Start implementing pSeries logical partition machine

This patch adds a "pseries" machine to qemu.  This aims to emulate a
logical partition on an IBM pSeries machine, compliant to the
"PowerPC Architecture Platform Requirements" (PAPR) document.

This initial version is quite limited, it implements a basic machine
and PAPR hypercall emulation.  So far only one hypercall is present -
H_PUT_TERM_CHAR - so that a (write-only) console is available.

Multiple CPUs are permitted, with SMP entry handled kexec() style.

The machine so far more resembles an old POWER4 style "full system
partition" rather than a modern LPAR, in that the guest manages the
page tables directly, rather than via hypercalls.

The machine requires qemu to be configured with --enable-fdt.  The
machine can (so far) only be booted with -kernel - i.e. no partition
firmware is provided.

Signed-off-by: David Gibson <dwg@au1.ibm.com>
Signed-off-by: Alexander Graf <agraf@suse.de>

1 files changed, 313 insertions, 0 deletions

diff --git a/hw/spapr.c b/hw/spapr.c
new file mode 100644
index 0000000..410213a
--- /dev/null
+++ b/hw/spapr.c
@@ -0,0 +1,313 @@
+/*
+ * 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 "qemu-char.h"
+#include "hw.h"
+#include "elf.h"
+
+#include "hw/boards.h"
+#include "hw/ppc.h"
+#include "hw/loader.h"
+
+#include "hw/spapr.h"
+
+#include <libfdt.h>
+
+#define KERNEL_LOAD_ADDR        0x00000000
+#define INITRD_LOAD_ADDR        0x02800000
+#define FDT_MAX_SIZE            0x10000
+
+#define TIMEBASE_FREQ           512000000ULL
+
+#define MAX_CPUS                32
+
+sPAPREnvironment *spapr;
+
+static void *spapr_create_fdt(int *fdt_size, ram_addr_t ramsize,
+                              const char *cpu_model, CPUState *envs[],
+                              sPAPREnvironment *spapr,
+                              target_phys_addr_t initrd_base,
+                              target_phys_addr_t initrd_size,
+                              const char *kernel_cmdline)
+{
+    void *fdt;
+    uint64_t mem_reg_property[] = { 0, cpu_to_be64(ramsize) };
+    uint32_t start_prop = cpu_to_be32(initrd_base);
+    uint32_t end_prop = cpu_to_be32(initrd_base + initrd_size);
+    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 = qemu_mallocz(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", "qemu,emulated-pSeries-LPAR")));
+
+    _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_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 = qemu_strdup(cpu_model);
+
+    for (i = 0; i < strlen(modelname); i++) {
+        modelname[i] = toupper(modelname[i]);
+    }
+
+    for (i = 0; i < smp_cpus; i++) {
+        CPUState *env = envs[i];
+        char *nodename;
+        uint32_t segs[] = {cpu_to_be32(28), cpu_to_be32(40),
+                           0xffffffff, 0xffffffff};
+
+        if (asprintf(&nodename, "%s@%x", modelname, i) < 0) {
+            fprintf(stderr, "Allocation failure\n");
+            exit(1);
+        }
+
+        _FDT((fdt_begin_node(fdt, nodename)));
+
+        free(nodename);
+
+        _FDT((fdt_property_cell(fdt, "reg", i)));
+        _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)));
+        _FDT((fdt_property_string(fdt, "status", "okay")));
+        _FDT((fdt_property(fdt, "64-bit", NULL, 0)));
+
+        if (envs[i]->mmu_model & POWERPC_MMU_1TSEG) {
+            _FDT((fdt_property(fdt, "ibm,processor-segment-sizes",
+                               segs, sizeof(segs))));
+        }
+
+        _FDT((fdt_end_node(fdt)));
+    }
+
+    qemu_free(modelname);
+
+    _FDT((fdt_end_node(fdt)));
+
+    _FDT((fdt_end_node(fdt))); /* close root node */
+    _FDT((fdt_finish(fdt)));
+
+    *fdt_size = fdt_totalsize(fdt);
+
+    return 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]);
+}
+
+/* FIXME: hack until we implement the proper VIO console */
+static target_ulong h_put_term_char(CPUState *env, sPAPREnvironment *spapr,
+                                    target_ulong opcode, target_ulong *args)
+{
+    uint8_t buf[16];
+
+    stq_p(buf, args[2]);
+    stq_p(buf + 8, args[3]);
+
+    qemu_chr_write(serial_hds[0], buf, args[1]);
+
+    return 0;
+}
+
+
+/* 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 *envs[MAX_CPUS];
+    void *fdt;
+    int i;
+    ram_addr_t ram_offset;
+    target_phys_addr_t fdt_addr;
+    uint32_t kernel_base, initrd_base;
+    long kernel_size, initrd_size;
+    int fdt_size;
+
+    spapr = qemu_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 */
+    fdt_addr = MIN(ram_size, 0x80000000) - FDT_MAX_SIZE;
+
+    /* init CPUs */
+    if (cpu_model == NULL) {
+        cpu_model = "POWER7";
+    }
+    for (i = 0; i < smp_cpus; i++) {
+        CPUState *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] = i;
+
+        envs[i] = env;
+    }
+
+    /* allocate RAM */
+    ram_offset = qemu_ram_alloc(NULL, "ppc_spapr.ram", ram_size);
+    cpu_register_physical_memory(0, ram_size, ram_offset);
+
+    spapr_register_hypercall(H_PUT_TERM_CHAR, h_put_term_char);
+
+    if (kernel_filename) {
+        uint64_t lowaddr = 0;
+
+        kernel_base = KERNEL_LOAD_ADDR;
+
+        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_base,
+                                              ram_size - kernel_base);
+        }
+        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;
+        }
+
+    } else {
+        fprintf(stderr, "pSeries machine needs -kernel for now");
+        exit(1);
+    }
+
+    /* Prepare the device tree */
+    fdt = spapr_create_fdt(&fdt_size, ram_size, cpu_model, envs, spapr,
+                           initrd_base, initrd_size, kernel_cmdline);
+    assert(fdt != NULL);
+
+    cpu_physical_memory_write(fdt_addr, fdt, fdt_size);
+
+    qemu_free(fdt);
+
+    envs[0]->gpr[3] = fdt_addr;
+    envs[0]->gpr[5] = 0;
+    envs[0]->hreset_vector = kernel_base;
+}
+
+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,
+};
+
+static void spapr_machine_init(void)
+{
+    qemu_register_machine(&spapr_machine);
+}
+
+machine_init(spapr_machine_init);