[qemu.git] / hw / spapr.c

/*
 * 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"
#include "net.h"
#include "blockdev.h"

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

#include "hw/spapr.h"
#include "hw/spapr_vio.h"
#include "hw/xics.h"

#include "kvm.h"
#include "kvm_ppc.h"

#include <libfdt.h>

#define KERNEL_LOAD_ADDR        0x00000000
#define INITRD_LOAD_ADDR        0x02800000
#define FDT_MAX_SIZE            0x10000
#define RTAS_MAX_SIZE           0x10000
#define FW_MAX_SIZE             0x400000
#define FW_FILE_NAME            "slof.bin"

#define MIN_RAM_SLOF		512UL

#define TIMEBASE_FREQ           512000000ULL

#define MAX_CPUS                256
#define XICS_IRQS		1024

sPAPREnvironment *spapr;

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)
{
    void *fdt;
    CPUState *env;
    uint64_t mem_reg_property[] = { 0, cpu_to_be64(ram_size) };
    uint32_t start_prop = cpu_to_be32(initrd_base);
    uint32_t end_prop = cpu_to_be32(initrd_base + initrd_size);
    uint32_t pft_size_prop[] = {0, cpu_to_be32(hash_shift)};
    char hypertas_prop[] = "hcall-pft\0hcall-term\0hcall-dabr\0hcall-interrupt"
        "\0hcall-tce\0hcall-vio\0hcall-splpar";
    uint32_t interrupt_server_ranges_prop[] = {0, cpu_to_be32(smp_cpus)};
    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)

    fdt = g_malloc0(FDT_MAX_SIZE);
    _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")));
    _FDT((fdt_property_string(fdt, "model", "IBM pSeries (emulated by qemu)")));

    _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))));
    _FDT((fdt_property_string(fdt, "qemu,boot-device", boot_device)));

    _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)));

    modelname = g_strdup(cpu_model);

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

    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! */
        char *nodename;
        uint32_t segs[] = {cpu_to_be32(28), cpu_to_be32(40),
                           0xffffffff, 0xffffffff};
        uint32_t tbfreq = kvm_enabled() ? kvmppc_get_tbfreq() : TIMEBASE_FREQ;
        uint32_t cpufreq = kvm_enabled() ? kvmppc_get_clockfreq() : 1000000000;

        if (asprintf(&nodename, "%s@%x", modelname, index) < 0) {
            fprintf(stderr, "Allocation failure\n");
            exit(1);
        }

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

        free(nodename);

        _FDT((fdt_property_cell(fdt, "reg", index)));
        _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", tbfreq)));
        _FDT((fdt_property_cell(fdt, "clock-frequency", cpufreq)));
        _FDT((fdt_property_cell(fdt, "ibm,slb-size", env->slb_nr)));
        _FDT((fdt_property(fdt, "ibm,pft-size",
                           pft_size_prop, sizeof(pft_size_prop))));
        _FDT((fdt_property_string(fdt, "status", "okay")));
        _FDT((fdt_property(fdt, "64-bit", NULL, 0)));
        _FDT((fdt_property_cell(fdt, "ibm,ppc-interrupt-server#s", index)));
        _FDT((fdt_property(fdt, "ibm,ppc-interrupt-gserver#s",
                           gserver_prop, sizeof(gserver_prop))));

        if (env->mmu_model & POWERPC_MMU_1TSEG) {
            _FDT((fdt_property(fdt, "ibm,processor-segment-sizes",
                               segs, sizeof(segs))));
        }

        _FDT((fdt_end_node(fdt)));
    }

    g_free(modelname);

    _FDT((fdt_end_node(fdt)));

    /* RTAS */
    _FDT((fdt_begin_node(fdt, "rtas")));

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

    _FDT((fdt_end_node(fdt)));

    /* 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)));

    /* 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)));
    _FDT((fdt_property_cell(fdt, "#interrupt-cells", 0x2)));
    _FDT((fdt_property(fdt, "interrupt-controller", NULL, 0)));

    _FDT((fdt_end_node(fdt)));

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

    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;

    fdt = g_malloc(FDT_MAX_SIZE);

    /* open out the base tree into a temp buffer for the final tweaks */
    _FDT((fdt_open_into(spapr->fdt_skel, fdt, FDT_MAX_SIZE)));

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

    /* 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");
    }

    _FDT((fdt_pack(fdt)));

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

    g_free(fdt);
}

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]);
}

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;

}

/* 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)
{
    CPUState *env;
    int i;
    ram_addr_t ram_offset;
    uint32_t initrd_base;
    long kernel_size, initrd_size, fw_size;
    long pteg_shift = 17;
    char *filename;

    spapr = g_malloc(sizeof(*spapr));
    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 */
    spapr->fdt_addr = MIN(ram_size, 0x80000000) - FDT_MAX_SIZE;
    spapr->rtas_addr = spapr->fdt_addr - RTAS_MAX_SIZE;

    /* init CPUs */
    if (cpu_model == NULL) {
        cpu_model = "POWER7";
    }
    for (i = 0; i < smp_cpus; i++) {
        env = cpu_init(cpu_model);

        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;
        env->gpr[3] = env->cpu_index;
    }

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

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

    for (env = first_cpu; env != NULL; env = env->next_cpu) {
        env->external_htab = spapr->htab;
        env->htab_base = -1;
        env->htab_mask = spapr->htab_size - 1;

        /* Tell KVM that we're in PAPR mode */
        env->spr[SPR_SDR1] = (unsigned long)spapr->htab |
                             ((pteg_shift + 7) - 18);
        env->spr[SPR_HIOR] = 0;

        if (kvm_enabled()) {
            kvmppc_set_papr(env);
        }
    }

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

    /* Set up Interrupt Controller */
    spapr->icp = xics_system_init(XICS_IRQS);

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

    for (i = 0; i < MAX_SERIAL_PORTS; i++) {
        if (serial_hds[i]) {
            spapr_vty_create(spapr->vio_bus, SPAPR_VTY_BASE_ADDRESS + i,
                             serial_hds[i]);
        }
    }

    for (i = 0; i < nb_nics; i++) {
        NICInfo *nd = &nd_table[i];

        if (!nd->model) {
            nd->model = g_strdup("ibmveth");
        }

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

    for (i = 0; i <= drive_get_max_bus(IF_SCSI); i++) {
        spapr_vscsi_create(spapr->vio_bus, 0x2000 + i);
    }

    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) {
            kernel_size = load_image_targphys(kernel_filename,
                                              KERNEL_LOAD_ADDR,
                                              ram_size - KERNEL_LOAD_ADDR);
        }
        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;
        }

        spapr->entry_point = KERNEL_LOAD_ADDR;
    } else {
        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);
        }
        g_free(filename);
        spapr->entry_point = 0x100;
        initrd_base = 0;
        initrd_size = 0;

        /* SLOF will startup the secondary CPUs using RTAS,
           rather than expecting a kexec() style entry */
        for (env = first_cpu; env != NULL; env = env->next_cpu) {
            env->halted = 1;
        }
    }

    /* Prepare the device tree */
    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);

    qemu_register_reset(spapr_reset, spapr);
}

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,
    .use_scsi = 1,
};

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

machine_init(spapr_machine_init);
Commit	Line	Data
9fdf0c29 DG	1	/*
	2	* QEMU PowerPC pSeries Logical Partition (aka sPAPR) hardware System Emulator
	3	*
	4	* Copyright (c) 2004-2007 Fabrice Bellard
	5	* Copyright (c) 2007 Jocelyn Mayer
	6	* Copyright (c) 2010 David Gibson, IBM Corporation.
	7	*
	8	* Permission is hereby granted, free of charge, to any person obtaining a copy
	9	* of this software and associated documentation files (the "Software"), to deal
	10	* in the Software without restriction, including without limitation the rights
	11	* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
	12	* copies of the Software, and to permit persons to whom the Software is
	13	* furnished to do so, subject to the following conditions:
	14	*
	15	* The above copyright notice and this permission notice shall be included in
	16	* all copies or substantial portions of the Software.
	17	*
	18	* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
	19	* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
	20	* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
	21	* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
	22	* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
	23	* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
	24	* THE SOFTWARE.
	25	*
	26	*/
	27	#include "sysemu.h"
9fdf0c29 DG	28	#include "hw.h"
9fdf0c29 DG	29	#include "elf.h"
8d90ad90	30	#include "net.h"
6e270446	31	#include "blockdev.h"
9fdf0c29 DG	32
	33	#include "hw/boards.h"
	34	#include "hw/ppc.h"
	35	#include "hw/loader.h"
	36
	37	#include "hw/spapr.h"
4040ab72	38	#include "hw/spapr_vio.h"
b5cec4c5	39	#include "hw/xics.h"
9fdf0c29	40
f61b4bed AG	41	#include "kvm.h"
	42	#include "kvm_ppc.h"
	43
9fdf0c29 DG	44	#include <libfdt.h>
	45
	46	#define KERNEL_LOAD_ADDR 0x00000000
	47	#define INITRD_LOAD_ADDR 0x02800000
	48	#define FDT_MAX_SIZE 0x10000
39ac8455	49	#define RTAS_MAX_SIZE 0x10000
a9f8ad8f DG	50	#define FW_MAX_SIZE 0x400000
	51	#define FW_FILE_NAME "slof.bin"
	52
	53	#define MIN_RAM_SLOF 512UL
9fdf0c29 DG	54
	55	#define TIMEBASE_FREQ 512000000ULL
	56
41019fec	57	#define MAX_CPUS 256
b5cec4c5	58	#define XICS_IRQS 1024
9fdf0c29 DG	59
	60	sPAPREnvironment *spapr;
	61
a3467baa DG	62	static void spapr_create_fdt_skel(const char cpu_model,
	63	target_phys_addr_t initrd_base,
	64	target_phys_addr_t initrd_size,
	65	const char *boot_device,
	66	const char *kernel_cmdline,
	67	long hash_shift)
9fdf0c29 DG	68	{
9fdf0c29 DG	69	void *fdt;
c7a5c0c9	70	CPUState *env;
a3467baa	71	uint64_t mem_reg_property[] = { 0, cpu_to_be64(ram_size) };
9fdf0c29 DG	72	uint32_t start_prop = cpu_to_be32(initrd_base);
9fdf0c29 DG	73	uint32_t end_prop = cpu_to_be32(initrd_base + initrd_size);
f43e3525	74	uint32_t pft_size_prop[] = {0, cpu_to_be32(hash_shift)};
ee86dfee	75	char hypertas_prop[] = "hcall-pft\0hcall-term\0hcall-dabr\0hcall-interrupt"
ed120055	76	"\0hcall-tce\0hcall-vio\0hcall-splpar";
b5cec4c5	77	uint32_t interrupt_server_ranges_prop[] = {0, cpu_to_be32(smp_cpus)};
9fdf0c29 DG	78	int i;
	79	char *modelname;
	80
	81	#define _FDT(exp) \
	82	do { \
	83	int ret = (exp); \
	84	if (ret < 0) { \
	85	fprintf(stderr, "qemu: error creating device tree: %s: %s\n", \
	86	#exp, fdt_strerror(ret)); \
	87	exit(1); \
	88	} \
	89	} while (0)
	90
7267c094	91	fdt = g_malloc0(FDT_MAX_SIZE);
9fdf0c29 DG	92	_FDT((fdt_create(fdt, FDT_MAX_SIZE)));
	93
	94	_FDT((fdt_finish_reservemap(fdt)));
	95
	96	/* Root node */
	97	_FDT((fdt_begin_node(fdt, "")));
	98	_FDT((fdt_property_string(fdt, "device_type", "chrp")));
5d73dd66	99	_FDT((fdt_property_string(fdt, "model", "IBM pSeries (emulated by qemu)")));
9fdf0c29 DG	100
	101	_FDT((fdt_property_cell(fdt, "#address-cells", 0x2)));
	102	_FDT((fdt_property_cell(fdt, "#size-cells", 0x2)));
	103
	104	/* /chosen */
	105	_FDT((fdt_begin_node(fdt, "chosen")));
	106
	107	_FDT((fdt_property_string(fdt, "bootargs", kernel_cmdline)));
	108	_FDT((fdt_property(fdt, "linux,initrd-start",
	109	&start_prop, sizeof(start_prop))));
	110	_FDT((fdt_property(fdt, "linux,initrd-end",
	111	&end_prop, sizeof(end_prop))));
a9f8ad8f	112	_FDT((fdt_property_string(fdt, "qemu,boot-device", boot_device)));
9fdf0c29 DG	113
	114	_FDT((fdt_end_node(fdt)));
	115
	116	/* memory node */
	117	_FDT((fdt_begin_node(fdt, "memory@0")));
	118
	119	_FDT((fdt_property_string(fdt, "device_type", "memory")));
	120	_FDT((fdt_property(fdt, "reg",
	121	mem_reg_property, sizeof(mem_reg_property))));
	122
	123	_FDT((fdt_end_node(fdt)));
	124
	125	/* cpus */
	126	_FDT((fdt_begin_node(fdt, "cpus")));
	127
	128	_FDT((fdt_property_cell(fdt, "#address-cells", 0x1)));
	129	_FDT((fdt_property_cell(fdt, "#size-cells", 0x0)));
	130
7267c094	131	modelname = g_strdup(cpu_model);
9fdf0c29 DG	132
	133	for (i = 0; i < strlen(modelname); i++) {
	134	modelname[i] = toupper(modelname[i]);
	135	}
	136
c7a5c0c9 DG	137	for (env = first_cpu; env != NULL; env = env->next_cpu) {
	138	int index = env->cpu_index;
	139	uint32_t gserver_prop[] = {cpu_to_be32(index), 0}; /* HACK! */
9fdf0c29 DG	140	char *nodename;
	141	uint32_t segs[] = {cpu_to_be32(28), cpu_to_be32(40),
	142	0xffffffff, 0xffffffff};
0a8b2938 AG	143	uint32_t tbfreq = kvm_enabled() ? kvmppc_get_tbfreq() : TIMEBASE_FREQ;
0a8b2938 AG	144	uint32_t cpufreq = kvm_enabled() ? kvmppc_get_clockfreq() : 1000000000;
9fdf0c29	145
c7a5c0c9	146	if (asprintf(&nodename, "%s@%x", modelname, index) < 0) {
9fdf0c29 DG	147	fprintf(stderr, "Allocation failure\n");
	148	exit(1);
	149	}
	150
	151	_FDT((fdt_begin_node(fdt, nodename)));
	152
	153	free(nodename);
	154
c7a5c0c9	155	_FDT((fdt_property_cell(fdt, "reg", index)));
9fdf0c29 DG	156	_FDT((fdt_property_string(fdt, "device_type", "cpu")));
	157
	158	_FDT((fdt_property_cell(fdt, "cpu-version", env->spr[SPR_PVR])));
	159	_FDT((fdt_property_cell(fdt, "dcache-block-size",
	160	env->dcache_line_size)));
	161	_FDT((fdt_property_cell(fdt, "icache-block-size",
	162	env->icache_line_size)));
0a8b2938 AG	163	_FDT((fdt_property_cell(fdt, "timebase-frequency", tbfreq)));
0a8b2938 AG	164	_FDT((fdt_property_cell(fdt, "clock-frequency", cpufreq)));
9fdf0c29	165	_FDT((fdt_property_cell(fdt, "ibm,slb-size", env->slb_nr)));
f43e3525 DG	166	_FDT((fdt_property(fdt, "ibm,pft-size",
f43e3525 DG	167	pft_size_prop, sizeof(pft_size_prop))));
9fdf0c29 DG	168	_FDT((fdt_property_string(fdt, "status", "okay")));
9fdf0c29 DG	169	_FDT((fdt_property(fdt, "64-bit", NULL, 0)));
c7a5c0c9	170	_FDT((fdt_property_cell(fdt, "ibm,ppc-interrupt-server#s", index)));
b5cec4c5 DG	171	_FDT((fdt_property(fdt, "ibm,ppc-interrupt-gserver#s",
b5cec4c5 DG	172	gserver_prop, sizeof(gserver_prop))));
9fdf0c29	173
c7a5c0c9	174	if (env->mmu_model & POWERPC_MMU_1TSEG) {
9fdf0c29 DG	175	_FDT((fdt_property(fdt, "ibm,processor-segment-sizes",
	176	segs, sizeof(segs))));
	177	}
	178
	179	_FDT((fdt_end_node(fdt)));
	180	}
	181
7267c094	182	g_free(modelname);
9fdf0c29 DG	183
	184	_FDT((fdt_end_node(fdt)));
	185
f43e3525 DG	186	/* RTAS */
	187	_FDT((fdt_begin_node(fdt, "rtas")));
	188
	189	_FDT((fdt_property(fdt, "ibm,hypertas-functions", hypertas_prop,
	190	sizeof(hypertas_prop))));
	191
	192	_FDT((fdt_end_node(fdt)));
	193
b5cec4c5 DG	194	/* interrupt controller */
	195	_FDT((fdt_begin_node(fdt, "interrupt-controller@0")));
	196
	197	_FDT((fdt_property_string(fdt, "device_type",
	198	"PowerPC-External-Interrupt-Presentation")));
	199	_FDT((fdt_property_string(fdt, "compatible", "IBM,ppc-xicp")));
	200	_FDT((fdt_property_cell(fdt, "reg", 0)));
	201	_FDT((fdt_property(fdt, "interrupt-controller", NULL, 0)));
	202	_FDT((fdt_property(fdt, "ibm,interrupt-server-ranges",
	203	interrupt_server_ranges_prop,
	204	sizeof(interrupt_server_ranges_prop))));
	205
	206	_FDT((fdt_end_node(fdt)));
	207
4040ab72 DG	208	/* vdevice */
	209	_FDT((fdt_begin_node(fdt, "vdevice")));
	210
	211	_FDT((fdt_property_string(fdt, "device_type", "vdevice")));
	212	_FDT((fdt_property_string(fdt, "compatible", "IBM,vdevice")));
	213	_FDT((fdt_property_cell(fdt, "#address-cells", 0x1)));
	214	_FDT((fdt_property_cell(fdt, "#size-cells", 0x0)));
b5cec4c5 DG	215	_FDT((fdt_property_cell(fdt, "#interrupt-cells", 0x2)));
b5cec4c5 DG	216	_FDT((fdt_property(fdt, "interrupt-controller", NULL, 0)));
4040ab72 DG	217
	218	_FDT((fdt_end_node(fdt)));
	219
9fdf0c29 DG	220	_FDT((fdt_end_node(fdt))); /* close root node */
	221	_FDT((fdt_finish(fdt)));
	222
a3467baa DG	223	return fdt;
	224	}
	225
	226	static void spapr_finalize_fdt(sPAPREnvironment *spapr,
	227	target_phys_addr_t fdt_addr,
	228	target_phys_addr_t rtas_addr,
	229	target_phys_addr_t rtas_size)
	230	{
	231	int ret;
	232	void *fdt;
	233
7267c094	234	fdt = g_malloc(FDT_MAX_SIZE);
a3467baa DG	235
	236	/* open out the base tree into a temp buffer for the final tweaks */
	237	_FDT((fdt_open_into(spapr->fdt_skel, fdt, FDT_MAX_SIZE)));
4040ab72 DG	238
	239	ret = spapr_populate_vdevice(spapr->vio_bus, fdt);
	240	if (ret < 0) {
	241	fprintf(stderr, "couldn't setup vio devices in fdt\n");
	242	exit(1);
	243	}
	244
39ac8455 DG	245	/* RTAS */
	246	ret = spapr_rtas_device_tree_setup(fdt, rtas_addr, rtas_size);
	247	if (ret < 0) {
	248	fprintf(stderr, "Couldn't set up RTAS device tree properties\n");
	249	}
	250
4040ab72 DG	251	_FDT((fdt_pack(fdt)));
4040ab72 DG	252
a3467baa	253	cpu_physical_memory_write(fdt_addr, fdt, fdt_totalsize(fdt));
9fdf0c29	254
7267c094	255	g_free(fdt);
9fdf0c29 DG	256	}
	257
	258	static uint64_t translate_kernel_address(void *opaque, uint64_t addr)
	259	{
	260	return (addr & 0x0fffffff) + KERNEL_LOAD_ADDR;
	261	}
	262
	263	static void emulate_spapr_hypercall(CPUState *env)
	264	{
	265	env->gpr[3] = spapr_hypercall(env, env->gpr[3], &env->gpr[4]);
	266	}
	267
a3467baa DG	268	static void spapr_reset(void *opaque)
	269	{
	270	sPAPREnvironment spapr = (sPAPREnvironment )opaque;
	271
	272	fprintf(stderr, "sPAPR reset\n");
	273
	274	/* flush out the hash table */
	275	memset(spapr->htab, 0, spapr->htab_size);
	276
	277	/* Load the fdt */
	278	spapr_finalize_fdt(spapr, spapr->fdt_addr, spapr->rtas_addr,
	279	spapr->rtas_size);
	280
	281	/* Set up the entry state */
	282	first_cpu->gpr[3] = spapr->fdt_addr;
	283	first_cpu->gpr[5] = 0;
	284	first_cpu->halted = 0;
	285	first_cpu->nip = spapr->entry_point;
	286
	287	}
	288
9fdf0c29 DG	289	/* pSeries LPAR / sPAPR hardware init */
	290	static void ppc_spapr_init(ram_addr_t ram_size,
	291	const char *boot_device,
	292	const char *kernel_filename,
	293	const char *kernel_cmdline,
	294	const char *initrd_filename,
	295	const char *cpu_model)
	296	{
c7a5c0c9	297	CPUState *env;
9fdf0c29 DG	298	int i;
9fdf0c29 DG	299	ram_addr_t ram_offset;
a3467baa DG	300	uint32_t initrd_base;
a3467baa DG	301	long kernel_size, initrd_size, fw_size;
f43e3525	302	long pteg_shift = 17;
39ac8455	303	char *filename;
9fdf0c29	304
7267c094	305	spapr = g_malloc(sizeof(*spapr));
9fdf0c29 DG	306	cpu_ppc_hypercall = emulate_spapr_hypercall;
	307
	308	/* We place the device tree just below either the top of RAM, or
	309	* 2GB, so that it can be processed with 32-bit code if
	310	* necessary */
a3467baa DG	311	spapr->fdt_addr = MIN(ram_size, 0x80000000) - FDT_MAX_SIZE;
a3467baa DG	312	spapr->rtas_addr = spapr->fdt_addr - RTAS_MAX_SIZE;
9fdf0c29 DG	313
	314	/* init CPUs */
	315	if (cpu_model == NULL) {
	316	cpu_model = "POWER7";
	317	}
	318	for (i = 0; i < smp_cpus; i++) {
c7a5c0c9	319	env = cpu_init(cpu_model);
9fdf0c29 DG	320
	321	if (!env) {
	322	fprintf(stderr, "Unable to find PowerPC CPU definition\n");
	323	exit(1);
	324	}
	325	/* Set time-base frequency to 512 MHz */
	326	cpu_ppc_tb_init(env, TIMEBASE_FREQ);
	327	qemu_register_reset((QEMUResetHandler *)&cpu_reset, env);
	328
	329	env->hreset_vector = 0x60;
	330	env->hreset_excp_prefix = 0;
c7a5c0c9	331	env->gpr[3] = env->cpu_index;
9fdf0c29 DG	332	}
	333
	334	/* allocate RAM */
	335	ram_offset = qemu_ram_alloc(NULL, "ppc_spapr.ram", ram_size);
	336	cpu_register_physical_memory(0, ram_size, ram_offset);
	337
f43e3525 DG	338	/* allocate hash page table. For now we always make this 16mb,
	339	* later we should probably make it scale to the size of guest
	340	* RAM */
a3467baa	341	spapr->htab_size = 1ULL << (pteg_shift + 7);
f61b4bed	342	spapr->htab = qemu_memalign(spapr->htab_size, spapr->htab_size);
f43e3525	343
c7a5c0c9	344	for (env = first_cpu; env != NULL; env = env->next_cpu) {
a3467baa	345	env->external_htab = spapr->htab;
c7a5c0c9	346	env->htab_base = -1;
a3467baa	347	env->htab_mask = spapr->htab_size - 1;
f61b4bed AG	348
	349	/* Tell KVM that we're in PAPR mode */
	350	env->spr[SPR_SDR1] = (unsigned long)spapr->htab \|
	351	((pteg_shift + 7) - 18);
	352	env->spr[SPR_HIOR] = 0;
	353
	354	if (kvm_enabled()) {
	355	kvmppc_set_papr(env);
	356	}
f43e3525 DG	357	}
f43e3525 DG	358
39ac8455	359	filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, "spapr-rtas.bin");
a3467baa DG	360	spapr->rtas_size = load_image_targphys(filename, spapr->rtas_addr,
	361	ram_size - spapr->rtas_addr);
	362	if (spapr->rtas_size < 0) {
39ac8455 DG	363	hw_error("qemu: could not load LPAR rtas '%s'\n", filename);
	364	exit(1);
	365	}
7267c094	366	g_free(filename);
39ac8455	367
b5cec4c5	368	/* Set up Interrupt Controller */
c7a5c0c9	369	spapr->icp = xics_system_init(XICS_IRQS);
b5cec4c5 DG	370
b5cec4c5 DG	371	/* Set up VIO bus */
4040ab72 DG	372	spapr->vio_bus = spapr_vio_bus_init();
4040ab72 DG	373
277f9acf	374	for (i = 0; i < MAX_SERIAL_PORTS; i++) {
4040ab72	375	if (serial_hds[i]) {
b4a78527	376	spapr_vty_create(spapr->vio_bus, SPAPR_VTY_BASE_ADDRESS + i,
277f9acf	377	serial_hds[i]);
4040ab72 DG	378	}
4040ab72 DG	379	}
9fdf0c29	380
277f9acf	381	for (i = 0; i < nb_nics; i++) {
8d90ad90 DG	382	NICInfo *nd = &nd_table[i];
	383
	384	if (!nd->model) {
7267c094	385	nd->model = g_strdup("ibmveth");
8d90ad90 DG	386	}
	387
	388	if (strcmp(nd->model, "ibmveth") == 0) {
277f9acf	389	spapr_vlan_create(spapr->vio_bus, 0x1000 + i, nd);
8d90ad90 DG	390	} else {
	391	fprintf(stderr, "pSeries (sPAPR) platform does not support "
	392	"NIC model '%s' (only ibmveth is supported)\n",
	393	nd->model);
	394	exit(1);
	395	}
	396	}
	397
6e270446	398	for (i = 0; i <= drive_get_max_bus(IF_SCSI); i++) {
277f9acf	399	spapr_vscsi_create(spapr->vio_bus, 0x2000 + i);
6e270446 BH	400	}
6e270446 BH	401
9fdf0c29 DG	402	if (kernel_filename) {
	403	uint64_t lowaddr = 0;
	404
9fdf0c29 DG	405	kernel_size = load_elf(kernel_filename, translate_kernel_address, NULL,
	406	NULL, &lowaddr, NULL, 1, ELF_MACHINE, 0);
	407	if (kernel_size < 0) {
a3467baa DG	408	kernel_size = load_image_targphys(kernel_filename,
	409	KERNEL_LOAD_ADDR,
	410	ram_size - KERNEL_LOAD_ADDR);
9fdf0c29 DG	411	}
	412	if (kernel_size < 0) {
	413	fprintf(stderr, "qemu: could not load kernel '%s'\n",
	414	kernel_filename);
	415	exit(1);
	416	}
	417
	418	/* load initrd */
	419	if (initrd_filename) {
	420	initrd_base = INITRD_LOAD_ADDR;
	421	initrd_size = load_image_targphys(initrd_filename, initrd_base,
	422	ram_size - initrd_base);
	423	if (initrd_size < 0) {
	424	fprintf(stderr, "qemu: could not load initial ram disk '%s'\n",
	425	initrd_filename);
	426	exit(1);
	427	}
	428	} else {
	429	initrd_base = 0;
	430	initrd_size = 0;
	431	}
a3467baa DG	432
a3467baa DG	433	spapr->entry_point = KERNEL_LOAD_ADDR;
9fdf0c29	434	} else {
a9f8ad8f DG	435	if (ram_size < (MIN_RAM_SLOF << 20)) {
	436	fprintf(stderr, "qemu: pSeries SLOF firmware requires >= "
	437	"%ldM guest RAM\n", MIN_RAM_SLOF);
	438	exit(1);
	439	}
	440	filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, "slof.bin");
	441	fw_size = load_image_targphys(filename, 0, FW_MAX_SIZE);
	442	if (fw_size < 0) {
	443	hw_error("qemu: could not load LPAR rtas '%s'\n", filename);
	444	exit(1);
	445	}
7267c094	446	g_free(filename);
a3467baa	447	spapr->entry_point = 0x100;
a9f8ad8f DG	448	initrd_base = 0;
	449	initrd_size = 0;
	450
	451	/* SLOF will startup the secondary CPUs using RTAS,
	452	rather than expecting a kexec() style entry */
c7a5c0c9 DG	453	for (env = first_cpu; env != NULL; env = env->next_cpu) {
c7a5c0c9 DG	454	env->halted = 1;
a9f8ad8f	455	}
9fdf0c29 DG	456	}
	457
	458	/* Prepare the device tree */
a3467baa DG	459	spapr->fdt_skel = spapr_create_fdt_skel(cpu_model,
	460	initrd_base, initrd_size,
	461	boot_device, kernel_cmdline,
	462	pteg_shift + 7);
	463	assert(spapr->fdt_skel != NULL);
9fdf0c29	464
a3467baa	465	qemu_register_reset(spapr_reset, spapr);
9fdf0c29 DG	466	}
	467
	468	static QEMUMachine spapr_machine = {
	469	.name = "pseries",
	470	.desc = "pSeries Logical Partition (PAPR compliant)",
	471	.init = ppc_spapr_init,
	472	.max_cpus = MAX_CPUS,
	473	.no_vga = 1,
	474	.no_parallel = 1,
6e270446	475	.use_scsi = 1,
9fdf0c29 DG	476	};
	477
	478	static void spapr_machine_init(void)
	479	{
	480	qemu_register_machine(&spapr_machine);
	481	}
	482
	483	machine_init(spapr_machine_init);