#include "hw/fw-path-provider.h"
#include "elf.h"
#include "net/net.h"
+#include "sysemu/device_tree.h"
#include "sysemu/block-backend.h"
#include "sysemu/cpus.h"
#include "sysemu/kvm.h"
+#include "sysemu/device_tree.h"
#include "kvm_ppc.h"
#include "migration/migration.h"
#include "mmu-hash64.h"
#include "hw/nmi.h"
#include "hw/compat.h"
+#include "qemu-common.h"
#include <libfdt.h>
*
* We load our kernel at 4M, leaving space for SLOF initial image
*/
-#define FDT_MAX_SIZE 0x40000
+#define FDT_MAX_SIZE 0x100000
#define RTAS_MAX_SIZE 0x10000
#define RTAS_MAX_ADDR 0x80000000 /* RTAS must stay below that */
#define FW_MAX_SIZE 0x400000
#define TIMEBASE_FREQ 512000000ULL
-#define MAX_CPUS 255
-
#define PHANDLE_XICP 0x00001111
#define HTAB_SIZE(spapr) (1ULL << ((spapr)->htab_shift))
-typedef struct sPAPRMachineState sPAPRMachineState;
-
-#define TYPE_SPAPR_MACHINE "spapr-machine"
-#define SPAPR_MACHINE(obj) \
- OBJECT_CHECK(sPAPRMachineState, (obj), TYPE_SPAPR_MACHINE)
-
-/**
- * sPAPRMachineState:
- */
-struct sPAPRMachineState {
- /*< private >*/
- MachineState parent_obj;
-
- /*< public >*/
- char *kvm_type;
-};
-
-sPAPREnvironment *spapr;
-
static XICSState *try_create_xics(const char *type, int nr_servers,
int nr_irqs, Error **errp)
{
return ret;
}
-static int spapr_fixup_cpu_dt(void *fdt, sPAPREnvironment *spapr)
+static int spapr_fixup_cpu_numa_dt(void *fdt, int offset, CPUState *cs)
+{
+ int ret = 0;
+ PowerPCCPU *cpu = POWERPC_CPU(cs);
+ int index = ppc_get_vcpu_dt_id(cpu);
+ uint32_t associativity[] = {cpu_to_be32(0x5),
+ cpu_to_be32(0x0),
+ cpu_to_be32(0x0),
+ cpu_to_be32(0x0),
+ cpu_to_be32(cs->numa_node),
+ cpu_to_be32(index)};
+
+ /* Advertise NUMA via ibm,associativity */
+ if (nb_numa_nodes > 1) {
+ ret = fdt_setprop(fdt, offset, "ibm,associativity", associativity,
+ sizeof(associativity));
+ }
+
+ return ret;
+}
+
+static int spapr_fixup_cpu_dt(void *fdt, sPAPRMachineState *spapr)
{
int ret = 0, offset, cpus_offset;
CPUState *cs;
PowerPCCPU *cpu = POWERPC_CPU(cs);
DeviceClass *dc = DEVICE_GET_CLASS(cs);
int index = ppc_get_vcpu_dt_id(cpu);
- uint32_t associativity[] = {cpu_to_be32(0x5),
- cpu_to_be32(0x0),
- cpu_to_be32(0x0),
- cpu_to_be32(0x0),
- cpu_to_be32(cs->numa_node),
- cpu_to_be32(index)};
if ((index % smt) != 0) {
continue;
}
}
- if (nb_numa_nodes > 1) {
- ret = fdt_setprop(fdt, offset, "ibm,associativity", associativity,
- sizeof(associativity));
- if (ret < 0) {
- return ret;
- }
- }
-
ret = fdt_setprop(fdt, offset, "ibm,pft-size",
pft_size_prop, sizeof(pft_size_prop));
if (ret < 0) {
return ret;
}
+ ret = spapr_fixup_cpu_numa_dt(fdt, offset, cs);
+ if (ret < 0) {
+ return ret;
+ }
+
ret = spapr_fixup_cpu_smt_dt(fdt, offset, cpu,
ppc_get_compat_smt_threads(cpu));
if (ret < 0) {
static hwaddr spapr_node0_size(void)
{
+ MachineState *machine = MACHINE(qdev_get_machine());
+
if (nb_numa_nodes) {
int i;
for (i = 0; i < nb_numa_nodes; ++i) {
if (numa_info[i].node_mem) {
- return MIN(pow2floor(numa_info[i].node_mem), ram_size);
+ return MIN(pow2floor(numa_info[i].node_mem),
+ machine->ram_size);
}
}
}
- return ram_size;
+ return machine->ram_size;
}
#define _FDT(exp) \
uint32_t epow_irq)
{
void *fdt;
- CPUState *cs;
uint32_t start_prop = cpu_to_be32(initrd_base);
uint32_t end_prop = cpu_to_be32(initrd_base + initrd_size);
GString *hypertas = g_string_sized_new(256);
GString *qemu_hypertas = g_string_sized_new(256);
uint32_t refpoints[] = {cpu_to_be32(0x4), cpu_to_be32(0x4)};
- uint32_t interrupt_server_ranges_prop[] = {0, cpu_to_be32(smp_cpus)};
- int smt = kvmppc_smt_threads();
+ uint32_t interrupt_server_ranges_prop[] = {0, cpu_to_be32(max_cpus)};
unsigned char vec5[] = {0x0, 0x0, 0x0, 0x0, 0x0, 0x80};
- QemuOpts *opts = qemu_opts_find(qemu_find_opts("smp-opts"), NULL);
- unsigned sockets = opts ? qemu_opt_get_number(opts, "sockets", 0) : 0;
- uint32_t cpus_per_socket = sockets ? (smp_cpus / sockets) : 1;
char *buf;
add_str(hypertas, "hcall-pft");
_FDT((fdt_property_string(fdt, "vm,uuid", buf)));
g_free(buf);
+ if (qemu_get_vm_name()) {
+ _FDT((fdt_property_string(fdt, "ibm,partition-name",
+ qemu_get_vm_name())));
+ }
+
_FDT((fdt_property_cell(fdt, "#address-cells", 0x2)));
_FDT((fdt_property_cell(fdt, "#size-cells", 0x2)));
_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)));
-
- CPU_FOREACH(cs) {
- PowerPCCPU *cpu = POWERPC_CPU(cs);
- CPUPPCState *env = &cpu->env;
- DeviceClass *dc = DEVICE_GET_CLASS(cs);
- PowerPCCPUClass *pcc = POWERPC_CPU_GET_CLASS(cs);
- int index = ppc_get_vcpu_dt_id(cpu);
- 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;
- uint32_t page_sizes_prop[64];
- size_t page_sizes_prop_size;
-
- if ((index % smt) != 0) {
- continue;
- }
-
- nodename = g_strdup_printf("%s@%x", dc->fw_name, index);
-
- _FDT((fdt_begin_node(fdt, nodename)));
-
- g_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, "d-cache-block-size",
- env->dcache_line_size)));
- _FDT((fdt_property_cell(fdt, "d-cache-line-size",
- env->dcache_line_size)));
- _FDT((fdt_property_cell(fdt, "i-cache-block-size",
- env->icache_line_size)));
- _FDT((fdt_property_cell(fdt, "i-cache-line-size",
- env->icache_line_size)));
-
- if (pcc->l1_dcache_size) {
- _FDT((fdt_property_cell(fdt, "d-cache-size", pcc->l1_dcache_size)));
- } else {
- fprintf(stderr, "Warning: Unknown L1 dcache size for cpu\n");
- }
- if (pcc->l1_icache_size) {
- _FDT((fdt_property_cell(fdt, "i-cache-size", pcc->l1_icache_size)));
- } else {
- fprintf(stderr, "Warning: Unknown L1 icache size for cpu\n");
- }
-
- _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_string(fdt, "status", "okay")));
- _FDT((fdt_property(fdt, "64-bit", NULL, 0)));
-
- if (env->spr_cb[SPR_PURR].oea_read) {
- _FDT((fdt_property(fdt, "ibm,purr", NULL, 0)));
- }
-
- if (env->mmu_model & POWERPC_MMU_1TSEG) {
- _FDT((fdt_property(fdt, "ibm,processor-segment-sizes",
- segs, sizeof(segs))));
- }
-
- /* Advertise VMX/VSX (vector extensions) if available
- * 0 / no property == no vector extensions
- * 1 == VMX / Altivec available
- * 2 == VSX available */
- if (env->insns_flags & PPC_ALTIVEC) {
- uint32_t vmx = (env->insns_flags2 & PPC2_VSX) ? 2 : 1;
-
- _FDT((fdt_property_cell(fdt, "ibm,vmx", vmx)));
- }
-
- /* Advertise DFP (Decimal Floating Point) if available
- * 0 / no property == no DFP
- * 1 == DFP available */
- if (env->insns_flags2 & PPC2_DFP) {
- _FDT((fdt_property_cell(fdt, "ibm,dfp", 1)));
- }
-
- page_sizes_prop_size = create_page_sizes_prop(env, page_sizes_prop,
- sizeof(page_sizes_prop));
- if (page_sizes_prop_size) {
- _FDT((fdt_property(fdt, "ibm,segment-page-sizes",
- page_sizes_prop, page_sizes_prop_size)));
- }
-
- _FDT((fdt_property_cell(fdt, "ibm,chip-id",
- cs->cpu_index / cpus_per_socket)));
-
- _FDT((fdt_end_node(fdt)));
- }
-
- _FDT((fdt_end_node(fdt)));
-
/* RTAS */
_FDT((fdt_begin_node(fdt, "rtas")));
_FDT((fdt_property_cell(fdt, "rtas-event-scan-rate",
RTAS_EVENT_SCAN_RATE)));
+ if (msi_supported) {
+ _FDT((fdt_property(fdt, "ibm,change-msix-capable", NULL, 0)));
+ }
+
/*
* According to PAPR, rtas ibm,os-term does not guarantee a return
* back to the guest cpu.
return fdt;
}
-int spapr_h_cas_compose_response(target_ulong addr, target_ulong size)
-{
- void *fdt, *fdt_skel;
- sPAPRDeviceTreeUpdateHeader hdr = { .version_id = 1 };
-
- size -= sizeof(hdr);
-
- /* Create sceleton */
- fdt_skel = g_malloc0(size);
- _FDT((fdt_create(fdt_skel, size)));
- _FDT((fdt_begin_node(fdt_skel, "")));
- _FDT((fdt_end_node(fdt_skel)));
- _FDT((fdt_finish(fdt_skel)));
- fdt = g_malloc0(size);
- _FDT((fdt_open_into(fdt_skel, fdt, size)));
- g_free(fdt_skel);
-
- /* Fix skeleton up */
- _FDT((spapr_fixup_cpu_dt(fdt, spapr)));
-
- /* Pack resulting tree */
- _FDT((fdt_pack(fdt)));
-
- if (fdt_totalsize(fdt) + sizeof(hdr) > size) {
- trace_spapr_cas_failed(size);
- return -1;
- }
-
- cpu_physical_memory_write(addr, &hdr, sizeof(hdr));
- cpu_physical_memory_write(addr + sizeof(hdr), fdt, fdt_totalsize(fdt));
- trace_spapr_cas_continue(fdt_totalsize(fdt) + sizeof(hdr));
- g_free(fdt);
-
- return 0;
-}
-
-static void spapr_populate_memory_node(void *fdt, int nodeid, hwaddr start,
+static int spapr_populate_memory_node(void *fdt, int nodeid, hwaddr start,
hwaddr size)
{
uint32_t associativity[] = {
sizeof(mem_reg_property))));
_FDT((fdt_setprop(fdt, off, "ibm,associativity", associativity,
sizeof(associativity))));
+ return off;
}
-static int spapr_populate_memory(sPAPREnvironment *spapr, void *fdt)
+static int spapr_populate_memory(sPAPRMachineState *spapr, void *fdt)
{
+ MachineState *machine = MACHINE(spapr);
hwaddr mem_start, node_size;
int i, nb_nodes = nb_numa_nodes;
NodeInfo *nodes = numa_info;
/* No NUMA nodes, assume there is just one node with whole RAM */
if (!nb_numa_nodes) {
nb_nodes = 1;
- ramnode.node_mem = ram_size;
+ ramnode.node_mem = machine->ram_size;
nodes = &ramnode;
}
if (!nodes[i].node_mem) {
continue;
}
- if (mem_start >= ram_size) {
+ if (mem_start >= machine->ram_size) {
node_size = 0;
} else {
node_size = nodes[i].node_mem;
- if (node_size > ram_size - mem_start) {
- node_size = ram_size - mem_start;
+ if (node_size > machine->ram_size - mem_start) {
+ node_size = machine->ram_size - mem_start;
}
}
if (!mem_start) {
return 0;
}
-static void spapr_finalize_fdt(sPAPREnvironment *spapr,
+static void spapr_populate_cpu_dt(CPUState *cs, void *fdt, int offset,
+ sPAPRMachineState *spapr)
+{
+ PowerPCCPU *cpu = POWERPC_CPU(cs);
+ CPUPPCState *env = &cpu->env;
+ PowerPCCPUClass *pcc = POWERPC_CPU_GET_CLASS(cs);
+ int index = ppc_get_vcpu_dt_id(cpu);
+ 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;
+ uint32_t page_sizes_prop[64];
+ size_t page_sizes_prop_size;
+ uint32_t vcpus_per_socket = smp_threads * smp_cores;
+ uint32_t pft_size_prop[] = {0, cpu_to_be32(spapr->htab_shift)};
+
+ /* Note: we keep CI large pages off for now because a 64K capable guest
+ * provisioned with large pages might otherwise try to map a qemu
+ * framebuffer (or other kind of memory mapped PCI BAR) using 64K pages
+ * even if that qemu runs on a 4k host.
+ *
+ * We can later add this bit back when we are confident this is not
+ * an issue (!HV KVM or 64K host)
+ */
+ uint8_t pa_features_206[] = { 6, 0,
+ 0xf6, 0x1f, 0xc7, 0x00, 0x80, 0xc0 };
+ uint8_t pa_features_207[] = { 24, 0,
+ 0xf6, 0x1f, 0xc7, 0xc0, 0x80, 0xf0,
+ 0x80, 0x00, 0x00, 0x00, 0x00, 0x00,
+ 0x00, 0x00, 0x00, 0x00, 0x80, 0x00,
+ 0x80, 0x00, 0x80, 0x00, 0x80, 0x00 };
+ uint8_t *pa_features;
+ size_t pa_size;
+
+ _FDT((fdt_setprop_cell(fdt, offset, "reg", index)));
+ _FDT((fdt_setprop_string(fdt, offset, "device_type", "cpu")));
+
+ _FDT((fdt_setprop_cell(fdt, offset, "cpu-version", env->spr[SPR_PVR])));
+ _FDT((fdt_setprop_cell(fdt, offset, "d-cache-block-size",
+ env->dcache_line_size)));
+ _FDT((fdt_setprop_cell(fdt, offset, "d-cache-line-size",
+ env->dcache_line_size)));
+ _FDT((fdt_setprop_cell(fdt, offset, "i-cache-block-size",
+ env->icache_line_size)));
+ _FDT((fdt_setprop_cell(fdt, offset, "i-cache-line-size",
+ env->icache_line_size)));
+
+ if (pcc->l1_dcache_size) {
+ _FDT((fdt_setprop_cell(fdt, offset, "d-cache-size",
+ pcc->l1_dcache_size)));
+ } else {
+ fprintf(stderr, "Warning: Unknown L1 dcache size for cpu\n");
+ }
+ if (pcc->l1_icache_size) {
+ _FDT((fdt_setprop_cell(fdt, offset, "i-cache-size",
+ pcc->l1_icache_size)));
+ } else {
+ fprintf(stderr, "Warning: Unknown L1 icache size for cpu\n");
+ }
+
+ _FDT((fdt_setprop_cell(fdt, offset, "timebase-frequency", tbfreq)));
+ _FDT((fdt_setprop_cell(fdt, offset, "clock-frequency", cpufreq)));
+ _FDT((fdt_setprop_cell(fdt, offset, "slb-size", env->slb_nr)));
+ _FDT((fdt_setprop_cell(fdt, offset, "ibm,slb-size", env->slb_nr)));
+ _FDT((fdt_setprop_string(fdt, offset, "status", "okay")));
+ _FDT((fdt_setprop(fdt, offset, "64-bit", NULL, 0)));
+
+ if (env->spr_cb[SPR_PURR].oea_read) {
+ _FDT((fdt_setprop(fdt, offset, "ibm,purr", NULL, 0)));
+ }
+
+ if (env->mmu_model & POWERPC_MMU_1TSEG) {
+ _FDT((fdt_setprop(fdt, offset, "ibm,processor-segment-sizes",
+ segs, sizeof(segs))));
+ }
+
+ /* Advertise VMX/VSX (vector extensions) if available
+ * 0 / no property == no vector extensions
+ * 1 == VMX / Altivec available
+ * 2 == VSX available */
+ if (env->insns_flags & PPC_ALTIVEC) {
+ uint32_t vmx = (env->insns_flags2 & PPC2_VSX) ? 2 : 1;
+
+ _FDT((fdt_setprop_cell(fdt, offset, "ibm,vmx", vmx)));
+ }
+
+ /* Advertise DFP (Decimal Floating Point) if available
+ * 0 / no property == no DFP
+ * 1 == DFP available */
+ if (env->insns_flags2 & PPC2_DFP) {
+ _FDT((fdt_setprop_cell(fdt, offset, "ibm,dfp", 1)));
+ }
+
+ page_sizes_prop_size = create_page_sizes_prop(env, page_sizes_prop,
+ sizeof(page_sizes_prop));
+ if (page_sizes_prop_size) {
+ _FDT((fdt_setprop(fdt, offset, "ibm,segment-page-sizes",
+ page_sizes_prop, page_sizes_prop_size)));
+ }
+
+ /* Do the ibm,pa-features property, adjust it for ci-large-pages */
+ if (env->mmu_model == POWERPC_MMU_2_06) {
+ pa_features = pa_features_206;
+ pa_size = sizeof(pa_features_206);
+ } else /* env->mmu_model == POWERPC_MMU_2_07 */ {
+ pa_features = pa_features_207;
+ pa_size = sizeof(pa_features_207);
+ }
+ if (env->ci_large_pages) {
+ pa_features[3] |= 0x20;
+ }
+ _FDT((fdt_setprop(fdt, offset, "ibm,pa-features", pa_features, pa_size)));
+
+ _FDT((fdt_setprop_cell(fdt, offset, "ibm,chip-id",
+ cs->cpu_index / vcpus_per_socket)));
+
+ _FDT((fdt_setprop(fdt, offset, "ibm,pft-size",
+ pft_size_prop, sizeof(pft_size_prop))));
+
+ _FDT(spapr_fixup_cpu_numa_dt(fdt, offset, cs));
+
+ _FDT(spapr_fixup_cpu_smt_dt(fdt, offset, cpu,
+ ppc_get_compat_smt_threads(cpu)));
+}
+
+static void spapr_populate_cpus_dt_node(void *fdt, sPAPRMachineState *spapr)
+{
+ CPUState *cs;
+ int cpus_offset;
+ char *nodename;
+ int smt = kvmppc_smt_threads();
+
+ cpus_offset = fdt_add_subnode(fdt, 0, "cpus");
+ _FDT(cpus_offset);
+ _FDT((fdt_setprop_cell(fdt, cpus_offset, "#address-cells", 0x1)));
+ _FDT((fdt_setprop_cell(fdt, cpus_offset, "#size-cells", 0x0)));
+
+ /*
+ * We walk the CPUs in reverse order to ensure that CPU DT nodes
+ * created by fdt_add_subnode() end up in the right order in FDT
+ * for the guest kernel the enumerate the CPUs correctly.
+ */
+ CPU_FOREACH_REVERSE(cs) {
+ PowerPCCPU *cpu = POWERPC_CPU(cs);
+ int index = ppc_get_vcpu_dt_id(cpu);
+ DeviceClass *dc = DEVICE_GET_CLASS(cs);
+ int offset;
+
+ if ((index % smt) != 0) {
+ continue;
+ }
+
+ nodename = g_strdup_printf("%s@%x", dc->fw_name, index);
+ offset = fdt_add_subnode(fdt, cpus_offset, nodename);
+ g_free(nodename);
+ _FDT(offset);
+ spapr_populate_cpu_dt(cs, fdt, offset, spapr);
+ }
+
+}
+
+/*
+ * Adds ibm,dynamic-reconfiguration-memory node.
+ * Refer to docs/specs/ppc-spapr-hotplug.txt for the documentation
+ * of this device tree node.
+ */
+static int spapr_populate_drconf_memory(sPAPRMachineState *spapr, void *fdt)
+{
+ MachineState *machine = MACHINE(spapr);
+ int ret, i, offset;
+ uint64_t lmb_size = SPAPR_MEMORY_BLOCK_SIZE;
+ uint32_t prop_lmb_size[] = {0, cpu_to_be32(lmb_size)};
+ uint32_t nr_lmbs = (machine->maxram_size - machine->ram_size)/lmb_size;
+ uint32_t *int_buf, *cur_index, buf_len;
+ int nr_nodes = nb_numa_nodes ? nb_numa_nodes : 1;
+
+ /*
+ * Allocate enough buffer size to fit in ibm,dynamic-memory
+ * or ibm,associativity-lookup-arrays
+ */
+ buf_len = MAX(nr_lmbs * SPAPR_DR_LMB_LIST_ENTRY_SIZE + 1, nr_nodes * 4 + 2)
+ * sizeof(uint32_t);
+ cur_index = int_buf = g_malloc0(buf_len);
+
+ offset = fdt_add_subnode(fdt, 0, "ibm,dynamic-reconfiguration-memory");
+
+ ret = fdt_setprop(fdt, offset, "ibm,lmb-size", prop_lmb_size,
+ sizeof(prop_lmb_size));
+ if (ret < 0) {
+ goto out;
+ }
+
+ ret = fdt_setprop_cell(fdt, offset, "ibm,memory-flags-mask", 0xff);
+ if (ret < 0) {
+ goto out;
+ }
+
+ ret = fdt_setprop_cell(fdt, offset, "ibm,memory-preservation-time", 0x0);
+ if (ret < 0) {
+ goto out;
+ }
+
+ /* ibm,dynamic-memory */
+ int_buf[0] = cpu_to_be32(nr_lmbs);
+ cur_index++;
+ for (i = 0; i < nr_lmbs; i++) {
+ sPAPRDRConnector *drc;
+ sPAPRDRConnectorClass *drck;
+ uint64_t addr = i * lmb_size + spapr->hotplug_memory.base;;
+ uint32_t *dynamic_memory = cur_index;
+
+ drc = spapr_dr_connector_by_id(SPAPR_DR_CONNECTOR_TYPE_LMB,
+ addr/lmb_size);
+ g_assert(drc);
+ drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc);
+
+ dynamic_memory[0] = cpu_to_be32(addr >> 32);
+ dynamic_memory[1] = cpu_to_be32(addr & 0xffffffff);
+ dynamic_memory[2] = cpu_to_be32(drck->get_index(drc));
+ dynamic_memory[3] = cpu_to_be32(0); /* reserved */
+ dynamic_memory[4] = cpu_to_be32(numa_get_node(addr, NULL));
+ if (addr < machine->ram_size ||
+ memory_region_present(get_system_memory(), addr)) {
+ dynamic_memory[5] = cpu_to_be32(SPAPR_LMB_FLAGS_ASSIGNED);
+ } else {
+ dynamic_memory[5] = cpu_to_be32(0);
+ }
+
+ cur_index += SPAPR_DR_LMB_LIST_ENTRY_SIZE;
+ }
+ ret = fdt_setprop(fdt, offset, "ibm,dynamic-memory", int_buf, buf_len);
+ if (ret < 0) {
+ goto out;
+ }
+
+ /* ibm,associativity-lookup-arrays */
+ cur_index = int_buf;
+ int_buf[0] = cpu_to_be32(nr_nodes);
+ int_buf[1] = cpu_to_be32(4); /* Number of entries per associativity list */
+ cur_index += 2;
+ for (i = 0; i < nr_nodes; i++) {
+ uint32_t associativity[] = {
+ cpu_to_be32(0x0),
+ cpu_to_be32(0x0),
+ cpu_to_be32(0x0),
+ cpu_to_be32(i)
+ };
+ memcpy(cur_index, associativity, sizeof(associativity));
+ cur_index += 4;
+ }
+ ret = fdt_setprop(fdt, offset, "ibm,associativity-lookup-arrays", int_buf,
+ (cur_index - int_buf) * sizeof(uint32_t));
+out:
+ g_free(int_buf);
+ return ret;
+}
+
+int spapr_h_cas_compose_response(sPAPRMachineState *spapr,
+ target_ulong addr, target_ulong size,
+ bool cpu_update, bool memory_update)
+{
+ void *fdt, *fdt_skel;
+ sPAPRDeviceTreeUpdateHeader hdr = { .version_id = 1 };
+ sPAPRMachineClass *smc = SPAPR_MACHINE_GET_CLASS(qdev_get_machine());
+
+ size -= sizeof(hdr);
+
+ /* Create sceleton */
+ fdt_skel = g_malloc0(size);
+ _FDT((fdt_create(fdt_skel, size)));
+ _FDT((fdt_begin_node(fdt_skel, "")));
+ _FDT((fdt_end_node(fdt_skel)));
+ _FDT((fdt_finish(fdt_skel)));
+ fdt = g_malloc0(size);
+ _FDT((fdt_open_into(fdt_skel, fdt, size)));
+ g_free(fdt_skel);
+
+ /* Fixup cpu nodes */
+ if (cpu_update) {
+ _FDT((spapr_fixup_cpu_dt(fdt, spapr)));
+ }
+
+ /* Generate memory nodes or ibm,dynamic-reconfiguration-memory node */
+ if (memory_update && smc->dr_lmb_enabled) {
+ _FDT((spapr_populate_drconf_memory(spapr, fdt)));
+ }
+
+ /* Pack resulting tree */
+ _FDT((fdt_pack(fdt)));
+
+ if (fdt_totalsize(fdt) + sizeof(hdr) > size) {
+ trace_spapr_cas_failed(size);
+ return -1;
+ }
+
+ cpu_physical_memory_write(addr, &hdr, sizeof(hdr));
+ cpu_physical_memory_write(addr + sizeof(hdr), fdt, fdt_totalsize(fdt));
+ trace_spapr_cas_continue(fdt_totalsize(fdt) + sizeof(hdr));
+ g_free(fdt);
+
+ return 0;
+}
+
+static void spapr_finalize_fdt(sPAPRMachineState *spapr,
hwaddr fdt_addr,
hwaddr rtas_addr,
hwaddr rtas_size)
{
MachineState *machine = MACHINE(qdev_get_machine());
+ sPAPRMachineClass *smc = SPAPR_MACHINE_GET_CLASS(machine);
const char *boot_device = machine->boot_order;
int ret, i;
size_t cb = 0;
exit(1);
}
+ if (object_resolve_path_type("", TYPE_SPAPR_RNG, NULL)) {
+ ret = spapr_rng_populate_dt(fdt);
+ if (ret < 0) {
+ fprintf(stderr, "could not set up rng device in the fdt\n");
+ exit(1);
+ }
+ }
+
QLIST_FOREACH(phb, &spapr->phbs, list) {
ret = spapr_populate_pci_dt(phb, PHANDLE_XICP, fdt);
}
fprintf(stderr, "Couldn't set up RTAS device tree properties\n");
}
- /* Advertise NUMA via ibm,associativity */
- ret = spapr_fixup_cpu_dt(fdt, spapr);
- if (ret < 0) {
- fprintf(stderr, "Couldn't finalize CPU device tree properties\n");
- }
+ /* cpus */
+ spapr_populate_cpus_dt_node(fdt, spapr);
bootlist = get_boot_devices_list(&cb, true);
if (cb && bootlist) {
spapr_populate_chosen_stdout(fdt, spapr->vio_bus);
}
+ if (smc->dr_lmb_enabled) {
+ _FDT(spapr_drc_populate_dt(fdt, 0, NULL, SPAPR_DR_CONNECTOR_TYPE_LMB));
+ }
+
_FDT((fdt_pack(fdt)));
if (fdt_totalsize(fdt) > FDT_MAX_SIZE) {
exit(1);
}
+ qemu_fdt_dumpdtb(fdt, fdt_totalsize(fdt));
cpu_physical_memory_write(fdt_addr, fdt, fdt_totalsize(fdt));
g_free(bootlist);
#define CLEAN_HPTE(_hpte) ((*(uint64_t *)(_hpte)) &= tswap64(~HPTE64_V_HPTE_DIRTY))
#define DIRTY_HPTE(_hpte) ((*(uint64_t *)(_hpte)) |= tswap64(HPTE64_V_HPTE_DIRTY))
-static void spapr_reset_htab(sPAPREnvironment *spapr)
+static void spapr_alloc_htab(sPAPRMachineState *spapr)
{
long shift;
int index;
if (shift > 0) {
/* Kernel handles htab, we don't need to allocate one */
+ if (shift != spapr->htab_shift) {
+ error_setg(&error_abort, "Failed to allocate HTAB of requested size, try with smaller maxmem");
+ }
+
spapr->htab_shift = shift;
kvmppc_kern_htab = true;
+ } else {
+ /* Allocate htab */
+ spapr->htab = qemu_memalign(HTAB_SIZE(spapr), HTAB_SIZE(spapr));
+
+ /* And clear it */
+ memset(spapr->htab, 0, HTAB_SIZE(spapr));
+
+ for (index = 0; index < HTAB_SIZE(spapr) / HASH_PTE_SIZE_64; index++) {
+ DIRTY_HPTE(HPTE(spapr->htab, index));
+ }
+ }
+}
+
+/*
+ * Clear HTAB entries during reset.
+ *
+ * If host kernel has allocated HTAB, KVM_PPC_ALLOCATE_HTAB ioctl is
+ * used to clear HTAB. Otherwise QEMU-allocated HTAB is cleared manually.
+ */
+static void spapr_reset_htab(sPAPRMachineState *spapr)
+{
+ long shift;
+ int index;
+
+ shift = kvmppc_reset_htab(spapr->htab_shift);
+ if (shift > 0) {
+ if (shift != spapr->htab_shift) {
+ error_setg(&error_abort, "Requested HTAB allocation failed during reset");
+ }
/* Tell readers to update their file descriptor */
if (spapr->htab_fd >= 0) {
spapr->htab_fd_stale = true;
}
} else {
- if (!spapr->htab) {
- /* Allocate an htab if we don't yet have one */
- spapr->htab = qemu_memalign(HTAB_SIZE(spapr), HTAB_SIZE(spapr));
- }
-
- /* And clear it */
memset(spapr->htab, 0, HTAB_SIZE(spapr));
for (index = 0; index < HTAB_SIZE(spapr) / HASH_PTE_SIZE_64; index++) {
* A guest reset will cause spapr->htab_fd to become stale if being used.
* Reopen the file descriptor to make sure the whole HTAB is properly read.
*/
-static int spapr_check_htab_fd(sPAPREnvironment *spapr)
+static int spapr_check_htab_fd(sPAPRMachineState *spapr)
{
int rc = 0;
static void ppc_spapr_reset(void)
{
+ sPAPRMachineState *spapr = SPAPR_MACHINE(qdev_get_machine());
PowerPCCPU *first_ppc_cpu;
uint32_t rtas_limit;
first_ppc_cpu->env.gpr[3] = spapr->fdt_addr;
first_ppc_cpu->env.gpr[5] = 0;
first_cpu->halted = 0;
- first_ppc_cpu->env.nip = spapr->entry_point;
+ first_ppc_cpu->env.nip = SPAPR_ENTRY_POINT;
}
static void spapr_cpu_reset(void *opaque)
{
+ sPAPRMachineState *spapr = SPAPR_MACHINE(qdev_get_machine());
PowerPCCPU *cpu = opaque;
CPUState *cs = CPU(cpu);
CPUPPCState *env = &cpu->env;
* We have 8 hpte per group, and each hpte is 16 bytes.
* ie have 128 bytes per hpte entry.
*/
- env->htab_mask = (1ULL << ((spapr)->htab_shift - 7)) - 1;
+ env->htab_mask = (1ULL << (spapr->htab_shift - 7)) - 1;
env->spr[SPR_SDR1] = (target_ulong)(uintptr_t)spapr->htab |
(spapr->htab_shift - 18);
}
-static void spapr_create_nvram(sPAPREnvironment *spapr)
+static void spapr_create_nvram(sPAPRMachineState *spapr)
{
DeviceState *dev = qdev_create(&spapr->vio_bus->bus, "spapr-nvram");
DriveInfo *dinfo = drive_get(IF_PFLASH, 0, 0);
spapr->nvram = (struct sPAPRNVRAM *)dev;
}
-static void spapr_rtc_create(sPAPREnvironment *spapr)
+static void spapr_rtc_create(sPAPRMachineState *spapr)
{
DeviceState *dev = qdev_create(NULL, TYPE_SPAPR_RTC);
case VGA_DEVICE:
return true;
case VGA_STD:
+ case VGA_VIRTIO:
return pci_vga_init(pci_bus) != NULL;
default:
fprintf(stderr, "This vga model is not supported,"
static int spapr_post_load(void *opaque, int version_id)
{
- sPAPREnvironment *spapr = (sPAPREnvironment *)opaque;
+ sPAPRMachineState *spapr = (sPAPRMachineState *)opaque;
int err = 0;
/* In earlier versions, there was no separate qdev for the PAPR
VMSTATE_UNUSED_BUFFER(version_before_3, 0, 4),
/* RTC offset */
- VMSTATE_UINT64_TEST(rtc_offset, sPAPREnvironment, version_before_3),
+ VMSTATE_UINT64_TEST(rtc_offset, sPAPRMachineState, version_before_3),
- VMSTATE_PPC_TIMEBASE_V(tb, sPAPREnvironment, 2),
+ VMSTATE_PPC_TIMEBASE_V(tb, sPAPRMachineState, 2),
VMSTATE_END_OF_LIST()
},
};
static int htab_save_setup(QEMUFile *f, void *opaque)
{
- sPAPREnvironment *spapr = opaque;
+ sPAPRMachineState *spapr = opaque;
/* "Iteration" header */
qemu_put_be32(f, spapr->htab_shift);
return 0;
}
-static void htab_save_first_pass(QEMUFile *f, sPAPREnvironment *spapr,
+static void htab_save_first_pass(QEMUFile *f, sPAPRMachineState *spapr,
int64_t max_ns)
{
int htabslots = HTAB_SIZE(spapr) / HASH_PTE_SIZE_64;
spapr->htab_save_index = index;
}
-static int htab_save_later_pass(QEMUFile *f, sPAPREnvironment *spapr,
+static int htab_save_later_pass(QEMUFile *f, sPAPRMachineState *spapr,
int64_t max_ns)
{
bool final = max_ns < 0;
static int htab_save_iterate(QEMUFile *f, void *opaque)
{
- sPAPREnvironment *spapr = opaque;
+ sPAPRMachineState *spapr = opaque;
int rc = 0;
/* Iteration header */
static int htab_save_complete(QEMUFile *f, void *opaque)
{
- sPAPREnvironment *spapr = opaque;
+ sPAPRMachineState *spapr = opaque;
/* Iteration header */
qemu_put_be32(f, 0);
static int htab_load(QEMUFile *f, void *opaque, int version_id)
{
- sPAPREnvironment *spapr = opaque;
+ sPAPRMachineState *spapr = opaque;
uint32_t section_hdr;
int fd = -1;
if (section_hdr) {
/* First section, just the hash shift */
if (spapr->htab_shift != section_hdr) {
+ error_report("htab_shift mismatch: source %d target %d",
+ section_hdr, spapr->htab_shift);
return -EINVAL;
}
return 0;
machine->boot_order = g_strdup(boot_device);
}
+static void spapr_cpu_init(sPAPRMachineState *spapr, PowerPCCPU *cpu)
+{
+ CPUPPCState *env = &cpu->env;
+
+ /* Set time-base frequency to 512 MHz */
+ cpu_ppc_tb_init(env, TIMEBASE_FREQ);
+
+ /* PAPR always has exception vectors in RAM not ROM. To ensure this,
+ * MSR[IP] should never be set.
+ */
+ env->msr_mask &= ~(1 << 6);
+
+ /* Tell KVM that we're in PAPR mode */
+ if (kvm_enabled()) {
+ kvmppc_set_papr(cpu);
+ }
+
+ if (cpu->max_compat) {
+ if (ppc_set_compat(cpu, cpu->max_compat) < 0) {
+ exit(1);
+ }
+ }
+
+ xics_cpu_setup(spapr->icp, cpu);
+
+ qemu_register_reset(spapr_cpu_reset, cpu);
+}
+
+/*
+ * Reset routine for LMB DR devices.
+ *
+ * Unlike PCI DR devices, LMB DR devices explicitly register this reset
+ * routine. Reset for PCI DR devices will be handled by PHB reset routine
+ * when it walks all its children devices. LMB devices reset occurs
+ * as part of spapr_ppc_reset().
+ */
+static void spapr_drc_reset(void *opaque)
+{
+ sPAPRDRConnector *drc = opaque;
+ DeviceState *d = DEVICE(drc);
+
+ if (d) {
+ device_reset(d);
+ }
+}
+
+static void spapr_create_lmb_dr_connectors(sPAPRMachineState *spapr)
+{
+ MachineState *machine = MACHINE(spapr);
+ uint64_t lmb_size = SPAPR_MEMORY_BLOCK_SIZE;
+ uint32_t nr_lmbs = (machine->maxram_size - machine->ram_size)/lmb_size;
+ int i;
+
+ for (i = 0; i < nr_lmbs; i++) {
+ sPAPRDRConnector *drc;
+ uint64_t addr;
+
+ addr = i * lmb_size + spapr->hotplug_memory.base;
+ drc = spapr_dr_connector_new(OBJECT(spapr), SPAPR_DR_CONNECTOR_TYPE_LMB,
+ addr/lmb_size);
+ qemu_register_reset(spapr_drc_reset, drc);
+ }
+}
+
+/*
+ * If RAM size, maxmem size and individual node mem sizes aren't aligned
+ * to SPAPR_MEMORY_BLOCK_SIZE(256MB), then refuse to start the guest
+ * since we can't support such unaligned sizes with DRCONF_MEMORY.
+ */
+static void spapr_validate_node_memory(MachineState *machine)
+{
+ int i;
+
+ if (machine->maxram_size % SPAPR_MEMORY_BLOCK_SIZE ||
+ machine->ram_size % SPAPR_MEMORY_BLOCK_SIZE) {
+ error_report("Can't support memory configuration where RAM size "
+ "0x" RAM_ADDR_FMT " or maxmem size "
+ "0x" RAM_ADDR_FMT " isn't aligned to %llu MB",
+ machine->ram_size, machine->maxram_size,
+ SPAPR_MEMORY_BLOCK_SIZE/M_BYTE);
+ exit(EXIT_FAILURE);
+ }
+
+ for (i = 0; i < nb_numa_nodes; i++) {
+ if (numa_info[i].node_mem % SPAPR_MEMORY_BLOCK_SIZE) {
+ error_report("Can't support memory configuration where memory size"
+ " %" PRIx64 " of node %d isn't aligned to %llu MB",
+ numa_info[i].node_mem, i,
+ SPAPR_MEMORY_BLOCK_SIZE/M_BYTE);
+ exit(EXIT_FAILURE);
+ }
+ }
+}
+
/* pSeries LPAR / sPAPR hardware init */
static void ppc_spapr_init(MachineState *machine)
{
- ram_addr_t ram_size = machine->ram_size;
- const char *cpu_model = machine->cpu_model;
+ sPAPRMachineState *spapr = SPAPR_MACHINE(machine);
+ sPAPRMachineClass *smc = SPAPR_MACHINE_GET_CLASS(machine);
const char *kernel_filename = machine->kernel_filename;
const char *kernel_cmdline = machine->kernel_cmdline;
const char *initrd_filename = machine->initrd_filename;
PowerPCCPU *cpu;
- CPUPPCState *env;
PCIHostState *phb;
int i;
MemoryRegion *sysmem = get_system_memory();
msi_supported = true;
- spapr = g_malloc0(sizeof(*spapr));
QLIST_INIT(&spapr->phbs);
cpu_ppc_hypercall = emulate_spapr_hypercall;
* more than needed for the Linux guests we support. */
spapr->htab_shift = 18; /* Minimum architected size */
while (spapr->htab_shift <= 46) {
- if ((1ULL << (spapr->htab_shift + 7)) >= ram_size) {
+ if ((1ULL << (spapr->htab_shift + 7)) >= machine->maxram_size) {
break;
}
spapr->htab_shift++;
}
+ spapr_alloc_htab(spapr);
/* Set up Interrupt Controller before we create the VCPUs */
spapr->icp = xics_system_init(machine,
- smp_cpus * kvmppc_smt_threads() / smp_threads,
+ DIV_ROUND_UP(max_cpus * kvmppc_smt_threads(),
+ smp_threads),
XICS_IRQS);
+ if (smc->dr_lmb_enabled) {
+ spapr_validate_node_memory(machine);
+ }
+
/* init CPUs */
- if (cpu_model == NULL) {
- cpu_model = kvm_enabled() ? "host" : "POWER7";
+ if (machine->cpu_model == NULL) {
+ machine->cpu_model = kvm_enabled() ? "host" : "POWER7";
}
for (i = 0; i < smp_cpus; i++) {
- cpu = cpu_ppc_init(cpu_model);
+ cpu = cpu_ppc_init(machine->cpu_model);
if (cpu == NULL) {
fprintf(stderr, "Unable to find PowerPC CPU definition\n");
exit(1);
}
- env = &cpu->env;
-
- /* Set time-base frequency to 512 MHz */
- cpu_ppc_tb_init(env, TIMEBASE_FREQ);
-
- /* PAPR always has exception vectors in RAM not ROM. To ensure this,
- * MSR[IP] should never be set.
- */
- env->msr_mask &= ~(1 << 6);
-
- /* Tell KVM that we're in PAPR mode */
- if (kvm_enabled()) {
- kvmppc_set_papr(cpu);
- }
-
- if (cpu->max_compat) {
- if (ppc_set_compat(cpu, cpu->max_compat) < 0) {
- exit(1);
- }
- }
-
- xics_cpu_setup(spapr->icp, cpu);
-
- qemu_register_reset(spapr_cpu_reset, cpu);
+ spapr_cpu_init(spapr, cpu);
}
if (kvm_enabled()) {
/* Enable H_LOGICAL_CI_* so SLOF can talk to in-kernel devices */
kvmppc_enable_logical_ci_hcalls();
+ kvmppc_enable_set_mode_hcall();
}
/* allocate RAM */
- spapr->ram_limit = ram_size;
memory_region_allocate_system_memory(ram, NULL, "ppc_spapr.ram",
- spapr->ram_limit);
+ machine->ram_size);
memory_region_add_subregion(sysmem, 0, ram);
if (rma_alloc_size && rma) {
memory_region_add_subregion(sysmem, 0, rma_region);
}
+ /* initialize hotplug memory address space */
+ if (machine->ram_size < machine->maxram_size) {
+ ram_addr_t hotplug_mem_size = machine->maxram_size - machine->ram_size;
+
+ if (machine->ram_slots > SPAPR_MAX_RAM_SLOTS) {
+ error_report("Specified number of memory slots %"PRIu64" exceeds max supported %d\n",
+ machine->ram_slots, SPAPR_MAX_RAM_SLOTS);
+ exit(EXIT_FAILURE);
+ }
+
+ spapr->hotplug_memory.base = ROUND_UP(machine->ram_size,
+ SPAPR_HOTPLUG_MEM_ALIGN);
+ memory_region_init(&spapr->hotplug_memory.mr, OBJECT(spapr),
+ "hotplug-memory", hotplug_mem_size);
+ memory_region_add_subregion(sysmem, spapr->hotplug_memory.base,
+ &spapr->hotplug_memory.mr);
+ }
+
+ if (smc->dr_lmb_enabled) {
+ spapr_create_lmb_dr_connectors(spapr);
+ }
+
filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, "spapr-rtas.bin");
if (!filename) {
error_report("Could not find LPAR rtas '%s'", "spapr-rtas.bin");
uint64_t lowaddr = 0;
kernel_size = load_elf(kernel_filename, translate_kernel_address, NULL,
- NULL, &lowaddr, NULL, 1, ELF_MACHINE, 0);
+ NULL, &lowaddr, NULL, 1, PPC_ELF_MACHINE, 0);
if (kernel_size == ELF_LOAD_WRONG_ENDIAN) {
kernel_size = load_elf(kernel_filename,
translate_kernel_address, NULL,
- NULL, &lowaddr, NULL, 0, ELF_MACHINE, 0);
+ NULL, &lowaddr, NULL, 0, PPC_ELF_MACHINE, 0);
kernel_le = kernel_size > 0;
}
if (kernel_size < 0) {
}
g_free(filename);
- spapr->entry_point = 0x100;
-
+ /* FIXME: Should register things through the MachineState's qdev
+ * interface, this is a legacy from the sPAPREnvironment structure
+ * which predated MachineState but had a similar function */
vmstate_register(NULL, 0, &vmstate_spapr, spapr);
register_savevm_live(NULL, "spapr/htab", -1, 1,
&savevm_htab_handlers, spapr);
static char *spapr_get_kvm_type(Object *obj, Error **errp)
{
- sPAPRMachineState *sm = SPAPR_MACHINE(obj);
+ sPAPRMachineState *spapr = SPAPR_MACHINE(obj);
- return g_strdup(sm->kvm_type);
+ return g_strdup(spapr->kvm_type);
}
static void spapr_set_kvm_type(Object *obj, const char *value, Error **errp)
{
- sPAPRMachineState *sm = SPAPR_MACHINE(obj);
+ sPAPRMachineState *spapr = SPAPR_MACHINE(obj);
- g_free(sm->kvm_type);
- sm->kvm_type = g_strdup(value);
+ g_free(spapr->kvm_type);
+ spapr->kvm_type = g_strdup(value);
}
static void spapr_machine_initfn(Object *obj)
}
}
+static void spapr_add_lmbs(DeviceState *dev, uint64_t addr, uint64_t size,
+ uint32_t node, Error **errp)
+{
+ sPAPRDRConnector *drc;
+ sPAPRDRConnectorClass *drck;
+ uint32_t nr_lmbs = size/SPAPR_MEMORY_BLOCK_SIZE;
+ int i, fdt_offset, fdt_size;
+ void *fdt;
+
+ /*
+ * Check for DRC connectors and send hotplug notification to the
+ * guest only in case of hotplugged memory. This allows cold plugged
+ * memory to be specified at boot time.
+ */
+ if (!dev->hotplugged) {
+ return;
+ }
+
+ for (i = 0; i < nr_lmbs; i++) {
+ drc = spapr_dr_connector_by_id(SPAPR_DR_CONNECTOR_TYPE_LMB,
+ addr/SPAPR_MEMORY_BLOCK_SIZE);
+ g_assert(drc);
+
+ fdt = create_device_tree(&fdt_size);
+ fdt_offset = spapr_populate_memory_node(fdt, node, addr,
+ SPAPR_MEMORY_BLOCK_SIZE);
+
+ drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc);
+ drck->attach(drc, dev, fdt, fdt_offset, !dev->hotplugged, errp);
+ addr += SPAPR_MEMORY_BLOCK_SIZE;
+ }
+ spapr_hotplug_req_add_by_count(SPAPR_DR_CONNECTOR_TYPE_LMB, nr_lmbs);
+}
+
+static void spapr_memory_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
+ uint32_t node, Error **errp)
+{
+ Error *local_err = NULL;
+ sPAPRMachineState *ms = SPAPR_MACHINE(hotplug_dev);
+ PCDIMMDevice *dimm = PC_DIMM(dev);
+ PCDIMMDeviceClass *ddc = PC_DIMM_GET_CLASS(dimm);
+ MemoryRegion *mr = ddc->get_memory_region(dimm);
+ uint64_t align = memory_region_get_alignment(mr);
+ uint64_t size = memory_region_size(mr);
+ uint64_t addr;
+
+ if (size % SPAPR_MEMORY_BLOCK_SIZE) {
+ error_setg(&local_err, "Hotplugged memory size must be a multiple of "
+ "%lld MB", SPAPR_MEMORY_BLOCK_SIZE/M_BYTE);
+ goto out;
+ }
+
+ pc_dimm_memory_plug(dev, &ms->hotplug_memory, mr, align, false, &local_err);
+ if (local_err) {
+ goto out;
+ }
+
+ addr = object_property_get_int(OBJECT(dimm), PC_DIMM_ADDR_PROP, &local_err);
+ if (local_err) {
+ pc_dimm_memory_unplug(dev, &ms->hotplug_memory, mr);
+ goto out;
+ }
+
+ spapr_add_lmbs(dev, addr, size, node, &error_abort);
+
+out:
+ error_propagate(errp, local_err);
+}
+
+static void spapr_machine_device_plug(HotplugHandler *hotplug_dev,
+ DeviceState *dev, Error **errp)
+{
+ sPAPRMachineClass *smc = SPAPR_MACHINE_GET_CLASS(qdev_get_machine());
+
+ if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM)) {
+ int node;
+
+ if (!smc->dr_lmb_enabled) {
+ error_setg(errp, "Memory hotplug not supported for this machine");
+ return;
+ }
+ node = object_property_get_int(OBJECT(dev), PC_DIMM_NODE_PROP, errp);
+ if (*errp) {
+ return;
+ }
+
+ /*
+ * Currently PowerPC kernel doesn't allow hot-adding memory to
+ * memory-less node, but instead will silently add the memory
+ * to the first node that has some memory. This causes two
+ * unexpected behaviours for the user.
+ *
+ * - Memory gets hotplugged to a different node than what the user
+ * specified.
+ * - Since pc-dimm subsystem in QEMU still thinks that memory belongs
+ * to memory-less node, a reboot will set things accordingly
+ * and the previously hotplugged memory now ends in the right node.
+ * This appears as if some memory moved from one node to another.
+ *
+ * So until kernel starts supporting memory hotplug to memory-less
+ * nodes, just prevent such attempts upfront in QEMU.
+ */
+ if (nb_numa_nodes && !numa_info[node].node_mem) {
+ error_setg(errp, "Can't hotplug memory to memory-less node %d",
+ node);
+ return;
+ }
+
+ spapr_memory_plug(hotplug_dev, dev, node, errp);
+ }
+}
+
+static void spapr_machine_device_unplug(HotplugHandler *hotplug_dev,
+ DeviceState *dev, Error **errp)
+{
+ if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM)) {
+ error_setg(errp, "Memory hot unplug not supported by sPAPR");
+ }
+}
+
+static HotplugHandler *spapr_get_hotpug_handler(MachineState *machine,
+ DeviceState *dev)
+{
+ if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM)) {
+ return HOTPLUG_HANDLER(machine);
+ }
+ return NULL;
+}
+
+static unsigned spapr_cpu_index_to_socket_id(unsigned cpu_index)
+{
+ /* Allocate to NUMA nodes on a "socket" basis (not that concept of
+ * socket means much for the paravirtualized PAPR platform) */
+ return cpu_index / smp_threads / smp_cores;
+}
+
static void spapr_machine_class_init(ObjectClass *oc, void *data)
{
MachineClass *mc = MACHINE_CLASS(oc);
+ sPAPRMachineClass *smc = SPAPR_MACHINE_CLASS(oc);
FWPathProviderClass *fwc = FW_PATH_PROVIDER_CLASS(oc);
NMIClass *nc = NMI_CLASS(oc);
+ HotplugHandlerClass *hc = HOTPLUG_HANDLER_CLASS(oc);
mc->init = ppc_spapr_init;
mc->reset = ppc_spapr_reset;
mc->block_default_type = IF_SCSI;
- mc->max_cpus = MAX_CPUS;
+ mc->max_cpus = MAX_CPUMASK_BITS;
mc->no_parallel = 1;
mc->default_boot_order = "";
mc->default_ram_size = 512 * M_BYTE;
mc->kvm_type = spapr_kvm_type;
mc->has_dynamic_sysbus = true;
+ mc->pci_allow_0_address = true;
+ mc->get_hotplug_handler = spapr_get_hotpug_handler;
+ hc->plug = spapr_machine_device_plug;
+ hc->unplug = spapr_machine_device_unplug;
+ mc->cpu_index_to_socket_id = spapr_cpu_index_to_socket_id;
+ smc->dr_lmb_enabled = false;
fwc->get_dev_path = spapr_get_fw_dev_path;
nc->nmi_monitor_handler = spapr_nmi;
}
.abstract = true,
.instance_size = sizeof(sPAPRMachineState),
.instance_init = spapr_machine_initfn,
+ .class_size = sizeof(sPAPRMachineClass),
.class_init = spapr_machine_class_init,
.interfaces = (InterfaceInfo[]) {
{ TYPE_FW_PATH_PROVIDER },
{ TYPE_NMI },
+ { TYPE_HOTPLUG_HANDLER },
{ }
},
};
{ /* end of list */ }
};
- mc->name = "pseries-2.1";
mc->desc = "pSeries Logical Partition (PAPR compliant) v2.1";
mc->compat_props = compat_props;
}
static const TypeInfo spapr_machine_2_1_info = {
- .name = TYPE_SPAPR_MACHINE "2.1",
+ .name = MACHINE_TYPE_NAME("pseries-2.1"),
.parent = TYPE_SPAPR_MACHINE,
.class_init = spapr_machine_2_1_class_init,
.instance_init = spapr_machine_2_1_instance_init,
};
MachineClass *mc = MACHINE_CLASS(oc);
- mc->name = "pseries-2.2";
mc->desc = "pSeries Logical Partition (PAPR compliant) v2.2";
mc->compat_props = compat_props;
}
static const TypeInfo spapr_machine_2_2_info = {
- .name = TYPE_SPAPR_MACHINE "2.2",
+ .name = MACHINE_TYPE_NAME("pseries-2.2"),
.parent = TYPE_SPAPR_MACHINE,
.class_init = spapr_machine_2_2_class_init,
.instance_init = spapr_machine_2_2_instance_init,
};
MachineClass *mc = MACHINE_CLASS(oc);
- mc->name = "pseries-2.3";
mc->desc = "pSeries Logical Partition (PAPR compliant) v2.3";
mc->compat_props = compat_props;
}
static const TypeInfo spapr_machine_2_3_info = {
- .name = TYPE_SPAPR_MACHINE "2.3",
+ .name = MACHINE_TYPE_NAME("pseries-2.3"),
.parent = TYPE_SPAPR_MACHINE,
.class_init = spapr_machine_2_3_class_init,
.instance_init = spapr_machine_2_3_instance_init,
{
MachineClass *mc = MACHINE_CLASS(oc);
- mc->name = "pseries-2.4";
mc->desc = "pSeries Logical Partition (PAPR compliant) v2.4";
mc->alias = "pseries";
- mc->is_default = 1;
+ mc->is_default = 0;
}
static const TypeInfo spapr_machine_2_4_info = {
- .name = TYPE_SPAPR_MACHINE "2.4",
+ .name = MACHINE_TYPE_NAME("pseries-2.4"),
.parent = TYPE_SPAPR_MACHINE,
.class_init = spapr_machine_2_4_class_init,
};
+static void spapr_machine_2_5_class_init(ObjectClass *oc, void *data)
+{
+ MachineClass *mc = MACHINE_CLASS(oc);
+ sPAPRMachineClass *smc = SPAPR_MACHINE_CLASS(oc);
+
+ mc->name = "pseries-2.5";
+ mc->desc = "pSeries Logical Partition (PAPR compliant) v2.5";
+ mc->alias = "pseries";
+ mc->is_default = 1;
+ smc->dr_lmb_enabled = true;
+}
+
+static const TypeInfo spapr_machine_2_5_info = {
+ .name = MACHINE_TYPE_NAME("pseries-2.5"),
+ .parent = TYPE_SPAPR_MACHINE,
+ .class_init = spapr_machine_2_5_class_init,
+};
+
static void spapr_machine_register_types(void)
{
type_register_static(&spapr_machine_info);
type_register_static(&spapr_machine_2_2_info);
type_register_static(&spapr_machine_2_3_info);
type_register_static(&spapr_machine_2_4_info);
+ type_register_static(&spapr_machine_2_5_info);
}
type_init(spapr_machine_register_types)
projects / qemu.git / blobdiff