diff options
author | Peter Maydell <peter.maydell@linaro.org> | 2020-08-25 22:50:42 +0100 |
---|---|---|
committer | Peter Maydell <peter.maydell@linaro.org> | 2020-08-25 22:50:42 +0100 |
commit | 78dca230c97ed0d6e16ae0c96d5407644d991994 (patch) | |
tree | d03a325e1b0288608eed42bb7ad0662321e40adb /hw | |
parent | d1a2b51f868d09ca8489ee9aee9c55632ed8fb92 (diff) | |
parent | e39a8320b088dd5efc9ebaafe387e52b3d962665 (diff) | |
download | qemu-78dca230c97ed0d6e16ae0c96d5407644d991994.zip qemu-78dca230c97ed0d6e16ae0c96d5407644d991994.tar.gz qemu-78dca230c97ed0d6e16ae0c96d5407644d991994.tar.bz2 |
Merge remote-tracking branch 'remotes/alistair/tags/pull-riscv-to-apply-20200825' into staging
This pull request first adds support for multi-socket NUMA RISC-V
machines. The Spike and Virt machines both support NUMA sockets.
This PR also updates the current experimental Hypervisor support to the
v0.6.1 spec.
# gpg: Signature made Tue 25 Aug 2020 19:47:41 BST
# gpg: using RSA key F6C4AC46D4934868D3B8CE8F21E10D29DF977054
# gpg: Good signature from "Alistair Francis <alistair@alistair23.me>" [full]
# Primary key fingerprint: F6C4 AC46 D493 4868 D3B8 CE8F 21E1 0D29 DF97 7054
* remotes/alistair/tags/pull-riscv-to-apply-20200825:
target/riscv: Support the Virtual Instruction fault
target/riscv: Return the exception from invalid CSR accesses
target/riscv: Support the v0.6 Hypervisor extension CRSs
target/riscv: Only support little endian guests
target/riscv: Only support a single VSXL length
target/riscv: Update the CSRs to the v0.6 Hyp extension
target/riscv: Update the Hypervisor trap return/entry
target/riscv: Fix the interrupt cause code
target/riscv: Convert MSTATUS MTL to GVA
target/riscv: Don't allow guest to write to htinst
target/riscv: Do two-stage lookups on hlv/hlvx/hsv instructions
target/riscv: Allow generating hlv/hlvx/hsv instructions
target/riscv: Allow setting a two-stage lookup in the virt status
hw/riscv: virt: Allow creating multiple NUMA sockets
hw/riscv: spike: Allow creating multiple NUMA sockets
hw/riscv: Add helpers for RISC-V multi-socket NUMA machines
hw/riscv: Allow creating multiple instances of PLIC
hw/riscv: Allow creating multiple instances of CLINT
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Diffstat (limited to 'hw')
-rw-r--r-- | hw/riscv/meson.build | 1 | ||||
-rw-r--r-- | hw/riscv/numa.c | 242 | ||||
-rw-r--r-- | hw/riscv/sifive_clint.c | 20 | ||||
-rw-r--r-- | hw/riscv/sifive_e.c | 4 | ||||
-rw-r--r-- | hw/riscv/sifive_plic.c | 24 | ||||
-rw-r--r-- | hw/riscv/sifive_u.c | 4 | ||||
-rw-r--r-- | hw/riscv/spike.c | 232 | ||||
-rw-r--r-- | hw/riscv/virt.c | 526 |
8 files changed, 729 insertions, 324 deletions
diff --git a/hw/riscv/meson.build b/hw/riscv/meson.build index 2de8e5a..25af9db 100644 --- a/hw/riscv/meson.build +++ b/hw/riscv/meson.build @@ -1,5 +1,6 @@ riscv_ss = ss.source_set() riscv_ss.add(files('boot.c')) +riscv_ss.add(files('numa.c')) riscv_ss.add(when: 'CONFIG_HART', if_true: files('riscv_hart.c')) riscv_ss.add(when: 'CONFIG_OPENTITAN', if_true: files('opentitan.c')) riscv_ss.add(when: 'CONFIG_RISCV_VIRT', if_true: files('virt.c')) diff --git a/hw/riscv/numa.c b/hw/riscv/numa.c new file mode 100644 index 0000000..4f92307 --- /dev/null +++ b/hw/riscv/numa.c @@ -0,0 +1,242 @@ +/* + * QEMU RISC-V NUMA Helper + * + * Copyright (c) 2020 Western Digital Corporation or its affiliates. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2 or later, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "qemu/log.h" +#include "qemu/error-report.h" +#include "qapi/error.h" +#include "hw/boards.h" +#include "hw/qdev-properties.h" +#include "hw/riscv/numa.h" +#include "sysemu/device_tree.h" + +static bool numa_enabled(const MachineState *ms) +{ + return (ms->numa_state && ms->numa_state->num_nodes) ? true : false; +} + +int riscv_socket_count(const MachineState *ms) +{ + return (numa_enabled(ms)) ? ms->numa_state->num_nodes : 1; +} + +int riscv_socket_first_hartid(const MachineState *ms, int socket_id) +{ + int i, first_hartid = ms->smp.cpus; + + if (!numa_enabled(ms)) { + return (!socket_id) ? 0 : -1; + } + + for (i = 0; i < ms->smp.cpus; i++) { + if (ms->possible_cpus->cpus[i].props.node_id != socket_id) { + continue; + } + if (i < first_hartid) { + first_hartid = i; + } + } + + return (first_hartid < ms->smp.cpus) ? first_hartid : -1; +} + +int riscv_socket_last_hartid(const MachineState *ms, int socket_id) +{ + int i, last_hartid = -1; + + if (!numa_enabled(ms)) { + return (!socket_id) ? ms->smp.cpus - 1 : -1; + } + + for (i = 0; i < ms->smp.cpus; i++) { + if (ms->possible_cpus->cpus[i].props.node_id != socket_id) { + continue; + } + if (i > last_hartid) { + last_hartid = i; + } + } + + return (last_hartid < ms->smp.cpus) ? last_hartid : -1; +} + +int riscv_socket_hart_count(const MachineState *ms, int socket_id) +{ + int first_hartid, last_hartid; + + if (!numa_enabled(ms)) { + return (!socket_id) ? ms->smp.cpus : -1; + } + + first_hartid = riscv_socket_first_hartid(ms, socket_id); + if (first_hartid < 0) { + return -1; + } + + last_hartid = riscv_socket_last_hartid(ms, socket_id); + if (last_hartid < 0) { + return -1; + } + + if (first_hartid > last_hartid) { + return -1; + } + + return last_hartid - first_hartid + 1; +} + +bool riscv_socket_check_hartids(const MachineState *ms, int socket_id) +{ + int i, first_hartid, last_hartid; + + if (!numa_enabled(ms)) { + return (!socket_id) ? true : false; + } + + first_hartid = riscv_socket_first_hartid(ms, socket_id); + if (first_hartid < 0) { + return false; + } + + last_hartid = riscv_socket_last_hartid(ms, socket_id); + if (last_hartid < 0) { + return false; + } + + for (i = first_hartid; i <= last_hartid; i++) { + if (ms->possible_cpus->cpus[i].props.node_id != socket_id) { + return false; + } + } + + return true; +} + +uint64_t riscv_socket_mem_offset(const MachineState *ms, int socket_id) +{ + int i; + uint64_t mem_offset = 0; + + if (!numa_enabled(ms)) { + return 0; + } + + for (i = 0; i < ms->numa_state->num_nodes; i++) { + if (i == socket_id) { + break; + } + mem_offset += ms->numa_state->nodes[i].node_mem; + } + + return (i == socket_id) ? mem_offset : 0; +} + +uint64_t riscv_socket_mem_size(const MachineState *ms, int socket_id) +{ + if (!numa_enabled(ms)) { + return (!socket_id) ? ms->ram_size : 0; + } + + return (socket_id < ms->numa_state->num_nodes) ? + ms->numa_state->nodes[socket_id].node_mem : 0; +} + +void riscv_socket_fdt_write_id(const MachineState *ms, void *fdt, + const char *node_name, int socket_id) +{ + if (numa_enabled(ms)) { + qemu_fdt_setprop_cell(fdt, node_name, "numa-node-id", socket_id); + } +} + +void riscv_socket_fdt_write_distance_matrix(const MachineState *ms, void *fdt) +{ + int i, j, idx; + uint32_t *dist_matrix, dist_matrix_size; + + if (numa_enabled(ms) && ms->numa_state->have_numa_distance) { + dist_matrix_size = riscv_socket_count(ms) * riscv_socket_count(ms); + dist_matrix_size *= (3 * sizeof(uint32_t)); + dist_matrix = g_malloc0(dist_matrix_size); + + for (i = 0; i < riscv_socket_count(ms); i++) { + for (j = 0; j < riscv_socket_count(ms); j++) { + idx = (i * riscv_socket_count(ms) + j) * 3; + dist_matrix[idx + 0] = cpu_to_be32(i); + dist_matrix[idx + 1] = cpu_to_be32(j); + dist_matrix[idx + 2] = + cpu_to_be32(ms->numa_state->nodes[i].distance[j]); + } + } + + qemu_fdt_add_subnode(fdt, "/distance-map"); + qemu_fdt_setprop_string(fdt, "/distance-map", "compatible", + "numa-distance-map-v1"); + qemu_fdt_setprop(fdt, "/distance-map", "distance-matrix", + dist_matrix, dist_matrix_size); + g_free(dist_matrix); + } +} + +CpuInstanceProperties +riscv_numa_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; +} + +int64_t riscv_numa_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; +} + +const CPUArchIdList *riscv_numa_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_core_id = true; + ms->possible_cpus->cpus[n].props.core_id = n; + } + + return ms->possible_cpus; +} diff --git a/hw/riscv/sifive_clint.c b/hw/riscv/sifive_clint.c index 669c21a..15e13d5 100644 --- a/hw/riscv/sifive_clint.c +++ b/hw/riscv/sifive_clint.c @@ -79,7 +79,7 @@ static uint64_t sifive_clint_read(void *opaque, hwaddr addr, unsigned size) SiFiveCLINTState *clint = opaque; if (addr >= clint->sip_base && addr < clint->sip_base + (clint->num_harts << 2)) { - size_t hartid = (addr - clint->sip_base) >> 2; + size_t hartid = clint->hartid_base + ((addr - clint->sip_base) >> 2); CPUState *cpu = qemu_get_cpu(hartid); CPURISCVState *env = cpu ? cpu->env_ptr : NULL; if (!env) { @@ -92,7 +92,8 @@ static uint64_t sifive_clint_read(void *opaque, hwaddr addr, unsigned size) } } else if (addr >= clint->timecmp_base && addr < clint->timecmp_base + (clint->num_harts << 3)) { - size_t hartid = (addr - clint->timecmp_base) >> 3; + size_t hartid = clint->hartid_base + + ((addr - clint->timecmp_base) >> 3); CPUState *cpu = qemu_get_cpu(hartid); CPURISCVState *env = cpu ? cpu->env_ptr : NULL; if (!env) { @@ -129,7 +130,7 @@ static void sifive_clint_write(void *opaque, hwaddr addr, uint64_t value, if (addr >= clint->sip_base && addr < clint->sip_base + (clint->num_harts << 2)) { - size_t hartid = (addr - clint->sip_base) >> 2; + size_t hartid = clint->hartid_base + ((addr - clint->sip_base) >> 2); CPUState *cpu = qemu_get_cpu(hartid); CPURISCVState *env = cpu ? cpu->env_ptr : NULL; if (!env) { @@ -142,7 +143,8 @@ static void sifive_clint_write(void *opaque, hwaddr addr, uint64_t value, return; } else if (addr >= clint->timecmp_base && addr < clint->timecmp_base + (clint->num_harts << 3)) { - size_t hartid = (addr - clint->timecmp_base) >> 3; + size_t hartid = clint->hartid_base + + ((addr - clint->timecmp_base) >> 3); CPUState *cpu = qemu_get_cpu(hartid); CPURISCVState *env = cpu ? cpu->env_ptr : NULL; if (!env) { @@ -186,6 +188,7 @@ static const MemoryRegionOps sifive_clint_ops = { }; static Property sifive_clint_properties[] = { + DEFINE_PROP_UINT32("hartid-base", SiFiveCLINTState, hartid_base, 0), DEFINE_PROP_UINT32("num-harts", SiFiveCLINTState, num_harts, 0), DEFINE_PROP_UINT32("sip-base", SiFiveCLINTState, sip_base, 0), DEFINE_PROP_UINT32("timecmp-base", SiFiveCLINTState, timecmp_base, 0), @@ -227,13 +230,13 @@ type_init(sifive_clint_register_types) /* * Create CLINT device. */ -DeviceState *sifive_clint_create(hwaddr addr, hwaddr size, uint32_t num_harts, - uint32_t sip_base, uint32_t timecmp_base, uint32_t time_base, - bool provide_rdtime) +DeviceState *sifive_clint_create(hwaddr addr, hwaddr size, + uint32_t hartid_base, uint32_t num_harts, uint32_t sip_base, + uint32_t timecmp_base, uint32_t time_base, bool provide_rdtime) { int i; for (i = 0; i < num_harts; i++) { - CPUState *cpu = qemu_get_cpu(i); + CPUState *cpu = qemu_get_cpu(hartid_base + i); CPURISCVState *env = cpu ? cpu->env_ptr : NULL; if (!env) { continue; @@ -247,6 +250,7 @@ DeviceState *sifive_clint_create(hwaddr addr, hwaddr size, uint32_t num_harts, } DeviceState *dev = qdev_new(TYPE_SIFIVE_CLINT); + qdev_prop_set_uint32(dev, "hartid-base", hartid_base); qdev_prop_set_uint32(dev, "num-harts", num_harts); qdev_prop_set_uint32(dev, "sip-base", sip_base); qdev_prop_set_uint32(dev, "timecmp-base", timecmp_base); diff --git a/hw/riscv/sifive_e.c b/hw/riscv/sifive_e.c index c8b0604..ca55cc4 100644 --- a/hw/riscv/sifive_e.c +++ b/hw/riscv/sifive_e.c @@ -200,7 +200,7 @@ static void sifive_e_soc_realize(DeviceState *dev, Error **errp) /* MMIO */ s->plic = sifive_plic_create(memmap[SIFIVE_E_PLIC].base, - (char *)SIFIVE_E_PLIC_HART_CONFIG, + (char *)SIFIVE_E_PLIC_HART_CONFIG, 0, SIFIVE_E_PLIC_NUM_SOURCES, SIFIVE_E_PLIC_NUM_PRIORITIES, SIFIVE_E_PLIC_PRIORITY_BASE, @@ -211,7 +211,7 @@ static void sifive_e_soc_realize(DeviceState *dev, Error **errp) SIFIVE_E_PLIC_CONTEXT_STRIDE, memmap[SIFIVE_E_PLIC].size); sifive_clint_create(memmap[SIFIVE_E_CLINT].base, - memmap[SIFIVE_E_CLINT].size, ms->smp.cpus, + memmap[SIFIVE_E_CLINT].size, 0, ms->smp.cpus, SIFIVE_SIP_BASE, SIFIVE_TIMECMP_BASE, SIFIVE_TIME_BASE, false); create_unimplemented_device("riscv.sifive.e.aon", memmap[SIFIVE_E_AON].base, memmap[SIFIVE_E_AON].size); diff --git a/hw/riscv/sifive_plic.c b/hw/riscv/sifive_plic.c index c20c192..11ef147 100644 --- a/hw/riscv/sifive_plic.c +++ b/hw/riscv/sifive_plic.c @@ -361,6 +361,7 @@ static const MemoryRegionOps sifive_plic_ops = { static Property sifive_plic_properties[] = { DEFINE_PROP_STRING("hart-config", SiFivePLICState, hart_config), + DEFINE_PROP_UINT32("hartid-base", SiFivePLICState, hartid_base, 0), DEFINE_PROP_UINT32("num-sources", SiFivePLICState, num_sources, 0), DEFINE_PROP_UINT32("num-priorities", SiFivePLICState, num_priorities, 0), DEFINE_PROP_UINT32("priority-base", SiFivePLICState, priority_base, 0), @@ -409,10 +410,12 @@ static void parse_hart_config(SiFivePLICState *plic) } hartid++; - /* store hart/mode combinations */ plic->num_addrs = addrid; + plic->num_harts = hartid; + + /* store hart/mode combinations */ plic->addr_config = g_new(PLICAddr, plic->num_addrs); - addrid = 0, hartid = 0; + addrid = 0, hartid = plic->hartid_base; p = plic->hart_config; while ((c = *p++)) { if (c == ',') { @@ -438,8 +441,6 @@ static void sifive_plic_irq_request(void *opaque, int irq, int level) static void sifive_plic_realize(DeviceState *dev, Error **errp) { - MachineState *ms = MACHINE(qdev_get_machine()); - unsigned int smp_cpus = ms->smp.cpus; SiFivePLICState *plic = SIFIVE_PLIC(dev); int i; @@ -460,8 +461,8 @@ static void sifive_plic_realize(DeviceState *dev, Error **errp) * lost a interrupt in the case a PLIC is attached. The SEIP bit must be * hardware controlled when a PLIC is attached. */ - for (i = 0; i < smp_cpus; i++) { - RISCVCPU *cpu = RISCV_CPU(qemu_get_cpu(i)); + for (i = 0; i < plic->num_harts; i++) { + RISCVCPU *cpu = RISCV_CPU(qemu_get_cpu(plic->hartid_base + i)); if (riscv_cpu_claim_interrupts(cpu, MIP_SEIP) < 0) { error_report("SEIP already claimed"); exit(1); @@ -497,16 +498,17 @@ type_init(sifive_plic_register_types) * Create PLIC device. */ DeviceState *sifive_plic_create(hwaddr addr, char *hart_config, - uint32_t num_sources, uint32_t num_priorities, - uint32_t priority_base, uint32_t pending_base, - uint32_t enable_base, uint32_t enable_stride, - uint32_t context_base, uint32_t context_stride, - uint32_t aperture_size) + uint32_t hartid_base, uint32_t num_sources, + uint32_t num_priorities, uint32_t priority_base, + uint32_t pending_base, uint32_t enable_base, + uint32_t enable_stride, uint32_t context_base, + uint32_t context_stride, uint32_t aperture_size) { DeviceState *dev = qdev_new(TYPE_SIFIVE_PLIC); assert(enable_stride == (enable_stride & -enable_stride)); assert(context_stride == (context_stride & -context_stride)); qdev_prop_set_string(dev, "hart-config", hart_config); + qdev_prop_set_uint32(dev, "hartid-base", hartid_base); qdev_prop_set_uint32(dev, "num-sources", num_sources); qdev_prop_set_uint32(dev, "num-priorities", num_priorities); qdev_prop_set_uint32(dev, "priority-base", priority_base); diff --git a/hw/riscv/sifive_u.c b/hw/riscv/sifive_u.c index 18301e6..a48046c 100644 --- a/hw/riscv/sifive_u.c +++ b/hw/riscv/sifive_u.c @@ -687,7 +687,7 @@ static void sifive_u_soc_realize(DeviceState *dev, Error **errp) /* MMIO */ s->plic = sifive_plic_create(memmap[SIFIVE_U_PLIC].base, - plic_hart_config, + plic_hart_config, 0, SIFIVE_U_PLIC_NUM_SOURCES, SIFIVE_U_PLIC_NUM_PRIORITIES, SIFIVE_U_PLIC_PRIORITY_BASE, @@ -703,7 +703,7 @@ static void sifive_u_soc_realize(DeviceState *dev, Error **errp) sifive_uart_create(system_memory, memmap[SIFIVE_U_UART1].base, serial_hd(1), qdev_get_gpio_in(DEVICE(s->plic), SIFIVE_U_UART1_IRQ)); sifive_clint_create(memmap[SIFIVE_U_CLINT].base, - memmap[SIFIVE_U_CLINT].size, ms->smp.cpus, + memmap[SIFIVE_U_CLINT].size, 0, ms->smp.cpus, SIFIVE_SIP_BASE, SIFIVE_TIMECMP_BASE, SIFIVE_TIME_BASE, false); if (!sysbus_realize(SYS_BUS_DEVICE(&s->prci), errp)) { diff --git a/hw/riscv/spike.c b/hw/riscv/spike.c index 13958bd..56f5fe7 100644 --- a/hw/riscv/spike.c +++ b/hw/riscv/spike.c @@ -36,6 +36,7 @@ #include "hw/riscv/sifive_clint.h" #include "hw/riscv/spike.h" #include "hw/riscv/boot.h" +#include "hw/riscv/numa.h" #include "chardev/char.h" #include "sysemu/arch_init.h" #include "sysemu/device_tree.h" @@ -66,9 +67,14 @@ static void create_fdt(SpikeState *s, const struct MemmapEntry *memmap, uint64_t mem_size, const char *cmdline) { void *fdt; - int cpu; - uint32_t *cells; - char *nodename; + uint64_t addr, size; + unsigned long clint_addr; + int cpu, socket; + MachineState *mc = MACHINE(s); + uint32_t *clint_cells; + uint32_t cpu_phandle, intc_phandle, phandle = 1; + char *name, *mem_name, *clint_name, *clust_name; + char *core_name, *cpu_name, *intc_name; fdt = s->fdt = create_device_tree(&s->fdt_size); if (!fdt) { @@ -90,68 +96,91 @@ static void create_fdt(SpikeState *s, const struct MemmapEntry *memmap, qemu_fdt_setprop_cell(fdt, "/soc", "#size-cells", 0x2); qemu_fdt_setprop_cell(fdt, "/soc", "#address-cells", 0x2); - nodename = g_strdup_printf("/memory@%lx", - (long)memmap[SPIKE_DRAM].base); - qemu_fdt_add_subnode(fdt, nodename); - qemu_fdt_setprop_cells(fdt, nodename, "reg", - memmap[SPIKE_DRAM].base >> 32, memmap[SPIKE_DRAM].base, - mem_size >> 32, mem_size); - qemu_fdt_setprop_string(fdt, nodename, "device_type", "memory"); - g_free(nodename); - qemu_fdt_add_subnode(fdt, "/cpus"); qemu_fdt_setprop_cell(fdt, "/cpus", "timebase-frequency", SIFIVE_CLINT_TIMEBASE_FREQ); qemu_fdt_setprop_cell(fdt, "/cpus", "#size-cells", 0x0); qemu_fdt_setprop_cell(fdt, "/cpus", "#address-cells", 0x1); + qemu_fdt_add_subnode(fdt, "/cpus/cpu-map"); + + for (socket = (riscv_socket_count(mc) - 1); socket >= 0; socket--) { + clust_name = g_strdup_printf("/cpus/cpu-map/cluster%d", socket); + qemu_fdt_add_subnode(fdt, clust_name); + + clint_cells = g_new0(uint32_t, s->soc[socket].num_harts * 4); - for (cpu = s->soc.num_harts - 1; cpu >= 0; cpu--) { - nodename = g_strdup_printf("/cpus/cpu@%d", cpu); - char *intc = g_strdup_printf("/cpus/cpu@%d/interrupt-controller", cpu); - char *isa = riscv_isa_string(&s->soc.harts[cpu]); - qemu_fdt_add_subnode(fdt, nodename); + for (cpu = s->soc[socket].num_harts - 1; cpu >= 0; cpu--) { + cpu_phandle = phandle++; + + cpu_name = g_strdup_printf("/cpus/cpu@%d", + s->soc[socket].hartid_base + cpu); + qemu_fdt_add_subnode(fdt, cpu_name); #if defined(TARGET_RISCV32) - qemu_fdt_setprop_string(fdt, nodename, "mmu-type", "riscv,sv32"); + qemu_fdt_setprop_string(fdt, cpu_name, "mmu-type", "riscv,sv32"); #else - qemu_fdt_setprop_string(fdt, nodename, "mmu-type", "riscv,sv48"); + qemu_fdt_setprop_string(fdt, cpu_name, "mmu-type", "riscv,sv48"); #endif - qemu_fdt_setprop_string(fdt, nodename, "riscv,isa", isa); - qemu_fdt_setprop_string(fdt, nodename, "compatible", "riscv"); - qemu_fdt_setprop_string(fdt, nodename, "status", "okay"); - qemu_fdt_setprop_cell(fdt, nodename, "reg", cpu); - qemu_fdt_setprop_string(fdt, nodename, "device_type", "cpu"); - qemu_fdt_add_subnode(fdt, intc); - qemu_fdt_setprop_cell(fdt, intc, "phandle", 1); - qemu_fdt_setprop_string(fdt, intc, "compatible", "riscv,cpu-intc"); - qemu_fdt_setprop(fdt, intc, "interrupt-controller", NULL, 0); - qemu_fdt_setprop_cell(fdt, intc, "#interrupt-cells", 1); - g_free(isa); - g_free(intc); - g_free(nodename); - } + name = riscv_isa_string(&s->soc[socket].harts[cpu]); + qemu_fdt_setprop_string(fdt, cpu_name, "riscv,isa", name); + g_free(name); + qemu_fdt_setprop_string(fdt, cpu_name, "compatible", "riscv"); + qemu_fdt_setprop_string(fdt, cpu_name, "status", "okay"); + qemu_fdt_setprop_cell(fdt, cpu_name, "reg", + s->soc[socket].hartid_base + cpu); + qemu_fdt_setprop_string(fdt, cpu_name, "device_type", "cpu"); + riscv_socket_fdt_write_id(mc, fdt, cpu_name, socket); + qemu_fdt_setprop_cell(fdt, cpu_name, "phandle", cpu_phandle); - cells = g_new0(uint32_t, s->soc.num_harts * 4); - for (cpu = 0; cpu < s->soc.num_harts; cpu++) { - nodename = - g_strdup_printf("/cpus/cpu@%d/interrupt-controller", cpu); - uint32_t intc_phandle = qemu_fdt_get_phandle(fdt, nodename); - cells[cpu * 4 + 0] = cpu_to_be32(intc_phandle); - cells[cpu * 4 + 1] = cpu_to_be32(IRQ_M_SOFT); - cells[cpu * 4 + 2] = cpu_to_be32(intc_phandle); - cells[cpu * 4 + 3] = cpu_to_be32(IRQ_M_TIMER); - g_free(nodename); + intc_name = g_strdup_printf("%s/interrupt-controller", cpu_name); + qemu_fdt_add_subnode(fdt, intc_name); + intc_phandle = phandle++; + qemu_fdt_setprop_cell(fdt, intc_name, "phandle", intc_phandle); + qemu_fdt_setprop_string(fdt, intc_name, "compatible", + "riscv,cpu-intc"); + qemu_fdt_setprop(fdt, intc_name, "interrupt-controller", NULL, 0); + qemu_fdt_setprop_cell(fdt, intc_name, "#interrupt-cells", 1); + + clint_cells[cpu * 4 + 0] = cpu_to_be32(intc_phandle); + clint_cells[cpu * 4 + 1] = cpu_to_be32(IRQ_M_SOFT); + clint_cells[cpu * 4 + 2] = cpu_to_be32(intc_phandle); + clint_cells[cpu * 4 + 3] = cpu_to_be32(IRQ_M_TIMER); + + core_name = g_strdup_printf("%s/core%d", clust_name, cpu); + qemu_fdt_add_subnode(fdt, core_name); + qemu_fdt_setprop_cell(fdt, core_name, "cpu", cpu_phandle); + + g_free(core_name); + g_free(intc_name); + g_free(cpu_name); + } + + addr = memmap[SPIKE_DRAM].base + riscv_socket_mem_offset(mc, socket); + size = riscv_socket_mem_size(mc, socket); + mem_name = g_strdup_printf("/memory@%lx", (long)addr); + qemu_fdt_add_subnode(fdt, mem_name); + qemu_fdt_setprop_cells(fdt, mem_name, "reg", + addr >> 32, addr, size >> 32, size); + qemu_fdt_setprop_string(fdt, mem_name, "device_type", "memory"); + riscv_socket_fdt_write_id(mc, fdt, mem_name, socket); + g_free(mem_name); + + clint_addr = memmap[SPIKE_CLINT].base + + (memmap[SPIKE_CLINT].size * socket); + clint_name = g_strdup_printf("/soc/clint@%lx", clint_addr); + qemu_fdt_add_subnode(fdt, clint_name); + qemu_fdt_setprop_string(fdt, clint_name, "compatible", "riscv,clint0"); + qemu_fdt_setprop_cells(fdt, clint_name, "reg", + 0x0, clint_addr, 0x0, memmap[SPIKE_CLINT].size); + qemu_fdt_setprop(fdt, clint_name, "interrupts-extended", + clint_cells, s->soc[socket].num_harts * sizeof(uint32_t) * 4); + riscv_socket_fdt_write_id(mc, fdt, clint_name, socket); + + g_free(clint_name); + g_free(clint_cells); + g_free(clust_name); } - nodename = g_strdup_printf("/soc/clint@%lx", - (long)memmap[SPIKE_CLINT].base); - qemu_fdt_add_subnode(fdt, nodename); - qemu_fdt_setprop_string(fdt, nodename, "compatible", "riscv,clint0"); - qemu_fdt_setprop_cells(fdt, nodename, "reg", - 0x0, memmap[SPIKE_CLINT].base, - 0x0, memmap[SPIKE_CLINT].size); - qemu_fdt_setprop(fdt, nodename, "interrupts-extended", - cells, s->soc.num_harts * sizeof(uint32_t) * 4); - g_free(cells); - g_free(nodename); + + riscv_socket_fdt_write_distance_matrix(mc, fdt); if (cmdline) { qemu_fdt_add_subnode(fdt, "/chosen"); @@ -162,23 +191,59 @@ static void create_fdt(SpikeState *s, const struct MemmapEntry *memmap, static void spike_board_init(MachineState *machine) { const struct MemmapEntry *memmap = spike_memmap; - - SpikeState *s = g_new0(SpikeState, 1); + SpikeState *s = SPIKE_MACHINE(machine); MemoryRegion *system_memory = get_system_memory(); MemoryRegion *main_mem = g_new(MemoryRegion, 1); MemoryRegion *mask_rom = g_new(MemoryRegion, 1); - unsigned int smp_cpus = machine->smp.cpus; uint32_t fdt_load_addr; uint64_t kernel_entry; + char *soc_name; + int i, base_hartid, hart_count; - /* Initialize SOC */ - object_initialize_child(OBJECT(machine), "soc", &s->soc, - TYPE_RISCV_HART_ARRAY); - object_property_set_str(OBJECT(&s->soc), "cpu-type", machine->cpu_type, - &error_abort); - object_property_set_int(OBJECT(&s->soc), "num-harts", smp_cpus, - &error_abort); - sysbus_realize(SYS_BUS_DEVICE(&s->soc), &error_abort); + /* Check socket count limit */ + if (SPIKE_SOCKETS_MAX < riscv_socket_count(machine)) { + error_report("number of sockets/nodes should be less than %d", + SPIKE_SOCKETS_MAX); + exit(1); + } + + /* Initialize sockets */ + for (i = 0; i < riscv_socket_count(machine); i++) { + if (!riscv_socket_check_hartids(machine, i)) { + error_report("discontinuous hartids in socket%d", i); + exit(1); + } + + base_hartid = riscv_socket_first_hartid(machine, i); + if (base_hartid < 0) { + error_report("can't find hartid base for socket%d", i); + exit(1); + } + + hart_count = riscv_socket_hart_count(machine, i); + if (hart_count < 0) { + error_report("can't find hart count for socket%d", i); + exit(1); + } + + soc_name = g_strdup_printf("soc%d", i); + object_initialize_child(OBJECT(machine), soc_name, &s->soc[i], + TYPE_RISCV_HART_ARRAY); + g_free(soc_name); + object_property_set_str(OBJECT(&s->soc[i]), "cpu-type", + machine->cpu_type, &error_abort); + object_property_set_int(OBJECT(&s->soc[i]), "hartid-base", + base_hartid, &error_abort); + object_property_set_int(OBJECT(&s->soc[i]), "num-harts", + hart_count, &error_abort); + sysbus_realize(SYS_BUS_DEVICE(&s->soc[i]), &error_abort); + + /* Core Local Interruptor (timer and IPI) for each socket */ + sifive_clint_create( + memmap[SPIKE_CLINT].base + i * memmap[SPIKE_CLINT].size, + memmap[SPIKE_CLINT].size, base_hartid, hart_count, + SIFIVE_SIP_BASE, SIFIVE_TIMECMP_BASE, SIFIVE_TIME_BASE, false); + } /* register system main memory (actual RAM) */ memory_region_init_ram(main_mem, NULL, "riscv.spike.ram", @@ -230,21 +295,40 @@ static void spike_board_init(MachineState *machine) fdt_load_addr, s->fdt); /* initialize HTIF using symbols found in load_kernel */ - htif_mm_init(system_memory, mask_rom, &s->soc.harts[0].env, serial_hd(0)); + htif_mm_init(system_memory, mask_rom, + &s->soc[0].harts[0].env, serial_hd(0)); +} - /* Core Local Interruptor (timer and IPI) */ - sifive_clint_create(memmap[SPIKE_CLINT].base, memmap[SPIKE_CLINT].size, - smp_cpus, SIFIVE_SIP_BASE, SIFIVE_TIMECMP_BASE, SIFIVE_TIME_BASE, - false); +static void spike_machine_instance_init(Object *obj) +{ } -static void spike_machine_init(MachineClass *mc) +static void spike_machine_class_init(ObjectClass *oc, void *data) { - mc->desc = "RISC-V Spike Board"; + MachineClass *mc = MACHINE_CLASS(oc); + + mc->desc = "RISC-V Spike board"; mc->init = spike_board_init; - mc->max_cpus = 8; + mc->max_cpus = SPIKE_CPUS_MAX; mc->is_default = true; mc->default_cpu_type = SPIKE_V1_10_0_CPU; + mc->possible_cpu_arch_ids = riscv_numa_possible_cpu_arch_ids; + mc->cpu_index_to_instance_props = riscv_numa_cpu_index_to_props; + mc->get_default_cpu_node_id = riscv_numa_get_default_cpu_node_id; + mc->numa_mem_supported = true; +} + +static const TypeInfo spike_machine_typeinfo = { + .name = MACHINE_TYPE_NAME("spike"), + .parent = TYPE_MACHINE, + .class_init = spike_machine_class_init, + .instance_init = spike_machine_instance_init, + .instance_size = sizeof(SpikeState), +}; + +static void spike_machine_init_register_types(void) +{ + type_register_static(&spike_machine_typeinfo); } -DEFINE_MACHINE("spike", spike_machine_init) +type_init(spike_machine_init_register_types) diff --git a/hw/riscv/virt.c b/hw/riscv/virt.c index 6e91cf1..6fca513 100644 --- a/hw/riscv/virt.c +++ b/hw/riscv/virt.c @@ -35,6 +35,7 @@ #include "hw/riscv/sifive_test.h" #include "hw/riscv/virt.h" #include "hw/riscv/boot.h" +#include "hw/riscv/numa.h" #include "chardev/char.h" #include "sysemu/arch_init.h" #include "sysemu/device_tree.h" @@ -58,7 +59,7 @@ static const struct MemmapEntry { [VIRT_RTC] = { 0x101000, 0x1000 }, [VIRT_CLINT] = { 0x2000000, 0x10000 }, [VIRT_PCIE_PIO] = { 0x3000000, 0x10000 }, - [VIRT_PLIC] = { 0xc000000, 0x4000000 }, + [VIRT_PLIC] = { 0xc000000, VIRT_PLIC_SIZE(VIRT_CPUS_MAX * 2) }, [VIRT_UART0] = { 0x10000000, 0x100 }, [VIRT_VIRTIO] = { 0x10001000, 0x1000 }, [VIRT_FLASH] = { 0x20000000, 0x4000000 }, @@ -179,10 +180,17 @@ static void create_fdt(RISCVVirtState *s, const struct MemmapEntry *memmap, uint64_t mem_size, const char *cmdline) { void *fdt; - int cpu, i; - uint32_t *cells; - char *nodename; - uint32_t plic_phandle, test_phandle, phandle = 1; + int i, cpu, socket; + MachineState *mc = MACHINE(s); + uint64_t addr, size; + uint32_t *clint_cells, *plic_cells; + unsigned long clint_addr, plic_addr; + uint32_t plic_phandle[MAX_NODES]; + uint32_t cpu_phandle, intc_phandle, test_phandle; + uint32_t phandle = 1, plic_mmio_phandle = 1; + uint32_t plic_pcie_phandle = 1, plic_virtio_phandle = 1; + char *mem_name, *cpu_name, *core_name, *intc_name; + char *name, *clint_name, *plic_name, *clust_name; hwaddr flashsize = virt_memmap[VIRT_FLASH].size / 2; hwaddr flashbase = virt_memmap[VIRT_FLASH].base; @@ -203,231 +211,238 @@ static void create_fdt(RISCVVirtState *s, const struct MemmapEntry *memmap, qemu_fdt_setprop_cell(fdt, "/soc", "#size-cells", 0x2); qemu_fdt_setprop_cell(fdt, "/soc", "#address-cells", 0x2); - nodename = g_strdup_printf("/memory@%lx", - (long)memmap[VIRT_DRAM].base); - qemu_fdt_add_subnode(fdt, nodename); - qemu_fdt_setprop_cells(fdt, nodename, "reg", - memmap[VIRT_DRAM].base >> 32, memmap[VIRT_DRAM].base, - mem_size >> 32, mem_size); - qemu_fdt_setprop_string(fdt, nodename, "device_type", "memory"); - g_free(nodename); - qemu_fdt_add_subnode(fdt, "/cpus"); qemu_fdt_setprop_cell(fdt, "/cpus", "timebase-frequency", SIFIVE_CLINT_TIMEBASE_FREQ); qemu_fdt_setprop_cell(fdt, "/cpus", "#size-cells", 0x0); qemu_fdt_setprop_cell(fdt, "/cpus", "#address-cells", 0x1); + qemu_fdt_add_subnode(fdt, "/cpus/cpu-map"); + + for (socket = (riscv_socket_count(mc) - 1); socket >= 0; socket--) { + clust_name = g_strdup_printf("/cpus/cpu-map/cluster%d", socket); + qemu_fdt_add_subnode(fdt, clust_name); + + plic_cells = g_new0(uint32_t, s->soc[socket].num_harts * 4); + clint_cells = g_new0(uint32_t, s->soc[socket].num_harts * 4); + + for (cpu = s->soc[socket].num_harts - 1; cpu >= 0; cpu--) { + cpu_phandle = phandle++; - for (cpu = s->soc.num_harts - 1; cpu >= 0; cpu--) { - int cpu_phandle = phandle++; - int intc_phandle; - nodename = g_strdup_printf("/cpus/cpu@%d", cpu); - char *intc = g_strdup_printf("/cpus/cpu@%d/interrupt-controller", cpu); - char *isa = riscv_isa_string(&s->soc.harts[cpu]); - qemu_fdt_add_subnode(fdt, nodename); + cpu_name = g_strdup_printf("/cpus/cpu@%d", + s->soc[socket].hartid_base + cpu); + qemu_fdt_add_subnode(fdt, cpu_name); #if defined(TARGET_RISCV32) - qemu_fdt_setprop_string(fdt, nodename, "mmu-type", "riscv,sv32"); + qemu_fdt_setprop_string(fdt, cpu_name, "mmu-type", "riscv,sv32"); #else - qemu_fdt_setprop_string(fdt, nodename, "mmu-type", "riscv,sv48"); + qemu_fdt_setprop_string(fdt, cpu_name, "mmu-type", "riscv,sv48"); #endif - qemu_fdt_setprop_string(fdt, nodename, "riscv,isa", isa); - qemu_fdt_setprop_string(fdt, nodename, "compatible", "riscv"); - qemu_fdt_setprop_string(fdt, nodename, "status", "okay"); - qemu_fdt_setprop_cell(fdt, nodename, "reg", cpu); - qemu_fdt_setprop_string(fdt, nodename, "device_type", "cpu"); - qemu_fdt_setprop_cell(fdt, nodename, "phandle", cpu_phandle); - intc_phandle = phandle++; - qemu_fdt_add_subnode(fdt, intc); - qemu_fdt_setprop_cell(fdt, intc, "phandle", intc_phandle); - qemu_fdt_setprop_string(fdt, intc, "compatible", "riscv,cpu-intc"); - qemu_fdt_setprop(fdt, intc, "interrupt-controller", NULL, 0); - qemu_fdt_setprop_cell(fdt, intc, "#interrupt-cells", 1); - g_free(isa); - g_free(intc); - g_free(nodename); - } + name = riscv_isa_string(&s->soc[socket].harts[cpu]); + qemu_fdt_setprop_string(fdt, cpu_name, "riscv,isa", name); + g_free(name); + qemu_fdt_setprop_string(fdt, cpu_name, "compatible", "riscv"); + qemu_fdt_setprop_string(fdt, cpu_name, "status", "okay"); + qemu_fdt_setprop_cell(fdt, cpu_name, "reg", + s->soc[socket].hartid_base + cpu); + qemu_fdt_setprop_string(fdt, cpu_name, "device_type", "cpu"); + riscv_socket_fdt_write_id(mc, fdt, cpu_name, socket); + qemu_fdt_setprop_cell(fdt, cpu_name, "phandle", cpu_phandle); + + intc_name = g_strdup_printf("%s/interrupt-controller", cpu_name); + qemu_fdt_add_subnode(fdt, intc_name); + intc_phandle = phandle++; + qemu_fdt_setprop_cell(fdt, intc_name, "phandle", intc_phandle); + qemu_fdt_setprop_string(fdt, intc_name, "compatible", + "riscv,cpu-intc"); + qemu_fdt_setprop(fdt, intc_name, "interrupt-controller", NULL, 0); + qemu_fdt_setprop_cell(fdt, intc_name, "#interrupt-cells", 1); + + clint_cells[cpu * 4 + 0] = cpu_to_be32(intc_phandle); + clint_cells[cpu * 4 + 1] = cpu_to_be32(IRQ_M_SOFT); + clint_cells[cpu * 4 + 2] = cpu_to_be32(intc_phandle); + clint_cells[cpu * 4 + 3] = cpu_to_be32(IRQ_M_TIMER); + + plic_cells[cpu * 4 + 0] = cpu_to_be32(intc_phandle); + plic_cells[cpu * 4 + 1] = cpu_to_be32(IRQ_M_EXT); + plic_cells[cpu * 4 + 2] = cpu_to_be32(intc_phandle); + plic_cells[cpu * 4 + 3] = cpu_to_be32(IRQ_S_EXT); + + core_name = g_strdup_printf("%s/core%d", clust_name, cpu); + qemu_fdt_add_subnode(fdt, core_name); + qemu_fdt_setprop_cell(fdt, core_name, "cpu", cpu_phandle); + + g_free(core_name); + g_free(intc_name); + g_free(cpu_name); + } - /* Add cpu-topology node */ - qemu_fdt_add_subnode(fdt, "/cpus/cpu-map"); - qemu_fdt_add_subnode(fdt, "/cpus/cpu-map/cluster0"); - for (cpu = s->soc.num_harts - 1; cpu >= 0; cpu--) { - char *core_nodename = g_strdup_printf("/cpus/cpu-map/cluster0/core%d", - cpu); - char *cpu_nodename = g_strdup_printf("/cpus/cpu@%d", cpu); - uint32_t intc_phandle = qemu_fdt_get_phandle(fdt, cpu_nodename); - qemu_fdt_add_subnode(fdt, core_nodename); - qemu_fdt_setprop_cell(fdt, core_nodename, "cpu", intc_phandle); - g_free(core_nodename); - g_free(cpu_nodename); + addr = memmap[VIRT_DRAM].base + riscv_socket_mem_offset(mc, socket); + size = riscv_socket_mem_size(mc, socket); + mem_name = g_strdup_printf("/memory@%lx", (long)addr); + qemu_fdt_add_subnode(fdt, mem_name); + qemu_fdt_setprop_cells(fdt, mem_name, "reg", + addr >> 32, addr, size >> 32, size); + qemu_fdt_setprop_string(fdt, mem_name, "device_type", "memory"); + riscv_socket_fdt_write_id(mc, fdt, mem_name, socket); + g_free(mem_name); + + clint_addr = memmap[VIRT_CLINT].base + + (memmap[VIRT_CLINT].size * socket); + clint_name = g_strdup_printf("/soc/clint@%lx", clint_addr); + qemu_fdt_add_subnode(fdt, clint_name); + qemu_fdt_setprop_string(fdt, clint_name, "compatible", "riscv,clint0"); + qemu_fdt_setprop_cells(fdt, clint_name, "reg", + 0x0, clint_addr, 0x0, memmap[VIRT_CLINT].size); + qemu_fdt_setprop(fdt, clint_name, "interrupts-extended", + clint_cells, s->soc[socket].num_harts * sizeof(uint32_t) * 4); + riscv_socket_fdt_write_id(mc, fdt, clint_name, socket); + g_free(clint_name); + + plic_phandle[socket] = phandle++; + plic_addr = memmap[VIRT_PLIC].base + (memmap[VIRT_PLIC].size * socket); + plic_name = g_strdup_printf("/soc/plic@%lx", plic_addr); + qemu_fdt_add_subnode(fdt, plic_name); + qemu_fdt_setprop_cell(fdt, plic_name, + "#address-cells", FDT_PLIC_ADDR_CELLS); + qemu_fdt_setprop_cell(fdt, plic_name, + "#interrupt-cells", FDT_PLIC_INT_CELLS); + qemu_fdt_setprop_string(fdt, plic_name, "compatible", "riscv,plic0"); + qemu_fdt_setprop(fdt, plic_name, "interrupt-controller", NULL, 0); + qemu_fdt_setprop(fdt, plic_name, "interrupts-extended", + plic_cells, s->soc[socket].num_harts * sizeof(uint32_t) * 4); + qemu_fdt_setprop_cells(fdt, plic_name, "reg", + 0x0, plic_addr, 0x0, memmap[VIRT_PLIC].size); + qemu_fdt_setprop_cell(fdt, plic_name, "riscv,ndev", VIRTIO_NDEV); + riscv_socket_fdt_write_id(mc, fdt, plic_name, socket); + qemu_fdt_setprop_cell(fdt, plic_name, "phandle", plic_phandle[socket]); + g_free(plic_name); + + g_free(clint_cells); + g_free(plic_cells); + g_free(clust_name); } - cells = g_new0(uint32_t, s->soc.num_harts * 4); - for (cpu = 0; cpu < s->soc.num_harts; cpu++) { - nodename = - g_strdup_printf("/cpus/cpu@%d/interrupt-controller", cpu); - uint32_t intc_phandle = qemu_fdt_get_phandle(fdt, nodename); - cells[cpu * 4 + 0] = cpu_to_be32(intc_phandle); - cells[cpu * 4 + 1] = cpu_to_be32(IRQ_M_SOFT); - cells[cpu * 4 + 2] = cpu_to_be32(intc_phandle); - cells[cpu * 4 + 3] = cpu_to_be32(IRQ_M_TIMER); - g_free(nodename); - } - nodename = g_strdup_printf("/soc/clint@%lx", - (long)memmap[VIRT_CLINT].base); - qemu_fdt_add_subnode(fdt, nodename); - qemu_fdt_setprop_string(fdt, nodename, "compatible", "riscv,clint0"); - qemu_fdt_setprop_cells(fdt, nodename, "reg", - 0x0, memmap[VIRT_CLINT].base, - 0x0, memmap[VIRT_CLINT].size); - qemu_fdt_setprop(fdt, nodename, "interrupts-extended", - cells, s->soc.num_harts * sizeof(uint32_t) * 4); - g_free(cells); - g_free(nodename); - - plic_phandle = phandle++; - cells = g_new0(uint32_t, s->soc.num_harts * 4); - for (cpu = 0; cpu < s->soc.num_harts; cpu++) { - nodename = - g_strdup_printf("/cpus/cpu@%d/interrupt-controller", cpu); - uint32_t intc_phandle = qemu_fdt_get_phandle(fdt, nodename); - cells[cpu * 4 + 0] = cpu_to_be32(intc_phandle); - cells[cpu * 4 + 1] = cpu_to_be32(IRQ_M_EXT); - cells[cpu * 4 + 2] = cpu_to_be32(intc_phandle); - cells[cpu * 4 + 3] = cpu_to_be32(IRQ_S_EXT); - g_free(nodename); + for (socket = 0; socket < riscv_socket_count(mc); socket++) { + if (socket == 0) { + plic_mmio_phandle = plic_phandle[socket]; + plic_virtio_phandle = plic_phandle[socket]; + plic_pcie_phandle = plic_phandle[socket]; + } + if (socket == 1) { + plic_virtio_phandle = plic_phandle[socket]; + plic_pcie_phandle = plic_phandle[socket]; + } + if (socket == 2) { + plic_pcie_phandle = plic_phandle[socket]; + } } - nodename = g_strdup_printf("/soc/interrupt-controller@%lx", - (long)memmap[VIRT_PLIC].base); - qemu_fdt_add_subnode(fdt, nodename); - qemu_fdt_setprop_cell(fdt, nodename, "#address-cells", - FDT_PLIC_ADDR_CELLS); - qemu_fdt_setprop_cell(fdt, nodename, "#interrupt-cells", - FDT_PLIC_INT_CELLS); - qemu_fdt_setprop_string(fdt, nodename, "compatible", "riscv,plic0"); - qemu_fdt_setprop(fdt, nodename, "interrupt-controller", NULL, 0); - qemu_fdt_setprop(fdt, nodename, "interrupts-extended", - cells, s->soc.num_harts * sizeof(uint32_t) * 4); - qemu_fdt_setprop_cells(fdt, nodename, "reg", - 0x0, memmap[VIRT_PLIC].base, - 0x0, memmap[VIRT_PLIC].size); - qemu_fdt_setprop_cell(fdt, nodename, "riscv,ndev", VIRTIO_NDEV); - qemu_fdt_setprop_cell(fdt, nodename, "phandle", plic_phandle); - plic_phandle = qemu_fdt_get_phandle(fdt, nodename); - g_free(cells); - g_free(nodename); + + riscv_socket_fdt_write_distance_matrix(mc, fdt); for (i = 0; i < VIRTIO_COUNT; i++) { - nodename = g_strdup_printf("/virtio_mmio@%lx", + name = g_strdup_printf("/soc/virtio_mmio@%lx", (long)(memmap[VIRT_VIRTIO].base + i * memmap[VIRT_VIRTIO].size)); - qemu_fdt_add_subnode(fdt, nodename); - qemu_fdt_setprop_string(fdt, nodename, "compatible", "virtio,mmio"); - qemu_fdt_setprop_cells(fdt, nodename, "reg", + qemu_fdt_add_subnode(fdt, name); + qemu_fdt_setprop_string(fdt, name, "compatible", "virtio,mmio"); + qemu_fdt_setprop_cells(fdt, name, "reg", 0x0, memmap[VIRT_VIRTIO].base + i * memmap[VIRT_VIRTIO].size, 0x0, memmap[VIRT_VIRTIO].size); - qemu_fdt_setprop_cell(fdt, nodename, "interrupt-parent", plic_phandle); - qemu_fdt_setprop_cell(fdt, nodename, "interrupts", VIRTIO_IRQ + i); - g_free(nodename); + qemu_fdt_setprop_cell(fdt, name, "interrupt-parent", + plic_virtio_phandle); + qemu_fdt_setprop_cell(fdt, name, "interrupts", VIRTIO_IRQ + i); + g_free(name); } - nodename = g_strdup_printf("/soc/pci@%lx", + name = g_strdup_printf("/soc/pci@%lx", (long) memmap[VIRT_PCIE_ECAM].base); - qemu_fdt_add_subnode(fdt, nodename); - qemu_fdt_setprop_cell(fdt, nodename, "#address-cells", - FDT_PCI_ADDR_CELLS); - qemu_fdt_setprop_cell(fdt, nodename, "#interrupt-cells", - FDT_PCI_INT_CELLS); - qemu_fdt_setprop_cell(fdt, nodename, "#size-cells", 0x2); - qemu_fdt_setprop_string(fdt, nodename, "compatible", - "pci-host-ecam-generic"); - qemu_fdt_setprop_string(fdt, nodename, "device_type", "pci"); - qemu_fdt_setprop_cell(fdt, nodename, "linux,pci-domain", 0); - qemu_fdt_setprop_cells(fdt, nodename, "bus-range", 0, - memmap[VIRT_PCIE_ECAM].size / - PCIE_MMCFG_SIZE_MIN - 1); - qemu_fdt_setprop(fdt, nodename, "dma-coherent", NULL, 0); - qemu_fdt_setprop_cells(fdt, nodename, "reg", 0, memmap[VIRT_PCIE_ECAM].base, - 0, memmap[VIRT_PCIE_ECAM].size); - qemu_fdt_setprop_sized_cells(fdt, nodename, "ranges", + qemu_fdt_add_subnode(fdt, name); + qemu_fdt_setprop_cell(fdt, name, "#address-cells", FDT_PCI_ADDR_CELLS); + qemu_fdt_setprop_cell(fdt, name, "#interrupt-cells", FDT_PCI_INT_CELLS); + qemu_fdt_setprop_cell(fdt, name, "#size-cells", 0x2); + qemu_fdt_setprop_string(fdt, name, "compatible", "pci-host-ecam-generic"); + qemu_fdt_setprop_string(fdt, name, "device_type", "pci"); + qemu_fdt_setprop_cell(fdt, name, "linux,pci-domain", 0); + qemu_fdt_setprop_cells(fdt, name, "bus-range", 0, + memmap[VIRT_PCIE_ECAM].size / PCIE_MMCFG_SIZE_MIN - 1); + qemu_fdt_setprop(fdt, name, "dma-coherent", NULL, 0); + qemu_fdt_setprop_cells(fdt, name, "reg", 0, + memmap[VIRT_PCIE_ECAM].base, 0, memmap[VIRT_PCIE_ECAM].size); + qemu_fdt_setprop_sized_cells(fdt, name, "ranges", 1, FDT_PCI_RANGE_IOPORT, 2, 0, 2, memmap[VIRT_PCIE_PIO].base, 2, memmap[VIRT_PCIE_PIO].size, 1, FDT_PCI_RANGE_MMIO, 2, memmap[VIRT_PCIE_MMIO].base, 2, memmap[VIRT_PCIE_MMIO].base, 2, memmap[VIRT_PCIE_MMIO].size); - create_pcie_irq_map(fdt, nodename, plic_phandle); - g_free(nodename); + create_pcie_irq_map(fdt, name, plic_pcie_phandle); + g_free(name); test_phandle = phandle++; - nodename = g_strdup_printf("/test@%lx", + name = g_strdup_printf("/soc/test@%lx", (long)memmap[VIRT_TEST].base); - qemu_fdt_add_subnode(fdt, nodename); + qemu_fdt_add_subnode(fdt, name); { const char compat[] = "sifive,test1\0sifive,test0\0syscon"; - qemu_fdt_setprop(fdt, nodename, "compatible", compat, sizeof(compat)); + qemu_fdt_setprop(fdt, name, "compatible", compat, sizeof(compat)); } - qemu_fdt_setprop_cells(fdt, nodename, "reg", + qemu_fdt_setprop_cells(fdt, name, "reg", 0x0, memmap[VIRT_TEST].base, 0x0, memmap[VIRT_TEST].size); - qemu_fdt_setprop_cell(fdt, nodename, "phandle", test_phandle); - test_phandle = qemu_fdt_get_phandle(fdt, nodename); - g_free(nodename); - - nodename = g_strdup_printf("/reboot"); - qemu_fdt_add_subnode(fdt, nodename); - qemu_fdt_setprop_string(fdt, nodename, "compatible", "syscon-reboot"); - qemu_fdt_setprop_cell(fdt, nodename, "regmap", test_phandle); - qemu_fdt_setprop_cell(fdt, nodename, "offset", 0x0); - qemu_fdt_setprop_cell(fdt, nodename, "value", FINISHER_RESET); - g_free(nodename); - - nodename = g_strdup_printf("/poweroff"); - qemu_fdt_add_subnode(fdt, nodename); - qemu_fdt_setprop_string(fdt, nodename, "compatible", "syscon-poweroff"); - qemu_fdt_setprop_cell(fdt, nodename, "regmap", test_phandle); - qemu_fdt_setprop_cell(fdt, nodename, "offset", 0x0); - qemu_fdt_setprop_cell(fdt, nodename, "value", FINISHER_PASS); - g_free(nodename); - - nodename = g_strdup_printf("/uart@%lx", - (long)memmap[VIRT_UART0].base); - qemu_fdt_add_subnode(fdt, nodename); - qemu_fdt_setprop_string(fdt, nodename, "compatible", "ns16550a"); - qemu_fdt_setprop_cells(fdt, nodename, "reg", + qemu_fdt_setprop_cell(fdt, name, "phandle", test_phandle); + test_phandle = qemu_fdt_get_phandle(fdt, name); + g_free(name); + + name = g_strdup_printf("/soc/reboot"); + qemu_fdt_add_subnode(fdt, name); + qemu_fdt_setprop_string(fdt, name, "compatible", "syscon-reboot"); + qemu_fdt_setprop_cell(fdt, name, "regmap", test_phandle); + qemu_fdt_setprop_cell(fdt, name, "offset", 0x0); + qemu_fdt_setprop_cell(fdt, name, "value", FINISHER_RESET); + g_free(name); + + name = g_strdup_printf("/soc/poweroff"); + qemu_fdt_add_subnode(fdt, name); + qemu_fdt_setprop_string(fdt, name, "compatible", "syscon-poweroff"); + qemu_fdt_setprop_cell(fdt, name, "regmap", test_phandle); + qemu_fdt_setprop_cell(fdt, name, "offset", 0x0); + qemu_fdt_setprop_cell(fdt, name, "value", FINISHER_PASS); + g_free(name); + + name = g_strdup_printf("/soc/uart@%lx", (long)memmap[VIRT_UART0].base); + qemu_fdt_add_subnode(fdt, name); + qemu_fdt_setprop_string(fdt, name, "compatible", "ns16550a"); + qemu_fdt_setprop_cells(fdt, name, "reg", 0x0, memmap[VIRT_UART0].base, 0x0, memmap[VIRT_UART0].size); - qemu_fdt_setprop_cell(fdt, nodename, "clock-frequency", 3686400); - qemu_fdt_setprop_cell(fdt, nodename, "interrupt-parent", plic_phandle); - qemu_fdt_setprop_cell(fdt, nodename, "interrupts", UART0_IRQ); + qemu_fdt_setprop_cell(fdt, name, "clock-frequency", 3686400); + qemu_fdt_setprop_cell(fdt, name, "interrupt-parent", plic_mmio_phandle); + qemu_fdt_setprop_cell(fdt, name, "interrupts", UART0_IRQ); qemu_fdt_add_subnode(fdt, "/chosen"); - qemu_fdt_setprop_string(fdt, "/chosen", "stdout-path", nodename); + qemu_fdt_setprop_string(fdt, "/chosen", "stdout-path", name); if (cmdline) { qemu_fdt_setprop_string(fdt, "/chosen", "bootargs", cmdline); } - g_free(nodename); - - nodename = g_strdup_printf("/rtc@%lx", - (long)memmap[VIRT_RTC].base); - qemu_fdt_add_subnode(fdt, nodename); - qemu_fdt_setprop_string(fdt, nodename, "compatible", - "google,goldfish-rtc"); - qemu_fdt_setprop_cells(fdt, nodename, "reg", + g_free(name); + + name = g_strdup_printf("/soc/rtc@%lx", (long)memmap[VIRT_RTC].base); + qemu_fdt_add_subnode(fdt, name); + qemu_fdt_setprop_string(fdt, name, "compatible", "google,goldfish-rtc"); + qemu_fdt_setprop_cells(fdt, name, "reg", 0x0, memmap[VIRT_RTC].base, 0x0, memmap[VIRT_RTC].size); - qemu_fdt_setprop_cell(fdt, nodename, "interrupt-parent", plic_phandle); - qemu_fdt_setprop_cell(fdt, nodename, "interrupts", RTC_IRQ); - g_free(nodename); - - nodename = g_strdup_printf("/flash@%" PRIx64, flashbase); - qemu_fdt_add_subnode(s->fdt, nodename); - qemu_fdt_setprop_string(s->fdt, nodename, "compatible", "cfi-flash"); - qemu_fdt_setprop_sized_cells(s->fdt, nodename, "reg", + qemu_fdt_setprop_cell(fdt, name, "interrupt-parent", plic_mmio_phandle); + qemu_fdt_setprop_cell(fdt, name, "interrupts", RTC_IRQ); + g_free(name); + + name = g_strdup_printf("/soc/flash@%" PRIx64, flashbase); + qemu_fdt_add_subnode(s->fdt, name); + qemu_fdt_setprop_string(s->fdt, name, "compatible", "cfi-flash"); + qemu_fdt_setprop_sized_cells(s->fdt, name, "reg", 2, flashbase, 2, flashsize, 2, flashbase + flashsize, 2, flashsize); - qemu_fdt_setprop_cell(s->fdt, nodename, "bank-width", 4); - g_free(nodename); + qemu_fdt_setprop_cell(s->fdt, name, "bank-width", 4); + g_free(name); } - static inline DeviceState *gpex_pcie_init(MemoryRegion *sys_mem, hwaddr ecam_base, hwaddr ecam_size, hwaddr mmio_base, hwaddr mmio_size, @@ -475,22 +490,101 @@ static void virt_machine_init(MachineState *machine) MemoryRegion *system_memory = get_system_memory(); MemoryRegion *main_mem = g_new(MemoryRegion, 1); MemoryRegion *mask_rom = g_new(MemoryRegion, 1); - char *plic_hart_config; + char *plic_hart_config, *soc_name; size_t plic_hart_config_len; target_ulong start_addr = memmap[VIRT_DRAM].base; uint32_t fdt_load_addr; uint64_t kernel_entry; - int i; - unsigned int smp_cpus = machine->smp.cpus; + DeviceState *mmio_plic, *virtio_plic, *pcie_plic; + int i, j, base_hartid, hart_count; - /* Initialize SOC */ - object_initialize_child(OBJECT(machine), "soc", &s->soc, - TYPE_RISCV_HART_ARRAY); - object_property_set_str(OBJECT(&s->soc), "cpu-type", machine->cpu_type, - &error_abort); - object_property_set_int(OBJECT(&s->soc), "num-harts", smp_cpus, - &error_abort); - sysbus_realize(SYS_BUS_DEVICE(&s->soc), &error_abort); + /* Check socket count limit */ + if (VIRT_SOCKETS_MAX < riscv_socket_count(machine)) { + error_report("number of sockets/nodes should be less than %d", + VIRT_SOCKETS_MAX); + exit(1); + } + + /* Initialize sockets */ + mmio_plic = virtio_plic = pcie_plic = NULL; + for (i = 0; i < riscv_socket_count(machine); i++) { + if (!riscv_socket_check_hartids(machine, i)) { + error_report("discontinuous hartids in socket%d", i); + exit(1); + } + + base_hartid = riscv_socket_first_hartid(machine, i); + if (base_hartid < 0) { + error_report("can't find hartid base for socket%d", i); + exit(1); + } + + hart_count = riscv_socket_hart_count(machine, i); + if (hart_count < 0) { + error_report("can't find hart count for socket%d", i); + exit(1); + } + + soc_name = g_strdup_printf("soc%d", i); + object_initialize_child(OBJECT(machine), soc_name, &s->soc[i], + TYPE_RISCV_HART_ARRAY); + g_free(soc_name); + object_property_set_str(OBJECT(&s->soc[i]), "cpu-type", + machine->cpu_type, &error_abort); + object_property_set_int(OBJECT(&s->soc[i]), "hartid-base", + base_hartid, &error_abort); + object_property_set_int(OBJECT(&s->soc[i]), "num-harts", + hart_count, &error_abort); + sysbus_realize(SYS_BUS_DEVICE(&s->soc[i]), &error_abort); + + /* Per-socket CLINT */ + sifive_clint_create( + memmap[VIRT_CLINT].base + i * memmap[VIRT_CLINT].size, + memmap[VIRT_CLINT].size, base_hartid, hart_count, + SIFIVE_SIP_BASE, SIFIVE_TIMECMP_BASE, SIFIVE_TIME_BASE, true); + + /* Per-socket PLIC hart topology configuration string */ + plic_hart_config_len = + (strlen(VIRT_PLIC_HART_CONFIG) + 1) * hart_count; + plic_hart_config = g_malloc0(plic_hart_config_len); + for (j = 0; j < hart_count; j++) { + if (j != 0) { + strncat(plic_hart_config, ",", plic_hart_config_len); + } + strncat(plic_hart_config, VIRT_PLIC_HART_CONFIG, + plic_hart_config_len); + plic_hart_config_len -= (strlen(VIRT_PLIC_HART_CONFIG) + 1); + } + + /* Per-socket PLIC */ + s->plic[i] = sifive_plic_create( + memmap[VIRT_PLIC].base + i * memmap[VIRT_PLIC].size, + plic_hart_config, base_hartid, + VIRT_PLIC_NUM_SOURCES, + VIRT_PLIC_NUM_PRIORITIES, + VIRT_PLIC_PRIORITY_BASE, + VIRT_PLIC_PENDING_BASE, + VIRT_PLIC_ENABLE_BASE, + VIRT_PLIC_ENABLE_STRIDE, + VIRT_PLIC_CONTEXT_BASE, + VIRT_PLIC_CONTEXT_STRIDE, + memmap[VIRT_PLIC].size); + g_free(plic_hart_config); + + /* Try to use different PLIC instance based device type */ + if (i == 0) { + mmio_plic = s->plic[i]; + virtio_plic = s->plic[i]; + pcie_plic = s->plic[i]; + } + if (i == 1) { + virtio_plic = s->plic[i]; + pcie_plic = s->plic[i]; + } + if (i == 2) { + pcie_plic = s->plic[i]; + } + } /* register system main memory (actual RAM) */ memory_region_init_ram(main_mem, NULL, "riscv_virt_board.ram", @@ -547,38 +641,14 @@ static void virt_machine_init(MachineState *machine) virt_memmap[VIRT_MROM].size, kernel_entry, fdt_load_addr, s->fdt); - /* create PLIC hart topology configuration string */ - plic_hart_config_len = (strlen(VIRT_PLIC_HART_CONFIG) + 1) * smp_cpus; - plic_hart_config = g_malloc0(plic_hart_config_len); - for (i = 0; i < smp_cpus; i++) { - if (i != 0) { - strncat(plic_hart_config, ",", plic_hart_config_len); - } - strncat(plic_hart_config, VIRT_PLIC_HART_CONFIG, plic_hart_config_len); - plic_hart_config_len -= (strlen(VIRT_PLIC_HART_CONFIG) + 1); - } - - /* MMIO */ - s->plic = sifive_plic_create(memmap[VIRT_PLIC].base, - plic_hart_config, - VIRT_PLIC_NUM_SOURCES, - VIRT_PLIC_NUM_PRIORITIES, - VIRT_PLIC_PRIORITY_BASE, - VIRT_PLIC_PENDING_BASE, - VIRT_PLIC_ENABLE_BASE, - VIRT_PLIC_ENABLE_STRIDE, - VIRT_PLIC_CONTEXT_BASE, - VIRT_PLIC_CONTEXT_STRIDE, - memmap[VIRT_PLIC].size); - sifive_clint_create(memmap[VIRT_CLINT].base, - memmap[VIRT_CLINT].size, smp_cpus, - SIFIVE_SIP_BASE, SIFIVE_TIMECMP_BASE, SIFIVE_TIME_BASE, true); + /* SiFive Test MMIO device */ sifive_test_create(memmap[VIRT_TEST].base); + /* VirtIO MMIO devices */ for (i = 0; i < VIRTIO_COUNT; i++) { sysbus_create_simple("virtio-mmio", memmap[VIRT_VIRTIO].base + i * memmap[VIRT_VIRTIO].size, - qdev_get_gpio_in(DEVICE(s->plic), VIRTIO_IRQ + i)); + qdev_get_gpio_in(DEVICE(virtio_plic), VIRTIO_IRQ + i)); } gpex_pcie_init(system_memory, @@ -587,14 +657,14 @@ static void virt_machine_init(MachineState *machine) memmap[VIRT_PCIE_MMIO].base, memmap[VIRT_PCIE_MMIO].size, memmap[VIRT_PCIE_PIO].base, - DEVICE(s->plic), true); + DEVICE(pcie_plic), true); serial_mm_init(system_memory, memmap[VIRT_UART0].base, - 0, qdev_get_gpio_in(DEVICE(s->plic), UART0_IRQ), 399193, + 0, qdev_get_gpio_in(DEVICE(mmio_plic), UART0_IRQ), 399193, serial_hd(0), DEVICE_LITTLE_ENDIAN); sysbus_create_simple("goldfish_rtc", memmap[VIRT_RTC].base, - qdev_get_gpio_in(DEVICE(s->plic), RTC_IRQ)); + qdev_get_gpio_in(DEVICE(mmio_plic), RTC_IRQ)); virt_flash_create(s); @@ -604,8 +674,6 @@ static void virt_machine_init(MachineState *machine) drive_get(IF_PFLASH, 0, i)); } virt_flash_map(s, system_memory); - - g_free(plic_hart_config); } static void virt_machine_instance_init(Object *obj) @@ -618,9 +686,13 @@ static void virt_machine_class_init(ObjectClass *oc, void *data) mc->desc = "RISC-V VirtIO board"; mc->init = virt_machine_init; - mc->max_cpus = 8; + mc->max_cpus = VIRT_CPUS_MAX; mc->default_cpu_type = VIRT_CPU; mc->pci_allow_0_address = true; + mc->possible_cpu_arch_ids = riscv_numa_possible_cpu_arch_ids; + mc->cpu_index_to_instance_props = riscv_numa_cpu_index_to_props; + mc->get_default_cpu_node_id = riscv_numa_get_default_cpu_node_id; + mc->numa_mem_supported = true; } static const TypeInfo virt_machine_typeinfo = { |