amd_iommu.c 38.9 KB
Newer Older
D
David Kiarie 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23
/*
 * QEMU emulation of AMD IOMMU (AMD-Vi)
 *
 * Copyright (C) 2011 Eduard - Gabriel Munteanu
 * Copyright (C) 2015 David Kiarie, <davidkiarie4@gmail.com>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.

 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.

 * You should have received a copy of the GNU General Public License along
 * with this program; if not, see <http://www.gnu.org/licenses/>.
 *
 * Cache implementation inspired by hw/i386/intel_iommu.c
 */
#include "qemu/osdep.h"
#include "hw/i386/amd_iommu.h"
24
#include "qapi/error.h"
25
#include "qemu/error-report.h"
D
David Kiarie 已提交
26 27 28 29 30 31 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 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 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
#include "trace.h"

/* used AMD-Vi MMIO registers */
const char *amdvi_mmio_low[] = {
    "AMDVI_MMIO_DEVTAB_BASE",
    "AMDVI_MMIO_CMDBUF_BASE",
    "AMDVI_MMIO_EVTLOG_BASE",
    "AMDVI_MMIO_CONTROL",
    "AMDVI_MMIO_EXCL_BASE",
    "AMDVI_MMIO_EXCL_LIMIT",
    "AMDVI_MMIO_EXT_FEATURES",
    "AMDVI_MMIO_PPR_BASE",
    "UNHANDLED"
};
const char *amdvi_mmio_high[] = {
    "AMDVI_MMIO_COMMAND_HEAD",
    "AMDVI_MMIO_COMMAND_TAIL",
    "AMDVI_MMIO_EVTLOG_HEAD",
    "AMDVI_MMIO_EVTLOG_TAIL",
    "AMDVI_MMIO_STATUS",
    "AMDVI_MMIO_PPR_HEAD",
    "AMDVI_MMIO_PPR_TAIL",
    "UNHANDLED"
};

struct AMDVIAddressSpace {
    uint8_t bus_num;            /* bus number                           */
    uint8_t devfn;              /* device function                      */
    AMDVIState *iommu_state;    /* AMDVI - one per machine              */
    MemoryRegion iommu;         /* Device's address translation region  */
    MemoryRegion iommu_ir;      /* Device's interrupt remapping region  */
    AddressSpace as;            /* device's corresponding address space */
};

/* AMDVI cache entry */
typedef struct AMDVIIOTLBEntry {
    uint16_t domid;             /* assigned domain id  */
    uint16_t devid;             /* device owning entry */
    uint64_t perms;             /* access permissions  */
    uint64_t translated_addr;   /* translated address  */
    uint64_t page_mask;         /* physical page size  */
} AMDVIIOTLBEntry;

/* configure MMIO registers at startup/reset */
static void amdvi_set_quad(AMDVIState *s, hwaddr addr, uint64_t val,
                           uint64_t romask, uint64_t w1cmask)
{
    stq_le_p(&s->mmior[addr], val);
    stq_le_p(&s->romask[addr], romask);
    stq_le_p(&s->w1cmask[addr], w1cmask);
}

static uint16_t amdvi_readw(AMDVIState *s, hwaddr addr)
{
    return lduw_le_p(&s->mmior[addr]);
}

static uint32_t amdvi_readl(AMDVIState *s, hwaddr addr)
{
    return ldl_le_p(&s->mmior[addr]);
}

static uint64_t amdvi_readq(AMDVIState *s, hwaddr addr)
{
    return ldq_le_p(&s->mmior[addr]);
}

/* internal write */
static void amdvi_writeq_raw(AMDVIState *s, uint64_t val, hwaddr addr)
{
    stq_le_p(&s->mmior[addr], val);
}

/* external write */
static void amdvi_writew(AMDVIState *s, hwaddr addr, uint16_t val)
{
    uint16_t romask = lduw_le_p(&s->romask[addr]);
    uint16_t w1cmask = lduw_le_p(&s->w1cmask[addr]);
    uint16_t oldval = lduw_le_p(&s->mmior[addr]);
    stw_le_p(&s->mmior[addr],
            ((oldval & romask) | (val & ~romask)) & ~(val & w1cmask));
}

static void amdvi_writel(AMDVIState *s, hwaddr addr, uint32_t val)
{
    uint32_t romask = ldl_le_p(&s->romask[addr]);
    uint32_t w1cmask = ldl_le_p(&s->w1cmask[addr]);
    uint32_t oldval = ldl_le_p(&s->mmior[addr]);
    stl_le_p(&s->mmior[addr],
            ((oldval & romask) | (val & ~romask)) & ~(val & w1cmask));
}

static void amdvi_writeq(AMDVIState *s, hwaddr addr, uint64_t val)
{
    uint64_t romask = ldq_le_p(&s->romask[addr]);
    uint64_t w1cmask = ldq_le_p(&s->w1cmask[addr]);
    uint32_t oldval = ldq_le_p(&s->mmior[addr]);
    stq_le_p(&s->mmior[addr],
            ((oldval & romask) | (val & ~romask)) & ~(val & w1cmask));
}

/* OR a 64-bit register with a 64-bit value */
static bool amdvi_test_mask(AMDVIState *s, hwaddr addr, uint64_t val)
{
    return amdvi_readq(s, addr) | val;
}

/* OR a 64-bit register with a 64-bit value storing result in the register */
static void amdvi_assign_orq(AMDVIState *s, hwaddr addr, uint64_t val)
{
    amdvi_writeq_raw(s, addr, amdvi_readq(s, addr) | val);
}

/* AND a 64-bit register with a 64-bit value storing result in the register */
static void amdvi_assign_andq(AMDVIState *s, hwaddr addr, uint64_t val)
{
   amdvi_writeq_raw(s, addr, amdvi_readq(s, addr) & val);
}

static void amdvi_generate_msi_interrupt(AMDVIState *s)
{
147 148 149 150
    MSIMessage msg = {};
    MemTxAttrs attrs = {
        .requester_id = pci_requester_id(&s->pci.dev)
    };
D
David Kiarie 已提交
151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188

    if (msi_enabled(&s->pci.dev)) {
        msg = msi_get_message(&s->pci.dev, 0);
        address_space_stl_le(&address_space_memory, msg.address, msg.data,
                             attrs, NULL);
    }
}

static void amdvi_log_event(AMDVIState *s, uint64_t *evt)
{
    /* event logging not enabled */
    if (!s->evtlog_enabled || amdvi_test_mask(s, AMDVI_MMIO_STATUS,
        AMDVI_MMIO_STATUS_EVT_OVF)) {
        return;
    }

    /* event log buffer full */
    if (s->evtlog_tail >= s->evtlog_len) {
        amdvi_assign_orq(s, AMDVI_MMIO_STATUS, AMDVI_MMIO_STATUS_EVT_OVF);
        /* generate interrupt */
        amdvi_generate_msi_interrupt(s);
        return;
    }

    if (dma_memory_write(&address_space_memory, s->evtlog + s->evtlog_tail,
        &evt, AMDVI_EVENT_LEN)) {
        trace_amdvi_evntlog_fail(s->evtlog, s->evtlog_tail);
    }

    s->evtlog_tail += AMDVI_EVENT_LEN;
    amdvi_assign_orq(s, AMDVI_MMIO_STATUS, AMDVI_MMIO_STATUS_COMP_INT);
    amdvi_generate_msi_interrupt(s);
}

static void amdvi_setevent_bits(uint64_t *buffer, uint64_t value, int start,
                                int length)
{
    int index = start / 64, bitpos = start % 64;
189
    uint64_t mask = MAKE_64BIT_MASK(start, length);
D
David Kiarie 已提交
190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336
    buffer[index] &= ~mask;
    buffer[index] |= (value << bitpos) & mask;
}
/*
 * AMDVi event structure
 *    0:15   -> DeviceID
 *    55:63  -> event type + miscellaneous info
 *    63:127 -> related address
 */
static void amdvi_encode_event(uint64_t *evt, uint16_t devid, uint64_t addr,
                               uint16_t info)
{
    amdvi_setevent_bits(evt, devid, 0, 16);
    amdvi_setevent_bits(evt, info, 55, 8);
    amdvi_setevent_bits(evt, addr, 63, 64);
}
/* log an error encountered during a page walk
 *
 * @addr: virtual address in translation request
 */
static void amdvi_page_fault(AMDVIState *s, uint16_t devid,
                             hwaddr addr, uint16_t info)
{
    uint64_t evt[4];

    info |= AMDVI_EVENT_IOPF_I | AMDVI_EVENT_IOPF;
    amdvi_encode_event(evt, devid, addr, info);
    amdvi_log_event(s, evt);
    pci_word_test_and_set_mask(s->pci.dev.config + PCI_STATUS,
            PCI_STATUS_SIG_TARGET_ABORT);
}
/*
 * log a master abort accessing device table
 *  @devtab : address of device table entry
 *  @info : error flags
 */
static void amdvi_log_devtab_error(AMDVIState *s, uint16_t devid,
                                   hwaddr devtab, uint16_t info)
{
    uint64_t evt[4];

    info |= AMDVI_EVENT_DEV_TAB_HW_ERROR;

    amdvi_encode_event(evt, devid, devtab, info);
    amdvi_log_event(s, evt);
    pci_word_test_and_set_mask(s->pci.dev.config + PCI_STATUS,
            PCI_STATUS_SIG_TARGET_ABORT);
}
/* log an event trying to access command buffer
 *   @addr : address that couldn't be accessed
 */
static void amdvi_log_command_error(AMDVIState *s, hwaddr addr)
{
    uint64_t evt[4], info = AMDVI_EVENT_COMMAND_HW_ERROR;

    amdvi_encode_event(evt, 0, addr, info);
    amdvi_log_event(s, evt);
    pci_word_test_and_set_mask(s->pci.dev.config + PCI_STATUS,
            PCI_STATUS_SIG_TARGET_ABORT);
}
/* log an illegal comand event
 *   @addr : address of illegal command
 */
static void amdvi_log_illegalcom_error(AMDVIState *s, uint16_t info,
                                       hwaddr addr)
{
    uint64_t evt[4];

    info |= AMDVI_EVENT_ILLEGAL_COMMAND_ERROR;
    amdvi_encode_event(evt, 0, addr, info);
    amdvi_log_event(s, evt);
}
/* log an error accessing device table
 *
 *  @devid : device owning the table entry
 *  @devtab : address of device table entry
 *  @info : error flags
 */
static void amdvi_log_illegaldevtab_error(AMDVIState *s, uint16_t devid,
                                          hwaddr addr, uint16_t info)
{
    uint64_t evt[4];

    info |= AMDVI_EVENT_ILLEGAL_DEVTAB_ENTRY;
    amdvi_encode_event(evt, devid, addr, info);
    amdvi_log_event(s, evt);
}
/* log an error accessing a PTE entry
 * @addr : address that couldn't be accessed
 */
static void amdvi_log_pagetab_error(AMDVIState *s, uint16_t devid,
                                    hwaddr addr, uint16_t info)
{
    uint64_t evt[4];

    info |= AMDVI_EVENT_PAGE_TAB_HW_ERROR;
    amdvi_encode_event(evt, devid, addr, info);
    amdvi_log_event(s, evt);
    pci_word_test_and_set_mask(s->pci.dev.config + PCI_STATUS,
             PCI_STATUS_SIG_TARGET_ABORT);
}

static gboolean amdvi_uint64_equal(gconstpointer v1, gconstpointer v2)
{
    return *((const uint64_t *)v1) == *((const uint64_t *)v2);
}

static guint amdvi_uint64_hash(gconstpointer v)
{
    return (guint)*(const uint64_t *)v;
}

static AMDVIIOTLBEntry *amdvi_iotlb_lookup(AMDVIState *s, hwaddr addr,
                                           uint64_t devid)
{
    uint64_t key = (addr >> AMDVI_PAGE_SHIFT_4K) |
                   ((uint64_t)(devid) << AMDVI_DEVID_SHIFT);
    return g_hash_table_lookup(s->iotlb, &key);
}

static void amdvi_iotlb_reset(AMDVIState *s)
{
    assert(s->iotlb);
    trace_amdvi_iotlb_reset();
    g_hash_table_remove_all(s->iotlb);
}

static gboolean amdvi_iotlb_remove_by_devid(gpointer key, gpointer value,
                                            gpointer user_data)
{
    AMDVIIOTLBEntry *entry = (AMDVIIOTLBEntry *)value;
    uint16_t devid = *(uint16_t *)user_data;
    return entry->devid == devid;
}

static void amdvi_iotlb_remove_page(AMDVIState *s, hwaddr addr,
                                    uint64_t devid)
{
    uint64_t key = (addr >> AMDVI_PAGE_SHIFT_4K) |
                   ((uint64_t)(devid) << AMDVI_DEVID_SHIFT);
    g_hash_table_remove(s->iotlb, &key);
}

static void amdvi_update_iotlb(AMDVIState *s, uint16_t devid,
                               uint64_t gpa, IOMMUTLBEntry to_cache,
                               uint16_t domid)
{
337 338
    AMDVIIOTLBEntry *entry = g_new(AMDVIIOTLBEntry, 1);
    uint64_t *key = g_new(uint64_t, 1);
D
David Kiarie 已提交
339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565
    uint64_t gfn = gpa >> AMDVI_PAGE_SHIFT_4K;

    /* don't cache erroneous translations */
    if (to_cache.perm != IOMMU_NONE) {
        trace_amdvi_cache_update(domid, PCI_BUS_NUM(devid), PCI_SLOT(devid),
                PCI_FUNC(devid), gpa, to_cache.translated_addr);

        if (g_hash_table_size(s->iotlb) >= AMDVI_IOTLB_MAX_SIZE) {
            amdvi_iotlb_reset(s);
        }

        entry->domid = domid;
        entry->perms = to_cache.perm;
        entry->translated_addr = to_cache.translated_addr;
        entry->page_mask = to_cache.addr_mask;
        *key = gfn | ((uint64_t)(devid) << AMDVI_DEVID_SHIFT);
        g_hash_table_replace(s->iotlb, key, entry);
    }
}

static void amdvi_completion_wait(AMDVIState *s, uint64_t *cmd)
{
    /* pad the last 3 bits */
    hwaddr addr = cpu_to_le64(extract64(cmd[0], 3, 49)) << 3;
    uint64_t data = cpu_to_le64(cmd[1]);

    if (extract64(cmd[0], 51, 8)) {
        amdvi_log_illegalcom_error(s, extract64(cmd[0], 60, 4),
                                   s->cmdbuf + s->cmdbuf_head);
    }
    if (extract64(cmd[0], 0, 1)) {
        if (dma_memory_write(&address_space_memory, addr, &data,
            AMDVI_COMPLETION_DATA_SIZE)) {
            trace_amdvi_completion_wait_fail(addr);
        }
    }
    /* set completion interrupt */
    if (extract64(cmd[0], 1, 1)) {
        amdvi_test_mask(s, AMDVI_MMIO_STATUS, AMDVI_MMIO_STATUS_COMP_INT);
        /* generate interrupt */
        amdvi_generate_msi_interrupt(s);
    }
    trace_amdvi_completion_wait(addr, data);
}

/* log error without aborting since linux seems to be using reserved bits */
static void amdvi_inval_devtab_entry(AMDVIState *s, uint64_t *cmd)
{
    uint16_t devid = cpu_to_le16((uint16_t)extract64(cmd[0], 0, 16));

    /* This command should invalidate internal caches of which there isn't */
    if (extract64(cmd[0], 15, 16) || cmd[1]) {
        amdvi_log_illegalcom_error(s, extract64(cmd[0], 60, 4),
                                   s->cmdbuf + s->cmdbuf_head);
    }
    trace_amdvi_devtab_inval(PCI_BUS_NUM(devid), PCI_SLOT(devid),
                             PCI_FUNC(devid));
}

static void amdvi_complete_ppr(AMDVIState *s, uint64_t *cmd)
{
    if (extract64(cmd[0], 15, 16) ||  extract64(cmd[0], 19, 8) ||
        extract64(cmd[1], 0, 2) || extract64(cmd[1], 3, 29)
        || extract64(cmd[1], 47, 16)) {
        amdvi_log_illegalcom_error(s, extract64(cmd[0], 60, 4),
                                   s->cmdbuf + s->cmdbuf_head);
    }
    trace_amdvi_ppr_exec();
}

static void amdvi_inval_all(AMDVIState *s, uint64_t *cmd)
{
    if (extract64(cmd[0], 0, 60) || cmd[1]) {
        amdvi_log_illegalcom_error(s, extract64(cmd[0], 60, 4),
                                   s->cmdbuf + s->cmdbuf_head);
    }

    amdvi_iotlb_reset(s);
    trace_amdvi_all_inval();
}

static gboolean amdvi_iotlb_remove_by_domid(gpointer key, gpointer value,
                                            gpointer user_data)
{
    AMDVIIOTLBEntry *entry = (AMDVIIOTLBEntry *)value;
    uint16_t domid = *(uint16_t *)user_data;
    return entry->domid == domid;
}

/* we don't have devid - we can't remove pages by address */
static void amdvi_inval_pages(AMDVIState *s, uint64_t *cmd)
{
    uint16_t domid = cpu_to_le16((uint16_t)extract64(cmd[0], 32, 16));

    if (extract64(cmd[0], 20, 12) || extract64(cmd[0], 16, 12) ||
        extract64(cmd[0], 3, 10)) {
        amdvi_log_illegalcom_error(s, extract64(cmd[0], 60, 4),
                                   s->cmdbuf + s->cmdbuf_head);
    }

    g_hash_table_foreach_remove(s->iotlb, amdvi_iotlb_remove_by_domid,
                                &domid);
    trace_amdvi_pages_inval(domid);
}

static void amdvi_prefetch_pages(AMDVIState *s, uint64_t *cmd)
{
    if (extract64(cmd[0], 16, 8) || extract64(cmd[0], 20, 8) ||
        extract64(cmd[1], 1, 1) || extract64(cmd[1], 3, 1) ||
        extract64(cmd[1], 5, 7)) {
        amdvi_log_illegalcom_error(s, extract64(cmd[0], 60, 4),
                                   s->cmdbuf + s->cmdbuf_head);
    }

    trace_amdvi_prefetch_pages();
}

static void amdvi_inval_inttable(AMDVIState *s, uint64_t *cmd)
{
    if (extract64(cmd[0], 16, 16) || cmd[1]) {
        amdvi_log_illegalcom_error(s, extract64(cmd[0], 60, 4),
                                   s->cmdbuf + s->cmdbuf_head);
        return;
    }

    trace_amdvi_intr_inval();
}

/* FIXME: Try to work with the specified size instead of all the pages
 * when the S bit is on
 */
static void iommu_inval_iotlb(AMDVIState *s, uint64_t *cmd)
{

    uint16_t devid = extract64(cmd[0], 0, 16);
    if (extract64(cmd[1], 1, 1) || extract64(cmd[1], 3, 9)) {
        amdvi_log_illegalcom_error(s, extract64(cmd[0], 60, 4),
                                   s->cmdbuf + s->cmdbuf_head);
        return;
    }

    if (extract64(cmd[1], 0, 1)) {
        g_hash_table_foreach_remove(s->iotlb, amdvi_iotlb_remove_by_devid,
                                    &devid);
    } else {
        amdvi_iotlb_remove_page(s, cpu_to_le64(extract64(cmd[1], 12, 52)) << 12,
                                cpu_to_le16(extract64(cmd[1], 0, 16)));
    }
    trace_amdvi_iotlb_inval();
}

/* not honouring reserved bits is regarded as an illegal command */
static void amdvi_cmdbuf_exec(AMDVIState *s)
{
    uint64_t cmd[2];

    if (dma_memory_read(&address_space_memory, s->cmdbuf + s->cmdbuf_head,
        cmd, AMDVI_COMMAND_SIZE)) {
        trace_amdvi_command_read_fail(s->cmdbuf, s->cmdbuf_head);
        amdvi_log_command_error(s, s->cmdbuf + s->cmdbuf_head);
        return;
    }

    switch (extract64(cmd[0], 60, 4)) {
    case AMDVI_CMD_COMPLETION_WAIT:
        amdvi_completion_wait(s, cmd);
        break;
    case AMDVI_CMD_INVAL_DEVTAB_ENTRY:
        amdvi_inval_devtab_entry(s, cmd);
        break;
    case AMDVI_CMD_INVAL_AMDVI_PAGES:
        amdvi_inval_pages(s, cmd);
        break;
    case AMDVI_CMD_INVAL_IOTLB_PAGES:
        iommu_inval_iotlb(s, cmd);
        break;
    case AMDVI_CMD_INVAL_INTR_TABLE:
        amdvi_inval_inttable(s, cmd);
        break;
    case AMDVI_CMD_PREFETCH_AMDVI_PAGES:
        amdvi_prefetch_pages(s, cmd);
        break;
    case AMDVI_CMD_COMPLETE_PPR_REQUEST:
        amdvi_complete_ppr(s, cmd);
        break;
    case AMDVI_CMD_INVAL_AMDVI_ALL:
        amdvi_inval_all(s, cmd);
        break;
    default:
        trace_amdvi_unhandled_command(extract64(cmd[1], 60, 4));
        /* log illegal command */
        amdvi_log_illegalcom_error(s, extract64(cmd[1], 60, 4),
                                   s->cmdbuf + s->cmdbuf_head);
    }
}

static void amdvi_cmdbuf_run(AMDVIState *s)
{
    if (!s->cmdbuf_enabled) {
        trace_amdvi_command_error(amdvi_readq(s, AMDVI_MMIO_CONTROL));
        return;
    }

    /* check if there is work to do. */
    while (s->cmdbuf_head != s->cmdbuf_tail) {
        trace_amdvi_command_exec(s->cmdbuf_head, s->cmdbuf_tail, s->cmdbuf);
        amdvi_cmdbuf_exec(s);
        s->cmdbuf_head += AMDVI_COMMAND_SIZE;
        amdvi_writeq_raw(s, s->cmdbuf_head, AMDVI_MMIO_COMMAND_HEAD);

        /* wrap head pointer */
        if (s->cmdbuf_head >= s->cmdbuf_len * AMDVI_COMMAND_SIZE) {
            s->cmdbuf_head = 0;
        }
    }
}

static void amdvi_mmio_trace(hwaddr addr, unsigned size)
{
    uint8_t index = (addr & ~0x2000) / 8;

    if ((addr & 0x2000)) {
        /* high table */
        index = index >= AMDVI_MMIO_REGS_HIGH ? AMDVI_MMIO_REGS_HIGH : index;
        trace_amdvi_mmio_read(amdvi_mmio_high[index], addr, size, addr & ~0x07);
    } else {
        index = index >= AMDVI_MMIO_REGS_LOW ? AMDVI_MMIO_REGS_LOW : index;
566
        trace_amdvi_mmio_read(amdvi_mmio_low[index], addr, size, addr & ~0x07);
D
David Kiarie 已提交
567 568 569 570 571 572 573 574 575
    }
}

static uint64_t amdvi_mmio_read(void *opaque, hwaddr addr, unsigned size)
{
    AMDVIState *s = opaque;

    uint64_t val = -1;
    if (addr + size > AMDVI_MMIO_SIZE) {
576
        trace_amdvi_mmio_read_invalid(AMDVI_MMIO_SIZE, addr, size);
D
David Kiarie 已提交
577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990
        return (uint64_t)-1;
    }

    if (size == 2) {
        val = amdvi_readw(s, addr);
    } else if (size == 4) {
        val = amdvi_readl(s, addr);
    } else if (size == 8) {
        val = amdvi_readq(s, addr);
    }
    amdvi_mmio_trace(addr, size);

    return val;
}

static void amdvi_handle_control_write(AMDVIState *s)
{
    unsigned long control = amdvi_readq(s, AMDVI_MMIO_CONTROL);
    s->enabled = !!(control & AMDVI_MMIO_CONTROL_AMDVIEN);

    s->ats_enabled = !!(control & AMDVI_MMIO_CONTROL_HTTUNEN);
    s->evtlog_enabled = s->enabled && !!(control &
                        AMDVI_MMIO_CONTROL_EVENTLOGEN);

    s->evtlog_intr = !!(control & AMDVI_MMIO_CONTROL_EVENTINTEN);
    s->completion_wait_intr = !!(control & AMDVI_MMIO_CONTROL_COMWAITINTEN);
    s->cmdbuf_enabled = s->enabled && !!(control &
                        AMDVI_MMIO_CONTROL_CMDBUFLEN);

    /* update the flags depending on the control register */
    if (s->cmdbuf_enabled) {
        amdvi_assign_orq(s, AMDVI_MMIO_STATUS, AMDVI_MMIO_STATUS_CMDBUF_RUN);
    } else {
        amdvi_assign_andq(s, AMDVI_MMIO_STATUS, ~AMDVI_MMIO_STATUS_CMDBUF_RUN);
    }
    if (s->evtlog_enabled) {
        amdvi_assign_orq(s, AMDVI_MMIO_STATUS, AMDVI_MMIO_STATUS_EVT_RUN);
    } else {
        amdvi_assign_andq(s, AMDVI_MMIO_STATUS, ~AMDVI_MMIO_STATUS_EVT_RUN);
    }

    trace_amdvi_control_status(control);
    amdvi_cmdbuf_run(s);
}

static inline void amdvi_handle_devtab_write(AMDVIState *s)

{
    uint64_t val = amdvi_readq(s, AMDVI_MMIO_DEVICE_TABLE);
    s->devtab = (val & AMDVI_MMIO_DEVTAB_BASE_MASK);

    /* set device table length */
    s->devtab_len = ((val & AMDVI_MMIO_DEVTAB_SIZE_MASK) + 1 *
                    (AMDVI_MMIO_DEVTAB_SIZE_UNIT /
                     AMDVI_MMIO_DEVTAB_ENTRY_SIZE));
}

static inline void amdvi_handle_cmdhead_write(AMDVIState *s)
{
    s->cmdbuf_head = amdvi_readq(s, AMDVI_MMIO_COMMAND_HEAD)
                     & AMDVI_MMIO_CMDBUF_HEAD_MASK;
    amdvi_cmdbuf_run(s);
}

static inline void amdvi_handle_cmdbase_write(AMDVIState *s)
{
    s->cmdbuf = amdvi_readq(s, AMDVI_MMIO_COMMAND_BASE)
                & AMDVI_MMIO_CMDBUF_BASE_MASK;
    s->cmdbuf_len = 1UL << (amdvi_readq(s, AMDVI_MMIO_CMDBUF_SIZE_BYTE)
                    & AMDVI_MMIO_CMDBUF_SIZE_MASK);
    s->cmdbuf_head = s->cmdbuf_tail = 0;
}

static inline void amdvi_handle_cmdtail_write(AMDVIState *s)
{
    s->cmdbuf_tail = amdvi_readq(s, AMDVI_MMIO_COMMAND_TAIL)
                     & AMDVI_MMIO_CMDBUF_TAIL_MASK;
    amdvi_cmdbuf_run(s);
}

static inline void amdvi_handle_excllim_write(AMDVIState *s)
{
    uint64_t val = amdvi_readq(s, AMDVI_MMIO_EXCL_LIMIT);
    s->excl_limit = (val & AMDVI_MMIO_EXCL_LIMIT_MASK) |
                    AMDVI_MMIO_EXCL_LIMIT_LOW;
}

static inline void amdvi_handle_evtbase_write(AMDVIState *s)
{
    uint64_t val = amdvi_readq(s, AMDVI_MMIO_EVENT_BASE);
    s->evtlog = val & AMDVI_MMIO_EVTLOG_BASE_MASK;
    s->evtlog_len = 1UL << (amdvi_readq(s, AMDVI_MMIO_EVTLOG_SIZE_BYTE)
                    & AMDVI_MMIO_EVTLOG_SIZE_MASK);
}

static inline void amdvi_handle_evttail_write(AMDVIState *s)
{
    uint64_t val = amdvi_readq(s, AMDVI_MMIO_EVENT_TAIL);
    s->evtlog_tail = val & AMDVI_MMIO_EVTLOG_TAIL_MASK;
}

static inline void amdvi_handle_evthead_write(AMDVIState *s)
{
    uint64_t val = amdvi_readq(s, AMDVI_MMIO_EVENT_HEAD);
    s->evtlog_head = val & AMDVI_MMIO_EVTLOG_HEAD_MASK;
}

static inline void amdvi_handle_pprbase_write(AMDVIState *s)
{
    uint64_t val = amdvi_readq(s, AMDVI_MMIO_PPR_BASE);
    s->ppr_log = val & AMDVI_MMIO_PPRLOG_BASE_MASK;
    s->pprlog_len = 1UL << (amdvi_readq(s, AMDVI_MMIO_PPRLOG_SIZE_BYTE)
                    & AMDVI_MMIO_PPRLOG_SIZE_MASK);
}

static inline void amdvi_handle_pprhead_write(AMDVIState *s)
{
    uint64_t val = amdvi_readq(s, AMDVI_MMIO_PPR_HEAD);
    s->pprlog_head = val & AMDVI_MMIO_PPRLOG_HEAD_MASK;
}

static inline void amdvi_handle_pprtail_write(AMDVIState *s)
{
    uint64_t val = amdvi_readq(s, AMDVI_MMIO_PPR_TAIL);
    s->pprlog_tail = val & AMDVI_MMIO_PPRLOG_TAIL_MASK;
}

/* FIXME: something might go wrong if System Software writes in chunks
 * of one byte but linux writes in chunks of 4 bytes so currently it
 * works correctly with linux but will definitely be busted if software
 * reads/writes 8 bytes
 */
static void amdvi_mmio_reg_write(AMDVIState *s, unsigned size, uint64_t val,
                                 hwaddr addr)
{
    if (size == 2) {
        amdvi_writew(s, addr, val);
    } else if (size == 4) {
        amdvi_writel(s, addr, val);
    } else if (size == 8) {
        amdvi_writeq(s, addr, val);
    }
}

static void amdvi_mmio_write(void *opaque, hwaddr addr, uint64_t val,
                             unsigned size)
{
    AMDVIState *s = opaque;
    unsigned long offset = addr & 0x07;

    if (addr + size > AMDVI_MMIO_SIZE) {
        trace_amdvi_mmio_write("error: addr outside region: max ",
                (uint64_t)AMDVI_MMIO_SIZE, size, val, offset);
        return;
    }

    amdvi_mmio_trace(addr, size);
    switch (addr & ~0x07) {
    case AMDVI_MMIO_CONTROL:
        amdvi_mmio_reg_write(s, size, val, addr);
        amdvi_handle_control_write(s);
        break;
    case AMDVI_MMIO_DEVICE_TABLE:
        amdvi_mmio_reg_write(s, size, val, addr);
       /*  set device table address
        *   This also suffers from inability to tell whether software
        *   is done writing
        */
        if (offset || (size == 8)) {
            amdvi_handle_devtab_write(s);
        }
        break;
    case AMDVI_MMIO_COMMAND_HEAD:
        amdvi_mmio_reg_write(s, size, val, addr);
        amdvi_handle_cmdhead_write(s);
        break;
    case AMDVI_MMIO_COMMAND_BASE:
        amdvi_mmio_reg_write(s, size, val, addr);
        /* FIXME - make sure System Software has finished writing incase
         * it writes in chucks less than 8 bytes in a robust way.As for
         * now, this hacks works for the linux driver
         */
        if (offset || (size == 8)) {
            amdvi_handle_cmdbase_write(s);
        }
        break;
    case AMDVI_MMIO_COMMAND_TAIL:
        amdvi_mmio_reg_write(s, size, val, addr);
        amdvi_handle_cmdtail_write(s);
        break;
    case AMDVI_MMIO_EVENT_BASE:
        amdvi_mmio_reg_write(s, size, val, addr);
        amdvi_handle_evtbase_write(s);
        break;
    case AMDVI_MMIO_EVENT_HEAD:
        amdvi_mmio_reg_write(s, size, val, addr);
        amdvi_handle_evthead_write(s);
        break;
    case AMDVI_MMIO_EVENT_TAIL:
        amdvi_mmio_reg_write(s, size, val, addr);
        amdvi_handle_evttail_write(s);
        break;
    case AMDVI_MMIO_EXCL_LIMIT:
        amdvi_mmio_reg_write(s, size, val, addr);
        amdvi_handle_excllim_write(s);
        break;
        /* PPR log base - unused for now */
    case AMDVI_MMIO_PPR_BASE:
        amdvi_mmio_reg_write(s, size, val, addr);
        amdvi_handle_pprbase_write(s);
        break;
        /* PPR log head - also unused for now */
    case AMDVI_MMIO_PPR_HEAD:
        amdvi_mmio_reg_write(s, size, val, addr);
        amdvi_handle_pprhead_write(s);
        break;
        /* PPR log tail - unused for now */
    case AMDVI_MMIO_PPR_TAIL:
        amdvi_mmio_reg_write(s, size, val, addr);
        amdvi_handle_pprtail_write(s);
        break;
    }
}

static inline uint64_t amdvi_get_perms(uint64_t entry)
{
    return (entry & (AMDVI_DEV_PERM_READ | AMDVI_DEV_PERM_WRITE)) >>
           AMDVI_DEV_PERM_SHIFT;
}

/* a valid entry should have V = 1 and reserved bits honoured */
static bool amdvi_validate_dte(AMDVIState *s, uint16_t devid,
                               uint64_t *dte)
{
    if ((dte[0] & AMDVI_DTE_LOWER_QUAD_RESERVED)
        || (dte[1] & AMDVI_DTE_MIDDLE_QUAD_RESERVED)
        || (dte[2] & AMDVI_DTE_UPPER_QUAD_RESERVED) || dte[3]) {
        amdvi_log_illegaldevtab_error(s, devid,
                                      s->devtab +
                                      devid * AMDVI_DEVTAB_ENTRY_SIZE, 0);
        return false;
    }

    return dte[0] & AMDVI_DEV_VALID;
}

/* get a device table entry given the devid */
static bool amdvi_get_dte(AMDVIState *s, int devid, uint64_t *entry)
{
    uint32_t offset = devid * AMDVI_DEVTAB_ENTRY_SIZE;

    if (dma_memory_read(&address_space_memory, s->devtab + offset, entry,
        AMDVI_DEVTAB_ENTRY_SIZE)) {
        trace_amdvi_dte_get_fail(s->devtab, offset);
        /* log error accessing dte */
        amdvi_log_devtab_error(s, devid, s->devtab + offset, 0);
        return false;
    }

    *entry = le64_to_cpu(*entry);
    if (!amdvi_validate_dte(s, devid, entry)) {
        trace_amdvi_invalid_dte(entry[0]);
        return false;
    }

    return true;
}

/* get pte translation mode */
static inline uint8_t get_pte_translation_mode(uint64_t pte)
{
    return (pte >> AMDVI_DEV_MODE_RSHIFT) & AMDVI_DEV_MODE_MASK;
}

static inline uint64_t pte_override_page_mask(uint64_t pte)
{
    uint8_t page_mask = 12;
    uint64_t addr = (pte & AMDVI_DEV_PT_ROOT_MASK) ^ AMDVI_DEV_PT_ROOT_MASK;
    /* find the first zero bit */
    while (addr & 1) {
        page_mask++;
        addr = addr >> 1;
    }

    return ~((1ULL << page_mask) - 1);
}

static inline uint64_t pte_get_page_mask(uint64_t oldlevel)
{
    return ~((1UL << ((oldlevel * 9) + 3)) - 1);
}

static inline uint64_t amdvi_get_pte_entry(AMDVIState *s, uint64_t pte_addr,
                                          uint16_t devid)
{
    uint64_t pte;

    if (dma_memory_read(&address_space_memory, pte_addr, &pte, sizeof(pte))) {
        trace_amdvi_get_pte_hwerror(pte_addr);
        amdvi_log_pagetab_error(s, devid, pte_addr, 0);
        pte = 0;
        return pte;
    }

    pte = le64_to_cpu(pte);
    return pte;
}

static void amdvi_page_walk(AMDVIAddressSpace *as, uint64_t *dte,
                            IOMMUTLBEntry *ret, unsigned perms,
                            hwaddr addr)
{
    unsigned level, present, pte_perms, oldlevel;
    uint64_t pte = dte[0], pte_addr, page_mask;

    /* make sure the DTE has TV = 1 */
    if (pte & AMDVI_DEV_TRANSLATION_VALID) {
        level = get_pte_translation_mode(pte);
        if (level >= 7) {
            trace_amdvi_mode_invalid(level, addr);
            return;
        }
        if (level == 0) {
            goto no_remap;
        }

        /* we are at the leaf page table or page table encodes a huge page */
        while (level > 0) {
            pte_perms = amdvi_get_perms(pte);
            present = pte & 1;
            if (!present || perms != (perms & pte_perms)) {
                amdvi_page_fault(as->iommu_state, as->devfn, addr, perms);
                trace_amdvi_page_fault(addr);
                return;
            }

            /* go to the next lower level */
            pte_addr = pte & AMDVI_DEV_PT_ROOT_MASK;
            /* add offset and load pte */
            pte_addr += ((addr >> (3 + 9 * level)) & 0x1FF) << 3;
            pte = amdvi_get_pte_entry(as->iommu_state, pte_addr, as->devfn);
            if (!pte) {
                return;
            }
            oldlevel = level;
            level = get_pte_translation_mode(pte);
            if (level == 0x7) {
                break;
            }
        }

        if (level == 0x7) {
            page_mask = pte_override_page_mask(pte);
        } else {
            page_mask = pte_get_page_mask(oldlevel);
        }

        /* get access permissions from pte */
        ret->iova = addr & page_mask;
        ret->translated_addr = (pte & AMDVI_DEV_PT_ROOT_MASK) & page_mask;
        ret->addr_mask = ~page_mask;
        ret->perm = amdvi_get_perms(pte);
        return;
    }
no_remap:
    ret->iova = addr & AMDVI_PAGE_MASK_4K;
    ret->translated_addr = addr & AMDVI_PAGE_MASK_4K;
    ret->addr_mask = ~AMDVI_PAGE_MASK_4K;
    ret->perm = amdvi_get_perms(pte);
}

static void amdvi_do_translate(AMDVIAddressSpace *as, hwaddr addr,
                               bool is_write, IOMMUTLBEntry *ret)
{
    AMDVIState *s = as->iommu_state;
    uint16_t devid = PCI_BUILD_BDF(as->bus_num, as->devfn);
    AMDVIIOTLBEntry *iotlb_entry = amdvi_iotlb_lookup(s, addr, devid);
    uint64_t entry[4];

    if (iotlb_entry) {
        trace_amdvi_iotlb_hit(PCI_BUS_NUM(devid), PCI_SLOT(devid),
                PCI_FUNC(devid), addr, iotlb_entry->translated_addr);
        ret->iova = addr & ~iotlb_entry->page_mask;
        ret->translated_addr = iotlb_entry->translated_addr;
        ret->addr_mask = iotlb_entry->page_mask;
        ret->perm = iotlb_entry->perms;
        return;
    }

    /* devices with V = 0 are not translated */
    if (!amdvi_get_dte(s, devid, entry)) {
        goto out;
    }

    amdvi_page_walk(as, entry, ret,
                    is_write ? AMDVI_PERM_WRITE : AMDVI_PERM_READ, addr);

    amdvi_update_iotlb(s, devid, addr, *ret,
                       entry[1] & AMDVI_DEV_DOMID_ID_MASK);
    return;

out:
    ret->iova = addr & AMDVI_PAGE_MASK_4K;
    ret->translated_addr = addr & AMDVI_PAGE_MASK_4K;
    ret->addr_mask = ~AMDVI_PAGE_MASK_4K;
    ret->perm = IOMMU_RW;
}

static inline bool amdvi_is_interrupt_addr(hwaddr addr)
{
    return addr >= AMDVI_INT_ADDR_FIRST && addr <= AMDVI_INT_ADDR_LAST;
}

static IOMMUTLBEntry amdvi_translate(MemoryRegion *iommu, hwaddr addr,
991
                                     IOMMUAccessFlags flag)
D
David Kiarie 已提交
992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019
{
    AMDVIAddressSpace *as = container_of(iommu, AMDVIAddressSpace, iommu);
    AMDVIState *s = as->iommu_state;
    IOMMUTLBEntry ret = {
        .target_as = &address_space_memory,
        .iova = addr,
        .translated_addr = 0,
        .addr_mask = ~(hwaddr)0,
        .perm = IOMMU_NONE
    };

    if (!s->enabled) {
        /* AMDVI disabled - corresponds to iommu=off not
         * failure to provide any parameter
         */
        ret.iova = addr & AMDVI_PAGE_MASK_4K;
        ret.translated_addr = addr & AMDVI_PAGE_MASK_4K;
        ret.addr_mask = ~AMDVI_PAGE_MASK_4K;
        ret.perm = IOMMU_RW;
        return ret;
    } else if (amdvi_is_interrupt_addr(addr)) {
        ret.iova = addr & AMDVI_PAGE_MASK_4K;
        ret.translated_addr = addr & AMDVI_PAGE_MASK_4K;
        ret.addr_mask = ~AMDVI_PAGE_MASK_4K;
        ret.perm = IOMMU_WO;
        return ret;
    }

1020
    amdvi_do_translate(as, addr, flag & IOMMU_WO, &ret);
D
David Kiarie 已提交
1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069
    trace_amdvi_translation_result(as->bus_num, PCI_SLOT(as->devfn),
            PCI_FUNC(as->devfn), addr, ret.translated_addr);
    return ret;
}

static AddressSpace *amdvi_host_dma_iommu(PCIBus *bus, void *opaque, int devfn)
{
    AMDVIState *s = opaque;
    AMDVIAddressSpace **iommu_as;
    int bus_num = pci_bus_num(bus);

    iommu_as = s->address_spaces[bus_num];

    /* allocate memory during the first run */
    if (!iommu_as) {
        iommu_as = g_malloc0(sizeof(AMDVIAddressSpace *) * PCI_DEVFN_MAX);
        s->address_spaces[bus_num] = iommu_as;
    }

    /* set up AMD-Vi region */
    if (!iommu_as[devfn]) {
        iommu_as[devfn] = g_malloc0(sizeof(AMDVIAddressSpace));
        iommu_as[devfn]->bus_num = (uint8_t)bus_num;
        iommu_as[devfn]->devfn = (uint8_t)devfn;
        iommu_as[devfn]->iommu_state = s;

        memory_region_init_iommu(&iommu_as[devfn]->iommu, OBJECT(s),
                                 &s->iommu_ops, "amd-iommu", UINT64_MAX);
        address_space_init(&iommu_as[devfn]->as, &iommu_as[devfn]->iommu,
                           "amd-iommu");
    }
    return &iommu_as[devfn]->as;
}

static const MemoryRegionOps mmio_mem_ops = {
    .read = amdvi_mmio_read,
    .write = amdvi_mmio_write,
    .endianness = DEVICE_LITTLE_ENDIAN,
    .impl = {
        .min_access_size = 1,
        .max_access_size = 8,
        .unaligned = false,
    },
    .valid = {
        .min_access_size = 1,
        .max_access_size = 8,
    }
};

1070 1071 1072
static void amdvi_iommu_notify_flag_changed(MemoryRegion *iommu,
                                            IOMMUNotifierFlag old,
                                            IOMMUNotifierFlag new)
D
David Kiarie 已提交
1073 1074 1075
{
    AMDVIAddressSpace *as = container_of(iommu, AMDVIAddressSpace, iommu);

1076 1077 1078 1079 1080 1081
    if (new & IOMMU_NOTIFIER_MAP) {
        error_report("device %02x.%02x.%x requires iommu notifier which is not "
                     "currently supported", as->bus_num, PCI_SLOT(as->devfn),
                     PCI_FUNC(as->devfn));
        exit(1);
    }
D
David Kiarie 已提交
1082 1083 1084 1085 1086 1087 1088
}

static void amdvi_init(AMDVIState *s)
{
    amdvi_iotlb_reset(s);

    s->iommu_ops.translate = amdvi_translate;
1089
    s->iommu_ops.notify_flag_changed = amdvi_iommu_notify_flag_changed;
D
David Kiarie 已提交
1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137
    s->devtab_len = 0;
    s->cmdbuf_len = 0;
    s->cmdbuf_head = 0;
    s->cmdbuf_tail = 0;
    s->evtlog_head = 0;
    s->evtlog_tail = 0;
    s->excl_enabled = false;
    s->excl_allow = false;
    s->mmio_enabled = false;
    s->enabled = false;
    s->ats_enabled = false;
    s->cmdbuf_enabled = false;

    /* reset MMIO */
    memset(s->mmior, 0, AMDVI_MMIO_SIZE);
    amdvi_set_quad(s, AMDVI_MMIO_EXT_FEATURES, AMDVI_EXT_FEATURES,
            0xffffffffffffffef, 0);
    amdvi_set_quad(s, AMDVI_MMIO_STATUS, 0, 0x98, 0x67);

    /* reset device ident */
    pci_config_set_vendor_id(s->pci.dev.config, PCI_VENDOR_ID_AMD);
    pci_config_set_prog_interface(s->pci.dev.config, 00);
    pci_config_set_device_id(s->pci.dev.config, s->devid);
    pci_config_set_class(s->pci.dev.config, 0x0806);

    /* reset AMDVI specific capabilities, all r/o */
    pci_set_long(s->pci.dev.config + s->capab_offset, AMDVI_CAPAB_FEATURES);
    pci_set_long(s->pci.dev.config + s->capab_offset + AMDVI_CAPAB_BAR_LOW,
                 s->mmio.addr & ~(0xffff0000));
    pci_set_long(s->pci.dev.config + s->capab_offset + AMDVI_CAPAB_BAR_HIGH,
                (s->mmio.addr & ~(0xffff)) >> 16);
    pci_set_long(s->pci.dev.config + s->capab_offset + AMDVI_CAPAB_RANGE,
                 0xff000000);
    pci_set_long(s->pci.dev.config + s->capab_offset + AMDVI_CAPAB_MISC, 0);
    pci_set_long(s->pci.dev.config + s->capab_offset + AMDVI_CAPAB_MISC,
            AMDVI_MAX_PH_ADDR | AMDVI_MAX_GVA_ADDR | AMDVI_MAX_VA_ADDR);
}

static void amdvi_reset(DeviceState *dev)
{
    AMDVIState *s = AMD_IOMMU_DEVICE(dev);

    msi_reset(&s->pci.dev);
    amdvi_init(s);
}

static void amdvi_realize(DeviceState *dev, Error **err)
{
1138
    int ret = 0;
D
David Kiarie 已提交
1139
    AMDVIState *s = AMD_IOMMU_DEVICE(dev);
D
David Kiarie 已提交
1140
    X86IOMMUState *x86_iommu = X86_IOMMU_DEVICE(dev);
1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153
    MachineState *ms = MACHINE(qdev_get_machine());
    MachineClass *mc = MACHINE_GET_CLASS(ms);
    PCMachineState *pcms =
        PC_MACHINE(object_dynamic_cast(OBJECT(ms), TYPE_PC_MACHINE));
    PCIBus *bus;

    if (!pcms) {
        error_setg(err, "Machine-type '%s' not supported by amd-iommu",
                   mc->name);
        return;
    }

    bus = pcms->bus;
D
David Kiarie 已提交
1154 1155 1156 1157
    s->iotlb = g_hash_table_new_full(amdvi_uint64_hash,
                                     amdvi_uint64_equal, g_free, g_free);

    /* This device should take care of IOMMU PCI properties */
D
David Kiarie 已提交
1158
    x86_iommu->type = TYPE_AMD;
D
David Kiarie 已提交
1159 1160
    qdev_set_parent_bus(DEVICE(&s->pci), &bus->qbus);
    object_property_set_bool(OBJECT(&s->pci), true, "realized", err);
1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177
    ret = pci_add_capability(&s->pci.dev, AMDVI_CAPAB_ID_SEC, 0,
                                         AMDVI_CAPAB_SIZE, err);
    if (ret < 0) {
        return;
    }
    s->capab_offset = ret;

    ret = pci_add_capability(&s->pci.dev, PCI_CAP_ID_MSI, 0,
                             AMDVI_CAPAB_REG_SIZE, err);
    if (ret < 0) {
        return;
    }
    ret = pci_add_capability(&s->pci.dev, PCI_CAP_ID_HT, 0,
                             AMDVI_CAPAB_REG_SIZE, err);
    if (ret < 0) {
        return;
    }
D
David Kiarie 已提交
1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211

    /* set up MMIO */
    memory_region_init_io(&s->mmio, OBJECT(s), &mmio_mem_ops, s, "amdvi-mmio",
                          AMDVI_MMIO_SIZE);

    sysbus_init_mmio(SYS_BUS_DEVICE(s), &s->mmio);
    sysbus_mmio_map(SYS_BUS_DEVICE(s), 0, AMDVI_BASE_ADDR);
    pci_setup_iommu(bus, amdvi_host_dma_iommu, s);
    s->devid = object_property_get_int(OBJECT(&s->pci), "addr", err);
    msi_init(&s->pci.dev, 0, 1, true, false, err);
    amdvi_init(s);
}

static const VMStateDescription vmstate_amdvi = {
    .name = "amd-iommu",
    .unmigratable = 1
};

static void amdvi_instance_init(Object *klass)
{
    AMDVIState *s = AMD_IOMMU_DEVICE(klass);

    object_initialize(&s->pci, sizeof(s->pci), TYPE_AMD_IOMMU_PCI);
}

static void amdvi_class_init(ObjectClass *klass, void* data)
{
    DeviceClass *dc = DEVICE_CLASS(klass);
    X86IOMMUClass *dc_class = X86_IOMMU_CLASS(klass);

    dc->reset = amdvi_reset;
    dc->vmsd = &vmstate_amdvi;
    dc->hotpluggable = false;
    dc_class->realize = amdvi_realize;
1212
    /* Supported by the pc-q35-* machine types */
1213
    dc->user_creatable = true;
D
David Kiarie 已提交
1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236
}

static const TypeInfo amdvi = {
    .name = TYPE_AMD_IOMMU_DEVICE,
    .parent = TYPE_X86_IOMMU_DEVICE,
    .instance_size = sizeof(AMDVIState),
    .instance_init = amdvi_instance_init,
    .class_init = amdvi_class_init
};

static const TypeInfo amdviPCI = {
    .name = "AMDVI-PCI",
    .parent = TYPE_PCI_DEVICE,
    .instance_size = sizeof(AMDVIPCIState),
};

static void amdviPCI_register_types(void)
{
    type_register_static(&amdviPCI);
    type_register_static(&amdvi);
}

type_init(amdviPCI_register_types);