spapr.c 15.8 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 23 24 25 26 27 28 29
/*
 * QEMU PowerPC pSeries Logical Partition (aka sPAPR) hardware System Emulator
 *
 * Copyright (c) 2004-2007 Fabrice Bellard
 * Copyright (c) 2007 Jocelyn Mayer
 * Copyright (c) 2010 David Gibson, IBM Corporation.
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
 * in the Software without restriction, including without limitation the rights
 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 * THE SOFTWARE.
 *
 */
#include "sysemu.h"
#include "hw.h"
#include "elf.h"
30
#include "net.h"
31
#include "blockdev.h"
32 33 34 35 36 37

#include "hw/boards.h"
#include "hw/ppc.h"
#include "hw/loader.h"

#include "hw/spapr.h"
38
#include "hw/spapr_vio.h"
39
#include "hw/xics.h"
40 41 42 43 44 45

#include <libfdt.h>

#define KERNEL_LOAD_ADDR        0x00000000
#define INITRD_LOAD_ADDR        0x02800000
#define FDT_MAX_SIZE            0x10000
46
#define RTAS_MAX_SIZE           0x10000
47 48 49 50
#define FW_MAX_SIZE             0x400000
#define FW_FILE_NAME            "slof.bin"

#define MIN_RAM_SLOF		512UL
51 52 53

#define TIMEBASE_FREQ           512000000ULL

54
#define MAX_CPUS                256
55
#define XICS_IRQS		1024
56 57 58

sPAPREnvironment *spapr;

59 60 61 62 63 64
static void *spapr_create_fdt_skel(const char *cpu_model,
                                   target_phys_addr_t initrd_base,
                                   target_phys_addr_t initrd_size,
                                   const char *boot_device,
                                   const char *kernel_cmdline,
                                   long hash_shift)
65 66
{
    void *fdt;
D
David Gibson 已提交
67
    CPUState *env;
68
    uint64_t mem_reg_property[] = { 0, cpu_to_be64(ram_size) };
69 70
    uint32_t start_prop = cpu_to_be32(initrd_base);
    uint32_t end_prop = cpu_to_be32(initrd_base + initrd_size);
71
    uint32_t pft_size_prop[] = {0, cpu_to_be32(hash_shift)};
72
    char hypertas_prop[] = "hcall-pft\0hcall-term\0hcall-dabr\0hcall-interrupt"
73
        "\0hcall-tce\0hcall-vio\0hcall-splpar";
74
    uint32_t interrupt_server_ranges_prop[] = {0, cpu_to_be32(smp_cpus)};
75 76 77 78 79 80 81 82 83 84 85 86 87
    int i;
    char *modelname;

#define _FDT(exp) \
    do { \
        int ret = (exp);                                           \
        if (ret < 0) {                                             \
            fprintf(stderr, "qemu: error creating device tree: %s: %s\n", \
                    #exp, fdt_strerror(ret));                      \
            exit(1);                                               \
        }                                                          \
    } while (0)

88
    fdt = g_malloc0(FDT_MAX_SIZE);
89 90 91 92 93 94 95
    _FDT((fdt_create(fdt, FDT_MAX_SIZE)));

    _FDT((fdt_finish_reservemap(fdt)));

    /* Root node */
    _FDT((fdt_begin_node(fdt, "")));
    _FDT((fdt_property_string(fdt, "device_type", "chrp")));
96
    _FDT((fdt_property_string(fdt, "model", "IBM pSeries (emulated by qemu)")));
97 98 99 100 101 102 103 104 105 106 107 108

    _FDT((fdt_property_cell(fdt, "#address-cells", 0x2)));
    _FDT((fdt_property_cell(fdt, "#size-cells", 0x2)));

    /* /chosen */
    _FDT((fdt_begin_node(fdt, "chosen")));

    _FDT((fdt_property_string(fdt, "bootargs", kernel_cmdline)));
    _FDT((fdt_property(fdt, "linux,initrd-start",
                       &start_prop, sizeof(start_prop))));
    _FDT((fdt_property(fdt, "linux,initrd-end",
                       &end_prop, sizeof(end_prop))));
109
    _FDT((fdt_property_string(fdt, "qemu,boot-device", boot_device)));
110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127

    _FDT((fdt_end_node(fdt)));

    /* memory node */
    _FDT((fdt_begin_node(fdt, "memory@0")));

    _FDT((fdt_property_string(fdt, "device_type", "memory")));
    _FDT((fdt_property(fdt, "reg",
                       mem_reg_property, sizeof(mem_reg_property))));

    _FDT((fdt_end_node(fdt)));

    /* cpus */
    _FDT((fdt_begin_node(fdt, "cpus")));

    _FDT((fdt_property_cell(fdt, "#address-cells", 0x1)));
    _FDT((fdt_property_cell(fdt, "#size-cells", 0x0)));

128
    modelname = g_strdup(cpu_model);
129 130 131 132 133

    for (i = 0; i < strlen(modelname); i++) {
        modelname[i] = toupper(modelname[i]);
    }

D
David Gibson 已提交
134 135 136
    for (env = first_cpu; env != NULL; env = env->next_cpu) {
        int index = env->cpu_index;
        uint32_t gserver_prop[] = {cpu_to_be32(index), 0}; /* HACK! */
137 138 139 140
        char *nodename;
        uint32_t segs[] = {cpu_to_be32(28), cpu_to_be32(40),
                           0xffffffff, 0xffffffff};

D
David Gibson 已提交
141
        if (asprintf(&nodename, "%s@%x", modelname, index) < 0) {
142 143 144 145 146 147 148 149
            fprintf(stderr, "Allocation failure\n");
            exit(1);
        }

        _FDT((fdt_begin_node(fdt, nodename)));

        free(nodename);

D
David Gibson 已提交
150
        _FDT((fdt_property_cell(fdt, "reg", index)));
151 152 153 154 155 156 157 158 159 160 161 162
        _FDT((fdt_property_string(fdt, "device_type", "cpu")));

        _FDT((fdt_property_cell(fdt, "cpu-version", env->spr[SPR_PVR])));
        _FDT((fdt_property_cell(fdt, "dcache-block-size",
                                env->dcache_line_size)));
        _FDT((fdt_property_cell(fdt, "icache-block-size",
                                env->icache_line_size)));
        _FDT((fdt_property_cell(fdt, "timebase-frequency", TIMEBASE_FREQ)));
        /* Hardcode CPU frequency for now.  It's kind of arbitrary on
         * full emu, for kvm we should copy it from the host */
        _FDT((fdt_property_cell(fdt, "clock-frequency", 1000000000)));
        _FDT((fdt_property_cell(fdt, "ibm,slb-size", env->slb_nr)));
163 164
        _FDT((fdt_property(fdt, "ibm,pft-size",
                           pft_size_prop, sizeof(pft_size_prop))));
165 166
        _FDT((fdt_property_string(fdt, "status", "okay")));
        _FDT((fdt_property(fdt, "64-bit", NULL, 0)));
D
David Gibson 已提交
167
        _FDT((fdt_property_cell(fdt, "ibm,ppc-interrupt-server#s", index)));
168 169
        _FDT((fdt_property(fdt, "ibm,ppc-interrupt-gserver#s",
                           gserver_prop, sizeof(gserver_prop))));
170

D
David Gibson 已提交
171
        if (env->mmu_model & POWERPC_MMU_1TSEG) {
172 173 174 175 176 177 178
            _FDT((fdt_property(fdt, "ibm,processor-segment-sizes",
                               segs, sizeof(segs))));
        }

        _FDT((fdt_end_node(fdt)));
    }

179
    g_free(modelname);
180 181 182

    _FDT((fdt_end_node(fdt)));

183 184 185 186 187 188 189 190
    /* RTAS */
    _FDT((fdt_begin_node(fdt, "rtas")));

    _FDT((fdt_property(fdt, "ibm,hypertas-functions", hypertas_prop,
                       sizeof(hypertas_prop))));

    _FDT((fdt_end_node(fdt)));

191 192 193 194 195 196 197 198 199 200 201 202 203 204
    /* interrupt controller */
    _FDT((fdt_begin_node(fdt, "interrupt-controller@0")));

    _FDT((fdt_property_string(fdt, "device_type",
                              "PowerPC-External-Interrupt-Presentation")));
    _FDT((fdt_property_string(fdt, "compatible", "IBM,ppc-xicp")));
    _FDT((fdt_property_cell(fdt, "reg", 0)));
    _FDT((fdt_property(fdt, "interrupt-controller", NULL, 0)));
    _FDT((fdt_property(fdt, "ibm,interrupt-server-ranges",
                       interrupt_server_ranges_prop,
                       sizeof(interrupt_server_ranges_prop))));

    _FDT((fdt_end_node(fdt)));

205 206 207 208 209 210 211
    /* vdevice */
    _FDT((fdt_begin_node(fdt, "vdevice")));

    _FDT((fdt_property_string(fdt, "device_type", "vdevice")));
    _FDT((fdt_property_string(fdt, "compatible", "IBM,vdevice")));
    _FDT((fdt_property_cell(fdt, "#address-cells", 0x1)));
    _FDT((fdt_property_cell(fdt, "#size-cells", 0x0)));
212 213
    _FDT((fdt_property_cell(fdt, "#interrupt-cells", 0x2)));
    _FDT((fdt_property(fdt, "interrupt-controller", NULL, 0)));
214 215 216

    _FDT((fdt_end_node(fdt)));

217 218 219
    _FDT((fdt_end_node(fdt))); /* close root node */
    _FDT((fdt_finish(fdt)));

220 221 222 223 224 225 226 227 228 229 230
    return fdt;
}

static void spapr_finalize_fdt(sPAPREnvironment *spapr,
                               target_phys_addr_t fdt_addr,
                               target_phys_addr_t rtas_addr,
                               target_phys_addr_t rtas_size)
{
    int ret;
    void *fdt;

231
    fdt = g_malloc(FDT_MAX_SIZE);
232 233 234

    /* open out the base tree into a temp buffer for the final tweaks */
    _FDT((fdt_open_into(spapr->fdt_skel, fdt, FDT_MAX_SIZE)));
235 236 237 238 239 240 241

    ret = spapr_populate_vdevice(spapr->vio_bus, fdt);
    if (ret < 0) {
        fprintf(stderr, "couldn't setup vio devices in fdt\n");
        exit(1);
    }

242 243 244 245 246 247
    /* RTAS */
    ret = spapr_rtas_device_tree_setup(fdt, rtas_addr, rtas_size);
    if (ret < 0) {
        fprintf(stderr, "Couldn't set up RTAS device tree properties\n");
    }

248 249
    _FDT((fdt_pack(fdt)));

250
    cpu_physical_memory_write(fdt_addr, fdt, fdt_totalsize(fdt));
251

252
    g_free(fdt);
253 254 255 256 257 258 259 260 261 262 263 264
}

static uint64_t translate_kernel_address(void *opaque, uint64_t addr)
{
    return (addr & 0x0fffffff) + KERNEL_LOAD_ADDR;
}

static void emulate_spapr_hypercall(CPUState *env)
{
    env->gpr[3] = spapr_hypercall(env, env->gpr[3], &env->gpr[4]);
}

265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285
static void spapr_reset(void *opaque)
{
    sPAPREnvironment *spapr = (sPAPREnvironment *)opaque;

    fprintf(stderr, "sPAPR reset\n");

    /* flush out the hash table */
    memset(spapr->htab, 0, spapr->htab_size);

    /* Load the fdt */
    spapr_finalize_fdt(spapr, spapr->fdt_addr, spapr->rtas_addr,
                       spapr->rtas_size);

    /* Set up the entry state */
    first_cpu->gpr[3] = spapr->fdt_addr;
    first_cpu->gpr[5] = 0;
    first_cpu->halted = 0;
    first_cpu->nip = spapr->entry_point;

}

286 287 288 289 290 291 292 293
/* pSeries LPAR / sPAPR hardware init */
static void ppc_spapr_init(ram_addr_t ram_size,
                           const char *boot_device,
                           const char *kernel_filename,
                           const char *kernel_cmdline,
                           const char *initrd_filename,
                           const char *cpu_model)
{
D
David Gibson 已提交
294
    CPUState *env;
295 296
    int i;
    ram_addr_t ram_offset;
297 298
    uint32_t initrd_base;
    long kernel_size, initrd_size, fw_size;
299
    long pteg_shift = 17;
300
    char *filename;
301
    int irq = 16;
302

303
    spapr = g_malloc(sizeof(*spapr));
304 305 306 307 308
    cpu_ppc_hypercall = emulate_spapr_hypercall;

    /* We place the device tree just below either the top of RAM, or
     * 2GB, so that it can be processed with 32-bit code if
     * necessary */
309 310
    spapr->fdt_addr = MIN(ram_size, 0x80000000) - FDT_MAX_SIZE;
    spapr->rtas_addr = spapr->fdt_addr - RTAS_MAX_SIZE;
311 312 313 314 315 316

    /* init CPUs */
    if (cpu_model == NULL) {
        cpu_model = "POWER7";
    }
    for (i = 0; i < smp_cpus; i++) {
D
David Gibson 已提交
317
        env = cpu_init(cpu_model);
318 319 320 321 322 323 324 325 326 327 328

        if (!env) {
            fprintf(stderr, "Unable to find PowerPC CPU definition\n");
            exit(1);
        }
        /* Set time-base frequency to 512 MHz */
        cpu_ppc_tb_init(env, TIMEBASE_FREQ);
        qemu_register_reset((QEMUResetHandler *)&cpu_reset, env);

        env->hreset_vector = 0x60;
        env->hreset_excp_prefix = 0;
D
David Gibson 已提交
329
        env->gpr[3] = env->cpu_index;
330 331 332 333 334 335
    }

    /* allocate RAM */
    ram_offset = qemu_ram_alloc(NULL, "ppc_spapr.ram", ram_size);
    cpu_register_physical_memory(0, ram_size, ram_offset);

336 337 338
    /* allocate hash page table.  For now we always make this 16mb,
     * later we should probably make it scale to the size of guest
     * RAM */
339
    spapr->htab_size = 1ULL << (pteg_shift + 7);
340
    spapr->htab = g_malloc(spapr->htab_size);
341

D
David Gibson 已提交
342
    for (env = first_cpu; env != NULL; env = env->next_cpu) {
343
        env->external_htab = spapr->htab;
D
David Gibson 已提交
344
        env->htab_base = -1;
345
        env->htab_mask = spapr->htab_size - 1;
346 347
    }

348
    filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, "spapr-rtas.bin");
349 350 351
    spapr->rtas_size = load_image_targphys(filename, spapr->rtas_addr,
                                           ram_size - spapr->rtas_addr);
    if (spapr->rtas_size < 0) {
352 353 354
        hw_error("qemu: could not load LPAR rtas '%s'\n", filename);
        exit(1);
    }
355
    g_free(filename);
356

357
    /* Set up Interrupt Controller */
D
David Gibson 已提交
358
    spapr->icp = xics_system_init(XICS_IRQS);
359 360

    /* Set up VIO bus */
361 362
    spapr->vio_bus = spapr_vio_bus_init();

363
    for (i = 0; i < MAX_SERIAL_PORTS; i++, irq++) {
364
        if (serial_hds[i]) {
365 366 367
            spapr_vty_create(spapr->vio_bus, SPAPR_VTY_BASE_ADDRESS + i,
                             serial_hds[i], xics_find_qirq(spapr->icp, irq),
                             irq);
368 369
        }
    }
370

371 372 373 374
    for (i = 0; i < nb_nics; i++, irq++) {
        NICInfo *nd = &nd_table[i];

        if (!nd->model) {
375
            nd->model = g_strdup("ibmveth");
376 377 378 379 380 381 382 383 384 385 386 387 388
        }

        if (strcmp(nd->model, "ibmveth") == 0) {
            spapr_vlan_create(spapr->vio_bus, 0x1000 + i, nd,
                              xics_find_qirq(spapr->icp, irq), irq);
        } else {
            fprintf(stderr, "pSeries (sPAPR) platform does not support "
                    "NIC model '%s' (only ibmveth is supported)\n",
                    nd->model);
            exit(1);
        }
    }

389 390 391 392 393 394
    for (i = 0; i <= drive_get_max_bus(IF_SCSI); i++) {
        spapr_vscsi_create(spapr->vio_bus, 0x2000 + i,
                           xics_find_qirq(spapr->icp, irq), irq);
        irq++;
    }

395 396 397 398 399 400
    if (kernel_filename) {
        uint64_t lowaddr = 0;

        kernel_size = load_elf(kernel_filename, translate_kernel_address, NULL,
                               NULL, &lowaddr, NULL, 1, ELF_MACHINE, 0);
        if (kernel_size < 0) {
401 402 403
            kernel_size = load_image_targphys(kernel_filename,
                                              KERNEL_LOAD_ADDR,
                                              ram_size - KERNEL_LOAD_ADDR);
404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424
        }
        if (kernel_size < 0) {
            fprintf(stderr, "qemu: could not load kernel '%s'\n",
                    kernel_filename);
            exit(1);
        }

        /* load initrd */
        if (initrd_filename) {
            initrd_base = INITRD_LOAD_ADDR;
            initrd_size = load_image_targphys(initrd_filename, initrd_base,
                                              ram_size - initrd_base);
            if (initrd_size < 0) {
                fprintf(stderr, "qemu: could not load initial ram disk '%s'\n",
                        initrd_filename);
                exit(1);
            }
        } else {
            initrd_base = 0;
            initrd_size = 0;
        }
425 426

        spapr->entry_point = KERNEL_LOAD_ADDR;
427
    } else {
428 429 430 431 432 433 434 435 436 437 438
        if (ram_size < (MIN_RAM_SLOF << 20)) {
            fprintf(stderr, "qemu: pSeries SLOF firmware requires >= "
                    "%ldM guest RAM\n", MIN_RAM_SLOF);
            exit(1);
        }
        filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, "slof.bin");
        fw_size = load_image_targphys(filename, 0, FW_MAX_SIZE);
        if (fw_size < 0) {
            hw_error("qemu: could not load LPAR rtas '%s'\n", filename);
            exit(1);
        }
439
        g_free(filename);
440
        spapr->entry_point = 0x100;
441 442 443 444 445
        initrd_base = 0;
        initrd_size = 0;

        /* SLOF will startup the secondary CPUs using RTAS,
           rather than expecting a kexec() style entry */
D
David Gibson 已提交
446 447
        for (env = first_cpu; env != NULL; env = env->next_cpu) {
            env->halted = 1;
448
        }
449 450 451
    }

    /* Prepare the device tree */
452 453 454 455 456
    spapr->fdt_skel = spapr_create_fdt_skel(cpu_model,
                                            initrd_base, initrd_size,
                                            boot_device, kernel_cmdline,
                                            pteg_shift + 7);
    assert(spapr->fdt_skel != NULL);
457

458
    qemu_register_reset(spapr_reset, spapr);
459 460 461 462 463 464 465 466 467
}

static QEMUMachine spapr_machine = {
    .name = "pseries",
    .desc = "pSeries Logical Partition (PAPR compliant)",
    .init = ppc_spapr_init,
    .max_cpus = MAX_CPUS,
    .no_vga = 1,
    .no_parallel = 1,
468
    .use_scsi = 1,
469 470 471 472 473 474 475 476
};

static void spapr_machine_init(void)
{
    qemu_register_machine(&spapr_machine);
}

machine_init(spapr_machine_init);