nvme.c 28.1 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22
/*
 * QEMU NVM Express Controller
 *
 * Copyright (c) 2012, Intel Corporation
 *
 * Written by Keith Busch <keith.busch@intel.com>
 *
 * This code is licensed under the GNU GPL v2 or later.
 */

/**
 * Reference Specs: http://www.nvmexpress.org, 1.1, 1.0e
 *
 *  http://www.nvmexpress.org/resources/
 */

/**
 * Usage: add options:
 *      -drive file=<file>,if=none,id=<drive_id>
 *      -device nvme,drive=<drive_id>,serial=<serial>,id=<id[optional]>
 */

P
Peter Maydell 已提交
23
#include "qemu/osdep.h"
24 25 26 27
#include "hw/block/block.h"
#include "hw/hw.h"
#include "hw/pci/msix.h"
#include "hw/pci/pci.h"
G
Gonglei 已提交
28
#include "sysemu/sysemu.h"
29
#include "qapi/error.h"
G
Gonglei 已提交
30
#include "qapi/visitor.h"
31
#include "sysemu/block-backend.h"
32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76

#include "nvme.h"

static void nvme_process_sq(void *opaque);

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

static int nvme_check_cqid(NvmeCtrl *n, uint16_t cqid)
{
    return cqid < n->num_queues && 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_isr_notify(NvmeCtrl *n, NvmeCQueue *cq)
{
    if (cq->irq_enabled) {
        if (msix_enabled(&(n->parent_obj))) {
            msix_notify(&(n->parent_obj), cq->vector);
        } else {
77
            pci_irq_pulse(&n->parent_obj);
78 79 80 81 82 83 84 85 86 87 88 89 90 91 92
        }
    }
}

static uint16_t nvme_map_prp(QEMUSGList *qsg, 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 (!prp1) {
        return NVME_INVALID_FIELD | NVME_DNR;
    }

P
Paolo Bonzini 已提交
93
    pci_dma_sglist_init(qsg, &n->parent_obj, num_prps);
94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158
    qemu_sglist_add(qsg, prp1, trans_len);
    len -= trans_len;
    if (len) {
        if (!prp2) {
            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);
            pci_dma_read(&n->parent_obj, 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 (!prp_ent || prp_ent & (n->page_size - 1)) {
                        goto unmap;
                    }

                    i = 0;
                    nents = (len + n->page_size - 1) >> n->page_bits;
                    prp_trans = MIN(n->max_prp_ents, nents) * sizeof(uint64_t);
                    pci_dma_read(&n->parent_obj, prp_ent, (void *)prp_list,
                        prp_trans);
                    prp_ent = le64_to_cpu(prp_list[i]);
                }

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

                trans_len = MIN(len, n->page_size);
                qemu_sglist_add(qsg, prp_ent, trans_len);
                len -= trans_len;
                i++;
            }
        } else {
            if (prp2 & (n->page_size - 1)) {
                goto unmap;
            }
            qemu_sglist_add(qsg, prp2, len);
        }
    }
    return NVME_SUCCESS;

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

static uint16_t nvme_dma_read_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
    uint64_t prp1, uint64_t prp2)
{
    QEMUSGList qsg;

    if (nvme_map_prp(&qsg, prp1, prp2, len, n)) {
        return NVME_INVALID_FIELD | NVME_DNR;
    }
    if (dma_buf_read(ptr, len, &qsg)) {
        qemu_sglist_destroy(&qsg);
        return NVME_INVALID_FIELD | NVME_DNR;
    }
L
Lu Lina 已提交
159
    qemu_sglist_destroy(&qsg);
160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195
    return NVME_SUCCESS;
}

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);
    }
    nvme_isr_notify(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);
196
    timer_mod(cq->timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + 500);
197 198 199 200 201 202 203 204 205 206
}

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) {
207
        block_acct_done(blk_get_stats(n->conf.blk), &req->acct);
208 209
        req->status = NVME_SUCCESS;
    } else {
210
        block_acct_failed(blk_get_stats(n->conf.blk), &req->acct);
211 212
        req->status = NVME_INTERNAL_DEV_ERROR;
    }
213 214 215
    if (req->has_sg) {
        qemu_sglist_destroy(&req->qsg);
    }
216 217 218
    nvme_enqueue_req_completion(cq, req);
}

219 220 221 222 223 224 225 226 227 228 229
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;
}

C
Christoph Hellwig 已提交
230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252
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 aio_slba = slba << (data_shift - BDRV_SECTOR_BITS);
    uint32_t aio_nlb = nlb << (data_shift - BDRV_SECTOR_BITS);

    if (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, aio_slba, aio_nlb,
                                        BDRV_REQ_MAY_UNMAP, nvme_rw_cb, req);
    return NVME_NO_COMPLETE;
}

253 254 255 256 257 258 259 260 261 262 263
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;
264
    uint64_t data_size = (uint64_t)nlb << data_shift;
265
    uint64_t data_offset = slba << data_shift;
266
    int is_write = rw->opcode == NVME_CMD_WRITE ? 1 : 0;
267
    enum BlockAcctType acct = is_write ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ;
268 269

    if ((slba + nlb) > ns->id_ns.nsze) {
270
        block_acct_invalid(blk_get_stats(n->conf.blk), acct);
271 272
        return NVME_LBA_RANGE | NVME_DNR;
    }
273

274
    if (nvme_map_prp(&req->qsg, prp1, prp2, data_size, n)) {
275
        block_acct_invalid(blk_get_stats(n->conf.blk), acct);
276 277
        return NVME_INVALID_FIELD | NVME_DNR;
    }
278

279 280
    assert((nlb << data_shift) == req->qsg.size);

281
    req->has_sg = true;
282
    dma_acct_start(n->conf.blk, &req->acct, &req->qsg, acct);
283
    req->aiocb = is_write ?
284 285 286 287
        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);
288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303

    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 (nsid == 0 || nsid > n->num_namespaces) {
        return NVME_INVALID_NSID | NVME_DNR;
    }

    ns = &n->namespaces[nsid - 1];
    switch (cmd->opcode) {
    case NVME_CMD_FLUSH:
304
        return nvme_flush(n, ns, cmd, req);
C
Christoph Hellwig 已提交
305 306
    case NVME_CMD_WRITE_ZEROS:
        return nvme_write_zeros(n, ns, cmd, req);
307 308 309 310 311 312 313 314 315 316 317
    case NVME_CMD_WRITE:
    case NVME_CMD_READ:
        return nvme_rw(n, ns, cmd, req);
    default:
        return NVME_INVALID_OPCODE | NVME_DNR;
    }
}

static void nvme_free_sq(NvmeSQueue *sq, NvmeCtrl *n)
{
    n->sq[sq->sqid] = NULL;
318 319
    timer_del(sq->timer);
    timer_free(sq->timer);
320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341
    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 (!qid || nvme_check_sqid(n, qid)) {
        return NVME_INVALID_QID | NVME_DNR;
    }

    sq = n->sq[qid];
    while (!QTAILQ_EMPTY(&sq->out_req_list)) {
        req = QTAILQ_FIRST(&sq->out_req_list);
        assert(req->aiocb);
342
        blk_aio_cancel(req->aiocb);
343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372
    }
    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;
373
    sq->io_req = g_new(NvmeRequest, sq->size);
374 375 376 377 378 379 380

    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);
    }
381
    sq->timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, nvme_process_sq, sq);
382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402

    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);

    if (!cqid || nvme_check_cqid(n, cqid)) {
        return NVME_INVALID_CQID | NVME_DNR;
    }
403
    if (!sqid || !nvme_check_sqid(n, sqid)) {
404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422
        return NVME_INVALID_QID | NVME_DNR;
    }
    if (!qsize || qsize > NVME_CAP_MQES(n->bar.cap)) {
        return NVME_MAX_QSIZE_EXCEEDED | NVME_DNR;
    }
    if (!prp1 || prp1 & (n->page_size - 1)) {
        return NVME_INVALID_FIELD | NVME_DNR;
    }
    if (!(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;
423 424
    timer_del(cq->timer);
    timer_free(cq->timer);
425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463
    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 (!qid || nvme_check_cqid(n, qid)) {
        return NVME_INVALID_CQID | NVME_DNR;
    }

    cq = n->cq[qid];
    if (!QTAILQ_EMPTY(&cq->sq_list)) {
        return NVME_INVALID_QUEUE_DEL;
    }
    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)
{
    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);
    msix_vector_use(&n->parent_obj, cq->vector);
    n->cq[cqid] = cq;
464
    cq->timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, nvme_post_cqes, cq);
465 466 467 468 469 470 471 472 473 474 475 476
}

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);

477
    if (!cqid || !nvme_check_cqid(n, cqid)) {
478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498
        return NVME_INVALID_CQID | NVME_DNR;
    }
    if (!qsize || qsize > NVME_CAP_MQES(n->bar.cap)) {
        return NVME_MAX_QSIZE_EXCEEDED | NVME_DNR;
    }
    if (!prp1) {
        return NVME_INVALID_FIELD | NVME_DNR;
    }
    if (vector > n->num_queues) {
        return NVME_INVALID_IRQ_VECTOR | NVME_DNR;
    }
    if (!(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;
}

499 500 501 502 503 504 505 506 507 508
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);

    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)
509 510 511 512 513 514 515 516 517 518 519 520 521 522 523
{
    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);

    if (nsid == 0 || 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);
}

524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565
static uint16_t nvme_identify_nslist(NvmeCtrl *n, NvmeIdentify *c)
{
    static const int data_len = 4096;
    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;

    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 0x00:
        return nvme_identify_ns(n, c);
    case 0x01:
        return nvme_identify_ctrl(n, c);
    case 0x02:
        return nvme_identify_nslist(n, c);
    default:
        return NVME_INVALID_FIELD | NVME_DNR;
    }
}

566 567 568
static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
{
    uint32_t dw10 = le32_to_cpu(cmd->cdw10);
569
    uint32_t result;
570 571

    switch (dw10) {
572
    case NVME_VOLATILE_WRITE_CACHE:
573 574 575 576
        result = blk_enable_write_cache(n->conf.blk);
        break;
    case NVME_NUMBER_OF_QUEUES:
        result = cpu_to_le32((n->num_queues - 1) | ((n->num_queues - 1) << 16));
577
        break;
578 579 580
    default:
        return NVME_INVALID_FIELD | NVME_DNR;
    }
581 582

    req->cqe.result = result;
583 584 585 586 587 588
    return NVME_SUCCESS;
}

static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
{
    uint32_t dw10 = le32_to_cpu(cmd->cdw10);
589
    uint32_t dw11 = le32_to_cpu(cmd->cdw11);
590 591

    switch (dw10) {
592 593 594
    case NVME_VOLATILE_WRITE_CACHE:
        blk_set_enable_write_cache(n->conf.blk, dw11 & 1);
        break;
595
    case NVME_NUMBER_OF_QUEUES:
596 597
        req->cqe.result =
            cpu_to_le32((n->num_queues - 1) | ((n->num_queues - 1) << 16));
598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672
        break;
    default:
        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:
        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;
        pci_dma_read(&n->parent_obj, 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;

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

673
    blk_flush(n->conf.blk);
674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689
    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 (n->cq[0] || n->sq[0] || !n->bar.asq || !n->bar.acq ||
            n->bar.asq & (page_size - 1) || n->bar.acq & (page_size - 1) ||
            NVME_CC_MPS(n->bar.cc) < NVME_CAP_MPSMIN(n->bar.cap) ||
            NVME_CC_MPS(n->bar.cc) > NVME_CAP_MPSMAX(n->bar.cap) ||
            NVME_CC_IOCQES(n->bar.cc) < NVME_CTRL_CQES_MIN(n->id_ctrl.cqes) ||
            NVME_CC_IOCQES(n->bar.cc) > NVME_CTRL_CQES_MAX(n->id_ctrl.cqes) ||
            NVME_CC_IOSQES(n->bar.cc) < NVME_CTRL_SQES_MIN(n->id_ctrl.sqes) ||
            NVME_CC_IOSQES(n->bar.cc) > NVME_CTRL_SQES_MAX(n->id_ctrl.sqes) ||
G
Gonglei 已提交
690
            !NVME_AQA_ASQS(n->bar.aqa) || !NVME_AQA_ACQS(n->bar.aqa)) {
691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719
        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);

    return 0;
}

static void nvme_write_bar(NvmeCtrl *n, hwaddr offset, uint64_t data,
    unsigned size)
{
    switch (offset) {
    case 0xc:
        n->bar.intms |= data & 0xffffffff;
        n->bar.intmc = n->bar.intms;
        break;
    case 0x10:
        n->bar.intms &= ~(data & 0xffffffff);
        n->bar.intmc = n->bar.intms;
        break;
    case 0x14:
720 721 722 723 724 725 726
        /* 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;
        }

727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806
        if (NVME_CC_EN(data) && !NVME_CC_EN(n->bar.cc)) {
            n->bar.cc = data;
            if (nvme_start_ctrl(n)) {
                n->bar.csts = NVME_CSTS_FAILED;
            } else {
                n->bar.csts = NVME_CSTS_READY;
            }
        } else if (!NVME_CC_EN(data) && NVME_CC_EN(n->bar.cc)) {
            nvme_clear_ctrl(n);
            n->bar.csts &= ~NVME_CSTS_READY;
        }
        if (NVME_CC_SHN(data) && !(NVME_CC_SHN(n->bar.cc))) {
                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)) {
                n->bar.csts &= ~NVME_CSTS_SHST_COMPLETE;
                n->bar.cc = data;
        }
        break;
    case 0x24:
        n->bar.aqa = data & 0xffffffff;
        break;
    case 0x28:
        n->bar.asq = data;
        break;
    case 0x2c:
        n->bar.asq |= data << 32;
        break;
    case 0x30:
        n->bar.acq = data;
        break;
    case 0x34:
        n->bar.acq |= data << 32;
        break;
    default:
        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 (addr < sizeof(n->bar)) {
        memcpy(&val, ptr + addr, size);
    }
    return val;
}

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

    if (addr & ((1 << 2) - 1)) {
        return;
    }

    if (((addr - 0x1000) >> 2) & 1) {
        uint16_t new_head = val & 0xffff;
        int start_sqs;
        NvmeCQueue *cq;

        qid = (addr - (0x1000 + (1 << 2))) >> 3;
        if (nvme_check_cqid(n, qid)) {
            return;
        }

        cq = n->cq[qid];
        if (new_head >= cq->size) {
            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) {
807
                timer_mod(sq->timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + 500);
808
            }
809
            timer_mod(cq->timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + 500);
810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829
        }

        if (cq->tail != cq->head) {
            nvme_isr_notify(n, cq);
        }
    } else {
        uint16_t new_tail = val & 0xffff;
        NvmeSQueue *sq;

        qid = (addr - 0x1000) >> 3;
        if (nvme_check_sqid(n, qid)) {
            return;
        }

        sq = n->sq[qid];
        if (new_tail >= sq->size) {
            return;
        }

        sq->tail = new_tail;
830
        timer_mod(sq->timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + 500);
831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862
    }
}

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 if (addr >= 0x1000) {
        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 int nvme_init(PCIDevice *pci_dev)
{
    NvmeCtrl *n = NVME(pci_dev);
    NvmeIdCtrl *id = &n->id_ctrl;

    int i;
    int64_t bs_size;
    uint8_t *pci_conf;
K
Kevin Wolf 已提交
863
    Error *local_err = NULL;
864

865
    if (!n->conf.blk) {
866 867 868
        return -1;
    }

869
    bs_size = blk_getlength(n->conf.blk);
870
    if (bs_size < 0) {
871 872 873 874 875 876 877
        return -1;
    }

    blkconf_serial(&n->conf, &n->serial);
    if (!n->serial) {
        return -1;
    }
878
    blkconf_blocksizes(&n->conf);
K
Kevin Wolf 已提交
879 880 881 882 883 884
    blkconf_apply_backend_options(&n->conf, blk_is_read_only(n->conf.blk),
                                  false, &local_err);
    if (local_err) {
        error_report_err(local_err);
        return -1;
    }
885 886 887 888 889 890 891 892 893

    pci_conf = pci_dev->config;
    pci_conf[PCI_INTERRUPT_PIN] = 1;
    pci_config_set_prog_interface(pci_dev->config, 0x2);
    pci_config_set_class(pci_dev->config, PCI_CLASS_STORAGE_EXPRESS);
    pcie_endpoint_cap_init(&n->parent_obj, 0x80);

    n->num_namespaces = 1;
    n->num_queues = 64;
894
    n->reg_size = pow2ceil(0x1004 + 2 * (n->num_queues + 1) * 4);
895 896
    n->ns_size = bs_size / (uint64_t)n->num_namespaces;

897 898 899
    n->namespaces = g_new0(NvmeNamespace, n->num_namespaces);
    n->sq = g_new0(NvmeSQueue *, n->num_queues);
    n->cq = g_new0(NvmeCQueue *, n->num_queues);
900

901 902
    memory_region_init_io(&n->iomem, OBJECT(n), &nvme_mmio_ops, n,
                          "nvme", n->reg_size);
903 904 905
    pci_register_bar(&n->parent_obj, 0,
        PCI_BASE_ADDRESS_SPACE_MEMORY | PCI_BASE_ADDRESS_MEM_TYPE_64,
        &n->iomem);
906
    msix_init_exclusive_bar(&n->parent_obj, n->num_queues, 4, NULL);
907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922

    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->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);
C
Christoph Hellwig 已提交
923
    id->oncs = cpu_to_le16(NVME_ONCS_WRITE_ZEROS);
924 925 926
    id->psd[0].mp = cpu_to_le16(0x9c4);
    id->psd[0].enlat = cpu_to_le32(0x10);
    id->psd[0].exlat = cpu_to_le32(0x4);
927 928 929
    if (blk_enable_write_cache(n->conf.blk)) {
        id->vwc = 1;
    }
930 931 932 933 934 935 936

    n->bar.cap = 0;
    NVME_CAP_SET_MQES(n->bar.cap, 0x7ff);
    NVME_CAP_SET_CQR(n->bar.cap, 1);
    NVME_CAP_SET_AMS(n->bar.cap, 1);
    NVME_CAP_SET_TO(n->bar.cap, 0xf);
    NVME_CAP_SET_CSS(n->bar.cap, 1);
A
Anton Blanchard 已提交
937
    NVME_CAP_SET_MPSMAX(n->bar.cap, 4);
938

939
    n->bar.vs = 0x00010100;
940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990
    n->bar.intmc = n->bar.intms = 0;

    for (i = 0; i < n->num_namespaces; i++) {
        NvmeNamespace *ns = &n->namespaces[i];
        NvmeIdNs *id_ns = &ns->id_ns;
        id_ns->nsfeat = 0;
        id_ns->nlbaf = 0;
        id_ns->flbas = 0;
        id_ns->mc = 0;
        id_ns->dpc = 0;
        id_ns->dps = 0;
        id_ns->lbaf[0].ds = BDRV_SECTOR_BITS;
        id_ns->ncap  = id_ns->nuse = id_ns->nsze =
            cpu_to_le64(n->ns_size >>
                id_ns->lbaf[NVME_ID_NS_FLBAS_INDEX(ns->id_ns.flbas)].ds);
    }
    return 0;
}

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);
    msix_uninit_exclusive_bar(pci_dev);
}

static Property nvme_props[] = {
    DEFINE_BLOCK_PROPERTIES(NvmeCtrl, conf),
    DEFINE_PROP_STRING("serial", NvmeCtrl, serial),
    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->init = nvme_init;
    pc->exit = nvme_exit;
    pc->class_id = PCI_CLASS_STORAGE_EXPRESS;
    pc->vendor_id = PCI_VENDOR_ID_INTEL;
    pc->device_id = 0x5845;
C
Christoph Hellwig 已提交
991
    pc->revision = 2;
992 993
    pc->is_express = 1;

994
    set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
995 996 997 998 999
    dc->desc = "Non-Volatile Memory Express";
    dc->props = nvme_props;
    dc->vmsd = &nvme_vmstate;
}

1000
static void nvme_instance_init(Object *obj)
G
Gonglei 已提交
1001 1002 1003
{
    NvmeCtrl *s = NVME(obj);

1004 1005 1006
    device_add_bootindex_property(obj, &s->conf.bootindex,
                                  "bootindex", "/namespace@1,0",
                                  DEVICE(obj), &error_abort);
G
Gonglei 已提交
1007 1008
}

1009 1010 1011 1012 1013
static const TypeInfo nvme_info = {
    .name          = "nvme",
    .parent        = TYPE_PCI_DEVICE,
    .instance_size = sizeof(NvmeCtrl),
    .class_init    = nvme_class_init,
G
Gonglei 已提交
1014
    .instance_init = nvme_instance_init,
1015 1016 1017 1018 1019 1020 1021 1022
};

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

type_init(nvme_register_types)