ? 'man1' : ''), 'virtfs-proxy-helper.1': (have_virtfs_proxy_helper ? 'man1' : ''), 'virtiofsd.1': (have_virtiofsd ? 'man1' : ''), diff --git a/docs/system/arm/aspeed.rst b/docs/system/arm/aspeed.rst index b7a176659c..690bada784 100644 --- a/docs/system/arm/aspeed.rst +++ b/docs/system/arm/aspeed.rst @@ -47,6 +47,7 @@ Supported devices * GPIO Controller (Master only) * UART * Ethernet controllers + * Front LEDs (PCA9552 on I2C bus) Missing devices diff --git a/docs/system/arm/raspi.rst b/docs/system/arm/raspi.rst new file mode 100644 index 0000000000..922fe375a6 --- /dev/null +++ b/docs/system/arm/raspi.rst @@ -0,0 +1,43 @@ +Raspberry Pi boards (``raspi0``, ``raspi1ap``, ``raspi2b``, ``raspi3ap``, ``raspi3b``) +====================================================================================== + + +QEMU provides models of the following Raspberry Pi boards: + +``raspi0`` and ``raspi1ap`` + ARM1176JZF-S core, 512 MiB of RAM +``raspi2b`` + Cortex-A7 (4 cores), 1 GiB of RAM +``raspi3ap`` + Cortex-A53 (4 cores), 512 MiB of RAM +``raspi3b`` + Cortex-A53 (4 cores), 1 GiB of RAM + + +Implemented devices +------------------- + + * ARM1176JZF-S, Cortex-A7 or Cortex-A53 CPU + * Interrupt controller + * DMA controller + * Clock and reset controller (CPRMAN) + * System Timer + * GPIO controller + * Serial ports (BCM2835 AUX - 16550 based - and PL011) + * Random Number Generator (RNG) + * Frame Buffer + * USB host (USBH) + * GPIO controller + * SD/MMC host controller + * SoC thermal sensor + * USB2 host controller (DWC2 and MPHI) + * MailBox controller (MBOX) + * VideoCore firmware (property) + + +Missing devices +--------------- + + * Peripheral SPI controller (SPI) + * Analog to Digital Converter (ADC) + * Pulse Width Modulation (PWM) diff --git a/docs/system/arm/xscale.rst b/docs/system/arm/xscale.rst index 89ec93e904..d2d5949e10 100644 --- a/docs/system/arm/xscale.rst +++ b/docs/system/arm/xscale.rst @@ -1,16 +1,22 @@ -Sharp XScale-based PDA models (``akita``, ``borzoi``, ``spitz``, ``terrier``) -============================================================================= +Sharp XScale-based PDA models (``akita``, ``borzoi``, ``spitz``, ``terrier``, ``tosa``) +======================================================================================= -The XScale-based clamshell PDA models (\"Spitz\", \"Akita\", \"Borzoi\" -and \"Terrier\") emulation includes the following peripherals: +The Sharp Zaurus are PDAs based on XScale, able to run Linux ('SL series'). -- Intel PXA270 System-on-chip (ARMv5TE core) +The SL-6000 (\"Tosa\"), released in 2005, uses a PXA255 System-on-chip. -- NAND Flash memory +The SL-C3000 (\"Spitz\"), SL-C1000 (\"Akita\"), SL-C3100 (\"Borzoi\") and +SL-C3200 (\"Terrier\") use a PXA270. + +The clamshell PDA models emulation includes the following peripherals: + +- Intel PXA255/PXA270 System-on-chip (ARMv5TE core) + +- NAND Flash memory - not in \"Tosa\" - IBM/Hitachi DSCM microdrive in a PXA PCMCIA slot - not in \"Akita\" -- On-chip OHCI USB controller +- On-chip OHCI USB controller - not in \"Tosa\" - On-chip LCD controller diff --git a/docs/cpu-hotplug.rst b/docs/system/cpu-hotplug.rst index d0b06403f1..d0b06403f1 100644 --- a/docs/cpu-hotplug.rst +++ b/docs/system/cpu-hotplug.rst diff --git a/docs/system/deprecated.rst b/docs/system/deprecated.rst index d98464098f..565389697e 100644 --- a/docs/system/deprecated.rst +++ b/docs/system/deprecated.rst @@ -346,6 +346,13 @@ This machine has been renamed ``fuloong2e``. These machine types are very old and likely can not be used for live migration from old QEMU versions anymore. A newer machine type should be used instead. +Raspberry Pi ``raspi2`` and ``raspi3`` machines (since 5.2) +''''''''''''''''''''''''''''''''''''''''''''''''''''''''''' + +The Raspberry Pi machines come in various models (A, A+, B, B+). To be able +to distinguish which model QEMU is implementing, the ``raspi2`` and ``raspi3`` +machines have been renamed ``raspi2b`` and ``raspi3b``. + Device options -------------- diff --git a/docs/microvm.rst b/docs/system/i386/microvm.rst index fcf41fc1f6..1675e37d3e 100644 --- a/docs/microvm.rst +++ b/docs/system/i386/microvm.rst @@ -1,6 +1,5 @@ -==================== -microvm Machine Type -==================== +'microvm' virtual platform (``microvm``) +======================================== ``microvm`` is a machine type inspired by ``Firecracker`` and constructed after its machine model. diff --git a/docs/system/i386/pc.rst b/docs/system/i386/pc.rst new file mode 100644 index 0000000000..d543c11a5c --- /dev/null +++ b/docs/system/i386/pc.rst @@ -0,0 +1,7 @@ +i440fx PC (``pc-i440fx``, ``pc``) +================================= + +Peripherals +~~~~~~~~~~~ + +.. include:: ../target-i386-desc.rst.inc diff --git a/docs/system/index.rst b/docs/system/index.rst index c0f685b818..e5a35817a2 100644 --- a/docs/system/index.rst +++ b/docs/system/index.rst @@ -21,6 +21,7 @@ Contents: monitor images net + virtio-net-failover usb ivshmem linuxboot @@ -28,6 +29,9 @@ Contents: tls gdb managed-startup + cpu-hotplug + virtio-pmem + pr-manager targets security deprecated diff --git a/docs/pr-manager.rst b/docs/system/pr-manager.rst index 9b1de198b1..b19a0c15e6 100644 --- a/docs/pr-manager.rst +++ b/docs/system/pr-manager.rst @@ -1,8 +1,8 @@ -====================================== +=============================== Persistent reservation managers -====================================== +=============================== -SCSI persistent Reservations allow restricting access to block devices +SCSI persistent reservations allow restricting access to block devices to specific initiators in a shared storage setup. When implementing clustering of virtual machines, it is a common requirement for virtual machines to send persistent reservation SCSI commands. However, @@ -50,39 +50,11 @@ Alternatively, using ``-blockdev``:: -blockdev node-name=hd,driver=raw,file.driver=host_device,file.filename=/dev/sdb,file.pr-manager=helper0 -device scsi-block,drive=hd ----------------------------------- -Invoking :program:`qemu-pr-helper` ----------------------------------- - -QEMU provides an implementation of the persistent reservation helper, -called :program:`qemu-pr-helper`. The helper should be started as a -system service and supports the following option: - --d, --daemon run in the background --q, --quiet decrease verbosity --v, --verbose increase verbosity --f, --pidfile=path PID file when running as a daemon --k, --socket=path path to the socket --T, --trace=trace-opts tracing options - -By default, the socket and PID file are placed in the runtime state -directory, for example :file:`/var/run/qemu-pr-helper.sock` and -:file:`/var/run/qemu-pr-helper.pid`. The PID file is not created -unless :option:`-d` is passed too. - -:program:`qemu-pr-helper` can also use the systemd socket activation -protocol. In this case, the systemd socket unit should specify a -Unix stream socket, like this:: - - [Socket] - ListenStream=/var/run/qemu-pr-helper.sock - -After connecting to the socket, :program:`qemu-pr-helper`` can optionally drop -root privileges, except for those capabilities that are needed for -its operation. To do this, add the following options: - --u, --user=user user to drop privileges to --g, --group=group group to drop privileges to +You will also need to ensure that the helper program +:command:`qemu-pr-helper` is running, and that it has been +set up to use the same socket filename as your QEMU commandline +specifies. See the qemu-pr-helper documentation or manpage for +further details. --------------------------------------------- Multipath devices and persistent reservations diff --git a/docs/system/target-arm.rst b/docs/system/target-arm.rst index a0d5c57799..bde4b8e044 100644 --- a/docs/system/target-arm.rst +++ b/docs/system/target-arm.rst @@ -90,6 +90,7 @@ undocumented; you can get a complete list by running arm/nuvoton arm/orangepi arm/palm + arm/raspi arm/xscale arm/collie arm/sx1 diff --git a/docs/system/target-i386.rst b/docs/system/target-i386.rst index 51be03d881..22ba5ce2c0 100644 --- a/docs/system/target-i386.rst +++ b/docs/system/target-i386.rst @@ -1,14 +1,23 @@ .. _QEMU-PC-System-emulator: -x86 (PC) System emulator ------------------------- +x86 System emulator +------------------- .. _pcsys_005fdevices: -Peripherals -~~~~~~~~~~~ +Board-specific documentation +~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -.. include:: target-i386-desc.rst.inc +.. + This table of contents should be kept sorted alphabetically + by the title text of each file, which isn't the same ordering + as an alphabetical sort by filename. + +.. toctree:: + :maxdepth: 1 + + i386/microvm + i386/pc .. include:: cpu-models-x86.rst.inc diff --git a/docs/virtio-net-failover.rst b/docs/system/virtio-net-failover.rst index 6002dc5d96..6002dc5d96 100644 --- a/docs/virtio-net-failover.rst +++ b/docs/system/virtio-net-failover.rst diff --git a/docs/system/virtio-pmem.rst b/docs/system/virtio-pmem.rst new file mode 100644 index 0000000000..c82ac06731 --- /dev/null +++ b/docs/system/virtio-pmem.rst @@ -0,0 +1,76 @@ + +=========== +virtio pmem +=========== + +This document explains the setup and usage of the virtio pmem device. +The virtio pmem device is a paravirtualized persistent memory device +on regular (i.e non-NVDIMM) storage. + +Usecase +------- + +Virtio pmem allows to bypass the guest page cache and directly use +host page cache. This reduces guest memory footprint as the host can +make efficient memory reclaim decisions under memory pressure. + +How does virtio-pmem compare to the nvdimm emulation? +----------------------------------------------------- + +NVDIMM emulation on regular (i.e. non-NVDIMM) host storage does not +persist the guest writes as there are no defined semantics in the device +specification. The virtio pmem device provides guest write persistence +on non-NVDIMM host storage. + +virtio pmem usage +----------------- + +A virtio pmem device backed by a memory-backend-file can be created on +the QEMU command line as in the following example:: + + -object memory-backend-file,id=mem1,share,mem-path=./virtio_pmem.img,size=4G + -device virtio-pmem-pci,memdev=mem1,id=nv1 + +where: + + - "object memory-backend-file,id=mem1,share,mem-path=<image>, size=<image size>" + creates a backend file with the specified size. + + - "device virtio-pmem-pci,id=nvdimm1,memdev=mem1" creates a virtio pmem + pci device whose storage is provided by above memory backend device. + +Multiple virtio pmem devices can be created if multiple pairs of "-object" +and "-device" are provided. + +Hotplug +------- + +Virtio pmem devices can be hotplugged via the QEMU monitor. First, the +memory backing has to be added via 'object_add'; afterwards, the virtio +pmem device can be added via 'device_add'. + +For example, the following commands add another 4GB virtio pmem device to +the guest:: + + (qemu) object_add memory-backend-file,id=mem2,share=on,mem-path=virtio_pmem2.img,size=4G + (qemu) device_add virtio-pmem-pci,id=virtio_pmem2,memdev=mem2 + +Guest Data Persistence +---------------------- + +Guest data persistence on non-NVDIMM requires guest userspace applications +to perform fsync/msync. This is different from a real nvdimm backend where +no additional fsync/msync is required. This is to persist guest writes in +host backing file which otherwise remains in host page cache and there is +risk of losing the data in case of power failure. + +With virtio pmem device, MAP_SYNC mmap flag is not supported. This provides +a hint to application to perform fsync for write persistence. + +Limitations +----------- + +- Real nvdimm device backend is not supported. +- virtio pmem hotunplug is not supported. +- ACPI NVDIMM features like regions/namespaces are not supported. +- ndctl command is not supported. diff --git a/docs/tools/conf.py b/docs/tools/conf.py index 9052d17d6d..4760d36ff2 100644 --- a/docs/tools/conf.py +++ b/docs/tools/conf.py @@ -22,6 +22,8 @@ man_pages = [ ['Fabrice Bellard'], 1), ('qemu-nbd', 'qemu-nbd', u'QEMU Disk Network Block Device Server', ['Anthony Liguori <anthony@codemonkey.ws>'], 8), + ('qemu-pr-helper', 'qemu-pr-helper', 'QEMU persistent reservation helper', + [], 8), ('qemu-trace-stap', 'qemu-trace-stap', u'QEMU SystemTap trace tool', [], 1), ('virtfs-proxy-helper', 'virtfs-proxy-helper', diff --git a/docs/tools/index.rst b/docs/tools/index.rst index 232ce9f3e4..b99f86c7c6 100644 --- a/docs/tools/index.rst +++ b/docs/tools/index.rst @@ -12,6 +12,7 @@ Contents: qemu-img qemu-nbd + qemu-pr-helper qemu-trace-stap virtfs-proxy-helper virtiofsd diff --git a/docs/tools/qemu-pr-helper.rst b/docs/tools/qemu-pr-helper.rst new file mode 100644 index 0000000000..ac036180ac --- /dev/null +++ b/docs/tools/qemu-pr-helper.rst @@ -0,0 +1,90 @@ +QEMU persistent reservation helper +================================== + +Synopsis +-------- + +**qemu-pr-helper** [*OPTION*] + +Description +----------- + +Implements the persistent reservation helper for QEMU. + +SCSI persistent reservations allow restricting access to block devices +to specific initiators in a shared storage setup. When implementing +clustering of virtual machines, it is a common requirement for virtual +machines to send persistent reservation SCSI commands. However, +the operating system restricts sending these commands to unprivileged +programs because incorrect usage can disrupt regular operation of the +storage fabric. QEMU's SCSI passthrough devices ``scsi-block`` +and ``scsi-generic`` support passing guest persistent reservation +requests to a privileged external helper program. :program:`qemu-pr-helper` +is that external helper; it creates a socket which QEMU can +connect to to communicate with it. + +If you want to run VMs in a setup like this, this helper should be +started as a system service, and you should read the QEMU manual +section on "persistent reservation managers" to find out how to +configure QEMU to connect to the socket created by +:program:`qemu-pr-helper`. + +After connecting to the socket, :program:`qemu-pr-helper` can +optionally drop root privileges, except for those capabilities that +are needed for its operation. + +:program:`qemu-pr-helper` can also use the systemd socket activation +protocol. In this case, the systemd socket unit should specify a +Unix stream socket, like this:: + + [Socket] + ListenStream=/var/run/qemu-pr-helper.sock + +Options +------- + +.. program:: qemu-pr-helper + +.. option:: -d, --daemon + + run in the background (and create a PID file) + +.. option:: -q, --quiet + + decrease verbosity + +.. option:: -v, --verbose + + increase verbosity + +.. option:: -f, --pidfile=PATH + + PID file when running as a daemon. By default the PID file + is created in the system runtime state directory, for example + :file:`/var/run/qemu-pr-helper.pid`. + +.. option:: -k, --socket=PATH + + path to the socket. By default the socket is created in + the system runtime state directory, for example + :file:`/var/run/qemu-pr-helper.sock`. + +.. option:: -T, --trace [[enable=]PATTERN][,events=FILE][,file=FILE] + + .. include:: ../qemu-option-trace.rst.inc + +.. option:: -u, --user=USER + + user to drop privileges to + +.. option:: -g, --group=GROUP + + group to drop privileges to + +.. option:: -h, --help + + Display a help message and exit. + +.. option:: -V, --version + + Display version information and exit. diff --git a/docs/virtio-pmem.rst b/docs/virtio-pmem.rst deleted file mode 100644 index 4bf5d00443..0000000000 --- a/docs/virtio-pmem.rst +++ /dev/null @@ -1,76 +0,0 @@ - -======================== -QEMU virtio pmem -======================== - - This document explains the setup and usage of the virtio pmem device - which is available since QEMU v4.1.0. - - The virtio pmem device is a paravirtualized persistent memory device - on regular (i.e non-NVDIMM) storage. - -Usecase --------- - - Virtio pmem allows to bypass the guest page cache and directly use - host page cache. This reduces guest memory footprint as the host can - make efficient memory reclaim decisions under memory pressure. - -o How does virtio-pmem compare to the nvdimm emulation supported by QEMU? - - NVDIMM emulation on regular (i.e. non-NVDIMM) host storage does not - persist the guest writes as there are no defined semantics in the device - specification. The virtio pmem device provides guest write persistence - on non-NVDIMM host storage. - -virtio pmem usage ------------------ - - A virtio pmem device backed by a memory-backend-file can be created on - the QEMU command line as in the following example:: - - -object memory-backend-file,id=mem1,share,mem-path=./virtio_pmem.img,size=4G - -device virtio-pmem-pci,memdev=mem1,id=nv1 - - where: - - - "object memory-backend-file,id=mem1,share,mem-path=<image>, size=<image size>" - creates a backend file with the specified size. - - - "device virtio-pmem-pci,id=nvdimm1,memdev=mem1" creates a virtio pmem - pci device whose storage is provided by above memory backend device. - - Multiple virtio pmem devices can be created if multiple pairs of "-object" - and "-device" are provided. - -Hotplug -------- - -Virtio pmem devices can be hotplugged via the QEMU monitor. First, the -memory backing has to be added via 'object_add'; afterwards, the virtio -pmem device can be added via 'device_add'. - -For example, the following commands add another 4GB virtio pmem device to -the guest:: - - (qemu) object_add memory-backend-file,id=mem2,share=on,mem-path=virtio_pmem2.img,size=4G - (qemu) device_add virtio-pmem-pci,id=virtio_pmem2,memdev=mem2 - -Guest Data Persistence ----------------------- - - Guest data persistence on non-NVDIMM requires guest userspace applications - to perform fsync/msync. This is different from a real nvdimm backend where - no additional fsync/msync is required. This is to persist guest writes in - host backing file which otherwise remains in host page cache and there is - risk of losing the data in case of power failure. - - With virtio pmem device, MAP_SYNC mmap flag is not supported. This provides - a hint to application to perform fsync for write persistence. - -Limitations ------------- -- Real nvdimm device backend is not supported. -- virtio pmem hotunplug is not supported. -- ACPI NVDIMM features like regions/namespaces are not supported. -- ndctl command is not supported. diff --git a/hw/arm/pxa2xx.c b/hw/arm/pxa2xx.c index 591776ba88..1a98f3bd5c 100644 --- a/hw/arm/pxa2xx.c +++ b/hw/arm/pxa2xx.c @@ -675,7 +675,7 @@ static void pxa2xx_ssp_write(void *opaque, hwaddr addr, if (value & SSCR0_MOD) printf("%s: Attempt to use network mode\n", __func__); if (s->enable && SSCR0_DSS(value) < 4) - printf("%s: Wrong data size: %i bits\n", __func__, + printf("%s: Wrong data size: %u bits\n", __func__, SSCR0_DSS(value)); if (!(value & SSCR0_SSE)) { s->sssr = 0; diff --git a/hw/arm/spitz.c b/hw/arm/spitz.c index 32bdeacfd3..772662f149 100644 --- a/hw/arm/spitz.c +++ b/hw/arm/spitz.c @@ -586,7 +586,7 @@ struct SpitzLCDTG { static void spitz_bl_update(SpitzLCDTG *s) { if (s->bl_power && s->bl_intensity) - zaurus_printf("LCD Backlight now at %i/63\n", s->bl_intensity); + zaurus_printf("LCD Backlight now at %u/63\n", s->bl_intensity); else zaurus_printf("LCD Backlight now off\n"); } diff --git a/hw/arm/tosa.c b/hw/arm/tosa.c index fe88ed89fe..66b244aeff 100644 --- a/hw/arm/tosa.c +++ b/hw/arm/tosa.c @@ -150,7 +150,7 @@ static void tosa_gpio_setup(PXA2xxState *cpu, static uint32_t tosa_ssp_tansfer(SSISlave *dev, uint32_t value) { - fprintf(stderr, "TG: %d %02x\n", value >> 5, value & 0x1f); + fprintf(stderr, "TG: %u %02x\n", value >> 5, value & 0x1f); return 0; } diff --git a/hw/core/qdev-properties-system.c b/hw/core/qdev-properties-system.c index b81a4e8d14..9d80a07d26 100644 --- a/hw/core/qdev-properties-system.c +++ b/hw/core/qdev-properties-system.c @@ -858,7 +858,7 @@ static void set_pci_host_devaddr(Object *obj, Visitor *v, const char *name, Property *prop = opaque; PCIHostDeviceAddress *addr = qdev_get_prop_ptr(dev, prop); char *str, *p; - const char *e; + char *e; unsigned long val; unsigned long dom = 0, bus = 0; unsigned int slot = 0, func = 0; @@ -873,23 +873,23 @@ static void set_pci_host_devaddr(Object *obj, Visitor *v, const char *name, } p = str; - if (qemu_strtoul(p, &e, 16, &val) < 0 || val > 0xffff || e == p) { - goto inval; - } - if (*e != ':') { + val = strtoul(p, &e, 16); + if (e == p || *e != ':') { goto inval; } bus = val; - p = (char *)e + 1; - if (qemu_strtoul(p, &e, 16, &val) < 0 || val > 0x1f || e == p) { + p = e + 1; + val = strtoul(p, &e, 16); + if (e == p) { goto inval; } if (*e == ':') { dom = bus; bus = val; - p = (char *)e + 1; - if (qemu_strtoul(p, &e, 16, &val) < 0 || val > 0x1f || e == p) { + p = e + 1; + val = strtoul(p, &e, 16); + if (e == p) { goto inval; } } @@ -898,13 +898,14 @@ static void set_pci_host_devaddr(Object *obj, Visitor *v, const char *name, if (*e != '.') { goto inval; } - p = (char *)e + 1; - if (qemu_strtoul(p, &e, 10, &val) < 0 || val > 7 || e == p) { + p = e + 1; + val = strtoul(p, &e, 10); + if (e == p) { goto inval; } func = val; - if (bus > 0xff) { + if (dom > 0xffff || bus > 0xff || slot > 0x1f || func > 7) { goto inval; } diff --git a/hw/intc/rx_icu.c b/hw/intc/rx_icu.c index 94e17a9dea..e5c01807b9 100644 --- a/hw/intc/rx_icu.c +++ b/hw/intc/rx_icu.c @@ -300,22 +300,20 @@ static const MemoryRegionOps icu_ops = { static void rxicu_realize(DeviceState *dev, Error **errp) { RXICUState *icu = RX_ICU(dev); - int i, j; + int i; if (icu->init_sense == NULL) { qemu_log_mask(LOG_GUEST_ERROR, "rx_icu: trigger-level property must be set."); return; } - for (i = j = 0; i < NR_IRQS; i++) { - if (icu->init_sense[j] == i) { - icu->src[i].sense = TRG_LEVEL; - if (j < icu->nr_sense) { - j++; - } - } else { - icu->src[i].sense = TRG_PEDGE; - } + + for (i = 0; i < NR_IRQS; i++) { + icu->src[i].sense = TRG_PEDGE; + } + for (i = 0; i < icu->nr_sense; i++) { + uint8_t irqno = icu->init_sense[i]; + icu->src[irqno].sense = TRG_LEVEL; } icu->req_irq = -1; } diff --git a/hw/net/e1000e_core.c b/hw/net/e1000e_core.c index d8b9e4b2f4..095c01ebc6 100644 --- a/hw/net/e1000e_core.c +++ b/hw/net/e1000e_core.c @@ -1596,13 +1596,13 @@ e1000e_write_packet_to_guest(E1000ECore *core, struct NetRxPkt *pkt, (const char *) &fcs_pad, e1000x_fcs_len(core->mac)); } } - desc_offset += desc_size; - if (desc_offset >= total_size) { - is_last = true; - } } else { /* as per intel docs; skip descriptors with null buf addr */ trace_e1000e_rx_null_descriptor(); } + desc_offset += desc_size; + if (desc_offset >= total_size) { + is_last = true; + } e1000e_write_rx_descr(core, desc, is_last ? core->rx_pkt : NULL, rss_info, do_ps ? ps_hdr_len : 0, &bastate.written); diff --git a/hw/vfio/common.c b/hw/vfio/common.c index c1fdbf17f2..6ff1daa763 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -311,7 +311,7 @@ bool vfio_mig_active(void) return true; } -static bool vfio_devices_all_stopped_and_saving(VFIOContainer *container) +static bool vfio_devices_all_saving(VFIOContainer *container) { VFIOGroup *group; VFIODevice *vbasedev; @@ -329,8 +329,11 @@ static bool vfio_devices_all_stopped_and_saving(VFIOContainer *container) return false; } - if ((migration->device_state & VFIO_DEVICE_STATE_SAVING) && - !(migration->device_state & VFIO_DEVICE_STATE_RUNNING)) { + if (migration->device_state & VFIO_DEVICE_STATE_SAVING) { + if ((vbasedev->pre_copy_dirty_page_tracking == ON_OFF_AUTO_OFF) + && (migration->device_state & VFIO_DEVICE_STATE_RUNNING)) { + return false; + } continue; } else { return false; @@ -1125,7 +1128,7 @@ static void vfio_listerner_log_sync(MemoryListener *listener, return; } - if (vfio_devices_all_stopped_and_saving(container)) { + if (vfio_devices_all_saving(container)) { vfio_sync_dirty_bitmap(container, section); } } diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c index 55261562d4..00daa50ed8 100644 --- a/hw/vfio/migration.c +++ b/hw/vfio/migration.c @@ -882,7 +882,7 @@ int vfio_migration_probe(VFIODevice *vbasedev, Error **errp) Error *local_err = NULL; int ret = -ENOTSUP; - if (!container->dirty_pages_supported) { + if (!vbasedev->enable_migration || !container->dirty_pages_supported) { goto add_blocker; } diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index 58c0ce8971..51dc373695 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -3182,6 +3182,9 @@ static void vfio_instance_init(Object *obj) static Property vfio_pci_dev_properties[] = { DEFINE_PROP_PCI_HOST_DEVADDR("host", VFIOPCIDevice, host), DEFINE_PROP_STRING("sysfsdev", VFIOPCIDevice, vbasedev.sysfsdev), + DEFINE_PROP_ON_OFF_AUTO("x-pre-copy-dirty-page-tracking", VFIOPCIDevice, + vbasedev.pre_copy_dirty_page_tracking, + ON_OFF_AUTO_ON), DEFINE_PROP_ON_OFF_AUTO("display", VFIOPCIDevice, display, ON_OFF_AUTO_OFF), DEFINE_PROP_UINT32("xres", VFIOPCIDevice, display_xres, 0), @@ -3194,6 +3197,8 @@ static Property vfio_pci_dev_properties[] = { VFIO_FEATURE_ENABLE_REQ_BIT, true), DEFINE_PROP_BIT("x-igd-opregion", VFIOPCIDevice, features, VFIO_FEATURE_ENABLE_IGD_OPREGION_BIT, false), + DEFINE_PROP_BOOL("x-enable-migration", VFIOPCIDevice, + vbasedev.enable_migration, false), DEFINE_PROP_BOOL("x-no-mmap", VFIOPCIDevice, vbasedev.no_mmap, false), DEFINE_PROP_BOOL("x-balloon-allowed", VFIOPCIDevice, vbasedev.ram_block_discard_allowed, false), diff --git a/include/block/nvme.h b/include/block/nvme.h index 8a46d9cf01..3e02d9ca98 100644 --- a/include/block/nvme.h +++ b/include/block/nvme.h @@ -501,6 +501,11 @@ typedef struct QEMU_PACKED NvmeCreateCq { #define NVME_CQ_FLAGS_PC(cq_flags) (cq_flags & 0x1) #define NVME_CQ_FLAGS_IEN(cq_flags) ((cq_flags >> 1) & 0x1) +enum NvmeFlagsCq { + NVME_CQ_PC = 1, + NVME_CQ_IEN = 2, +}; + typedef struct QEMU_PACKED NvmeCreateSq { uint8_t opcode; uint8_t flags; @@ -518,12 +523,13 @@ typedef struct QEMU_PACKED NvmeCreateSq { #define NVME_SQ_FLAGS_PC(sq_flags) (sq_flags & 0x1) #define NVME_SQ_FLAGS_QPRIO(sq_flags) ((sq_flags >> 1) & 0x3) -enum NvmeQueueFlags { - NVME_Q_PC = 1, - NVME_Q_PRIO_URGENT = 0, - NVME_Q_PRIO_HIGH = 1, - NVME_Q_PRIO_NORMAL = 2, - NVME_Q_PRIO_LOW = 3, +enum NvmeFlagsSq { + NVME_SQ_PC = 1, + + NVME_SQ_PRIO_URGENT = 0, + NVME_SQ_PRIO_HIGH = 1, + NVME_SQ_PRIO_NORMAL = 2, + NVME_SQ_PRIO_LOW = 3, }; typedef struct QEMU_PACKED NvmeIdentify { diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index baeb4dcff1..6141162d7a 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -123,12 +123,14 @@ typedef struct VFIODevice { bool needs_reset; bool no_mmap; bool ram_block_discard_allowed; + bool enable_migration; VFIODeviceOps *ops; unsigned int num_irqs; unsigned int num_regions; unsigned int flags; VFIOMigration *migration; Error *migration_blocker; + OnOffAuto pre_copy_dirty_page_tracking; } VFIODevice; struct VFIODeviceOps { diff --git a/include/net/net.h b/include/net/net.h index 897b2d7595..778fc787ca 100644 --- a/include/net/net.h +++ b/include/net/net.h @@ -199,6 +199,7 @@ extern const char *host_net_devices[]; /* from net.c */ int net_client_parse(QemuOptsList *opts_list, const char *str); +void show_netdevs(void); int net_init_clients(Error **errp); void net_check_clients(void); void net_cleanup(void); diff --git a/linux-user/arm/cpu_loop.c b/linux-user/arm/cpu_loop.c index 13629ee1f6..3d272b56ef 100644 --- a/linux-user/arm/cpu_loop.c +++ b/linux-user/arm/cpu_loop.c @@ -205,6 +205,24 @@ do_kernel_trap(CPUARMState *env) return 0; } +static bool insn_is_linux_bkpt(uint32_t opcode, bool is_thumb) +{ + /* + * Return true if this insn is one of the three magic UDF insns + * which the kernel treats as breakpoint insns. + */ + if (!is_thumb) { + return (opcode & 0x0fffffff) == 0x07f001f0; + } else { + /* + * Note that we get the two halves of the 32-bit T32 insn + * in the opposite order to the value the kernel uses in + * its undef_hook struct. + */ + return ((opcode & 0xffff) == 0xde01) || (opcode == 0xa000f7f0); + } +} + void cpu_loop(CPUARMState *env) { CPUState *cs = env_cpu(env); @@ -234,6 +252,16 @@ void cpu_loop(CPUARMState *env) /* FIXME - what to do if get_user() fails? */ get_user_code_u32(opcode, env->regs[15], env); + /* + * The Linux kernel treats some UDF patterns specially + * to use as breakpoints (instead of the architectural + * bkpt insn). These should trigger a SIGTRAP rather + * than SIGILL. + */ + if (insn_is_linux_bkpt(opcode, env->thumb)) { + goto excp_debug; + } + rc = EmulateAll(opcode, &ts->fpa, env); if (rc == 0) { /* illegal instruction */ info.si_signo = TARGET_SIGILL; diff --git a/monitor/hmp-cmds.c b/monitor/hmp-cmds.c index a6a6684df1..65d8ff4849 100644 --- a/monitor/hmp-cmds.c +++ b/monitor/hmp-cmds.c @@ -24,6 +24,7 @@ #include "qemu/option.h" #include "qemu/timer.h" #include "qemu/sockets.h" +#include "qemu/help_option.h" #include "monitor/monitor-internal.h" #include "qapi/error.h" #include "qapi/clone-visitor.h" @@ -1631,7 +1632,12 @@ void hmp_netdev_add(Monitor *mon, const QDict *qdict) { Error *err = NULL; QemuOpts *opts; + const char *type = qdict_get_try_str(qdict, "type"); + if (type && is_help_option(type)) { + show_netdevs(); + return; + } opts = qemu_opts_from_qdict(qemu_find_opts("netdev"), qdict, &err); if (err) { goto out; diff --git a/net/net.c b/net/net.c index 794c652282..6a2c3d9567 100644 --- a/net/net.c +++ b/net/net.c @@ -44,6 +44,7 @@ #include "qemu/config-file.h" #include "qemu/ctype.h" #include "qemu/iov.h" +#include "qemu/qemu-print.h" #include "qemu/main-loop.h" #include "qemu/option.h" #include "qapi/error.h" @@ -411,10 +412,14 @@ void qemu_del_nic(NICState *nic) qemu_macaddr_set_free(&nic->conf->macaddr); - /* If this is a peer NIC and peer has already been deleted, free it now. */ - if (nic->peer_deleted) { - for (i = 0; i < queues; i++) { - qemu_free_net_client(qemu_get_subqueue(nic, i)->peer); + for (i = 0; i < queues; i++) { + NetClientState *nc = qemu_get_subqueue(nic, i); + /* If this is a peer NIC and peer has already been deleted, free it now. */ + if (nic->peer_deleted) { + qemu_free_net_client(nc->peer); + } else if (nc->peer) { + /* if there are RX packets pending, complete them */ + qemu_purge_queued_packets(nc->peer); } } @@ -1025,7 +1030,7 @@ static int net_client_init1(const Netdev *netdev, bool is_netdev, Error **errp) return 0; } -static void show_netdevs(void) +void show_netdevs(void) { int idx; const char *available_netdevs[] = { @@ -1055,9 +1060,9 @@ static void show_netdevs(void) #endif }; - printf("Available netdev backend types:\n"); + qemu_printf("Available netdev backend types:\n"); for (idx = 0; idx < ARRAY_SIZE(available_netdevs); idx++) { - puts(available_netdevs[idx]); + qemu_printf("%s\n", available_netdevs[idx]); } } @@ -1068,42 +1073,35 @@ static int net_client_init(QemuOpts *opts, bool is_netdev, Error **errp) int ret = -1; Visitor *v = opts_visitor_new(opts); - const char *type = qemu_opt_get(opts, "type"); - - if (is_netdev && type && is_help_option(type)) { - show_netdevs(); - exit(0); - } else { - /* Parse convenience option format ip6-net=fec0::0[/64] */ - const char *ip6_net = qemu_opt_get(opts, "ipv6-net"); + /* Parse convenience option format ip6-net=fec0::0[/64] */ + const char *ip6_net = qemu_opt_get(opts, "ipv6-net"); - if (ip6_net) { - char *prefix_addr; - unsigned long prefix_len = 64; /* Default 64bit prefix length. */ - - substrings = g_strsplit(ip6_net, "/", 2); - if (!substrings || !substrings[0]) { - error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "ipv6-net", - "a valid IPv6 prefix"); - goto out; - } + if (ip6_net) { + char *prefix_addr; + unsigned long prefix_len = 64; /* Default 64bit prefix length. */ - prefix_addr = substrings[0]; + substrings = g_strsplit(ip6_net, "/", 2); + if (!substrings || !substrings[0]) { + error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "ipv6-net", + "a valid IPv6 prefix"); + goto out; + } - /* Handle user-specified prefix length. */ - if (substrings[1] && - qemu_strtoul(substrings[1], NULL, 10, &prefix_len)) - { - error_setg(errp, QERR_INVALID_PARAMETER_VALUE, - "ipv6-prefixlen", "a number"); - goto out; - } + prefix_addr = substrings[0]; - qemu_opt_set(opts, "ipv6-prefix", prefix_addr, &error_abort); - qemu_opt_set_number(opts, "ipv6-prefixlen", prefix_len, - &error_abort); - qemu_opt_unset(opts, "ipv6-net"); + /* Handle user-specified prefix length. */ + if (substrings[1] && + qemu_strtoul(substrings[1], NULL, 10, &prefix_len)) + { + error_setg(errp, QERR_INVALID_PARAMETER_VALUE, + "ipv6-prefixlen", "a number"); + goto out; } + + qemu_opt_set(opts, "ipv6-prefix", prefix_addr, &error_abort); + qemu_opt_set_number(opts, "ipv6-prefixlen", prefix_len, + &error_abort); + qemu_opt_unset(opts, "ipv6-net"); } /* Create an ID for -net if the user did not specify one */ @@ -1421,6 +1419,12 @@ static int net_init_client(void *dummy, QemuOpts *opts, Error **errp) static int net_init_netdev(void *dummy, QemuOpts *opts, Error **errp) { + const char *type = qemu_opt_get(opts, "type"); + + if (type && is_help_option(type)) { + show_netdevs(); + exit(0); + } return net_client_init(opts, true, errp); } diff --git a/net/tap.c b/net/tap.c index c46ff66184..b7512853f4 100644 --- a/net/tap.c +++ b/net/tap.c @@ -817,6 +817,7 @@ int net_init_tap(const Netdev *netdev, const char *name, if (ret < 0) { error_setg_errno(errp, -ret, "%s: Can't use file descriptor %d", name, fd); + close(fd); return -1; } @@ -831,6 +832,7 @@ int net_init_tap(const Netdev *netdev, const char *name, vhostfdname, vnet_hdr, fd, &err); if (err) { error_propagate(errp, err); + close(fd); return -1; } } else if (tap->has_fds) { @@ -951,7 +953,8 @@ free_fail: script = default_script = get_relocated_path(DEFAULT_NETWORK_SCRIPT); } if (!downscript) { - downscript = default_downscript = get_relocated_path(DEFAULT_NETWORK_SCRIPT); + downscript = default_downscript = + get_relocated_path(DEFAULT_NETWORK_DOWN_SCRIPT); } if (tap->has_ifname) { diff --git a/pc-bios/s390-ccw.img b/pc-bios/s390-ccw.img index 4e4b3207c4..5aaeac9f79 100644 --- a/pc-bios/s390-ccw.img +++ b/pc-bios/s390-ccw.img Binary files differdiff --git a/pc-bios/s390-ccw/dasd-ipl.c b/pc-bios/s390-ccw/dasd-ipl.c index 0fc879bb8e..71cbae2f16 100644 --- a/pc-bios/s390-ccw/dasd-ipl.c +++ b/pc-bios/s390-ccw/dasd-ipl.c @@ -100,6 +100,9 @@ static void make_readipl(void) { Ccw0 *ccwIplRead = (Ccw0 *)0x00; + /* Clear out any existing data */ + memset(ccwIplRead, 0, sizeof(Ccw0)); + /* Create Read IPL ccw at address 0 */ ccwIplRead->cmd_code = CCW_CMD_READ_IPL; ccwIplRead->cda = 0x00; /* Read into address 0x00 in main memory */ diff --git a/pc-bios/s390-ccw/jump2ipl.c b/pc-bios/s390-ccw/jump2ipl.c index fbae45b03c..b9c70d64a5 100644 --- a/pc-bios/s390-ccw/jump2ipl.c +++ b/pc-bios/s390-ccw/jump2ipl.c @@ -78,7 +78,7 @@ void jump_to_low_kernel(void) * kernel start address (when jumping to the PSW-at-zero address instead, * the kernel startup code fails when we booted from a network device). */ - if (!memcmp((char *)0x10008, "S390EP", 6)) { + if (!memcmp((char *)S390EP, "S390EP", 6)) { jump_to_IPL_code(KERN_IMAGE_START); } diff --git a/pc-bios/s390-ccw/main.c b/pc-bios/s390-ccw/main.c index fc4bfaa455..5d2b7ba94d 100644 --- a/pc-bios/s390-ccw/main.c +++ b/pc-bios/s390-ccw/main.c @@ -178,6 +178,12 @@ static void boot_setup(void) memcpy(lpmsg + 10, loadparm_str, 8); sclp_print(lpmsg); + /* + * Clear out any potential S390EP magic (see jump_to_low_kernel()), + * so we don't taint our decision-making process during a reboot. + */ + memset((char *)S390EP, 0, 6); + have_iplb = store_iplb(&iplb); } diff --git a/pc-bios/s390-ccw/s390-arch.h b/pc-bios/s390-ccw/s390-arch.h index 6da44d4436..a741488aaa 100644 --- a/pc-bios/s390-ccw/s390-arch.h +++ b/pc-bios/s390-ccw/s390-arch.h @@ -95,6 +95,9 @@ typedef struct LowCore { extern LowCore *lowcore; +/* Location of "S390EP" in a Linux binary (see arch/s390/boot/head.S) */ +#define S390EP 0x10008 + static inline void set_prefix(uint32_t address) { asm volatile("spx %0" : : "m" (address) : "memory"); diff --git a/pc-bios/s390-netboot.img b/pc-bios/s390-netboot.img index 3532f70f6f..120bd40ca9 100644 --- a/pc-bios/s390-netboot.img +++ b/pc-bios/s390-netboot.img Binary files differdiff --git a/python/qemu/machine.py b/python/qemu/machine.py index 6420f01bed..64d966aeeb 100644 --- a/python/qemu/machine.py +++ b/python/qemu/machine.py @@ -303,7 +303,8 @@ class QEMUMachine: return args def _pre_launch(self) -> None: - self._temp_dir = tempfile.mkdtemp(dir=self._test_dir) + self._temp_dir = tempfile.mkdtemp(prefix="qemu-machine-", + dir=self._test_dir) self._qemu_log_path = os.path.join(self._temp_dir, self._name + ".log") self._qemu_log_file = open(self._qemu_log_path, 'wb') diff --git a/scripts/ci/gitlab-pipeline-status b/scripts/ci/gitlab-pipeline-status index bac8233079..78e72f6008 100755 --- a/scripts/ci/gitlab-pipeline-status +++ b/scripts/ci/gitlab-pipeline-status @@ -31,7 +31,7 @@ class NoPipelineFound(Exception): """Communication is successfull but pipeline is not found.""" -def get_local_branch_commit(branch='staging'): +def get_local_branch_commit(branch): """ Returns the commit sha1 for the *local* branch named "staging" """ @@ -126,18 +126,16 @@ def create_parser(): help=('The GitLab project ID. Defaults to the project ' 'for https://gitlab.com/qemu-project/qemu, that ' 'is, "%(default)s"')) - try: - default_commit = get_local_branch_commit() - commit_required = False - except ValueError: - default_commit = '' - commit_required = True - parser.add_argument('-c', '--commit', required=commit_required, - default=default_commit, + parser.add_argument('-b', '--branch', type=str, default="staging", + help=('Specify the branch to check. ' + 'Use HEAD for your current branch. ' + 'Otherwise looks at "%(default)s"')) + parser.add_argument('-c', '--commit', + default=None, help=('Look for a pipeline associated with the given ' 'commit. If one is not explicitly given, the ' - 'commit associated with the local branch named ' - '"staging" is used. Default: %(default)s')) + 'commit associated with the default branch ' + 'is used.')) parser.add_argument('--verbose', action='store_true', default=False, help=('A minimal verbosity level that prints the ' 'overall result of the check/wait')) @@ -149,6 +147,10 @@ def main(): """ parser = create_parser() args = parser.parse_args() + + if not args.commit: + args.commit = get_local_branch_commit(args.branch) + success = False try: if args.wait: diff --git a/softmmu/memory.c b/softmmu/memory.c index aa393f1bb0..11ca94d037 100644 --- a/softmmu/memory.c +++ b/softmmu/memory.c @@ -205,8 +205,15 @@ static bool memory_region_ioeventfd_before(MemoryRegionIoeventfd *a, static bool memory_region_ioeventfd_equal(MemoryRegionIoeventfd *a, MemoryRegionIoeventfd *b) { - return !memory_region_ioeventfd_before(a, b) - && !memory_region_ioeventfd_before(b, a); + if (int128_eq(a->addr.start, b->addr.start) && + (!int128_nz(a->addr.size) || !int128_nz(b->addr.size) || + (int128_eq(a->addr.size, b->addr.size) && + (a->match_data == b->match_data) && + ((a->match_data && (a->data == b->data)) || !a->match_data) && + (a->e == b->e)))) + return true; + + return false; } /* Range of memory in the global map. Addresses are absolute. */ diff --git a/target/arm/arm-semi.c b/target/arm/arm-semi.c index c1df664f7e..c892e0e674 100644 --- a/target/arm/arm-semi.c +++ b/target/arm/arm-semi.c @@ -36,6 +36,7 @@ #else #include "exec/gdbstub.h" #include "qemu/cutils.h" +#include "hw/arm/boot.h" #endif #define TARGET_SYS_OPEN 0x01 @@ -1014,6 +1015,9 @@ target_ulong do_arm_semihosting(CPUARMState *env) int i; #ifdef CONFIG_USER_ONLY TaskState *ts = cs->opaque; +#else + const struct arm_boot_info *info = env->boot_info; + target_ulong rambase = info->loader_start; #endif GET_ARG(0); @@ -1046,10 +1050,10 @@ target_ulong do_arm_semihosting(CPUARMState *env) #else limit = ram_size; /* TODO: Make this use the limit of the loaded application. */ - retvals[0] = limit / 2; - retvals[1] = limit; - retvals[2] = limit; /* Stack base */ - retvals[3] = 0; /* Stack limit. */ + retvals[0] = rambase + limit / 2; + retvals[1] = rambase + limit; + retvals[2] = rambase + limit; /* Stack base */ + retvals[3] = rambase; /* Stack limit. */ #endif for (i = 0; i < ARRAY_SIZE(retvals); i++) { diff --git a/target/arm/helper.c b/target/arm/helper.c index 11b0803df7..38cd35c049 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -40,7 +40,7 @@ #ifndef CONFIG_USER_ONLY -static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address, +static bool get_phys_addr_lpae(CPUARMState *env, uint64_t address, MMUAccessType access_type, ARMMMUIdx mmu_idx, bool s1_is_el0, hwaddr *phys_ptr, MemTxAttrs *txattrs, int *prot, @@ -10988,7 +10988,7 @@ static ARMVAParameters aa32_va_parameters(CPUARMState *env, uint32_t va, * @fi: set to fault info if the translation fails * @cacheattrs: (if non-NULL) set to the cacheability/shareability attributes */ -static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address, +static bool get_phys_addr_lpae(CPUARMState *env, uint64_t address, MMUAccessType access_type, ARMMMUIdx mmu_idx, bool s1_is_el0, hwaddr *phys_ptr, MemTxAttrs *txattrs, int *prot, diff --git a/target/ppc/translate/vsx-impl.c.inc b/target/ppc/translate/vsx-impl.c.inc index b518de46db..075f063e98 100644 --- a/target/ppc/translate/vsx-impl.c.inc +++ b/target/ppc/translate/vsx-impl.c.inc @@ -139,6 +139,36 @@ static void gen_lxvw4x(DisasContext *ctx) tcg_temp_free_i64(xtl); } +static void gen_lxvwsx(DisasContext *ctx) +{ + TCGv EA; + TCGv_i32 data; + + if (xT(ctx->opcode) < 32) { + if (unlikely(!ctx->vsx_enabled)) { + gen_exception(ctx, POWERPC_EXCP_VSXU); + return; + } + } else { + if (unlikely(!ctx->altivec_enabled)) { + gen_exception(ctx, POWERPC_EXCP_VPU); + return; + } + } + + gen_set_access_type(ctx, ACCESS_INT); + EA = tcg_temp_new(); + + gen_addr_reg_index(ctx, EA); + + data = tcg_temp_new_i32(); + tcg_gen_qemu_ld_i32(data, EA, ctx->mem_idx, MO_TEUL); + tcg_gen_gvec_dup_i32(MO_UL, vsr_full_offset(xT(ctx->opcode)), 16, 16, data); + + tcg_temp_free(EA); + tcg_temp_free_i32(data); +} + static void gen_bswap16x8(TCGv_i64 outh, TCGv_i64 outl, TCGv_i64 inh, TCGv_i64 inl) { diff --git a/target/ppc/translate/vsx-ops.c.inc b/target/ppc/translate/vsx-ops.c.inc index 7fd3942b84..1d41beef26 100644 --- a/target/ppc/translate/vsx-ops.c.inc +++ b/target/ppc/translate/vsx-ops.c.inc @@ -5,6 +5,7 @@ GEN_HANDLER_E(lxsibzx, 0x1F, 0x0D, 0x18, 0, PPC_NONE, PPC2_ISA300), GEN_HANDLER_E(lxsihzx, 0x1F, 0x0D, 0x19, 0, PPC_NONE, PPC2_ISA300), GEN_HANDLER_E(lxsspx, 0x1F, 0x0C, 0x10, 0, PPC_NONE, PPC2_VSX207), GEN_HANDLER_E(lxvd2x, 0x1F, 0x0C, 0x1A, 0, PPC_NONE, PPC2_VSX), +GEN_HANDLER_E(lxvwsx, 0x1F, 0x0C, 0x0B, 0, PPC_NONE, PPC2_ISA300), GEN_HANDLER_E(lxvdsx, 0x1F, 0x0C, 0x0A, 0, PPC_NONE, PPC2_VSX), GEN_HANDLER_E(lxvw4x, 0x1F, 0x0C, 0x18, 0, PPC_NONE, PPC2_VSX), GEN_HANDLER_E(lxvh8x, 0x1F, 0x0C, 0x19, 0, PPC_NONE, PPC2_ISA300), diff --git a/tests/acceptance/avocado_qemu/__init__.py b/tests/acceptance/avocado_qemu/__init__.py index 4cda037187..bf54e419da 100644 --- a/tests/acceptance/avocado_qemu/__init__.py +++ b/tests/acceptance/avocado_qemu/__init__.py @@ -171,7 +171,8 @@ class Test(avocado.Test): self.cancel("No QEMU binary defined or found in the build tree") def _new_vm(self, *args): - vm = QEMUMachine(self.qemu_bin, sock_dir=tempfile.mkdtemp()) + self._sd = tempfile.TemporaryDirectory(prefix="avo_qemu_sock_") + vm = QEMUMachine(self.qemu_bin, sock_dir=self._sd.name) if args: vm.add_args(*args) return vm @@ -192,6 +193,7 @@ class Test(avocado.Test): def tearDown(self): for vm in self._vms.values(): vm.shutdown() + self._sd = None def fetch_asset(self, name, asset_hash=None, algorithm=None, diff --git a/tests/docker/dockerfiles/ubuntu2004.docker b/tests/docker/dockerfiles/ubuntu2004.docker index 355bbb3c63..ae889d8482 100644 --- a/tests/docker/dockerfiles/ubuntu2004.docker +++ b/tests/docker/dockerfiles/ubuntu2004.docker @@ -23,6 +23,7 @@ ENV PACKAGES flex bison \ libiscsi-dev \ libjemalloc-dev \ libjpeg-turbo8-dev \ + liblttng-ust-dev \ liblzo2-dev \ libncurses5-dev \ libncursesw5-dev \ diff --git a/tests/qtest/virtio-9p-test.c b/tests/qtest/virtio-9p-test.c index 21e340fa5f..92a498f249 100644 --- a/tests/qtest/virtio-9p-test.c +++ b/tests/qtest/virtio-9p-test.c @@ -1456,6 +1456,15 @@ static void register_virtio_9p_test(void) /* 9pfs test cases using the 'local' filesystem driver */ + + /* + * XXX: Until we are sure that these tests can run everywhere, + * keep them as "slow" so that they aren't run with "make check". + */ + if (!g_test_slow()) { + return; + } + opts.before = assign_9p_local_driver; qos_add_test("local/config", "virtio-9p", pci_config, &opts); qos_add_test("local/create_dir", "virtio-9p", fs_create_dir, &opts); diff --git a/util/trace-events b/util/trace-events index 24c31803b0..61e0d4bcdf 100644 --- a/util/trace-events +++ b/util/trace-events @@ -80,8 +80,14 @@ qemu_mutex_unlock(void *mutex, const char *file, const int line) "released mutex qemu_vfio_dma_reset_temporary(void *s) "s %p" qemu_vfio_ram_block_added(void *s, void *p, size_t size) "s %p host %p size 0x%zx" qemu_vfio_ram_block_removed(void *s, void *p, size_t size) "s %p host %p size 0x%zx" +qemu_vfio_dump_mapping(void *host, uint64_t iova, size_t size) "vfio mapping %p to iova 0x%08" PRIx64 " size 0x%zx" qemu_vfio_find_mapping(void *s, void *p) "s %p host %p" qemu_vfio_new_mapping(void *s, void *host, size_t size, int index, uint64_t iova) "s %p host %p size 0x%zx index %d iova 0x%"PRIx64 -qemu_vfio_do_mapping(void *s, void *host, size_t size, uint64_t iova) "s %p host %p size 0x%zx iova 0x%"PRIx64 -qemu_vfio_dma_map(void *s, void *host, size_t size, bool temporary, uint64_t *iova) "s %p host %p size 0x%zx temporary %d iova %p" +qemu_vfio_do_mapping(void *s, void *host, uint64_t iova, size_t size) "s %p host %p <-> iova 0x%"PRIx64 " size 0x%zx" +qemu_vfio_dma_map(void *s, void *host, size_t size, bool temporary, uint64_t *iova) "s %p host %p size 0x%zx temporary %d &iova %p" +qemu_vfio_dma_mapped(void *s, void *host, uint64_t iova, size_t size) "s %p host %p <-> iova 0x%"PRIx64" size 0x%zx" qemu_vfio_dma_unmap(void *s, void *host) "s %p host %p" +qemu_vfio_pci_read_config(void *buf, int ofs, int size, uint64_t region_ofs, uint64_t region_size) "read cfg ptr %p ofs 0x%x size 0x%x (region addr 0x%"PRIx64" size 0x%"PRIx64")" +qemu_vfio_pci_write_config(void *buf, int ofs, int size, uint64_t region_ofs, uint64_t region_size) "write cfg ptr %p ofs 0x%x size 0x%x (region addr 0x%"PRIx64" size 0x%"PRIx64")" +qemu_vfio_region_info(const char *desc, uint64_t region_ofs, uint64_t region_size, uint32_t cap_offset) "region '%s' addr 0x%"PRIx64" size 0x%"PRIx64" cap_ofs 0x%"PRIx32 +qemu_vfio_pci_map_bar(int index, uint64_t region_ofs, uint64_t region_size, int ofs, void *host) "map region bar#%d addr 0x%"PRIx64" size 0x%"PRIx64" ofs 0x%x host %p" diff --git a/util/vfio-helpers.c b/util/vfio-helpers.c index 2bec48e163..97dfa3fd57 100644 --- a/util/vfio-helpers.c +++ b/util/vfio-helpers.c @@ -137,6 +137,7 @@ static inline void assert_bar_index_valid(QEMUVFIOState *s, int index) static int qemu_vfio_pci_init_bar(QEMUVFIOState *s, int index, Error **errp) { + g_autofree char *barname = NULL; assert_bar_index_valid(s, index); s->bar_region_info[index] = (struct vfio_region_info) { .index = VFIO_PCI_BAR0_REGION_INDEX + index, @@ -146,6 +147,10 @@ static int qemu_vfio_pci_init_bar(QEMUVFIOState *s, int index, Error **errp) error_setg_errno(errp, errno, "Failed to get BAR region info"); return -errno; } + barname = g_strdup_printf("bar[%d]", index); + trace_qemu_vfio_region_info(barname, s->bar_region_info[index].offset, + s->bar_region_info[index].size, + s->bar_region_info[index].cap_offset); return 0; } @@ -158,10 +163,13 @@ void *qemu_vfio_pci_map_bar(QEMUVFIOState *s, int index, Error **errp) { void *p; + assert(QEMU_IS_ALIGNED(offset, qemu_real_host_page_size)); assert_bar_index_valid(s, index); p = mmap(NULL, MIN(size, s->bar_region_info[index].size - offset), prot, MAP_SHARED, s->device, s->bar_region_info[index].offset + offset); + trace_qemu_vfio_pci_map_bar(index, s->bar_region_info[index].offset , + size, offset, p); if (p == MAP_FAILED) { error_setg_errno(errp, errno, "Failed to map BAR region"); p = NULL; @@ -228,6 +236,10 @@ static int qemu_vfio_pci_read_config(QEMUVFIOState *s, void *buf, { int ret; + trace_qemu_vfio_pci_read_config(buf, ofs, size, + s->config_region_info.offset, + s->config_region_info.size); + assert(QEMU_IS_ALIGNED(s->config_region_info.offset + ofs, size)); do { ret = pread(s->device, buf, size, s->config_region_info.offset + ofs); } while (ret == -1 && errno == EINTR); @@ -238,6 +250,10 @@ static int qemu_vfio_pci_write_config(QEMUVFIOState *s, void *buf, int size, int { int ret; + trace_qemu_vfio_pci_write_config(buf, ofs, size, + s->config_region_info.offset, + s->config_region_info.size); + assert(QEMU_IS_ALIGNED(s->config_region_info.offset + ofs, size)); do { ret = pwrite(s->device, buf, size, s->config_region_info.offset + ofs); } while (ret == -1 && errno == EINTR); @@ -301,7 +317,7 @@ static int qemu_vfio_init_pci(QEMUVFIOState *s, const char *device, } if (!ioctl(s->container, VFIO_CHECK_EXTENSION, VFIO_TYPE1_IOMMU)) { - error_setg_errno(errp, errno, "VFIO IOMMU check failed"); + error_setg_errno(errp, errno, "VFIO IOMMU Type1 is not supported"); ret = -EINVAL; goto fail_container; } @@ -409,6 +425,9 @@ static int qemu_vfio_init_pci(QEMUVFIOState *s, const char *device, ret = -errno; goto fail; } + trace_qemu_vfio_region_info("config", s->config_region_info.offset, + s->config_region_info.size, + s->config_region_info.cap_offset); for (i = 0; i < ARRAY_SIZE(s->bar_region_info); i++) { ret = qemu_vfio_pci_init_bar(s, i, errp); @@ -516,23 +535,12 @@ QEMUVFIOState *qemu_vfio_open_pci(const char *device, Error **errp) return s; } -static void qemu_vfio_dump_mapping(IOVAMapping *m) -{ - if (QEMU_VFIO_DEBUG) { - printf(" vfio mapping %p %" PRIx64 " to %" PRIx64 "\n", m->host, - (uint64_t)m->size, (uint64_t)m->iova); - } -} - static void qemu_vfio_dump_mappings(QEMUVFIOState *s) { - int i; - - if (QEMU_VFIO_DEBUG) { - printf("vfio mappings\n"); - for (i = 0; i < s->nr_mappings; ++i) { - qemu_vfio_dump_mapping(&s->mappings[i]); - } + for (int i = 0; i < s->nr_mappings; ++i) { + trace_qemu_vfio_dump_mapping(s->mappings[i].host, + s->mappings[i].iova, + s->mappings[i].size); } } @@ -622,7 +630,7 @@ static int qemu_vfio_do_mapping(QEMUVFIOState *s, void *host, size_t size, .vaddr = (uintptr_t)host, .size = size, }; - trace_qemu_vfio_do_mapping(s, host, size, iova); + trace_qemu_vfio_do_mapping(s, host, iova, size); if (ioctl(s->container, VFIO_IOMMU_MAP_DMA, &dma_map)) { error_report("VFIO_MAP_DMA failed: %s", strerror(errno)); @@ -778,6 +786,7 @@ int qemu_vfio_dma_map(QEMUVFIOState *s, void *host, size_t size, } } } + trace_qemu_vfio_dma_mapped(s, host, iova0, size); if (iova) { *iova = iova0; } |