diff options
Diffstat (limited to 'drivers/acpi/numa')
-rw-r--r-- | drivers/acpi/numa/Kconfig | 5 | ||||
-rw-r--r-- | drivers/acpi/numa/hmat.c | 122 | ||||
-rw-r--r-- | drivers/acpi/numa/srat.c | 203 |
3 files changed, 244 insertions, 86 deletions
diff --git a/drivers/acpi/numa/Kconfig b/drivers/acpi/numa/Kconfig index 849c2bd820b9..f33194d1e43f 100644 --- a/drivers/acpi/numa/Kconfig +++ b/drivers/acpi/numa/Kconfig @@ -1,9 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 config ACPI_NUMA - bool "NUMA support" - depends on NUMA - depends on (X86 || ARM64 || LOONGARCH) - default y if ARM64 + def_bool NUMA && !X86 config ACPI_HMAT bool "ACPI Heterogeneous Memory Attribute Table Support" diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c index d6b85f0f6082..bfbb08b1e6af 100644 --- a/drivers/acpi/numa/hmat.c +++ b/drivers/acpi/numa/hmat.c @@ -59,9 +59,8 @@ struct target_cache { }; enum { - NODE_ACCESS_CLASS_0 = 0, - NODE_ACCESS_CLASS_1, - NODE_ACCESS_CLASS_GENPORT_SINK, + NODE_ACCESS_CLASS_GENPORT_SINK_LOCAL = ACCESS_COORDINATE_MAX, + NODE_ACCESS_CLASS_GENPORT_SINK_CPU, NODE_ACCESS_CLASS_MAX, }; @@ -75,6 +74,7 @@ struct memory_target { struct node_cache_attrs cache_attrs; u8 gen_port_device_handle[ACPI_SRAT_DEVICE_HANDLE_SIZE]; bool registered; + bool ext_updated; /* externally updated */ }; struct memory_initiator { @@ -127,7 +127,8 @@ static struct memory_target *acpi_find_genport_target(u32 uid) /** * acpi_get_genport_coordinates - Retrieve the access coordinates for a generic port * @uid: ACPI unique id - * @coord: The access coordinates written back out for the generic port + * @coord: The access coordinates written back out for the generic port. + * Expect 2 levels array. * * Return: 0 on success. Errno on failure. * @@ -143,11 +144,14 @@ int acpi_get_genport_coordinates(u32 uid, if (!target) return -ENOENT; - *coord = target->coord[NODE_ACCESS_CLASS_GENPORT_SINK]; + coord[ACCESS_COORDINATE_LOCAL] = + target->coord[NODE_ACCESS_CLASS_GENPORT_SINK_LOCAL]; + coord[ACCESS_COORDINATE_CPU] = + target->coord[NODE_ACCESS_CLASS_GENPORT_SINK_CPU]; return 0; } -EXPORT_SYMBOL_NS_GPL(acpi_get_genport_coordinates, CXL); +EXPORT_SYMBOL_NS_GPL(acpi_get_genport_coordinates, "CXL"); static __init void alloc_memory_initiator(unsigned int cpu_pxm) { @@ -325,6 +329,35 @@ static void hmat_update_target_access(struct memory_target *target, } } +int hmat_update_target_coordinates(int nid, struct access_coordinate *coord, + enum access_coordinate_class access) +{ + struct memory_target *target; + int pxm; + + if (nid == NUMA_NO_NODE) + return -EINVAL; + + pxm = node_to_pxm(nid); + guard(mutex)(&target_lock); + target = find_mem_target(pxm); + if (!target) + return -ENODEV; + + hmat_update_target_access(target, ACPI_HMAT_READ_LATENCY, + coord->read_latency, access); + hmat_update_target_access(target, ACPI_HMAT_WRITE_LATENCY, + coord->write_latency, access); + hmat_update_target_access(target, ACPI_HMAT_READ_BANDWIDTH, + coord->read_bandwidth, access); + hmat_update_target_access(target, ACPI_HMAT_WRITE_BANDWIDTH, + coord->write_bandwidth, access); + target->ext_updated = true; + + return 0; +} +EXPORT_SYMBOL_GPL(hmat_update_target_coordinates); + static __init void hmat_add_locality(struct acpi_hmat_locality *hmat_loc) { struct memory_locality *loc; @@ -374,11 +407,11 @@ static __init void hmat_update_target(unsigned int tgt_pxm, unsigned int init_px if (target && target->processor_pxm == init_pxm) { hmat_update_target_access(target, type, value, - NODE_ACCESS_CLASS_0); - /* If the node has a CPU, update access 1 */ + ACCESS_COORDINATE_LOCAL); + /* If the node has a CPU, update access ACCESS_COORDINATE_CPU */ if (node_state(pxm_to_node(init_pxm), N_CPU)) hmat_update_target_access(target, type, value, - NODE_ACCESS_CLASS_1); + ACCESS_COORDINATE_CPU); } } @@ -409,9 +442,9 @@ static __init int hmat_parse_locality(union acpi_subtable_headers *header, return -EINVAL; } - pr_info("Locality: Flags:%02x Type:%s Initiator Domains:%u Target Domains:%u Base:%lld\n", - hmat_loc->flags, hmat_data_type(type), ipds, tpds, - hmat_loc->entry_base_unit); + pr_debug("Locality: Flags:%02x Type:%s Initiator Domains:%u Target Domains:%u Base:%lld\n", + hmat_loc->flags, hmat_data_type(type), ipds, tpds, + hmat_loc->entry_base_unit); inits = (u32 *)(hmat_loc + 1); targs = inits + ipds; @@ -422,9 +455,9 @@ static __init int hmat_parse_locality(union acpi_subtable_headers *header, value = hmat_normalize(entries[init * tpds + targ], hmat_loc->entry_base_unit, type); - pr_info(" Initiator-Target[%u-%u]:%u%s\n", - inits[init], targs[targ], value, - hmat_data_type_suffix(type)); + pr_debug(" Initiator-Target[%u-%u]:%u%s\n", + inits[init], targs[targ], value, + hmat_data_type_suffix(type)); hmat_update_target(targs[targ], inits[init], mem_hier, type, value); @@ -452,9 +485,9 @@ static __init int hmat_parse_cache(union acpi_subtable_headers *header, } attrs = cache->cache_attributes; - pr_info("Cache: Domain:%u Size:%llu Attrs:%08x SMBIOS Handles:%d\n", - cache->memory_PD, cache->cache_size, attrs, - cache->number_of_SMBIOShandles); + pr_debug("Cache: Domain:%u Size:%llu Attrs:%08x SMBIOS Handles:%d\n", + cache->memory_PD, cache->cache_size, attrs, + cache->number_of_SMBIOShandles); target = find_mem_target(cache->memory_PD); if (!target) @@ -513,9 +546,9 @@ static int __init hmat_parse_proximity_domain(union acpi_subtable_headers *heade } if (hmat_revision == 1) - pr_info("Memory (%#llx length %#llx) Flags:%04x Processor Domain:%u Memory Domain:%u\n", - p->reserved3, p->reserved4, p->flags, p->processor_PD, - p->memory_PD); + pr_debug("Memory (%#llx length %#llx) Flags:%04x Processor Domain:%u Memory Domain:%u\n", + p->reserved3, p->reserved4, p->flags, p->processor_PD, + p->memory_PD); else pr_info("Memory Flags:%04x Processor Domain:%u Memory Domain:%u\n", p->flags, p->processor_PD, p->memory_PD); @@ -696,8 +729,13 @@ static void hmat_update_target_attrs(struct memory_target *target, u32 best = 0; int i; + /* Don't update if an external agent has changed the data. */ + if (target->ext_updated) + return; + /* Don't update for generic port if there's no device handle */ - if (access == NODE_ACCESS_CLASS_GENPORT_SINK && + if ((access == NODE_ACCESS_CLASS_GENPORT_SINK_LOCAL || + access == NODE_ACCESS_CLASS_GENPORT_SINK_CPU) && !(*(u16 *)target->gen_port_device_handle)) return; @@ -709,7 +747,8 @@ static void hmat_update_target_attrs(struct memory_target *target, */ if (target->processor_pxm != PXM_INVAL) { cpu_nid = pxm_to_node(target->processor_pxm); - if (access == 0 || node_state(cpu_nid, N_CPU)) { + if (access == ACCESS_COORDINATE_LOCAL || + node_state(cpu_nid, N_CPU)) { set_bit(target->processor_pxm, p_nodes); return; } @@ -737,7 +776,9 @@ static void hmat_update_target_attrs(struct memory_target *target, list_for_each_entry(initiator, &initiators, node) { u32 value; - if (access == 1 && !initiator->has_cpu) { + if ((access == ACCESS_COORDINATE_CPU || + access == NODE_ACCESS_CLASS_GENPORT_SINK_CPU) && + !initiator->has_cpu) { clear_bit(initiator->processor_pxm, p_nodes); continue; } @@ -770,20 +811,24 @@ static void __hmat_register_target_initiators(struct memory_target *target, } } -static void hmat_register_generic_target_initiators(struct memory_target *target) +static void hmat_update_generic_target(struct memory_target *target) { static DECLARE_BITMAP(p_nodes, MAX_NUMNODES); - __hmat_register_target_initiators(target, p_nodes, - NODE_ACCESS_CLASS_GENPORT_SINK); + hmat_update_target_attrs(target, p_nodes, + NODE_ACCESS_CLASS_GENPORT_SINK_LOCAL); + hmat_update_target_attrs(target, p_nodes, + NODE_ACCESS_CLASS_GENPORT_SINK_CPU); } static void hmat_register_target_initiators(struct memory_target *target) { static DECLARE_BITMAP(p_nodes, MAX_NUMNODES); - __hmat_register_target_initiators(target, p_nodes, 0); - __hmat_register_target_initiators(target, p_nodes, 1); + __hmat_register_target_initiators(target, p_nodes, + ACCESS_COORDINATE_LOCAL); + __hmat_register_target_initiators(target, p_nodes, + ACCESS_COORDINATE_CPU); } static void hmat_register_target_cache(struct memory_target *target) @@ -835,7 +880,7 @@ static void hmat_register_target(struct memory_target *target) */ mutex_lock(&target_lock); if (*(u16 *)target->gen_port_device_handle) { - hmat_register_generic_target_initiators(target); + hmat_update_generic_target(target); target->registered = true; } mutex_unlock(&target_lock); @@ -854,8 +899,8 @@ static void hmat_register_target(struct memory_target *target) if (!target->registered) { hmat_register_target_initiators(target); hmat_register_target_cache(target); - hmat_register_target_perf(target, NODE_ACCESS_CLASS_0); - hmat_register_target_perf(target, NODE_ACCESS_CLASS_1); + hmat_register_target_perf(target, ACCESS_COORDINATE_LOCAL); + hmat_register_target_perf(target, ACCESS_COORDINATE_CPU); target->registered = true; } mutex_unlock(&target_lock); @@ -888,22 +933,19 @@ static int hmat_callback(struct notifier_block *self, return NOTIFY_OK; } -static int hmat_set_default_dram_perf(void) +static int __init hmat_set_default_dram_perf(void) { int rc; int nid, pxm; struct memory_target *target; struct access_coordinate *attrs; - if (!default_dram_type) - return -EIO; - - for_each_node_mask(nid, default_dram_type->nodes) { + for_each_node_mask(nid, default_dram_nodes) { pxm = node_to_pxm(nid); target = find_mem_target(pxm); if (!target) continue; - attrs = &target->coord[1]; + attrs = &target->coord[ACCESS_COORDINATE_CPU]; rc = mt_set_default_dram_perf(nid, attrs, "ACPI HMAT"); if (rc) return rc; @@ -927,10 +969,10 @@ static int hmat_calculate_adistance(struct notifier_block *self, return NOTIFY_OK; mutex_lock(&target_lock); - hmat_update_target_attrs(target, p_nodes, 1); + hmat_update_target_attrs(target, p_nodes, ACCESS_COORDINATE_CPU); mutex_unlock(&target_lock); - perf = &target->coord[1]; + perf = &target->coord[ACCESS_COORDINATE_CPU]; if (mt_perf_to_adistance(perf, adist)) return NOTIFY_OK; diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c index 0214518fc582..00ac0d7bb8c9 100644 --- a/drivers/acpi/numa/srat.c +++ b/drivers/acpi/numa/srat.c @@ -17,6 +17,7 @@ #include <linux/numa.h> #include <linux/nodemask.h> #include <linux/topology.h> +#include <linux/numa_memblks.h> static nodemask_t nodes_found_map = NODE_MASK_NONE; @@ -29,6 +30,8 @@ static int node_to_pxm_map[MAX_NUMNODES] unsigned char acpi_srat_revision __initdata; static int acpi_numa __initdata; +static int last_real_pxm; + void __init disable_srat(void) { acpi_numa = -1; @@ -78,6 +81,101 @@ int acpi_map_pxm_to_node(int pxm) } EXPORT_SYMBOL(acpi_map_pxm_to_node); +#ifdef CONFIG_NUMA_EMU +/* + * Take max_nid - 1 fake-numa nodes into account in both + * pxm_to_node_map()/node_to_pxm_map[] tables. + */ +int __init fix_pxm_node_maps(int max_nid) +{ + static int pxm_to_node_map_copy[MAX_PXM_DOMAINS] __initdata + = { [0 ... MAX_PXM_DOMAINS - 1] = NUMA_NO_NODE }; + static int node_to_pxm_map_copy[MAX_NUMNODES] __initdata + = { [0 ... MAX_NUMNODES - 1] = PXM_INVAL }; + int i, j, index = -1, count = 0; + nodemask_t nodes_to_enable; + + if (numa_off) + return -1; + + /* no or incomplete node/PXM mapping set, nothing to do */ + if (srat_disabled()) + return 0; + + /* find fake nodes PXM mapping */ + for (i = 0; i < MAX_NUMNODES; i++) { + if (node_to_pxm_map[i] != PXM_INVAL) { + for (j = 0; j <= max_nid; j++) { + if ((emu_nid_to_phys[j] == i) && + WARN(node_to_pxm_map_copy[j] != PXM_INVAL, + "Node %d is already binded to PXM %d\n", + j, node_to_pxm_map_copy[j])) + return -1; + if (emu_nid_to_phys[j] == i) { + node_to_pxm_map_copy[j] = + node_to_pxm_map[i]; + if (j > index) + index = j; + count++; + } + } + } + } + if (index == -1) { + pr_debug("No node/PXM mapping has been set\n"); + /* nothing more to be done */ + return 0; + } + if (WARN(index != max_nid, "%d max nid when expected %d\n", + index, max_nid)) + return -1; + + nodes_clear(nodes_to_enable); + + /* map phys nodes not used for fake nodes */ + for (i = 0; i < MAX_NUMNODES; i++) { + if (node_to_pxm_map[i] != PXM_INVAL) { + for (j = 0; j <= max_nid; j++) + if (emu_nid_to_phys[j] == i) + break; + /* fake nodes PXM mapping has been done */ + if (j <= max_nid) + continue; + /* find first hole */ + for (j = 0; + j < MAX_NUMNODES && + node_to_pxm_map_copy[j] != PXM_INVAL; + j++) + ; + if (WARN(j == MAX_NUMNODES, + "Number of nodes exceeds MAX_NUMNODES\n")) + return -1; + node_to_pxm_map_copy[j] = node_to_pxm_map[i]; + node_set(j, nodes_to_enable); + count++; + } + } + + /* creating reverse mapping in pxm_to_node_map[] */ + for (i = 0; i < MAX_NUMNODES; i++) + if (node_to_pxm_map_copy[i] != PXM_INVAL && + pxm_to_node_map_copy[node_to_pxm_map_copy[i]] == NUMA_NO_NODE) + pxm_to_node_map_copy[node_to_pxm_map_copy[i]] = i; + + /* overwrite with new mapping */ + for (i = 0; i < MAX_NUMNODES; i++) { + node_to_pxm_map[i] = node_to_pxm_map_copy[i]; + pxm_to_node_map[i] = pxm_to_node_map_copy[i]; + } + + /* enable other nodes found in PXM for hotplug */ + nodes_or(numa_nodes_parsed, nodes_to_enable, numa_nodes_parsed); + + pr_debug("found %d total number of nodes\n", count); + return 0; +} +#endif + static void __init acpi_table_print_srat_entry(struct acpi_subtable_header *header) { @@ -165,6 +263,19 @@ acpi_table_print_srat_entry(struct acpi_subtable_header *header) } } break; + + case ACPI_SRAT_TYPE_RINTC_AFFINITY: + { + struct acpi_srat_rintc_affinity *p = + (struct acpi_srat_rintc_affinity *)header; + pr_debug("SRAT Processor (acpi id[0x%04x]) in proximity domain %d %s\n", + p->acpi_processor_uid, + p->proximity_domain, + (p->flags & ACPI_SRAT_RINTC_ENABLED) ? + "enabled" : "disabled"); + } + break; + default: pr_warn("Found unsupported SRAT entry (type = 0x%x)\n", header->type); @@ -206,16 +317,26 @@ int __init srat_disabled(void) return acpi_numa < 0; } -#if defined(CONFIG_X86) || defined(CONFIG_ARM64) || defined(CONFIG_LOONGARCH) +__weak int __init numa_fill_memblks(u64 start, u64 end) +{ + return NUMA_NO_MEMBLK; +} + /* * Callback for SLIT parsing. pxm_to_node() returns NUMA_NO_NODE for * I/O localities since SRAT does not list them. I/O localities are * not supported at this point. */ -void __init acpi_numa_slit_init(struct acpi_table_slit *slit) +static int __init acpi_parse_slit(struct acpi_table_header *table) { + struct acpi_table_slit *slit = (struct acpi_table_slit *)table; int i, j; + if (!slit_valid(slit)) { + pr_info("SLIT table looks invalid. Not used.\n"); + return -EINVAL; + } + for (i = 0; i < slit->locality_count; i++) { const int from_node = pxm_to_node(i); @@ -232,28 +353,34 @@ void __init acpi_numa_slit_init(struct acpi_table_slit *slit) slit->entry[slit->locality_count * i + j]); } } + + return 0; } -/* - * Default callback for parsing of the Proximity Domain <-> Memory - * Area mappings - */ -int __init -acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) +static int parsed_numa_memblks __initdata; + +static int __init +acpi_parse_memory_affinity(union acpi_subtable_headers *header, + const unsigned long table_end) { + struct acpi_srat_mem_affinity *ma; u64 start, end; u32 hotpluggable; int node, pxm; + ma = (struct acpi_srat_mem_affinity *)header; + + acpi_table_print_srat_entry(&header->common); + if (srat_disabled()) - goto out_err; + return 0; if (ma->header.length < sizeof(struct acpi_srat_mem_affinity)) { pr_err("SRAT: Unexpected header length: %d\n", ma->header.length); goto out_err_bad_srat; } if ((ma->flags & ACPI_SRAT_MEM_ENABLED) == 0) - goto out_err; + return 0; hotpluggable = IS_ENABLED(CONFIG_MEMORY_HOTPLUG) && (ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE); @@ -291,11 +418,15 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) max_possible_pfn = max(max_possible_pfn, PFN_UP(end - 1)); + parsed_numa_memblks++; + return 0; + out_err_bad_srat: + /* Just disable SRAT, but do not fail and ignore errors. */ bad_srat(); -out_err: - return -EINVAL; + + return 0; } static int __init acpi_parse_cfmws(union acpi_subtable_headers *header, @@ -338,26 +469,6 @@ static int __init acpi_parse_cfmws(union acpi_subtable_headers *header, (*fake_pxm)++; return 0; } -#else -static int __init acpi_parse_cfmws(union acpi_subtable_headers *header, - void *arg, const unsigned long table_end) -{ - return 0; -} -#endif /* defined(CONFIG_X86) || defined (CONFIG_ARM64) */ - -static int __init acpi_parse_slit(struct acpi_table_header *table) -{ - struct acpi_table_slit *slit = (struct acpi_table_slit *)table; - - if (!slit_valid(slit)) { - pr_info("SLIT table looks invalid. Not used.\n"); - return -EINVAL; - } - acpi_numa_slit_init(slit); - - return 0; -} void __init __weak acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa) @@ -448,21 +559,18 @@ acpi_parse_gi_affinity(union acpi_subtable_headers *header, } #endif /* defined(CONFIG_X86) || defined (CONFIG_ARM64) */ -static int __initdata parsed_numa_memblks; - static int __init -acpi_parse_memory_affinity(union acpi_subtable_headers * header, - const unsigned long end) +acpi_parse_rintc_affinity(union acpi_subtable_headers *header, + const unsigned long end) { - struct acpi_srat_mem_affinity *memory_affinity; - - memory_affinity = (struct acpi_srat_mem_affinity *)header; + struct acpi_srat_rintc_affinity *rintc_affinity; + rintc_affinity = (struct acpi_srat_rintc_affinity *)header; acpi_table_print_srat_entry(&header->common); /* let architecture-dependent part to do it */ - if (!acpi_numa_memory_affinity_init(memory_affinity)) - parsed_numa_memblks++; + acpi_numa_rintc_affinity_init(rintc_affinity); + return 0; } @@ -501,7 +609,7 @@ int __init acpi_numa_init(void) /* SRAT: System Resource Affinity Table */ if (!acpi_table_parse(ACPI_SIG_SRAT, acpi_parse_srat)) { - struct acpi_subtable_proc srat_proc[4]; + struct acpi_subtable_proc srat_proc[5]; memset(srat_proc, 0, sizeof(srat_proc)); srat_proc[0].id = ACPI_SRAT_TYPE_CPU_AFFINITY; @@ -512,6 +620,8 @@ int __init acpi_numa_init(void) srat_proc[2].handler = acpi_parse_gicc_affinity; srat_proc[3].id = ACPI_SRAT_TYPE_GENERIC_AFFINITY; srat_proc[3].handler = acpi_parse_gi_affinity; + srat_proc[4].id = ACPI_SRAT_TYPE_RINTC_AFFINITY; + srat_proc[4].handler = acpi_parse_rintc_affinity; acpi_table_parse_entries_array(ACPI_SIG_SRAT, sizeof(struct acpi_table_srat), @@ -536,6 +646,7 @@ int __init acpi_numa_init(void) if (node_to_pxm_map[i] > fake_pxm) fake_pxm = node_to_pxm_map[i]; } + last_real_pxm = fake_pxm; fake_pxm++; acpi_table_parse_cedt(ACPI_CEDT_TYPE_CFMWS, acpi_parse_cfmws, &fake_pxm); @@ -547,6 +658,14 @@ int __init acpi_numa_init(void) return 0; } +bool acpi_node_backed_by_real_pxm(int nid) +{ + int pxm = node_to_pxm(nid); + + return pxm <= last_real_pxm; +} +EXPORT_SYMBOL_GPL(acpi_node_backed_by_real_pxm); + static int acpi_get_pxm(acpi_handle h) { unsigned long long pxm; |