diff options
| author | Peter Maydell <peter.maydell@linaro.org> | 2020-09-02 21:20:20 +0100 |
|---|---|---|
| committer | Peter Maydell <peter.maydell@linaro.org> | 2020-09-02 21:20:20 +0100 |
| commit | e4d8b7c1a95fffcfa4bdab9aa7ffd1cf590cdcf5 (patch) | |
| tree | c8c3147e5ed1fbc46090025a6e8d497b27dc140c | |
| parent | ed215cec0fcaeaece064b0fdf37fe3bceb06d76c (diff) | |
| parent | 82386d4a0f19ff1e6a04e29f104da1d12269539e (diff) | |
| download | focaccia-qemu-e4d8b7c1a95fffcfa4bdab9aa7ffd1cf590cdcf5.tar.gz focaccia-qemu-e4d8b7c1a95fffcfa4bdab9aa7ffd1cf590cdcf5.zip | |
Merge remote-tracking branch 'remotes/nvme/tags/pull-nvme-20200902' into staging
qemu-nvme # gpg: Signature made Wed 02 Sep 2020 15:39:10 BST # gpg: using RSA key DBC11D2D373B4A3755F502EC625156610A4F6CC0 # gpg: Good signature from "Keith Busch <kbusch@kernel.org>" [unknown] # gpg: aka "Keith Busch <keith.busch@gmail.com>" [unknown] # gpg: aka "Keith Busch <keith.busch@intel.com>" [unknown] # gpg: WARNING: This key is not certified with a trusted signature! # gpg: There is no indication that the signature belongs to the owner. # Primary key fingerprint: DBC1 1D2D 373B 4A37 55F5 02EC 6251 5661 0A4F 6CC0 * remotes/nvme/tags/pull-nvme-20200902: (39 commits) hw/block/nvme: remove explicit qsg/iov parameters hw/block/nvme: use preallocated qsg/iov in nvme_dma_prp hw/block/nvme: consolidate qsg/iov clearing hw/block/nvme: add ns/cmd references in NvmeRequest hw/block/nvme: be consistent about zeros vs zeroes hw/block/nvme: add check for mdts hw/block/nvme: refactor request bounds checking hw/block/nvme: verify validity of prp lists in the cmb hw/block/nvme: add request mapping helper hw/block/nvme: add tracing to nvme_map_prp hw/block/nvme: refactor dma read/write hw/block/nvme: destroy request iov before reuse hw/block/nvme: remove redundant has_sg member hw/block/nvme: replace dma_acct with blk_acct equivalent hw/block/nvme: add mapping helpers hw/block/nvme: memset preallocated requests structures hw/block/nvme: bump supported version to v1.3 hw/block/nvme: provide the mandatory subnqn field hw/block/nvme: enforce valid queue creation sequence hw/block/nvme: reject invalid nsid values in active namespace id list ... Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
| -rw-r--r-- | MAINTAINERS | 2 | ||||
| -rw-r--r-- | block/nvme.c | 22 | ||||
| -rw-r--r-- | hw/block/nvme.c | 1136 | ||||
| -rw-r--r-- | hw/block/nvme.h | 26 | ||||
| -rw-r--r-- | hw/block/trace-events | 31 | ||||
| -rw-r--r-- | include/block/nvme.h | 271 |
6 files changed, 1248 insertions, 240 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index b5ba553ee0..b233da2a73 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1856,10 +1856,12 @@ F: include/hw/virtio/virtio-mem.h nvme M: Keith Busch <kbusch@kernel.org> +M: Klaus Jensen <its@irrelevant.dk> L: qemu-block@nongnu.org S: Supported F: hw/block/nvme* F: tests/qtest/nvme-test.c +T: git git://git.infradead.org/qemu-nvme.git nvme-next megasas M: Hannes Reinecke <hare@suse.com> diff --git a/block/nvme.c b/block/nvme.c index 374e268915..05485fdd11 100644 --- a/block/nvme.c +++ b/block/nvme.c @@ -518,7 +518,7 @@ static void nvme_identify(BlockDriverState *bs, int namespace, Error **errp) error_setg(errp, "Cannot map buffer for DMA"); goto out; } - cmd.prp1 = cpu_to_le64(iova); + cmd.dptr.prp1 = cpu_to_le64(iova); if (nvme_cmd_sync(bs, s->queues[0], &cmd)) { error_setg(errp, "Failed to identify controller"); @@ -537,7 +537,7 @@ static void nvme_identify(BlockDriverState *bs, int namespace, Error **errp) s->page_size / sizeof(uint64_t) * s->page_size); oncs = le16_to_cpu(idctrl->oncs); - s->supports_write_zeroes = !!(oncs & NVME_ONCS_WRITE_ZEROS); + s->supports_write_zeroes = !!(oncs & NVME_ONCS_WRITE_ZEROES); s->supports_discard = !!(oncs & NVME_ONCS_DSM); memset(resp, 0, 4096); @@ -629,7 +629,7 @@ static bool nvme_add_io_queue(BlockDriverState *bs, Error **errp) } cmd = (NvmeCmd) { .opcode = NVME_ADM_CMD_CREATE_CQ, - .prp1 = cpu_to_le64(q->cq.iova), + .dptr.prp1 = cpu_to_le64(q->cq.iova), .cdw10 = cpu_to_le32(((queue_size - 1) << 16) | (n & 0xFFFF)), .cdw11 = cpu_to_le32(0x3), }; @@ -640,7 +640,7 @@ static bool nvme_add_io_queue(BlockDriverState *bs, Error **errp) } cmd = (NvmeCmd) { .opcode = NVME_ADM_CMD_CREATE_SQ, - .prp1 = cpu_to_le64(q->sq.iova), + .dptr.prp1 = cpu_to_le64(q->sq.iova), .cdw10 = cpu_to_le32(((queue_size - 1) << 16) | (n & 0xFFFF)), .cdw11 = cpu_to_le32(0x1 | (n << 16)), }; @@ -988,16 +988,16 @@ try_map: case 0: abort(); case 1: - cmd->prp1 = pagelist[0]; - cmd->prp2 = 0; + cmd->dptr.prp1 = pagelist[0]; + cmd->dptr.prp2 = 0; break; case 2: - cmd->prp1 = pagelist[0]; - cmd->prp2 = pagelist[1]; + cmd->dptr.prp1 = pagelist[0]; + cmd->dptr.prp2 = pagelist[1]; break; default: - cmd->prp1 = pagelist[0]; - cmd->prp2 = cpu_to_le64(req->prp_list_iova + sizeof(uint64_t)); + cmd->dptr.prp1 = pagelist[0]; + cmd->dptr.prp2 = cpu_to_le64(req->prp_list_iova + sizeof(uint64_t)); break; } trace_nvme_cmd_map_qiov(s, cmd, req, qiov, entries); @@ -1201,7 +1201,7 @@ static coroutine_fn int nvme_co_pwrite_zeroes(BlockDriverState *bs, } NvmeCmd cmd = { - .opcode = NVME_CMD_WRITE_ZEROS, + .opcode = NVME_CMD_WRITE_ZEROES, .nsid = cpu_to_le32(s->nsid), .cdw10 = cpu_to_le32((offset >> s->blkshift) & 0xFFFFFFFF), .cdw11 = cpu_to_le32(((offset >> s->blkshift) >> 32) & 0xFFFFFFFF), diff --git a/hw/block/nvme.c b/hw/block/nvme.c index 3426e17e65..63078f6009 100644 --- a/hw/block/nvme.c +++ b/hw/block/nvme.c @@ -11,7 +11,7 @@ /** * Reference Specs: http://www.nvmexpress.org, 1.2, 1.1, 1.0e * - * http://www.nvmexpress.org/resources/ + * https://nvmexpress.org/developers/nvme-specification/ */ /** @@ -20,7 +20,9 @@ * -device nvme,drive=<drive_id>,serial=<serial>,id=<id[optional]>, \ * cmb_size_mb=<cmb_size_mb[optional]>, \ * [pmrdev=<mem_backend_file_id>,] \ - * max_ioqpairs=<N[optional]> + * max_ioqpairs=<N[optional]>, \ + * aerl=<N[optional]>, aer_max_queued=<N[optional]>, \ + * mdts=<N[optional]> * * 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. @@ -32,6 +34,20 @@ * For example: * -object memory-backend-file,id=<mem_id>,share=on,mem-path=<file_path>, \ * size=<size> .... -device nvme,...,pmrdev=<mem_id> + * + * + * nvme device parameters + * ~~~~~~~~~~~~~~~~~~~~~~ + * - `aerl` + * The Asynchronous Event Request Limit (AERL). Indicates the maximum number + * of concurrently outstanding Asynchronous Event Request commands suppoert + * by the controller. This is a 0's based value. + * + * - `aer_max_queued` + * This is the maximum number of events that the device will enqueue for + * completion when there are no oustanding AERs. When the maximum number of + * enqueued events are reached, subsequent events will be dropped. + * */ #include "qemu/osdep.h" @@ -55,10 +71,14 @@ #include "nvme.h" #define NVME_MAX_IOQPAIRS 0xffff -#define NVME_REG_SIZE 0x1000 #define NVME_DB_SIZE 4 +#define NVME_SPEC_VER 0x00010300 #define NVME_CMB_BIR 2 #define NVME_PMR_BIR 2 +#define NVME_TEMPERATURE 0x143 +#define NVME_TEMPERATURE_WARNING 0x157 +#define NVME_TEMPERATURE_CRITICAL 0x175 +#define NVME_NUM_FW_SLOTS 1 #define NVME_GUEST_ERR(trace, fmt, ...) \ do { \ @@ -67,8 +87,44 @@ " in %s: " fmt "\n", __func__, ## __VA_ARGS__); \ } while (0) +static const bool nvme_feature_support[NVME_FID_MAX] = { + [NVME_ARBITRATION] = true, + [NVME_POWER_MANAGEMENT] = true, + [NVME_TEMPERATURE_THRESHOLD] = true, + [NVME_ERROR_RECOVERY] = true, + [NVME_VOLATILE_WRITE_CACHE] = true, + [NVME_NUMBER_OF_QUEUES] = true, + [NVME_INTERRUPT_COALESCING] = true, + [NVME_INTERRUPT_VECTOR_CONF] = true, + [NVME_WRITE_ATOMICITY] = true, + [NVME_ASYNCHRONOUS_EVENT_CONF] = true, + [NVME_TIMESTAMP] = true, +}; + +static const uint32_t nvme_feature_cap[NVME_FID_MAX] = { + [NVME_TEMPERATURE_THRESHOLD] = NVME_FEAT_CAP_CHANGE, + [NVME_VOLATILE_WRITE_CACHE] = NVME_FEAT_CAP_CHANGE, + [NVME_NUMBER_OF_QUEUES] = NVME_FEAT_CAP_CHANGE, + [NVME_ASYNCHRONOUS_EVENT_CONF] = NVME_FEAT_CAP_CHANGE, + [NVME_TIMESTAMP] = NVME_FEAT_CAP_CHANGE, +}; + static void nvme_process_sq(void *opaque); +static uint16_t nvme_cid(NvmeRequest *req) +{ + if (!req) { + return 0xffff; + } + + return le16_to_cpu(req->cqe.cid); +} + +static uint16_t nvme_sqid(NvmeRequest *req) +{ + return le16_to_cpu(req->sq->sqid); +} + static bool nvme_addr_is_cmb(NvmeCtrl *n, hwaddr addr) { hwaddr low = n->ctrl_mem.addr; @@ -77,10 +133,17 @@ static bool nvme_addr_is_cmb(NvmeCtrl *n, hwaddr addr) return addr >= low && addr < hi; } +static inline void *nvme_addr_to_cmb(NvmeCtrl *n, hwaddr addr) +{ + assert(nvme_addr_is_cmb(n, addr)); + + return &n->cmbuf[addr - n->ctrl_mem.addr]; +} + static void nvme_addr_read(NvmeCtrl *n, hwaddr addr, void *buf, int size) { if (n->bar.cmbsz && nvme_addr_is_cmb(n, addr)) { - memcpy(buf, (void *)&n->cmbuf[addr - n->ctrl_mem.addr], size); + memcpy(buf, nvme_addr_to_cmb(n, addr), size); return; } @@ -163,36 +226,125 @@ static void nvme_irq_deassert(NvmeCtrl *n, NvmeCQueue *cq) } } -static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1, - uint64_t prp2, uint32_t len, NvmeCtrl *n) +static void nvme_req_clear(NvmeRequest *req) +{ + req->ns = NULL; + memset(&req->cqe, 0x0, sizeof(req->cqe)); +} + +static void nvme_req_exit(NvmeRequest *req) +{ + if (req->qsg.sg) { + qemu_sglist_destroy(&req->qsg); + } + + if (req->iov.iov) { + qemu_iovec_destroy(&req->iov); + } +} + +static uint16_t nvme_map_addr_cmb(NvmeCtrl *n, QEMUIOVector *iov, hwaddr addr, + size_t len) +{ + if (!len) { + return NVME_SUCCESS; + } + + trace_pci_nvme_map_addr_cmb(addr, len); + + if (!nvme_addr_is_cmb(n, addr) || !nvme_addr_is_cmb(n, addr + len - 1)) { + return NVME_DATA_TRAS_ERROR; + } + + qemu_iovec_add(iov, nvme_addr_to_cmb(n, addr), len); + + return NVME_SUCCESS; +} + +static uint16_t nvme_map_addr(NvmeCtrl *n, QEMUSGList *qsg, QEMUIOVector *iov, + hwaddr addr, size_t len) +{ + if (!len) { + return NVME_SUCCESS; + } + + trace_pci_nvme_map_addr(addr, len); + + if (nvme_addr_is_cmb(n, addr)) { + if (qsg && qsg->sg) { + return NVME_INVALID_USE_OF_CMB | NVME_DNR; + } + + assert(iov); + + if (!iov->iov) { + qemu_iovec_init(iov, 1); + } + + return nvme_map_addr_cmb(n, iov, addr, len); + } + + if (iov && iov->iov) { + return NVME_INVALID_USE_OF_CMB | NVME_DNR; + } + + assert(qsg); + + if (!qsg->sg) { + pci_dma_sglist_init(qsg, &n->parent_obj, 1); + } + + qemu_sglist_add(qsg, addr, len); + + return NVME_SUCCESS; +} + +static uint16_t nvme_map_prp(NvmeCtrl *n, uint64_t prp1, uint64_t prp2, + uint32_t len, NvmeRequest *req) { hwaddr trans_len = n->page_size - (prp1 % n->page_size); trans_len = MIN(len, trans_len); int num_prps = (len >> n->page_bits) + 1; + uint16_t status; + bool prp_list_in_cmb = false; + + 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; - } else if (n->bar.cmbsz && prp1 >= n->ctrl_mem.addr && - prp1 < n->ctrl_mem.addr + int128_get64(n->ctrl_mem.size)) { - qsg->nsg = 0; + } + + if (nvme_addr_is_cmb(n, prp1)) { qemu_iovec_init(iov, num_prps); - qemu_iovec_add(iov, (void *)&n->cmbuf[prp1 - n->ctrl_mem.addr], trans_len); } else { pci_dma_sglist_init(qsg, &n->parent_obj, num_prps); - qemu_sglist_add(qsg, prp1, trans_len); } + + status = nvme_map_addr(n, qsg, iov, prp1, trans_len); + if (status) { + return status; + } + len -= trans_len; if (len) { if (unlikely(!prp2)) { trace_pci_nvme_err_invalid_prp2_missing(); - goto unmap; + return NVME_INVALID_FIELD | NVME_DNR; } + if (len > n->page_size) { uint64_t prp_list[n->max_prp_ents]; uint32_t nents, prp_trans; int i = 0; + if (nvme_addr_is_cmb(n, prp2)) { + prp_list_in_cmb = true; + } + 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); @@ -202,7 +354,11 @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1, if (i == n->max_prp_ents - 1 && len > n->page_size) { if (unlikely(!prp_ent || prp_ent & (n->page_size - 1))) { trace_pci_nvme_err_invalid_prplist_ent(prp_ent); - goto unmap; + return NVME_INVALID_FIELD | NVME_DNR; + } + + if (prp_list_in_cmb != nvme_addr_is_cmb(n, prp_ent)) { + return NVME_INVALID_USE_OF_CMB | NVME_DNR; } i = 0; @@ -215,89 +371,87 @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1, if (unlikely(!prp_ent || prp_ent & (n->page_size - 1))) { trace_pci_nvme_err_invalid_prplist_ent(prp_ent); - goto unmap; + return NVME_INVALID_FIELD | NVME_DNR; } trans_len = MIN(len, n->page_size); - if (qsg->nsg){ - qemu_sglist_add(qsg, prp_ent, trans_len); - } else { - qemu_iovec_add(iov, (void *)&n->cmbuf[prp_ent - n->ctrl_mem.addr], trans_len); + status = nvme_map_addr(n, qsg, iov, prp_ent, trans_len); + if (status) { + return status; } + len -= trans_len; i++; } } else { if (unlikely(prp2 & (n->page_size - 1))) { trace_pci_nvme_err_invalid_prp2_align(prp2); - goto unmap; + return NVME_INVALID_FIELD | NVME_DNR; } - if (qsg->nsg) { - qemu_sglist_add(qsg, prp2, len); - } else { - qemu_iovec_add(iov, (void *)&n->cmbuf[prp2 - n->ctrl_mem.addr], trans_len); + status = nvme_map_addr(n, qsg, iov, prp2, len); + if (status) { + return status; } } } - return NVME_SUCCESS; - unmap: - qemu_sglist_destroy(qsg); - return NVME_INVALID_FIELD | NVME_DNR; + return NVME_SUCCESS; } -static uint16_t nvme_dma_write_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len, - uint64_t prp1, uint64_t prp2) +static uint16_t nvme_dma_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len, + uint64_t prp1, uint64_t prp2, DMADirection dir, + NvmeRequest *req) { - QEMUSGList qsg; - QEMUIOVector iov; uint16_t status = NVME_SUCCESS; - if (nvme_map_prp(&qsg, &iov, prp1, prp2, len, n)) { - return NVME_INVALID_FIELD | NVME_DNR; - } - if (qsg.nsg > 0) { - if (dma_buf_write(ptr, len, &qsg)) { - status = NVME_INVALID_FIELD | NVME_DNR; - } - qemu_sglist_destroy(&qsg); - } else { - if (qemu_iovec_to_buf(&iov, 0, ptr, len) != len) { - status = NVME_INVALID_FIELD | NVME_DNR; - } - qemu_iovec_destroy(&iov); + status = nvme_map_prp(n, prp1, prp2, len, req); + if (status) { + return status; } - return status; -} -static uint16_t nvme_dma_read_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len, - uint64_t prp1, uint64_t prp2) -{ - QEMUSGList qsg; - QEMUIOVector iov; - uint16_t status = NVME_SUCCESS; + /* assert that only one of qsg and iov carries data */ + assert((req->qsg.nsg > 0) != (req->iov.niov > 0)); - trace_pci_nvme_dma_read(prp1, prp2); + if (req->qsg.nsg > 0) { + uint64_t residual; - if (nvme_map_prp(&qsg, &iov, prp1, prp2, len, n)) { - return NVME_INVALID_FIELD | NVME_DNR; - } - if (qsg.nsg > 0) { - if (unlikely(dma_buf_read(ptr, len, &qsg))) { + if (dir == DMA_DIRECTION_TO_DEVICE) { + residual = dma_buf_write(ptr, len, &req->qsg); + } else { + residual = dma_buf_read(ptr, len, &req->qsg); + } + + if (unlikely(residual)) { trace_pci_nvme_err_invalid_dma(); status = NVME_INVALID_FIELD | NVME_DNR; } - qemu_sglist_destroy(&qsg); } else { - if (unlikely(qemu_iovec_from_buf(&iov, 0, ptr, len) != len)) { + size_t bytes; + + if (dir == DMA_DIRECTION_TO_DEVICE) { + bytes = qemu_iovec_to_buf(&req->iov, 0, ptr, len); + } else { + bytes = qemu_iovec_from_buf(&req->iov, 0, ptr, len); + } + + if (unlikely(bytes != len)) { trace_pci_nvme_err_invalid_dma(); status = NVME_INVALID_FIELD | NVME_DNR; } - qemu_iovec_destroy(&iov); } + 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; @@ -321,6 +475,7 @@ static void nvme_post_cqes(void *opaque) 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); } if (cq->tail != cq->head) { @@ -331,11 +486,115 @@ static void nvme_post_cqes(void *opaque) 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); 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); } +static void nvme_process_aers(void *opaque) +{ + NvmeCtrl *n = opaque; + NvmeAsyncEvent *event, *next; + + trace_pci_nvme_process_aers(n->aer_queued); + + QTAILQ_FOREACH_SAFE(event, &n->aer_queue, entry, next) { + NvmeRequest *req; + NvmeAerResult *result; + + /* can't post cqe if there is nothing to complete */ + if (!n->outstanding_aers) { + trace_pci_nvme_no_outstanding_aers(); + break; + } + + /* ignore if masked (cqe posted, but event not cleared) */ + if (n->aer_mask & (1 << event->result.event_type)) { + trace_pci_nvme_aer_masked(event->result.event_type, n->aer_mask); + continue; + } + + QTAILQ_REMOVE(&n->aer_queue, event, entry); + n->aer_queued--; + + n->aer_mask |= 1 << event->result.event_type; + n->outstanding_aers--; + + req = n->aer_reqs[n->outstanding_aers]; + + result = (NvmeAerResult *) &req->cqe.result; + result->event_type = event->result.event_type; + result->event_info = event->result.event_info; + 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); + + nvme_enqueue_req_completion(&n->admin_cq, req); + } +} + +static void nvme_enqueue_event(NvmeCtrl *n, uint8_t event_type, + uint8_t event_info, uint8_t log_page) +{ + NvmeAsyncEvent *event; + + trace_pci_nvme_enqueue_event(event_type, event_info, log_page); + + if (n->aer_queued == n->params.aer_max_queued) { + trace_pci_nvme_enqueue_event_noqueue(n->aer_queued); + return; + } + + event = g_new(NvmeAsyncEvent, 1); + event->result = (NvmeAerResult) { + .event_type = event_type, + .event_info = event_info, + .log_page = log_page, + }; + + QTAILQ_INSERT_TAIL(&n->aer_queue, event, entry); + n->aer_queued++; + + nvme_process_aers(n); +} + +static void nvme_clear_events(NvmeCtrl *n, uint8_t event_type) +{ + n->aer_mask &= ~(1 << event_type); + if (!QTAILQ_EMPTY(&n->aer_queue)) { + nvme_process_aers(n); + } +} + +static inline uint16_t nvme_check_mdts(NvmeCtrl *n, size_t len) +{ + uint8_t mdts = n->params.mdts; + + if (mdts && len > n->page_size << mdts) { + return NVME_INVALID_FIELD | NVME_DNR; + } + + return NVME_SUCCESS; +} + +static inline uint16_t nvme_check_bounds(NvmeCtrl *n, NvmeNamespace *ns, + uint64_t slba, uint32_t nlb) +{ + uint64_t nsze = le64_to_cpu(ns->id_ns.nsze); + + if (unlikely(UINT64_MAX - slba < nlb || slba + nlb > nsze)) { + return NVME_LBA_RANGE | NVME_DNR; + } + + return NVME_SUCCESS; +} + static void nvme_rw_cb(void *opaque, int ret) { NvmeRequest *req = opaque; @@ -343,6 +602,8 @@ static void nvme_rw_cb(void *opaque, int ret) NvmeCtrl *n = sq->ctrl; NvmeCQueue *cq = n->cq[sq->cqid]; + trace_pci_nvme_rw_cb(nvme_cid(req)); + if (!ret) { block_acct_done(blk_get_stats(n->conf.blk), &req->acct); req->status = NVME_SUCCESS; @@ -350,16 +611,12 @@ static void nvme_rw_cb(void *opaque, int ret) block_acct_failed(blk_get_stats(n->conf.blk), &req->acct); req->status = NVME_INTERNAL_DEV_ERROR; } - if (req->has_sg) { - qemu_sglist_destroy(&req->qsg); - } + nvme_enqueue_req_completion(cq, req); } -static uint16_t nvme_flush(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd, - NvmeRequest *req) +static uint16_t nvme_flush(NvmeCtrl *n, NvmeRequest *req) { - req->has_sg = false; 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); @@ -367,23 +624,26 @@ static uint16_t nvme_flush(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd, return NVME_NO_COMPLETE; } -static uint16_t nvme_write_zeros(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd, - NvmeRequest *req) +static uint16_t nvme_write_zeroes(NvmeCtrl *n, NvmeRequest *req) { - NvmeRwCmd *rw = (NvmeRwCmd *)cmd; + 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; + uint16_t status; + + trace_pci_nvme_write_zeroes(nvme_cid(req), slba, nlb); - if (unlikely(slba + nlb > ns->id_ns.nsze)) { + status = nvme_check_bounds(n, ns, slba, nlb); + if (status) { trace_pci_nvme_err_invalid_lba_range(slba, nlb, ns->id_ns.nsze); - return NVME_LBA_RANGE | NVME_DNR; + return status; } - req->has_sg = false; block_acct_start(blk_get_stats(n->conf.blk), &req->acct, 0, BLOCK_ACCT_WRITE); req->aiocb = blk_aio_pwrite_zeroes(n->conf.blk, offset, count, @@ -391,14 +651,12 @@ static uint16_t nvme_write_zeros(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd, return NVME_NO_COMPLETE; } -static uint16_t nvme_rw(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd, - NvmeRequest *req) +static uint16_t nvme_rw(NvmeCtrl *n, NvmeRequest *req) { - NvmeRwCmd *rw = (NvmeRwCmd *)cmd; + NvmeRwCmd *rw = (NvmeRwCmd *)&req->cmd; + NvmeNamespace *ns = req->ns; uint32_t nlb = le32_to_cpu(rw->nlb) + 1; uint64_t slba = le64_to_cpu(rw->slba); - uint64_t prp1 = le64_to_cpu(rw->prp1); - uint64_t prp2 = le64_to_cpu(rw->prp2); uint8_t lba_index = NVME_ID_NS_FLBAS_INDEX(ns->id_ns.flbas); uint8_t data_shift = ns->id_ns.lbaf[lba_index].ds; @@ -406,30 +664,40 @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd, 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; + uint16_t status; trace_pci_nvme_rw(is_write ? "write" : "read", nlb, data_size, slba); - if (unlikely((slba + nlb) > ns->id_ns.nsze)) { + 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; + } + + status = nvme_check_bounds(n, ns, slba, nlb); + if (status) { trace_pci_nvme_err_invalid_lba_range(slba, nlb, ns->id_ns.nsze); - return NVME_LBA_RANGE | NVME_DNR; + block_acct_invalid(blk_get_stats(n->conf.blk), acct); + return status; } - if (nvme_map_prp(&req->qsg, &req->iov, prp1, prp2, data_size, n)) { + if (nvme_map_dptr(n, data_size, req)) { block_acct_invalid(blk_get_stats(n->conf.blk), acct); return NVME_INVALID_FIELD | NVME_DNR; } - dma_acct_start(n->conf.blk, &req->acct, &req->qsg, acct); if (req->qsg.nsg > 0) { - req->has_sg = true; + 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); } else { - req->has_sg = false; + 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) : @@ -440,27 +708,29 @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd, return NVME_NO_COMPLETE; } -static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req) +static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeRequest *req) { - NvmeNamespace *ns; - uint32_t nsid = le32_to_cpu(cmd->nsid); + uint32_t nsid = le32_to_cpu(req->cmd.nsid); + + trace_pci_nvme_io_cmd(nvme_cid(req), nsid, nvme_sqid(req), + req->cmd.opcode); if (unlikely(nsid == 0 || nsid > n->num_namespaces)) { trace_pci_nvme_err_invalid_ns(nsid, n->num_namespaces); return NVME_INVALID_NSID | NVME_DNR; } - ns = &n->namespaces[nsid - 1]; - switch (cmd->opcode) { + req->ns = &n->namespaces[nsid - 1]; + switch (req->cmd.opcode) { case NVME_CMD_FLUSH: - return nvme_flush(n, ns, cmd, req); - case NVME_CMD_WRITE_ZEROS: - return nvme_write_zeros(n, ns, cmd, req); + return nvme_flush(n, req); + case NVME_CMD_WRITE_ZEROES: + return nvme_write_zeroes(n, req); case NVME_CMD_WRITE: case NVME_CMD_READ: - return nvme_rw(n, ns, cmd, req); + return nvme_rw(n, req); default: - trace_pci_nvme_err_invalid_opc(cmd->opcode); + trace_pci_nvme_err_invalid_opc(req->cmd.opcode); return NVME_INVALID_OPCODE | NVME_DNR; } } @@ -476,10 +746,10 @@ static void nvme_free_sq(NvmeSQueue *sq, NvmeCtrl *n) } } -static uint16_t nvme_del_sq(NvmeCtrl *n, NvmeCmd *cmd) +static uint16_t nvme_del_sq(NvmeCtrl *n, NvmeRequest *req) { - NvmeDeleteQ *c = (NvmeDeleteQ *)cmd; - NvmeRequest *req, *next; + NvmeDeleteQ *c = (NvmeDeleteQ *)&req->cmd; + NvmeRequest *r, *next; NvmeSQueue *sq; NvmeCQueue *cq; uint16_t qid = le16_to_cpu(c->qid); @@ -493,19 +763,19 @@ static uint16_t nvme_del_sq(NvmeCtrl *n, NvmeCmd *cmd) sq = n->sq[qid]; while (!QTAILQ_EMPTY(&sq->out_req_list)) { - req = QTAILQ_FIRST(&sq->out_req_list); - assert(req->aiocb); - blk_aio_cancel(req->aiocb); + r = QTAILQ_FIRST(&sq->out_req_list); + assert(r->aiocb); + blk_aio_cancel(r->aiocb); } if (!nvme_check_cqid(n, sq->cqid)) { cq = n->cq[sq->cqid]; QTAILQ_REMOVE(&cq->sq_list, sq, entry); nvme_post_cqes(cq); - QTAILQ_FOREACH_SAFE(req, &cq->req_list, entry, next) { - if (req->sq == sq) { - QTAILQ_REMOVE(&cq->req_list, req, entry); - QTAILQ_INSERT_TAIL(&sq->req_list, req, entry); + QTAILQ_FOREACH_SAFE(r, &cq->req_list, entry, next) { + if (r->sq == sq) { + QTAILQ_REMOVE(&cq->req_list, r, entry); + QTAILQ_INSERT_TAIL(&sq->req_list, r, entry); } } } @@ -526,7 +796,7 @@ static void nvme_init_sq(NvmeSQueue *sq, NvmeCtrl *n, uint64_t dma_addr, sq->size = size; sq->cqid = cqid; sq->head = sq->tail = 0; - sq->io_req = g_new(NvmeRequest, sq->size); + sq->io_req = g_new0(NvmeRequest, sq->size); QTAILQ_INIT(&sq->req_list); QTAILQ_INIT(&sq->out_req_list); @@ -542,10 +812,10 @@ static void nvme_init_sq(NvmeSQueue *sq, NvmeCtrl *n, uint64_t dma_addr, n->sq[sqid] = sq; } -static uint16_t nvme_create_sq(NvmeCtrl *n, NvmeCmd *cmd) +static uint16_t nvme_create_sq(NvmeCtrl *n, NvmeRequest *req) { NvmeSQueue *sq; - NvmeCreateSq *c = (NvmeCreateSq *)cmd; + NvmeCreateSq *c = (NvmeCreateSq *)&req->cmd; uint16_t cqid = le16_to_cpu(c->cqid); uint16_t sqid = le16_to_cpu(c->sqid); @@ -580,6 +850,162 @@ static uint16_t nvme_create_sq(NvmeCtrl *n, NvmeCmd *cmd) return NVME_SUCCESS; } +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 trans_len; + 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) { + 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 (off > sizeof(smart)) { + return NVME_INVALID_FIELD | NVME_DNR; + } + + 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, + 1000)); + smart.host_read_commands[0] = cpu_to_le64(read_commands); + smart.host_write_commands[0] = cpu_to_le64(write_commands); + + smart.temperature = cpu_to_le16(n->temperature); + + if ((n->temperature >= n->features.temp_thresh_hi) || + (n->temperature <= n->features.temp_thresh_low)) { + smart.critical_warning |= NVME_SMART_TEMPERATURE; + } + + current_ms = qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL); + smart.power_on_hours[0] = + cpu_to_le64((((current_ms - n->starttime_ms) / 1000) / 60) / 60); + + if (!rae) { + 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); +} + +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)) { + return NVME_INVALID_FIELD | NVME_DNR; + } + + 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); +} + +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; + } + + 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); +} + +static uint16_t nvme_get_log(NvmeCtrl *n, NvmeRequest *req) +{ + NvmeCmd *cmd = &req->cmd; + + uint32_t dw10 = le32_to_cpu(cmd->cdw10); + uint32_t dw11 = le32_to_cpu(cmd->cdw11); + uint32_t dw12 = le32_to_cpu(cmd->cdw12); + uint32_t dw13 = le32_to_cpu(cmd->cdw13); + uint8_t lid = dw10 & 0xff; + uint8_t lsp = (dw10 >> 8) & 0xf; + uint8_t rae = (dw10 >> 15) & 0x1; + uint32_t numdl, numdu; + uint64_t off, lpol, lpou; + size_t len; + uint16_t status; + + numdl = (dw10 >> 16); + numdu = (dw11 & 0xffff); + lpol = dw12; + lpou = dw13; + + len = (((numdu << 16) | numdl) + 1) << 2; + off = (lpou << 32ULL) | lpol; + + if (off & 0x3) { + return NVME_INVALID_FIELD | NVME_DNR; + } + + trace_pci_nvme_get_log(nvme_cid(req), lid, lsp, rae, len, off); + + status = nvme_check_mdts(n, len); + if (status) { + trace_pci_nvme_err_mdts(nvme_cid(req), len); + return status; + } + + switch (lid) { + case NVME_LOG_ERROR_INFO: + return nvme_error_info(n, rae, len, off, req); + case NVME_LOG_SMART_INFO: + return nvme_smart_info(n, rae, len, off, req); + case NVME_LOG_FW_SLOT_INFO: + return nvme_fw_log_info(n, len, off, req); + default: + trace_pci_nvme_err_invalid_log_page(nvme_cid(req), lid); + return NVME_INVALID_FIELD | NVME_DNR; + } +} + static void nvme_free_cq(NvmeCQueue *cq, NvmeCtrl *n) { n->cq[cq->cqid] = NULL; @@ -591,9 +1017,9 @@ static void nvme_free_cq(NvmeCQueue *cq, NvmeCtrl *n) } } -static uint16_t nvme_del_cq(NvmeCtrl *n, NvmeCmd *cmd) +static uint16_t nvme_del_cq(NvmeCtrl *n, NvmeRequest *req) { - NvmeDeleteQ *c = (NvmeDeleteQ *)cmd; + NvmeDeleteQ *c = (NvmeDeleteQ *)&req->cmd; NvmeCQueue *cq; uint16_t qid = le16_to_cpu(c->qid); @@ -634,10 +1060,10 @@ static void nvme_init_cq(NvmeCQueue *cq, NvmeCtrl *n, uint64_t dma_addr, cq->timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, nvme_post_cqes, cq); } -static uint16_t nvme_create_cq(NvmeCtrl *n, NvmeCmd *cmd) +static uint16_t nvme_create_cq(NvmeCtrl *n, NvmeRequest *req) { NvmeCQueue *cq; - NvmeCreateCq *c = (NvmeCreateCq *)cmd; + NvmeCreateCq *c = (NvmeCreateCq *)&req->cmd; uint16_t cqid = le16_to_cpu(c->cqid); uint16_t vector = le16_to_cpu(c->irq_vector); uint16_t qsize = le16_to_cpu(c->qsize); @@ -675,23 +1101,32 @@ static uint16_t nvme_create_cq(NvmeCtrl *n, NvmeCmd *cmd) cq = g_malloc0(sizeof(*cq)); nvme_init_cq(cq, n, prp1, cqid, vector, qsize + 1, NVME_CQ_FLAGS_IEN(qflags)); + + /* + * It is only required to set qs_created when creating a completion queue; + * creating a submission queue without a matching completion queue will + * fail. + */ + n->qs_created = true; return NVME_SUCCESS; } -static uint16_t nvme_identify_ctrl(NvmeCtrl *n, NvmeIdentify *c) +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_read_prp(n, (uint8_t *)&n->id_ctrl, sizeof(n->id_ctrl), - prp1, prp2); + return nvme_dma_prp(n, (uint8_t *)&n->id_ctrl, sizeof(n->id_ctrl), prp1, + prp2, DMA_DIRECTION_FROM_DEVICE, req); } -static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeIdentify *c) +static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeRequest *req) { NvmeNamespace *ns; + 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); @@ -705,12 +1140,13 @@ static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeIdentify *c) ns = &n->namespaces[nsid - 1]; - return nvme_dma_read_prp(n, (uint8_t *)&ns->id_ns, sizeof(ns->id_ns), - prp1, prp2); + return nvme_dma_prp(n, (uint8_t *)&ns->id_ns, sizeof(ns->id_ns), prp1, + prp2, DMA_DIRECTION_FROM_DEVICE, req); } -static uint16_t nvme_identify_nslist(NvmeCtrl *n, NvmeIdentify *c) +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); @@ -721,6 +1157,16 @@ static uint16_t nvme_identify_nslist(NvmeCtrl *n, NvmeIdentify *c) trace_pci_nvme_identify_nslist(min_nsid); + /* + * Both 0xffffffff (NVME_NSID_BROADCAST) and 0xfffffffe are invalid values + * since the Active Namespace ID List should return namespaces with ids + * *higher* than the NSID specified in the command. This is also specified + * in the spec (NVM Express v1.3d, Section 5.15.4). + */ + if (min_nsid >= NVME_NSID_BROADCAST - 1) { + return NVME_INVALID_NSID | NVME_DNR; + } + list = g_malloc0(data_len); for (i = 0; i < n->num_namespaces; i++) { if (i < min_nsid) { @@ -731,28 +1177,84 @@ static uint16_t nvme_identify_nslist(NvmeCtrl *n, NvmeIdentify *c) break; } } - ret = nvme_dma_read_prp(n, (uint8_t *)list, data_len, prp1, prp2); + ret = nvme_dma_prp(n, (uint8_t *)list, data_len, prp1, prp2, + DMA_DIRECTION_FROM_DEVICE, req); g_free(list); return ret; } -static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd) +static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeRequest *req) { - NvmeIdentify *c = (NvmeIdentify *)cmd; + 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 { + struct { + NvmeIdNsDescr hdr; + uint8_t v[16]; + } uuid; + }; + + struct data *ns_descrs = (struct data *)list; + + 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); + return NVME_INVALID_NSID | NVME_DNR; + } + + memset(list, 0x0, sizeof(list)); + + /* + * Because the NGUID and EUI64 fields are 0 in the Identify Namespace data + * structure, a Namespace UUID (nidt = 0x3) must be reported in the + * Namespace Identification Descriptor. Add a very basic Namespace UUID + * here. + */ + ns_descrs->uuid.hdr.nidt = NVME_NIDT_UUID; + 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); +} + +static uint16_t nvme_identify(NvmeCtrl *n, NvmeRequest *req) +{ + NvmeIdentify *c = (NvmeIdentify *)&req->cmd; switch (le32_to_cpu(c->cns)) { case NVME_ID_CNS_NS: - return nvme_identify_ns(n, c); + return nvme_identify_ns(n, req); case NVME_ID_CNS_CTRL: - return nvme_identify_ctrl(n, c); + return nvme_identify_ctrl(n, req); case NVME_ID_CNS_NS_ACTIVE_LIST: - return nvme_identify_nslist(n, c); + return nvme_identify_nslist(n, req); + case NVME_ID_CNS_NS_DESCR_LIST: + return nvme_identify_ns_descr_list(n, req); default: trace_pci_nvme_err_invalid_identify_cns(le32_to_cpu(c->cns)); return NVME_INVALID_FIELD | NVME_DNR; } } +static uint16_t nvme_abort(NvmeCtrl *n, NvmeRequest *req) +{ + uint16_t sqid = le32_to_cpu(req->cmd.cdw10) & 0xffff; + + req->cqe.result = 1; + if (nvme_check_sqid(n, sqid)) { + return NVME_INVALID_FIELD | NVME_DNR; + } + + return NVME_SUCCESS; +} + static inline void nvme_set_timestamp(NvmeCtrl *n, uint64_t ts) { trace_pci_nvme_setfeat_timestamp(ts); @@ -793,52 +1295,150 @@ static inline uint64_t nvme_get_timestamp(const NvmeCtrl *n) return cpu_to_le64(ts.all); } -static uint16_t nvme_get_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd) +static uint16_t nvme_get_feature_timestamp(NvmeCtrl *n, NvmeRequest *req) { - uint64_t prp1 = le64_to_cpu(cmd->prp1); - uint64_t prp2 = le64_to_cpu(cmd->prp2); + 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_read_prp(n, (uint8_t *)×tamp, - sizeof(timestamp), prp1, prp2); + return nvme_dma_prp(n, (uint8_t *)×tamp, sizeof(timestamp), prp1, + prp2, DMA_DIRECTION_FROM_DEVICE, req); } -static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req) +static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeRequest *req) { + NvmeCmd *cmd = &req->cmd; uint32_t dw10 = le32_to_cpu(cmd->cdw10); + uint32_t dw11 = le32_to_cpu(cmd->cdw11); + uint32_t nsid = le32_to_cpu(cmd->nsid); uint32_t result; + uint8_t fid = NVME_GETSETFEAT_FID(dw10); + NvmeGetFeatureSelect sel = NVME_GETFEAT_SELECT(dw10); + uint16_t iv; + + static const uint32_t nvme_feature_default[NVME_FID_MAX] = { + [NVME_ARBITRATION] = NVME_ARB_AB_NOLIMIT, + }; + + trace_pci_nvme_getfeat(nvme_cid(req), 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) { + /* + * The Reservation Notification Mask and Reservation Persistence + * features require a status code of Invalid Field in Command when + * NSID is 0xFFFFFFFF. Since the device does not support those + * features we can always return Invalid Namespace or Format as we + * should do for all other features. + */ + return NVME_INVALID_NSID | NVME_DNR; + } + } + + switch (sel) { + case NVME_GETFEAT_SELECT_CURRENT: + break; + case NVME_GETFEAT_SELECT_SAVED: + /* no features are saveable by the controller; fallthrough */ + case NVME_GETFEAT_SELECT_DEFAULT: + goto defaults; + case NVME_GETFEAT_SELECT_CAP: + result = nvme_feature_cap[fid]; + goto out; + } + + switch (fid) { + case NVME_TEMPERATURE_THRESHOLD: + result = 0; + + /* + * The controller only implements the Composite Temperature sensor, so + * return 0 for all other sensors. + */ + if (NVME_TEMP_TMPSEL(dw11) != NVME_TEMP_TMPSEL_COMPOSITE) { + goto out; + } - switch (dw10) { + switch (NVME_TEMP_THSEL(dw11)) { + case NVME_TEMP_THSEL_OVER: + result = n->features.temp_thresh_hi; + goto out; + case NVME_TEMP_THSEL_UNDER: + result = n->features.temp_thresh_low; + goto out; + } + + return NVME_INVALID_FIELD | NVME_DNR; case NVME_VOLATILE_WRITE_CACHE: result = blk_enable_write_cache(n->conf.blk); trace_pci_nvme_getfeat_vwcache(result ? "enabled" : "disabled"); + goto out; + case NVME_ASYNCHRONOUS_EVENT_CONF: + result = n->features.async_config; + goto out; + case NVME_TIMESTAMP: + return nvme_get_feature_timestamp(n, req); + default: + break; + } + +defaults: + switch (fid) { + case NVME_TEMPERATURE_THRESHOLD: + result = 0; + + if (NVME_TEMP_TMPSEL(dw11) != NVME_TEMP_TMPSEL_COMPOSITE) { + break; + } + + if (NVME_TEMP_THSEL(dw11) == NVME_TEMP_THSEL_OVER) { + result = NVME_TEMPERATURE_WARNING; + } + break; case NVME_NUMBER_OF_QUEUES: - result = cpu_to_le32((n->params.max_ioqpairs - 1) | - ((n->params.max_ioqpairs - 1) << 16)); + result = (n->params.max_ioqpairs - 1) | + ((n->params.max_ioqpairs - 1) << 16); trace_pci_nvme_getfeat_numq(result); break; - case NVME_TIMESTAMP: - return nvme_get_feature_timestamp(n, cmd); + case NVME_INTERRUPT_VECTOR_CONF: + iv = dw11 & 0xffff; + if (iv >= n->params.max_ioqpairs + 1) { + return NVME_INVALID_FIELD | NVME_DNR; + } + + result = iv; + if (iv == n->admin_cq.vector) { + result |= NVME_INTVC_NOCOALESCING; + } + + break; default: - trace_pci_nvme_err_invalid_getfeat(dw10); - return NVME_INVALID_FIELD | NVME_DNR; + result = nvme_feature_default[fid]; + break; } - req->cqe.result = result; +out: + req->cqe.result = cpu_to_le32(result); return NVME_SUCCESS; } -static uint16_t nvme_set_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd) +static uint16_t nvme_set_feature_timestamp(NvmeCtrl *n, NvmeRequest *req) { uint16_t ret; uint64_t timestamp; - uint64_t prp1 = le64_to_cpu(cmd->prp1); - uint64_t prp2 = le64_to_cpu(cmd->prp2); + 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_write_prp(n, (uint8_t *)×tamp, - sizeof(timestamp), prp1, prp2); + ret = nvme_dma_prp(n, (uint8_t *)×tamp, sizeof(timestamp), prp1, + prp2, DMA_DIRECTION_TO_DEVICE, req); if (ret != NVME_SUCCESS) { return ret; } @@ -848,16 +1448,88 @@ static uint16_t nvme_set_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd) return NVME_SUCCESS; } -static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req) +static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeRequest *req) { + NvmeCmd *cmd = &req->cmd; uint32_t dw10 = le32_to_cpu(cmd->cdw10); uint32_t dw11 = le32_to_cpu(cmd->cdw11); + uint32_t nsid = le32_to_cpu(cmd->nsid); + uint8_t fid = NVME_GETSETFEAT_FID(dw10); + uint8_t save = NVME_SETFEAT_SAVE(dw10); + + trace_pci_nvme_setfeat(nvme_cid(req), fid, save, dw11); - switch (dw10) { + if (save) { + return NVME_FID_NOT_SAVEABLE | NVME_DNR; + } + + if (!nvme_feature_support[fid]) { + return NVME_INVALID_FIELD | NVME_DNR; + } + + 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; + } + } else if (nsid && nsid != NVME_NSID_BROADCAST) { + if (nsid > n->num_namespaces) { + return NVME_INVALID_NSID | NVME_DNR; + } + + return NVME_FEAT_NOT_NS_SPEC | NVME_DNR; + } + + if (!(nvme_feature_cap[fid] & NVME_FEAT_CAP_CHANGE)) { + return NVME_FEAT_NOT_CHANGEABLE | NVME_DNR; + } + + switch (fid) { + case NVME_TEMPERATURE_THRESHOLD: + if (NVME_TEMP_TMPSEL(dw11) != NVME_TEMP_TMPSEL_COMPOSITE) { + break; + } + + switch (NVME_TEMP_THSEL(dw11)) { + case NVME_TEMP_THSEL_OVER: + n->features.temp_thresh_hi = NVME_TEMP_TMPTH(dw11); + break; + case NVME_TEMP_THSEL_UNDER: + n->features.temp_thresh_low = NVME_TEMP_TMPTH(dw11); + break; + default: + return NVME_INVALID_FIELD | NVME_DNR; + } + + if (((n->temperature >= n->features.temp_thresh_hi) || + (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, + NVME_LOG_SMART_INFO); + } + + break; case NVME_VOLATILE_WRITE_CACHE: + if (!(dw11 & 0x1) && blk_enable_write_cache(n->conf.blk)) { + blk_flush(n->conf.blk); + } + 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; + } + + /* + * NVMe v1.3, Section 5.21.1.7: 0xffff is not an allowed value for NCQR + * and NSQR. + */ + if ((dw11 & 0xffff) == 0xffff || ((dw11 >> 16) & 0xffff) == 0xffff) { + return NVME_INVALID_FIELD | NVME_DNR; + } + trace_pci_nvme_setfeat_numq((dw11 & 0xFFFF) + 1, ((dw11 >> 16) & 0xFFFF) + 1, n->params.max_ioqpairs, @@ -865,34 +1537,63 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req) req->cqe.result = cpu_to_le32((n->params.max_ioqpairs - 1) | ((n->params.max_ioqpairs - 1) << 16)); break; + case NVME_ASYNCHRONOUS_EVENT_CONF: + n->features.async_config = dw11; + break; case NVME_TIMESTAMP: - return nvme_set_feature_timestamp(n, cmd); + return nvme_set_feature_timestamp(n, req); default: - trace_pci_nvme_err_invalid_setfeat(dw10); - return NVME_INVALID_FIELD | NVME_DNR; + return NVME_FEAT_NOT_CHANGEABLE | NVME_DNR; } return NVME_SUCCESS; } -static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req) +static uint16_t nvme_aer(NvmeCtrl *n, NvmeRequest *req) +{ + trace_pci_nvme_aer(nvme_cid(req)); + + if (n->outstanding_aers > n->params.aerl) { + trace_pci_nvme_aer_aerl_exceeded(); + return NVME_AER_LIMIT_EXCEEDED; + } + + n->aer_reqs[n->outstanding_aers] = req; + n->outstanding_aers++; + + if (!QTAILQ_EMPTY(&n->aer_queue)) { + nvme_process_aers(n); + } + + return NVME_NO_COMPLETE; +} + +static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeRequest *req) { - switch (cmd->opcode) { + trace_pci_nvme_admin_cmd(nvme_cid(req), nvme_sqid(req), req->cmd.opcode); + + switch (req->cmd.opcode) { case NVME_ADM_CMD_DELETE_SQ: - return nvme_del_sq(n, cmd); + return nvme_del_sq(n, req); case NVME_ADM_CMD_CREATE_SQ: - return nvme_create_sq(n, cmd); + return nvme_create_sq(n, req); + case NVME_ADM_CMD_GET_LOG_PAGE: + return nvme_get_log(n, req); case NVME_ADM_CMD_DELETE_CQ: - return nvme_del_cq(n, cmd); + return nvme_del_cq(n, req); case NVME_ADM_CMD_CREATE_CQ: - return nvme_create_cq(n, cmd); + return nvme_create_cq(n, req); case NVME_ADM_CMD_IDENTIFY: - return nvme_identify(n, cmd); + return nvme_identify(n, req); + case NVME_ADM_CMD_ABORT: + return nvme_abort(n, req); case NVME_ADM_CMD_SET_FEATURES: - return nvme_set_feature(n, cmd, req); + return nvme_set_feature(n, req); case NVME_ADM_CMD_GET_FEATURES: - return nvme_get_feature(n, cmd, req); + return nvme_get_feature(n, req); + case NVME_ADM_CMD_ASYNC_EV_REQ: + return nvme_aer(n, req); default: - trace_pci_nvme_err_invalid_admin_opc(cmd->opcode); + trace_pci_nvme_err_invalid_admin_opc(req->cmd.opcode); return NVME_INVALID_OPCODE | NVME_DNR; } } @@ -916,11 +1617,12 @@ static void nvme_process_sq(void *opaque) req = QTAILQ_FIRST(&sq->req_list); QTAILQ_REMOVE(&sq->req_list, req, entry); QTAILQ_INSERT_TAIL(&sq->out_req_list, req, entry); - memset(&req->cqe, 0, sizeof(req->cqe)); + nvme_req_clear(req); req->cqe.cid = cmd.cid; + memcpy(&req->cmd, &cmd, sizeof(NvmeCmd)); - status = sq->sqid ? nvme_io_cmd(n, &cmd, req) : - nvme_admin_cmd(n, &cmd, req); + status = sq->sqid ? nvme_io_cmd(n, req) : + nvme_admin_cmd(n, req); if (status != NVME_NO_COMPLETE) { req->status = status; nvme_enqueue_req_completion(cq, req); @@ -945,6 +1647,16 @@ static void nvme_clear_ctrl(NvmeCtrl *n) } } + while (!QTAILQ_EMPTY(&n->aer_queue)) { + NvmeAsyncEvent *event = QTAILQ_FIRST(&n->aer_queue); + QTAILQ_REMOVE(&n->aer_queue, event, entry); + g_free(event); + } + + n->aer_queued = 0; + n->outstanding_aers = 0; + n->qs_created = false; + blk_flush(n->conf.blk); n->bar.cc = 0; } @@ -1041,6 +1753,8 @@ static int nvme_start_ctrl(NvmeCtrl *n) nvme_set_timestamp(n, 0ULL); + QTAILQ_INIT(&n->aer_queue); + return 0; } @@ -1204,6 +1918,8 @@ static uint64_t nvme_mmio_read(void *opaque, hwaddr addr, unsigned size) uint8_t *ptr = (uint8_t *)&n->bar; uint64_t val = 0; + trace_pci_nvme_mmio_read(addr); + if (unlikely(addr & (sizeof(uint32_t) - 1))) { NVME_GUEST_ERR(pci_nvme_ub_mmiord_misaligned32, "MMIO read not 32-bit aligned," @@ -1260,6 +1976,26 @@ static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val) "completion queue doorbell write" " for nonexistent queue," " sqid=%"PRIu32", ignoring", qid); + + /* + * NVM Express v1.3d, Section 4.1 state: "If host software writes + * an invalid value to the Submission Queue Tail Doorbell or + * Completion Queue Head Doorbell regiter and an Asynchronous Event + * Request command is outstanding, then an asynchronous event is + * posted to the Admin Completion Queue with a status code of + * Invalid Doorbell Write Value." + * + * Also note that the spec includes the "Invalid Doorbell Register" + * status code, but nowhere does it specify when to use it. + * However, it seems reasonable to use it here in a similar + * fashion. + */ + if (n->outstanding_aers) { + nvme_enqueue_event(n, NVME_AER_TYPE_ERROR, + NVME_AER_INFO_ERR_INVALID_DB_REGISTER, + NVME_LOG_ERROR_INFO); + } + return; } @@ -1270,9 +2006,18 @@ static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val) " beyond queue size, sqid=%"PRIu32"," " new_head=%"PRIu16", ignoring", qid, new_head); + + if (n->outstanding_aers) { + nvme_enqueue_event(n, NVME_AER_TYPE_ERROR, + NVME_AER_INFO_ERR_INVALID_DB_VALUE, + NVME_LOG_ERROR_INFO); + } + return; } + trace_pci_nvme_mmio_doorbell_cq(cq->cqid, new_head); + start_sqs = nvme_cq_full(cq) ? 1 : 0; cq->head = new_head; if (start_sqs) { @@ -1298,6 +2043,13 @@ static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val) "submission queue doorbell write" " for nonexistent queue," " sqid=%"PRIu32", ignoring", qid); + + if (n->outstanding_aers) { + nvme_enqueue_event(n, NVME_AER_TYPE_ERROR, + NVME_AER_INFO_ERR_INVALID_DB_REGISTER, + NVME_LOG_ERROR_INFO); + } + return; } @@ -1308,9 +2060,18 @@ static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val) " beyond queue size, sqid=%"PRIu32"," " new_tail=%"PRIu16", ignoring", qid, new_tail); + + if (n->outstanding_aers) { + nvme_enqueue_event(n, NVME_AER_TYPE_ERROR, + NVME_AER_INFO_ERR_INVALID_DB_VALUE, + NVME_LOG_ERROR_INFO); + } + return; } + trace_pci_nvme_mmio_doorbell_sq(sq->sqid, new_tail); + sq->tail = new_tail; timer_mod(sq->timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + 500); } @@ -1320,9 +2081,12 @@ static void nvme_mmio_write(void *opaque, hwaddr addr, uint64_t data, unsigned size) { NvmeCtrl *n = (NvmeCtrl *)opaque; + + trace_pci_nvme_mmio_write(addr, data); + if (addr < sizeof(n->bar)) { nvme_write_bar(n, addr, data, size); - } else if (addr >= 0x1000) { + } else { nvme_process_db(n, addr, data); } } @@ -1415,11 +2179,15 @@ static void nvme_init_state(NvmeCtrl *n) { n->num_namespaces = 1; /* add one to max_ioqpairs to account for the admin queue pair */ - n->reg_size = pow2ceil(NVME_REG_SIZE + + 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; + n->features.temp_thresh_hi = NVME_TEMPERATURE_WARNING; + n->starttime_ms = qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL); + n->aer_reqs = g_new0(NvmeRequest *, n->params.aerl + 1); } static void nvme_init_blk(NvmeCtrl *n, Error **errp) @@ -1459,7 +2227,7 @@ static void nvme_init_cmb(NvmeCtrl *n, PCIDevice *pci_dev) NVME_CMBSZ_SET_SQS(n->bar.cmbsz, 1); NVME_CMBSZ_SET_CQS(n->bar.cmbsz, 0); - NVME_CMBSZ_SET_LISTS(n->bar.cmbsz, 0); + NVME_CMBSZ_SET_LISTS(n->bar.cmbsz, 1); NVME_CMBSZ_SET_RDS(n->bar.cmbsz, 1); NVME_CMBSZ_SET_WDS(n->bar.cmbsz, 1); NVME_CMBSZ_SET_SZU(n->bar.cmbsz, 2); /* MBs */ @@ -1551,6 +2319,7 @@ static void nvme_init_ctrl(NvmeCtrl *n, PCIDevice *pci_dev) { NvmeIdCtrl *id = &n->id_ctrl; uint8_t *pci_conf = pci_dev->config; + char *subnqn; id->vid = cpu_to_le16(pci_get_word(pci_conf + PCI_VENDOR_ID)); id->ssvid = cpu_to_le16(pci_get_word(pci_conf + PCI_SUBSYSTEM_VENDOR_ID)); @@ -1561,13 +2330,40 @@ static void nvme_init_ctrl(NvmeCtrl *n, PCIDevice *pci_dev) id->ieee[0] = 0x00; id->ieee[1] = 0x02; id->ieee[2] = 0xb3; + id->mdts = n->params.mdts; + id->ver = cpu_to_le32(NVME_SPEC_VER); id->oacs = cpu_to_le16(0); - id->frmw = 7 << 1; - id->lpa = 1 << 0; + + /* + * Because the controller always completes the Abort command immediately, + * there can never be more than one concurrently executing Abort command, + * so this value is never used for anything. Note that there can easily be + * many Abort commands in the queues, but they are not considered + * "executing" until processed by nvme_abort. + * + * The specification recommends a value of 3 for Abort Command Limit (four + * concurrently outstanding Abort commands), so lets use that though it is + * inconsequential. + */ + id->acl = 3; + id->aerl = n->params.aerl; + id->frmw = (NVME_NUM_FW_SLOTS << 1) | NVME_FRMW_SLOT1_RO; + id->lpa = NVME_LPA_EXTENDED; + + /* recommended default value (~70 C) */ + id->wctemp = cpu_to_le16(NVME_TEMPERATURE_WARNING); + id->cctemp = cpu_to_le16(NVME_TEMPERATURE_CRITICAL); + id->sqes = (0x6 << 4) | 0x6; id->cqes = (0x4 << 4) | 0x4; id->nn = cpu_to_le32(n->num_namespaces); - id->oncs = cpu_to_le16(NVME_ONCS_WRITE_ZEROS | NVME_ONCS_TIMESTAMP); + id->oncs = cpu_to_le16(NVME_ONCS_WRITE_ZEROES | NVME_ONCS_TIMESTAMP | + NVME_ONCS_FEATURES); + + 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); + id->psd[0].mp = cpu_to_le16(0x9c4); id->psd[0].enlat = cpu_to_le32(0x10); id->psd[0].exlat = cpu_to_le32(0x4); @@ -1582,7 +2378,7 @@ static void nvme_init_ctrl(NvmeCtrl *n, PCIDevice *pci_dev) NVME_CAP_SET_CSS(n->bar.cap, 1); NVME_CAP_SET_MPSMAX(n->bar.cap, 4); - n->bar.vs = 0x00010200; + n->bar.vs = NVME_SPEC_VER; n->bar.intmc = n->bar.intms = 0; } @@ -1631,6 +2427,7 @@ static void nvme_exit(PCIDevice *pci_dev) g_free(n->namespaces); g_free(n->cq); g_free(n->sq); + g_free(n->aer_reqs); if (n->params.cmb_size_mb) { g_free(n->cmbuf); @@ -1651,6 +2448,9 @@ static Property nvme_props[] = { DEFINE_PROP_UINT32("num_queues", NvmeCtrl, params.num_queues, 0), DEFINE_PROP_UINT32("max_ioqpairs", NvmeCtrl, params.max_ioqpairs, 64), DEFINE_PROP_UINT16("msix_qsize", NvmeCtrl, params.msix_qsize, 65), + 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_END_OF_LIST(), }; diff --git a/hw/block/nvme.h b/hw/block/nvme.h index 1d30c0bca2..52ba794f2e 100644 --- a/hw/block/nvme.h +++ b/hw/block/nvme.h @@ -9,19 +9,23 @@ typedef struct NvmeParams { uint32_t max_ioqpairs; uint16_t msix_qsize; uint32_t cmb_size_mb; + uint8_t aerl; + uint32_t aer_max_queued; + uint8_t mdts; } NvmeParams; typedef struct NvmeAsyncEvent { - QSIMPLEQ_ENTRY(NvmeAsyncEvent) entry; + QTAILQ_ENTRY(NvmeAsyncEvent) entry; NvmeAerResult result; } NvmeAsyncEvent; typedef struct NvmeRequest { struct NvmeSQueue *sq; + struct NvmeNamespace *ns; BlockAIOCB *aiocb; uint16_t status; - bool has_sg; NvmeCqe cqe; + NvmeCmd cmd; BlockAcctCookie acct; QEMUSGList qsg; QEMUIOVector iov; @@ -77,6 +81,14 @@ static inline uint8_t nvme_ns_lbads(NvmeNamespace *ns) #define NVME(obj) \ OBJECT_CHECK(NvmeCtrl, (obj), TYPE_NVME) +typedef struct NvmeFeatureVal { + struct { + uint16_t temp_thresh_hi; + uint16_t temp_thresh_low; + }; + uint32_t async_config; +} NvmeFeatureVal; + typedef struct NvmeCtrl { PCIDevice parent_obj; MemoryRegion iomem; @@ -85,6 +97,7 @@ typedef struct NvmeCtrl { BlockConf conf; NvmeParams params; + bool qs_created; uint32_t page_size; uint16_t page_bits; uint16_t max_prp_ents; @@ -94,19 +107,28 @@ typedef struct NvmeCtrl { uint32_t num_namespaces; uint32_t max_q_ents; uint64_t ns_size; + uint8_t outstanding_aers; uint8_t *cmbuf; uint32_t irq_status; uint64_t host_timestamp; /* Timestamp sent by the host */ uint64_t timestamp_set_qemu_clock_ms; /* QEMU clock time */ + uint64_t starttime_ms; + uint16_t temperature; HostMemoryBackend *pmrdev; + uint8_t aer_mask; + NvmeRequest **aer_reqs; + QTAILQ_HEAD(, NvmeAsyncEvent) aer_queue; + int aer_queued; + NvmeNamespace *namespaces; NvmeSQueue **sq; NvmeCQueue **cq; NvmeSQueue admin_sq; NvmeCQueue admin_cq; NvmeIdCtrl id_ctrl; + NvmeFeatureVal features; } NvmeCtrl; /* calculate the number of LBAs that the namespace can accomodate */ diff --git a/hw/block/trace-events b/hw/block/trace-events index 958fcc5508..72cf2d15cb 100644 --- a/hw/block/trace-events +++ b/hw/block/trace-events @@ -33,19 +33,44 @@ 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" pci_nvme_dma_read(uint64_t prp1, uint64_t prp2) "DMA read, prp1=0x%"PRIx64" prp2=0x%"PRIx64"" +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_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"" pci_nvme_del_cq(uint16_t cqid) "deleted completion queue, cqid=%"PRIu16"" pci_nvme_identify_ctrl(void) "identify controller" -pci_nvme_identify_ns(uint16_t ns) "identify namespace, nsid=%"PRIu16"" -pci_nvme_identify_nslist(uint16_t ns) "identify namespace list, nsid=%"PRIu16"" +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_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" pci_nvme_setfeat_timestamp(uint64_t ts) "set feature timestamp = 0x%"PRIx64"" pci_nvme_getfeat_timestamp(uint64_t ts) "get feature timestamp = 0x%"PRIx64"" +pci_nvme_process_aers(int queued) "queued %d" +pci_nvme_aer(uint16_t cid) "cid %"PRIu16"" +pci_nvme_aer_aerl_exceeded(void) "aerl exceeded" +pci_nvme_aer_masked(uint8_t type, uint8_t mask) "type 0x%"PRIx8" mask 0x%"PRIx8"" +pci_nvme_aer_post_cqe(uint8_t typ, uint8_t info, uint8_t log_page) "type 0x%"PRIx8" info 0x%"PRIx8" lid 0x%"PRIx8"" +pci_nvme_enqueue_event(uint8_t typ, uint8_t info, uint8_t log_page) "type 0x%"PRIx8" info 0x%"PRIx8" lid 0x%"PRIx8"" +pci_nvme_enqueue_event_noqueue(int queued) "queued %d" +pci_nvme_enqueue_event_masked(uint8_t typ) "type 0x%"PRIx8"" +pci_nvme_no_outstanding_aers(void) "ignoring event; no outstanding AERs" +pci_nvme_enqueue_req_completion(uint16_t cid, uint16_t cqid, uint16_t status) "cid %"PRIu16" cqid %"PRIu16" status 0x%"PRIx16"" +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_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"" @@ -60,6 +85,7 @@ pci_nvme_mmio_shutdown_set(void) "shutdown bit set" 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_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_prp2_align(uint64_t prp2) "PRP2 is not page aligned: 0x%"PRIx64"" @@ -85,6 +111,7 @@ pci_nvme_err_invalid_create_cq_qflags(uint16_t qflags) "failed creating completi pci_nvme_err_invalid_identify_cns(uint16_t cns) "identify, invalid cns=0x%"PRIx16"" pci_nvme_err_invalid_getfeat(int dw10) "invalid get features, dw10=0x%"PRIx32"" pci_nvme_err_invalid_setfeat(uint32_t dw10) "invalid set features, dw10=0x%"PRIx32"" +pci_nvme_err_invalid_log_page(uint16_t cid, uint16_t lid) "cid %"PRIu16" lid 0x%"PRIx16"" pci_nvme_err_startfail_cq(void) "nvme_start_ctrl failed because there are non-admin completion queues" pci_nvme_err_startfail_sq(void) "nvme_start_ctrl failed because there are non-admin submission queues" pci_nvme_err_startfail_nbarasq(void) "nvme_start_ctrl failed because the admin submission queue address is null" diff --git a/include/block/nvme.h b/include/block/nvme.h index 1720ee1d51..65e68a82c8 100644 --- a/include/block/nvme.h +++ b/include/block/nvme.h @@ -1,7 +1,7 @@ #ifndef BLOCK_NVME_H #define BLOCK_NVME_H -typedef struct NvmeBar { +typedef struct QEMU_PACKED NvmeBar { uint64_t cap; uint32_t vs; uint32_t intms; @@ -21,7 +21,8 @@ typedef struct NvmeBar { uint32_t pmrsts; uint32_t pmrebs; uint32_t pmrswtp; - uint32_t pmrmsc; + uint64_t pmrmsc; + uint8_t reserved[484]; } NvmeBar; enum NvmeCapShift { @@ -377,15 +378,53 @@ enum NvmePmrmscMask { #define NVME_PMRMSC_SET_CBA(pmrmsc, val) \ (pmrmsc |= (uint64_t)(val & PMRMSC_CBA_MASK) << PMRMSC_CBA_SHIFT) -typedef struct NvmeCmd { +enum NvmeSglDescriptorType { + NVME_SGL_DESCR_TYPE_DATA_BLOCK = 0x0, + NVME_SGL_DESCR_TYPE_BIT_BUCKET = 0x1, + NVME_SGL_DESCR_TYPE_SEGMENT = 0x2, + NVME_SGL_DESCR_TYPE_LAST_SEGMENT = 0x3, + NVME_SGL_DESCR_TYPE_KEYED_DATA_BLOCK = 0x4, + + NVME_SGL_DESCR_TYPE_VENDOR_SPECIFIC = 0xf, +}; + +enum NvmeSglDescriptorSubtype { + NVME_SGL_DESCR_SUBTYPE_ADDRESS = 0x0, +}; + +typedef struct QEMU_PACKED NvmeSglDescriptor { + uint64_t addr; + uint32_t len; + uint8_t rsvd[3]; + uint8_t type; +} NvmeSglDescriptor; + +#define NVME_SGL_TYPE(type) ((type >> 4) & 0xf) +#define NVME_SGL_SUBTYPE(type) (type & 0xf) + +typedef union NvmeCmdDptr { + struct { + uint64_t prp1; + uint64_t prp2; + }; + + NvmeSglDescriptor sgl; +} NvmeCmdDptr; + +enum NvmePsdt { + PSDT_PRP = 0x0, + PSDT_SGL_MPTR_CONTIGUOUS = 0x1, + PSDT_SGL_MPTR_SGL = 0x2, +}; + +typedef struct QEMU_PACKED NvmeCmd { uint8_t opcode; - uint8_t fuse; + uint8_t flags; uint16_t cid; uint32_t nsid; uint64_t res1; uint64_t mptr; - uint64_t prp1; - uint64_t prp2; + NvmeCmdDptr dptr; uint32_t cdw10; uint32_t cdw11; uint32_t cdw12; @@ -394,6 +433,9 @@ typedef struct NvmeCmd { uint32_t cdw15; } NvmeCmd; +#define NVME_CMD_FLAGS_FUSE(flags) (flags & 0x3) +#define NVME_CMD_FLAGS_PSDT(flags) ((flags >> 6) & 0x3) + enum NvmeAdminCommands { NVME_ADM_CMD_DELETE_SQ = 0x00, NVME_ADM_CMD_CREATE_SQ = 0x01, @@ -418,11 +460,11 @@ enum NvmeIoCommands { NVME_CMD_READ = 0x02, NVME_CMD_WRITE_UNCOR = 0x04, NVME_CMD_COMPARE = 0x05, - NVME_CMD_WRITE_ZEROS = 0x08, + NVME_CMD_WRITE_ZEROES = 0x08, NVME_CMD_DSM = 0x09, }; -typedef struct NvmeDeleteQ { +typedef struct QEMU_PACKED NvmeDeleteQ { uint8_t opcode; uint8_t flags; uint16_t cid; @@ -432,7 +474,7 @@ typedef struct NvmeDeleteQ { uint32_t rsvd11[5]; } NvmeDeleteQ; -typedef struct NvmeCreateCq { +typedef struct QEMU_PACKED NvmeCreateCq { uint8_t opcode; uint8_t flags; uint16_t cid; @@ -449,7 +491,7 @@ typedef struct NvmeCreateCq { #define NVME_CQ_FLAGS_PC(cq_flags) (cq_flags & 0x1) #define NVME_CQ_FLAGS_IEN(cq_flags) ((cq_flags >> 1) & 0x1) -typedef struct NvmeCreateSq { +typedef struct QEMU_PACKED NvmeCreateSq { uint8_t opcode; uint8_t flags; uint16_t cid; @@ -474,7 +516,7 @@ enum NvmeQueueFlags { NVME_Q_PRIO_LOW = 3, }; -typedef struct NvmeIdentify { +typedef struct QEMU_PACKED NvmeIdentify { uint8_t opcode; uint8_t flags; uint16_t cid; @@ -486,15 +528,14 @@ typedef struct NvmeIdentify { uint32_t rsvd11[5]; } NvmeIdentify; -typedef struct NvmeRwCmd { +typedef struct QEMU_PACKED NvmeRwCmd { uint8_t opcode; uint8_t flags; uint16_t cid; uint32_t nsid; uint64_t rsvd2; uint64_t mptr; - uint64_t prp1; - uint64_t prp2; + NvmeCmdDptr dptr; uint64_t slba; uint16_t nlb; uint16_t control; @@ -528,14 +569,13 @@ enum { NVME_RW_PRINFO_PRCHK_REF = 1 << 10, }; -typedef struct NvmeDsmCmd { +typedef struct QEMU_PACKED NvmeDsmCmd { uint8_t opcode; uint8_t flags; uint16_t cid; uint32_t nsid; uint64_t rsvd2[2]; - uint64_t prp1; - uint64_t prp2; + NvmeCmdDptr dptr; uint32_t nr; uint32_t attributes; uint32_t rsvd12[4]; @@ -547,7 +587,7 @@ enum { NVME_DSMGMT_AD = 1 << 2, }; -typedef struct NvmeDsmRange { +typedef struct QEMU_PACKED NvmeDsmRange { uint32_t cattr; uint32_t nlb; uint64_t slba; @@ -558,8 +598,8 @@ enum NvmeAsyncEventRequest { NVME_AER_TYPE_SMART = 1, NVME_AER_TYPE_IO_SPECIFIC = 6, NVME_AER_TYPE_VENDOR_SPECIFIC = 7, - NVME_AER_INFO_ERR_INVALID_SQ = 0, - NVME_AER_INFO_ERR_INVALID_DB = 1, + NVME_AER_INFO_ERR_INVALID_DB_REGISTER = 0, + NVME_AER_INFO_ERR_INVALID_DB_VALUE = 1, NVME_AER_INFO_ERR_DIAG_FAIL = 2, NVME_AER_INFO_ERR_PERS_INTERNAL_ERR = 3, NVME_AER_INFO_ERR_TRANS_INTERNAL_ERR = 4, @@ -569,14 +609,14 @@ enum NvmeAsyncEventRequest { NVME_AER_INFO_SMART_SPARE_THRESH = 2, }; -typedef struct NvmeAerResult { +typedef struct QEMU_PACKED NvmeAerResult { uint8_t event_type; uint8_t event_info; uint8_t log_page; uint8_t resv; } NvmeAerResult; -typedef struct NvmeCqe { +typedef struct QEMU_PACKED NvmeCqe { uint32_t result; uint32_t rsvd; uint16_t sq_head; @@ -599,6 +639,12 @@ enum NvmeStatusCodes { NVME_CMD_ABORT_MISSING_FUSE = 0x000a, NVME_INVALID_NSID = 0x000b, NVME_CMD_SEQ_ERROR = 0x000c, + NVME_INVALID_SGL_SEG_DESCR = 0x000d, + NVME_INVALID_NUM_SGL_DESCRS = 0x000e, + NVME_DATA_SGL_LEN_INVALID = 0x000f, + NVME_MD_SGL_LEN_INVALID = 0x0010, + NVME_SGL_DESCR_TYPE_INVALID = 0x0011, + NVME_INVALID_USE_OF_CMB = 0x0012, NVME_LBA_RANGE = 0x0080, NVME_CAP_EXCEEDED = 0x0081, NVME_NS_NOT_READY = 0x0082, @@ -617,7 +663,8 @@ enum NvmeStatusCodes { NVME_FW_REQ_RESET = 0x010b, NVME_INVALID_QUEUE_DEL = 0x010c, NVME_FID_NOT_SAVEABLE = 0x010d, - NVME_FID_NOT_NSID_SPEC = 0x010f, + NVME_FEAT_NOT_CHANGEABLE = 0x010e, + NVME_FEAT_NOT_NS_SPEC = 0x010f, NVME_FW_REQ_SUSYSTEM_RESET = 0x0110, NVME_CONFLICTING_ATTRS = 0x0180, NVME_INVALID_PROT_INFO = 0x0181, @@ -634,7 +681,7 @@ enum NvmeStatusCodes { NVME_NO_COMPLETE = 0xffff, }; -typedef struct NvmeFwSlotInfoLog { +typedef struct QEMU_PACKED NvmeFwSlotInfoLog { uint8_t afi; uint8_t reserved1[7]; uint8_t frs1[8]; @@ -647,7 +694,7 @@ typedef struct NvmeFwSlotInfoLog { uint8_t reserved2[448]; } NvmeFwSlotInfoLog; -typedef struct NvmeErrorLog { +typedef struct QEMU_PACKED NvmeErrorLog { uint64_t error_count; uint16_t sqid; uint16_t cid; @@ -659,9 +706,9 @@ typedef struct NvmeErrorLog { uint8_t resv[35]; } NvmeErrorLog; -typedef struct NvmeSmartLog { +typedef struct QEMU_PACKED NvmeSmartLog { uint8_t critical_warning; - uint8_t temperature[2]; + uint16_t temperature; uint8_t available_spare; uint8_t available_spare_threshold; uint8_t percentage_used; @@ -687,13 +734,13 @@ enum NvmeSmartWarn { NVME_SMART_FAILED_VOLATILE_MEDIA = 1 << 4, }; -enum LogIdentifier { +enum NvmeLogIdentifier { NVME_LOG_ERROR_INFO = 0x01, NVME_LOG_SMART_INFO = 0x02, NVME_LOG_FW_SLOT_INFO = 0x03, }; -typedef struct NvmePSD { +typedef struct QEMU_PACKED NvmePSD { uint16_t mp; uint16_t reserved; uint32_t enlat; @@ -711,9 +758,10 @@ enum { NVME_ID_CNS_NS = 0x0, NVME_ID_CNS_CTRL = 0x1, NVME_ID_CNS_NS_ACTIVE_LIST = 0x2, + NVME_ID_CNS_NS_DESCR_LIST = 0x3, }; -typedef struct NvmeIdCtrl { +typedef struct QEMU_PACKED NvmeIdCtrl { uint16_t vid; uint16_t ssvid; uint8_t sn[20]; @@ -723,7 +771,15 @@ typedef struct NvmeIdCtrl { uint8_t ieee[3]; uint8_t cmic; uint8_t mdts; - uint8_t rsvd255[178]; + uint16_t cntlid; + uint32_t ver; + uint32_t rtd3r; + uint32_t rtd3e; + uint32_t oaes; + uint32_t ctratt; + uint8_t rsvd100[12]; + uint8_t fguid[16]; + uint8_t rsvd128[128]; uint16_t oacs; uint8_t acl; uint8_t aerl; @@ -731,10 +787,28 @@ typedef struct NvmeIdCtrl { uint8_t lpa; uint8_t elpe; uint8_t npss; - uint8_t rsvd511[248]; + uint8_t avscc; + uint8_t apsta; + uint16_t wctemp; + uint16_t cctemp; + uint16_t mtfa; + uint32_t hmpre; + uint32_t hmmin; + uint8_t tnvmcap[16]; + uint8_t unvmcap[16]; + uint32_t rpmbs; + uint16_t edstt; + uint8_t dsto; + uint8_t fwug; + uint16_t kas; + uint16_t hctma; + uint16_t mntmt; + uint16_t mxtmt; + uint32_t sanicap; + uint8_t rsvd332[180]; uint8_t sqes; uint8_t cqes; - uint16_t rsvd515; + uint16_t maxcmd; uint32_t nn; uint16_t oncs; uint16_t fuses; @@ -742,8 +816,14 @@ typedef struct NvmeIdCtrl { uint8_t vwc; uint16_t awun; uint16_t awupf; - uint8_t rsvd703[174]; - uint8_t rsvd2047[1344]; + uint8_t nvscc; + uint8_t rsvd531; + uint16_t acwu; + uint8_t rsvd534[2]; + uint32_t sgls; + uint8_t rsvd540[228]; + uint8_t subnqn[256]; + uint8_t rsvd1024[1024]; NvmePSD psd[32]; uint8_t vs[1024]; } NvmeIdCtrl; @@ -758,32 +838,37 @@ enum NvmeIdCtrlOncs { NVME_ONCS_COMPARE = 1 << 0, NVME_ONCS_WRITE_UNCORR = 1 << 1, NVME_ONCS_DSM = 1 << 2, - NVME_ONCS_WRITE_ZEROS = 1 << 3, + NVME_ONCS_WRITE_ZEROES = 1 << 3, NVME_ONCS_FEATURES = 1 << 4, NVME_ONCS_RESRVATIONS = 1 << 5, NVME_ONCS_TIMESTAMP = 1 << 6, }; +enum NvmeIdCtrlFrmw { + NVME_FRMW_SLOT1_RO = 1 << 0, +}; + +enum NvmeIdCtrlLpa { + NVME_LPA_EXTENDED = 1 << 2, +}; + #define NVME_CTRL_SQES_MIN(sqes) ((sqes) & 0xf) #define NVME_CTRL_SQES_MAX(sqes) (((sqes) >> 4) & 0xf) #define NVME_CTRL_CQES_MIN(cqes) ((cqes) & 0xf) #define NVME_CTRL_CQES_MAX(cqes) (((cqes) >> 4) & 0xf) -typedef struct NvmeFeatureVal { - uint32_t arbitration; - uint32_t power_mgmt; - uint32_t temp_thresh; - uint32_t err_rec; - uint32_t volatile_wc; - uint32_t num_queues; - uint32_t int_coalescing; - uint32_t *int_vector_config; - uint32_t write_atomicity; - uint32_t async_config; - uint32_t sw_prog_marker; -} NvmeFeatureVal; +#define NVME_CTRL_SGLS_SUPPORT_MASK (0x3 << 0) +#define NVME_CTRL_SGLS_SUPPORT_NO_ALIGN (0x1 << 0) +#define NVME_CTRL_SGLS_SUPPORT_DWORD_ALIGN (0x1 << 1) +#define NVME_CTRL_SGLS_KEYED (0x1 << 2) +#define NVME_CTRL_SGLS_BITBUCKET (0x1 << 16) +#define NVME_CTRL_SGLS_MPTR_CONTIGUOUS (0x1 << 17) +#define NVME_CTRL_SGLS_EXCESS_LENGTH (0x1 << 18) +#define NVME_CTRL_SGLS_MPTR_SGL (0x1 << 19) +#define NVME_CTRL_SGLS_ADDR_OFFSET (0x1 << 20) #define NVME_ARB_AB(arb) (arb & 0x7) +#define NVME_ARB_AB_NOLIMIT 0x7 #define NVME_ARB_LPW(arb) ((arb >> 8) & 0xff) #define NVME_ARB_MPW(arb) ((arb >> 16) & 0xff) #define NVME_ARB_HPW(arb) ((arb >> 24) & 0xff) @@ -791,6 +876,21 @@ typedef struct NvmeFeatureVal { #define NVME_INTC_THR(intc) (intc & 0xff) #define NVME_INTC_TIME(intc) ((intc >> 8) & 0xff) +#define NVME_INTVC_NOCOALESCING (0x1 << 16) + +#define NVME_TEMP_THSEL(temp) ((temp >> 20) & 0x3) +#define NVME_TEMP_THSEL_OVER 0x0 +#define NVME_TEMP_THSEL_UNDER 0x1 + +#define NVME_TEMP_TMPSEL(temp) ((temp >> 16) & 0xf) +#define NVME_TEMP_TMPSEL_COMPOSITE 0x0 + +#define NVME_TEMP_TMPTH(temp) (temp & 0xffff) + +#define NVME_AEC_SMART(aec) (aec & 0xff) +#define NVME_AEC_NS_ATTR(aec) ((aec >> 8) & 0x1) +#define NVME_AEC_FW_ACTIVATION(aec) ((aec >> 9) & 0x1) + enum NvmeFeatureIds { NVME_ARBITRATION = 0x1, NVME_POWER_MANAGEMENT = 0x2, @@ -804,10 +904,37 @@ enum NvmeFeatureIds { NVME_WRITE_ATOMICITY = 0xa, NVME_ASYNCHRONOUS_EVENT_CONF = 0xb, NVME_TIMESTAMP = 0xe, - NVME_SOFTWARE_PROGRESS_MARKER = 0x80 + NVME_SOFTWARE_PROGRESS_MARKER = 0x80, + NVME_FID_MAX = 0x100, }; -typedef struct NvmeRangeType { +typedef enum NvmeFeatureCap { + NVME_FEAT_CAP_SAVE = 1 << 0, + NVME_FEAT_CAP_NS = 1 << 1, + NVME_FEAT_CAP_CHANGE = 1 << 2, +} NvmeFeatureCap; + +typedef enum NvmeGetFeatureSelect { + NVME_GETFEAT_SELECT_CURRENT = 0x0, + NVME_GETFEAT_SELECT_DEFAULT = 0x1, + NVME_GETFEAT_SELECT_SAVED = 0x2, + NVME_GETFEAT_SELECT_CAP = 0x3, +} NvmeGetFeatureSelect; + +#define NVME_GETSETFEAT_FID_MASK 0xff +#define NVME_GETSETFEAT_FID(dw10) (dw10 & NVME_GETSETFEAT_FID_MASK) + +#define NVME_GETFEAT_SELECT_SHIFT 8 +#define NVME_GETFEAT_SELECT_MASK 0x7 +#define NVME_GETFEAT_SELECT(dw10) \ + ((dw10 >> NVME_GETFEAT_SELECT_SHIFT) & NVME_GETFEAT_SELECT_MASK) + +#define NVME_SETFEAT_SAVE_SHIFT 31 +#define NVME_SETFEAT_SAVE_MASK 0x1 +#define NVME_SETFEAT_SAVE(dw10) \ + ((dw10 >> NVME_SETFEAT_SAVE_SHIFT) & NVME_SETFEAT_SAVE_MASK) + +typedef struct QEMU_PACKED NvmeRangeType { uint8_t type; uint8_t attributes; uint8_t rsvd2[14]; @@ -817,13 +944,15 @@ typedef struct NvmeRangeType { uint8_t rsvd48[16]; } NvmeRangeType; -typedef struct NvmeLBAF { +typedef struct QEMU_PACKED NvmeLBAF { uint16_t ms; uint8_t ds; uint8_t rp; } NvmeLBAF; -typedef struct NvmeIdNs { +#define NVME_NSID_BROADCAST 0xffffffff + +typedef struct QEMU_PACKED NvmeIdNs { uint64_t nsze; uint64_t ncap; uint64_t nuse; @@ -833,18 +962,43 @@ typedef struct NvmeIdNs { uint8_t mc; uint8_t dpc; uint8_t dps; - uint8_t nmic; uint8_t rescap; uint8_t fpi; uint8_t dlfeat; - - uint8_t res34[94]; + uint16_t nawun; + uint16_t nawupf; + uint16_t nacwu; + uint16_t nabsn; + uint16_t nabo; + uint16_t nabspf; + uint16_t noiob; + uint8_t nvmcap[16]; + uint8_t rsvd64[40]; + uint8_t nguid[16]; + uint64_t eui64; NvmeLBAF lbaf[16]; - uint8_t res192[192]; + uint8_t rsvd192[192]; uint8_t vs[3712]; } NvmeIdNs; +typedef struct QEMU_PACKED NvmeIdNsDescr { + uint8_t nidt; + uint8_t nidl; + uint8_t rsvd2[2]; +} NvmeIdNsDescr; + +enum { + NVME_NIDT_EUI64_LEN = 8, + NVME_NIDT_NGUID_LEN = 16, + NVME_NIDT_UUID_LEN = 16, +}; + +enum NvmeNsIdentifierType { + NVME_NIDT_EUI64 = 0x1, + NVME_NIDT_NGUID = 0x2, + NVME_NIDT_UUID = 0x3, +}; /*Deallocate Logical Block Features*/ #define NVME_ID_NS_DLFEAT_GUARD_CRC(dlfeat) ((dlfeat) & 0x10) @@ -879,6 +1033,7 @@ enum NvmeIdNsDps { static inline void _nvme_check_size(void) { + QEMU_BUILD_BUG_ON(sizeof(NvmeBar) != 4096); QEMU_BUILD_BUG_ON(sizeof(NvmeAerResult) != 4); QEMU_BUILD_BUG_ON(sizeof(NvmeCqe) != 16); QEMU_BUILD_BUG_ON(sizeof(NvmeDsmRange) != 16); @@ -895,5 +1050,7 @@ static inline void _nvme_check_size(void) QEMU_BUILD_BUG_ON(sizeof(NvmeSmartLog) != 512); QEMU_BUILD_BUG_ON(sizeof(NvmeIdCtrl) != 4096); QEMU_BUILD_BUG_ON(sizeof(NvmeIdNs) != 4096); + QEMU_BUILD_BUG_ON(sizeof(NvmeSglDescriptor) != 16); + QEMU_BUILD_BUG_ON(sizeof(NvmeIdNsDescr) != 4); } #endif |