[qemu.git] / hw / block / nvme.c

/*
 * QEMU NVM Express Controller
 *
 * Copyright (c) 2012, Intel Corporation
 *
 * Written by Keith Busch <[email protected]>
 *
 * This code is licensed under the GNU GPL v2 or later.
 */

/**
 * Reference Specs: http://www.nvmexpress.org, 1.2, 1.1, 1.0e
 *
 *  https://nvmexpress.org/developers/nvme-specification/
 */

/**
 * Usage: add options:
 *      -drive file=<file>,if=none,id=<drive_id>
 *      -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]>
 *
 * 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.
 *
 * cmb_size_mb= and pmrdev= options are mutually exclusive due to limitation
 * in available BAR's. cmb_size_mb= will take precedence over pmrdev= when
 * both provided.
 * Enabling pmr emulation can be achieved by pointing to memory-backend-file.
 * For example:
 * -object memory-backend-file,id=<mem_id>,share=on,mem-path=<file_path>, \
 *  size=<size> .... -device nvme,...,pmrdev=<mem_id>
 */

#include "qemu/osdep.h"
#include "qemu/units.h"
#include "qemu/error-report.h"
#include "hw/block/block.h"
#include "hw/pci/msix.h"
#include "hw/pci/pci.h"
#include "hw/qdev-properties.h"
#include "migration/vmstate.h"
#include "sysemu/sysemu.h"
#include "qapi/error.h"
#include "qapi/visitor.h"
#include "sysemu/hostmem.h"
#include "sysemu/block-backend.h"
#include "exec/memory.h"
#include "qemu/log.h"
#include "qemu/module.h"
#include "qemu/cutils.h"
#include "trace.h"
#include "nvme.h"

#define NVME_MAX_IOQPAIRS 0xffff
#define NVME_DB_SIZE  4
#define NVME_CMB_BIR 2
#define NVME_PMR_BIR 2

#define NVME_GUEST_ERR(trace, fmt, ...) \
    do { \
        (trace_##trace)(__VA_ARGS__); \
        qemu_log_mask(LOG_GUEST_ERROR, #trace \
            " in %s: " fmt "\n", __func__, ## __VA_ARGS__); \
    } while (0)

static void nvme_process_sq(void *opaque);

static bool nvme_addr_is_cmb(NvmeCtrl *n, hwaddr addr)
{
    hwaddr low = n->ctrl_mem.addr;
    hwaddr hi  = n->ctrl_mem.addr + int128_get64(n->ctrl_mem.size);

    return addr >= low && addr < hi;
}

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);
        return;
    }

    pci_dma_read(&n->parent_obj, addr, buf, size);
}

static int nvme_check_sqid(NvmeCtrl *n, uint16_t sqid)
{
    return sqid < n->params.max_ioqpairs + 1 && n->sq[sqid] != NULL ? 0 : -1;
}

static int nvme_check_cqid(NvmeCtrl *n, uint16_t cqid)
{
    return cqid < n->params.max_ioqpairs + 1 && n->cq[cqid] != NULL ? 0 : -1;
}

static void nvme_inc_cq_tail(NvmeCQueue *cq)
{
    cq->tail++;
    if (cq->tail >= cq->size) {
        cq->tail = 0;
        cq->phase = !cq->phase;
    }
}

static void nvme_inc_sq_head(NvmeSQueue *sq)
{
    sq->head = (sq->head + 1) % sq->size;
}

static uint8_t nvme_cq_full(NvmeCQueue *cq)
{
    return (cq->tail + 1) % cq->size == cq->head;
}

static uint8_t nvme_sq_empty(NvmeSQueue *sq)
{
    return sq->head == sq->tail;
}

static void nvme_irq_check(NvmeCtrl *n)
{
    if (msix_enabled(&(n->parent_obj))) {
        return;
    }
    if (~n->bar.intms & n->irq_status) {
        pci_irq_assert(&n->parent_obj);
    } else {
        pci_irq_deassert(&n->parent_obj);
    }
}

static void nvme_irq_assert(NvmeCtrl *n, NvmeCQueue *cq)
{
    if (cq->irq_enabled) {
        if (msix_enabled(&(n->parent_obj))) {
            trace_pci_nvme_irq_msix(cq->vector);
            msix_notify(&(n->parent_obj), cq->vector);
        } else {
            trace_pci_nvme_irq_pin();
            assert(cq->vector < 32);
            n->irq_status |= 1 << cq->vector;
            nvme_irq_check(n);
        }
    } else {
        trace_pci_nvme_irq_masked();
    }
}

static void nvme_irq_deassert(NvmeCtrl *n, NvmeCQueue *cq)
{
    if (cq->irq_enabled) {
        if (msix_enabled(&(n->parent_obj))) {
            return;
        } else {
            assert(cq->vector < 32);
            n->irq_status &= ~(1 << cq->vector);
            nvme_irq_check(n);
        }
    }
}

static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1,
                             uint64_t prp2, uint32_t len, NvmeCtrl *n)
{
    hwaddr trans_len = n->page_size - (prp1 % n->page_size);
    trans_len = MIN(len, trans_len);
    int num_prps = (len >> n->page_bits) + 1;

    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;
        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);
    }
    len -= trans_len;
    if (len) {
        if (unlikely(!prp2)) {
            trace_pci_nvme_err_invalid_prp2_missing();
            goto unmap;
        }
        if (len > n->page_size) {
            uint64_t prp_list[n->max_prp_ents];
            uint32_t nents, prp_trans;
            int 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, prp2, (void *)prp_list, prp_trans);
            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))) {
                        trace_pci_nvme_err_invalid_prplist_ent(prp_ent);
                        goto unmap;
                    }

                    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);
                    prp_ent = le64_to_cpu(prp_list[i]);
                }

                if (unlikely(!prp_ent || prp_ent & (n->page_size - 1))) {
                    trace_pci_nvme_err_invalid_prplist_ent(prp_ent);
                    goto unmap;
                }

                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);
                }
                len -= trans_len;
                i++;
            }
        } else {
            if (unlikely(prp2 & (n->page_size - 1))) {
                trace_pci_nvme_err_invalid_prp2_align(prp2);
                goto unmap;
            }
            if (qsg->nsg) {
                qemu_sglist_add(qsg, prp2, len);
            } else {
                qemu_iovec_add(iov, (void *)&n->cmbuf[prp2 - n->ctrl_mem.addr], trans_len);
            }
        }
    }
    return NVME_SUCCESS;

 unmap:
    qemu_sglist_destroy(qsg);
    return NVME_INVALID_FIELD | NVME_DNR;
}

static uint16_t nvme_dma_write_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
                                   uint64_t prp1, uint64_t prp2)
{
    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);
    }
    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;

    trace_pci_nvme_dma_read(prp1, prp2);

    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))) {
            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)) {
            trace_pci_nvme_err_invalid_dma();
            status = NVME_INVALID_FIELD | NVME_DNR;
        }
        qemu_iovec_destroy(&iov);
    }
    return status;
}

static void nvme_post_cqes(void *opaque)
{
    NvmeCQueue *cq = opaque;
    NvmeCtrl *n = cq->ctrl;
    NvmeRequest *req, *next;

    QTAILQ_FOREACH_SAFE(req, &cq->req_list, entry, next) {
        NvmeSQueue *sq;
        hwaddr addr;

        if (nvme_cq_full(cq)) {
            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;
        nvme_inc_cq_tail(cq);
        pci_dma_write(&n->parent_obj, addr, (void *)&req->cqe,
            sizeof(req->cqe));
        QTAILQ_INSERT_TAIL(&sq->req_list, req, entry);
    }
    if (cq->tail != cq->head) {
        nvme_irq_assert(n, cq);
    }
}

static void nvme_enqueue_req_completion(NvmeCQueue *cq, NvmeRequest *req)
{
    assert(cq->cqid == req->sq->cqid);
    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_rw_cb(void *opaque, int ret)
{
    NvmeRequest *req = opaque;
    NvmeSQueue *sq = req->sq;
    NvmeCtrl *n = sq->ctrl;
    NvmeCQueue *cq = n->cq[sq->cqid];

    if (!ret) {
        block_acct_done(blk_get_stats(n->conf.blk), &req->acct);
        req->status = NVME_SUCCESS;
    } else {
        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)
{
    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);

    return NVME_NO_COMPLETE;
}

static uint16_t nvme_write_zeros(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,
    NvmeRequest *req)
{
    NvmeRwCmd *rw = (NvmeRwCmd *)cmd;
    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;

    if (unlikely(slba + nlb > ns->id_ns.nsze)) {
        trace_pci_nvme_err_invalid_lba_range(slba, nlb, ns->id_ns.nsze);
        return NVME_LBA_RANGE | NVME_DNR;
    }

    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,
                                        BDRV_REQ_MAY_UNMAP, nvme_rw_cb, req);
    return NVME_NO_COMPLETE;
}

static uint16_t nvme_rw(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,
    NvmeRequest *req)
{
    NvmeRwCmd *rw = (NvmeRwCmd *)cmd;
    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;
    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;

    trace_pci_nvme_rw(is_write ? "write" : "read", nlb, data_size, slba);

    if (unlikely((slba + nlb) > ns->id_ns.nsze)) {
        block_acct_invalid(blk_get_stats(n->conf.blk), acct);
        trace_pci_nvme_err_invalid_lba_range(slba, nlb, ns->id_ns.nsze);
        return NVME_LBA_RANGE | NVME_DNR;
    }

    if (nvme_map_prp(&req->qsg, &req->iov, prp1, prp2, data_size, n)) {
        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;
        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;
        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);
    }

    return NVME_NO_COMPLETE;
}

static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
{
    NvmeNamespace *ns;
    uint32_t nsid = le32_to_cpu(cmd->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;
    }

    ns = &n->namespaces[nsid - 1];
    switch (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);
    case NVME_CMD_WRITE:
    case NVME_CMD_READ:
        return nvme_rw(n, ns, cmd, req);
    default:
        trace_pci_nvme_err_invalid_opc(cmd->opcode);
        return NVME_INVALID_OPCODE | NVME_DNR;
    }
}

static void nvme_free_sq(NvmeSQueue *sq, NvmeCtrl *n)
{
    n->sq[sq->sqid] = NULL;
    timer_del(sq->timer);
    timer_free(sq->timer);
    g_free(sq->io_req);
    if (sq->sqid) {
        g_free(sq);
    }
}

static uint16_t nvme_del_sq(NvmeCtrl *n, NvmeCmd *cmd)
{
    NvmeDeleteQ *c = (NvmeDeleteQ *)cmd;
    NvmeRequest *req, *next;
    NvmeSQueue *sq;
    NvmeCQueue *cq;
    uint16_t qid = le16_to_cpu(c->qid);

    if (unlikely(!qid || nvme_check_sqid(n, qid))) {
        trace_pci_nvme_err_invalid_del_sq(qid);
        return NVME_INVALID_QID | NVME_DNR;
    }

    trace_pci_nvme_del_sq(qid);

    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);
    }
    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);
            }
        }
    }

    nvme_free_sq(sq, n);
    return NVME_SUCCESS;
}

static void nvme_init_sq(NvmeSQueue *sq, NvmeCtrl *n, uint64_t dma_addr,
    uint16_t sqid, uint16_t cqid, uint16_t size)
{
    int i;
    NvmeCQueue *cq;

    sq->ctrl = n;
    sq->dma_addr = dma_addr;
    sq->sqid = sqid;
    sq->size = size;
    sq->cqid = cqid;
    sq->head = sq->tail = 0;
    sq->io_req = g_new(NvmeRequest, sq->size);

    QTAILQ_INIT(&sq->req_list);
    QTAILQ_INIT(&sq->out_req_list);
    for (i = 0; i < sq->size; i++) {
        sq->io_req[i].sq = sq;
        QTAILQ_INSERT_TAIL(&(sq->req_list), &sq->io_req[i], entry);
    }
    sq->timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, nvme_process_sq, sq);

    assert(n->cq[cqid]);
    cq = n->cq[cqid];
    QTAILQ_INSERT_TAIL(&(cq->sq_list), sq, entry);
    n->sq[sqid] = sq;
}

static uint16_t nvme_create_sq(NvmeCtrl *n, NvmeCmd *cmd)
{
    NvmeSQueue *sq;
    NvmeCreateSq *c = (NvmeCreateSq *)cmd;

    uint16_t cqid = le16_to_cpu(c->cqid);
    uint16_t sqid = le16_to_cpu(c->sqid);
    uint16_t qsize = le16_to_cpu(c->qsize);
    uint16_t qflags = le16_to_cpu(c->sq_flags);
    uint64_t prp1 = le64_to_cpu(c->prp1);

    trace_pci_nvme_create_sq(prp1, sqid, cqid, qsize, qflags);

    if (unlikely(!cqid || nvme_check_cqid(n, cqid))) {
        trace_pci_nvme_err_invalid_create_sq_cqid(cqid);
        return NVME_INVALID_CQID | NVME_DNR;
    }
    if (unlikely(!sqid || !nvme_check_sqid(n, sqid))) {
        trace_pci_nvme_err_invalid_create_sq_sqid(sqid);
        return NVME_INVALID_QID | NVME_DNR;
    }
    if (unlikely(!qsize || qsize > NVME_CAP_MQES(n->bar.cap))) {
        trace_pci_nvme_err_invalid_create_sq_size(qsize);
        return NVME_MAX_QSIZE_EXCEEDED | NVME_DNR;
    }
    if (unlikely(!prp1 || prp1 & (n->page_size - 1))) {
        trace_pci_nvme_err_invalid_create_sq_addr(prp1);
        return NVME_INVALID_FIELD | NVME_DNR;
    }
    if (unlikely(!(NVME_SQ_FLAGS_PC(qflags)))) {
        trace_pci_nvme_err_invalid_create_sq_qflags(NVME_SQ_FLAGS_PC(qflags));
        return NVME_INVALID_FIELD | NVME_DNR;
    }
    sq = g_malloc0(sizeof(*sq));
    nvme_init_sq(sq, n, prp1, sqid, cqid, qsize + 1);
    return NVME_SUCCESS;
}

static void nvme_free_cq(NvmeCQueue *cq, NvmeCtrl *n)
{
    n->cq[cq->cqid] = NULL;
    timer_del(cq->timer);
    timer_free(cq->timer);
    msix_vector_unuse(&n->parent_obj, cq->vector);
    if (cq->cqid) {
        g_free(cq);
    }
}

static uint16_t nvme_del_cq(NvmeCtrl *n, NvmeCmd *cmd)
{
    NvmeDeleteQ *c = (NvmeDeleteQ *)cmd;
    NvmeCQueue *cq;
    uint16_t qid = le16_to_cpu(c->qid);

    if (unlikely(!qid || nvme_check_cqid(n, qid))) {
        trace_pci_nvme_err_invalid_del_cq_cqid(qid);
        return NVME_INVALID_CQID | NVME_DNR;
    }

    cq = n->cq[qid];
    if (unlikely(!QTAILQ_EMPTY(&cq->sq_list))) {
        trace_pci_nvme_err_invalid_del_cq_notempty(qid);
        return NVME_INVALID_QUEUE_DEL;
    }
    nvme_irq_deassert(n, cq);
    trace_pci_nvme_del_cq(qid);
    nvme_free_cq(cq, n);
    return NVME_SUCCESS;
}

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)
{
    int ret;

    ret = msix_vector_use(&n->parent_obj, vector);
    assert(ret == 0);
    cq->ctrl = n;
    cq->cqid = cqid;
    cq->size = size;
    cq->dma_addr = dma_addr;
    cq->phase = 1;
    cq->irq_enabled = irq_enabled;
    cq->vector = vector;
    cq->head = cq->tail = 0;
    QTAILQ_INIT(&cq->req_list);
    QTAILQ_INIT(&cq->sq_list);
    n->cq[cqid] = cq;
    cq->timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, nvme_post_cqes, cq);
}

static uint16_t nvme_create_cq(NvmeCtrl *n, NvmeCmd *cmd)
{
    NvmeCQueue *cq;
    NvmeCreateCq *c = (NvmeCreateCq *)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);
    uint16_t qflags = le16_to_cpu(c->cq_flags);
    uint64_t prp1 = le64_to_cpu(c->prp1);

    trace_pci_nvme_create_cq(prp1, cqid, vector, qsize, qflags,
                             NVME_CQ_FLAGS_IEN(qflags) != 0);

    if (unlikely(!cqid || !nvme_check_cqid(n, cqid))) {
        trace_pci_nvme_err_invalid_create_cq_cqid(cqid);
        return NVME_INVALID_CQID | 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)) {
        trace_pci_nvme_err_invalid_create_cq_addr(prp1);
        return NVME_INVALID_FIELD | NVME_DNR;
    }
    if (unlikely(!msix_enabled(&n->parent_obj) && vector)) {
        trace_pci_nvme_err_invalid_create_cq_vector(vector);
        return NVME_INVALID_IRQ_VECTOR | NVME_DNR;
    }
    if (unlikely(vector >= n->params.msix_qsize)) {
        trace_pci_nvme_err_invalid_create_cq_vector(vector);
        return NVME_INVALID_IRQ_VECTOR | NVME_DNR;
    }
    if (unlikely(!(NVME_CQ_FLAGS_PC(qflags)))) {
        trace_pci_nvme_err_invalid_create_cq_qflags(NVME_CQ_FLAGS_PC(qflags));
        return NVME_INVALID_FIELD | NVME_DNR;
    }

    cq = g_malloc0(sizeof(*cq));
    nvme_init_cq(cq, n, prp1, cqid, vector, qsize + 1,
        NVME_CQ_FLAGS_IEN(qflags));
    return NVME_SUCCESS;
}

static uint16_t nvme_identify_ctrl(NvmeCtrl *n, NvmeIdentify *c)
{
    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);
}

static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeIdentify *c)
{
    NvmeNamespace *ns;
    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);
        return NVME_INVALID_NSID | NVME_DNR;
    }

    ns = &n->namespaces[nsid - 1];

    return nvme_dma_read_prp(n, (uint8_t *)&ns->id_ns, sizeof(ns->id_ns),
        prp1, prp2);
}

static uint16_t nvme_identify_nslist(NvmeCtrl *n, NvmeIdentify *c)
{
    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;

    trace_pci_nvme_identify_nslist(min_nsid);

    list = g_malloc0(data_len);
    for (i = 0; i < n->num_namespaces; i++) {
        if (i < min_nsid) {
            continue;
        }
        list[j++] = cpu_to_le32(i + 1);
        if (j == data_len / sizeof(uint32_t)) {
            break;
        }
    }
    ret = nvme_dma_read_prp(n, (uint8_t *)list, data_len, prp1, prp2);
    g_free(list);
    return ret;
}

static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd)
{
    NvmeIdentify *c = (NvmeIdentify *)cmd;

    switch (le32_to_cpu(c->cns)) {
    case NVME_ID_CNS_NS:
        return nvme_identify_ns(n, c);
    case NVME_ID_CNS_CTRL:
        return nvme_identify_ctrl(n, c);
    case NVME_ID_CNS_NS_ACTIVE_LIST:
        return nvme_identify_nslist(n, c);
    default:
        trace_pci_nvme_err_invalid_identify_cns(le32_to_cpu(c->cns));
        return NVME_INVALID_FIELD | NVME_DNR;
    }
}

static inline void nvme_set_timestamp(NvmeCtrl *n, uint64_t ts)
{
    trace_pci_nvme_setfeat_timestamp(ts);

    n->host_timestamp = le64_to_cpu(ts);
    n->timestamp_set_qemu_clock_ms = qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL);
}

static inline uint64_t nvme_get_timestamp(const NvmeCtrl *n)
{
    uint64_t current_time = qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL);
    uint64_t elapsed_time = current_time - n->timestamp_set_qemu_clock_ms;

    union nvme_timestamp {
        struct {
            uint64_t timestamp:48;
            uint64_t sync:1;
            uint64_t origin:3;
            uint64_t rsvd1:12;
        };
        uint64_t all;
    };

    union nvme_timestamp ts;
    ts.all = 0;

    /*
     * If the sum of the Timestamp value set by the host and the elapsed
     * time exceeds 2^48, the value returned should be reduced modulo 2^48.
     */
    ts.timestamp = (n->host_timestamp + elapsed_time) & 0xffffffffffff;

    /* If the host timestamp is non-zero, set the timestamp origin */
    ts.origin = n->host_timestamp ? 0x01 : 0x00;

    trace_pci_nvme_getfeat_timestamp(ts.all);

    return cpu_to_le64(ts.all);
}

static uint16_t nvme_get_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd)
{
    uint64_t prp1 = le64_to_cpu(cmd->prp1);
    uint64_t prp2 = le64_to_cpu(cmd->prp2);

    uint64_t timestamp = nvme_get_timestamp(n);

    return nvme_dma_read_prp(n, (uint8_t *)&timestamp,
                                 sizeof(timestamp), prp1, prp2);
}

static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
{
    uint32_t dw10 = le32_to_cpu(cmd->cdw10);
    uint32_t result;

    switch (dw10) {
    case NVME_VOLATILE_WRITE_CACHE:
        result = blk_enable_write_cache(n->conf.blk);
        trace_pci_nvme_getfeat_vwcache(result ? "enabled" : "disabled");
        break;
    case NVME_NUMBER_OF_QUEUES:
        result = cpu_to_le32((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);
    default:
        trace_pci_nvme_err_invalid_getfeat(dw10);
        return NVME_INVALID_FIELD | NVME_DNR;
    }

    req->cqe.result = result;
    return NVME_SUCCESS;
}

static uint16_t nvme_set_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd)
{
    uint16_t ret;
    uint64_t timestamp;
    uint64_t prp1 = le64_to_cpu(cmd->prp1);
    uint64_t prp2 = le64_to_cpu(cmd->prp2);

    ret = nvme_dma_write_prp(n, (uint8_t *)&timestamp,
                                sizeof(timestamp), prp1, prp2);
    if (ret != NVME_SUCCESS) {
        return ret;
    }

    nvme_set_timestamp(n, timestamp);

    return NVME_SUCCESS;
}

static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
{
    uint32_t dw10 = le32_to_cpu(cmd->cdw10);
    uint32_t dw11 = le32_to_cpu(cmd->cdw11);

    switch (dw10) {
    case NVME_VOLATILE_WRITE_CACHE:
        blk_set_enable_write_cache(n->conf.blk, dw11 & 1);
        break;
    case NVME_NUMBER_OF_QUEUES:
        trace_pci_nvme_setfeat_numq((dw11 & 0xFFFF) + 1,
                                    ((dw11 >> 16) & 0xFFFF) + 1,
                                    n->params.max_ioqpairs,
                                    n->params.max_ioqpairs);
        req->cqe.result = cpu_to_le32((n->params.max_ioqpairs - 1) |
                                      ((n->params.max_ioqpairs - 1) << 16));
        break;
    case NVME_TIMESTAMP:
        return nvme_set_feature_timestamp(n, cmd);
    default:
        trace_pci_nvme_err_invalid_setfeat(dw10);
        return NVME_INVALID_FIELD | NVME_DNR;
    }
    return NVME_SUCCESS;
}

static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
{
    switch (cmd->opcode) {
    case NVME_ADM_CMD_DELETE_SQ:
        return nvme_del_sq(n, cmd);
    case NVME_ADM_CMD_CREATE_SQ:
        return nvme_create_sq(n, cmd);
    case NVME_ADM_CMD_DELETE_CQ:
        return nvme_del_cq(n, cmd);
    case NVME_ADM_CMD_CREATE_CQ:
        return nvme_create_cq(n, cmd);
    case NVME_ADM_CMD_IDENTIFY:
        return nvme_identify(n, cmd);
    case NVME_ADM_CMD_SET_FEATURES:
        return nvme_set_feature(n, cmd, req);
    case NVME_ADM_CMD_GET_FEATURES:
        return nvme_get_feature(n, cmd, req);
    default:
        trace_pci_nvme_err_invalid_admin_opc(cmd->opcode);
        return NVME_INVALID_OPCODE | NVME_DNR;
    }
}

static void nvme_process_sq(void *opaque)
{
    NvmeSQueue *sq = opaque;
    NvmeCtrl *n = sq->ctrl;
    NvmeCQueue *cq = n->cq[sq->cqid];

    uint16_t status;
    hwaddr addr;
    NvmeCmd cmd;
    NvmeRequest *req;

    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));
        nvme_inc_sq_head(sq);

        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));
        req->cqe.cid = cmd.cid;

        status = sq->sqid ? nvme_io_cmd(n, &cmd, req) :
            nvme_admin_cmd(n, &cmd, req);
        if (status != NVME_NO_COMPLETE) {
            req->status = status;
            nvme_enqueue_req_completion(cq, req);
        }
    }
}

static void nvme_clear_ctrl(NvmeCtrl *n)
{
    int i;

    blk_drain(n->conf.blk);

    for (i = 0; i < n->params.max_ioqpairs + 1; i++) {
        if (n->sq[i] != NULL) {
            nvme_free_sq(n->sq[i], n);
        }
    }
    for (i = 0; i < n->params.max_ioqpairs + 1; i++) {
        if (n->cq[i] != NULL) {
            nvme_free_cq(n->cq[i], n);
        }
    }

    blk_flush(n->conf.blk);
    n->bar.cc = 0;
}

static int nvme_start_ctrl(NvmeCtrl *n)
{
    uint32_t page_bits = NVME_CC_MPS(n->bar.cc) + 12;
    uint32_t page_size = 1 << page_bits;

    if (unlikely(n->cq[0])) {
        trace_pci_nvme_err_startfail_cq();
        return -1;
    }
    if (unlikely(n->sq[0])) {
        trace_pci_nvme_err_startfail_sq();
        return -1;
    }
    if (unlikely(!n->bar.asq)) {
        trace_pci_nvme_err_startfail_nbarasq();
        return -1;
    }
    if (unlikely(!n->bar.acq)) {
        trace_pci_nvme_err_startfail_nbaracq();
        return -1;
    }
    if (unlikely(n->bar.asq & (page_size - 1))) {
        trace_pci_nvme_err_startfail_asq_misaligned(n->bar.asq);
        return -1;
    }
    if (unlikely(n->bar.acq & (page_size - 1))) {
        trace_pci_nvme_err_startfail_acq_misaligned(n->bar.acq);
        return -1;
    }
    if (unlikely(NVME_CC_MPS(n->bar.cc) <
                 NVME_CAP_MPSMIN(n->bar.cap))) {
        trace_pci_nvme_err_startfail_page_too_small(
                    NVME_CC_MPS(n->bar.cc),
                    NVME_CAP_MPSMIN(n->bar.cap));
        return -1;
    }
    if (unlikely(NVME_CC_MPS(n->bar.cc) >
                 NVME_CAP_MPSMAX(n->bar.cap))) {
        trace_pci_nvme_err_startfail_page_too_large(
                    NVME_CC_MPS(n->bar.cc),
                    NVME_CAP_MPSMAX(n->bar.cap));
        return -1;
    }
    if (unlikely(NVME_CC_IOCQES(n->bar.cc) <
                 NVME_CTRL_CQES_MIN(n->id_ctrl.cqes))) {
        trace_pci_nvme_err_startfail_cqent_too_small(
                    NVME_CC_IOCQES(n->bar.cc),
                    NVME_CTRL_CQES_MIN(n->bar.cap));
        return -1;
    }
    if (unlikely(NVME_CC_IOCQES(n->bar.cc) >
                 NVME_CTRL_CQES_MAX(n->id_ctrl.cqes))) {
        trace_pci_nvme_err_startfail_cqent_too_large(
                    NVME_CC_IOCQES(n->bar.cc),
                    NVME_CTRL_CQES_MAX(n->bar.cap));
        return -1;
    }
    if (unlikely(NVME_CC_IOSQES(n->bar.cc) <
                 NVME_CTRL_SQES_MIN(n->id_ctrl.sqes))) {
        trace_pci_nvme_err_startfail_sqent_too_small(
                    NVME_CC_IOSQES(n->bar.cc),
                    NVME_CTRL_SQES_MIN(n->bar.cap));
        return -1;
    }
    if (unlikely(NVME_CC_IOSQES(n->bar.cc) >
                 NVME_CTRL_SQES_MAX(n->id_ctrl.sqes))) {
        trace_pci_nvme_err_startfail_sqent_too_large(
                    NVME_CC_IOSQES(n->bar.cc),
                    NVME_CTRL_SQES_MAX(n->bar.cap));
        return -1;
    }
    if (unlikely(!NVME_AQA_ASQS(n->bar.aqa))) {
        trace_pci_nvme_err_startfail_asqent_sz_zero();
        return -1;
    }
    if (unlikely(!NVME_AQA_ACQS(n->bar.aqa))) {
        trace_pci_nvme_err_startfail_acqent_sz_zero();
        return -1;
    }

    n->page_bits = page_bits;
    n->page_size = page_size;
    n->max_prp_ents = n->page_size / sizeof(uint64_t);
    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_init_sq(&n->admin_sq, n, n->bar.asq, 0, 0,
        NVME_AQA_ASQS(n->bar.aqa) + 1);

    nvme_set_timestamp(n, 0ULL);

    return 0;
}

static void nvme_write_bar(NvmeCtrl *n, hwaddr offset, uint64_t data,
    unsigned size)
{
    if (unlikely(offset & (sizeof(uint32_t) - 1))) {
        NVME_GUEST_ERR(pci_nvme_ub_mmiowr_misaligned32,
                       "MMIO write not 32-bit aligned,"
                       " offset=0x%"PRIx64"", offset);
        /* should be ignored, fall through for now */
    }

    if (unlikely(size < sizeof(uint32_t))) {
        NVME_GUEST_ERR(pci_nvme_ub_mmiowr_toosmall,
                       "MMIO write smaller than 32-bits,"
                       " offset=0x%"PRIx64", size=%u",
                       offset, size);
        /* should be ignored, fall through for now */
    }

    switch (offset) {
    case 0xc:   /* INTMS */
        if (unlikely(msix_enabled(&(n->parent_obj)))) {
            NVME_GUEST_ERR(pci_nvme_ub_mmiowr_intmask_with_msix,
                           "undefined access to interrupt mask set"
                           " when MSI-X is enabled");
            /* should be ignored, fall through for now */
        }
        n->bar.intms |= data & 0xffffffff;
        n->bar.intmc = n->bar.intms;
        trace_pci_nvme_mmio_intm_set(data & 0xffffffff, n->bar.intmc);
        nvme_irq_check(n);
        break;
    case 0x10:  /* INTMC */
        if (unlikely(msix_enabled(&(n->parent_obj)))) {
            NVME_GUEST_ERR(pci_nvme_ub_mmiowr_intmask_with_msix,
                           "undefined access to interrupt mask clr"
                           " when MSI-X is enabled");
            /* should be ignored, fall through for now */
        }
        n->bar.intms &= ~(data & 0xffffffff);
        n->bar.intmc = n->bar.intms;
        trace_pci_nvme_mmio_intm_clr(data & 0xffffffff, n->bar.intmc);
        nvme_irq_check(n);
        break;
    case 0x14:  /* CC */
        trace_pci_nvme_mmio_cfg(data & 0xffffffff);
        /* Windows first sends data, then sends enable bit */
        if (!NVME_CC_EN(data) && !NVME_CC_EN(n->bar.cc) &&
            !NVME_CC_SHN(data) && !NVME_CC_SHN(n->bar.cc))
        {
            n->bar.cc = data;
        }

        if (NVME_CC_EN(data) && !NVME_CC_EN(n->bar.cc)) {
            n->bar.cc = data;
            if (unlikely(nvme_start_ctrl(n))) {
                trace_pci_nvme_err_startfail();
                n->bar.csts = NVME_CSTS_FAILED;
            } else {
                trace_pci_nvme_mmio_start_success();
                n->bar.csts = NVME_CSTS_READY;
            }
        } else if (!NVME_CC_EN(data) && NVME_CC_EN(n->bar.cc)) {
            trace_pci_nvme_mmio_stopped();
            nvme_clear_ctrl(n);
            n->bar.csts &= ~NVME_CSTS_READY;
        }
        if (NVME_CC_SHN(data) && !(NVME_CC_SHN(n->bar.cc))) {
            trace_pci_nvme_mmio_shutdown_set();
            nvme_clear_ctrl(n);
            n->bar.cc = data;
            n->bar.csts |= NVME_CSTS_SHST_COMPLETE;
        } else if (!NVME_CC_SHN(data) && NVME_CC_SHN(n->bar.cc)) {
            trace_pci_nvme_mmio_shutdown_cleared();
            n->bar.csts &= ~NVME_CSTS_SHST_COMPLETE;
            n->bar.cc = data;
        }
        break;
    case 0x1C:  /* CSTS */
        if (data & (1 << 4)) {
            NVME_GUEST_ERR(pci_nvme_ub_mmiowr_ssreset_w1c_unsupported,
                           "attempted to W1C CSTS.NSSRO"
                           " but CAP.NSSRS is zero (not supported)");
        } else if (data != 0) {
            NVME_GUEST_ERR(pci_nvme_ub_mmiowr_ro_csts,
                           "attempted to set a read only bit"
                           " of controller status");
        }
        break;
    case 0x20:  /* NSSR */
        if (data == 0x4E564D65) {
            trace_pci_nvme_ub_mmiowr_ssreset_unsupported();
        } else {
            /* The spec says that writes of other values have no effect */
            return;
        }
        break;
    case 0x24:  /* AQA */
        n->bar.aqa = data & 0xffffffff;
        trace_pci_nvme_mmio_aqattr(data & 0xffffffff);
        break;
    case 0x28:  /* ASQ */
        n->bar.asq = data;
        trace_pci_nvme_mmio_asqaddr(data);
        break;
    case 0x2c:  /* ASQ hi */
        n->bar.asq |= data << 32;
        trace_pci_nvme_mmio_asqaddr_hi(data, n->bar.asq);
        break;
    case 0x30:  /* ACQ */
        trace_pci_nvme_mmio_acqaddr(data);
        n->bar.acq = data;
        break;
    case 0x34:  /* ACQ hi */
        n->bar.acq |= data << 32;
        trace_pci_nvme_mmio_acqaddr_hi(data, n->bar.acq);
        break;
    case 0x38:  /* CMBLOC */
        NVME_GUEST_ERR(pci_nvme_ub_mmiowr_cmbloc_reserved,
                       "invalid write to reserved CMBLOC"
                       " when CMBSZ is zero, ignored");
        return;
    case 0x3C:  /* CMBSZ */
        NVME_GUEST_ERR(pci_nvme_ub_mmiowr_cmbsz_readonly,
                       "invalid write to read only CMBSZ, ignored");
        return;
    case 0xE00: /* PMRCAP */
        NVME_GUEST_ERR(pci_nvme_ub_mmiowr_pmrcap_readonly,
                       "invalid write to PMRCAP register, ignored");
        return;
    case 0xE04: /* TODO PMRCTL */
        break;
    case 0xE08: /* PMRSTS */
        NVME_GUEST_ERR(pci_nvme_ub_mmiowr_pmrsts_readonly,
                       "invalid write to PMRSTS register, ignored");
        return;
    case 0xE0C: /* PMREBS */
        NVME_GUEST_ERR(pci_nvme_ub_mmiowr_pmrebs_readonly,
                       "invalid write to PMREBS register, ignored");
        return;
    case 0xE10: /* PMRSWTP */
        NVME_GUEST_ERR(pci_nvme_ub_mmiowr_pmrswtp_readonly,
                       "invalid write to PMRSWTP register, ignored");
        return;
    case 0xE14: /* TODO PMRMSC */
         break;
    default:
        NVME_GUEST_ERR(pci_nvme_ub_mmiowr_invalid,
                       "invalid MMIO write,"
                       " offset=0x%"PRIx64", data=%"PRIx64"",
                       offset, data);
        break;
    }
}

static uint64_t nvme_mmio_read(void *opaque, hwaddr addr, unsigned size)
{
    NvmeCtrl *n = (NvmeCtrl *)opaque;
    uint8_t *ptr = (uint8_t *)&n->bar;
    uint64_t val = 0;

    if (unlikely(addr & (sizeof(uint32_t) - 1))) {
        NVME_GUEST_ERR(pci_nvme_ub_mmiord_misaligned32,
                       "MMIO read not 32-bit aligned,"
                       " offset=0x%"PRIx64"", addr);
        /* should RAZ, fall through for now */
    } else if (unlikely(size < sizeof(uint32_t))) {
        NVME_GUEST_ERR(pci_nvme_ub_mmiord_toosmall,
                       "MMIO read smaller than 32-bits,"
                       " offset=0x%"PRIx64"", addr);
        /* should RAZ, fall through for now */
    }

    if (addr < sizeof(n->bar)) {
        /*
         * When PMRWBM bit 1 is set then read from
         * from PMRSTS should ensure prior writes
         * made it to persistent media
         */
        if (addr == 0xE08 &&
            (NVME_PMRCAP_PMRWBM(n->bar.pmrcap) & 0x02)) {
            memory_region_msync(&n->pmrdev->mr, 0, n->pmrdev->size);
        }
        memcpy(&val, ptr + addr, size);
    } else {
        NVME_GUEST_ERR(pci_nvme_ub_mmiord_invalid_ofs,
                       "MMIO read beyond last register,"
                       " offset=0x%"PRIx64", returning 0", addr);
    }

    return val;
}

static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val)
{
    uint32_t qid;

    if (unlikely(addr & ((1 << 2) - 1))) {
        NVME_GUEST_ERR(pci_nvme_ub_db_wr_misaligned,
                       "doorbell write not 32-bit aligned,"
                       " offset=0x%"PRIx64", ignoring", addr);
        return;
    }

    if (((addr - 0x1000) >> 2) & 1) {
        /* Completion queue doorbell write */

        uint16_t new_head = val & 0xffff;
        int start_sqs;
        NvmeCQueue *cq;

        qid = (addr - (0x1000 + (1 << 2))) >> 3;
        if (unlikely(nvme_check_cqid(n, qid))) {
            NVME_GUEST_ERR(pci_nvme_ub_db_wr_invalid_cq,
                           "completion queue doorbell write"
                           " for nonexistent queue,"
                           " sqid=%"PRIu32", ignoring", qid);
            return;
        }

        cq = n->cq[qid];
        if (unlikely(new_head >= cq->size)) {
            NVME_GUEST_ERR(pci_nvme_ub_db_wr_invalid_cqhead,
                           "completion queue doorbell write value"
                           " beyond queue size, sqid=%"PRIu32","
                           " new_head=%"PRIu16", ignoring",
                           qid, new_head);
            return;
        }

        start_sqs = nvme_cq_full(cq) ? 1 : 0;
        cq->head = new_head;
        if (start_sqs) {
            NvmeSQueue *sq;
            QTAILQ_FOREACH(sq, &cq->sq_list, entry) {
                timer_mod(sq->timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + 500);
            }
            timer_mod(cq->timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + 500);
        }

        if (cq->tail == cq->head) {
            nvme_irq_deassert(n, cq);
        }
    } else {
        /* Submission queue doorbell write */

        uint16_t new_tail = val & 0xffff;
        NvmeSQueue *sq;

        qid = (addr - 0x1000) >> 3;
        if (unlikely(nvme_check_sqid(n, qid))) {
            NVME_GUEST_ERR(pci_nvme_ub_db_wr_invalid_sq,
                           "submission queue doorbell write"
                           " for nonexistent queue,"
                           " sqid=%"PRIu32", ignoring", qid);
            return;
        }

        sq = n->sq[qid];
        if (unlikely(new_tail >= sq->size)) {
            NVME_GUEST_ERR(pci_nvme_ub_db_wr_invalid_sqtail,
                           "submission queue doorbell write value"
                           " beyond queue size, sqid=%"PRIu32","
                           " new_tail=%"PRIu16", ignoring",
                           qid, new_tail);
            return;
        }

        sq->tail = new_tail;
        timer_mod(sq->timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + 500);
    }
}

static void nvme_mmio_write(void *opaque, hwaddr addr, uint64_t data,
    unsigned size)
{
    NvmeCtrl *n = (NvmeCtrl *)opaque;
    if (addr < sizeof(n->bar)) {
        nvme_write_bar(n, addr, data, size);
    } else {
        nvme_process_db(n, addr, data);
    }
}

static const MemoryRegionOps nvme_mmio_ops = {
    .read = nvme_mmio_read,
    .write = nvme_mmio_write,
    .endianness = DEVICE_LITTLE_ENDIAN,
    .impl = {
        .min_access_size = 2,
        .max_access_size = 8,
    },
};

static void nvme_cmb_write(void *opaque, hwaddr addr, uint64_t data,
    unsigned size)
{
    NvmeCtrl *n = (NvmeCtrl *)opaque;
    stn_le_p(&n->cmbuf[addr], size, data);
}

static uint64_t nvme_cmb_read(void *opaque, hwaddr addr, unsigned size)
{
    NvmeCtrl *n = (NvmeCtrl *)opaque;
    return ldn_le_p(&n->cmbuf[addr], size);
}

static const MemoryRegionOps nvme_cmb_ops = {
    .read = nvme_cmb_read,
    .write = nvme_cmb_write,
    .endianness = DEVICE_LITTLE_ENDIAN,
    .impl = {
        .min_access_size = 1,
        .max_access_size = 8,
    },
};

static void nvme_check_constraints(NvmeCtrl *n, Error **errp)
{
    NvmeParams *params = &n->params;

    if (params->num_queues) {
        warn_report("num_queues is deprecated; please use max_ioqpairs "
                    "instead");

        params->max_ioqpairs = params->num_queues - 1;
    }

    if (params->max_ioqpairs < 1 ||
        params->max_ioqpairs > NVME_MAX_IOQPAIRS) {
        error_setg(errp, "max_ioqpairs must be between 1 and %d",
                   NVME_MAX_IOQPAIRS);
        return;
    }

    if (params->msix_qsize < 1 ||
        params->msix_qsize > PCI_MSIX_FLAGS_QSIZE + 1) {
        error_setg(errp, "msix_qsize must be between 1 and %d",
                   PCI_MSIX_FLAGS_QSIZE + 1);
        return;
    }

    if (!n->conf.blk) {
        error_setg(errp, "drive property not set");
        return;
    }

    if (!params->serial) {
        error_setg(errp, "serial property not set");
        return;
    }

    if (!n->params.cmb_size_mb && n->pmrdev) {
        if (host_memory_backend_is_mapped(n->pmrdev)) {
            error_setg(errp, "can't use already busy memdev: %s",
                       object_get_canonical_path_component(OBJECT(n->pmrdev)));
            return;
        }

        if (!is_power_of_2(n->pmrdev->size)) {
            error_setg(errp, "pmr backend size needs to be power of 2 in size");
            return;
        }

        host_memory_backend_set_mapped(n->pmrdev, true);
    }
}

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(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);
}

static void nvme_init_blk(NvmeCtrl *n, Error **errp)
{
    if (!blkconf_blocksizes(&n->conf, errp)) {
        return;
    }
    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;

    bs_size = blk_getlength(n->conf.blk);
    if (bs_size < 0) {
        error_setg_errno(errp, -bs_size, "could not get backing file size");
        return;
    }

    n->ns_size = bs_size;

    id_ns->lbaf[0].ds = BDRV_SECTOR_BITS;
    id_ns->nsze = cpu_to_le64(nvme_ns_nlbas(n, ns));

    /* no thin provisioning */
    id_ns->ncap = id_ns->nsze;
    id_ns->nuse = id_ns->ncap;
}

static void nvme_init_cmb(NvmeCtrl *n, PCIDevice *pci_dev)
{
    NVME_CMBLOC_SET_BIR(n->bar.cmbloc, NVME_CMB_BIR);
    NVME_CMBLOC_SET_OFST(n->bar.cmbloc, 0);

    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_RDS(n->bar.cmbsz, 1);
    NVME_CMBSZ_SET_WDS(n->bar.cmbsz, 1);
    NVME_CMBSZ_SET_SZU(n->bar.cmbsz, 2); /* MBs */
    NVME_CMBSZ_SET_SZ(n->bar.cmbsz, n->params.cmb_size_mb);

    n->cmbuf = g_malloc0(NVME_CMBSZ_GETSIZE(n->bar.cmbsz));
    memory_region_init_io(&n->ctrl_mem, OBJECT(n), &nvme_cmb_ops, n,
                          "nvme-cmb", NVME_CMBSZ_GETSIZE(n->bar.cmbsz));
    pci_register_bar(pci_dev, NVME_CMBLOC_BIR(n->bar.cmbloc),
                     PCI_BASE_ADDRESS_SPACE_MEMORY |
                     PCI_BASE_ADDRESS_MEM_TYPE_64 |
                     PCI_BASE_ADDRESS_MEM_PREFETCH, &n->ctrl_mem);
}

static void nvme_init_pmr(NvmeCtrl *n, PCIDevice *pci_dev)
{
    /* Controller Capabilities register */
    NVME_CAP_SET_PMRS(n->bar.cap, 1);

    /* PMR Capabities register */
    n->bar.pmrcap = 0;
    NVME_PMRCAP_SET_RDS(n->bar.pmrcap, 0);
    NVME_PMRCAP_SET_WDS(n->bar.pmrcap, 0);
    NVME_PMRCAP_SET_BIR(n->bar.pmrcap, NVME_PMR_BIR);
    NVME_PMRCAP_SET_PMRTU(n->bar.pmrcap, 0);
    /* Turn on bit 1 support */
    NVME_PMRCAP_SET_PMRWBM(n->bar.pmrcap, 0x02);
    NVME_PMRCAP_SET_PMRTO(n->bar.pmrcap, 0);
    NVME_PMRCAP_SET_CMSS(n->bar.pmrcap, 0);

    /* PMR Control register */
    n->bar.pmrctl = 0;
    NVME_PMRCTL_SET_EN(n->bar.pmrctl, 0);

    /* PMR Status register */
    n->bar.pmrsts = 0;
    NVME_PMRSTS_SET_ERR(n->bar.pmrsts, 0);
    NVME_PMRSTS_SET_NRDY(n->bar.pmrsts, 0);
    NVME_PMRSTS_SET_HSTS(n->bar.pmrsts, 0);
    NVME_PMRSTS_SET_CBAI(n->bar.pmrsts, 0);

    /* PMR Elasticity Buffer Size register */
    n->bar.pmrebs = 0;
    NVME_PMREBS_SET_PMRSZU(n->bar.pmrebs, 0);
    NVME_PMREBS_SET_RBB(n->bar.pmrebs, 0);
    NVME_PMREBS_SET_PMRWBZ(n->bar.pmrebs, 0);

    /* PMR Sustained Write Throughput register */
    n->bar.pmrswtp = 0;
    NVME_PMRSWTP_SET_PMRSWTU(n->bar.pmrswtp, 0);
    NVME_PMRSWTP_SET_PMRSWTV(n->bar.pmrswtp, 0);

    /* PMR Memory Space Control register */
    n->bar.pmrmsc = 0;
    NVME_PMRMSC_SET_CMSE(n->bar.pmrmsc, 0);
    NVME_PMRMSC_SET_CBA(n->bar.pmrmsc, 0);

    pci_register_bar(pci_dev, NVME_PMRCAP_BIR(n->bar.pmrcap),
                     PCI_BASE_ADDRESS_SPACE_MEMORY |
                     PCI_BASE_ADDRESS_MEM_TYPE_64 |
                     PCI_BASE_ADDRESS_MEM_PREFETCH, &n->pmrdev->mr);
}

static void nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev, Error **errp)
{
    uint8_t *pci_conf = pci_dev->config;

    pci_conf[PCI_INTERRUPT_PIN] = 1;
    pci_config_set_prog_interface(pci_conf, 0x2);
    pci_config_set_class(pci_conf, PCI_CLASS_STORAGE_EXPRESS);
    pcie_endpoint_cap_init(pci_dev, 0x80);

    memory_region_init_io(&n->iomem, OBJECT(n), &nvme_mmio_ops, n, "nvme",
                          n->reg_size);
    pci_register_bar(pci_dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY |
                     PCI_BASE_ADDRESS_MEM_TYPE_64, &n->iomem);
    if (msix_init_exclusive_bar(pci_dev, n->params.msix_qsize, 4, errp)) {
        return;
    }

    if (n->params.cmb_size_mb) {
        nvme_init_cmb(n, pci_dev);
    } else if (n->pmrdev) {
        nvme_init_pmr(n, pci_dev);
    }
}

static void nvme_init_ctrl(NvmeCtrl *n, PCIDevice *pci_dev)
{
    NvmeIdCtrl *id = &n->id_ctrl;
    uint8_t *pci_conf = pci_dev->config;

    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));
    strpadcpy((char *)id->mn, sizeof(id->mn), "QEMU NVMe Ctrl", ' ');
    strpadcpy((char *)id->fr, sizeof(id->fr), "1.0", ' ');
    strpadcpy((char *)id->sn, sizeof(id->sn), n->params.serial, ' ');
    id->rab = 6;
    id->ieee[0] = 0x00;
    id->ieee[1] = 0x02;
    id->ieee[2] = 0xb3;
    id->oacs = cpu_to_le16(0);
    id->frmw = 7 << 1;
    id->lpa = 1 << 0;
    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->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_MPSMAX(n->bar.cap, 4);

    n->bar.vs = 0x00010200;
    n->bar.intmc = n->bar.intms = 0;
}

static void nvme_realize(PCIDevice *pci_dev, Error **errp)
{
    NvmeCtrl *n = NVME(pci_dev);
    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;
    }

    nvme_init_pci(n, pci_dev, &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
        return;
    }

    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);
            return;
        }
    }
}

static void nvme_exit(PCIDevice *pci_dev)
{
    NvmeCtrl *n = NVME(pci_dev);

    nvme_clear_ctrl(n);
    g_free(n->namespaces);
    g_free(n->cq);
    g_free(n->sq);

    if (n->params.cmb_size_mb) {
        g_free(n->cmbuf);
    }

    if (n->pmrdev) {
        host_memory_backend_set_mapped(n->pmrdev, false);
    }
    msix_uninit_exclusive_bar(pci_dev);
}

static Property nvme_props[] = {
    DEFINE_BLOCK_PROPERTIES(NvmeCtrl, conf),
    DEFINE_PROP_LINK("pmrdev", NvmeCtrl, pmrdev, TYPE_MEMORY_BACKEND,
                     HostMemoryBackend *),
    DEFINE_PROP_STRING("serial", NvmeCtrl, params.serial),
    DEFINE_PROP_UINT32("cmb_size_mb", NvmeCtrl, params.cmb_size_mb, 0),
    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_END_OF_LIST(),
};

static const VMStateDescription nvme_vmstate = {
    .name = "nvme",
    .unmigratable = 1,
};

static void nvme_class_init(ObjectClass *oc, void *data)
{
    DeviceClass *dc = DEVICE_CLASS(oc);
    PCIDeviceClass *pc = PCI_DEVICE_CLASS(oc);

    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);
    dc->desc = "Non-Volatile Memory Express";
    device_class_set_props(dc, nvme_props);
    dc->vmsd = &nvme_vmstate;
}

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));
}

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,
    .interfaces = (InterfaceInfo[]) {
        { INTERFACE_PCIE_DEVICE },
        { }
    },
};

static void nvme_register_types(void)
{
    type_register_static(&nvme_info);
}

type_init(nvme_register_types)