ppc/pnv: Improve pervasive topology calculation for big-core

Big (SMT8) cores have a complicated function to map the core, thread ID
to pervasive topology (PIR). Fix this for power8, power9, and power10.

Reviewed-by: Cédric Le Goater <clg@kaod.org>
Signed-off-by: Caleb Schlossin <calebs@linux.vnet.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
This commit is contained in:
Caleb Schlossin 2024-02-27 14:36:23 -06:00 committed by Nicholas Piggin
parent 0b8893236e
commit 9940412ae4
5 changed files with 57 additions and 28 deletions

View File

@ -141,8 +141,10 @@ static int pnv_dt_core(PnvChip *chip, PnvCore *pc, void *fdt)
int smt_threads = CPU_CORE(pc)->nr_threads;
CPUPPCState *env = &cpu->env;
PowerPCCPUClass *pcc = POWERPC_CPU_GET_CLASS(cs);
PnvChipClass *pnv_cc = PNV_CHIP_GET_CLASS(chip);
g_autofree uint32_t *servers_prop = g_new(uint32_t, smt_threads);
int i;
uint32_t pir;
uint32_t segs[] = {cpu_to_be32(28), cpu_to_be32(40),
0xffffffff, 0xffffffff};
uint32_t tbfreq = PNV_TIMEBASE_FREQ;
@ -153,15 +155,17 @@ static int pnv_dt_core(PnvChip *chip, PnvCore *pc, void *fdt)
char *nodename;
int cpus_offset = get_cpus_node(fdt);
nodename = g_strdup_printf("%s@%x", dc->fw_name, pc->pir);
pir = pnv_cc->chip_pir(chip, pc->hwid, 0);
nodename = g_strdup_printf("%s@%x", dc->fw_name, pir);
offset = fdt_add_subnode(fdt, cpus_offset, nodename);
_FDT(offset);
g_free(nodename);
_FDT((fdt_setprop_cell(fdt, offset, "ibm,chip-id", chip->chip_id)));
_FDT((fdt_setprop_cell(fdt, offset, "reg", pc->pir)));
_FDT((fdt_setprop_cell(fdt, offset, "ibm,pir", pc->pir)));
_FDT((fdt_setprop_cell(fdt, offset, "reg", pir)));
_FDT((fdt_setprop_cell(fdt, offset, "ibm,pir", pir)));
_FDT((fdt_setprop_string(fdt, offset, "device_type", "cpu")));
_FDT((fdt_setprop_cell(fdt, offset, "cpu-version", env->spr[SPR_PVR])));
@ -233,7 +237,7 @@ static int pnv_dt_core(PnvChip *chip, PnvCore *pc, void *fdt)
/* Build interrupt servers properties */
for (i = 0; i < smt_threads; i++) {
servers_prop[i] = cpu_to_be32(pc->pir + i);
servers_prop[i] = cpu_to_be32(pnv_cc->chip_pir(chip, pc->hwid, i));
}
_FDT((fdt_setprop(fdt, offset, "ibm,ppc-interrupt-server#s",
servers_prop, sizeof(*servers_prop) * smt_threads)));
@ -241,9 +245,11 @@ static int pnv_dt_core(PnvChip *chip, PnvCore *pc, void *fdt)
return offset;
}
static void pnv_dt_icp(PnvChip *chip, void *fdt, uint32_t pir,
static void pnv_dt_icp(PnvChip *chip, void *fdt, uint32_t hwid,
uint32_t nr_threads)
{
PnvChipClass *pcc = PNV_CHIP_GET_CLASS(chip);
uint32_t pir = pcc->chip_pir(chip, hwid, 0);
uint64_t addr = PNV_ICP_BASE(chip) | (pir << 12);
char *name;
const char compat[] = "IBM,power8-icp\0IBM,ppc-xicp";
@ -257,6 +263,7 @@ static void pnv_dt_icp(PnvChip *chip, void *fdt, uint32_t pir,
rsize = sizeof(uint64_t) * 2 * nr_threads;
reg = g_malloc(rsize);
for (i = 0; i < nr_threads; i++) {
/* We know P8 PIR is linear with thread id */
reg[i * 2] = cpu_to_be64(addr | ((pir + i) * 0x1000));
reg[i * 2 + 1] = cpu_to_be64(0x1000);
}
@ -324,7 +331,7 @@ static void pnv_chip_power8_dt_populate(PnvChip *chip, void *fdt)
pa_features_207, sizeof(pa_features_207))));
/* Interrupt Control Presenters (ICP). One per core. */
pnv_dt_icp(chip, fdt, pnv_core->pir, CPU_CORE(pnv_core)->nr_threads);
pnv_dt_icp(chip, fdt, pnv_core->hwid, CPU_CORE(pnv_core)->nr_threads);
}
if (chip->ram_size) {
@ -1075,9 +1082,10 @@ static void pnv_init(MachineState *machine)
* 25:28 Core number
* 29:31 Thread ID
*/
static uint32_t pnv_chip_core_pir_p8(PnvChip *chip, uint32_t core_id)
static uint32_t pnv_chip_pir_p8(PnvChip *chip, uint32_t core_id,
uint32_t thread_id)
{
return (chip->chip_id << 7) | (core_id << 3);
return (chip->chip_id << 7) | (core_id << 3) | thread_id;
}
static void pnv_chip_power8_intc_create(PnvChip *chip, PowerPCCPU *cpu,
@ -1129,14 +1137,37 @@ static void pnv_chip_power8_intc_print_info(PnvChip *chip, PowerPCCPU *cpu,
*
* We only care about the lower bits. uint32_t is fine for the moment.
*/
static uint32_t pnv_chip_core_pir_p9(PnvChip *chip, uint32_t core_id)
static uint32_t pnv_chip_pir_p9(PnvChip *chip, uint32_t core_id,
uint32_t thread_id)
{
return (chip->chip_id << 8) | (core_id << 2);
if (chip->nr_threads == 8) {
return (chip->chip_id << 8) | ((thread_id & 1) << 2) | (core_id << 3) |
(thread_id >> 1);
} else {
return (chip->chip_id << 8) | (core_id << 2) | thread_id;
}
}
static uint32_t pnv_chip_core_pir_p10(PnvChip *chip, uint32_t core_id)
/*
* 0:48 Reserved - Read as zeroes
* 49:52 Node ID
* 53:55 Chip ID
* 56 Reserved - Read as zero
* 57:59 Quad ID
* 60 Core Chiplet Pair ID
* 61:63 Thread/Core Chiplet ID t0-t2
*
* We only care about the lower bits. uint32_t is fine for the moment.
*/
static uint32_t pnv_chip_pir_p10(PnvChip *chip, uint32_t core_id,
uint32_t thread_id)
{
return (chip->chip_id << 8) | (core_id << 2);
if (chip->nr_threads == 8) {
return (chip->chip_id << 8) | ((core_id / 4) << 4) |
((core_id % 2) << 3) | thread_id;
} else {
return (chip->chip_id << 8) | (core_id << 2) | thread_id;
}
}
static void pnv_chip_power9_intc_create(PnvChip *chip, PowerPCCPU *cpu,
@ -1315,7 +1346,7 @@ static void pnv_chip_icp_realize(Pnv8Chip *chip8, Error **errp)
int core_hwid = CPU_CORE(pnv_core)->core_id;
for (j = 0; j < CPU_CORE(pnv_core)->nr_threads; j++) {
uint32_t pir = pcc->core_pir(chip, core_hwid) + j;
uint32_t pir = pcc->chip_pir(chip, core_hwid, j);
PnvICPState *icp = PNV_ICP(xics_icp_get(chip8->xics, pir));
memory_region_add_subregion(&chip8->icp_mmio, pir << 12,
@ -1428,7 +1459,7 @@ static void pnv_chip_power8e_class_init(ObjectClass *klass, void *data)
k->chip_cfam_id = 0x221ef04980000000ull; /* P8 Murano DD2.1 */
k->cores_mask = POWER8E_CORE_MASK;
k->num_phbs = 3;
k->core_pir = pnv_chip_core_pir_p8;
k->chip_pir = pnv_chip_pir_p8;
k->intc_create = pnv_chip_power8_intc_create;
k->intc_reset = pnv_chip_power8_intc_reset;
k->intc_destroy = pnv_chip_power8_intc_destroy;
@ -1452,7 +1483,7 @@ static void pnv_chip_power8_class_init(ObjectClass *klass, void *data)
k->chip_cfam_id = 0x220ea04980000000ull; /* P8 Venice DD2.0 */
k->cores_mask = POWER8_CORE_MASK;
k->num_phbs = 3;
k->core_pir = pnv_chip_core_pir_p8;
k->chip_pir = pnv_chip_pir_p8;
k->intc_create = pnv_chip_power8_intc_create;
k->intc_reset = pnv_chip_power8_intc_reset;
k->intc_destroy = pnv_chip_power8_intc_destroy;
@ -1476,7 +1507,7 @@ static void pnv_chip_power8nvl_class_init(ObjectClass *klass, void *data)
k->chip_cfam_id = 0x120d304980000000ull; /* P8 Naples DD1.0 */
k->cores_mask = POWER8_CORE_MASK;
k->num_phbs = 4;
k->core_pir = pnv_chip_core_pir_p8;
k->chip_pir = pnv_chip_pir_p8;
k->intc_create = pnv_chip_power8_intc_create;
k->intc_reset = pnv_chip_power8_intc_reset;
k->intc_destroy = pnv_chip_power8_intc_destroy;
@ -1749,7 +1780,7 @@ static void pnv_chip_power9_class_init(ObjectClass *klass, void *data)
k->chip_cfam_id = 0x220d104900008000ull; /* P9 Nimbus DD2.0 */
k->cores_mask = POWER9_CORE_MASK;
k->core_pir = pnv_chip_core_pir_p9;
k->chip_pir = pnv_chip_pir_p9;
k->intc_create = pnv_chip_power9_intc_create;
k->intc_reset = pnv_chip_power9_intc_reset;
k->intc_destroy = pnv_chip_power9_intc_destroy;
@ -2061,7 +2092,7 @@ static void pnv_chip_power10_class_init(ObjectClass *klass, void *data)
k->chip_cfam_id = 0x120da04900008000ull; /* P10 DD1.0 (with NX) */
k->cores_mask = POWER10_CORE_MASK;
k->core_pir = pnv_chip_core_pir_p10;
k->chip_pir = pnv_chip_pir_p10;
k->intc_create = pnv_chip_power10_intc_create;
k->intc_reset = pnv_chip_power10_intc_reset;
k->intc_destroy = pnv_chip_power10_intc_destroy;
@ -2151,8 +2182,8 @@ static void pnv_chip_core_realize(PnvChip *chip, Error **errp)
chip->nr_threads, &error_fatal);
object_property_set_int(OBJECT(pnv_core), CPU_CORE_PROP_CORE_ID,
core_hwid, &error_fatal);
object_property_set_int(OBJECT(pnv_core), "pir",
pcc->core_pir(chip, core_hwid), &error_fatal);
object_property_set_int(OBJECT(pnv_core), "hwid", core_hwid,
&error_fatal);
object_property_set_int(OBJECT(pnv_core), "hrmor", pnv->fw_load_addr,
&error_fatal);
object_property_set_link(OBJECT(pnv_core), "chip", OBJECT(chip),

View File

@ -226,7 +226,7 @@ static void pnv_core_cpu_realize(PnvCore *pc, PowerPCCPU *cpu, Error **errp,
int thread_index)
{
CPUPPCState *env = &cpu->env;
int core_pir;
int core_hwid;
ppc_spr_t *pir = &env->spr_cb[SPR_PIR];
ppc_spr_t *tir = &env->spr_cb[SPR_TIR];
Error *local_err = NULL;
@ -242,10 +242,10 @@ static void pnv_core_cpu_realize(PnvCore *pc, PowerPCCPU *cpu, Error **errp,
return;
}
core_pir = object_property_get_uint(OBJECT(pc), "pir", &error_abort);
core_hwid = object_property_get_uint(OBJECT(pc), "hwid", &error_abort);
tir->default_value = thread_index;
pir->default_value = core_pir + thread_index;
pir->default_value = pcc->chip_pir(pc->chip, core_hwid, thread_index);
/* Set time-base frequency to 512 MHz */
cpu_ppc_tb_init(env, PNV_TIMEBASE_FREQ);
@ -342,7 +342,7 @@ static void pnv_core_unrealize(DeviceState *dev)
}
static Property pnv_core_properties[] = {
DEFINE_PROP_UINT32("pir", PnvCore, pir, 0),
DEFINE_PROP_UINT32("hwid", PnvCore, hwid, 0),
DEFINE_PROP_UINT64("hrmor", PnvCore, hrmor, 0),
DEFINE_PROP_LINK("chip", PnvCore, chip, TYPE_PNV_CHIP, PnvChip *),
DEFINE_PROP_END_OF_LIST(),

View File

@ -147,7 +147,7 @@ struct PnvChipClass {
DeviceRealize parent_realize;
uint32_t (*core_pir)(PnvChip *chip, uint32_t core_id);
uint32_t (*chip_pir)(PnvChip *chip, uint32_t core_id, uint32_t thread_id);
void (*intc_create)(PnvChip *chip, PowerPCCPU *cpu, Error **errp);
void (*intc_reset)(PnvChip *chip, PowerPCCPU *cpu);
void (*intc_destroy)(PnvChip *chip, PowerPCCPU *cpu);

View File

@ -36,6 +36,7 @@ struct PnvCore {
/*< public >*/
PowerPCCPU **threads;
uint32_t pir;
uint32_t hwid;
uint64_t hrmor;
PnvChip *chip;

View File

@ -49,9 +49,6 @@ void helper_spr_core_write_generic(CPUPPCState *env, uint32_t sprn,
CPUState *cs = env_cpu(env);
CPUState *ccs;
uint32_t nr_threads = cs->nr_threads;
uint32_t core_id = env->spr[SPR_PIR] & ~(nr_threads - 1);
assert(core_id == env->spr[SPR_PIR] - env->spr[SPR_TIR]);
if (nr_threads == 1) {
env->spr[sprn] = val;