diff options
author | Richard Henderson <richard.henderson@linaro.org> | 2023-06-16 12:30:16 +0200 |
---|---|---|
committer | Richard Henderson <richard.henderson@linaro.org> | 2023-06-16 12:30:16 +0200 |
commit | e3660cc1e3cb136af50c0eaaeac27943c2438d1d (patch) | |
tree | fc37d365443153e8d76e87a274fb1b2ed9a0a821 | |
parent | 0d7c8da0cca563850e0cde6c864bab1981cc52bf (diff) | |
parent | 505aa8d8f29b79fcef77563bb4124208badbd8d4 (diff) | |
download | qemu-e3660cc1e3cb136af50c0eaaeac27943c2438d1d.zip qemu-e3660cc1e3cb136af50c0eaaeac27943c2438d1d.tar.gz qemu-e3660cc1e3cb136af50c0eaaeac27943c2438d1d.tar.bz2 |
Merge tag 'pull-loongarch-20230616' of https://gitlab.com/gaosong/qemu into staging
pull-loongarch-20230616
# -----BEGIN PGP SIGNATURE-----
#
# iLMEAAEIAB0WIQS4/x2g0v3LLaCcbCxAov/yOSY+3wUCZIwysgAKCRBAov/yOSY+
# 39FYA/465KtY2jDt4xG6AdwZDHckfxZQWlrfhyZvtapOkUG4AprOBV2nSS/ukyD4
# V8bg2/6cLS0GRKfDsqA3DcxSASWCAggIU4fTSj+DlYOZhNUIq14qzwqciZnO5CIH
# QDczSqu2LKRdP9j6MCtzIaZq/8pPDcOlgm7Dyct/kDo/64E2sg==
# =rD4j
# -----END PGP SIGNATURE-----
# gpg: Signature made Fri 16 Jun 2023 12:00:18 PM CEST
# gpg: using RSA key B8FF1DA0D2FDCB2DA09C6C2C40A2FFF239263EDF
# gpg: Good signature from "Song Gao <m17746591750@163.com>" [unknown]
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg: There is no indication that the signature belongs to the owner.
# Primary key fingerprint: B8FF 1DA0 D2FD CB2D A09C 6C2C 40A2 FFF2 3926 3EDF
* tag 'pull-loongarch-20230616' of https://gitlab.com/gaosong/qemu:
target/loongarch: Fix CSR.DMW0-3.VSEG check
hw/loongarch: Supplement cpu topology arguments
hw/loongarch: Add numa support
hw/intc: Set physical cpuid route for LoongArch ipi device
hw/loongarch/virt: Add cpu arch_id support
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
-rw-r--r-- | hw/intc/loongarch_ipi.c | 44 | ||||
-rw-r--r-- | hw/loongarch/Kconfig | 1 | ||||
-rw-r--r-- | hw/loongarch/acpi-build.c | 78 | ||||
-rw-r--r-- | hw/loongarch/virt.c | 144 | ||||
-rw-r--r-- | target/loongarch/cpu.h | 2 | ||||
-rw-r--r-- | target/loongarch/tlb_helper.c | 4 |
6 files changed, 235 insertions, 38 deletions
diff --git a/hw/intc/loongarch_ipi.c b/hw/intc/loongarch_ipi.c index 3e45381..67858b5 100644 --- a/hw/intc/loongarch_ipi.c +++ b/hw/intc/loongarch_ipi.c @@ -17,6 +17,8 @@ #include "target/loongarch/internals.h" #include "trace.h" +static void loongarch_ipi_writel(void *, hwaddr, uint64_t, unsigned); + static uint64_t loongarch_ipi_readl(void *opaque, hwaddr addr, unsigned size) { IPICore *s = opaque; @@ -75,13 +77,42 @@ static void send_ipi_data(CPULoongArchState *env, uint64_t val, hwaddr addr) data, MEMTXATTRS_UNSPECIFIED, NULL); } +static int archid_cmp(const void *a, const void *b) +{ + CPUArchId *archid_a = (CPUArchId *)a; + CPUArchId *archid_b = (CPUArchId *)b; + + return archid_a->arch_id - archid_b->arch_id; +} + +static CPUArchId *find_cpu_by_archid(MachineState *ms, uint32_t id) +{ + CPUArchId apic_id, *found_cpu; + + apic_id.arch_id = id; + found_cpu = bsearch(&apic_id, ms->possible_cpus->cpus, + ms->possible_cpus->len, sizeof(*ms->possible_cpus->cpus), + archid_cmp); + + return found_cpu; +} + +static CPUState *ipi_getcpu(int arch_id) +{ + MachineState *machine = MACHINE(qdev_get_machine()); + CPUArchId *archid; + + archid = find_cpu_by_archid(machine, arch_id); + return CPU(archid->cpu); +} + static void ipi_send(uint64_t val) { uint32_t cpuid; uint8_t vector; - CPULoongArchState *env; CPUState *cs; LoongArchCPU *cpu; + LoongArchIPI *s; cpuid = extract32(val, 16, 10); if (cpuid >= LOONGARCH_MAX_CPUS) { @@ -92,11 +123,10 @@ static void ipi_send(uint64_t val) /* IPI status vector */ vector = extract8(val, 0, 5); - cs = qemu_get_cpu(cpuid); + cs = ipi_getcpu(cpuid); cpu = LOONGARCH_CPU(cs); - env = &cpu->env; - address_space_stl(&env->address_space_iocsr, 0x1008, - BIT(vector), MEMTXATTRS_UNSPECIFIED, NULL); + s = LOONGARCH_IPI(cpu->env.ipistate); + loongarch_ipi_writel(&s->ipi_core, CORE_SET_OFF, BIT(vector), 4); } static void mail_send(uint64_t val) @@ -114,7 +144,7 @@ static void mail_send(uint64_t val) } addr = 0x1020 + (val & 0x1c); - cs = qemu_get_cpu(cpuid); + cs = ipi_getcpu(cpuid); cpu = LOONGARCH_CPU(cs); env = &cpu->env; send_ipi_data(env, val, addr); @@ -135,7 +165,7 @@ static void any_send(uint64_t val) } addr = val & 0xffff; - cs = qemu_get_cpu(cpuid); + cs = ipi_getcpu(cpuid); cpu = LOONGARCH_CPU(cs); env = &cpu->env; send_ipi_data(env, val, addr); diff --git a/hw/loongarch/Kconfig b/hw/loongarch/Kconfig index eb112af..1e7c5b4 100644 --- a/hw/loongarch/Kconfig +++ b/hw/loongarch/Kconfig @@ -21,3 +21,4 @@ config LOONGARCH_VIRT select FW_CFG_DMA select DIMM select PFLASH_CFI01 + select ACPI_HMAT diff --git a/hw/loongarch/acpi-build.c b/hw/loongarch/acpi-build.c index 8e3ce07..0b62c3a 100644 --- a/hw/loongarch/acpi-build.c +++ b/hw/loongarch/acpi-build.c @@ -34,6 +34,7 @@ #include "sysemu/tpm.h" #include "hw/platform-bus.h" #include "hw/acpi/aml-build.h" +#include "hw/acpi/hmat.h" #define ACPI_BUILD_ALIGN_SIZE 0x1000 #define ACPI_BUILD_TABLE_SIZE 0x20000 @@ -107,7 +108,9 @@ static void build_madt(GArray *table_data, BIOSLinker *linker, LoongArchMachineState *lams) { MachineState *ms = MACHINE(lams); - int i; + MachineClass *mc = MACHINE_GET_CLASS(ms); + const CPUArchIdList *arch_ids = mc->possible_cpu_arch_ids(ms); + int i, arch_id; AcpiTable table = { .sig = "APIC", .rev = 1, .oem_id = lams->oem_id, .oem_table_id = lams->oem_table_id }; @@ -117,13 +120,15 @@ build_madt(GArray *table_data, BIOSLinker *linker, LoongArchMachineState *lams) build_append_int_noprefix(table_data, 0, 4); build_append_int_noprefix(table_data, 1 /* PCAT_COMPAT */, 4); /* Flags */ - for (i = 0; i < ms->smp.cpus; i++) { + for (i = 0; i < arch_ids->len; i++) { /* Processor Core Interrupt Controller Structure */ + arch_id = arch_ids->cpus[i].arch_id; + build_append_int_noprefix(table_data, 17, 1); /* Type */ build_append_int_noprefix(table_data, 15, 1); /* Length */ build_append_int_noprefix(table_data, 1, 1); /* Version */ build_append_int_noprefix(table_data, i + 1, 4); /* ACPI Processor ID */ - build_append_int_noprefix(table_data, i, 4); /* Core ID */ + build_append_int_noprefix(table_data, arch_id, 4); /* Core ID */ build_append_int_noprefix(table_data, 1, 4); /* Flags */ } @@ -159,9 +164,12 @@ build_madt(GArray *table_data, BIOSLinker *linker, LoongArchMachineState *lams) static void build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine) { - uint64_t i; + int i, arch_id, node_id; + uint64_t mem_len, mem_base; + int nb_numa_nodes = machine->numa_state->num_nodes; LoongArchMachineState *lams = LOONGARCH_MACHINE(machine); - MachineState *ms = MACHINE(lams); + MachineClass *mc = MACHINE_GET_CLASS(lams); + const CPUArchIdList *arch_ids = mc->possible_cpu_arch_ids(machine); AcpiTable table = { .sig = "SRAT", .rev = 1, .oem_id = lams->oem_id, .oem_table_id = lams->oem_table_id }; @@ -169,13 +177,16 @@ build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine) build_append_int_noprefix(table_data, 1, 4); /* Reserved */ build_append_int_noprefix(table_data, 0, 8); /* Reserved */ - for (i = 0; i < ms->smp.cpus; ++i) { + for (i = 0; i < arch_ids->len; ++i) { + arch_id = arch_ids->cpus[i].arch_id; + node_id = arch_ids->cpus[i].props.node_id; + /* Processor Local APIC/SAPIC Affinity Structure */ build_append_int_noprefix(table_data, 0, 1); /* Type */ build_append_int_noprefix(table_data, 16, 1); /* Length */ /* Proximity Domain [7:0] */ - build_append_int_noprefix(table_data, 0, 1); - build_append_int_noprefix(table_data, i, 1); /* APIC ID */ + build_append_int_noprefix(table_data, node_id, 1); + build_append_int_noprefix(table_data, arch_id, 1); /* APIC ID */ /* Flags, Table 5-36 */ build_append_int_noprefix(table_data, 1, 4); build_append_int_noprefix(table_data, 0, 1); /* Local SAPIC EID */ @@ -184,16 +195,36 @@ build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine) build_append_int_noprefix(table_data, 0, 4); /* Reserved */ } + /* Node0 */ build_srat_memory(table_data, VIRT_LOWMEM_BASE, VIRT_LOWMEM_SIZE, 0, MEM_AFFINITY_ENABLED); + mem_base = VIRT_HIGHMEM_BASE; + if (!nb_numa_nodes) { + mem_len = machine->ram_size - VIRT_LOWMEM_SIZE; + } else { + mem_len = machine->numa_state->nodes[0].node_mem - VIRT_LOWMEM_SIZE; + } + if (mem_len) + build_srat_memory(table_data, mem_base, mem_len, 0, MEM_AFFINITY_ENABLED); + + /* Node1 - Nodemax */ + if (nb_numa_nodes) { + mem_base += mem_len; + for (i = 1; i < nb_numa_nodes; ++i) { + if (machine->numa_state->nodes[i].node_mem > 0) { + build_srat_memory(table_data, mem_base, + machine->numa_state->nodes[i].node_mem, i, + MEM_AFFINITY_ENABLED); + mem_base += machine->numa_state->nodes[i].node_mem; + } + } + } - build_srat_memory(table_data, VIRT_HIGHMEM_BASE, machine->ram_size - VIRT_LOWMEM_SIZE, - 0, MEM_AFFINITY_ENABLED); - - if (ms->device_memory) { - build_srat_memory(table_data, ms->device_memory->base, - memory_region_size(&ms->device_memory->mr), - 0, MEM_AFFINITY_HOTPLUGGABLE | MEM_AFFINITY_ENABLED); + if (machine->device_memory) { + build_srat_memory(table_data, machine->device_memory->base, + memory_region_size(&machine->device_memory->mr), + nb_numa_nodes - 1, + MEM_AFFINITY_HOTPLUGGABLE | MEM_AFFINITY_ENABLED); } acpi_table_end(linker, &table); @@ -407,8 +438,25 @@ static void acpi_build(AcpiBuildTables *tables, MachineState *machine) build_madt(tables_blob, tables->linker, lams); acpi_add_table(table_offsets, tables_blob); + build_pptt(tables_blob, tables->linker, machine, + lams->oem_id, lams->oem_table_id); + + acpi_add_table(table_offsets, tables_blob); build_srat(tables_blob, tables->linker, machine); + if (machine->numa_state->num_nodes) { + if (machine->numa_state->have_numa_distance) { + acpi_add_table(table_offsets, tables_blob); + build_slit(tables_blob, tables->linker, machine, lams->oem_id, + lams->oem_table_id); + } + if (machine->numa_state->hmat_enabled) { + acpi_add_table(table_offsets, tables_blob); + build_hmat(tables_blob, tables->linker, machine->numa_state, + lams->oem_id, lams->oem_table_id); + } + } + acpi_add_table(table_offsets, tables_blob); { AcpiMcfgInfo mcfg = { diff --git a/hw/loongarch/virt.c b/hw/loongarch/virt.c index ceddec1..ca8824b 100644 --- a/hw/loongarch/virt.c +++ b/hw/loongarch/virt.c @@ -164,11 +164,16 @@ static void fdt_add_cpu_nodes(const LoongArchMachineState *lams) for (num = smp_cpus - 1; num >= 0; num--) { char *nodename = g_strdup_printf("/cpus/cpu@%d", num); LoongArchCPU *cpu = LOONGARCH_CPU(qemu_get_cpu(num)); + CPUState *cs = CPU(cpu); qemu_fdt_add_subnode(ms->fdt, nodename); qemu_fdt_setprop_string(ms->fdt, nodename, "device_type", "cpu"); qemu_fdt_setprop_string(ms->fdt, nodename, "compatible", cpu->dtb_compatible); + if (ms->possible_cpus->cpus[cs->cpu_index].props.has_node_id) { + qemu_fdt_setprop_cell(ms->fdt, nodename, "numa-node-id", + ms->possible_cpus->cpus[cs->cpu_index].props.node_id); + } qemu_fdt_setprop_cell(ms->fdt, nodename, "reg", num); qemu_fdt_setprop_cell(ms->fdt, nodename, "phandle", qemu_fdt_alloc_phandle(ms->fdt)); @@ -280,6 +285,22 @@ static void fdt_add_irqchip_node(LoongArchMachineState *lams) g_free(nodename); } +static void fdt_add_memory_node(MachineState *ms, + uint64_t base, uint64_t size, int node_id) +{ + char *nodename = g_strdup_printf("/memory@%" PRIx64, base); + + qemu_fdt_add_subnode(ms->fdt, nodename); + qemu_fdt_setprop_cells(ms->fdt, nodename, "reg", 2, base, 2, size); + qemu_fdt_setprop_string(ms->fdt, nodename, "device_type", "memory"); + + if (ms->numa_state && ms->numa_state->num_nodes) { + qemu_fdt_setprop_cell(ms->fdt, nodename, "numa-node-id", node_id); + } + + g_free(nodename); +} + #define PM_BASE 0x10080000 #define PM_SIZE 0x100 #define PM_CTRL 0x10 @@ -617,6 +638,7 @@ static void loongarch_irq_init(LoongArchMachineState *lams) memory_region_add_subregion(&env->system_iocsr, APIC_BASE, sysbus_mmio_get_region(SYS_BUS_DEVICE(extioi), cpu)); + env->ipistate = ipi; } /* @@ -766,11 +788,17 @@ static void loongarch_init(MachineState *machine) const char *cpu_model = machine->cpu_type; ram_addr_t offset = 0; ram_addr_t ram_size = machine->ram_size; - uint64_t highram_size = 0; + uint64_t highram_size = 0, phyAddr = 0; MemoryRegion *address_space_mem = get_system_memory(); LoongArchMachineState *lams = LOONGARCH_MACHINE(machine); + int nb_numa_nodes = machine->numa_state->num_nodes; + NodeInfo *numa_info = machine->numa_state->nodes; int i; hwaddr fdt_base; + const CPUArchIdList *possible_cpus; + MachineClass *mc = MACHINE_GET_CLASS(machine); + CPUState *cpu; + char *ramName = NULL; if (!cpu_model) { cpu_model = LOONGARCH_CPU_TYPE_NAME("la464"); @@ -787,21 +815,51 @@ static void loongarch_init(MachineState *machine) } create_fdt(lams); /* Init CPUs */ - for (i = 0; i < machine->smp.cpus; i++) { - cpu_create(machine->cpu_type); + + possible_cpus = mc->possible_cpu_arch_ids(machine); + for (i = 0; i < possible_cpus->len; i++) { + cpu = cpu_create(machine->cpu_type); + cpu->cpu_index = i; + machine->possible_cpus->cpus[i].cpu = OBJECT(cpu); } fdt_add_cpu_nodes(lams); - /* Add memory region */ - memory_region_init_alias(&lams->lowmem, NULL, "loongarch.lowram", - machine->ram, 0, 256 * MiB); - memory_region_add_subregion(address_space_mem, offset, &lams->lowmem); - offset += 256 * MiB; - memmap_add_entry(0, 256 * MiB, 1); - highram_size = ram_size - 256 * MiB; - memory_region_init_alias(&lams->highmem, NULL, "loongarch.highmem", - machine->ram, offset, highram_size); - memory_region_add_subregion(address_space_mem, 0x90000000, &lams->highmem); - memmap_add_entry(0x90000000, highram_size, 1); + + /* Node0 memory */ + memmap_add_entry(VIRT_LOWMEM_BASE, VIRT_LOWMEM_SIZE, 1); + fdt_add_memory_node(machine, VIRT_LOWMEM_BASE, VIRT_LOWMEM_SIZE, 0); + memory_region_init_alias(&lams->lowmem, NULL, "loongarch.node0.lowram", + machine->ram, offset, VIRT_LOWMEM_SIZE); + memory_region_add_subregion(address_space_mem, phyAddr, &lams->lowmem); + + offset += VIRT_LOWMEM_SIZE; + if (nb_numa_nodes > 0) { + assert(numa_info[0].node_mem > VIRT_LOWMEM_SIZE); + highram_size = numa_info[0].node_mem - VIRT_LOWMEM_SIZE; + } else { + highram_size = ram_size - VIRT_LOWMEM_SIZE; + } + phyAddr = VIRT_HIGHMEM_BASE; + memmap_add_entry(phyAddr, highram_size, 1); + fdt_add_memory_node(machine, phyAddr, highram_size, 0); + memory_region_init_alias(&lams->highmem, NULL, "loongarch.node0.highram", + machine->ram, offset, highram_size); + memory_region_add_subregion(address_space_mem, phyAddr, &lams->highmem); + + /* Node1 - Nodemax memory */ + offset += highram_size; + phyAddr += highram_size; + + for (i = 1; i < nb_numa_nodes; i++) { + MemoryRegion *nodemem = g_new(MemoryRegion, 1); + ramName = g_strdup_printf("loongarch.node%d.ram", i); + memory_region_init_alias(nodemem, NULL, ramName, machine->ram, + offset, numa_info[i].node_mem); + memory_region_add_subregion(address_space_mem, phyAddr, nodemem); + memmap_add_entry(phyAddr, numa_info[i].node_mem, 1); + fdt_add_memory_node(machine, phyAddr, numa_info[i].node_mem, i); + offset += numa_info[i].node_mem; + phyAddr += numa_info[i].node_mem; + } /* initialize device memory address space */ if (machine->ram_size < machine->maxram_size) { @@ -1022,6 +1080,58 @@ static HotplugHandler *virt_machine_get_hotplug_handler(MachineState *machine, return NULL; } +static const CPUArchIdList *virt_possible_cpu_arch_ids(MachineState *ms) +{ + int n; + unsigned int max_cpus = ms->smp.max_cpus; + + if (ms->possible_cpus) { + assert(ms->possible_cpus->len == max_cpus); + return ms->possible_cpus; + } + + ms->possible_cpus = g_malloc0(sizeof(CPUArchIdList) + + sizeof(CPUArchId) * max_cpus); + ms->possible_cpus->len = max_cpus; + for (n = 0; n < ms->possible_cpus->len; n++) { + ms->possible_cpus->cpus[n].type = ms->cpu_type; + ms->possible_cpus->cpus[n].arch_id = n; + + ms->possible_cpus->cpus[n].props.has_socket_id = true; + ms->possible_cpus->cpus[n].props.socket_id = + n / (ms->smp.cores * ms->smp.threads); + ms->possible_cpus->cpus[n].props.has_core_id = true; + ms->possible_cpus->cpus[n].props.core_id = + n / ms->smp.threads % ms->smp.cores; + ms->possible_cpus->cpus[n].props.has_thread_id = true; + ms->possible_cpus->cpus[n].props.thread_id = n % ms->smp.threads; + } + return ms->possible_cpus; +} + +static CpuInstanceProperties +virt_cpu_index_to_props(MachineState *ms, unsigned cpu_index) +{ + MachineClass *mc = MACHINE_GET_CLASS(ms); + const CPUArchIdList *possible_cpus = mc->possible_cpu_arch_ids(ms); + + assert(cpu_index < possible_cpus->len); + return possible_cpus->cpus[cpu_index].props; +} + +static int64_t virt_get_default_cpu_node_id(const MachineState *ms, int idx) +{ + int64_t nidx = 0; + + if (ms->numa_state->num_nodes) { + nidx = idx / (ms->smp.cpus / ms->numa_state->num_nodes); + if (ms->numa_state->num_nodes <= nidx) { + nidx = ms->numa_state->num_nodes - 1; + } + } + return nidx; +} + static void loongarch_class_init(ObjectClass *oc, void *data) { MachineClass *mc = MACHINE_CLASS(oc); @@ -1038,6 +1148,12 @@ static void loongarch_class_init(ObjectClass *oc, void *data) mc->block_default_type = IF_VIRTIO; mc->default_boot_order = "c"; mc->no_cdrom = 1; + mc->possible_cpu_arch_ids = virt_possible_cpu_arch_ids; + mc->cpu_index_to_instance_props = virt_cpu_index_to_props; + mc->get_default_cpu_node_id = virt_get_default_cpu_node_id; + mc->numa_mem_supported = true; + mc->auto_enable_numa_with_memhp = true; + mc->auto_enable_numa_with_memdev = true; mc->get_hotplug_handler = virt_machine_get_hotplug_handler; mc->default_nic = "virtio-net-pci"; hc->plug = loongarch_machine_device_plug_cb; diff --git a/target/loongarch/cpu.h b/target/loongarch/cpu.h index 1f37e36..b23f38c 100644 --- a/target/loongarch/cpu.h +++ b/target/loongarch/cpu.h @@ -351,6 +351,8 @@ typedef struct CPUArchState { MemoryRegion iocsr_mem; bool load_elf; uint64_t elf_address; + /* Store ipistate to access from this struct */ + DeviceState *ipistate; #endif } CPULoongArchState; diff --git a/target/loongarch/tlb_helper.c b/target/loongarch/tlb_helper.c index cce1db1..6e00190 100644 --- a/target/loongarch/tlb_helper.c +++ b/target/loongarch/tlb_helper.c @@ -185,10 +185,10 @@ static int get_physical_address(CPULoongArchState *env, hwaddr *physical, } plv = kernel_mode | (user_mode << R_CSR_DMW_PLV3_SHIFT); - base_v = address >> TARGET_VIRT_ADDR_SPACE_BITS; + base_v = address >> R_CSR_DMW_VSEG_SHIFT; /* Check direct map window */ for (int i = 0; i < 4; i++) { - base_c = env->CSR_DMW[i] >> TARGET_VIRT_ADDR_SPACE_BITS; + base_c = FIELD_EX64(env->CSR_DMW[i], CSR_DMW, VSEG); if ((plv & env->CSR_DMW[i]) && (base_c == base_v)) { *physical = dmw_va2pa(address); *prot = PAGE_READ | PAGE_WRITE | PAGE_EXEC; |