diff options
29 files changed, 1867 insertions, 338 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index 2c22bbca5a..c1d16026ba 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1879,6 +1879,7 @@ L: qemu-block@nongnu.org S: Supported F: hw/block/nvme* F: tests/qtest/nvme-test.c +F: docs/specs/nvme.txt T: git git://git.infradead.org/qemu-nvme.git nvme-next megasas diff --git a/docs/specs/nvme.txt b/docs/specs/nvme.txt new file mode 100644 index 0000000000..56d393884e --- /dev/null +++ b/docs/specs/nvme.txt @@ -0,0 +1,23 @@ +NVM Express Controller +====================== + +The nvme device (-device nvme) emulates an NVM Express Controller. + + +Reference Specifications +------------------------ + +The device currently implements most mandatory features of NVMe v1.3d, see + + https://nvmexpress.org/resources/specifications/ + +for the specification. + + +Known issues +------------ + +* The accounting numbers in the SMART/Health are reset across power cycles + +* Interrupt Coalescing is not supported and is disabled by default in volation + of the specification. diff --git a/docs/specs/pci-ids.txt b/docs/specs/pci-ids.txt index 4d53e5c7d9..abbdbca6be 100644 --- a/docs/specs/pci-ids.txt +++ b/docs/specs/pci-ids.txt @@ -63,6 +63,7 @@ PCI devices (other than virtio): 1b36:000b PCIe Expander Bridge (-device pxb-pcie) 1b36:000d PCI xhci usb host adapter 1b36:000f mdpy (mdev sample device), linux/samples/vfio-mdev/mdpy.c +1b36:0010 PCIe NVMe device (-device nvme) All these devices are documented in docs/specs. diff --git a/hw/block/meson.build b/hw/block/meson.build index 78cad8f7cb..602ca6c854 100644 --- a/hw/block/meson.build +++ b/hw/block/meson.build @@ -13,7 +13,7 @@ softmmu_ss.add(when: 'CONFIG_SSI_M25P80', if_true: files('m25p80.c')) softmmu_ss.add(when: 'CONFIG_SWIM', if_true: files('swim.c')) softmmu_ss.add(when: 'CONFIG_XEN', if_true: files('xen-block.c')) softmmu_ss.add(when: 'CONFIG_SH4', if_true: files('tc58128.c')) -softmmu_ss.add(when: 'CONFIG_NVME_PCI', if_true: files('nvme.c')) +softmmu_ss.add(when: 'CONFIG_NVME_PCI', if_true: files('nvme.c', 'nvme-ns.c')) specific_ss.add(when: 'CONFIG_VIRTIO_BLK', if_true: files('virtio-blk.c')) specific_ss.add(when: 'CONFIG_VHOST_USER_BLK', if_true: files('vhost-user-blk.c')) diff --git a/hw/block/nvme-ns.c b/hw/block/nvme-ns.c new file mode 100644 index 0000000000..31c80cdf5b --- /dev/null +++ b/hw/block/nvme-ns.c @@ -0,0 +1,168 @@ +/* + * QEMU NVM Express Virtual Namespace + * + * Copyright (c) 2019 CNEX Labs + * Copyright (c) 2020 Samsung Electronics + * + * Authors: + * Klaus Jensen <k.jensen@samsung.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See the + * COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "qemu/cutils.h" +#include "qemu/log.h" +#include "hw/block/block.h" +#include "hw/pci/pci.h" +#include "sysemu/sysemu.h" +#include "sysemu/block-backend.h" +#include "qapi/error.h" + +#include "hw/qdev-properties.h" +#include "hw/qdev-core.h" + +#include "nvme.h" +#include "nvme-ns.h" + +static void nvme_ns_init(NvmeNamespace *ns) +{ + NvmeIdNs *id_ns = &ns->id_ns; + int lba_index = NVME_ID_NS_FLBAS_INDEX(ns->id_ns.flbas); + + if (blk_get_flags(ns->blkconf.blk) & BDRV_O_UNMAP) { + ns->id_ns.dlfeat = 0x9; + } + + id_ns->lbaf[lba_index].ds = 31 - clz32(ns->blkconf.logical_block_size); + + id_ns->nsze = cpu_to_le64(nvme_ns_nlbas(ns)); + + /* no thin provisioning */ + id_ns->ncap = id_ns->nsze; + id_ns->nuse = id_ns->ncap; +} + +static int nvme_ns_init_blk(NvmeCtrl *n, NvmeNamespace *ns, Error **errp) +{ + if (!blkconf_blocksizes(&ns->blkconf, errp)) { + return -1; + } + + if (!blkconf_apply_backend_options(&ns->blkconf, + blk_is_read_only(ns->blkconf.blk), + false, errp)) { + return -1; + } + + ns->size = blk_getlength(ns->blkconf.blk); + if (ns->size < 0) { + error_setg_errno(errp, -ns->size, "could not get blockdev size"); + return -1; + } + + if (blk_enable_write_cache(ns->blkconf.blk)) { + n->features.vwc = 0x1; + } + + return 0; +} + +static int nvme_ns_check_constraints(NvmeNamespace *ns, Error **errp) +{ + if (!ns->blkconf.blk) { + error_setg(errp, "block backend not configured"); + return -1; + } + + return 0; +} + +int nvme_ns_setup(NvmeCtrl *n, NvmeNamespace *ns, Error **errp) +{ + if (nvme_ns_check_constraints(ns, errp)) { + return -1; + } + + if (nvme_ns_init_blk(n, ns, errp)) { + return -1; + } + + nvme_ns_init(ns); + if (nvme_register_namespace(n, ns, errp)) { + return -1; + } + + return 0; +} + +void nvme_ns_drain(NvmeNamespace *ns) +{ + blk_drain(ns->blkconf.blk); +} + +void nvme_ns_flush(NvmeNamespace *ns) +{ + blk_flush(ns->blkconf.blk); +} + +static void nvme_ns_realize(DeviceState *dev, Error **errp) +{ + NvmeNamespace *ns = NVME_NS(dev); + BusState *s = qdev_get_parent_bus(dev); + NvmeCtrl *n = NVME(s->parent); + Error *local_err = NULL; + + if (nvme_ns_setup(n, ns, &local_err)) { + error_propagate_prepend(errp, local_err, + "could not setup namespace: "); + return; + } +} + +static Property nvme_ns_props[] = { + DEFINE_BLOCK_PROPERTIES(NvmeNamespace, blkconf), + DEFINE_PROP_UINT32("nsid", NvmeNamespace, params.nsid, 0), + DEFINE_PROP_END_OF_LIST(), +}; + +static void nvme_ns_class_init(ObjectClass *oc, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(oc); + + set_bit(DEVICE_CATEGORY_STORAGE, dc->categories); + + dc->bus_type = TYPE_NVME_BUS; + dc->realize = nvme_ns_realize; + device_class_set_props(dc, nvme_ns_props); + dc->desc = "Virtual NVMe namespace"; +} + +static void nvme_ns_instance_init(Object *obj) +{ + NvmeNamespace *ns = NVME_NS(obj); + char *bootindex = g_strdup_printf("/namespace@%d,0", ns->params.nsid); + + device_add_bootindex_property(obj, &ns->bootindex, "bootindex", + bootindex, DEVICE(obj)); + + g_free(bootindex); +} + +static const TypeInfo nvme_ns_info = { + .name = TYPE_NVME_NS, + .parent = TYPE_DEVICE, + .class_init = nvme_ns_class_init, + .instance_size = sizeof(NvmeNamespace), + .instance_init = nvme_ns_instance_init, +}; + +static void nvme_ns_register_types(void) +{ + type_register_static(&nvme_ns_info); +} + +type_init(nvme_ns_register_types) diff --git a/hw/block/nvme-ns.h b/hw/block/nvme-ns.h new file mode 100644 index 0000000000..83734f4606 --- /dev/null +++ b/hw/block/nvme-ns.h @@ -0,0 +1,74 @@ +/* + * QEMU NVM Express Virtual Namespace + * + * Copyright (c) 2019 CNEX Labs + * Copyright (c) 2020 Samsung Electronics + * + * Authors: + * Klaus Jensen <k.jensen@samsung.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See the + * COPYING file in the top-level directory. + * + */ + +#ifndef NVME_NS_H +#define NVME_NS_H + +#define TYPE_NVME_NS "nvme-ns" +#define NVME_NS(obj) \ + OBJECT_CHECK(NvmeNamespace, (obj), TYPE_NVME_NS) + +typedef struct NvmeNamespaceParams { + uint32_t nsid; +} NvmeNamespaceParams; + +typedef struct NvmeNamespace { + DeviceState parent_obj; + BlockConf blkconf; + int32_t bootindex; + int64_t size; + NvmeIdNs id_ns; + + NvmeNamespaceParams params; +} NvmeNamespace; + +static inline uint32_t nvme_nsid(NvmeNamespace *ns) +{ + if (ns) { + return ns->params.nsid; + } + + return -1; +} + +static inline NvmeLBAF *nvme_ns_lbaf(NvmeNamespace *ns) +{ + NvmeIdNs *id_ns = &ns->id_ns; + return &id_ns->lbaf[NVME_ID_NS_FLBAS_INDEX(id_ns->flbas)]; +} + +static inline uint8_t nvme_ns_lbads(NvmeNamespace *ns) +{ + return nvme_ns_lbaf(ns)->ds; +} + +/* calculate the number of LBAs that the namespace can accomodate */ +static inline uint64_t nvme_ns_nlbas(NvmeNamespace *ns) +{ + return ns->size >> nvme_ns_lbads(ns); +} + +/* convert an LBA to the equivalent in bytes */ +static inline size_t nvme_l2b(NvmeNamespace *ns, uint64_t lba) +{ + return lba << nvme_ns_lbads(ns); +} + +typedef struct NvmeCtrl NvmeCtrl; + +int nvme_ns_setup(NvmeCtrl *n, NvmeNamespace *ns, Error **errp); +void nvme_ns_drain(NvmeNamespace *ns); +void nvme_ns_flush(NvmeNamespace *ns); + +#endif /* NVME_NS_H */ diff --git a/hw/block/nvme.c b/hw/block/nvme.c index 44fa5b9076..fa2cba744b 100644 --- a/hw/block/nvme.c +++ b/hw/block/nvme.c @@ -17,12 +17,13 @@ /** * Usage: add options: * -drive file=<file>,if=none,id=<drive_id> - * -device nvme,drive=<drive_id>,serial=<serial>,id=<id[optional]>, \ + * -device nvme,serial=<serial>,id=<bus_name>, \ * cmb_size_mb=<cmb_size_mb[optional]>, \ * [pmrdev=<mem_backend_file_id>,] \ * max_ioqpairs=<N[optional]>, \ * aerl=<N[optional]>, aer_max_queued=<N[optional]>, \ * mdts=<N[optional]> + * -device nvme-ns,drive=<drive_id>,bus=bus_name,nsid=<nsid> * * Note cmb_size_mb denotes size of CMB in MB. CMB is assumed to be at * offset 0 in BAR2 and supports only WDS, RDS and SQS for now. @@ -69,6 +70,7 @@ #include "qemu/cutils.h" #include "trace.h" #include "nvme.h" +#include "nvme-ns.h" #define NVME_MAX_IOQPAIRS 0xffff #define NVME_DB_SIZE 4 @@ -140,14 +142,24 @@ static inline void *nvme_addr_to_cmb(NvmeCtrl *n, hwaddr addr) return &n->cmbuf[addr - n->ctrl_mem.addr]; } -static void nvme_addr_read(NvmeCtrl *n, hwaddr addr, void *buf, int size) +static int nvme_addr_read(NvmeCtrl *n, hwaddr addr, void *buf, int size) { - if (n->bar.cmbsz && nvme_addr_is_cmb(n, addr)) { + hwaddr hi = addr + size - 1; + if (hi < addr) { + return 1; + } + + if (n->bar.cmbsz && nvme_addr_is_cmb(n, addr) && nvme_addr_is_cmb(n, hi)) { memcpy(buf, nvme_addr_to_cmb(n, addr), size); - return; + return 0; } - pci_dma_read(&n->parent_obj, addr, buf, size); + return pci_dma_read(&n->parent_obj, addr, buf, size); +} + +static bool nvme_nsid_valid(NvmeCtrl *n, uint32_t nsid) +{ + return nsid && (nsid == NVME_NSID_BROADCAST || nsid <= n->num_namespaces); } static int nvme_check_sqid(NvmeCtrl *n, uint16_t sqid) @@ -230,6 +242,7 @@ static void nvme_req_clear(NvmeRequest *req) { req->ns = NULL; memset(&req->cqe, 0x0, sizeof(req->cqe)); + req->status = NVME_SUCCESS; } static void nvme_req_exit(NvmeRequest *req) @@ -307,17 +320,13 @@ static uint16_t nvme_map_prp(NvmeCtrl *n, uint64_t prp1, uint64_t prp2, int num_prps = (len >> n->page_bits) + 1; uint16_t status; bool prp_list_in_cmb = false; + int ret; QEMUSGList *qsg = &req->qsg; QEMUIOVector *iov = &req->iov; trace_pci_nvme_map_prp(trans_len, len, prp1, prp2, num_prps); - if (unlikely(!prp1)) { - trace_pci_nvme_err_invalid_prp(); - return NVME_INVALID_FIELD | NVME_DNR; - } - if (nvme_addr_is_cmb(n, prp1)) { qemu_iovec_init(iov, num_prps); } else { @@ -331,11 +340,6 @@ static uint16_t nvme_map_prp(NvmeCtrl *n, uint64_t prp1, uint64_t prp2, len -= trans_len; if (len) { - if (unlikely(!prp2)) { - trace_pci_nvme_err_invalid_prp2_missing(); - return NVME_INVALID_FIELD | NVME_DNR; - } - if (len > n->page_size) { uint64_t prp_list[n->max_prp_ents]; uint32_t nents, prp_trans; @@ -347,14 +351,18 @@ static uint16_t nvme_map_prp(NvmeCtrl *n, uint64_t prp1, uint64_t prp2, nents = (len + n->page_size - 1) >> n->page_bits; prp_trans = MIN(n->max_prp_ents, nents) * sizeof(uint64_t); - nvme_addr_read(n, prp2, (void *)prp_list, prp_trans); + ret = nvme_addr_read(n, prp2, (void *)prp_list, prp_trans); + if (ret) { + trace_pci_nvme_err_addr_read(prp2); + return NVME_DATA_TRAS_ERROR; + } while (len != 0) { uint64_t prp_ent = le64_to_cpu(prp_list[i]); if (i == n->max_prp_ents - 1 && len > n->page_size) { - if (unlikely(!prp_ent || prp_ent & (n->page_size - 1))) { + if (unlikely(prp_ent & (n->page_size - 1))) { trace_pci_nvme_err_invalid_prplist_ent(prp_ent); - return NVME_INVALID_FIELD | NVME_DNR; + return NVME_INVALID_PRP_OFFSET | NVME_DNR; } if (prp_list_in_cmb != nvme_addr_is_cmb(n, prp_ent)) { @@ -364,14 +372,18 @@ static uint16_t nvme_map_prp(NvmeCtrl *n, uint64_t prp1, uint64_t prp2, i = 0; nents = (len + n->page_size - 1) >> n->page_bits; prp_trans = MIN(n->max_prp_ents, nents) * sizeof(uint64_t); - nvme_addr_read(n, prp_ent, (void *)prp_list, - prp_trans); + ret = nvme_addr_read(n, prp_ent, (void *)prp_list, + prp_trans); + if (ret) { + trace_pci_nvme_err_addr_read(prp_ent); + return NVME_DATA_TRAS_ERROR; + } prp_ent = le64_to_cpu(prp_list[i]); } - if (unlikely(!prp_ent || prp_ent & (n->page_size - 1))) { + if (unlikely(prp_ent & (n->page_size - 1))) { trace_pci_nvme_err_invalid_prplist_ent(prp_ent); - return NVME_INVALID_FIELD | NVME_DNR; + return NVME_INVALID_PRP_OFFSET | NVME_DNR; } trans_len = MIN(len, n->page_size); @@ -386,7 +398,7 @@ static uint16_t nvme_map_prp(NvmeCtrl *n, uint64_t prp1, uint64_t prp2, } else { if (unlikely(prp2 & (n->page_size - 1))) { trace_pci_nvme_err_invalid_prp2_align(prp2); - return NVME_INVALID_FIELD | NVME_DNR; + return NVME_INVALID_PRP_OFFSET | NVME_DNR; } status = nvme_map_addr(n, qsg, iov, prp2, len); if (status) { @@ -398,13 +410,282 @@ static uint16_t nvme_map_prp(NvmeCtrl *n, uint64_t prp1, uint64_t prp2, return NVME_SUCCESS; } -static uint16_t nvme_dma_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len, - uint64_t prp1, uint64_t prp2, DMADirection dir, +/* + * Map 'nsgld' data descriptors from 'segment'. The function will subtract the + * number of bytes mapped in len. + */ +static uint16_t nvme_map_sgl_data(NvmeCtrl *n, QEMUSGList *qsg, + QEMUIOVector *iov, + NvmeSglDescriptor *segment, uint64_t nsgld, + size_t *len, NvmeRequest *req) +{ + dma_addr_t addr, trans_len; + uint32_t dlen; + uint16_t status; + + for (int i = 0; i < nsgld; i++) { + uint8_t type = NVME_SGL_TYPE(segment[i].type); + + switch (type) { + case NVME_SGL_DESCR_TYPE_BIT_BUCKET: + if (req->cmd.opcode == NVME_CMD_WRITE) { + continue; + } + case NVME_SGL_DESCR_TYPE_DATA_BLOCK: + break; + case NVME_SGL_DESCR_TYPE_SEGMENT: + case NVME_SGL_DESCR_TYPE_LAST_SEGMENT: + return NVME_INVALID_NUM_SGL_DESCRS | NVME_DNR; + default: + return NVME_SGL_DESCR_TYPE_INVALID | NVME_DNR; + } + + dlen = le32_to_cpu(segment[i].len); + + if (!dlen) { + continue; + } + + if (*len == 0) { + /* + * All data has been mapped, but the SGL contains additional + * segments and/or descriptors. The controller might accept + * ignoring the rest of the SGL. + */ + uint16_t sgls = le16_to_cpu(n->id_ctrl.sgls); + if (sgls & NVME_CTRL_SGLS_EXCESS_LENGTH) { + break; + } + + trace_pci_nvme_err_invalid_sgl_excess_length(nvme_cid(req)); + return NVME_DATA_SGL_LEN_INVALID | NVME_DNR; + } + + trans_len = MIN(*len, dlen); + + if (type == NVME_SGL_DESCR_TYPE_BIT_BUCKET) { + goto next; + } + + addr = le64_to_cpu(segment[i].addr); + + if (UINT64_MAX - addr < dlen) { + return NVME_DATA_SGL_LEN_INVALID | NVME_DNR; + } + + status = nvme_map_addr(n, qsg, iov, addr, trans_len); + if (status) { + return status; + } + +next: + *len -= trans_len; + } + + return NVME_SUCCESS; +} + +static uint16_t nvme_map_sgl(NvmeCtrl *n, QEMUSGList *qsg, QEMUIOVector *iov, + NvmeSglDescriptor sgl, size_t len, NvmeRequest *req) { + /* + * Read the segment in chunks of 256 descriptors (one 4k page) to avoid + * dynamically allocating a potentially huge SGL. The spec allows the SGL + * to be larger (as in number of bytes required to describe the SGL + * descriptors and segment chain) than the command transfer size, so it is + * not bounded by MDTS. + */ + const int SEG_CHUNK_SIZE = 256; + + NvmeSglDescriptor segment[SEG_CHUNK_SIZE], *sgld, *last_sgld; + uint64_t nsgld; + uint32_t seg_len; + uint16_t status; + bool sgl_in_cmb = false; + hwaddr addr; + int ret; + + sgld = &sgl; + addr = le64_to_cpu(sgl.addr); + + trace_pci_nvme_map_sgl(nvme_cid(req), NVME_SGL_TYPE(sgl.type), len); + + /* + * If the entire transfer can be described with a single data block it can + * be mapped directly. + */ + if (NVME_SGL_TYPE(sgl.type) == NVME_SGL_DESCR_TYPE_DATA_BLOCK) { + status = nvme_map_sgl_data(n, qsg, iov, sgld, 1, &len, req); + if (status) { + goto unmap; + } + + goto out; + } + + /* + * If the segment is located in the CMB, the submission queue of the + * request must also reside there. + */ + if (nvme_addr_is_cmb(n, addr)) { + if (!nvme_addr_is_cmb(n, req->sq->dma_addr)) { + return NVME_INVALID_USE_OF_CMB | NVME_DNR; + } + + sgl_in_cmb = true; + } + + for (;;) { + switch (NVME_SGL_TYPE(sgld->type)) { + case NVME_SGL_DESCR_TYPE_SEGMENT: + case NVME_SGL_DESCR_TYPE_LAST_SEGMENT: + break; + default: + return NVME_INVALID_SGL_SEG_DESCR | NVME_DNR; + } + + seg_len = le32_to_cpu(sgld->len); + + /* check the length of the (Last) Segment descriptor */ + if ((!seg_len || seg_len & 0xf) && + (NVME_SGL_TYPE(sgld->type) != NVME_SGL_DESCR_TYPE_BIT_BUCKET)) { + return NVME_INVALID_SGL_SEG_DESCR | NVME_DNR; + } + + if (UINT64_MAX - addr < seg_len) { + return NVME_DATA_SGL_LEN_INVALID | NVME_DNR; + } + + nsgld = seg_len / sizeof(NvmeSglDescriptor); + + while (nsgld > SEG_CHUNK_SIZE) { + if (nvme_addr_read(n, addr, segment, sizeof(segment))) { + trace_pci_nvme_err_addr_read(addr); + status = NVME_DATA_TRAS_ERROR; + goto unmap; + } + + status = nvme_map_sgl_data(n, qsg, iov, segment, SEG_CHUNK_SIZE, + &len, req); + if (status) { + goto unmap; + } + + nsgld -= SEG_CHUNK_SIZE; + addr += SEG_CHUNK_SIZE * sizeof(NvmeSglDescriptor); + } + + ret = nvme_addr_read(n, addr, segment, nsgld * + sizeof(NvmeSglDescriptor)); + if (ret) { + trace_pci_nvme_err_addr_read(addr); + status = NVME_DATA_TRAS_ERROR; + goto unmap; + } + + last_sgld = &segment[nsgld - 1]; + + /* + * If the segment ends with a Data Block or Bit Bucket Descriptor Type, + * then we are done. + */ + switch (NVME_SGL_TYPE(last_sgld->type)) { + case NVME_SGL_DESCR_TYPE_DATA_BLOCK: + case NVME_SGL_DESCR_TYPE_BIT_BUCKET: + status = nvme_map_sgl_data(n, qsg, iov, segment, nsgld, &len, req); + if (status) { + goto unmap; + } + + goto out; + + default: + break; + } + + /* + * If the last descriptor was not a Data Block or Bit Bucket, then the + * current segment must not be a Last Segment. + */ + if (NVME_SGL_TYPE(sgld->type) == NVME_SGL_DESCR_TYPE_LAST_SEGMENT) { + status = NVME_INVALID_SGL_SEG_DESCR | NVME_DNR; + goto unmap; + } + + sgld = last_sgld; + addr = le64_to_cpu(sgld->addr); + + /* + * Do not map the last descriptor; it will be a Segment or Last Segment + * descriptor and is handled by the next iteration. + */ + status = nvme_map_sgl_data(n, qsg, iov, segment, nsgld - 1, &len, req); + if (status) { + goto unmap; + } + + /* + * If the next segment is in the CMB, make sure that the sgl was + * already located there. + */ + if (sgl_in_cmb != nvme_addr_is_cmb(n, addr)) { + status = NVME_INVALID_USE_OF_CMB | NVME_DNR; + goto unmap; + } + } + +out: + /* if there is any residual left in len, the SGL was too short */ + if (len) { + status = NVME_DATA_SGL_LEN_INVALID | NVME_DNR; + goto unmap; + } + + return NVME_SUCCESS; + +unmap: + if (iov->iov) { + qemu_iovec_destroy(iov); + } + + if (qsg->sg) { + qemu_sglist_destroy(qsg); + } + + return status; +} + +static uint16_t nvme_map_dptr(NvmeCtrl *n, size_t len, NvmeRequest *req) +{ + uint64_t prp1, prp2; + + switch (NVME_CMD_FLAGS_PSDT(req->cmd.flags)) { + case NVME_PSDT_PRP: + prp1 = le64_to_cpu(req->cmd.dptr.prp1); + prp2 = le64_to_cpu(req->cmd.dptr.prp2); + + return nvme_map_prp(n, prp1, prp2, len, req); + case NVME_PSDT_SGL_MPTR_CONTIGUOUS: + case NVME_PSDT_SGL_MPTR_SGL: + /* SGLs shall not be used for Admin commands in NVMe over PCIe */ + if (!req->sq->sqid) { + return NVME_INVALID_FIELD | NVME_DNR; + } + + return nvme_map_sgl(n, &req->qsg, &req->iov, req->cmd.dptr.sgl, len, + req); + default: + return NVME_INVALID_FIELD; + } +} + +static uint16_t nvme_dma(NvmeCtrl *n, uint8_t *ptr, uint32_t len, + DMADirection dir, NvmeRequest *req) +{ uint16_t status = NVME_SUCCESS; - status = nvme_map_prp(n, prp1, prp2, len, req); + status = nvme_map_dptr(n, len, req); if (status) { return status; } @@ -443,20 +724,12 @@ static uint16_t nvme_dma_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len, return status; } -static uint16_t nvme_map_dptr(NvmeCtrl *n, size_t len, NvmeRequest *req) -{ - NvmeCmd *cmd = &req->cmd; - uint64_t prp1 = le64_to_cpu(cmd->dptr.prp1); - uint64_t prp2 = le64_to_cpu(cmd->dptr.prp2); - - return nvme_map_prp(n, prp1, prp2, len, req); -} - static void nvme_post_cqes(void *opaque) { NvmeCQueue *cq = opaque; NvmeCtrl *n = cq->ctrl; NvmeRequest *req, *next; + int ret; QTAILQ_FOREACH_SAFE(req, &cq->req_list, entry, next) { NvmeSQueue *sq; @@ -466,15 +739,21 @@ static void nvme_post_cqes(void *opaque) break; } - QTAILQ_REMOVE(&cq->req_list, req, entry); sq = req->sq; req->cqe.status = cpu_to_le16((req->status << 1) | cq->phase); req->cqe.sq_id = cpu_to_le16(sq->sqid); req->cqe.sq_head = cpu_to_le16(sq->head); addr = cq->dma_addr + cq->tail * n->cqe_size; + ret = pci_dma_write(&n->parent_obj, addr, (void *)&req->cqe, + sizeof(req->cqe)); + if (ret) { + trace_pci_nvme_err_addr_write(addr); + trace_pci_nvme_err_cfs(); + n->bar.csts = NVME_CSTS_FAILED; + break; + } + QTAILQ_REMOVE(&cq->req_list, req, entry); nvme_inc_cq_tail(cq); - pci_dma_write(&n->parent_obj, addr, (void *)&req->cqe, - sizeof(req->cqe)); nvme_req_exit(req); QTAILQ_INSERT_TAIL(&sq->req_list, req, entry); } @@ -488,6 +767,12 @@ static void nvme_enqueue_req_completion(NvmeCQueue *cq, NvmeRequest *req) assert(cq->cqid == req->sq->cqid); trace_pci_nvme_enqueue_req_completion(nvme_cid(req), cq->cqid, req->status); + + if (req->status) { + trace_pci_nvme_err_req_status(nvme_cid(req), nvme_nsid(req->ns), + req->status, req->cmd.opcode); + } + QTAILQ_REMOVE(&req->sq->out_req_list, req, entry); QTAILQ_INSERT_TAIL(&cq->req_list, req, entry); timer_mod(cq->timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + 500); @@ -530,8 +815,6 @@ static void nvme_process_aers(void *opaque) result->log_page = event->result.log_page; g_free(event); - req->status = NVME_SUCCESS; - trace_pci_nvme_aer_post_cqe(result->event_type, result->event_info, result->log_page); @@ -598,29 +881,53 @@ static inline uint16_t nvme_check_bounds(NvmeCtrl *n, NvmeNamespace *ns, static void nvme_rw_cb(void *opaque, int ret) { NvmeRequest *req = opaque; - NvmeSQueue *sq = req->sq; - NvmeCtrl *n = sq->ctrl; - NvmeCQueue *cq = n->cq[sq->cqid]; + NvmeNamespace *ns = req->ns; - trace_pci_nvme_rw_cb(nvme_cid(req)); + BlockBackend *blk = ns->blkconf.blk; + BlockAcctCookie *acct = &req->acct; + BlockAcctStats *stats = blk_get_stats(blk); + + Error *local_err = NULL; + + trace_pci_nvme_rw_cb(nvme_cid(req), blk_name(blk)); if (!ret) { - block_acct_done(blk_get_stats(n->conf.blk), &req->acct); - req->status = NVME_SUCCESS; + block_acct_done(stats, acct); } else { - block_acct_failed(blk_get_stats(n->conf.blk), &req->acct); - req->status = NVME_INTERNAL_DEV_ERROR; + uint16_t status; + + block_acct_failed(stats, acct); + + switch (req->cmd.opcode) { + case NVME_CMD_READ: + status = NVME_UNRECOVERED_READ; + break; + case NVME_CMD_FLUSH: + case NVME_CMD_WRITE: + case NVME_CMD_WRITE_ZEROES: + status = NVME_WRITE_FAULT; + break; + default: + status = NVME_INTERNAL_DEV_ERROR; + break; + } + + trace_pci_nvme_err_aio(nvme_cid(req), strerror(ret), status); + + error_setg_errno(&local_err, -ret, "aio failed"); + error_report_err(local_err); + + req->status = status; } - nvme_enqueue_req_completion(cq, req); + nvme_enqueue_req_completion(nvme_cq(req), req); } static uint16_t nvme_flush(NvmeCtrl *n, NvmeRequest *req) { - block_acct_start(blk_get_stats(n->conf.blk), &req->acct, 0, - BLOCK_ACCT_FLUSH); - req->aiocb = blk_aio_flush(n->conf.blk, nvme_rw_cb, req); - + block_acct_start(blk_get_stats(req->ns->blkconf.blk), &req->acct, 0, + BLOCK_ACCT_FLUSH); + req->aiocb = blk_aio_flush(req->ns->blkconf.blk, nvme_rw_cb, req); return NVME_NO_COMPLETE; } @@ -628,15 +935,13 @@ static uint16_t nvme_write_zeroes(NvmeCtrl *n, NvmeRequest *req) { NvmeRwCmd *rw = (NvmeRwCmd *)&req->cmd; NvmeNamespace *ns = req->ns; - const uint8_t lba_index = NVME_ID_NS_FLBAS_INDEX(ns->id_ns.flbas); - const uint8_t data_shift = ns->id_ns.lbaf[lba_index].ds; uint64_t slba = le64_to_cpu(rw->slba); - uint32_t nlb = le16_to_cpu(rw->nlb) + 1; - uint64_t offset = slba << data_shift; - uint32_t count = nlb << data_shift; + uint32_t nlb = (uint32_t)le16_to_cpu(rw->nlb) + 1; + uint64_t offset = nvme_l2b(ns, slba); + uint32_t count = nvme_l2b(ns, nlb); uint16_t status; - trace_pci_nvme_write_zeroes(nvme_cid(req), slba, nlb); + trace_pci_nvme_write_zeroes(nvme_cid(req), nvme_nsid(ns), slba, nlb); status = nvme_check_bounds(n, ns, slba, nlb); if (status) { @@ -644,10 +949,10 @@ static uint16_t nvme_write_zeroes(NvmeCtrl *n, NvmeRequest *req) return status; } - block_acct_start(blk_get_stats(n->conf.blk), &req->acct, 0, + block_acct_start(blk_get_stats(req->ns->blkconf.blk), &req->acct, 0, BLOCK_ACCT_WRITE); - req->aiocb = blk_aio_pwrite_zeroes(n->conf.blk, offset, count, - BDRV_REQ_MAY_UNMAP, nvme_rw_cb, req); + req->aiocb = blk_aio_pwrite_zeroes(req->ns->blkconf.blk, offset, count, + BDRV_REQ_MAY_UNMAP, nvme_rw_cb, req); return NVME_NO_COMPLETE; } @@ -655,57 +960,59 @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeRequest *req) { NvmeRwCmd *rw = (NvmeRwCmd *)&req->cmd; NvmeNamespace *ns = req->ns; - uint32_t nlb = le32_to_cpu(rw->nlb) + 1; + uint32_t nlb = (uint32_t)le16_to_cpu(rw->nlb) + 1; uint64_t slba = le64_to_cpu(rw->slba); - uint8_t lba_index = NVME_ID_NS_FLBAS_INDEX(ns->id_ns.flbas); - uint8_t data_shift = ns->id_ns.lbaf[lba_index].ds; - uint64_t data_size = (uint64_t)nlb << data_shift; - uint64_t data_offset = slba << data_shift; - int is_write = rw->opcode == NVME_CMD_WRITE ? 1 : 0; - enum BlockAcctType acct = is_write ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ; + uint64_t data_size = nvme_l2b(ns, nlb); + uint64_t data_offset = nvme_l2b(ns, slba); + enum BlockAcctType acct = req->cmd.opcode == NVME_CMD_WRITE ? + BLOCK_ACCT_WRITE : BLOCK_ACCT_READ; + BlockBackend *blk = ns->blkconf.blk; uint16_t status; - trace_pci_nvme_rw(is_write ? "write" : "read", nlb, data_size, slba); + trace_pci_nvme_rw(nvme_cid(req), nvme_io_opc_str(rw->opcode), + nvme_nsid(ns), nlb, data_size, slba); status = nvme_check_mdts(n, data_size); if (status) { trace_pci_nvme_err_mdts(nvme_cid(req), data_size); - block_acct_invalid(blk_get_stats(n->conf.blk), acct); - return status; + goto invalid; } status = nvme_check_bounds(n, ns, slba, nlb); if (status) { trace_pci_nvme_err_invalid_lba_range(slba, nlb, ns->id_ns.nsze); - block_acct_invalid(blk_get_stats(n->conf.blk), acct); - return status; + goto invalid; } - if (nvme_map_dptr(n, data_size, req)) { - block_acct_invalid(blk_get_stats(n->conf.blk), acct); - return NVME_INVALID_FIELD | NVME_DNR; + status = nvme_map_dptr(n, data_size, req); + if (status) { + goto invalid; } - if (req->qsg.nsg > 0) { - block_acct_start(blk_get_stats(n->conf.blk), &req->acct, req->qsg.size, - acct); - req->aiocb = is_write ? - dma_blk_write(n->conf.blk, &req->qsg, data_offset, BDRV_SECTOR_SIZE, - nvme_rw_cb, req) : - dma_blk_read(n->conf.blk, &req->qsg, data_offset, BDRV_SECTOR_SIZE, - nvme_rw_cb, req); + block_acct_start(blk_get_stats(blk), &req->acct, data_size, acct); + if (req->qsg.sg) { + if (acct == BLOCK_ACCT_WRITE) { + req->aiocb = dma_blk_write(blk, &req->qsg, data_offset, + BDRV_SECTOR_SIZE, nvme_rw_cb, req); + } else { + req->aiocb = dma_blk_read(blk, &req->qsg, data_offset, + BDRV_SECTOR_SIZE, nvme_rw_cb, req); + } } else { - block_acct_start(blk_get_stats(n->conf.blk), &req->acct, req->iov.size, - acct); - req->aiocb = is_write ? - blk_aio_pwritev(n->conf.blk, data_offset, &req->iov, 0, nvme_rw_cb, - req) : - blk_aio_preadv(n->conf.blk, data_offset, &req->iov, 0, nvme_rw_cb, - req); + if (acct == BLOCK_ACCT_WRITE) { + req->aiocb = blk_aio_pwritev(blk, data_offset, &req->iov, 0, + nvme_rw_cb, req); + } else { + req->aiocb = blk_aio_preadv(blk, data_offset, &req->iov, 0, + nvme_rw_cb, req); + } } - return NVME_NO_COMPLETE; + +invalid: + block_acct_invalid(blk_get_stats(ns->blkconf.blk), acct); + return status; } static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeRequest *req) @@ -713,14 +1020,21 @@ static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeRequest *req) uint32_t nsid = le32_to_cpu(req->cmd.nsid); trace_pci_nvme_io_cmd(nvme_cid(req), nsid, nvme_sqid(req), - req->cmd.opcode); + req->cmd.opcode, nvme_io_opc_str(req->cmd.opcode)); + + if (NVME_CC_CSS(n->bar.cc) == NVME_CC_CSS_ADMIN_ONLY) { + return NVME_INVALID_OPCODE | NVME_DNR; + } - if (unlikely(nsid == 0 || nsid > n->num_namespaces)) { - trace_pci_nvme_err_invalid_ns(nsid, n->num_namespaces); + if (!nvme_nsid_valid(n, nsid)) { return NVME_INVALID_NSID | NVME_DNR; } - req->ns = &n->namespaces[nsid - 1]; + req->ns = nvme_ns(n, nsid); + if (unlikely(!req->ns)) { + return NVME_INVALID_FIELD | NVME_DNR; + } + switch (req->cmd.opcode) { case NVME_CMD_FLUSH: return nvme_flush(n, req); @@ -785,7 +1099,7 @@ static uint16_t nvme_del_sq(NvmeCtrl *n, NvmeRequest *req) } static void nvme_init_sq(NvmeSQueue *sq, NvmeCtrl *n, uint64_t dma_addr, - uint16_t sqid, uint16_t cqid, uint16_t size) + uint16_t sqid, uint16_t cqid, uint16_t size) { int i; NvmeCQueue *cq; @@ -829,7 +1143,8 @@ static uint16_t nvme_create_sq(NvmeCtrl *n, NvmeRequest *req) trace_pci_nvme_err_invalid_create_sq_cqid(cqid); return NVME_INVALID_CQID | NVME_DNR; } - if (unlikely(!sqid || !nvme_check_sqid(n, sqid))) { + if (unlikely(!sqid || sqid > n->params.max_ioqpairs || + n->sq[sqid] != NULL)) { trace_pci_nvme_err_invalid_create_sq_sqid(sqid); return NVME_INVALID_QID | NVME_DNR; } @@ -837,9 +1152,9 @@ static uint16_t nvme_create_sq(NvmeCtrl *n, NvmeRequest *req) trace_pci_nvme_err_invalid_create_sq_size(qsize); return NVME_MAX_QSIZE_EXCEEDED | NVME_DNR; } - if (unlikely(!prp1 || prp1 & (n->page_size - 1))) { + if (unlikely(prp1 & (n->page_size - 1))) { trace_pci_nvme_err_invalid_create_sq_addr(prp1); - return NVME_INVALID_FIELD | NVME_DNR; + return NVME_INVALID_PRP_OFFSET | NVME_DNR; } if (unlikely(!(NVME_SQ_FLAGS_PC(qflags)))) { trace_pci_nvme_err_invalid_create_sq_qflags(NVME_SQ_FLAGS_PC(qflags)); @@ -850,45 +1165,63 @@ static uint16_t nvme_create_sq(NvmeCtrl *n, NvmeRequest *req) return NVME_SUCCESS; } +struct nvme_stats { + uint64_t units_read; + uint64_t units_written; + uint64_t read_commands; + uint64_t write_commands; +}; + +static void nvme_set_blk_stats(NvmeNamespace *ns, struct nvme_stats *stats) +{ + BlockAcctStats *s = blk_get_stats(ns->blkconf.blk); + + stats->units_read += s->nr_bytes[BLOCK_ACCT_READ] >> BDRV_SECTOR_BITS; + stats->units_written += s->nr_bytes[BLOCK_ACCT_WRITE] >> BDRV_SECTOR_BITS; + stats->read_commands += s->nr_ops[BLOCK_ACCT_READ]; + stats->write_commands += s->nr_ops[BLOCK_ACCT_WRITE]; +} + static uint16_t nvme_smart_info(NvmeCtrl *n, uint8_t rae, uint32_t buf_len, uint64_t off, NvmeRequest *req) { - NvmeCmd *cmd = &req->cmd; - uint64_t prp1 = le64_to_cpu(cmd->dptr.prp1); - uint64_t prp2 = le64_to_cpu(cmd->dptr.prp2); - uint32_t nsid = le32_to_cpu(cmd->nsid); - + uint32_t nsid = le32_to_cpu(req->cmd.nsid); + struct nvme_stats stats = { 0 }; + NvmeSmartLog smart = { 0 }; uint32_t trans_len; + NvmeNamespace *ns; time_t current_ms; - uint64_t units_read = 0, units_written = 0; - uint64_t read_commands = 0, write_commands = 0; - NvmeSmartLog smart; - BlockAcctStats *s; - if (nsid && nsid != 0xffffffff) { + if (off >= sizeof(smart)) { return NVME_INVALID_FIELD | NVME_DNR; } - s = blk_get_stats(n->conf.blk); - - units_read = s->nr_bytes[BLOCK_ACCT_READ] >> BDRV_SECTOR_BITS; - units_written = s->nr_bytes[BLOCK_ACCT_WRITE] >> BDRV_SECTOR_BITS; - read_commands = s->nr_ops[BLOCK_ACCT_READ]; - write_commands = s->nr_ops[BLOCK_ACCT_WRITE]; + if (nsid != 0xffffffff) { + ns = nvme_ns(n, nsid); + if (!ns) { + return NVME_INVALID_NSID | NVME_DNR; + } + nvme_set_blk_stats(ns, &stats); + } else { + int i; - if (off > sizeof(smart)) { - return NVME_INVALID_FIELD | NVME_DNR; + for (i = 1; i <= n->num_namespaces; i++) { + ns = nvme_ns(n, i); + if (!ns) { + continue; + } + nvme_set_blk_stats(ns, &stats); + } } trans_len = MIN(sizeof(smart) - off, buf_len); - memset(&smart, 0x0, sizeof(smart)); - - smart.data_units_read[0] = cpu_to_le64(DIV_ROUND_UP(units_read, 1000)); - smart.data_units_written[0] = cpu_to_le64(DIV_ROUND_UP(units_written, + smart.data_units_read[0] = cpu_to_le64(DIV_ROUND_UP(stats.units_read, + 1000)); + smart.data_units_written[0] = cpu_to_le64(DIV_ROUND_UP(stats.units_written, 1000)); - smart.host_read_commands[0] = cpu_to_le64(read_commands); - smart.host_write_commands[0] = cpu_to_le64(write_commands); + smart.host_read_commands[0] = cpu_to_le64(stats.read_commands); + smart.host_write_commands[0] = cpu_to_le64(stats.write_commands); smart.temperature = cpu_to_le16(n->temperature); @@ -905,56 +1238,48 @@ static uint16_t nvme_smart_info(NvmeCtrl *n, uint8_t rae, uint32_t buf_len, nvme_clear_events(n, NVME_AER_TYPE_SMART); } - return nvme_dma_prp(n, (uint8_t *) &smart + off, trans_len, prp1, prp2, - DMA_DIRECTION_FROM_DEVICE, req); + return nvme_dma(n, (uint8_t *) &smart + off, trans_len, + DMA_DIRECTION_FROM_DEVICE, req); } static uint16_t nvme_fw_log_info(NvmeCtrl *n, uint32_t buf_len, uint64_t off, NvmeRequest *req) { uint32_t trans_len; - NvmeCmd *cmd = &req->cmd; - uint64_t prp1 = le64_to_cpu(cmd->dptr.prp1); - uint64_t prp2 = le64_to_cpu(cmd->dptr.prp2); NvmeFwSlotInfoLog fw_log = { .afi = 0x1, }; - strpadcpy((char *)&fw_log.frs1, sizeof(fw_log.frs1), "1.0", ' '); - - if (off > sizeof(fw_log)) { + if (off >= sizeof(fw_log)) { return NVME_INVALID_FIELD | NVME_DNR; } + strpadcpy((char *)&fw_log.frs1, sizeof(fw_log.frs1), "1.0", ' '); trans_len = MIN(sizeof(fw_log) - off, buf_len); - return nvme_dma_prp(n, (uint8_t *) &fw_log + off, trans_len, prp1, prp2, - DMA_DIRECTION_FROM_DEVICE, req); + return nvme_dma(n, (uint8_t *) &fw_log + off, trans_len, + DMA_DIRECTION_FROM_DEVICE, req); } static uint16_t nvme_error_info(NvmeCtrl *n, uint8_t rae, uint32_t buf_len, uint64_t off, NvmeRequest *req) { uint32_t trans_len; - NvmeCmd *cmd = &req->cmd; - uint64_t prp1 = le64_to_cpu(cmd->dptr.prp1); - uint64_t prp2 = le64_to_cpu(cmd->dptr.prp2); NvmeErrorLog errlog; - if (!rae) { - nvme_clear_events(n, NVME_AER_TYPE_ERROR); + if (off >= sizeof(errlog)) { + return NVME_INVALID_FIELD | NVME_DNR; } - if (off > sizeof(errlog)) { - return NVME_INVALID_FIELD | NVME_DNR; + if (!rae) { + nvme_clear_events(n, NVME_AER_TYPE_ERROR); } memset(&errlog, 0x0, sizeof(errlog)); - trans_len = MIN(sizeof(errlog) - off, buf_len); - return nvme_dma_prp(n, (uint8_t *)&errlog, trans_len, prp1, prp2, - DMA_DIRECTION_FROM_DEVICE, req); + return nvme_dma(n, (uint8_t *)&errlog, trans_len, + DMA_DIRECTION_FROM_DEVICE, req); } static uint16_t nvme_get_log(NvmeCtrl *n, NvmeRequest *req) @@ -1040,7 +1365,8 @@ static uint16_t nvme_del_cq(NvmeCtrl *n, NvmeRequest *req) } static void nvme_init_cq(NvmeCQueue *cq, NvmeCtrl *n, uint64_t dma_addr, - uint16_t cqid, uint16_t vector, uint16_t size, uint16_t irq_enabled) + uint16_t cqid, uint16_t vector, uint16_t size, + uint16_t irq_enabled) { int ret; @@ -1073,17 +1399,18 @@ static uint16_t nvme_create_cq(NvmeCtrl *n, NvmeRequest *req) trace_pci_nvme_create_cq(prp1, cqid, vector, qsize, qflags, NVME_CQ_FLAGS_IEN(qflags) != 0); - if (unlikely(!cqid || !nvme_check_cqid(n, cqid))) { + if (unlikely(!cqid || cqid > n->params.max_ioqpairs || + n->cq[cqid] != NULL)) { trace_pci_nvme_err_invalid_create_cq_cqid(cqid); - return NVME_INVALID_CQID | NVME_DNR; + return NVME_INVALID_QID | NVME_DNR; } if (unlikely(!qsize || qsize > NVME_CAP_MQES(n->bar.cap))) { trace_pci_nvme_err_invalid_create_cq_size(qsize); return NVME_MAX_QSIZE_EXCEEDED | NVME_DNR; } - if (unlikely(!prp1)) { + if (unlikely(prp1 & (n->page_size - 1))) { trace_pci_nvme_err_invalid_create_cq_addr(prp1); - return NVME_INVALID_FIELD | NVME_DNR; + return NVME_INVALID_PRP_OFFSET | NVME_DNR; } if (unlikely(!msix_enabled(&n->parent_obj) && vector)) { trace_pci_nvme_err_invalid_create_cq_vector(vector); @@ -1100,7 +1427,7 @@ static uint16_t nvme_create_cq(NvmeCtrl *n, NvmeRequest *req) cq = g_malloc0(sizeof(*cq)); nvme_init_cq(cq, n, prp1, cqid, vector, qsize + 1, - NVME_CQ_FLAGS_IEN(qflags)); + NVME_CQ_FLAGS_IEN(qflags)); /* * It is only required to set qs_created when creating a completion queue; @@ -1113,35 +1440,34 @@ static uint16_t nvme_create_cq(NvmeCtrl *n, NvmeRequest *req) static uint16_t nvme_identify_ctrl(NvmeCtrl *n, NvmeRequest *req) { - NvmeIdentify *c = (NvmeIdentify *)&req->cmd; - uint64_t prp1 = le64_to_cpu(c->prp1); - uint64_t prp2 = le64_to_cpu(c->prp2); - trace_pci_nvme_identify_ctrl(); - return nvme_dma_prp(n, (uint8_t *)&n->id_ctrl, sizeof(n->id_ctrl), prp1, - prp2, DMA_DIRECTION_FROM_DEVICE, req); + return nvme_dma(n, (uint8_t *)&n->id_ctrl, sizeof(n->id_ctrl), + DMA_DIRECTION_FROM_DEVICE, req); } static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeRequest *req) { NvmeNamespace *ns; NvmeIdentify *c = (NvmeIdentify *)&req->cmd; + NvmeIdNs *id_ns, inactive = { 0 }; uint32_t nsid = le32_to_cpu(c->nsid); - uint64_t prp1 = le64_to_cpu(c->prp1); - uint64_t prp2 = le64_to_cpu(c->prp2); trace_pci_nvme_identify_ns(nsid); - if (unlikely(nsid == 0 || nsid > n->num_namespaces)) { - trace_pci_nvme_err_invalid_ns(nsid, n->num_namespaces); + if (!nvme_nsid_valid(n, nsid) || nsid == NVME_NSID_BROADCAST) { return NVME_INVALID_NSID | NVME_DNR; } - ns = &n->namespaces[nsid - 1]; + ns = nvme_ns(n, nsid); + if (unlikely(!ns)) { + id_ns = &inactive; + } else { + id_ns = &ns->id_ns; + } - return nvme_dma_prp(n, (uint8_t *)&ns->id_ns, sizeof(ns->id_ns), prp1, - prp2, DMA_DIRECTION_FROM_DEVICE, req); + return nvme_dma(n, (uint8_t *)id_ns, sizeof(NvmeIdNs), + DMA_DIRECTION_FROM_DEVICE, req); } static uint16_t nvme_identify_nslist(NvmeCtrl *n, NvmeRequest *req) @@ -1149,11 +1475,9 @@ static uint16_t nvme_identify_nslist(NvmeCtrl *n, NvmeRequest *req) NvmeIdentify *c = (NvmeIdentify *)&req->cmd; static const int data_len = NVME_IDENTIFY_DATA_SIZE; uint32_t min_nsid = le32_to_cpu(c->nsid); - uint64_t prp1 = le64_to_cpu(c->prp1); - uint64_t prp2 = le64_to_cpu(c->prp2); uint32_t *list; uint16_t ret; - int i, j = 0; + int j = 0; trace_pci_nvme_identify_nslist(min_nsid); @@ -1168,17 +1492,17 @@ static uint16_t nvme_identify_nslist(NvmeCtrl *n, NvmeRequest *req) } list = g_malloc0(data_len); - for (i = 0; i < n->num_namespaces; i++) { - if (i < min_nsid) { + for (int i = 1; i <= n->num_namespaces; i++) { + if (i <= min_nsid || !nvme_ns(n, i)) { continue; } - list[j++] = cpu_to_le32(i + 1); + list[j++] = cpu_to_le32(i); if (j == data_len / sizeof(uint32_t)) { break; } } - ret = nvme_dma_prp(n, (uint8_t *)list, data_len, prp1, prp2, - DMA_DIRECTION_FROM_DEVICE, req); + ret = nvme_dma(n, (uint8_t *)list, data_len, DMA_DIRECTION_FROM_DEVICE, + req); g_free(list); return ret; } @@ -1187,9 +1511,6 @@ static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeRequest *req) { NvmeIdentify *c = (NvmeIdentify *)&req->cmd; uint32_t nsid = le32_to_cpu(c->nsid); - uint64_t prp1 = le64_to_cpu(c->prp1); - uint64_t prp2 = le64_to_cpu(c->prp2); - uint8_t list[NVME_IDENTIFY_DATA_SIZE]; struct data { @@ -1203,11 +1524,14 @@ static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeRequest *req) trace_pci_nvme_identify_ns_descr_list(nsid); - if (unlikely(nsid == 0 || nsid > n->num_namespaces)) { - trace_pci_nvme_err_invalid_ns(nsid, n->num_namespaces); + if (!nvme_nsid_valid(n, nsid) || nsid == NVME_NSID_BROADCAST) { return NVME_INVALID_NSID | NVME_DNR; } + if (unlikely(!nvme_ns(n, nsid))) { + return NVME_INVALID_FIELD | NVME_DNR; + } + memset(list, 0x0, sizeof(list)); /* @@ -1220,8 +1544,8 @@ static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeRequest *req) ns_descrs->uuid.hdr.nidl = NVME_NIDT_UUID_LEN; stl_be_p(&ns_descrs->uuid.v, nsid); - return nvme_dma_prp(n, list, NVME_IDENTIFY_DATA_SIZE, prp1, prp2, - DMA_DIRECTION_FROM_DEVICE, req); + return nvme_dma(n, list, NVME_IDENTIFY_DATA_SIZE, + DMA_DIRECTION_FROM_DEVICE, req); } static uint16_t nvme_identify(NvmeCtrl *n, NvmeRequest *req) @@ -1292,14 +1616,10 @@ static inline uint64_t nvme_get_timestamp(const NvmeCtrl *n) static uint16_t nvme_get_feature_timestamp(NvmeCtrl *n, NvmeRequest *req) { - NvmeCmd *cmd = &req->cmd; - uint64_t prp1 = le64_to_cpu(cmd->dptr.prp1); - uint64_t prp2 = le64_to_cpu(cmd->dptr.prp2); - uint64_t timestamp = nvme_get_timestamp(n); - return nvme_dma_prp(n, (uint8_t *)×tamp, sizeof(timestamp), prp1, - prp2, DMA_DIRECTION_FROM_DEVICE, req); + return nvme_dma(n, (uint8_t *)×tamp, sizeof(timestamp), + DMA_DIRECTION_FROM_DEVICE, req); } static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeRequest *req) @@ -1317,14 +1637,14 @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeRequest *req) [NVME_ARBITRATION] = NVME_ARB_AB_NOLIMIT, }; - trace_pci_nvme_getfeat(nvme_cid(req), fid, sel, dw11); + trace_pci_nvme_getfeat(nvme_cid(req), nsid, fid, sel, dw11); if (!nvme_feature_support[fid]) { return NVME_INVALID_FIELD | NVME_DNR; } if (nvme_feature_cap[fid] & NVME_FEAT_CAP_NS) { - if (!nsid || nsid > n->num_namespaces) { + if (!nvme_nsid_valid(n, nsid) || nsid == NVME_NSID_BROADCAST) { /* * The Reservation Notification Mask and Reservation Persistence * features require a status code of Invalid Field in Command when @@ -1334,6 +1654,10 @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeRequest *req) */ return NVME_INVALID_NSID | NVME_DNR; } + + if (!nvme_ns(n, nsid)) { + return NVME_INVALID_FIELD | NVME_DNR; + } } switch (sel) { @@ -1371,7 +1695,7 @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeRequest *req) return NVME_INVALID_FIELD | NVME_DNR; case NVME_VOLATILE_WRITE_CACHE: - result = blk_enable_write_cache(n->conf.blk); + result = n->features.vwc; trace_pci_nvme_getfeat_vwcache(result ? "enabled" : "disabled"); goto out; case NVME_ASYNCHRONOUS_EVENT_CONF: @@ -1428,12 +1752,9 @@ static uint16_t nvme_set_feature_timestamp(NvmeCtrl *n, NvmeRequest *req) { uint16_t ret; uint64_t timestamp; - NvmeCmd *cmd = &req->cmd; - uint64_t prp1 = le64_to_cpu(cmd->dptr.prp1); - uint64_t prp2 = le64_to_cpu(cmd->dptr.prp2); - ret = nvme_dma_prp(n, (uint8_t *)×tamp, sizeof(timestamp), prp1, - prp2, DMA_DIRECTION_TO_DEVICE, req); + ret = nvme_dma(n, (uint8_t *)×tamp, sizeof(timestamp), + DMA_DIRECTION_TO_DEVICE, req); if (ret != NVME_SUCCESS) { return ret; } @@ -1445,6 +1766,8 @@ static uint16_t nvme_set_feature_timestamp(NvmeCtrl *n, NvmeRequest *req) static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeRequest *req) { + NvmeNamespace *ns; + NvmeCmd *cmd = &req->cmd; uint32_t dw10 = le32_to_cpu(cmd->cdw10); uint32_t dw11 = le32_to_cpu(cmd->cdw11); @@ -1452,7 +1775,7 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeRequest *req) uint8_t fid = NVME_GETSETFEAT_FID(dw10); uint8_t save = NVME_SETFEAT_SAVE(dw10); - trace_pci_nvme_setfeat(nvme_cid(req), fid, save, dw11); + trace_pci_nvme_setfeat(nvme_cid(req), nsid, fid, save, dw11); if (save) { return NVME_FID_NOT_SAVEABLE | NVME_DNR; @@ -1463,12 +1786,18 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeRequest *req) } if (nvme_feature_cap[fid] & NVME_FEAT_CAP_NS) { - if (!nsid || (nsid != NVME_NSID_BROADCAST && - nsid > n->num_namespaces)) { - return NVME_INVALID_NSID | NVME_DNR; + if (nsid != NVME_NSID_BROADCAST) { + if (!nvme_nsid_valid(n, nsid)) { + return NVME_INVALID_NSID | NVME_DNR; + } + + ns = nvme_ns(n, nsid); + if (unlikely(!ns)) { + return NVME_INVALID_FIELD | NVME_DNR; + } } } else if (nsid && nsid != NVME_NSID_BROADCAST) { - if (nsid > n->num_namespaces) { + if (!nvme_nsid_valid(n, nsid)) { return NVME_INVALID_NSID | NVME_DNR; } @@ -1497,7 +1826,7 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeRequest *req) } if (((n->temperature >= n->features.temp_thresh_hi) || - (n->temperature <= n->features.temp_thresh_low)) && + (n->temperature <= n->features.temp_thresh_low)) && NVME_AEC_SMART(n->features.async_config) & NVME_SMART_TEMPERATURE) { nvme_enqueue_event(n, NVME_AER_TYPE_SMART, NVME_AER_INFO_SMART_TEMP_THRESH, @@ -1506,12 +1835,23 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeRequest *req) break; case NVME_VOLATILE_WRITE_CACHE: - if (!(dw11 & 0x1) && blk_enable_write_cache(n->conf.blk)) { - blk_flush(n->conf.blk); + n->features.vwc = dw11 & 0x1; + + for (int i = 1; i <= n->num_namespaces; i++) { + ns = nvme_ns(n, i); + if (!ns) { + continue; + } + + if (!(dw11 & 0x1) && blk_enable_write_cache(ns->blkconf.blk)) { + blk_flush(ns->blkconf.blk); + } + + blk_set_enable_write_cache(ns->blkconf.blk, dw11 & 1); } - blk_set_enable_write_cache(n->conf.blk, dw11 & 1); break; + case NVME_NUMBER_OF_QUEUES: if (n->qs_created) { return NVME_CMD_SEQ_ERROR | NVME_DNR; @@ -1564,7 +1904,8 @@ static uint16_t nvme_aer(NvmeCtrl *n, NvmeRequest *req) static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeRequest *req) { - trace_pci_nvme_admin_cmd(nvme_cid(req), nvme_sqid(req), req->cmd.opcode); + trace_pci_nvme_admin_cmd(nvme_cid(req), nvme_sqid(req), req->cmd.opcode, + nvme_adm_opc_str(req->cmd.opcode)); switch (req->cmd.opcode) { case NVME_ADM_CMD_DELETE_SQ: @@ -1606,7 +1947,12 @@ static void nvme_process_sq(void *opaque) while (!(nvme_sq_empty(sq) || QTAILQ_EMPTY(&sq->req_list))) { addr = sq->dma_addr + sq->head * n->sqe_size; - nvme_addr_read(n, addr, (void *)&cmd, sizeof(cmd)); + if (nvme_addr_read(n, addr, (void *)&cmd, sizeof(cmd))) { + trace_pci_nvme_err_addr_read(addr); + trace_pci_nvme_err_cfs(); + n->bar.csts = NVME_CSTS_FAILED; + break; + } nvme_inc_sq_head(sq); req = QTAILQ_FIRST(&sq->req_list); @@ -1627,9 +1973,17 @@ static void nvme_process_sq(void *opaque) static void nvme_clear_ctrl(NvmeCtrl *n) { + NvmeNamespace *ns; int i; - blk_drain(n->conf.blk); + for (i = 1; i <= n->num_namespaces; i++) { + ns = nvme_ns(n, i); + if (!ns) { + continue; + } + + nvme_ns_drain(ns); + } for (i = 0; i < n->params.max_ioqpairs + 1; i++) { if (n->sq[i] != NULL) { @@ -1652,7 +2006,15 @@ static void nvme_clear_ctrl(NvmeCtrl *n) n->outstanding_aers = 0; n->qs_created = false; - blk_flush(n->conf.blk); + for (i = 1; i <= n->num_namespaces; i++) { + ns = nvme_ns(n, i); + if (!ns) { + continue; + } + + nvme_ns_flush(ns); + } + n->bar.cc = 0; } @@ -1685,6 +2047,10 @@ static int nvme_start_ctrl(NvmeCtrl *n) trace_pci_nvme_err_startfail_acq_misaligned(n->bar.acq); return -1; } + if (unlikely(!(NVME_CAP_CSS(n->bar.cap) & (1 << NVME_CC_CSS(n->bar.cc))))) { + trace_pci_nvme_err_startfail_css(NVME_CC_CSS(n->bar.cc)); + return -1; + } if (unlikely(NVME_CC_MPS(n->bar.cc) < NVME_CAP_MPSMIN(n->bar.cap))) { trace_pci_nvme_err_startfail_page_too_small( @@ -1742,9 +2108,9 @@ static int nvme_start_ctrl(NvmeCtrl *n) n->cqe_size = 1 << NVME_CC_IOCQES(n->bar.cc); n->sqe_size = 1 << NVME_CC_IOSQES(n->bar.cc); nvme_init_cq(&n->admin_cq, n, n->bar.acq, 0, 0, - NVME_AQA_ACQS(n->bar.aqa) + 1, 1); + NVME_AQA_ACQS(n->bar.aqa) + 1, 1); nvme_init_sq(&n->admin_sq, n, n->bar.asq, 0, 0, - NVME_AQA_ASQS(n->bar.aqa) + 1); + NVME_AQA_ASQS(n->bar.aqa) + 1); nvme_set_timestamp(n, 0ULL); @@ -1754,7 +2120,7 @@ static int nvme_start_ctrl(NvmeCtrl *n) } static void nvme_write_bar(NvmeCtrl *n, hwaddr offset, uint64_t data, - unsigned size) + unsigned size) { if (unlikely(offset & (sizeof(uint32_t) - 1))) { NVME_GUEST_ERR(pci_nvme_ub_mmiowr_misaligned32, @@ -1897,7 +2263,7 @@ static void nvme_write_bar(NvmeCtrl *n, hwaddr offset, uint64_t data, "invalid write to PMRSWTP register, ignored"); return; case 0xE14: /* TODO PMRMSC */ - break; + break; default: NVME_GUEST_ERR(pci_nvme_ub_mmiowr_invalid, "invalid MMIO write," @@ -2073,7 +2439,7 @@ static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val) } static void nvme_mmio_write(void *opaque, hwaddr addr, uint64_t data, - unsigned size) + unsigned size) { NvmeCtrl *n = (NvmeCtrl *)opaque; @@ -2097,7 +2463,7 @@ static const MemoryRegionOps nvme_mmio_ops = { }; static void nvme_cmb_write(void *opaque, hwaddr addr, uint64_t data, - unsigned size) + unsigned size) { NvmeCtrl *n = (NvmeCtrl *)opaque; stn_le_p(&n->cmbuf[addr], size, data); @@ -2130,6 +2496,11 @@ static void nvme_check_constraints(NvmeCtrl *n, Error **errp) params->max_ioqpairs = params->num_queues - 1; } + if (n->conf.blk) { + warn_report("drive property is deprecated; " + "please use an nvme-ns device instead"); + } + if (params->max_ioqpairs < 1 || params->max_ioqpairs > NVME_MAX_IOQPAIRS) { error_setg(errp, "max_ioqpairs must be between 1 and %d", @@ -2144,11 +2515,6 @@ static void nvme_check_constraints(NvmeCtrl *n, Error **errp) return; } - if (!n->conf.blk) { - error_setg(errp, "drive property not set"); - return; - } - if (!params->serial) { error_setg(errp, "serial property not set"); return; @@ -2172,11 +2538,10 @@ static void nvme_check_constraints(NvmeCtrl *n, Error **errp) static void nvme_init_state(NvmeCtrl *n) { - n->num_namespaces = 1; + n->num_namespaces = NVME_MAX_NAMESPACES; /* add one to max_ioqpairs to account for the admin queue pair */ n->reg_size = pow2ceil(sizeof(NvmeBar) + 2 * (n->params.max_ioqpairs + 1) * NVME_DB_SIZE); - n->namespaces = g_new0(NvmeNamespace, n->num_namespaces); n->sq = g_new0(NvmeSQueue *, n->params.max_ioqpairs + 1); n->cq = g_new0(NvmeCQueue *, n->params.max_ioqpairs + 1); n->temperature = NVME_TEMPERATURE; @@ -2185,34 +2550,41 @@ static void nvme_init_state(NvmeCtrl *n) n->aer_reqs = g_new0(NvmeRequest *, n->params.aerl + 1); } -static void nvme_init_blk(NvmeCtrl *n, Error **errp) +int nvme_register_namespace(NvmeCtrl *n, NvmeNamespace *ns, Error **errp) { - if (!blkconf_blocksizes(&n->conf, errp)) { - return; + uint32_t nsid = nvme_nsid(ns); + + if (nsid > NVME_MAX_NAMESPACES) { + error_setg(errp, "invalid namespace id (must be between 0 and %d)", + NVME_MAX_NAMESPACES); + return -1; } - blkconf_apply_backend_options(&n->conf, blk_is_read_only(n->conf.blk), - false, errp); -} -static void nvme_init_namespace(NvmeCtrl *n, NvmeNamespace *ns, Error **errp) -{ - int64_t bs_size; - NvmeIdNs *id_ns = &ns->id_ns; + if (!nsid) { + for (int i = 1; i <= n->num_namespaces; i++) { + NvmeNamespace *ns = nvme_ns(n, i); + if (!ns) { + nsid = ns->params.nsid = i; + break; + } + } - bs_size = blk_getlength(n->conf.blk); - if (bs_size < 0) { - error_setg_errno(errp, -bs_size, "could not get backing file size"); - return; + if (!nsid) { + error_setg(errp, "no free namespace id"); + return -1; + } + } else { + if (n->namespaces[nsid - 1]) { + error_setg(errp, "namespace id '%d' is already in use", nsid); + return -1; + } } - n->ns_size = bs_size; + trace_pci_nvme_register_namespace(nsid); - id_ns->lbaf[0].ds = BDRV_SECTOR_BITS; - id_ns->nsze = cpu_to_le64(nvme_ns_nlbas(n, ns)); + n->namespaces[nsid - 1] = ns; - /* no thin provisioning */ - id_ns->ncap = id_ns->nsze; - id_ns->nuse = id_ns->ncap; + return 0; } static void nvme_init_cmb(NvmeCtrl *n, PCIDevice *pci_dev) @@ -2292,6 +2664,15 @@ static void nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev, Error **errp) pci_conf[PCI_INTERRUPT_PIN] = 1; pci_config_set_prog_interface(pci_conf, 0x2); + + if (n->params.use_intel_id) { + pci_config_set_vendor_id(pci_conf, PCI_VENDOR_ID_INTEL); + pci_config_set_device_id(pci_conf, 0x5845); + } else { + pci_config_set_vendor_id(pci_conf, PCI_VENDOR_ID_REDHAT); + pci_config_set_device_id(pci_conf, PCI_DEVICE_ID_REDHAT_NVME); + } + pci_config_set_class(pci_conf, PCI_CLASS_STORAGE_EXPRESS); pcie_endpoint_cap_init(pci_dev, 0x80); @@ -2343,7 +2724,7 @@ static void nvme_init_ctrl(NvmeCtrl *n, PCIDevice *pci_dev) id->acl = 3; id->aerl = n->params.aerl; id->frmw = (NVME_NUM_FW_SLOTS << 1) | NVME_FRMW_SLOT1_RO; - id->lpa = NVME_LPA_EXTENDED; + id->lpa = NVME_LPA_NS_SMART | NVME_LPA_EXTENDED; /* recommended default value (~70 C) */ id->wctemp = cpu_to_le16(NVME_TEMPERATURE_WARNING); @@ -2355,6 +2736,10 @@ static void nvme_init_ctrl(NvmeCtrl *n, PCIDevice *pci_dev) id->oncs = cpu_to_le16(NVME_ONCS_WRITE_ZEROES | NVME_ONCS_TIMESTAMP | NVME_ONCS_FEATURES); + id->vwc = 0x1; + id->sgls = cpu_to_le32(NVME_CTRL_SGLS_SUPPORT_NO_ALIGN | + NVME_CTRL_SGLS_BITBUCKET); + subnqn = g_strdup_printf("nqn.2019-08.org.qemu:%s", n->params.serial); strpadcpy((char *)id->subnqn, sizeof(id->subnqn), subnqn, '\0'); g_free(subnqn); @@ -2362,15 +2747,13 @@ static void nvme_init_ctrl(NvmeCtrl *n, PCIDevice *pci_dev) id->psd[0].mp = cpu_to_le16(0x9c4); id->psd[0].enlat = cpu_to_le32(0x10); id->psd[0].exlat = cpu_to_le32(0x4); - if (blk_enable_write_cache(n->conf.blk)) { - id->vwc = 1; - } n->bar.cap = 0; NVME_CAP_SET_MQES(n->bar.cap, 0x7ff); NVME_CAP_SET_CQR(n->bar.cap, 1); NVME_CAP_SET_TO(n->bar.cap, 0xf); - NVME_CAP_SET_CSS(n->bar.cap, 1); + NVME_CAP_SET_CSS(n->bar.cap, NVME_CAP_CSS_NVM); + NVME_CAP_SET_CSS(n->bar.cap, NVME_CAP_CSS_ADMIN_ONLY); NVME_CAP_SET_MPSMAX(n->bar.cap, 4); n->bar.vs = NVME_SPEC_VER; @@ -2380,23 +2763,19 @@ static void nvme_init_ctrl(NvmeCtrl *n, PCIDevice *pci_dev) static void nvme_realize(PCIDevice *pci_dev, Error **errp) { NvmeCtrl *n = NVME(pci_dev); + NvmeNamespace *ns; Error *local_err = NULL; - int i; - nvme_check_constraints(n, &local_err); if (local_err) { error_propagate(errp, local_err); return; } - nvme_init_state(n); - nvme_init_blk(n, &local_err); - if (local_err) { - error_propagate(errp, local_err); - return; - } + qbus_create_inplace(&n->bus, sizeof(NvmeBus), TYPE_NVME_BUS, + &pci_dev->qdev, n->parent_obj.qdev.id); + nvme_init_state(n); nvme_init_pci(n, pci_dev, &local_err); if (local_err) { error_propagate(errp, local_err); @@ -2405,10 +2784,12 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp) nvme_init_ctrl(n, pci_dev); - for (i = 0; i < n->num_namespaces; i++) { - nvme_init_namespace(n, &n->namespaces[i], &local_err); - if (local_err) { - error_propagate(errp, local_err); + /* setup a namespace if the controller drive property was given */ + if (n->namespace.blkconf.blk) { + ns = &n->namespace; + ns->params.nsid = 1; + + if (nvme_ns_setup(n, ns, errp)) { return; } } @@ -2435,7 +2816,7 @@ static void nvme_exit(PCIDevice *pci_dev) } static Property nvme_props[] = { - DEFINE_BLOCK_PROPERTIES(NvmeCtrl, conf), + DEFINE_BLOCK_PROPERTIES(NvmeCtrl, namespace.blkconf), DEFINE_PROP_LINK("pmrdev", NvmeCtrl, pmrdev, TYPE_MEMORY_BACKEND, HostMemoryBackend *), DEFINE_PROP_STRING("serial", NvmeCtrl, params.serial), @@ -2446,6 +2827,7 @@ static Property nvme_props[] = { DEFINE_PROP_UINT8("aerl", NvmeCtrl, params.aerl, 3), DEFINE_PROP_UINT32("aer_max_queued", NvmeCtrl, params.aer_max_queued, 64), DEFINE_PROP_UINT8("mdts", NvmeCtrl, params.mdts, 7), + DEFINE_PROP_BOOL("use-intel-id", NvmeCtrl, params.use_intel_id, false), DEFINE_PROP_END_OF_LIST(), }; @@ -2462,8 +2844,6 @@ static void nvme_class_init(ObjectClass *oc, void *data) pc->realize = nvme_realize; pc->exit = nvme_exit; pc->class_id = PCI_CLASS_STORAGE_EXPRESS; - pc->vendor_id = PCI_VENDOR_ID_INTEL; - pc->device_id = 0x5845; pc->revision = 2; set_bit(DEVICE_CATEGORY_STORAGE, dc->categories); @@ -2476,26 +2856,35 @@ static void nvme_instance_init(Object *obj) { NvmeCtrl *s = NVME(obj); - device_add_bootindex_property(obj, &s->conf.bootindex, - "bootindex", "/namespace@1,0", - DEVICE(obj)); + if (s->namespace.blkconf.blk) { + device_add_bootindex_property(obj, &s->namespace.blkconf.bootindex, + "bootindex", "/namespace@1,0", + DEVICE(obj)); + } } static const TypeInfo nvme_info = { .name = TYPE_NVME, .parent = TYPE_PCI_DEVICE, .instance_size = sizeof(NvmeCtrl), - .class_init = nvme_class_init, .instance_init = nvme_instance_init, + .class_init = nvme_class_init, .interfaces = (InterfaceInfo[]) { { INTERFACE_PCIE_DEVICE }, { } }, }; +static const TypeInfo nvme_bus_info = { + .name = TYPE_NVME_BUS, + .parent = TYPE_BUS, + .instance_size = sizeof(NvmeBus), +}; + static void nvme_register_types(void) { type_register_static(&nvme_info); + type_register_static(&nvme_bus_info); } type_init(nvme_register_types) diff --git a/hw/block/nvme.h b/hw/block/nvme.h index 52ba794f2e..e080a2318a 100644 --- a/hw/block/nvme.h +++ b/hw/block/nvme.h @@ -2,6 +2,9 @@ #define HW_NVME_H #include "block/nvme.h" +#include "nvme-ns.h" + +#define NVME_MAX_NAMESPACES 256 typedef struct NvmeParams { char *serial; @@ -12,6 +15,7 @@ typedef struct NvmeParams { uint8_t aerl; uint32_t aer_max_queued; uint8_t mdts; + bool use_intel_id; } NvmeParams; typedef struct NvmeAsyncEvent { @@ -32,6 +36,34 @@ typedef struct NvmeRequest { QTAILQ_ENTRY(NvmeRequest)entry; } NvmeRequest; +static inline const char *nvme_adm_opc_str(uint8_t opc) +{ + switch (opc) { + case NVME_ADM_CMD_DELETE_SQ: return "NVME_ADM_CMD_DELETE_SQ"; + case NVME_ADM_CMD_CREATE_SQ: return "NVME_ADM_CMD_CREATE_SQ"; + case NVME_ADM_CMD_GET_LOG_PAGE: return "NVME_ADM_CMD_GET_LOG_PAGE"; + case NVME_ADM_CMD_DELETE_CQ: return "NVME_ADM_CMD_DELETE_CQ"; + case NVME_ADM_CMD_CREATE_CQ: return "NVME_ADM_CMD_CREATE_CQ"; + case NVME_ADM_CMD_IDENTIFY: return "NVME_ADM_CMD_IDENTIFY"; + case NVME_ADM_CMD_ABORT: return "NVME_ADM_CMD_ABORT"; + case NVME_ADM_CMD_SET_FEATURES: return "NVME_ADM_CMD_SET_FEATURES"; + case NVME_ADM_CMD_GET_FEATURES: return "NVME_ADM_CMD_GET_FEATURES"; + case NVME_ADM_CMD_ASYNC_EV_REQ: return "NVME_ADM_CMD_ASYNC_EV_REQ"; + default: return "NVME_ADM_CMD_UNKNOWN"; + } +} + +static inline const char *nvme_io_opc_str(uint8_t opc) +{ + switch (opc) { + case NVME_CMD_FLUSH: return "NVME_NVM_CMD_FLUSH"; + case NVME_CMD_WRITE: return "NVME_NVM_CMD_WRITE"; + case NVME_CMD_READ: return "NVME_NVM_CMD_READ"; + case NVME_CMD_WRITE_ZEROES: return "NVME_NVM_CMD_WRITE_ZEROES"; + default: return "NVME_NVM_CMD_UNKNOWN"; + } +} + typedef struct NvmeSQueue { struct NvmeCtrl *ctrl; uint16_t sqid; @@ -62,20 +94,12 @@ typedef struct NvmeCQueue { QTAILQ_HEAD(, NvmeRequest) req_list; } NvmeCQueue; -typedef struct NvmeNamespace { - NvmeIdNs id_ns; -} NvmeNamespace; - -static inline NvmeLBAF *nvme_ns_lbaf(NvmeNamespace *ns) -{ - NvmeIdNs *id_ns = &ns->id_ns; - return &id_ns->lbaf[NVME_ID_NS_FLBAS_INDEX(id_ns->flbas)]; -} +#define TYPE_NVME_BUS "nvme-bus" +#define NVME_BUS(obj) OBJECT_CHECK(NvmeBus, (obj), TYPE_NVME_BUS) -static inline uint8_t nvme_ns_lbads(NvmeNamespace *ns) -{ - return nvme_ns_lbaf(ns)->ds; -} +typedef struct NvmeBus { + BusState parent_bus; +} NvmeBus; #define TYPE_NVME "nvme" #define NVME(obj) \ @@ -87,6 +111,7 @@ typedef struct NvmeFeatureVal { uint16_t temp_thresh_low; }; uint32_t async_config; + uint32_t vwc; } NvmeFeatureVal; typedef struct NvmeCtrl { @@ -94,8 +119,9 @@ typedef struct NvmeCtrl { MemoryRegion iomem; MemoryRegion ctrl_mem; NvmeBar bar; - BlockConf conf; NvmeParams params; + NvmeBus bus; + BlockConf conf; bool qs_created; uint32_t page_size; @@ -106,7 +132,6 @@ typedef struct NvmeCtrl { uint32_t reg_size; uint32_t num_namespaces; uint32_t max_q_ents; - uint64_t ns_size; uint8_t outstanding_aers; uint8_t *cmbuf; uint32_t irq_status; @@ -122,7 +147,8 @@ typedef struct NvmeCtrl { QTAILQ_HEAD(, NvmeAsyncEvent) aer_queue; int aer_queued; - NvmeNamespace *namespaces; + NvmeNamespace namespace; + NvmeNamespace *namespaces[NVME_MAX_NAMESPACES]; NvmeSQueue **sq; NvmeCQueue **cq; NvmeSQueue admin_sq; @@ -131,10 +157,29 @@ typedef struct NvmeCtrl { NvmeFeatureVal features; } NvmeCtrl; -/* calculate the number of LBAs that the namespace can accomodate */ -static inline uint64_t nvme_ns_nlbas(NvmeCtrl *n, NvmeNamespace *ns) +static inline NvmeNamespace *nvme_ns(NvmeCtrl *n, uint32_t nsid) { - return n->ns_size >> nvme_ns_lbads(ns); + if (!nsid || nsid > n->num_namespaces) { + return NULL; + } + + return n->namespaces[nsid - 1]; } +static inline NvmeCQueue *nvme_cq(NvmeRequest *req) +{ + NvmeSQueue *sq = req->sq; + NvmeCtrl *n = sq->ctrl; + + return n->cq[sq->cqid]; +} + +static inline NvmeCtrl *nvme_ctrl(NvmeRequest *req) +{ + NvmeSQueue *sq = req->sq; + return sq->ctrl; +} + +int nvme_register_namespace(NvmeCtrl *n, NvmeNamespace *ns, Error **errp); + #endif /* HW_NVME_H */ diff --git a/hw/block/trace-events b/hw/block/trace-events index ec94c56a41..c1537e3ac0 100644 --- a/hw/block/trace-events +++ b/hw/block/trace-events @@ -29,6 +29,7 @@ hd_geometry_guess(void *blk, uint32_t cyls, uint32_t heads, uint32_t secs, int t # nvme.c # nvme traces for successful events +pci_nvme_register_namespace(uint32_t nsid) "nsid %"PRIu32"" pci_nvme_irq_msix(uint32_t vector) "raising MSI-X IRQ vector %u" pci_nvme_irq_pin(void) "pulsing IRQ pin" pci_nvme_irq_masked(void) "IRQ is masked" @@ -36,11 +37,12 @@ pci_nvme_dma_read(uint64_t prp1, uint64_t prp2) "DMA read, prp1=0x%"PRIx64" prp2 pci_nvme_map_addr(uint64_t addr, uint64_t len) "addr 0x%"PRIx64" len %"PRIu64"" pci_nvme_map_addr_cmb(uint64_t addr, uint64_t len) "addr 0x%"PRIx64" len %"PRIu64"" pci_nvme_map_prp(uint64_t trans_len, uint32_t len, uint64_t prp1, uint64_t prp2, int num_prps) "trans_len %"PRIu64" len %"PRIu32" prp1 0x%"PRIx64" prp2 0x%"PRIx64" num_prps %d" -pci_nvme_io_cmd(uint16_t cid, uint32_t nsid, uint16_t sqid, uint8_t opcode) "cid %"PRIu16" nsid %"PRIu32" sqid %"PRIu16" opc 0x%"PRIx8"" -pci_nvme_admin_cmd(uint16_t cid, uint16_t sqid, uint8_t opcode) "cid %"PRIu16" sqid %"PRIu16" opc 0x%"PRIx8"" -pci_nvme_rw(const char *verb, uint32_t blk_count, uint64_t byte_count, uint64_t lba) "%s %"PRIu32" blocks (%"PRIu64" bytes) from LBA %"PRIu64"" -pci_nvme_rw_cb(uint16_t cid) "cid %"PRIu16"" -pci_nvme_write_zeroes(uint16_t cid, uint64_t slba, uint32_t nlb) "cid %"PRIu16" slba %"PRIu64" nlb %"PRIu32"" +pci_nvme_map_sgl(uint16_t cid, uint8_t typ, uint64_t len) "cid %"PRIu16" type 0x%"PRIx8" len %"PRIu64"" +pci_nvme_io_cmd(uint16_t cid, uint32_t nsid, uint16_t sqid, uint8_t opcode, const char *opname) "cid %"PRIu16" nsid %"PRIu32" sqid %"PRIu16" opc 0x%"PRIx8" opname '%s'" +pci_nvme_admin_cmd(uint16_t cid, uint16_t sqid, uint8_t opcode, const char *opname) "cid %"PRIu16" sqid %"PRIu16" opc 0x%"PRIx8" opname '%s'" +pci_nvme_rw(uint16_t cid, const char *verb, uint32_t nsid, uint32_t nlb, uint64_t count, uint64_t lba) "cid %"PRIu16" opname '%s' nsid %"PRIu32" nlb %"PRIu32" count %"PRIu64" lba 0x%"PRIx64"" +pci_nvme_rw_cb(uint16_t cid, const char *blkname) "cid %"PRIu16" blk '%s'" +pci_nvme_write_zeroes(uint16_t cid, uint32_t nsid, uint64_t slba, uint32_t nlb) "cid %"PRIu16" nsid %"PRIu32" slba %"PRIu64" nlb %"PRIu32"" pci_nvme_create_sq(uint64_t addr, uint16_t sqid, uint16_t cqid, uint16_t qsize, uint16_t qflags) "create submission queue, addr=0x%"PRIx64", sqid=%"PRIu16", cqid=%"PRIu16", qsize=%"PRIu16", qflags=%"PRIu16"" pci_nvme_create_cq(uint64_t addr, uint16_t cqid, uint16_t vector, uint16_t size, uint16_t qflags, int ien) "create completion queue, addr=0x%"PRIx64", cqid=%"PRIu16", vector=%"PRIu16", qsize=%"PRIu16", qflags=%"PRIu16", ien=%d" pci_nvme_del_sq(uint16_t qid) "deleting submission queue sqid=%"PRIu16"" @@ -50,8 +52,8 @@ pci_nvme_identify_ns(uint32_t ns) "nsid %"PRIu32"" pci_nvme_identify_nslist(uint32_t ns) "nsid %"PRIu32"" pci_nvme_identify_ns_descr_list(uint32_t ns) "nsid %"PRIu32"" pci_nvme_get_log(uint16_t cid, uint8_t lid, uint8_t lsp, uint8_t rae, uint32_t len, uint64_t off) "cid %"PRIu16" lid 0x%"PRIx8" lsp 0x%"PRIx8" rae 0x%"PRIx8" len %"PRIu32" off %"PRIu64"" -pci_nvme_getfeat(uint16_t cid, uint8_t fid, uint8_t sel, uint32_t cdw11) "cid %"PRIu16" fid 0x%"PRIx8" sel 0x%"PRIx8" cdw11 0x%"PRIx32"" -pci_nvme_setfeat(uint16_t cid, uint8_t fid, uint8_t save, uint32_t cdw11) "cid %"PRIu16" fid 0x%"PRIx8" save 0x%"PRIx8" cdw11 0x%"PRIx32"" +pci_nvme_getfeat(uint16_t cid, uint32_t nsid, uint8_t fid, uint8_t sel, uint32_t cdw11) "cid %"PRIu16" nsid 0x%"PRIx32" fid 0x%"PRIx8" sel 0x%"PRIx8" cdw11 0x%"PRIx32"" +pci_nvme_setfeat(uint16_t cid, uint32_t nsid, uint8_t fid, uint8_t save, uint32_t cdw11) "cid %"PRIu16" nsid 0x%"PRIx32" fid 0x%"PRIx8" save 0x%"PRIx8" cdw11 0x%"PRIx32"" pci_nvme_getfeat_vwcache(const char* result) "get feature volatile write cache, result=%s" pci_nvme_getfeat_numq(int result) "get feature number of queues, result=%d" pci_nvme_setfeat_numq(int reqcq, int reqsq, int gotcq, int gotsq) "requested cq_count=%d sq_count=%d, responding with cq_count=%d sq_count=%d" @@ -70,7 +72,7 @@ pci_nvme_enqueue_req_completion(uint16_t cid, uint16_t cqid, uint16_t status) "c pci_nvme_mmio_read(uint64_t addr) "addr 0x%"PRIx64"" pci_nvme_mmio_write(uint64_t addr, uint64_t data) "addr 0x%"PRIx64" data 0x%"PRIx64"" pci_nvme_mmio_doorbell_cq(uint16_t cqid, uint16_t new_head) "cqid %"PRIu16" new_head %"PRIu16"" -pci_nvme_mmio_doorbell_sq(uint16_t sqid, uint16_t new_tail) "cqid %"PRIu16" new_tail %"PRIu16"" +pci_nvme_mmio_doorbell_sq(uint16_t sqid, uint16_t new_tail) "sqid %"PRIu16" new_tail %"PRIu16"" pci_nvme_mmio_intm_set(uint64_t data, uint64_t new_mask) "wrote MMIO, interrupt mask set, data=0x%"PRIx64", new_mask=0x%"PRIx64"" pci_nvme_mmio_intm_clr(uint64_t data, uint64_t new_mask) "wrote MMIO, interrupt mask clr, data=0x%"PRIx64", new_mask=0x%"PRIx64"" pci_nvme_mmio_cfg(uint64_t data) "wrote MMIO, config controller config=0x%"PRIx64"" @@ -86,12 +88,17 @@ pci_nvme_mmio_shutdown_cleared(void) "shutdown bit cleared" # nvme traces for error conditions pci_nvme_err_mdts(uint16_t cid, size_t len) "cid %"PRIu16" len %zu" +pci_nvme_err_req_status(uint16_t cid, uint32_t nsid, uint16_t status, uint8_t opc) "cid %"PRIu16" nsid %"PRIu32" status 0x%"PRIx16" opc 0x%"PRIx8"" +pci_nvme_err_addr_read(uint64_t addr) "addr 0x%"PRIx64"" +pci_nvme_err_addr_write(uint64_t addr) "addr 0x%"PRIx64"" +pci_nvme_err_cfs(void) "controller fatal status" +pci_nvme_err_aio(uint16_t cid, const char *errname, uint16_t status) "cid %"PRIu16" err '%s' status 0x%"PRIx16"" +pci_nvme_err_invalid_sgld(uint16_t cid, uint8_t typ) "cid %"PRIu16" type 0x%"PRIx8"" +pci_nvme_err_invalid_num_sgld(uint16_t cid, uint8_t typ) "cid %"PRIu16" type 0x%"PRIx8"" +pci_nvme_err_invalid_sgl_excess_length(uint16_t cid) "cid %"PRIu16"" pci_nvme_err_invalid_dma(void) "PRP/SGL is too small for transfer size" -pci_nvme_err_invalid_prplist_ent(uint64_t prplist) "PRP list entry is null or not page aligned: 0x%"PRIx64"" +pci_nvme_err_invalid_prplist_ent(uint64_t prplist) "PRP list entry is not page aligned: 0x%"PRIx64"" pci_nvme_err_invalid_prp2_align(uint64_t prp2) "PRP2 is not page aligned: 0x%"PRIx64"" -pci_nvme_err_invalid_prp2_missing(void) "PRP2 is null and more data to be transferred" -pci_nvme_err_invalid_prp(void) "invalid PRP" -pci_nvme_err_invalid_ns(uint32_t ns, uint32_t limit) "invalid namespace %u not within 1-%u" pci_nvme_err_invalid_opc(uint8_t opc) "invalid opcode 0x%"PRIx8"" pci_nvme_err_invalid_admin_opc(uint8_t opc) "invalid admin opcode 0x%"PRIx8"" pci_nvme_err_invalid_lba_range(uint64_t start, uint64_t len, uint64_t limit) "Invalid LBA start=%"PRIu64" len=%"PRIu64" limit=%"PRIu64"" @@ -124,6 +131,7 @@ pci_nvme_err_startfail_cqent_too_small(uint8_t log2ps, uint8_t maxlog2ps) "nvme_ pci_nvme_err_startfail_cqent_too_large(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the completion queue entry size is too large: log2size=%u, max=%u" pci_nvme_err_startfail_sqent_too_small(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the submission queue entry size is too small: log2size=%u, min=%u" pci_nvme_err_startfail_sqent_too_large(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the submission queue entry size is too large: log2size=%u, max=%u" +pci_nvme_err_startfail_css(uint8_t css) "nvme_start_ctrl failed because invalid command set selected:%u" pci_nvme_err_startfail_asqent_sz_zero(void) "nvme_start_ctrl failed because the admin submission queue size is zero" pci_nvme_err_startfail_acqent_sz_zero(void) "nvme_start_ctrl failed because the admin completion queue size is zero" pci_nvme_err_startfail(void) "setting controller enable bit failed" diff --git a/hw/core/machine.c b/hw/core/machine.c index c5e0e79e6d..98b87f76cb 100644 --- a/hw/core/machine.c +++ b/hw/core/machine.c @@ -34,6 +34,7 @@ GlobalProperty hw_compat_5_1[] = { { "vhost-user-scsi", "num_queues", "1"}, { "virtio-blk-device", "num-queues", "1"}, { "virtio-scsi-device", "num_queues", "1"}, + { "nvme", "use-intel-id", "on"}, }; const size_t hw_compat_5_1_len = G_N_ELEMENTS(hw_compat_5_1); diff --git a/hw/ide/piix.c b/hw/ide/piix.c index b402a93636..b9860e35a5 100644 --- a/hw/ide/piix.c +++ b/hw/ide/piix.c @@ -164,30 +164,29 @@ static void pci_piix_ide_realize(PCIDevice *dev, Error **errp) int pci_piix3_xen_ide_unplug(DeviceState *dev, bool aux) { PCIIDEState *pci_ide; - DriveInfo *di; int i; IDEDevice *idedev; + IDEBus *idebus; + BlockBackend *blk; pci_ide = PCI_IDE(dev); for (i = aux ? 1 : 0; i < 4; i++) { - di = drive_get_by_index(IF_IDE, i); - if (di != NULL && !di->media_cd) { - BlockBackend *blk = blk_by_legacy_dinfo(di); - DeviceState *ds = blk_get_attached_dev(blk); + idebus = &pci_ide->bus[i / 2]; + blk = idebus->ifs[i % 2].blk; - blk_drain(blk); - blk_flush(blk); - - if (ds) { - blk_detach_dev(blk, ds); - } - pci_ide->bus[di->bus].ifs[di->unit].blk = NULL; + if (blk && idebus->ifs[i % 2].drive_kind != IDE_CD) { if (!(i % 2)) { - idedev = pci_ide->bus[di->bus].master; + idedev = idebus->master; } else { - idedev = pci_ide->bus[di->bus].slave; + idedev = idebus->slave; } + + blk_drain(blk); + blk_flush(blk); + + blk_detach_dev(blk, DEVICE(idedev)); + idebus->ifs[i % 2].blk = NULL; idedev->conf.blk = NULL; monitor_remove_blk(blk); blk_unref(blk); diff --git a/include/block/nvme.h b/include/block/nvme.h index 65e68a82c8..8a46d9cf01 100644 --- a/include/block/nvme.h +++ b/include/block/nvme.h @@ -82,6 +82,11 @@ enum NvmeCapMask { #define NVME_CAP_SET_PMRS(cap, val) (cap |= (uint64_t)(val & CAP_PMR_MASK)\ << CAP_PMR_SHIFT) +enum NvmeCapCss { + NVME_CAP_CSS_NVM = 1 << 0, + NVME_CAP_CSS_ADMIN_ONLY = 1 << 7, +}; + enum NvmeCcShift { CC_EN_SHIFT = 0, CC_CSS_SHIFT = 4, @@ -110,6 +115,11 @@ enum NvmeCcMask { #define NVME_CC_IOSQES(cc) ((cc >> CC_IOSQES_SHIFT) & CC_IOSQES_MASK) #define NVME_CC_IOCQES(cc) ((cc >> CC_IOCQES_SHIFT) & CC_IOCQES_MASK) +enum NvmeCcCss { + NVME_CC_CSS_NVM = 0x0, + NVME_CC_CSS_ADMIN_ONLY = 0x7, +}; + enum NvmeCstsShift { CSTS_RDY_SHIFT = 0, CSTS_CFS_SHIFT = 1, @@ -412,9 +422,9 @@ typedef union NvmeCmdDptr { } NvmeCmdDptr; enum NvmePsdt { - PSDT_PRP = 0x0, - PSDT_SGL_MPTR_CONTIGUOUS = 0x1, - PSDT_SGL_MPTR_SGL = 0x2, + NVME_PSDT_PRP = 0x0, + NVME_PSDT_SGL_MPTR_CONTIGUOUS = 0x1, + NVME_PSDT_SGL_MPTR_SGL = 0x2, }; typedef struct QEMU_PACKED NvmeCmd { @@ -645,6 +655,7 @@ enum NvmeStatusCodes { NVME_MD_SGL_LEN_INVALID = 0x0010, NVME_SGL_DESCR_TYPE_INVALID = 0x0011, NVME_INVALID_USE_OF_CMB = 0x0012, + NVME_INVALID_PRP_OFFSET = 0x0013, NVME_LBA_RANGE = 0x0080, NVME_CAP_EXCEEDED = 0x0081, NVME_NS_NOT_READY = 0x0082, @@ -849,6 +860,7 @@ enum NvmeIdCtrlFrmw { }; enum NvmeIdCtrlLpa { + NVME_LPA_NS_SMART = 1 << 0, NVME_LPA_EXTENDED = 1 << 2, }; diff --git a/include/hw/pci/pci.h b/include/hw/pci/pci.h index 0a59a06b14..72ce649eee 100644 --- a/include/hw/pci/pci.h +++ b/include/hw/pci/pci.h @@ -106,6 +106,7 @@ extern bool pci_available; #define PCI_DEVICE_ID_REDHAT_XHCI 0x000d #define PCI_DEVICE_ID_REDHAT_PCIE_BRIDGE 0x000e #define PCI_DEVICE_ID_REDHAT_MDPY 0x000f +#define PCI_DEVICE_ID_REDHAT_NVME 0x0010 #define PCI_DEVICE_ID_REDHAT_QXL 0x0100 #define FMT_PCIBUS PRIx64 @@ -783,8 +784,7 @@ static inline AddressSpace *pci_get_address_space(PCIDevice *dev) static inline int pci_dma_rw(PCIDevice *dev, dma_addr_t addr, void *buf, dma_addr_t len, DMADirection dir) { - dma_memory_rw(pci_get_address_space(dev), addr, buf, len, dir); - return 0; + return dma_memory_rw(pci_get_address_space(dev), addr, buf, len, dir); } static inline int pci_dma_read(PCIDevice *dev, dma_addr_t addr, diff --git a/meson.build b/meson.build index 47e32e1fcb..39ac5cf6d8 100644 --- a/meson.build +++ b/meson.build @@ -736,6 +736,21 @@ if not has_malloc_trim and get_option('malloc_trim').enabled() endif endif +# Check whether the glibc provides statx() + +statx_test = ''' + #ifndef _GNU_SOURCE + #define _GNU_SOURCE + #endif + #include <sys/stat.h> + int main(void) { + struct statx statxbuf; + statx(0, "", 0, STATX_BASIC_STATS, &statxbuf); + return 0; + }''' + +has_statx = cc.links(statx_test) + ################# # config-host.h # ################# @@ -768,6 +783,7 @@ config_host_data.set('CONFIG_XKBCOMMON', xkbcommon.found()) config_host_data.set('CONFIG_KEYUTILS', keyutils.found()) config_host_data.set('CONFIG_GETTID', has_gettid) config_host_data.set('CONFIG_MALLOC_TRIM', has_malloc_trim) +config_host_data.set('CONFIG_STATX', has_statx) config_host_data.set('QEMU_VERSION', '"@0@"'.format(meson.project_version())) config_host_data.set('QEMU_VERSION_MAJOR', meson.project_version().split('.')[0]) config_host_data.set('QEMU_VERSION_MINOR', meson.project_version().split('.')[1]) diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c index d3bb3a744b..d99842eb1b 100644 --- a/migration/postcopy-ram.c +++ b/migration/postcopy-ram.c @@ -903,7 +903,6 @@ static void *postcopy_ram_fault_thread(void *opaque) * the channel is rebuilt. */ if (postcopy_pause_fault_thread(mis)) { - mis->last_rb = NULL; /* Continue to read the userfaultfd */ } else { error_report("%s: paused but don't allow to continue", @@ -985,7 +984,6 @@ retry: /* May be network failure, try to wait for recovery */ if (ret == -EIO && postcopy_pause_fault_thread(mis)) { /* We got reconnected somehow, try to continue */ - mis->last_rb = NULL; goto retry; } else { /* This is a unavoidable fault */ diff --git a/migration/savevm.c b/migration/savevm.c index 21ccba9fb3..5f937a2762 100644 --- a/migration/savevm.c +++ b/migration/savevm.c @@ -2062,13 +2062,16 @@ static int loadvm_postcopy_handle_resume(MigrationIncomingState *mis) } /* + * Reset the last_rb before we resend any page req to source again, since + * the source should have it reset already. + */ + mis->last_rb = NULL; + + /* * This means source VM is ready to resume the postcopy migration. - * It's time to switch state and release the fault thread to - * continue service page faults. */ migrate_set_state(&mis->state, MIGRATION_STATUS_POSTCOPY_RECOVER, MIGRATION_STATUS_POSTCOPY_ACTIVE); - qemu_sem_post(&mis->postcopy_pause_sem_fault); trace_loadvm_postcopy_handle_resume(); @@ -2089,6 +2092,14 @@ static int loadvm_postcopy_handle_resume(MigrationIncomingState *mis) */ migrate_send_rp_req_pages_pending(mis); + /* + * It's time to switch state and release the fault thread to continue + * service page faults. Note that this should be explicitly after the + * above call to migrate_send_rp_req_pages_pending(). In short: + * migrate_send_rp_message_req_pages() is not thread safe, yet. + */ + qemu_sem_post(&mis->postcopy_pause_sem_fault); + return 0; } diff --git a/tests/acceptance/boot_linux.py b/tests/acceptance/boot_linux.py index c743e231f4..1da4a53d6a 100644 --- a/tests/acceptance/boot_linux.py +++ b/tests/acceptance/boot_linux.py @@ -57,7 +57,7 @@ class BootLinuxBase(Test): self.cancel('Failed to download/prepare boot image') return boot.path - def download_cloudinit(self): + def download_cloudinit(self, ssh_pubkey=None): self.log.info('Preparing cloudinit image') try: cloudinit_iso = os.path.join(self.workdir, 'cloudinit.iso') @@ -67,7 +67,8 @@ class BootLinuxBase(Test): password='password', # QEMU's hard coded usermode router address phone_home_host='10.0.2.2', - phone_home_port=self.phone_home_port) + phone_home_port=self.phone_home_port, + authorized_key=ssh_pubkey) except Exception: self.cancel('Failed to prepared cloudinit image') return cloudinit_iso @@ -80,19 +81,19 @@ class BootLinux(BootLinuxBase): timeout = 900 chksum = None - def setUp(self): + def setUp(self, ssh_pubkey=None): super(BootLinux, self).setUp() self.vm.add_args('-smp', '2') self.vm.add_args('-m', '1024') self.prepare_boot() - self.prepare_cloudinit() + self.prepare_cloudinit(ssh_pubkey) def prepare_boot(self): path = self.download_boot() self.vm.add_args('-drive', 'file=%s' % path) - def prepare_cloudinit(self): - cloudinit_iso = self.download_cloudinit() + def prepare_cloudinit(self, ssh_pubkey=None): + cloudinit_iso = self.download_cloudinit(ssh_pubkey) self.vm.add_args('-drive', 'file=%s,format=raw' % cloudinit_iso) def launch_and_wait(self): diff --git a/tests/acceptance/virtiofs_submounts.py b/tests/acceptance/virtiofs_submounts.py new file mode 100644 index 0000000000..361e5990b6 --- /dev/null +++ b/tests/acceptance/virtiofs_submounts.py @@ -0,0 +1,321 @@ +import logging +import re +import os +import subprocess +import time + +from avocado import skipUnless +from avocado_qemu import Test, BUILD_DIR +from avocado_qemu import wait_for_console_pattern +from avocado.utils import ssh + +from qemu.accel import kvm_available + +from boot_linux import BootLinux + + +def run_cmd(args): + subp = subprocess.Popen(args, + stdout=subprocess.PIPE, + stderr=subprocess.PIPE, + universal_newlines=True) + stdout, stderr = subp.communicate() + ret = subp.returncode + + return (stdout, stderr, ret) + +def has_cmd(name, args=None): + """ + This function is for use in a @avocado.skipUnless decorator, e.g.: + + @skipUnless(*has_cmd('sudo -n', ('sudo', '-n', 'true'))) + def test_something_that_needs_sudo(self): + ... + """ + + if args is None: + args = ('which', name) + + try: + _, stderr, exitcode = run_cmd(args) + except Exception as e: + exitcode = -1 + stderr = str(e) + + if exitcode != 0: + cmd_line = ' '.join(args) + err = f'{name} required, but "{cmd_line}" failed: {stderr.strip()}' + return (False, err) + else: + return (True, '') + +def has_cmds(*cmds): + """ + This function is for use in a @avocado.skipUnless decorator and + allows checking for the availability of multiple commands, e.g.: + + @skipUnless(*has_cmds(('cmd1', ('cmd1', '--some-parameter')), + 'cmd2', 'cmd3')) + def test_something_that_needs_cmd1_and_cmd2(self): + ... + """ + + for cmd in cmds: + if isinstance(cmd, str): + cmd = (cmd,) + + ok, errstr = has_cmd(*cmd) + if not ok: + return (False, errstr) + + return (True, '') + + +class VirtiofsSubmountsTest(BootLinux): + """ + :avocado: tags=arch:x86_64 + """ + + def get_portfwd(self): + port = None + + res = self.vm.command('human-monitor-command', + command_line='info usernet') + for line in res.split('\r\n'): + match = \ + re.search(r'TCP.HOST_FORWARD.*127\.0\.0\.1\s*(\d+)\s+10\.', + line) + if match is not None: + port = match[1] + break + + self.assertIsNotNone(port) + self.log.debug('sshd listening on port: ' + port) + return port + + def ssh_connect(self, username, keyfile): + self.ssh_logger = logging.getLogger('ssh') + port = self.get_portfwd() + self.ssh_session = ssh.Session('127.0.0.1', port=int(port), + user=username, key=keyfile) + for i in range(10): + try: + self.ssh_session.connect() + return + except: + time.sleep(4) + pass + self.fail('sshd timeout') + + def ssh_command(self, command): + self.ssh_logger.info(command) + result = self.ssh_session.cmd(command) + stdout_lines = [line.rstrip() for line + in result.stdout_text.splitlines()] + for line in stdout_lines: + self.ssh_logger.info(line) + stderr_lines = [line.rstrip() for line + in result.stderr_text.splitlines()] + for line in stderr_lines: + self.ssh_logger.warning(line) + + self.assertEqual(result.exit_status, 0, + f'Guest command failed: {command}') + return stdout_lines, stderr_lines + + def run(self, args, ignore_error=False): + stdout, stderr, ret = run_cmd(args) + + if ret != 0: + cmdline = ' '.join(args) + if not ignore_error: + self.fail(f'{cmdline}: Returned {ret}: {stderr}') + else: + self.log.warn(f'{cmdline}: Returned {ret}: {stderr}') + + return (stdout, stderr, ret) + + def set_up_shared_dir(self): + atwd = os.getenv('AVOCADO_TEST_WORKDIR') + self.shared_dir = os.path.join(atwd, 'virtiofs-shared') + + os.mkdir(self.shared_dir) + + self.run(('cp', self.get_data('guest.sh'), + os.path.join(self.shared_dir, 'check.sh'))) + + self.run(('cp', self.get_data('guest-cleanup.sh'), + os.path.join(self.shared_dir, 'cleanup.sh'))) + + def set_up_virtiofs(self): + attmp = os.getenv('AVOCADO_TESTS_COMMON_TMPDIR') + self.vfsdsock = os.path.join(attmp, 'vfsdsock') + + self.run(('sudo', '-n', 'rm', '-f', self.vfsdsock), ignore_error=True) + + self.virtiofsd = \ + subprocess.Popen(('sudo', '-n', + 'tools/virtiofsd/virtiofsd', + f'--socket-path={self.vfsdsock}', + '-o', f'source={self.shared_dir}', + '-o', 'cache=always', + '-o', 'xattr', + '-o', 'announce_submounts', + '-f'), + stdout=subprocess.DEVNULL, + stderr=subprocess.PIPE, + universal_newlines=True) + + while not os.path.exists(self.vfsdsock): + if self.virtiofsd.poll() is not None: + self.fail('virtiofsd exited prematurely: ' + + self.virtiofsd.communicate()[1]) + time.sleep(0.1) + + self.run(('sudo', '-n', 'chmod', 'go+rw', self.vfsdsock)) + + self.vm.add_args('-chardev', + f'socket,id=vfsdsock,path={self.vfsdsock}', + '-device', + 'vhost-user-fs-pci,queue-size=1024,chardev=vfsdsock' \ + ',tag=host', + '-object', + 'memory-backend-file,id=mem,size=1G,' \ + 'mem-path=/dev/shm,share=on', + '-numa', + 'node,memdev=mem') + + def launch_vm(self): + self.launch_and_wait() + self.ssh_connect('root', self.ssh_key) + + def set_up_nested_mounts(self): + scratch_dir = os.path.join(self.shared_dir, 'scratch') + try: + os.mkdir(scratch_dir) + except FileExistsError: + pass + + args = ['bash', self.get_data('host.sh'), scratch_dir] + if self.seed: + args += [self.seed] + + out, _, _ = self.run(args) + seed = re.search(r'^Seed: \d+', out) + self.log.info(seed[0]) + + def mount_in_guest(self): + self.ssh_command('mkdir -p /mnt/host') + self.ssh_command('mount -t virtiofs host /mnt/host') + + def check_in_guest(self): + self.ssh_command('bash /mnt/host/check.sh /mnt/host/scratch/share') + + def live_cleanup(self): + self.ssh_command('bash /mnt/host/cleanup.sh /mnt/host/scratch') + + # It would be nice if the above was sufficient to make virtiofsd clear + # all references to the mounted directories (so they can be unmounted + # on the host), but unfortunately it is not. To do so, we have to + # resort to a remount. + self.ssh_command('mount -o remount /mnt/host') + + scratch_dir = os.path.join(self.shared_dir, 'scratch') + self.run(('bash', self.get_data('cleanup.sh'), scratch_dir)) + + @skipUnless(*has_cmds(('sudo -n', ('sudo', '-n', 'true')), + 'ssh-keygen', 'bash', 'losetup', 'mkfs.xfs', 'mount')) + def setUp(self): + vmlinuz = self.params.get('vmlinuz') + if vmlinuz is None: + self.cancel('vmlinuz parameter not set; you must point it to a ' + 'Linux kernel binary to test (to run this test with ' \ + 'the on-image kernel, set it to an empty string)') + + self.seed = self.params.get('seed') + + atwd = os.getenv('AVOCADO_TEST_WORKDIR') + self.ssh_key = os.path.join(atwd, 'id_ed25519') + + self.run(('ssh-keygen', '-t', 'ed25519', '-f', self.ssh_key)) + + pubkey = open(self.ssh_key + '.pub').read() + + super(VirtiofsSubmountsTest, self).setUp(pubkey) + + if len(vmlinuz) > 0: + self.vm.add_args('-kernel', vmlinuz, + '-append', 'console=ttyS0 root=/dev/sda1') + + # Allow us to connect to SSH + self.vm.add_args('-netdev', 'user,id=vnet,hostfwd=:127.0.0.1:0-:22', + '-device', 'e1000,netdev=vnet') + + if not kvm_available(self.arch, self.qemu_bin): + self.cancel(KVM_NOT_AVAILABLE) + self.vm.add_args('-accel', 'kvm') + + def tearDown(self): + try: + self.vm.shutdown() + except: + pass + + scratch_dir = os.path.join(self.shared_dir, 'scratch') + self.run(('bash', self.get_data('cleanup.sh'), scratch_dir), + ignore_error=True) + + def test_pre_virtiofsd_set_up(self): + self.set_up_shared_dir() + + self.set_up_nested_mounts() + + self.set_up_virtiofs() + self.launch_vm() + self.mount_in_guest() + self.check_in_guest() + + def test_pre_launch_set_up(self): + self.set_up_shared_dir() + self.set_up_virtiofs() + + self.set_up_nested_mounts() + + self.launch_vm() + self.mount_in_guest() + self.check_in_guest() + + def test_post_launch_set_up(self): + self.set_up_shared_dir() + self.set_up_virtiofs() + self.launch_vm() + + self.set_up_nested_mounts() + + self.mount_in_guest() + self.check_in_guest() + + def test_post_mount_set_up(self): + self.set_up_shared_dir() + self.set_up_virtiofs() + self.launch_vm() + self.mount_in_guest() + + self.set_up_nested_mounts() + + self.check_in_guest() + + def test_two_runs(self): + self.set_up_shared_dir() + + self.set_up_nested_mounts() + + self.set_up_virtiofs() + self.launch_vm() + self.mount_in_guest() + self.check_in_guest() + + self.live_cleanup() + self.set_up_nested_mounts() + + self.check_in_guest() diff --git a/tests/acceptance/virtiofs_submounts.py.data/cleanup.sh b/tests/acceptance/virtiofs_submounts.py.data/cleanup.sh new file mode 100644 index 0000000000..2a6579a0fe --- /dev/null +++ b/tests/acceptance/virtiofs_submounts.py.data/cleanup.sh @@ -0,0 +1,46 @@ +#!/bin/bash + +function print_usage() +{ + if [ -n "$2" ]; then + echo "Error: $2" + echo + fi + echo "Usage: $1 <scratch dir>" +} + +scratch_dir=$1 +if [ -z "$scratch_dir" ]; then + print_usage "$0" 'Scratch dir not given' >&2 + exit 1 +fi + +cd "$scratch_dir/share" || exit 1 +mps=(mnt*) +mp_i=0 +for mp in "${mps[@]}"; do + mp_i=$((mp_i + 1)) + printf "Unmounting %i/%i...\r" "$mp_i" "${#mps[@]}" + + sudo umount -R "$mp" + rm -rf "$mp" +done +echo + +rm some-file +cd .. +rmdir share + +imgs=(fs*.img) +img_i=0 +for img in "${imgs[@]}"; do + img_i=$((img_i + 1)) + printf "Detaching and deleting %i/%i...\r" "$img_i" "${#imgs[@]}" + + dev=$(losetup -j "$img" | sed -e 's/:.*//') + sudo losetup -d "$dev" + rm -f "$img" +done +echo + +echo 'Done.' diff --git a/tests/acceptance/virtiofs_submounts.py.data/guest-cleanup.sh b/tests/acceptance/virtiofs_submounts.py.data/guest-cleanup.sh new file mode 100644 index 0000000000..729cb2d1a5 --- /dev/null +++ b/tests/acceptance/virtiofs_submounts.py.data/guest-cleanup.sh @@ -0,0 +1,30 @@ +#!/bin/bash + +function print_usage() +{ + if [ -n "$2" ]; then + echo "Error: $2" + echo + fi + echo "Usage: $1 <scratch dir>" +} + +scratch_dir=$1 +if [ -z "$scratch_dir" ]; then + print_usage "$0" 'Scratch dir not given' >&2 + exit 1 +fi + +cd "$scratch_dir/share" || exit 1 + +mps=(mnt*) +mp_i=0 +for mp in "${mps[@]}"; do + mp_i=$((mp_i + 1)) + printf "Unmounting %i/%i...\r" "$mp_i" "${#mps[@]}" + + sudo umount -R "$mp" +done +echo + +echo 'Done.' diff --git a/tests/acceptance/virtiofs_submounts.py.data/guest.sh b/tests/acceptance/virtiofs_submounts.py.data/guest.sh new file mode 100644 index 0000000000..59ba40fde1 --- /dev/null +++ b/tests/acceptance/virtiofs_submounts.py.data/guest.sh @@ -0,0 +1,138 @@ +#!/bin/bash + +function print_usage() +{ + if [ -n "$2" ]; then + echo "Error: $2" + echo + fi + echo "Usage: $1 <shared dir>" + echo '(The shared directory is the "share" directory in the scratch' \ + 'directory)' +} + +shared_dir=$1 +if [ -z "$shared_dir" ]; then + print_usage "$0" 'Shared dir not given' >&2 + exit 1 +fi + +cd "$shared_dir" + +# FIXME: This should not be necessary, but it is. In order for all +# submounts to be proper mount points, we need to visit them. +# (Before we visit them, they will not be auto-mounted, and so just +# appear as normal directories, with the catch that their st_ino will +# be the st_ino of the filesystem they host, while the st_dev will +# still be the st_dev of the parent.) +# `find` does not work, because it will refuse to touch the mount +# points as long as they are not mounted; their st_dev being shared +# with the parent and st_ino just being the root node's inode ID +# will practically ensure that this node exists elsewhere on the +# filesystem, and `find` is required to recognize loops and not to +# follow them. +# Thus, we have to manually visit all nodes first. + +mnt_i=0 + +function recursively_visit() +{ + pushd "$1" >/dev/null + for entry in *; do + if [[ "$entry" == mnt* ]]; then + mnt_i=$((mnt_i + 1)) + printf "Triggering auto-mount $mnt_i...\r" + fi + + if [ -d "$entry" ]; then + recursively_visit "$entry" + fi + done + popd >/dev/null +} + +recursively_visit . +echo + + +if [ -n "$(find -name not-mounted)" ]; then + echo "Error: not-mounted files visible on mount points:" >&2 + find -name not-mounted >&2 + exit 1 +fi + +if [ ! -f some-file -o "$(cat some-file)" != 'root' ]; then + echo "Error: Bad file in the share root" >&2 + exit 1 +fi + +shopt -s nullglob + +function check_submounts() +{ + local base_path=$1 + + for mp in mnt*; do + printf "Checking submount %i...\r" "$((${#devs[@]} + 1))" + + mp_i=$(echo "$mp" | sed -e 's/mnt//') + dev=$(stat -c '%D' "$mp") + + if [ -n "${devs[mp_i]}" ]; then + echo "Error: $mp encountered twice" >&2 + exit 1 + fi + devs[mp_i]=$dev + + pushd "$mp" >/dev/null + path="$base_path$mp" + while true; do + expected_content="$(printf '%s\n%s\n' "$mp_i" "$path")" + if [ ! -f some-file ]; then + echo "Error: $PWD/some-file does not exist" >&2 + exit 1 + fi + + if [ "$(cat some-file)" != "$expected_content" ]; then + echo "Error: Bad content in $PWD/some-file:" >&2 + echo '--- found ---' + cat some-file + echo '--- expected ---' + echo "$expected_content" + exit 1 + fi + if [ "$(stat -c '%D' some-file)" != "$dev" ]; then + echo "Error: $PWD/some-file has the wrong device ID" >&2 + exit 1 + fi + + if [ -d sub ]; then + if [ "$(stat -c '%D' sub)" != "$dev" ]; then + echo "Error: $PWD/some-file has the wrong device ID" >&2 + exit 1 + fi + cd sub + path="$path/sub" + else + if [ -n "$(echo mnt*)" ]; then + check_submounts "$path/" + fi + break + fi + done + popd >/dev/null + done +} + +root_dev=$(stat -c '%D' some-file) +devs=() +check_submounts '' +echo + +reused_devs=$(echo "$root_dev ${devs[@]}" | tr ' ' '\n' | sort | uniq -d) +if [ -n "$reused_devs" ]; then + echo "Error: Reused device IDs: $reused_devs" >&2 + exit 1 +fi + +echo "Test passed for ${#devs[@]} submounts." diff --git a/tests/acceptance/virtiofs_submounts.py.data/host.sh b/tests/acceptance/virtiofs_submounts.py.data/host.sh new file mode 100644 index 0000000000..d8a9afebdb --- /dev/null +++ b/tests/acceptance/virtiofs_submounts.py.data/host.sh @@ -0,0 +1,127 @@ +#!/bin/bash + +mount_count=128 + +function print_usage() +{ + if [ -n "$2" ]; then + echo "Error: $2" + echo + fi + echo "Usage: $1 <scratch dir> [seed]" + echo "(If no seed is given, it will be randomly generated.)" +} + +scratch_dir=$1 +if [ -z "$scratch_dir" ]; then + print_usage "$0" 'No scratch dir given' >&2 + exit 1 +fi + +if [ ! -d "$scratch_dir" ]; then + print_usage "$0" "$scratch_dir is not a directory" >&2 + exit 1 +fi + +seed=$2 +if [ -z "$seed" ]; then + seed=$RANDOM +fi +RANDOM=$seed + +echo "Seed: $seed" + +set -e +shopt -s nullglob + +cd "$scratch_dir" +if [ -d share ]; then + echo 'Error: This directory seems to be in use already' >&2 + exit 1 +fi + +for ((i = 0; i < $mount_count; i++)); do + printf "Setting up fs %i/%i...\r" "$((i + 1))" "$mount_count" + + rm -f fs$i.img + truncate -s 512M fs$i.img + mkfs.xfs -q fs$i.img + devs[i]=$(sudo losetup -f --show fs$i.img) +done +echo + +top_level_mounts=$((RANDOM % mount_count + 1)) + +mkdir -p share +echo 'root' > share/some-file + +for ((i = 0; i < $top_level_mounts; i++)); do + printf "Mounting fs %i/%i...\r" "$((i + 1))" "$mount_count" + + mkdir -p share/mnt$i + touch share/mnt$i/not-mounted + sudo mount "${devs[i]}" share/mnt$i + sudo chown "$(id -u):$(id -g)" share/mnt$i + + pushd share/mnt$i >/dev/null + path=mnt$i + nesting=$((RANDOM % 4)) + for ((j = 0; j < $nesting; j++)); do + cat > some-file <<EOF +$i +$path +EOF + mkdir sub + cd sub + path="$path/sub" + done +cat > some-file <<EOF +$i +$path +EOF + popd >/dev/null +done + +for ((; i < $mount_count; i++)); do + printf "Mounting fs %i/%i...\r" "$((i + 1))" "$mount_count" + + mp_i=$((i % top_level_mounts)) + + pushd share/mnt$mp_i >/dev/null + path=mnt$mp_i + while true; do + sub_mp="$(echo mnt*)" + if cd sub 2>/dev/null; then + path="$path/sub" + elif [ -n "$sub_mp" ] && cd "$sub_mp" 2>/dev/null; then + path="$path/$sub_mp" + else + break + fi + done + mkdir mnt$i + touch mnt$i/not-mounted + sudo mount "${devs[i]}" mnt$i + sudo chown "$(id -u):$(id -g)" mnt$i + + cd mnt$i + path="$path/mnt$i" + nesting=$((RANDOM % 4)) + for ((j = 0; j < $nesting; j++)); do + cat > some-file <<EOF +$i +$path +EOF + mkdir sub + cd sub + path="$path/sub" + done + cat > some-file <<EOF +$i +$path +EOF + popd >/dev/null +done +echo + +echo 'Done.' diff --git a/tools/virtiofsd/fuse_common.h b/tools/virtiofsd/fuse_common.h index 686c42c0a5..5aee5193eb 100644 --- a/tools/virtiofsd/fuse_common.h +++ b/tools/virtiofsd/fuse_common.h @@ -353,6 +353,13 @@ struct fuse_file_info { #define FUSE_CAP_NO_OPENDIR_SUPPORT (1 << 24) /** + * Indicates that the kernel supports the FUSE_ATTR_SUBMOUNT flag. + * + * Setting (or unsetting) this flag in the `want` field has *no effect*. + */ +#define FUSE_CAP_SUBMOUNTS (1 << 27) + +/** * Ioctl flags * * FUSE_IOCTL_COMPAT: 32bit compat ioctl on 64bit machine diff --git a/tools/virtiofsd/fuse_lowlevel.c b/tools/virtiofsd/fuse_lowlevel.c index 4d1ba2925d..c70fb16a9a 100644 --- a/tools/virtiofsd/fuse_lowlevel.c +++ b/tools/virtiofsd/fuse_lowlevel.c @@ -341,6 +341,8 @@ static void fill_entry(struct fuse_entry_out *arg, .attr_valid_nsec = calc_timeout_nsec(e->attr_timeout), }; convert_stat(&e->attr, &arg->attr); + + arg->attr.flags = e->attr_flags; } /* @@ -1988,6 +1990,9 @@ static void do_init(fuse_req_t req, fuse_ino_t nodeid, bufsize = max_bufsize; } } + if (arg->flags & FUSE_SUBMOUNTS) { + se->conn.capable |= FUSE_CAP_SUBMOUNTS; + } #ifdef HAVE_SPLICE #ifdef HAVE_VMSPLICE se->conn.capable |= FUSE_CAP_SPLICE_WRITE | FUSE_CAP_SPLICE_MOVE; diff --git a/tools/virtiofsd/fuse_lowlevel.h b/tools/virtiofsd/fuse_lowlevel.h index 562fd5241e..9c06240f9e 100644 --- a/tools/virtiofsd/fuse_lowlevel.h +++ b/tools/virtiofsd/fuse_lowlevel.h @@ -102,6 +102,11 @@ struct fuse_entry_param { * large value. */ double entry_timeout; + + /** + * Flags for fuse_attr.flags that do not fit into attr. + */ + uint32_t attr_flags; }; /** diff --git a/tools/virtiofsd/fuse_virtio.c b/tools/virtiofsd/fuse_virtio.c index 324936948d..83ba07c6cd 100644 --- a/tools/virtiofsd/fuse_virtio.c +++ b/tools/virtiofsd/fuse_virtio.c @@ -1013,8 +1013,11 @@ int virtio_session_mount(struct fuse_session *se) se->vu_socketfd = data_sock; se->virtio_dev->se = se; pthread_rwlock_init(&se->virtio_dev->vu_dispatch_rwlock, NULL); - vu_init(&se->virtio_dev->dev, 2, se->vu_socketfd, fv_panic, NULL, - fv_set_watch, fv_remove_watch, &fv_iface); + if (!vu_init(&se->virtio_dev->dev, 2, se->vu_socketfd, fv_panic, NULL, + fv_set_watch, fv_remove_watch, &fv_iface)) { + fuse_log(FUSE_LOG_ERR, "%s: vu_init failed\n", __func__); + return -1; + } return 0; } diff --git a/tools/virtiofsd/helper.c b/tools/virtiofsd/helper.c index 2e181a49b5..75ac48dec2 100644 --- a/tools/virtiofsd/helper.c +++ b/tools/virtiofsd/helper.c @@ -161,7 +161,7 @@ void fuse_cmdline_help(void) " allowed (default: 10)\n" " -o posix_lock|no_posix_lock\n" " enable/disable remote posix lock\n" - " default: posix_lock\n" + " default: no_posix_lock\n" " -o readdirplus|no_readdirplus\n" " enable/disable readirplus\n" " default: readdirplus except with " @@ -190,6 +190,7 @@ void fuse_cmdline_help(void) " retain/discard O_DIRECT flags passed down\n" " to virtiofsd from guest applications.\n" " default: no_allow_direct_io\n" + " -o announce_submounts Announce sub-mount points to the guest\n" ); } diff --git a/tools/virtiofsd/passthrough_ll.c b/tools/virtiofsd/passthrough_ll.c index a0beb986f3..ec1008bceb 100644 --- a/tools/virtiofsd/passthrough_ll.c +++ b/tools/virtiofsd/passthrough_ll.c @@ -40,6 +40,7 @@ #include "fuse_virtio.h" #include "fuse_log.h" #include "fuse_lowlevel.h" +#include "standard-headers/linux/fuse.h" #include <assert.h> #include <cap-ng.h> #include <dirent.h> @@ -94,6 +95,7 @@ struct lo_map { struct lo_key { ino_t ino; dev_t dev; + uint64_t mnt_id; }; struct lo_inode { @@ -166,6 +168,8 @@ struct lo_data { int readdirplus_set; int readdirplus_clear; int allow_direct_io; + int announce_submounts; + bool use_statx; struct lo_inode root; GHashTable *inodes; /* protected by lo->mutex */ struct lo_map ino_map; /* protected by lo->mutex */ @@ -205,6 +209,7 @@ static const struct fuse_opt lo_opts[] = { { "no_readdirplus", offsetof(struct lo_data, readdirplus_clear), 1 }, { "allow_direct_io", offsetof(struct lo_data, allow_direct_io), 1 }, { "no_allow_direct_io", offsetof(struct lo_data, allow_direct_io), 0 }, + { "announce_submounts", offsetof(struct lo_data, announce_submounts), 1 }, FUSE_OPT_END }; static bool use_syslog = false; @@ -219,7 +224,8 @@ static struct { /* That we loaded cap-ng in the current thread from the saved */ static __thread bool cap_loaded = 0; -static struct lo_inode *lo_find(struct lo_data *lo, struct stat *st); +static struct lo_inode *lo_find(struct lo_data *lo, struct stat *st, + uint64_t mnt_id); static int is_dot_or_dotdot(const char *name) { @@ -598,6 +604,20 @@ static void lo_init(void *userdata, struct fuse_conn_info *conn) fuse_log(FUSE_LOG_DEBUG, "lo_init: disabling readdirplus\n"); conn->want &= ~FUSE_CAP_READDIRPLUS; } + + if (!(conn->capable & FUSE_CAP_SUBMOUNTS) && lo->announce_submounts) { + fuse_log(FUSE_LOG_WARNING, "lo_init: Cannot announce submounts, client " + "does not support it\n"); + lo->announce_submounts = false; + } + +#ifndef CONFIG_STATX + if (lo->announce_submounts) { + fuse_log(FUSE_LOG_WARNING, "lo_init: Cannot announce submounts, there " + "is no statx()\n"); + lo->announce_submounts = false; + } +#endif } static void lo_getattr(fuse_req_t req, fuse_ino_t ino, @@ -741,12 +761,14 @@ out_err: fuse_reply_err(req, saverr); } -static struct lo_inode *lo_find(struct lo_data *lo, struct stat *st) +static struct lo_inode *lo_find(struct lo_data *lo, struct stat *st, + uint64_t mnt_id) { struct lo_inode *p; struct lo_key key = { .ino = st->st_ino, .dev = st->st_dev, + .mnt_id = mnt_id, }; pthread_mutex_lock(&lo->mutex); @@ -774,6 +796,60 @@ static void posix_locks_value_destroy(gpointer data) free(plock); } +static int do_statx(struct lo_data *lo, int dirfd, const char *pathname, + struct stat *statbuf, int flags, uint64_t *mnt_id) +{ + int res; + +#if defined(CONFIG_STATX) && defined(STATX_MNT_ID) + if (lo->use_statx) { + struct statx statxbuf; + + res = statx(dirfd, pathname, flags, STATX_BASIC_STATS | STATX_MNT_ID, + &statxbuf); + if (!res) { + memset(statbuf, 0, sizeof(*statbuf)); + statbuf->st_dev = makedev(statxbuf.stx_dev_major, + statxbuf.stx_dev_minor); + statbuf->st_ino = statxbuf.stx_ino; + statbuf->st_mode = statxbuf.stx_mode; + statbuf->st_nlink = statxbuf.stx_nlink; + statbuf->st_uid = statxbuf.stx_uid; + statbuf->st_gid = statxbuf.stx_gid; + statbuf->st_rdev = makedev(statxbuf.stx_rdev_major, + statxbuf.stx_rdev_minor); + statbuf->st_size = statxbuf.stx_size; + statbuf->st_blksize = statxbuf.stx_blksize; + statbuf->st_blocks = statxbuf.stx_blocks; + statbuf->st_atim.tv_sec = statxbuf.stx_atime.tv_sec; + statbuf->st_atim.tv_nsec = statxbuf.stx_atime.tv_nsec; + statbuf->st_mtim.tv_sec = statxbuf.stx_mtime.tv_sec; + statbuf->st_mtim.tv_nsec = statxbuf.stx_mtime.tv_nsec; + statbuf->st_ctim.tv_sec = statxbuf.stx_ctime.tv_sec; + statbuf->st_ctim.tv_nsec = statxbuf.stx_ctime.tv_nsec; + + if (statxbuf.stx_mask & STATX_MNT_ID) { + *mnt_id = statxbuf.stx_mnt_id; + } else { + *mnt_id = 0; + } + return 0; + } else if (errno != ENOSYS) { + return -1; + } + lo->use_statx = false; + /* fallback */ + } +#endif + res = fstatat(dirfd, pathname, statbuf, flags); + if (res == -1) { + return -1; + } + *mnt_id = 0; + + return 0; +} + /* * Increments nlookup and caller must release refcount using * lo_inode_put(&parent). @@ -784,6 +860,7 @@ static int lo_do_lookup(fuse_req_t req, fuse_ino_t parent, const char *name, int newfd; int res; int saverr; + uint64_t mnt_id; struct lo_data *lo = lo_data(req); struct lo_inode *inode = NULL; struct lo_inode *dir = lo_inode(req, parent); @@ -811,12 +888,18 @@ static int lo_do_lookup(fuse_req_t req, fuse_ino_t parent, const char *name, goto out_err; } - res = fstatat(newfd, "", &e->attr, AT_EMPTY_PATH | AT_SYMLINK_NOFOLLOW); + res = do_statx(lo, newfd, "", &e->attr, AT_EMPTY_PATH | AT_SYMLINK_NOFOLLOW, + &mnt_id); if (res == -1) { goto out_err; } - inode = lo_find(lo, &e->attr); + if (S_ISDIR(e->attr.st_mode) && lo->announce_submounts && + (e->attr.st_dev != dir->key.dev || mnt_id != dir->key.mnt_id)) { + e->attr_flags |= FUSE_ATTR_SUBMOUNT; + } + + inode = lo_find(lo, &e->attr, mnt_id); if (inode) { close(newfd); } else { @@ -838,6 +921,7 @@ static int lo_do_lookup(fuse_req_t req, fuse_ino_t parent, const char *name, inode->fd = newfd; inode->key.ino = e->attr.st_ino; inode->key.dev = e->attr.st_dev; + inode->key.mnt_id = mnt_id; pthread_mutex_init(&inode->plock_mutex, NULL); inode->posix_locks = g_hash_table_new_full( g_direct_hash, g_direct_equal, NULL, posix_locks_value_destroy); @@ -1090,15 +1174,23 @@ static struct lo_inode *lookup_name(fuse_req_t req, fuse_ino_t parent, const char *name) { int res; + uint64_t mnt_id; struct stat attr; + struct lo_data *lo = lo_data(req); + struct lo_inode *dir = lo_inode(req, parent); - res = fstatat(lo_fd(req, parent), name, &attr, - AT_EMPTY_PATH | AT_SYMLINK_NOFOLLOW); + if (!dir) { + return NULL; + } + + res = do_statx(lo, dir->fd, name, &attr, + AT_EMPTY_PATH | AT_SYMLINK_NOFOLLOW, &mnt_id); + lo_inode_put(lo, &dir); if (res == -1) { return NULL; } - return lo_find(lo_data(req), &attr); + return lo_find(lo, &attr, mnt_id); } static void lo_rmdir(fuse_req_t req, fuse_ino_t parent, const char *name) @@ -3266,6 +3358,7 @@ static void setup_root(struct lo_data *lo, struct lo_inode *root) { int fd, res; struct stat stat; + uint64_t mnt_id; fd = open("/", O_PATH); if (fd == -1) { @@ -3273,7 +3366,8 @@ static void setup_root(struct lo_data *lo, struct lo_inode *root) exit(1); } - res = fstatat(fd, "", &stat, AT_EMPTY_PATH | AT_SYMLINK_NOFOLLOW); + res = do_statx(lo, fd, "", &stat, AT_EMPTY_PATH | AT_SYMLINK_NOFOLLOW, + &mnt_id); if (res == -1) { fuse_log(FUSE_LOG_ERR, "fstatat(%s): %m\n", lo->source); exit(1); @@ -3283,6 +3377,7 @@ static void setup_root(struct lo_data *lo, struct lo_inode *root) root->fd = fd; root->key.ino = stat.st_ino; root->key.dev = stat.st_dev; + root->key.mnt_id = mnt_id; root->nlookup = 2; g_atomic_int_set(&root->refcount, 2); } @@ -3291,7 +3386,7 @@ static guint lo_key_hash(gconstpointer key) { const struct lo_key *lkey = key; - return (guint)lkey->ino + (guint)lkey->dev; + return (guint)lkey->ino + (guint)lkey->dev + (guint)lkey->mnt_id; } static gboolean lo_key_equal(gconstpointer a, gconstpointer b) @@ -3299,7 +3394,7 @@ static gboolean lo_key_equal(gconstpointer a, gconstpointer b) const struct lo_key *la = a; const struct lo_key *lb = b; - return la->ino == lb->ino && la->dev == lb->dev; + return la->ino == lb->ino && la->dev == lb->dev && la->mnt_id == lb->mnt_id; } static void fuse_lo_data_cleanup(struct lo_data *lo) @@ -3445,6 +3540,8 @@ int main(int argc, char *argv[]) exit(1); } + lo.use_statx = true; + se = fuse_session_new(&args, &lo_oper, sizeof(lo_oper), &lo); if (se == NULL) { goto err_out1; diff --git a/tools/virtiofsd/passthrough_seccomp.c b/tools/virtiofsd/passthrough_seccomp.c index eb9af8265f..11623f56f2 100644 --- a/tools/virtiofsd/passthrough_seccomp.c +++ b/tools/virtiofsd/passthrough_seccomp.c @@ -76,6 +76,7 @@ static const int syscall_whitelist[] = { SCMP_SYS(mremap), SCMP_SYS(munmap), SCMP_SYS(newfstatat), + SCMP_SYS(statx), SCMP_SYS(open), SCMP_SYS(openat), SCMP_SYS(ppoll), @@ -118,6 +119,7 @@ static const int syscall_whitelist[] = { /* Syscalls used when --syslog is enabled */ static const int syscall_whitelist_syslog[] = { + SCMP_SYS(send), SCMP_SYS(sendto), }; |