[PATCH 0/4] RISC-V multi-socket support

[PATCH 0/4] RISC-V multi-socket support

[Anup Patel]

This series adds multi-socket support for RISC-V virt machine and
RISC-V spike machine. The multi-socket support will help us improve
various RISC-V operating systems, firmwares, and bootloader to
support RISC-V NUMA systems.

These patch can be found in riscv_multi_socket_v1 branch at:
https://github.com/avpatel/qemu.git

To try this patches, we will need:
1. OpenSBI multi-PLIC and multi-CLINT support which can be found in
   multi_plic_clint_v1 branch at:
   https://github.com/avpatel/opensbi.git
2. Linux multi-PLIC improvements support which can be found in
   plic_imp_v1 branch at:
   https://github.com/avpatel/linux.git

Anup Patel (4):
  hw/riscv: Allow creating multiple instances of CLINT
  hw/riscv: spike: Allow creating multiple sockets
  hw/riscv: Allow creating multiple instances of PLIC
  hw/riscv: virt: Allow creating multiple sockets

 hw/riscv/sifive_clint.c         |  20 +-
 hw/riscv/sifive_e.c             |   4 +-
 hw/riscv/sifive_plic.c          |  24 +-
 hw/riscv/sifive_u.c             |   4 +-
 hw/riscv/spike.c                | 210 ++++++++------
 hw/riscv/virt.c                 | 495 ++++++++++++++++++--------------
 include/hw/riscv/sifive_clint.h |   7 +-
 include/hw/riscv/sifive_plic.h  |  12 +-
 include/hw/riscv/spike.h        |   8 +-
 include/hw/riscv/virt.h         |  12 +-
 10 files changed, 458 insertions(+), 338 deletions(-)

-- 
2.25.1

[PATCH 1/4] hw/riscv: Allow creating multiple instances of CLINT

[Anup Patel]

We extend CLINT emulation to allow multiple instances of CLINT in
a QEMU RISC-V machine. To achieve this, we remove first HART id
zero assumption from CLINT emulation.

Signed-off-by: Anup Patel <anup.patel@wdc.com>
---
 hw/riscv/sifive_clint.c         | 20 ++++++++++++--------
 hw/riscv/sifive_e.c             |  2 +-
 hw/riscv/sifive_u.c             |  2 +-
 hw/riscv/spike.c                |  6 +++---
 hw/riscv/virt.c                 |  2 +-
 include/hw/riscv/sifive_clint.h |  7 ++++---
 6 files changed, 22 insertions(+), 17 deletions(-)

diff --git a/hw/riscv/sifive_clint.c b/hw/riscv/sifive_clint.c
index e933d35092..7d713fd743 100644
--- a/hw/riscv/sifive_clint.c
+++ b/hw/riscv/sifive_clint.c
@@ -78,7 +78,7 @@ 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) {
@@ -91,7 +91,8 @@ 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) {
@@ -128,7 +129,7 @@ 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) {
@@ -141,7 +142,8 @@ 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) {
@@ -185,6 +187,7 @@ 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),
@@ -226,13 +229,13 @@ 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;
@@ -246,6 +249,7 @@ DeviceState *sifive_clint_create(hwaddr addr, hwaddr size, uint32_t num_harts,
     }
 
     DeviceState *dev = qdev_create(NULL, 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 b53109521e..1c3b37d0ba 100644
--- a/hw/riscv/sifive_e.c
+++ b/hw/riscv/sifive_e.c
@@ -163,7 +163,7 @@ static void riscv_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_u.c b/hw/riscv/sifive_u.c
index bed10fcfa8..22997fbf13 100644
--- a/hw/riscv/sifive_u.c
+++ b/hw/riscv/sifive_u.c
@@ -601,7 +601,7 @@ static void riscv_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);
 
     object_property_set_bool(OBJECT(&s->prci), true, "realized", &err);
diff --git a/hw/riscv/spike.c b/hw/riscv/spike.c
index d0c4843712..d5e0103d89 100644
--- a/hw/riscv/spike.c
+++ b/hw/riscv/spike.c
@@ -253,7 +253,7 @@ static void spike_board_init(MachineState *machine)
 
     /* 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,
+        0, smp_cpus, SIFIVE_SIP_BASE, SIFIVE_TIMECMP_BASE, SIFIVE_TIME_BASE,
         false);
 }
 
@@ -343,7 +343,7 @@ static void spike_v1_10_0_board_init(MachineState *machine)
 
     /* 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,
+        0, smp_cpus, SIFIVE_SIP_BASE, SIFIVE_TIMECMP_BASE, SIFIVE_TIME_BASE,
         false);
 }
 
@@ -452,7 +452,7 @@ static void spike_v1_09_1_board_init(MachineState *machine)
 
     /* 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,
+        0, smp_cpus, SIFIVE_SIP_BASE, SIFIVE_TIMECMP_BASE, SIFIVE_TIME_BASE,
         false);
 
     g_free(config_string);
diff --git a/hw/riscv/virt.c b/hw/riscv/virt.c
index daae3ebdbb..dcb8a83b35 100644
--- a/hw/riscv/virt.c
+++ b/hw/riscv/virt.c
@@ -596,7 +596,7 @@ static void riscv_virt_board_init(MachineState *machine)
         VIRT_PLIC_CONTEXT_STRIDE,
         memmap[VIRT_PLIC].size);
     sifive_clint_create(memmap[VIRT_CLINT].base,
-        memmap[VIRT_CLINT].size, smp_cpus,
+        memmap[VIRT_CLINT].size, 0, smp_cpus,
         SIFIVE_SIP_BASE, SIFIVE_TIMECMP_BASE, SIFIVE_TIME_BASE, true);
     sifive_test_create(memmap[VIRT_TEST].base);
 
diff --git a/include/hw/riscv/sifive_clint.h b/include/hw/riscv/sifive_clint.h
index 4a720bfece..9f5fb3d31d 100644
--- a/include/hw/riscv/sifive_clint.h
+++ b/include/hw/riscv/sifive_clint.h
@@ -33,6 +33,7 @@ typedef struct SiFiveCLINTState {
 
     /*< public >*/
     MemoryRegion mmio;
+    uint32_t hartid_base;
     uint32_t num_harts;
     uint32_t sip_base;
     uint32_t timecmp_base;
@@ -40,9 +41,9 @@ typedef struct SiFiveCLINTState {
     uint32_t aperture_size;
 } SiFiveCLINTState;
 
-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);
 
 enum {
     SIFIVE_SIP_BASE     = 0x0,
-- 
2.25.1

Re: [PATCH 1/4] hw/riscv: Allow creating multiple instances of CLINT

[Alistair Francis]

On Fri, May 15, 2020 at 11:39 PM Anup Patel <anup.patel@wdc.com> wrote:
>
> We extend CLINT emulation to allow multiple instances of CLINT in
> a QEMU RISC-V machine. To achieve this, we remove first HART id
> zero assumption from CLINT emulation.
>
> Signed-off-by: Anup Patel <anup.patel@wdc.com>

Reviewed-by: Alistair Francis <alistair.francis@wdc.com>

Alistair

> ---
>  hw/riscv/sifive_clint.c         | 20 ++++++++++++--------
>  hw/riscv/sifive_e.c             |  2 +-
>  hw/riscv/sifive_u.c             |  2 +-
>  hw/riscv/spike.c                |  6 +++---
>  hw/riscv/virt.c                 |  2 +-
>  include/hw/riscv/sifive_clint.h |  7 ++++---
>  6 files changed, 22 insertions(+), 17 deletions(-)
>
> diff --git a/hw/riscv/sifive_clint.c b/hw/riscv/sifive_clint.c
> index e933d35092..7d713fd743 100644
> --- a/hw/riscv/sifive_clint.c
> +++ b/hw/riscv/sifive_clint.c
> @@ -78,7 +78,7 @@ 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) {
> @@ -91,7 +91,8 @@ 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) {
> @@ -128,7 +129,7 @@ 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) {
> @@ -141,7 +142,8 @@ 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) {
> @@ -185,6 +187,7 @@ 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),
> @@ -226,13 +229,13 @@ 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;
> @@ -246,6 +249,7 @@ DeviceState *sifive_clint_create(hwaddr addr, hwaddr size, uint32_t num_harts,
>      }
>
>      DeviceState *dev = qdev_create(NULL, 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 b53109521e..1c3b37d0ba 100644
> --- a/hw/riscv/sifive_e.c
> +++ b/hw/riscv/sifive_e.c
> @@ -163,7 +163,7 @@ static void riscv_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_u.c b/hw/riscv/sifive_u.c
> index bed10fcfa8..22997fbf13 100644
> --- a/hw/riscv/sifive_u.c
> +++ b/hw/riscv/sifive_u.c
> @@ -601,7 +601,7 @@ static void riscv_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);
>
>      object_property_set_bool(OBJECT(&s->prci), true, "realized", &err);
> diff --git a/hw/riscv/spike.c b/hw/riscv/spike.c
> index d0c4843712..d5e0103d89 100644
> --- a/hw/riscv/spike.c
> +++ b/hw/riscv/spike.c
> @@ -253,7 +253,7 @@ static void spike_board_init(MachineState *machine)
>
>      /* 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,
> +        0, smp_cpus, SIFIVE_SIP_BASE, SIFIVE_TIMECMP_BASE, SIFIVE_TIME_BASE,
>          false);
>  }
>
> @@ -343,7 +343,7 @@ static void spike_v1_10_0_board_init(MachineState *machine)
>
>      /* 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,
> +        0, smp_cpus, SIFIVE_SIP_BASE, SIFIVE_TIMECMP_BASE, SIFIVE_TIME_BASE,
>          false);
>  }
>
> @@ -452,7 +452,7 @@ static void spike_v1_09_1_board_init(MachineState *machine)
>
>      /* 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,
> +        0, smp_cpus, SIFIVE_SIP_BASE, SIFIVE_TIMECMP_BASE, SIFIVE_TIME_BASE,
>          false);
>
>      g_free(config_string);
> diff --git a/hw/riscv/virt.c b/hw/riscv/virt.c
> index daae3ebdbb..dcb8a83b35 100644
> --- a/hw/riscv/virt.c
> +++ b/hw/riscv/virt.c
> @@ -596,7 +596,7 @@ static void riscv_virt_board_init(MachineState *machine)
>          VIRT_PLIC_CONTEXT_STRIDE,
>          memmap[VIRT_PLIC].size);
>      sifive_clint_create(memmap[VIRT_CLINT].base,
> -        memmap[VIRT_CLINT].size, smp_cpus,
> +        memmap[VIRT_CLINT].size, 0, smp_cpus,
>          SIFIVE_SIP_BASE, SIFIVE_TIMECMP_BASE, SIFIVE_TIME_BASE, true);
>      sifive_test_create(memmap[VIRT_TEST].base);
>
> diff --git a/include/hw/riscv/sifive_clint.h b/include/hw/riscv/sifive_clint.h
> index 4a720bfece..9f5fb3d31d 100644
> --- a/include/hw/riscv/sifive_clint.h
> +++ b/include/hw/riscv/sifive_clint.h
> @@ -33,6 +33,7 @@ typedef struct SiFiveCLINTState {
>
>      /*< public >*/
>      MemoryRegion mmio;
> +    uint32_t hartid_base;
>      uint32_t num_harts;
>      uint32_t sip_base;
>      uint32_t timecmp_base;
> @@ -40,9 +41,9 @@ typedef struct SiFiveCLINTState {
>      uint32_t aperture_size;
>  } SiFiveCLINTState;
>
> -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);
>
>  enum {
>      SIFIVE_SIP_BASE     = 0x0,
> --
> 2.25.1
>
>

Re: [PATCH 1/4] hw/riscv: Allow creating multiple instances of CLINT

[Palmer Dabbelt]

On Fri, 15 May 2020 23:37:43 PDT (-0700), Anup Patel wrote:
> We extend CLINT emulation to allow multiple instances of CLINT in
> a QEMU RISC-V machine. To achieve this, we remove first HART id
> zero assumption from CLINT emulation.
>
> Signed-off-by: Anup Patel <anup.patel@wdc.com>
> ---
>  hw/riscv/sifive_clint.c         | 20 ++++++++++++--------
>  hw/riscv/sifive_e.c             |  2 +-
>  hw/riscv/sifive_u.c             |  2 +-
>  hw/riscv/spike.c                |  6 +++---
>  hw/riscv/virt.c                 |  2 +-
>  include/hw/riscv/sifive_clint.h |  7 ++++---
>  6 files changed, 22 insertions(+), 17 deletions(-)
>
> diff --git a/hw/riscv/sifive_clint.c b/hw/riscv/sifive_clint.c
> index e933d35092..7d713fd743 100644
> --- a/hw/riscv/sifive_clint.c
> +++ b/hw/riscv/sifive_clint.c
> @@ -78,7 +78,7 @@ 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) {
> @@ -91,7 +91,8 @@ 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) {
> @@ -128,7 +129,7 @@ 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) {
> @@ -141,7 +142,8 @@ 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) {
> @@ -185,6 +187,7 @@ 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),
> @@ -226,13 +229,13 @@ 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;
> @@ -246,6 +249,7 @@ DeviceState *sifive_clint_create(hwaddr addr, hwaddr size, uint32_t num_harts,
>      }
>
>      DeviceState *dev = qdev_create(NULL, 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 b53109521e..1c3b37d0ba 100644
> --- a/hw/riscv/sifive_e.c
> +++ b/hw/riscv/sifive_e.c
> @@ -163,7 +163,7 @@ static void riscv_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_u.c b/hw/riscv/sifive_u.c
> index bed10fcfa8..22997fbf13 100644
> --- a/hw/riscv/sifive_u.c
> +++ b/hw/riscv/sifive_u.c
> @@ -601,7 +601,7 @@ static void riscv_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);
>
>      object_property_set_bool(OBJECT(&s->prci), true, "realized", &err);
> diff --git a/hw/riscv/spike.c b/hw/riscv/spike.c
> index d0c4843712..d5e0103d89 100644
> --- a/hw/riscv/spike.c
> +++ b/hw/riscv/spike.c
> @@ -253,7 +253,7 @@ static void spike_board_init(MachineState *machine)
>
>      /* 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,
> +        0, smp_cpus, SIFIVE_SIP_BASE, SIFIVE_TIMECMP_BASE, SIFIVE_TIME_BASE,
>          false);
>  }
>
> @@ -343,7 +343,7 @@ static void spike_v1_10_0_board_init(MachineState *machine)
>
>      /* 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,
> +        0, smp_cpus, SIFIVE_SIP_BASE, SIFIVE_TIMECMP_BASE, SIFIVE_TIME_BASE,
>          false);
>  }
>
> @@ -452,7 +452,7 @@ static void spike_v1_09_1_board_init(MachineState *machine)
>
>      /* 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,
> +        0, smp_cpus, SIFIVE_SIP_BASE, SIFIVE_TIMECMP_BASE, SIFIVE_TIME_BASE,
>          false);
>
>      g_free(config_string);
> diff --git a/hw/riscv/virt.c b/hw/riscv/virt.c
> index daae3ebdbb..dcb8a83b35 100644
> --- a/hw/riscv/virt.c
> +++ b/hw/riscv/virt.c
> @@ -596,7 +596,7 @@ static void riscv_virt_board_init(MachineState *machine)
>          VIRT_PLIC_CONTEXT_STRIDE,
>          memmap[VIRT_PLIC].size);
>      sifive_clint_create(memmap[VIRT_CLINT].base,
> -        memmap[VIRT_CLINT].size, smp_cpus,
> +        memmap[VIRT_CLINT].size, 0, smp_cpus,
>          SIFIVE_SIP_BASE, SIFIVE_TIMECMP_BASE, SIFIVE_TIME_BASE, true);
>      sifive_test_create(memmap[VIRT_TEST].base);
>
> diff --git a/include/hw/riscv/sifive_clint.h b/include/hw/riscv/sifive_clint.h
> index 4a720bfece..9f5fb3d31d 100644
> --- a/include/hw/riscv/sifive_clint.h
> +++ b/include/hw/riscv/sifive_clint.h
> @@ -33,6 +33,7 @@ typedef struct SiFiveCLINTState {
>
>      /*< public >*/
>      MemoryRegion mmio;
> +    uint32_t hartid_base;
>      uint32_t num_harts;
>      uint32_t sip_base;
>      uint32_t timecmp_base;
> @@ -40,9 +41,9 @@ typedef struct SiFiveCLINTState {
>      uint32_t aperture_size;
>  } SiFiveCLINTState;
>
> -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);
>
>  enum {
>      SIFIVE_SIP_BASE     = 0x0,

Reviewed-by: Palmer Dabbelt <palmerdabbelt@google.com>

[PATCH 2/4] hw/riscv: spike: Allow creating multiple sockets

[Anup Patel]

We extend RISC-V spike machine to allow creating a multi-socket machine.
Each RISC-V spike machine socket is a set of HARTs and a CLINT instance.
Other peripherals are shared between all RISC-V spike machine sockets.
We also update RISC-V spike machine device tree to treat each socket as
a NUMA node.

The number of sockets in RISC-V spike machine can be specified using
the "sockets=" sub-option of QEMU "-smp" command-line option. By
default, only one socket RISC-V spike machine will be created.

Currently, we only allow creating upto maximum 4 sockets with minimum
2 HARTs per socket. In future, this limits can be changed.

Signed-off-by: Anup Patel <anup.patel@wdc.com>
---
 hw/riscv/spike.c         | 206 ++++++++++++++++++++++++---------------
 include/hw/riscv/spike.h |   8 +-
 2 files changed, 133 insertions(+), 81 deletions(-)

diff --git a/hw/riscv/spike.c b/hw/riscv/spike.c
index d5e0103d89..f63c57a87c 100644
--- a/hw/riscv/spike.c
+++ b/hw/riscv/spike.c
@@ -64,9 +64,11 @@ 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;
+    int cpu, socket;
+    uint32_t *clint_cells;
+    unsigned long clint_addr;
+    uint32_t cpu_phandle, intc_phandle, phandle = 1;
+    char *name, *clint_name, *clust_name, *core_name, *cpu_name, *intc_name;
 
     fdt = s->fdt = create_device_tree(&s->fdt_size);
     if (!fdt) {
@@ -88,68 +90,85 @@ 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",
+    name = g_strdup_printf("/memory@%lx", (long)memmap[SPIKE_DRAM].base);
+    qemu_fdt_add_subnode(fdt, name);
+    qemu_fdt_setprop_cells(fdt, name, "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_setprop_string(fdt, name, "device_type", "memory");
+    g_free(name);
 
     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 (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 (socket = (s->num_socs - 1); socket >= 0; socket--) {
+        clust_name = g_strdup_printf("/cpus/cpu-map/cluster0%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[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");
+            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);
+
+            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);
+        }
 
-    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);
+        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);
+
+        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);
 
     if (cmdline) {
         qemu_fdt_add_subnode(fdt, "/chosen");
@@ -160,23 +179,51 @@ 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);
     MemoryRegion *system_memory = get_system_memory();
     MemoryRegion *main_mem = g_new(MemoryRegion, 1);
     MemoryRegion *mask_rom = g_new(MemoryRegion, 1);
     int i;
+    char *soc_name;
     unsigned int smp_cpus = machine->smp.cpus;
-
-    /* Initialize SOC */
-    object_initialize_child(OBJECT(machine), "soc", &s->soc, sizeof(s->soc),
-                            TYPE_RISCV_HART_ARRAY, &error_abort, NULL);
-    object_property_set_str(OBJECT(&s->soc), machine->cpu_type, "cpu-type",
-                            &error_abort);
-    object_property_set_int(OBJECT(&s->soc), smp_cpus, "num-harts",
-                            &error_abort);
-    object_property_set_bool(OBJECT(&s->soc), true, "realized",
-                            &error_abort);
+    unsigned int base_hartid, cpus_per_socket;
+
+    s->num_socs = machine->smp.sockets;
+
+    /* Ensure minumum required CPUs per socket */
+    if ((smp_cpus / s->num_socs) < SPIKE_CPUS_PER_SOCKET_MIN)
+        s->num_socs = 1;
+
+    /* Limit the number of sockets */
+    if (SPIKE_SOCKETS_MAX < s->num_socs)
+        s->num_socs = SPIKE_SOCKETS_MAX;
+
+    /* Initialize socket */
+    for (i = 0; i < s->num_socs; i++) {
+        base_hartid = i * (smp_cpus / s->num_socs);
+        if (i == (s->num_socs - 1))
+            cpus_per_socket = smp_cpus - base_hartid;
+        else
+            cpus_per_socket = smp_cpus / s->num_socs;
+        soc_name = g_strdup_printf("soc%d", i);
+        object_initialize_child(OBJECT(machine), soc_name, &s->soc[i],
+            sizeof(s->soc[i]), TYPE_RISCV_HART_ARRAY, &error_abort, NULL);
+        g_free(soc_name);
+        object_property_set_str(OBJECT(&s->soc[i]),
+            machine->cpu_type, "cpu-type", &error_abort);
+        object_property_set_int(OBJECT(&s->soc[i]),
+            base_hartid, "hartid-base", &error_abort);
+        object_property_set_int(OBJECT(&s->soc[i]),
+            cpus_per_socket, "num-harts", &error_abort);
+        object_property_set_bool(OBJECT(&s->soc[i]),
+            true, "realized", &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, cpus_per_socket,
+            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",
@@ -249,12 +296,7 @@ static void spike_board_init(MachineState *machine)
                           &address_space_memory);
 
     /* initialize HTIF using symbols found in load_kernel */
-    htif_mm_init(system_memory, mask_rom, &s->soc.harts[0].env, serial_hd(0));
-
-    /* Core Local Interruptor (timer and IPI) */
-    sifive_clint_create(memmap[SPIKE_CLINT].base, memmap[SPIKE_CLINT].size,
-        0, smp_cpus, SIFIVE_SIP_BASE, SIFIVE_TIMECMP_BASE, SIFIVE_TIME_BASE,
-        false);
+    htif_mm_init(system_memory, mask_rom, &s->soc[0].harts[0].env, serial_hd(0));
 }
 
 static void spike_v1_10_0_board_init(MachineState *machine)
@@ -268,6 +310,8 @@ static void spike_v1_10_0_board_init(MachineState *machine)
     int i;
     unsigned int smp_cpus = machine->smp.cpus;
 
+    s->num_socs = 1;
+
     if (!qtest_enabled()) {
         info_report("The Spike v1.10.0 machine has been deprecated. "
                     "Please use the generic spike machine and specify the ISA "
@@ -275,13 +319,13 @@ static void spike_v1_10_0_board_init(MachineState *machine)
     }
 
     /* Initialize SOC */
-    object_initialize_child(OBJECT(machine), "soc", &s->soc, sizeof(s->soc),
+    object_initialize_child(OBJECT(machine), "soc", &s->soc[0], sizeof(s->soc[0]),
                             TYPE_RISCV_HART_ARRAY, &error_abort, NULL);
-    object_property_set_str(OBJECT(&s->soc), SPIKE_V1_10_0_CPU, "cpu-type",
+    object_property_set_str(OBJECT(&s->soc[0]), SPIKE_V1_10_0_CPU, "cpu-type",
                             &error_abort);
-    object_property_set_int(OBJECT(&s->soc), smp_cpus, "num-harts",
+    object_property_set_int(OBJECT(&s->soc[0]), smp_cpus, "num-harts",
                             &error_abort);
-    object_property_set_bool(OBJECT(&s->soc), true, "realized",
+    object_property_set_bool(OBJECT(&s->soc[0]), true, "realized",
                             &error_abort);
 
     /* register system main memory (actual RAM) */
@@ -339,7 +383,7 @@ static void spike_v1_10_0_board_init(MachineState *machine)
                           &address_space_memory);
 
     /* 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,
@@ -358,6 +402,8 @@ static void spike_v1_09_1_board_init(MachineState *machine)
     int i;
     unsigned int smp_cpus = machine->smp.cpus;
 
+    s->num_socs = 1;
+
     if (!qtest_enabled()) {
         info_report("The Spike v1.09.1 machine has been deprecated. "
                     "Please use the generic spike machine and specify the ISA "
@@ -365,13 +411,13 @@ static void spike_v1_09_1_board_init(MachineState *machine)
     }
 
     /* Initialize SOC */
-    object_initialize_child(OBJECT(machine), "soc", &s->soc, sizeof(s->soc),
+    object_initialize_child(OBJECT(machine), "soc", &s->soc[0], sizeof(s->soc[0]),
                             TYPE_RISCV_HART_ARRAY, &error_abort, NULL);
-    object_property_set_str(OBJECT(&s->soc), SPIKE_V1_09_1_CPU, "cpu-type",
+    object_property_set_str(OBJECT(&s->soc[0]), SPIKE_V1_09_1_CPU, "cpu-type",
                             &error_abort);
-    object_property_set_int(OBJECT(&s->soc), smp_cpus, "num-harts",
+    object_property_set_int(OBJECT(&s->soc[0]), smp_cpus, "num-harts",
                             &error_abort);
-    object_property_set_bool(OBJECT(&s->soc), true, "realized",
+    object_property_set_bool(OBJECT(&s->soc[0]), true, "realized",
                             &error_abort);
 
     /* register system main memory (actual RAM) */
@@ -425,7 +471,7 @@ static void spike_v1_09_1_board_init(MachineState *machine)
         "};\n";
 
     /* build config string with supplied memory size */
-    char *isa = riscv_isa_string(&s->soc.harts[0]);
+    char *isa = riscv_isa_string(&s->soc[0].harts[0]);
     char *config_string = g_strdup_printf(config_string_tmpl,
         (uint64_t)memmap[SPIKE_CLINT].base + SIFIVE_TIME_BASE,
         (uint64_t)memmap[SPIKE_DRAM].base,
@@ -448,7 +494,7 @@ static void spike_v1_09_1_board_init(MachineState *machine)
                           &address_space_memory);
 
     /* 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,
@@ -476,7 +522,7 @@ static void spike_machine_init(MachineClass *mc)
 {
     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;
 }
diff --git a/include/hw/riscv/spike.h b/include/hw/riscv/spike.h
index dc770421bc..04a9f593b5 100644
--- a/include/hw/riscv/spike.h
+++ b/include/hw/riscv/spike.h
@@ -22,12 +22,18 @@
 #include "hw/riscv/riscv_hart.h"
 #include "hw/sysbus.h"
 
+#define SPIKE_SOCKETS_MAX 4
+#define SPIKE_CPUS_PER_SOCKET_MIN 2
+#define SPIKE_CPUS_PER_SOCKET_MAX 4
+#define SPIKE_CPUS_MAX (SPIKE_SOCKETS_MAX * SPIKE_CPUS_PER_SOCKET_MAX)
+
 typedef struct {
     /*< private >*/
     SysBusDevice parent_obj;
 
     /*< public >*/
-    RISCVHartArrayState soc;
+    unsigned int num_socs;
+    RISCVHartArrayState soc[SPIKE_SOCKETS_MAX];
     void *fdt;
     int fdt_size;
 } SpikeState;
-- 
2.25.1

Re: [PATCH 2/4] hw/riscv: spike: Allow creating multiple sockets

[Palmer Dabbelt]

On Fri, 15 May 2020 23:37:44 PDT (-0700), Anup Patel wrote:
> We extend RISC-V spike machine to allow creating a multi-socket machine.
> Each RISC-V spike machine socket is a set of HARTs and a CLINT instance.
> Other peripherals are shared between all RISC-V spike machine sockets.
> We also update RISC-V spike machine device tree to treat each socket as
> a NUMA node.
>
> The number of sockets in RISC-V spike machine can be specified using
> the "sockets=" sub-option of QEMU "-smp" command-line option. By
> default, only one socket RISC-V spike machine will be created.
>
> Currently, we only allow creating upto maximum 4 sockets with minimum
> 2 HARTs per socket. In future, this limits can be changed.
>
> Signed-off-by: Anup Patel <anup.patel@wdc.com>
> ---
>  hw/riscv/spike.c         | 206 ++++++++++++++++++++++++---------------
>  include/hw/riscv/spike.h |   8 +-
>  2 files changed, 133 insertions(+), 81 deletions(-)
>
> diff --git a/hw/riscv/spike.c b/hw/riscv/spike.c
> index d5e0103d89..f63c57a87c 100644
> --- a/hw/riscv/spike.c
> +++ b/hw/riscv/spike.c
> @@ -64,9 +64,11 @@ 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;
> +    int cpu, socket;
> +    uint32_t *clint_cells;
> +    unsigned long clint_addr;
> +    uint32_t cpu_phandle, intc_phandle, phandle = 1;
> +    char *name, *clint_name, *clust_name, *core_name, *cpu_name, *intc_name;
>
>      fdt = s->fdt = create_device_tree(&s->fdt_size);
>      if (!fdt) {
> @@ -88,68 +90,85 @@ 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",
> +    name = g_strdup_printf("/memory@%lx", (long)memmap[SPIKE_DRAM].base);
> +    qemu_fdt_add_subnode(fdt, name);
> +    qemu_fdt_setprop_cells(fdt, name, "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_setprop_string(fdt, name, "device_type", "memory");
> +    g_free(name);
>
>      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 (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 (socket = (s->num_socs - 1); socket >= 0; socket--) {
> +        clust_name = g_strdup_printf("/cpus/cpu-map/cluster0%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[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");
> +            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);
> +
> +            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);
> +        }
>
> -    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);
> +        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);
> +
> +        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);
>
>      if (cmdline) {
>          qemu_fdt_add_subnode(fdt, "/chosen");
> @@ -160,23 +179,51 @@ 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);
>      MemoryRegion *system_memory = get_system_memory();
>      MemoryRegion *main_mem = g_new(MemoryRegion, 1);
>      MemoryRegion *mask_rom = g_new(MemoryRegion, 1);
>      int i;
> +    char *soc_name;
>      unsigned int smp_cpus = machine->smp.cpus;
> -
> -    /* Initialize SOC */
> -    object_initialize_child(OBJECT(machine), "soc", &s->soc, sizeof(s->soc),
> -                            TYPE_RISCV_HART_ARRAY, &error_abort, NULL);
> -    object_property_set_str(OBJECT(&s->soc), machine->cpu_type, "cpu-type",
> -                            &error_abort);
> -    object_property_set_int(OBJECT(&s->soc), smp_cpus, "num-harts",
> -                            &error_abort);
> -    object_property_set_bool(OBJECT(&s->soc), true, "realized",
> -                            &error_abort);
> +    unsigned int base_hartid, cpus_per_socket;
> +
> +    s->num_socs = machine->smp.sockets;
> +
> +    /* Ensure minumum required CPUs per socket */
> +    if ((smp_cpus / s->num_socs) < SPIKE_CPUS_PER_SOCKET_MIN)
> +        s->num_socs = 1;

Why?  It seems like creating single-hart sockets would be a good test case, and
I'm pretty sure it's a configuration that we had in embedded systems.

> +    /* Limit the number of sockets */
> +    if (SPIKE_SOCKETS_MAX < s->num_socs)
> +        s->num_socs = SPIKE_SOCKETS_MAX;
> +
> +    /* Initialize socket */
> +    for (i = 0; i < s->num_socs; i++) {
> +        base_hartid = i * (smp_cpus / s->num_socs);
> +        if (i == (s->num_socs - 1))
> +            cpus_per_socket = smp_cpus - base_hartid;
> +        else
> +            cpus_per_socket = smp_cpus / s->num_socs;
> +        soc_name = g_strdup_printf("soc%d", i);
> +        object_initialize_child(OBJECT(machine), soc_name, &s->soc[i],
> +            sizeof(s->soc[i]), TYPE_RISCV_HART_ARRAY, &error_abort, NULL);
> +        g_free(soc_name);
> +        object_property_set_str(OBJECT(&s->soc[i]),
> +            machine->cpu_type, "cpu-type", &error_abort);
> +        object_property_set_int(OBJECT(&s->soc[i]),
> +            base_hartid, "hartid-base", &error_abort);
> +        object_property_set_int(OBJECT(&s->soc[i]),
> +            cpus_per_socket, "num-harts", &error_abort);
> +        object_property_set_bool(OBJECT(&s->soc[i]),
> +            true, "realized", &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, cpus_per_socket,
> +            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",
> @@ -249,12 +296,7 @@ static void spike_board_init(MachineState *machine)
>                            &address_space_memory);
>
>      /* initialize HTIF using symbols found in load_kernel */
> -    htif_mm_init(system_memory, mask_rom, &s->soc.harts[0].env, serial_hd(0));
> -
> -    /* Core Local Interruptor (timer and IPI) */
> -    sifive_clint_create(memmap[SPIKE_CLINT].base, memmap[SPIKE_CLINT].size,
> -        0, smp_cpus, SIFIVE_SIP_BASE, SIFIVE_TIMECMP_BASE, SIFIVE_TIME_BASE,
> -        false);
> +    htif_mm_init(system_memory, mask_rom, &s->soc[0].harts[0].env, serial_hd(0));
>  }
>
>  static void spike_v1_10_0_board_init(MachineState *machine)
> @@ -268,6 +310,8 @@ static void spike_v1_10_0_board_init(MachineState *machine)
>      int i;
>      unsigned int smp_cpus = machine->smp.cpus;
>
> +    s->num_socs = 1;
> +
>      if (!qtest_enabled()) {
>          info_report("The Spike v1.10.0 machine has been deprecated. "
>                      "Please use the generic spike machine and specify the ISA "
> @@ -275,13 +319,13 @@ static void spike_v1_10_0_board_init(MachineState *machine)
>      }
>
>      /* Initialize SOC */
> -    object_initialize_child(OBJECT(machine), "soc", &s->soc, sizeof(s->soc),
> +    object_initialize_child(OBJECT(machine), "soc", &s->soc[0], sizeof(s->soc[0]),
>                              TYPE_RISCV_HART_ARRAY, &error_abort, NULL);
> -    object_property_set_str(OBJECT(&s->soc), SPIKE_V1_10_0_CPU, "cpu-type",
> +    object_property_set_str(OBJECT(&s->soc[0]), SPIKE_V1_10_0_CPU, "cpu-type",
>                              &error_abort);
> -    object_property_set_int(OBJECT(&s->soc), smp_cpus, "num-harts",
> +    object_property_set_int(OBJECT(&s->soc[0]), smp_cpus, "num-harts",
>                              &error_abort);
> -    object_property_set_bool(OBJECT(&s->soc), true, "realized",
> +    object_property_set_bool(OBJECT(&s->soc[0]), true, "realized",
>                              &error_abort);
>
>      /* register system main memory (actual RAM) */
> @@ -339,7 +383,7 @@ static void spike_v1_10_0_board_init(MachineState *machine)
>                            &address_space_memory);
>
>      /* 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,
> @@ -358,6 +402,8 @@ static void spike_v1_09_1_board_init(MachineState *machine)
>      int i;
>      unsigned int smp_cpus = machine->smp.cpus;
>
> +    s->num_socs = 1;
> +
>      if (!qtest_enabled()) {
>          info_report("The Spike v1.09.1 machine has been deprecated. "
>                      "Please use the generic spike machine and specify the ISA "
> @@ -365,13 +411,13 @@ static void spike_v1_09_1_board_init(MachineState *machine)
>      }
>
>      /* Initialize SOC */
> -    object_initialize_child(OBJECT(machine), "soc", &s->soc, sizeof(s->soc),
> +    object_initialize_child(OBJECT(machine), "soc", &s->soc[0], sizeof(s->soc[0]),
>                              TYPE_RISCV_HART_ARRAY, &error_abort, NULL);
> -    object_property_set_str(OBJECT(&s->soc), SPIKE_V1_09_1_CPU, "cpu-type",
> +    object_property_set_str(OBJECT(&s->soc[0]), SPIKE_V1_09_1_CPU, "cpu-type",
>                              &error_abort);
> -    object_property_set_int(OBJECT(&s->soc), smp_cpus, "num-harts",
> +    object_property_set_int(OBJECT(&s->soc[0]), smp_cpus, "num-harts",
>                              &error_abort);
> -    object_property_set_bool(OBJECT(&s->soc), true, "realized",
> +    object_property_set_bool(OBJECT(&s->soc[0]), true, "realized",
>                              &error_abort);
>
>      /* register system main memory (actual RAM) */
> @@ -425,7 +471,7 @@ static void spike_v1_09_1_board_init(MachineState *machine)
>          "};\n";
>
>      /* build config string with supplied memory size */
> -    char *isa = riscv_isa_string(&s->soc.harts[0]);
> +    char *isa = riscv_isa_string(&s->soc[0].harts[0]);
>      char *config_string = g_strdup_printf(config_string_tmpl,
>          (uint64_t)memmap[SPIKE_CLINT].base + SIFIVE_TIME_BASE,
>          (uint64_t)memmap[SPIKE_DRAM].base,
> @@ -448,7 +494,7 @@ static void spike_v1_09_1_board_init(MachineState *machine)
>                            &address_space_memory);
>
>      /* 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,
> @@ -476,7 +522,7 @@ static void spike_machine_init(MachineClass *mc)
>  {
>      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;
>  }
> diff --git a/include/hw/riscv/spike.h b/include/hw/riscv/spike.h
> index dc770421bc..04a9f593b5 100644
> --- a/include/hw/riscv/spike.h
> +++ b/include/hw/riscv/spike.h
> @@ -22,12 +22,18 @@
>  #include "hw/riscv/riscv_hart.h"
>  #include "hw/sysbus.h"
>
> +#define SPIKE_SOCKETS_MAX 4
> +#define SPIKE_CPUS_PER_SOCKET_MIN 2
> +#define SPIKE_CPUS_PER_SOCKET_MAX 4
> +#define SPIKE_CPUS_MAX (SPIKE_SOCKETS_MAX * SPIKE_CPUS_PER_SOCKET_MAX)
> +
>  typedef struct {
>      /*< private >*/
>      SysBusDevice parent_obj;
>
>      /*< public >*/
> -    RISCVHartArrayState soc;
> +    unsigned int num_socs;
> +    RISCVHartArrayState soc[SPIKE_SOCKETS_MAX];
>      void *fdt;
>      int fdt_size;
>  } SpikeState;

RE: [PATCH 2/4] hw/riscv: spike: Allow creating multiple sockets

[Anup Patel]

> -----Original Message-----
> From: Palmer Dabbelt <palmer@dabbelt.com>
> Sent: 22 May 2020 01:46
> To: Anup Patel <Anup.Patel@wdc.com>
> Cc: Peter Maydell <peter.maydell@linaro.org>; Alistair Francis
> <Alistair.Francis@wdc.com>; sagark@eecs.berkeley.edu; Atish Patra
> <Atish.Patra@wdc.com>; anup@brainfault.org; qemu-riscv@nongnu.org;
> qemu-devel@nongnu.org; Anup Patel <Anup.Patel@wdc.com>
> Subject: Re: [PATCH 2/4] hw/riscv: spike: Allow creating multiple sockets
> 
> On Fri, 15 May 2020 23:37:44 PDT (-0700), Anup Patel wrote:
> > We extend RISC-V spike machine to allow creating a multi-socket machine.
> > Each RISC-V spike machine socket is a set of HARTs and a CLINT instance.
> > Other peripherals are shared between all RISC-V spike machine sockets.
> > We also update RISC-V spike machine device tree to treat each socket
> > as a NUMA node.
> >
> > The number of sockets in RISC-V spike machine can be specified using
> > the "sockets=" sub-option of QEMU "-smp" command-line option. By
> > default, only one socket RISC-V spike machine will be created.
> >
> > Currently, we only allow creating upto maximum 4 sockets with minimum
> > 2 HARTs per socket. In future, this limits can be changed.
> >
> > Signed-off-by: Anup Patel <anup.patel@wdc.com>
> > ---
> >  hw/riscv/spike.c         | 206 ++++++++++++++++++++++++---------------
> >  include/hw/riscv/spike.h |   8 +-
> >  2 files changed, 133 insertions(+), 81 deletions(-)
> >
> > diff --git a/hw/riscv/spike.c b/hw/riscv/spike.c index
> > d5e0103d89..f63c57a87c 100644
> > --- a/hw/riscv/spike.c
> > +++ b/hw/riscv/spike.c
> > @@ -64,9 +64,11 @@ 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;
> > +    int cpu, socket;
> > +    uint32_t *clint_cells;
> > +    unsigned long clint_addr;
> > +    uint32_t cpu_phandle, intc_phandle, phandle = 1;
> > +    char *name, *clint_name, *clust_name, *core_name, *cpu_name,
> > + *intc_name;
> >
> >      fdt = s->fdt = create_device_tree(&s->fdt_size);
> >      if (!fdt) {
> > @@ -88,68 +90,85 @@ 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",
> > +    name = g_strdup_printf("/memory@%lx",
> (long)memmap[SPIKE_DRAM].base);
> > +    qemu_fdt_add_subnode(fdt, name);
> > +    qemu_fdt_setprop_cells(fdt, name, "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_setprop_string(fdt, name, "device_type", "memory");
> > +    g_free(name);
> >
> >      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 (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 (socket = (s->num_socs - 1); socket >= 0; socket--) {
> > +        clust_name = g_strdup_printf("/cpus/cpu-map/cluster0%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[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");
> > +            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);
> > +
> > +            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);
> > +        }
> >
> > -    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);
> > +        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);
> > +
> > +        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);
> >
> >      if (cmdline) {
> >          qemu_fdt_add_subnode(fdt, "/chosen"); @@ -160,23 +179,51 @@
> > 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);
> >      MemoryRegion *system_memory = get_system_memory();
> >      MemoryRegion *main_mem = g_new(MemoryRegion, 1);
> >      MemoryRegion *mask_rom = g_new(MemoryRegion, 1);
> >      int i;
> > +    char *soc_name;
> >      unsigned int smp_cpus = machine->smp.cpus;
> > -
> > -    /* Initialize SOC */
> > -    object_initialize_child(OBJECT(machine), "soc", &s->soc, sizeof(s->soc),
> > -                            TYPE_RISCV_HART_ARRAY, &error_abort, NULL);
> > -    object_property_set_str(OBJECT(&s->soc), machine->cpu_type, "cpu-
> type",
> > -                            &error_abort);
> > -    object_property_set_int(OBJECT(&s->soc), smp_cpus, "num-harts",
> > -                            &error_abort);
> > -    object_property_set_bool(OBJECT(&s->soc), true, "realized",
> > -                            &error_abort);
> > +    unsigned int base_hartid, cpus_per_socket;
> > +
> > +    s->num_socs = machine->smp.sockets;
> > +
> > +    /* Ensure minumum required CPUs per socket */
> > +    if ((smp_cpus / s->num_socs) < SPIKE_CPUS_PER_SOCKET_MIN)
> > +        s->num_socs = 1;
> 
> Why?  It seems like creating single-hart sockets would be a good test case, and
> I'm pretty sure it's a configuration that we had in embedded systems.

Yes, single-hart sockets are sensible for testing software.

When "sockets=" sub-option is not provided in "-smp " command line
options, the machine->smp.sockets is set same as machine->smp.cpus
by smp_parse() function in hw/core/machine.c. This means by default
we will always get single-hart per socket. In other words, "-smp 4" will
be 4 cpus and 4 sockets. This is counter intuitive for users because when
"sockets=" is not provided we should default to single socket irrespective
to number of cpus.

I had added SPIKE_CPUS_PER_SOCKET_MIN to handle the default case
when no "sockets=" sub-option is provided.

Alternate approach will be: 
1. Add more members in struct CpuTopology of include/hw/boards.h
    to help us know whether "sockets=" option was passed or not
2. Update smp_parse() for new members in struct CpuTopology
3. Assume single-socket machine in QEMU RISC-V virt and QEMU
    RISC-V spike machines when "sockets=" option was not passed

Suggestions ??

> 
> > +    /* Limit the number of sockets */
> > +    if (SPIKE_SOCKETS_MAX < s->num_socs)
> > +        s->num_socs = SPIKE_SOCKETS_MAX;
> > +
> > +    /* Initialize socket */
> > +    for (i = 0; i < s->num_socs; i++) {
> > +        base_hartid = i * (smp_cpus / s->num_socs);
> > +        if (i == (s->num_socs - 1))
> > +            cpus_per_socket = smp_cpus - base_hartid;
> > +        else
> > +            cpus_per_socket = smp_cpus / s->num_socs;
> > +        soc_name = g_strdup_printf("soc%d", i);
> > +        object_initialize_child(OBJECT(machine), soc_name, &s->soc[i],
> > +            sizeof(s->soc[i]), TYPE_RISCV_HART_ARRAY, &error_abort, NULL);
> > +        g_free(soc_name);
> > +        object_property_set_str(OBJECT(&s->soc[i]),
> > +            machine->cpu_type, "cpu-type", &error_abort);
> > +        object_property_set_int(OBJECT(&s->soc[i]),
> > +            base_hartid, "hartid-base", &error_abort);
> > +        object_property_set_int(OBJECT(&s->soc[i]),
> > +            cpus_per_socket, "num-harts", &error_abort);
> > +        object_property_set_bool(OBJECT(&s->soc[i]),
> > +            true, "realized", &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, cpus_per_socket,
> > +            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", @@
> > -249,12 +296,7 @@ static void spike_board_init(MachineState *machine)
> >                            &address_space_memory);
> >
> >      /* initialize HTIF using symbols found in load_kernel */
> > -    htif_mm_init(system_memory, mask_rom, &s->soc.harts[0].env,
> serial_hd(0));
> > -
> > -    /* Core Local Interruptor (timer and IPI) */
> > -    sifive_clint_create(memmap[SPIKE_CLINT].base,
> memmap[SPIKE_CLINT].size,
> > -        0, smp_cpus, SIFIVE_SIP_BASE, SIFIVE_TIMECMP_BASE,
> SIFIVE_TIME_BASE,
> > -        false);
> > +    htif_mm_init(system_memory, mask_rom, &s->soc[0].harts[0].env,
> > + serial_hd(0));
> >  }
> >
> >  static void spike_v1_10_0_board_init(MachineState *machine) @@ -268,6
> > +310,8 @@ static void spike_v1_10_0_board_init(MachineState *machine)
> >      int i;
> >      unsigned int smp_cpus = machine->smp.cpus;
> >
> > +    s->num_socs = 1;
> > +
> >      if (!qtest_enabled()) {
> >          info_report("The Spike v1.10.0 machine has been deprecated. "
> >                      "Please use the generic spike machine and specify the ISA "
> > @@ -275,13 +319,13 @@ static void
> spike_v1_10_0_board_init(MachineState *machine)
> >      }
> >
> >      /* Initialize SOC */
> > -    object_initialize_child(OBJECT(machine), "soc", &s->soc, sizeof(s->soc),
> > +    object_initialize_child(OBJECT(machine), "soc", &s->soc[0],
> > + sizeof(s->soc[0]),
> >                              TYPE_RISCV_HART_ARRAY, &error_abort, NULL);
> > -    object_property_set_str(OBJECT(&s->soc), SPIKE_V1_10_0_CPU, "cpu-
> type",
> > +    object_property_set_str(OBJECT(&s->soc[0]), SPIKE_V1_10_0_CPU,
> > + "cpu-type",
> >                              &error_abort);
> > -    object_property_set_int(OBJECT(&s->soc), smp_cpus, "num-harts",
> > +    object_property_set_int(OBJECT(&s->soc[0]), smp_cpus,
> > + "num-harts",
> >                              &error_abort);
> > -    object_property_set_bool(OBJECT(&s->soc), true, "realized",
> > +    object_property_set_bool(OBJECT(&s->soc[0]), true, "realized",
> >                              &error_abort);
> >
> >      /* register system main memory (actual RAM) */ @@ -339,7 +383,7
> > @@ static void spike_v1_10_0_board_init(MachineState *machine)
> >                            &address_space_memory);
> >
> >      /* 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, @@ -358,6 +402,8 @@ static void
> spike_v1_09_1_board_init(MachineState *machine)
> >      int i;
> >      unsigned int smp_cpus = machine->smp.cpus;
> >
> > +    s->num_socs = 1;
> > +
> >      if (!qtest_enabled()) {
> >          info_report("The Spike v1.09.1 machine has been deprecated. "
> >                      "Please use the generic spike machine and specify the ISA "
> > @@ -365,13 +411,13 @@ static void
> spike_v1_09_1_board_init(MachineState *machine)
> >      }
> >
> >      /* Initialize SOC */
> > -    object_initialize_child(OBJECT(machine), "soc", &s->soc, sizeof(s->soc),
> > +    object_initialize_child(OBJECT(machine), "soc", &s->soc[0],
> > + sizeof(s->soc[0]),
> >                              TYPE_RISCV_HART_ARRAY, &error_abort, NULL);
> > -    object_property_set_str(OBJECT(&s->soc), SPIKE_V1_09_1_CPU, "cpu-
> type",
> > +    object_property_set_str(OBJECT(&s->soc[0]), SPIKE_V1_09_1_CPU,
> > + "cpu-type",
> >                              &error_abort);
> > -    object_property_set_int(OBJECT(&s->soc), smp_cpus, "num-harts",
> > +    object_property_set_int(OBJECT(&s->soc[0]), smp_cpus,
> > + "num-harts",
> >                              &error_abort);
> > -    object_property_set_bool(OBJECT(&s->soc), true, "realized",
> > +    object_property_set_bool(OBJECT(&s->soc[0]), true, "realized",
> >                              &error_abort);
> >
> >      /* register system main memory (actual RAM) */ @@ -425,7 +471,7
> > @@ static void spike_v1_09_1_board_init(MachineState *machine)
> >          "};\n";
> >
> >      /* build config string with supplied memory size */
> > -    char *isa = riscv_isa_string(&s->soc.harts[0]);
> > +    char *isa = riscv_isa_string(&s->soc[0].harts[0]);
> >      char *config_string = g_strdup_printf(config_string_tmpl,
> >          (uint64_t)memmap[SPIKE_CLINT].base + SIFIVE_TIME_BASE,
> >          (uint64_t)memmap[SPIKE_DRAM].base,
> > @@ -448,7 +494,7 @@ static void spike_v1_09_1_board_init(MachineState
> *machine)
> >                            &address_space_memory);
> >
> >      /* 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, @@ -476,7 +522,7 @@ static void
> > spike_machine_init(MachineClass *mc)  {
> >      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;  } diff --git
> > a/include/hw/riscv/spike.h b/include/hw/riscv/spike.h index
> > dc770421bc..04a9f593b5 100644
> > --- a/include/hw/riscv/spike.h
> > +++ b/include/hw/riscv/spike.h
> > @@ -22,12 +22,18 @@
> >  #include "hw/riscv/riscv_hart.h"
> >  #include "hw/sysbus.h"
> >
> > +#define SPIKE_SOCKETS_MAX 4
> > +#define SPIKE_CPUS_PER_SOCKET_MIN 2
> > +#define SPIKE_CPUS_PER_SOCKET_MAX 4
> > +#define SPIKE_CPUS_MAX (SPIKE_SOCKETS_MAX *
> > +SPIKE_CPUS_PER_SOCKET_MAX)
> > +
> >  typedef struct {
> >      /*< private >*/
> >      SysBusDevice parent_obj;
> >
> >      /*< public >*/
> > -    RISCVHartArrayState soc;
> > +    unsigned int num_socs;
> > +    RISCVHartArrayState soc[SPIKE_SOCKETS_MAX];
> >      void *fdt;
> >      int fdt_size;
> >  } SpikeState;

Regards,
Anup

Re: [PATCH 2/4] hw/riscv: spike: Allow creating multiple sockets

[Alistair Francis]

On Fri, May 22, 2020 at 3:10 AM Anup Patel <Anup.Patel@wdc.com> wrote:
>
>
>
> > -----Original Message-----
> > From: Palmer Dabbelt <palmer@dabbelt.com>
> > Sent: 22 May 2020 01:46
> > To: Anup Patel <Anup.Patel@wdc.com>
> > Cc: Peter Maydell <peter.maydell@linaro.org>; Alistair Francis
> > <Alistair.Francis@wdc.com>; sagark@eecs.berkeley.edu; Atish Patra
> > <Atish.Patra@wdc.com>; anup@brainfault.org; qemu-riscv@nongnu.org;
> > qemu-devel@nongnu.org; Anup Patel <Anup.Patel@wdc.com>
> > Subject: Re: [PATCH 2/4] hw/riscv: spike: Allow creating multiple sockets
> >
> > On Fri, 15 May 2020 23:37:44 PDT (-0700), Anup Patel wrote:
> > > We extend RISC-V spike machine to allow creating a multi-socket machine.
> > > Each RISC-V spike machine socket is a set of HARTs and a CLINT instance.
> > > Other peripherals are shared between all RISC-V spike machine sockets.
> > > We also update RISC-V spike machine device tree to treat each socket
> > > as a NUMA node.
> > >
> > > The number of sockets in RISC-V spike machine can be specified using
> > > the "sockets=" sub-option of QEMU "-smp" command-line option. By
> > > default, only one socket RISC-V spike machine will be created.
> > >
> > > Currently, we only allow creating upto maximum 4 sockets with minimum
> > > 2 HARTs per socket. In future, this limits can be changed.
> > >
> > > Signed-off-by: Anup Patel <anup.patel@wdc.com>
> > > ---
> > >  hw/riscv/spike.c         | 206 ++++++++++++++++++++++++---------------
> > >  include/hw/riscv/spike.h |   8 +-
> > >  2 files changed, 133 insertions(+), 81 deletions(-)
> > >
> > > diff --git a/hw/riscv/spike.c b/hw/riscv/spike.c index
> > > d5e0103d89..f63c57a87c 100644
> > > --- a/hw/riscv/spike.c
> > > +++ b/hw/riscv/spike.c
> > > @@ -64,9 +64,11 @@ 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;
> > > +    int cpu, socket;
> > > +    uint32_t *clint_cells;
> > > +    unsigned long clint_addr;
> > > +    uint32_t cpu_phandle, intc_phandle, phandle = 1;
> > > +    char *name, *clint_name, *clust_name, *core_name, *cpu_name,
> > > + *intc_name;
> > >
> > >      fdt = s->fdt = create_device_tree(&s->fdt_size);
> > >      if (!fdt) {
> > > @@ -88,68 +90,85 @@ 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",
> > > +    name = g_strdup_printf("/memory@%lx",
> > (long)memmap[SPIKE_DRAM].base);
> > > +    qemu_fdt_add_subnode(fdt, name);
> > > +    qemu_fdt_setprop_cells(fdt, name, "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_setprop_string(fdt, name, "device_type", "memory");
> > > +    g_free(name);
> > >
> > >      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 (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 (socket = (s->num_socs - 1); socket >= 0; socket--) {
> > > +        clust_name = g_strdup_printf("/cpus/cpu-map/cluster0%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[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");
> > > +            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);
> > > +
> > > +            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);
> > > +        }
> > >
> > > -    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);
> > > +        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);
> > > +
> > > +        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);
> > >
> > >      if (cmdline) {
> > >          qemu_fdt_add_subnode(fdt, "/chosen"); @@ -160,23 +179,51 @@
> > > 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);
> > >      MemoryRegion *system_memory = get_system_memory();
> > >      MemoryRegion *main_mem = g_new(MemoryRegion, 1);
> > >      MemoryRegion *mask_rom = g_new(MemoryRegion, 1);
> > >      int i;
> > > +    char *soc_name;
> > >      unsigned int smp_cpus = machine->smp.cpus;
> > > -
> > > -    /* Initialize SOC */
> > > -    object_initialize_child(OBJECT(machine), "soc", &s->soc, sizeof(s->soc),
> > > -                            TYPE_RISCV_HART_ARRAY, &error_abort, NULL);
> > > -    object_property_set_str(OBJECT(&s->soc), machine->cpu_type, "cpu-
> > type",
> > > -                            &error_abort);
> > > -    object_property_set_int(OBJECT(&s->soc), smp_cpus, "num-harts",
> > > -                            &error_abort);
> > > -    object_property_set_bool(OBJECT(&s->soc), true, "realized",
> > > -                            &error_abort);
> > > +    unsigned int base_hartid, cpus_per_socket;
> > > +
> > > +    s->num_socs = machine->smp.sockets;
> > > +
> > > +    /* Ensure minumum required CPUs per socket */
> > > +    if ((smp_cpus / s->num_socs) < SPIKE_CPUS_PER_SOCKET_MIN)
> > > +        s->num_socs = 1;
> >
> > Why?  It seems like creating single-hart sockets would be a good test case, and
> > I'm pretty sure it's a configuration that we had in embedded systems.
>
> Yes, single-hart sockets are sensible for testing software.
>
> When "sockets=" sub-option is not provided in "-smp " command line
> options, the machine->smp.sockets is set same as machine->smp.cpus
> by smp_parse() function in hw/core/machine.c. This means by default
> we will always get single-hart per socket. In other words, "-smp 4" will
> be 4 cpus and 4 sockets. This is counter intuitive for users because when
> "sockets=" is not provided we should default to single socket irrespective
> to number of cpus.
>
> I had added SPIKE_CPUS_PER_SOCKET_MIN to handle the default case
> when no "sockets=" sub-option is provided.
>
> Alternate approach will be:
> 1. Add more members in struct CpuTopology of include/hw/boards.h
>     to help us know whether "sockets=" option was passed or not
> 2. Update smp_parse() for new members in struct CpuTopology
> 3. Assume single-socket machine in QEMU RISC-V virt and QEMU
>     RISC-V spike machines when "sockets=" option was not passed
>
> Suggestions ??
>

I think it makes sense to just stick to what smp_parse() does. That's
what QEMU users are used to so we should follow that.

I agree it is strange that is specifying `-smp x' you will get
max_cpus number of sockets and split the CPUs via them, but that's
what every other board (besides x86) does.

Alistair

RE: [PATCH 2/4] hw/riscv: spike: Allow creating multiple sockets

[Anup Patel]

> -----Original Message-----
> From: Alistair Francis <alistair23@gmail.com>
> Sent: 27 May 2020 06:08
> To: Anup Patel <Anup.Patel@wdc.com>
> Cc: Palmer Dabbelt <palmer@dabbelt.com>; Peter Maydell
> <peter.maydell@linaro.org>; qemu-riscv@nongnu.org;
> sagark@eecs.berkeley.edu; anup@brainfault.org; qemu-devel@nongnu.org;
> Atish Patra <Atish.Patra@wdc.com>; Alistair Francis
> <Alistair.Francis@wdc.com>
> Subject: Re: [PATCH 2/4] hw/riscv: spike: Allow creating multiple sockets
> 
> On Fri, May 22, 2020 at 3:10 AM Anup Patel <Anup.Patel@wdc.com> wrote:
> >
> >
> >
> > > -----Original Message-----
> > > From: Palmer Dabbelt <palmer@dabbelt.com>
> > > Sent: 22 May 2020 01:46
> > > To: Anup Patel <Anup.Patel@wdc.com>
> > > Cc: Peter Maydell <peter.maydell@linaro.org>; Alistair Francis
> > > <Alistair.Francis@wdc.com>; sagark@eecs.berkeley.edu; Atish Patra
> > > <Atish.Patra@wdc.com>; anup@brainfault.org; qemu-riscv@nongnu.org;
> > > qemu-devel@nongnu.org; Anup Patel <Anup.Patel@wdc.com>
> > > Subject: Re: [PATCH 2/4] hw/riscv: spike: Allow creating multiple
> > > sockets
> > >
> > > On Fri, 15 May 2020 23:37:44 PDT (-0700), Anup Patel wrote:
> > > > We extend RISC-V spike machine to allow creating a multi-socket
> machine.
> > > > Each RISC-V spike machine socket is a set of HARTs and a CLINT instance.
> > > > Other peripherals are shared between all RISC-V spike machine sockets.
> > > > We also update RISC-V spike machine device tree to treat each
> > > > socket as a NUMA node.
> > > >
> > > > The number of sockets in RISC-V spike machine can be specified
> > > > using the "sockets=" sub-option of QEMU "-smp" command-line
> > > > option. By default, only one socket RISC-V spike machine will be created.
> > > >
> > > > Currently, we only allow creating upto maximum 4 sockets with
> > > > minimum
> > > > 2 HARTs per socket. In future, this limits can be changed.
> > > >
> > > > Signed-off-by: Anup Patel <anup.patel@wdc.com>
> > > > ---
> > > >  hw/riscv/spike.c         | 206 ++++++++++++++++++++++++---------------
> > > >  include/hw/riscv/spike.h |   8 +-
> > > >  2 files changed, 133 insertions(+), 81 deletions(-)
> > > >
> > > > diff --git a/hw/riscv/spike.c b/hw/riscv/spike.c index
> > > > d5e0103d89..f63c57a87c 100644
> > > > --- a/hw/riscv/spike.c
> > > > +++ b/hw/riscv/spike.c
> > > > @@ -64,9 +64,11 @@ 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;
> > > > +    int cpu, socket;
> > > > +    uint32_t *clint_cells;
> > > > +    unsigned long clint_addr;
> > > > +    uint32_t cpu_phandle, intc_phandle, phandle = 1;
> > > > +    char *name, *clint_name, *clust_name, *core_name, *cpu_name,
> > > > + *intc_name;
> > > >
> > > >      fdt = s->fdt = create_device_tree(&s->fdt_size);
> > > >      if (!fdt) {
> > > > @@ -88,68 +90,85 @@ 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",
> > > > +    name = g_strdup_printf("/memory@%lx",
> > > (long)memmap[SPIKE_DRAM].base);
> > > > +    qemu_fdt_add_subnode(fdt, name);
> > > > +    qemu_fdt_setprop_cells(fdt, name, "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_setprop_string(fdt, name, "device_type", "memory");
> > > > +    g_free(name);
> > > >
> > > >      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 (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 (socket = (s->num_socs - 1); socket >= 0; socket--) {
> > > > +        clust_name = g_strdup_printf("/cpus/cpu-map/cluster0%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[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");
> > > > +            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);
> > > > +
> > > > +            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);
> > > > +        }
> > > >
> > > > -    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);
> > > > +        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);
> > > > +
> > > > +        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);
> > > >
> > > >      if (cmdline) {
> > > >          qemu_fdt_add_subnode(fdt, "/chosen"); @@ -160,23 +179,51
> > > > @@ 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);
> > > >      MemoryRegion *system_memory = get_system_memory();
> > > >      MemoryRegion *main_mem = g_new(MemoryRegion, 1);
> > > >      MemoryRegion *mask_rom = g_new(MemoryRegion, 1);
> > > >      int i;
> > > > +    char *soc_name;
> > > >      unsigned int smp_cpus = machine->smp.cpus;
> > > > -
> > > > -    /* Initialize SOC */
> > > > -    object_initialize_child(OBJECT(machine), "soc", &s->soc, sizeof(s->soc),
> > > > -                            TYPE_RISCV_HART_ARRAY, &error_abort, NULL);
> > > > -    object_property_set_str(OBJECT(&s->soc), machine->cpu_type, "cpu-
> > > type",
> > > > -                            &error_abort);
> > > > -    object_property_set_int(OBJECT(&s->soc), smp_cpus, "num-harts",
> > > > -                            &error_abort);
> > > > -    object_property_set_bool(OBJECT(&s->soc), true, "realized",
> > > > -                            &error_abort);
> > > > +    unsigned int base_hartid, cpus_per_socket;
> > > > +
> > > > +    s->num_socs = machine->smp.sockets;
> > > > +
> > > > +    /* Ensure minumum required CPUs per socket */
> > > > +    if ((smp_cpus / s->num_socs) < SPIKE_CPUS_PER_SOCKET_MIN)
> > > > +        s->num_socs = 1;
> > >
> > > Why?  It seems like creating single-hart sockets would be a good
> > > test case, and I'm pretty sure it's a configuration that we had in embedded
> systems.
> >
> > Yes, single-hart sockets are sensible for testing software.
> >
> > When "sockets=" sub-option is not provided in "-smp " command line
> > options, the machine->smp.sockets is set same as machine->smp.cpus by
> > smp_parse() function in hw/core/machine.c. This means by default we
> > will always get single-hart per socket. In other words, "-smp 4" will
> > be 4 cpus and 4 sockets. This is counter intuitive for users because
> > when "sockets=" is not provided we should default to single socket
> > irrespective to number of cpus.
> >
> > I had added SPIKE_CPUS_PER_SOCKET_MIN to handle the default case when
> > no "sockets=" sub-option is provided.
> >
> > Alternate approach will be:
> > 1. Add more members in struct CpuTopology of include/hw/boards.h
> >     to help us know whether "sockets=" option was passed or not 2.
> > Update smp_parse() for new members in struct CpuTopology 3. Assume
> > single-socket machine in QEMU RISC-V virt and QEMU
> >     RISC-V spike machines when "sockets=" option was not passed
> >
> > Suggestions ??
> >
> 
> I think it makes sense to just stick to what smp_parse() does. That's what QEMU
> users are used to so we should follow that.
> 
> I agree it is strange that is specifying `-smp x' you will get max_cpus number of
> sockets and split the CPUs via them, but that's what every other board (besides
> x86) does.

So we are fine with SPIKE_CPUS_PER_SOCKET_MIN=2 for now, right ??

Regards,
Anup

Re: [PATCH 2/4] hw/riscv: spike: Allow creating multiple sockets

[Alistair Francis]

 at all?

AlistairOn Tue, May 26, 2020 at 7:55 PM Anup Patel <Anup.Patel@wdc.com> wrote:
>
>
>
> > -----Original Message-----
> > From: Alistair Francis <alistair23@gmail.com>
> > Sent: 27 May 2020 06:08
> > To: Anup Patel <Anup.Patel@wdc.com>
> > Cc: Palmer Dabbelt <palmer@dabbelt.com>; Peter Maydell
> > <peter.maydell@linaro.org>; qemu-riscv@nongnu.org;
> > sagark@eecs.berkeley.edu; anup@brainfault.org; qemu-devel@nongnu.org;
> > Atish Patra <Atish.Patra@wdc.com>; Alistair Francis
> > <Alistair.Francis@wdc.com>
> > Subject: Re: [PATCH 2/4] hw/riscv: spike: Allow creating multiple sockets
> >
> > On Fri, May 22, 2020 at 3:10 AM Anup Patel <Anup.Patel@wdc.com> wrote:
> > >
> > >
> > >
> > > > -----Original Message-----
> > > > From: Palmer Dabbelt <palmer@dabbelt.com>
> > > > Sent: 22 May 2020 01:46
> > > > To: Anup Patel <Anup.Patel@wdc.com>
> > > > Cc: Peter Maydell <peter.maydell@linaro.org>; Alistair Francis
> > > > <Alistair.Francis@wdc.com>; sagark@eecs.berkeley.edu; Atish Patra
> > > > <Atish.Patra@wdc.com>; anup@brainfault.org; qemu-riscv@nongnu.org;
> > > > qemu-devel@nongnu.org; Anup Patel <Anup.Patel@wdc.com>
> > > > Subject: Re: [PATCH 2/4] hw/riscv: spike: Allow creating multiple
> > > > sockets
> > > >
> > > > On Fri, 15 May 2020 23:37:44 PDT (-0700), Anup Patel wrote:
> > > > > We extend RISC-V spike machine to allow creating a multi-socket
> > machine.
> > > > > Each RISC-V spike machine socket is a set of HARTs and a CLINT instance.
> > > > > Other peripherals are shared between all RISC-V spike machine sockets.
> > > > > We also update RISC-V spike machine device tree to treat each
> > > > > socket as a NUMA node.
> > > > >
> > > > > The number of sockets in RISC-V spike machine can be specified
> > > > > using the "sockets=" sub-option of QEMU "-smp" command-line
> > > > > option. By default, only one socket RISC-V spike machine will be created.
> > > > >
> > > > > Currently, we only allow creating upto maximum 4 sockets with
> > > > > minimum
> > > > > 2 HARTs per socket. In future, this limits can be changed.
> > > > >
> > > > > Signed-off-by: Anup Patel <anup.patel@wdc.com>
> > > > > ---
> > > > >  hw/riscv/spike.c         | 206 ++++++++++++++++++++++++---------------
> > > > >  include/hw/riscv/spike.h |   8 +-
> > > > >  2 files changed, 133 insertions(+), 81 deletions(-)
> > > > >
> > > > > diff --git a/hw/riscv/spike.c b/hw/riscv/spike.c index
> > > > > d5e0103d89..f63c57a87c 100644
> > > > > --- a/hw/riscv/spike.c
> > > > > +++ b/hw/riscv/spike.c
> > > > > @@ -64,9 +64,11 @@ 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;
> > > > > +    int cpu, socket;
> > > > > +    uint32_t *clint_cells;
> > > > > +    unsigned long clint_addr;
> > > > > +    uint32_t cpu_phandle, intc_phandle, phandle = 1;
> > > > > +    char *name, *clint_name, *clust_name, *core_name, *cpu_name,
> > > > > + *intc_name;
> > > > >
> > > > >      fdt = s->fdt = create_device_tree(&s->fdt_size);
> > > > >      if (!fdt) {
> > > > > @@ -88,68 +90,85 @@ 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",
> > > > > +    name = g_strdup_printf("/memory@%lx",
> > > > (long)memmap[SPIKE_DRAM].base);
> > > > > +    qemu_fdt_add_subnode(fdt, name);
> > > > > +    qemu_fdt_setprop_cells(fdt, name, "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_setprop_string(fdt, name, "device_type", "memory");
> > > > > +    g_free(name);
> > > > >
> > > > >      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 (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 (socket = (s->num_socs - 1); socket >= 0; socket--) {
> > > > > +        clust_name = g_strdup_printf("/cpus/cpu-map/cluster0%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[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");
> > > > > +            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);
> > > > > +
> > > > > +            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);
> > > > > +        }
> > > > >
> > > > > -    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);
> > > > > +        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);
> > > > > +
> > > > > +        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);
> > > > >
> > > > >      if (cmdline) {
> > > > >          qemu_fdt_add_subnode(fdt, "/chosen"); @@ -160,23 +179,51
> > > > > @@ 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);
> > > > >      MemoryRegion *system_memory = get_system_memory();
> > > > >      MemoryRegion *main_mem = g_new(MemoryRegion, 1);
> > > > >      MemoryRegion *mask_rom = g_new(MemoryRegion, 1);
> > > > >      int i;
> > > > > +    char *soc_name;
> > > > >      unsigned int smp_cpus = machine->smp.cpus;
> > > > > -
> > > > > -    /* Initialize SOC */
> > > > > -    object_initialize_child(OBJECT(machine), "soc", &s->soc, sizeof(s->soc),
> > > > > -                            TYPE_RISCV_HART_ARRAY, &error_abort, NULL);
> > > > > -    object_property_set_str(OBJECT(&s->soc), machine->cpu_type, "cpu-
> > > > type",
> > > > > -                            &error_abort);
> > > > > -    object_property_set_int(OBJECT(&s->soc), smp_cpus, "num-harts",
> > > > > -                            &error_abort);
> > > > > -    object_property_set_bool(OBJECT(&s->soc), true, "realized",
> > > > > -                            &error_abort);
> > > > > +    unsigned int base_hartid, cpus_per_socket;
> > > > > +
> > > > > +    s->num_socs = machine->smp.sockets;
> > > > > +
> > > > > +    /* Ensure minumum required CPUs per socket */
> > > > > +    if ((smp_cpus / s->num_socs) < SPIKE_CPUS_PER_SOCKET_MIN)
> > > > > +        s->num_socs = 1;
> > > >
> > > > Why?  It seems like creating single-hart sockets would be a good
> > > > test case, and I'm pretty sure it's a configuration that we had in embedded
> > systems.
> > >
> > > Yes, single-hart sockets are sensible for testing software.
> > >
> > > When "sockets=" sub-option is not provided in "-smp " command line
> > > options, the machine->smp.sockets is set same as machine->smp.cpus by
> > > smp_parse() function in hw/core/machine.c. This means by default we
> > > will always get single-hart per socket. In other words, "-smp 4" will
> > > be 4 cpus and 4 sockets. This is counter intuitive for users because
> > > when "sockets=" is not provided we should default to single socket
> > > irrespective to number of cpus.
> > >
> > > I had added SPIKE_CPUS_PER_SOCKET_MIN to handle the default case when
> > > no "sockets=" sub-option is provided.
> > >
> > > Alternate approach will be:
> > > 1. Add more members in struct CpuTopology of include/hw/boards.h
> > >     to help us know whether "sockets=" option was passed or not 2.
> > > Update smp_parse() for new members in struct CpuTopology 3. Assume
> > > single-socket machine in QEMU RISC-V virt and QEMU
> > >     RISC-V spike machines when "sockets=" option was not passed
> > >
> > > Suggestions ??
> > >
> >
> > I think it makes sense to just stick to what smp_parse() does. That's what QEMU
> > users are used to so we should follow that.
> >
> > I agree it is strange that is specifying `-smp x' you will get max_cpus number of
> > sockets and split the CPUs via them, but that's what every other board (besides
> > x86) does.
>
> So we are fine with SPIKE_CPUS_PER_SOCKET_MIN=2 for now, right ??

Why do we need SPIKE_CPUS_PER_SOCKET_MIN at all?

Alistair

>
> Regards,
> Anup

RE: [PATCH 2/4] hw/riscv: spike: Allow creating multiple sockets

[Anup Patel]

> -----Original Message-----
> From: Alistair Francis <alistair23@gmail.com>
> Sent: 27 May 2020 09:00
> To: Anup Patel <Anup.Patel@wdc.com>
> Cc: Palmer Dabbelt <palmer@dabbelt.com>; Peter Maydell
> <peter.maydell@linaro.org>; qemu-riscv@nongnu.org;
> sagark@eecs.berkeley.edu; anup@brainfault.org; qemu-devel@nongnu.org;
> Atish Patra <Atish.Patra@wdc.com>; Alistair Francis
> <Alistair.Francis@wdc.com>
> Subject: Re: [PATCH 2/4] hw/riscv: spike: Allow creating multiple sockets
> 
>  at all?
> 
> AlistairOn Tue, May 26, 2020 at 7:55 PM Anup Patel <Anup.Patel@wdc.com>
> wrote:
> >
> >
> >
> > > -----Original Message-----
> > > From: Alistair Francis <alistair23@gmail.com>
> > > Sent: 27 May 2020 06:08
> > > To: Anup Patel <Anup.Patel@wdc.com>
> > > Cc: Palmer Dabbelt <palmer@dabbelt.com>; Peter Maydell
> > > <peter.maydell@linaro.org>; qemu-riscv@nongnu.org;
> > > sagark@eecs.berkeley.edu; anup@brainfault.org;
> > > qemu-devel@nongnu.org; Atish Patra <Atish.Patra@wdc.com>; Alistair
> > > Francis <Alistair.Francis@wdc.com>
> > > Subject: Re: [PATCH 2/4] hw/riscv: spike: Allow creating multiple
> > > sockets
> > >
> > > On Fri, May 22, 2020 at 3:10 AM Anup Patel <Anup.Patel@wdc.com> wrote:
> > > >
> > > >
> > > >
> > > > > -----Original Message-----
> > > > > From: Palmer Dabbelt <palmer@dabbelt.com>
> > > > > Sent: 22 May 2020 01:46
> > > > > To: Anup Patel <Anup.Patel@wdc.com>
> > > > > Cc: Peter Maydell <peter.maydell@linaro.org>; Alistair Francis
> > > > > <Alistair.Francis@wdc.com>; sagark@eecs.berkeley.edu; Atish
> > > > > Patra <Atish.Patra@wdc.com>; anup@brainfault.org;
> > > > > qemu-riscv@nongnu.org; qemu-devel@nongnu.org; Anup Patel
> > > > > <Anup.Patel@wdc.com>
> > > > > Subject: Re: [PATCH 2/4] hw/riscv: spike: Allow creating
> > > > > multiple sockets
> > > > >
> > > > > On Fri, 15 May 2020 23:37:44 PDT (-0700), Anup Patel wrote:
> > > > > > We extend RISC-V spike machine to allow creating a
> > > > > > multi-socket
> > > machine.
> > > > > > Each RISC-V spike machine socket is a set of HARTs and a CLINT
> instance.
> > > > > > Other peripherals are shared between all RISC-V spike machine
> sockets.
> > > > > > We also update RISC-V spike machine device tree to treat each
> > > > > > socket as a NUMA node.
> > > > > >
> > > > > > The number of sockets in RISC-V spike machine can be specified
> > > > > > using the "sockets=" sub-option of QEMU "-smp" command-line
> > > > > > option. By default, only one socket RISC-V spike machine will be
> created.
> > > > > >
> > > > > > Currently, we only allow creating upto maximum 4 sockets with
> > > > > > minimum
> > > > > > 2 HARTs per socket. In future, this limits can be changed.
> > > > > >
> > > > > > Signed-off-by: Anup Patel <anup.patel@wdc.com>
> > > > > > ---
> > > > > >  hw/riscv/spike.c         | 206 ++++++++++++++++++++++++---------------
> > > > > >  include/hw/riscv/spike.h |   8 +-
> > > > > >  2 files changed, 133 insertions(+), 81 deletions(-)
> > > > > >
> > > > > > diff --git a/hw/riscv/spike.c b/hw/riscv/spike.c index
> > > > > > d5e0103d89..f63c57a87c 100644
> > > > > > --- a/hw/riscv/spike.c
> > > > > > +++ b/hw/riscv/spike.c
> > > > > > @@ -64,9 +64,11 @@ 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;
> > > > > > +    int cpu, socket;
> > > > > > +    uint32_t *clint_cells;
> > > > > > +    unsigned long clint_addr;
> > > > > > +    uint32_t cpu_phandle, intc_phandle, phandle = 1;
> > > > > > +    char *name, *clint_name, *clust_name, *core_name,
> > > > > > + *cpu_name, *intc_name;
> > > > > >
> > > > > >      fdt = s->fdt = create_device_tree(&s->fdt_size);
> > > > > >      if (!fdt) {
> > > > > > @@ -88,68 +90,85 @@ 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",
> > > > > > +    name = g_strdup_printf("/memory@%lx",
> > > > > (long)memmap[SPIKE_DRAM].base);
> > > > > > +    qemu_fdt_add_subnode(fdt, name);
> > > > > > +    qemu_fdt_setprop_cells(fdt, name, "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_setprop_string(fdt, name, "device_type", "memory");
> > > > > > +    g_free(name);
> > > > > >
> > > > > >      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 (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 (socket = (s->num_socs - 1); socket >= 0; socket--) {
> > > > > > +        clust_name = g_strdup_printf("/cpus/cpu-map/cluster0%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[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");
> > > > > > +            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);
> > > > > > +
> > > > > > +            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);
> > > > > > +        }
> > > > > >
> > > > > > -    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);
> > > > > > +        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);
> > > > > > +
> > > > > > +        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);
> > > > > >
> > > > > >      if (cmdline) {
> > > > > >          qemu_fdt_add_subnode(fdt, "/chosen"); @@ -160,23
> > > > > > +179,51 @@ 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);
> > > > > >      MemoryRegion *system_memory = get_system_memory();
> > > > > >      MemoryRegion *main_mem = g_new(MemoryRegion, 1);
> > > > > >      MemoryRegion *mask_rom = g_new(MemoryRegion, 1);
> > > > > >      int i;
> > > > > > +    char *soc_name;
> > > > > >      unsigned int smp_cpus = machine->smp.cpus;
> > > > > > -
> > > > > > -    /* Initialize SOC */
> > > > > > -    object_initialize_child(OBJECT(machine), "soc", &s->soc, sizeof(s-
> >soc),
> > > > > > -                            TYPE_RISCV_HART_ARRAY, &error_abort, NULL);
> > > > > > -    object_property_set_str(OBJECT(&s->soc), machine->cpu_type,
> "cpu-
> > > > > type",
> > > > > > -                            &error_abort);
> > > > > > -    object_property_set_int(OBJECT(&s->soc), smp_cpus, "num-harts",
> > > > > > -                            &error_abort);
> > > > > > -    object_property_set_bool(OBJECT(&s->soc), true, "realized",
> > > > > > -                            &error_abort);
> > > > > > +    unsigned int base_hartid, cpus_per_socket;
> > > > > > +
> > > > > > +    s->num_socs = machine->smp.sockets;
> > > > > > +
> > > > > > +    /* Ensure minumum required CPUs per socket */
> > > > > > +    if ((smp_cpus / s->num_socs) < SPIKE_CPUS_PER_SOCKET_MIN)
> > > > > > +        s->num_socs = 1;
> > > > >
> > > > > Why?  It seems like creating single-hart sockets would be a good
> > > > > test case, and I'm pretty sure it's a configuration that we had
> > > > > in embedded
> > > systems.
> > > >
> > > > Yes, single-hart sockets are sensible for testing software.
> > > >
> > > > When "sockets=" sub-option is not provided in "-smp " command line
> > > > options, the machine->smp.sockets is set same as machine->smp.cpus
> > > > by
> > > > smp_parse() function in hw/core/machine.c. This means by default
> > > > we will always get single-hart per socket. In other words, "-smp
> > > > 4" will be 4 cpus and 4 sockets. This is counter intuitive for
> > > > users because when "sockets=" is not provided we should default to
> > > > single socket irrespective to number of cpus.
> > > >
> > > > I had added SPIKE_CPUS_PER_SOCKET_MIN to handle the default case
> > > > when no "sockets=" sub-option is provided.
> > > >
> > > > Alternate approach will be:
> > > > 1. Add more members in struct CpuTopology of include/hw/boards.h
> > > >     to help us know whether "sockets=" option was passed or not 2.
> > > > Update smp_parse() for new members in struct CpuTopology 3. Assume
> > > > single-socket machine in QEMU RISC-V virt and QEMU
> > > >     RISC-V spike machines when "sockets=" option was not passed
> > > >
> > > > Suggestions ??
> > > >
> > >
> > > I think it makes sense to just stick to what smp_parse() does.
> > > That's what QEMU users are used to so we should follow that.
> > >
> > > I agree it is strange that is specifying `-smp x' you will get
> > > max_cpus number of sockets and split the CPUs via them, but that's
> > > what every other board (besides
> > > x86) does.
> >
> > So we are fine with SPIKE_CPUS_PER_SOCKET_MIN=2 for now, right ??
> 
> Why do we need SPIKE_CPUS_PER_SOCKET_MIN at all?

We are creating a separate CLINT and PLIC for each socket but the
VirtIO and other devices can only connect to one PLIC instance.

Now if we have one CPU/HART per socket (by default) then only
one CPU can take all VirtIO interrupts. We can't even change the
irq affinity.

The SPIKE_CPUS_PER_SOCKET_MIN=2 helps us ensure that
smp_parse() gives us one CPU/HART per socket (by default),
we ignore the "sockets" and force it to just one socket. That's
why SPIKE_CPUS_PER_SOCKET_MIN is a work-around for
the non-intuitive behavior of smp_parse().

My previous suggestion was to add "sockets_available" field in
"Struct CpuTopology". The other fields of "Struct CpuTopology"
will remain as-in (no change in semantics) so it will work fine
for other architectures. The "sockets_available" field will tell
use whether "sockets" sub-option was specified in command
line (or not). Using "sockets_available" field we can remove the
SPIKE_CPUS_PER_SOCKET_MIN=2 work-around. In fact, we can
totally remove SPIKE_CPUS_PER_SOCKET_MIN.

Regards,
Anup

[PATCH 3/4] hw/riscv: Allow creating multiple instances of PLIC

[Anup Patel]

We extend PLIC emulation to allow multiple instances of PLIC in
a QEMU RISC-V machine. To achieve this, we remove first HART id
zero assumption from PLIC emulation.

Signed-off-by: Anup Patel <anup.patel@wdc.com>
---
 hw/riscv/sifive_e.c            |  2 +-
 hw/riscv/sifive_plic.c         | 24 +++++++++++++-----------
 hw/riscv/sifive_u.c            |  2 +-
 hw/riscv/virt.c                |  2 +-
 include/hw/riscv/sifive_plic.h | 12 +++++++-----
 5 files changed, 23 insertions(+), 19 deletions(-)

diff --git a/hw/riscv/sifive_e.c b/hw/riscv/sifive_e.c
index 1c3b37d0ba..bd122e71ae 100644
--- a/hw/riscv/sifive_e.c
+++ b/hw/riscv/sifive_e.c
@@ -152,7 +152,7 @@ static void riscv_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,
diff --git a/hw/riscv/sifive_plic.c b/hw/riscv/sifive_plic.c
index c1e04cbb98..f88bb48053 100644
--- a/hw/riscv/sifive_plic.c
+++ b/hw/riscv/sifive_plic.c
@@ -352,6 +352,7 @@ 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),
@@ -400,10 +401,12 @@ 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 == ',') {
@@ -429,8 +432,6 @@ 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;
 
@@ -451,8 +452,8 @@ 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);
@@ -488,16 +489,17 @@ 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_create(NULL, 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 22997fbf13..69dbd7980b 100644
--- a/hw/riscv/sifive_u.c
+++ b/hw/riscv/sifive_u.c
@@ -585,7 +585,7 @@ static void riscv_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,
diff --git a/hw/riscv/virt.c b/hw/riscv/virt.c
index dcb8a83b35..f40efcb193 100644
--- a/hw/riscv/virt.c
+++ b/hw/riscv/virt.c
@@ -585,7 +585,7 @@ static void riscv_virt_board_init(MachineState *machine)
 
     /* MMIO */
     s->plic = sifive_plic_create(memmap[VIRT_PLIC].base,
-        plic_hart_config,
+        plic_hart_config, 0,
         VIRT_PLIC_NUM_SOURCES,
         VIRT_PLIC_NUM_PRIORITIES,
         VIRT_PLIC_PRIORITY_BASE,
diff --git a/include/hw/riscv/sifive_plic.h b/include/hw/riscv/sifive_plic.h
index 4421e81249..ace76d0f1b 100644
--- a/include/hw/riscv/sifive_plic.h
+++ b/include/hw/riscv/sifive_plic.h
@@ -48,6 +48,7 @@ typedef struct SiFivePLICState {
     /*< public >*/
     MemoryRegion mmio;
     uint32_t num_addrs;
+    uint32_t num_harts;
     uint32_t bitfield_words;
     PLICAddr *addr_config;
     uint32_t *source_priority;
@@ -58,6 +59,7 @@ typedef struct SiFivePLICState {
 
     /* config */
     char *hart_config;
+    uint32_t hartid_base;
     uint32_t num_sources;
     uint32_t num_priorities;
     uint32_t priority_base;
@@ -70,10 +72,10 @@ typedef struct SiFivePLICState {
 } SiFivePLICState;
 
 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);
 
 #endif
-- 
2.25.1

Re: [PATCH 3/4] hw/riscv: Allow creating multiple instances of PLIC

[Palmer Dabbelt]

On Fri, 15 May 2020 23:37:45 PDT (-0700), Anup Patel wrote:
> We extend PLIC emulation to allow multiple instances of PLIC in
> a QEMU RISC-V machine. To achieve this, we remove first HART id
> zero assumption from PLIC emulation.
>
> Signed-off-by: Anup Patel <anup.patel@wdc.com>
> ---
>  hw/riscv/sifive_e.c            |  2 +-
>  hw/riscv/sifive_plic.c         | 24 +++++++++++++-----------
>  hw/riscv/sifive_u.c            |  2 +-
>  hw/riscv/virt.c                |  2 +-
>  include/hw/riscv/sifive_plic.h | 12 +++++++-----
>  5 files changed, 23 insertions(+), 19 deletions(-)
>
> diff --git a/hw/riscv/sifive_e.c b/hw/riscv/sifive_e.c
> index 1c3b37d0ba..bd122e71ae 100644
> --- a/hw/riscv/sifive_e.c
> +++ b/hw/riscv/sifive_e.c
> @@ -152,7 +152,7 @@ static void riscv_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,
> diff --git a/hw/riscv/sifive_plic.c b/hw/riscv/sifive_plic.c
> index c1e04cbb98..f88bb48053 100644
> --- a/hw/riscv/sifive_plic.c
> +++ b/hw/riscv/sifive_plic.c
> @@ -352,6 +352,7 @@ 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),
> @@ -400,10 +401,12 @@ 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 == ',') {
> @@ -429,8 +432,6 @@ 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;
>
> @@ -451,8 +452,8 @@ 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);
> @@ -488,16 +489,17 @@ 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_create(NULL, 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 22997fbf13..69dbd7980b 100644
> --- a/hw/riscv/sifive_u.c
> +++ b/hw/riscv/sifive_u.c
> @@ -585,7 +585,7 @@ static void riscv_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,
> diff --git a/hw/riscv/virt.c b/hw/riscv/virt.c
> index dcb8a83b35..f40efcb193 100644
> --- a/hw/riscv/virt.c
> +++ b/hw/riscv/virt.c
> @@ -585,7 +585,7 @@ static void riscv_virt_board_init(MachineState *machine)
>
>      /* MMIO */
>      s->plic = sifive_plic_create(memmap[VIRT_PLIC].base,
> -        plic_hart_config,
> +        plic_hart_config, 0,
>          VIRT_PLIC_NUM_SOURCES,
>          VIRT_PLIC_NUM_PRIORITIES,
>          VIRT_PLIC_PRIORITY_BASE,
> diff --git a/include/hw/riscv/sifive_plic.h b/include/hw/riscv/sifive_plic.h
> index 4421e81249..ace76d0f1b 100644
> --- a/include/hw/riscv/sifive_plic.h
> +++ b/include/hw/riscv/sifive_plic.h
> @@ -48,6 +48,7 @@ typedef struct SiFivePLICState {
>      /*< public >*/
>      MemoryRegion mmio;
>      uint32_t num_addrs;
> +    uint32_t num_harts;
>      uint32_t bitfield_words;
>      PLICAddr *addr_config;
>      uint32_t *source_priority;
> @@ -58,6 +59,7 @@ typedef struct SiFivePLICState {
>
>      /* config */
>      char *hart_config;
> +    uint32_t hartid_base;
>      uint32_t num_sources;
>      uint32_t num_priorities;
>      uint32_t priority_base;
> @@ -70,10 +72,10 @@ typedef struct SiFivePLICState {
>  } SiFivePLICState;
>
>  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);
>
>  #endif

Reviewed-by: Palmer Dabbelt <palmerdabbelt@google.com>

Re: [PATCH 3/4] hw/riscv: Allow creating multiple instances of PLIC

[Alistair Francis]

On Fri, May 15, 2020 at 11:39 PM Anup Patel <anup.patel@wdc.com> wrote:
>
> We extend PLIC emulation to allow multiple instances of PLIC in
> a QEMU RISC-V machine. To achieve this, we remove first HART id
> zero assumption from PLIC emulation.
>
> Signed-off-by: Anup Patel <anup.patel@wdc.com>

Reviewed-by: Alistair Francis <alistair.francis@wdc.com>

Alistair

> ---
>  hw/riscv/sifive_e.c            |  2 +-
>  hw/riscv/sifive_plic.c         | 24 +++++++++++++-----------
>  hw/riscv/sifive_u.c            |  2 +-
>  hw/riscv/virt.c                |  2 +-
>  include/hw/riscv/sifive_plic.h | 12 +++++++-----
>  5 files changed, 23 insertions(+), 19 deletions(-)
>
> diff --git a/hw/riscv/sifive_e.c b/hw/riscv/sifive_e.c
> index 1c3b37d0ba..bd122e71ae 100644
> --- a/hw/riscv/sifive_e.c
> +++ b/hw/riscv/sifive_e.c
> @@ -152,7 +152,7 @@ static void riscv_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,
> diff --git a/hw/riscv/sifive_plic.c b/hw/riscv/sifive_plic.c
> index c1e04cbb98..f88bb48053 100644
> --- a/hw/riscv/sifive_plic.c
> +++ b/hw/riscv/sifive_plic.c
> @@ -352,6 +352,7 @@ 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),
> @@ -400,10 +401,12 @@ 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 == ',') {
> @@ -429,8 +432,6 @@ 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;
>
> @@ -451,8 +452,8 @@ 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);
> @@ -488,16 +489,17 @@ 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_create(NULL, 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 22997fbf13..69dbd7980b 100644
> --- a/hw/riscv/sifive_u.c
> +++ b/hw/riscv/sifive_u.c
> @@ -585,7 +585,7 @@ static void riscv_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,
> diff --git a/hw/riscv/virt.c b/hw/riscv/virt.c
> index dcb8a83b35..f40efcb193 100644
> --- a/hw/riscv/virt.c
> +++ b/hw/riscv/virt.c
> @@ -585,7 +585,7 @@ static void riscv_virt_board_init(MachineState *machine)
>
>      /* MMIO */
>      s->plic = sifive_plic_create(memmap[VIRT_PLIC].base,
> -        plic_hart_config,
> +        plic_hart_config, 0,
>          VIRT_PLIC_NUM_SOURCES,
>          VIRT_PLIC_NUM_PRIORITIES,
>          VIRT_PLIC_PRIORITY_BASE,
> diff --git a/include/hw/riscv/sifive_plic.h b/include/hw/riscv/sifive_plic.h
> index 4421e81249..ace76d0f1b 100644
> --- a/include/hw/riscv/sifive_plic.h
> +++ b/include/hw/riscv/sifive_plic.h
> @@ -48,6 +48,7 @@ typedef struct SiFivePLICState {
>      /*< public >*/
>      MemoryRegion mmio;
>      uint32_t num_addrs;
> +    uint32_t num_harts;
>      uint32_t bitfield_words;
>      PLICAddr *addr_config;
>      uint32_t *source_priority;
> @@ -58,6 +59,7 @@ typedef struct SiFivePLICState {
>
>      /* config */
>      char *hart_config;
> +    uint32_t hartid_base;
>      uint32_t num_sources;
>      uint32_t num_priorities;
>      uint32_t priority_base;
> @@ -70,10 +72,10 @@ typedef struct SiFivePLICState {
>  } SiFivePLICState;
>
>  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);
>
>  #endif
> --
> 2.25.1
>
>

[PATCH 4/4] hw/riscv: virt: Allow creating multiple sockets

[Anup Patel]

We extend RISC-V virt machine to allow creating a multi-socket machine.
Each RISC-V virt machine socket is a set of HARTs, a CLINT instance,
and a PLIC instance. Other peripherals are shared between all RISC-V
virt machine sockets. We also update RISC-V virt machine device tree
to treat each socket as a NUMA node.

The number of sockets in RISC-V virt machine can be specified using
the "sockets=" sub-option of QEMU "-smp" command-line option. By
default, only one socket RISC-V virt machine will be created.

Currently, we only allow creating upto maximum 4 sockets with minimum
2 HARTs per socket. In future, this limits can be changed.

Signed-off-by: Anup Patel <anup.patel@wdc.com>
---
 hw/riscv/virt.c         | 495 ++++++++++++++++++++++------------------
 include/hw/riscv/virt.h |  12 +-
 2 files changed, 283 insertions(+), 224 deletions(-)

diff --git a/hw/riscv/virt.c b/hw/riscv/virt.c
index f40efcb193..205224c01c 100644
--- a/hw/riscv/virt.c
+++ b/hw/riscv/virt.c
@@ -60,7 +60,7 @@ static const struct MemmapEntry {
     [VIRT_TEST] =        {   0x100000,        0x1000 },
     [VIRT_RTC] =         {   0x101000,        0x1000 },
     [VIRT_CLINT] =       {  0x2000000,       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 },
@@ -183,10 +183,15 @@ 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;
+    uint32_t *clint_cells, *plic_cells;
+    unsigned long clint_addr, plic_addr;
+    uint32_t plic_phandle[VIRT_SOCKETS_MAX];
+    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 *name, *cpu_name, *core_name, *intc_name;
+    char *clint_name, *plic_name, *clust_name;
     hwaddr flashsize = virt_memmap[VIRT_FLASH].size / 2;
     hwaddr flashbase = virt_memmap[VIRT_FLASH].base;
 
@@ -207,231 +212,231 @@ 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",
+    name = g_strdup_printf("/memory@%lx",
         (long)memmap[VIRT_DRAM].base);
-    qemu_fdt_add_subnode(fdt, nodename);
-    qemu_fdt_setprop_cells(fdt, nodename, "reg",
+    qemu_fdt_add_subnode(fdt, name);
+    qemu_fdt_setprop_cells(fdt, name, "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_setprop_string(fdt, name, "device_type", "memory");
+    g_free(name);
 
     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 = (s->num_socs - 1); socket >= 0; socket--) {
+        clust_name = g_strdup_printf("/cpus/cpu-map/cluster0%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");
+            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);
+        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);
+        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);
+        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 < s->num_socs; 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);
 
     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,
@@ -479,21 +484,93 @@ static void riscv_virt_board_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;
-    int i;
+    int i, j;
     unsigned int smp_cpus = machine->smp.cpus;
+    unsigned int base_hartid, cpus_per_socket;
+    DeviceState *mmio_plic, *virtio_plic, *pcie_plic;
+
+    s->num_socs = machine->smp.sockets;
+
+    /* Ensure minumum required CPUs per socket */
+    if ((smp_cpus / s->num_socs) < VIRT_CPUS_PER_SOCKET_MIN)
+        s->num_socs = 1;
+
+    /* Limit the number of sockets */
+    if (VIRT_SOCKETS_MAX < s->num_socs)
+        s->num_socs = VIRT_SOCKETS_MAX;
 
     /* Initialize SOC */
-    object_initialize_child(OBJECT(machine), "soc", &s->soc, sizeof(s->soc),
-                            TYPE_RISCV_HART_ARRAY, &error_abort, NULL);
-    object_property_set_str(OBJECT(&s->soc), machine->cpu_type, "cpu-type",
-                            &error_abort);
-    object_property_set_int(OBJECT(&s->soc), smp_cpus, "num-harts",
-                            &error_abort);
-    object_property_set_bool(OBJECT(&s->soc), true, "realized",
-                            &error_abort);
+    mmio_plic = virtio_plic = pcie_plic = NULL;
+    for (i = 0; i < s->num_socs; i++) {
+        base_hartid = i * (smp_cpus / s->num_socs);
+        if (i == (s->num_socs - 1))
+            cpus_per_socket = smp_cpus - base_hartid;
+        else
+            cpus_per_socket = smp_cpus / s->num_socs;
+        soc_name = g_strdup_printf("soc%d", i);
+        object_initialize_child(OBJECT(machine), soc_name, &s->soc[i],
+            sizeof(s->soc[i]), TYPE_RISCV_HART_ARRAY, &error_abort, NULL);
+        g_free(soc_name);
+        object_property_set_str(OBJECT(&s->soc[i]),
+            machine->cpu_type, "cpu-type", &error_abort);
+        object_property_set_int(OBJECT(&s->soc[i]),
+            base_hartid, "hartid-base", &error_abort);
+        object_property_set_int(OBJECT(&s->soc[i]),
+            cpus_per_socket, "num-harts", &error_abort);
+        object_property_set_bool(OBJECT(&s->soc[i]),
+            true, "realized", &error_abort);
+
+        /* Per-socket CLINT */
+        sifive_clint_create(
+            memmap[VIRT_CLINT].base + i * memmap[VIRT_CLINT].size,
+            memmap[VIRT_CLINT].size, base_hartid, cpus_per_socket,
+            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) * cpus_per_socket;
+        plic_hart_config = g_malloc0(plic_hart_config_len);
+        for (j = 0; j < cpus_per_socket; 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",
@@ -572,38 +649,14 @@ static void riscv_virt_board_init(MachineState *machine)
                           memmap[VIRT_MROM].base + sizeof(reset_vec),
                           &address_space_memory);
 
-    /* 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, 0,
-        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, 0, 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,
@@ -612,14 +665,14 @@ static void riscv_virt_board_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);
 
@@ -629,8 +682,6 @@ static void riscv_virt_board_init(MachineState *machine)
                                   drive_get(IF_PFLASH, 0, i));
     }
     virt_flash_map(s, system_memory);
-
-    g_free(plic_hart_config);
 }
 
 static void riscv_virt_machine_instance_init(Object *obj)
@@ -643,7 +694,7 @@ static void riscv_virt_machine_class_init(ObjectClass *oc, void *data)
 
     mc->desc = "RISC-V VirtIO board";
     mc->init = riscv_virt_board_init;
-    mc->max_cpus = 8;
+    mc->max_cpus = VIRT_CPUS_MAX;
     mc->default_cpu_type = VIRT_CPU;
     mc->pci_allow_0_address = true;
 }
diff --git a/include/hw/riscv/virt.h b/include/hw/riscv/virt.h
index e69355efaf..333d1edbc2 100644
--- a/include/hw/riscv/virt.h
+++ b/include/hw/riscv/virt.h
@@ -23,6 +23,11 @@
 #include "hw/sysbus.h"
 #include "hw/block/flash.h"
 
+#define VIRT_SOCKETS_MAX 4
+#define VIRT_CPUS_PER_SOCKET_MIN 2
+#define VIRT_CPUS_PER_SOCKET_MAX 4
+#define VIRT_CPUS_MAX (VIRT_SOCKETS_MAX * VIRT_CPUS_PER_SOCKET_MAX)
+
 #define TYPE_RISCV_VIRT_MACHINE MACHINE_TYPE_NAME("virt")
 #define RISCV_VIRT_MACHINE(obj) \
     OBJECT_CHECK(RISCVVirtState, (obj), TYPE_RISCV_VIRT_MACHINE)
@@ -32,8 +37,9 @@ typedef struct {
     MachineState parent;
 
     /*< public >*/
-    RISCVHartArrayState soc;
-    DeviceState *plic;
+    unsigned int num_socs;
+    RISCVHartArrayState soc[VIRT_SOCKETS_MAX];
+    DeviceState *plic[VIRT_SOCKETS_MAX];
     PFlashCFI01 *flash[2];
 
     void *fdt;
@@ -74,6 +80,8 @@ enum {
 #define VIRT_PLIC_ENABLE_STRIDE 0x80
 #define VIRT_PLIC_CONTEXT_BASE 0x200000
 #define VIRT_PLIC_CONTEXT_STRIDE 0x1000
+#define VIRT_PLIC_SIZE(__num_context) \
+    (VIRT_PLIC_CONTEXT_BASE + (__num_context) * VIRT_PLIC_CONTEXT_STRIDE)
 
 #define FDT_PCI_ADDR_CELLS    3
 #define FDT_PCI_INT_CELLS     1
-- 
2.25.1

Re: [PATCH 4/4] hw/riscv: virt: Allow creating multiple sockets

[Palmer Dabbelt]

On Fri, 15 May 2020 23:37:46 PDT (-0700), Anup Patel wrote:
> We extend RISC-V virt machine to allow creating a multi-socket machine.
> Each RISC-V virt machine socket is a set of HARTs, a CLINT instance,
> and a PLIC instance. Other peripherals are shared between all RISC-V
> virt machine sockets. We also update RISC-V virt machine device tree
> to treat each socket as a NUMA node.
>
> The number of sockets in RISC-V virt machine can be specified using
> the "sockets=" sub-option of QEMU "-smp" command-line option. By
> default, only one socket RISC-V virt machine will be created.
>
> Currently, we only allow creating upto maximum 4 sockets with minimum
> 2 HARTs per socket. In future, this limits can be changed.
>
> Signed-off-by: Anup Patel <anup.patel@wdc.com>
> ---
>  hw/riscv/virt.c         | 495 ++++++++++++++++++++++------------------
>  include/hw/riscv/virt.h |  12 +-
>  2 files changed, 283 insertions(+), 224 deletions(-)
>
> diff --git a/hw/riscv/virt.c b/hw/riscv/virt.c
> index f40efcb193..205224c01c 100644
> --- a/hw/riscv/virt.c
> +++ b/hw/riscv/virt.c
> @@ -60,7 +60,7 @@ static const struct MemmapEntry {
>      [VIRT_TEST] =        {   0x100000,        0x1000 },
>      [VIRT_RTC] =         {   0x101000,        0x1000 },
>      [VIRT_CLINT] =       {  0x2000000,       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 },
> @@ -183,10 +183,15 @@ 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;
> +    uint32_t *clint_cells, *plic_cells;
> +    unsigned long clint_addr, plic_addr;
> +    uint32_t plic_phandle[VIRT_SOCKETS_MAX];
> +    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 *name, *cpu_name, *core_name, *intc_name;
> +    char *clint_name, *plic_name, *clust_name;
>      hwaddr flashsize = virt_memmap[VIRT_FLASH].size / 2;
>      hwaddr flashbase = virt_memmap[VIRT_FLASH].base;
>
> @@ -207,231 +212,231 @@ 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",
> +    name = g_strdup_printf("/memory@%lx",
>          (long)memmap[VIRT_DRAM].base);
> -    qemu_fdt_add_subnode(fdt, nodename);
> -    qemu_fdt_setprop_cells(fdt, nodename, "reg",
> +    qemu_fdt_add_subnode(fdt, name);
> +    qemu_fdt_setprop_cells(fdt, name, "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_setprop_string(fdt, name, "device_type", "memory");
> +    g_free(name);
>
>      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 = (s->num_socs - 1); socket >= 0; socket--) {
> +        clust_name = g_strdup_printf("/cpus/cpu-map/cluster0%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");
> +            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);
> +        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);
> +        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);
> +        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 < s->num_socs; 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);
>
>      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,
> @@ -479,21 +484,93 @@ static void riscv_virt_board_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;
> -    int i;
> +    int i, j;
>      unsigned int smp_cpus = machine->smp.cpus;
> +    unsigned int base_hartid, cpus_per_socket;
> +    DeviceState *mmio_plic, *virtio_plic, *pcie_plic;
> +
> +    s->num_socs = machine->smp.sockets;
> +
> +    /* Ensure minumum required CPUs per socket */
> +    if ((smp_cpus / s->num_socs) < VIRT_CPUS_PER_SOCKET_MIN)
> +        s->num_socs = 1;
> +
> +    /* Limit the number of sockets */
> +    if (VIRT_SOCKETS_MAX < s->num_socs)
> +        s->num_socs = VIRT_SOCKETS_MAX;
>
>      /* Initialize SOC */
> -    object_initialize_child(OBJECT(machine), "soc", &s->soc, sizeof(s->soc),
> -                            TYPE_RISCV_HART_ARRAY, &error_abort, NULL);
> -    object_property_set_str(OBJECT(&s->soc), machine->cpu_type, "cpu-type",
> -                            &error_abort);
> -    object_property_set_int(OBJECT(&s->soc), smp_cpus, "num-harts",
> -                            &error_abort);
> -    object_property_set_bool(OBJECT(&s->soc), true, "realized",
> -                            &error_abort);
> +    mmio_plic = virtio_plic = pcie_plic = NULL;
> +    for (i = 0; i < s->num_socs; i++) {
> +        base_hartid = i * (smp_cpus / s->num_socs);
> +        if (i == (s->num_socs - 1))
> +            cpus_per_socket = smp_cpus - base_hartid;
> +        else
> +            cpus_per_socket = smp_cpus / s->num_socs;
> +        soc_name = g_strdup_printf("soc%d", i);
> +        object_initialize_child(OBJECT(machine), soc_name, &s->soc[i],
> +            sizeof(s->soc[i]), TYPE_RISCV_HART_ARRAY, &error_abort, NULL);
> +        g_free(soc_name);
> +        object_property_set_str(OBJECT(&s->soc[i]),
> +            machine->cpu_type, "cpu-type", &error_abort);
> +        object_property_set_int(OBJECT(&s->soc[i]),
> +            base_hartid, "hartid-base", &error_abort);
> +        object_property_set_int(OBJECT(&s->soc[i]),
> +            cpus_per_socket, "num-harts", &error_abort);
> +        object_property_set_bool(OBJECT(&s->soc[i]),
> +            true, "realized", &error_abort);
> +
> +        /* Per-socket CLINT */
> +        sifive_clint_create(
> +            memmap[VIRT_CLINT].base + i * memmap[VIRT_CLINT].size,
> +            memmap[VIRT_CLINT].size, base_hartid, cpus_per_socket,
> +            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) * cpus_per_socket;
> +        plic_hart_config = g_malloc0(plic_hart_config_len);
> +        for (j = 0; j < cpus_per_socket; 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",
> @@ -572,38 +649,14 @@ static void riscv_virt_board_init(MachineState *machine)
>                            memmap[VIRT_MROM].base + sizeof(reset_vec),
>                            &address_space_memory);
>
> -    /* 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, 0,
> -        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, 0, 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,
> @@ -612,14 +665,14 @@ static void riscv_virt_board_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);
>
> @@ -629,8 +682,6 @@ static void riscv_virt_board_init(MachineState *machine)
>                                    drive_get(IF_PFLASH, 0, i));
>      }
>      virt_flash_map(s, system_memory);
> -
> -    g_free(plic_hart_config);
>  }
>
>  static void riscv_virt_machine_instance_init(Object *obj)
> @@ -643,7 +694,7 @@ static void riscv_virt_machine_class_init(ObjectClass *oc, void *data)
>
>      mc->desc = "RISC-V VirtIO board";
>      mc->init = riscv_virt_board_init;
> -    mc->max_cpus = 8;
> +    mc->max_cpus = VIRT_CPUS_MAX;
>      mc->default_cpu_type = VIRT_CPU;
>      mc->pci_allow_0_address = true;
>  }
> diff --git a/include/hw/riscv/virt.h b/include/hw/riscv/virt.h
> index e69355efaf..333d1edbc2 100644
> --- a/include/hw/riscv/virt.h
> +++ b/include/hw/riscv/virt.h
> @@ -23,6 +23,11 @@
>  #include "hw/sysbus.h"
>  #include "hw/block/flash.h"
>
> +#define VIRT_SOCKETS_MAX 4
> +#define VIRT_CPUS_PER_SOCKET_MIN 2
> +#define VIRT_CPUS_PER_SOCKET_MAX 4
> +#define VIRT_CPUS_MAX (VIRT_SOCKETS_MAX * VIRT_CPUS_PER_SOCKET_MAX)
> +
>  #define TYPE_RISCV_VIRT_MACHINE MACHINE_TYPE_NAME("virt")
>  #define RISCV_VIRT_MACHINE(obj) \
>      OBJECT_CHECK(RISCVVirtState, (obj), TYPE_RISCV_VIRT_MACHINE)
> @@ -32,8 +37,9 @@ typedef struct {
>      MachineState parent;
>
>      /*< public >*/
> -    RISCVHartArrayState soc;
> -    DeviceState *plic;
> +    unsigned int num_socs;
> +    RISCVHartArrayState soc[VIRT_SOCKETS_MAX];
> +    DeviceState *plic[VIRT_SOCKETS_MAX];
>      PFlashCFI01 *flash[2];
>
>      void *fdt;
> @@ -74,6 +80,8 @@ enum {
>  #define VIRT_PLIC_ENABLE_STRIDE 0x80
>  #define VIRT_PLIC_CONTEXT_BASE 0x200000
>  #define VIRT_PLIC_CONTEXT_STRIDE 0x1000
> +#define VIRT_PLIC_SIZE(__num_context) \
> +    (VIRT_PLIC_CONTEXT_BASE + (__num_context) * VIRT_PLIC_CONTEXT_STRIDE)
>
>  #define FDT_PCI_ADDR_CELLS    3
>  #define FDT_PCI_INT_CELLS     1

This has the same "minimum two CPUs per socket issue".

Re: [PATCH 0/4] RISC-V multi-socket support

[no-reply]

Patchew URL: https://patchew.org/QEMU/20200516063746.18296-1-anup.patel@wdc.com/



Hi,

This series seems to have some coding style problems. See output below for
more information:

Message-id: 20200516063746.18296-1-anup.patel@wdc.com
Subject: [PATCH 0/4] RISC-V multi-socket support
Type: series

=== TEST SCRIPT BEGIN ===
#!/bin/bash
git rev-parse base > /dev/null || exit 0
git config --local diff.renamelimit 0
git config --local diff.renames True
git config --local diff.algorithm histogram
./scripts/checkpatch.pl --mailback base..
=== TEST SCRIPT END ===

Updating 3c8cf5a9c21ff8782164d1def7f44bd888713384
Switched to a new branch 'test'
9031755 hw/riscv: virt: Allow creating multiple sockets
67e9547 hw/riscv: Allow creating multiple instances of PLIC
2999a11 hw/riscv: spike: Allow creating multiple sockets
b563a80 hw/riscv: Allow creating multiple instances of CLINT

=== OUTPUT BEGIN ===
1/4 Checking commit b563a8089a7a (hw/riscv: Allow creating multiple instances of CLINT)
2/4 Checking commit 2999a1101f27 (hw/riscv: spike: Allow creating multiple sockets)
ERROR: braces {} are necessary for all arms of this statement
#202: FILE: hw/riscv/spike.c:194:
+    if ((smp_cpus / s->num_socs) < SPIKE_CPUS_PER_SOCKET_MIN)
[...]

ERROR: braces {} are necessary for all arms of this statement
#206: FILE: hw/riscv/spike.c:198:
+    if (SPIKE_SOCKETS_MAX < s->num_socs)
[...]

ERROR: braces {} are necessary for all arms of this statement
#212: FILE: hw/riscv/spike.c:204:
+        if (i == (s->num_socs - 1))
[...]
+        else
[...]

WARNING: line over 80 characters
#248: FILE: hw/riscv/spike.c:299:
+    htif_mm_init(system_memory, mask_rom, &s->soc[0].harts[0].env, serial_hd(0));

WARNING: line over 80 characters
#266: FILE: hw/riscv/spike.c:322:
+    object_initialize_child(OBJECT(machine), "soc", &s->soc[0], sizeof(s->soc[0]),

WARNING: line over 80 characters
#284: FILE: hw/riscv/spike.c:386:
+    htif_mm_init(system_memory, mask_rom, &s->soc[0].harts[0].env, serial_hd(0));

WARNING: line over 80 characters
#302: FILE: hw/riscv/spike.c:414:
+    object_initialize_child(OBJECT(machine), "soc", &s->soc[0], sizeof(s->soc[0]),

WARNING: line over 80 characters
#329: FILE: hw/riscv/spike.c:497:
+    htif_mm_init(system_memory, mask_rom, &s->soc[0].harts[0].env, serial_hd(0));

total: 3 errors, 5 warnings, 322 lines checked

Patch 2/4 has style problems, please review.  If any of these errors
are false positives report them to the maintainer, see
CHECKPATCH in MAINTAINERS.

3/4 Checking commit 67e95477fcbe (hw/riscv: Allow creating multiple instances of PLIC)
4/4 Checking commit 90317551d9da (hw/riscv: virt: Allow creating multiple sockets)
ERROR: spaces required around that '*' (ctx:VxV)
#32: FILE: hw/riscv/virt.c:63:
+    [VIRT_PLIC] =        {  0xc000000, VIRT_PLIC_SIZE(VIRT_CPUS_MAX*2) },
                                                                    ^

WARNING: line over 80 characters
#295: FILE: hw/riscv/virt.c:343:
+        qemu_fdt_setprop_cell(fdt, name, "interrupt-parent", plic_virtio_phandle);

ERROR: braces {} are necessary for all arms of this statement
#478: FILE: hw/riscv/virt.c:497:
+    if ((smp_cpus / s->num_socs) < VIRT_CPUS_PER_SOCKET_MIN)
[...]

ERROR: braces {} are necessary for all arms of this statement
#482: FILE: hw/riscv/virt.c:501:
+    if (VIRT_SOCKETS_MAX < s->num_socs)
[...]

ERROR: braces {} are necessary for all arms of this statement
#497: FILE: hw/riscv/virt.c:508:
+        if (i == (s->num_socs - 1))
[...]
+        else
[...]

total: 4 errors, 1 warnings, 638 lines checked

Patch 4/4 has style problems, please review.  If any of these errors
are false positives report them to the maintainer, see
CHECKPATCH in MAINTAINERS.

=== OUTPUT END ===

Test command exited with code: 1


The full log is available at
http://patchew.org/logs/20200516063746.18296-1-anup.patel@wdc.com/testing.checkpatch/?type=message.
---
Email generated automatically by Patchew [https://patchew.org/].
Please send your feedback to patchew-devel@redhat.com

Re: [PATCH 0/4] RISC-V multi-socket support

[Alistair Francis]

On Fri, May 15, 2020 at 11:40 PM Anup Patel <anup.patel@wdc.com> wrote:
>
> This series adds multi-socket support for RISC-V virt machine and
> RISC-V spike machine. The multi-socket support will help us improve
> various RISC-V operating systems, firmwares, and bootloader to
> support RISC-V NUMA systems.
>
> These patch can be found in riscv_multi_socket_v1 branch at:
> https://github.com/avpatel/qemu.git
>
> To try this patches, we will need:
> 1. OpenSBI multi-PLIC and multi-CLINT support which can be found in
>    multi_plic_clint_v1 branch at:
>    https://github.com/avpatel/opensbi.git
> 2. Linux multi-PLIC improvements support which can be found in
>    plic_imp_v1 branch at:
>    https://github.com/avpatel/linux.git
>
> Anup Patel (4):
>   hw/riscv: Allow creating multiple instances of CLINT
>   hw/riscv: spike: Allow creating multiple sockets
>   hw/riscv: Allow creating multiple instances of PLIC
>   hw/riscv: virt: Allow creating multiple sockets

Can you make sure all the patches pass checkpatch?

Alistair

>
>  hw/riscv/sifive_clint.c         |  20 +-
>  hw/riscv/sifive_e.c             |   4 +-
>  hw/riscv/sifive_plic.c          |  24 +-
>  hw/riscv/sifive_u.c             |   4 +-
>  hw/riscv/spike.c                | 210 ++++++++------
>  hw/riscv/virt.c                 | 495 ++++++++++++++++++--------------
>  include/hw/riscv/sifive_clint.h |   7 +-
>  include/hw/riscv/sifive_plic.h  |  12 +-
>  include/hw/riscv/spike.h        |   8 +-
>  include/hw/riscv/virt.h         |  12 +-
>  10 files changed, 458 insertions(+), 338 deletions(-)
>
> --
> 2.25.1
>
>

RE: [PATCH 0/4] RISC-V multi-socket support

[Anup Patel]

> -----Original Message-----
> From: Alistair Francis <alistair23@gmail.com>
> Sent: 20 May 2020 02:50
> To: Anup Patel <Anup.Patel@wdc.com>
> Cc: Peter Maydell <peter.maydell@linaro.org>; Palmer Dabbelt
> <palmer@dabbelt.com>; Alistair Francis <Alistair.Francis@wdc.com>; Sagar
> Karandikar <sagark@eecs.berkeley.edu>; Atish Patra <Atish.Patra@wdc.com>;
> open list:RISC-V <qemu-riscv@nongnu.org>; qemu-devel@nongnu.org
> Developers <qemu-devel@nongnu.org>; Anup Patel <anup@brainfault.org>
> Subject: Re: [PATCH 0/4] RISC-V multi-socket support
> 
> On Fri, May 15, 2020 at 11:40 PM Anup Patel <anup.patel@wdc.com> wrote:
> >
> > This series adds multi-socket support for RISC-V virt machine and
> > RISC-V spike machine. The multi-socket support will help us improve
> > various RISC-V operating systems, firmwares, and bootloader to support
> > RISC-V NUMA systems.
> >
> > These patch can be found in riscv_multi_socket_v1 branch at:
> > https://github.com/avpatel/qemu.git
> >
> > To try this patches, we will need:
> > 1. OpenSBI multi-PLIC and multi-CLINT support which can be found in
> >    multi_plic_clint_v1 branch at:
> >    https://github.com/avpatel/opensbi.git
> > 2. Linux multi-PLIC improvements support which can be found in
> >    plic_imp_v1 branch at:
> >    https://github.com/avpatel/linux.git
> >
> > Anup Patel (4):
> >   hw/riscv: Allow creating multiple instances of CLINT
> >   hw/riscv: spike: Allow creating multiple sockets
> >   hw/riscv: Allow creating multiple instances of PLIC
> >   hw/riscv: virt: Allow creating multiple sockets
> 
> Can you make sure all the patches pass checkpatch?

My bad, I forgot to run checkpatch on this series.

I will update in v2.

Regards,
Anup