From: Rafael J. Wysocki Date: Mon, 25 Jul 2016 11:40:39 +0000 (+0200) Subject: Merge branch 'acpi-numa' X-Git-Tag: v4.8-rc1~157^2~6 X-Git-Url: http://git.cascardo.eti.br/?a=commitdiff_plain;h=d85f4eb6993d8c743ac89e427479cbe9efc14683;hp=523d939ef98fd712632d93a5a2b588e477a7565e;p=cascardo%2Flinux.git Merge branch 'acpi-numa' * acpi-numa: ACPI / NUMA: Enable ACPI based NUMA on ARM64 arm64, ACPI, NUMA: NUMA support based on SRAT and SLIT ACPI / processor: Add acpi_map_madt_entry() ACPI / NUMA: Improve SRAT error detection and add messages ACPI / NUMA: Move acpi_numa_memory_affinity_init() to drivers/acpi/numa.c ACPI / NUMA: remove unneeded acpi_numa=1 ACPI / NUMA: move bad_srat() and srat_disabled() to drivers/acpi/numa.c x86 / ACPI / NUMA: cleanup acpi_numa_processor_affinity_init() arm64, NUMA: Cleanup NUMA disabled messages arm64, NUMA: rework numa_add_memblk() ACPI / NUMA: move acpi_numa_slit_init() to drivers/acpi/numa.c ACPI / NUMA: Move acpi_numa_arch_fixup() to ia64 only ACPI / NUMA: remove duplicate NULL check ACPI / NUMA: Replace ACPI_DEBUG_PRINT() with pr_debug() ACPI / NUMA: Use pr_fmt() instead of printk --- diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h index aee323b13802..4b13ecd3977a 100644 --- a/arch/arm64/include/asm/acpi.h +++ b/arch/arm64/include/asm/acpi.h @@ -113,4 +113,12 @@ static inline const char *acpi_get_enable_method(int cpu) pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr); #endif +#ifdef CONFIG_ACPI_NUMA +int arm64_acpi_numa_init(void); +int acpi_numa_get_nid(unsigned int cpu, u64 hwid); +#else +static inline int arm64_acpi_numa_init(void) { return -ENOSYS; } +static inline int acpi_numa_get_nid(unsigned int cpu, u64 hwid) { return NUMA_NO_NODE; } +#endif /* CONFIG_ACPI_NUMA */ + #endif /*_ASM_ACPI_H*/ diff --git a/arch/arm64/include/asm/numa.h b/arch/arm64/include/asm/numa.h index e9b4f2942335..600887e491fd 100644 --- a/arch/arm64/include/asm/numa.h +++ b/arch/arm64/include/asm/numa.h @@ -5,6 +5,8 @@ #ifdef CONFIG_NUMA +#define NR_NODE_MEMBLKS (MAX_NUMNODES * 2) + /* currently, arm64 implements flat NUMA topology */ #define parent_node(node) (node) diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 2173149d8954..a5125c6d1f87 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -42,6 +42,7 @@ arm64-obj-$(CONFIG_EFI) += efi.o efi-entry.stub.o arm64-obj-$(CONFIG_PCI) += pci.o arm64-obj-$(CONFIG_ARMV8_DEPRECATED) += armv8_deprecated.o arm64-obj-$(CONFIG_ACPI) += acpi.o +arm64-obj-$(CONFIG_ACPI_NUMA) += acpi_numa.o arm64-obj-$(CONFIG_ARM64_ACPI_PARKING_PROTOCOL) += acpi_parking_protocol.o arm64-obj-$(CONFIG_PARAVIRT) += paravirt.o arm64-obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o diff --git a/arch/arm64/kernel/acpi_numa.c b/arch/arm64/kernel/acpi_numa.c new file mode 100644 index 000000000000..f85149cc7c71 --- /dev/null +++ b/arch/arm64/kernel/acpi_numa.c @@ -0,0 +1,112 @@ +/* + * ACPI 5.1 based NUMA setup for ARM64 + * Lots of code was borrowed from arch/x86/mm/srat.c + * + * Copyright 2004 Andi Kleen, SuSE Labs. + * Copyright (C) 2013-2016, Linaro Ltd. + * Author: Hanjun Guo + * + * Reads the ACPI SRAT table to figure out what memory belongs to which CPUs. + * + * Called from acpi_numa_init while reading the SRAT and SLIT tables. + * Assumes all memory regions belonging to a single proximity domain + * are in one chunk. Holes between them will be included in the node. + */ + +#define pr_fmt(fmt) "ACPI: NUMA: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +static int cpus_in_srat; + +struct __node_cpu_hwid { + u32 node_id; /* logical node containing this CPU */ + u64 cpu_hwid; /* MPIDR for this CPU */ +}; + +static struct __node_cpu_hwid early_node_cpu_hwid[NR_CPUS] = { +[0 ... NR_CPUS - 1] = {NUMA_NO_NODE, PHYS_CPUID_INVALID} }; + +int acpi_numa_get_nid(unsigned int cpu, u64 hwid) +{ + int i; + + for (i = 0; i < cpus_in_srat; i++) { + if (hwid == early_node_cpu_hwid[i].cpu_hwid) + return early_node_cpu_hwid[i].node_id; + } + + return NUMA_NO_NODE; +} + +/* Callback for Proximity Domain -> ACPI processor UID mapping */ +void __init acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa) +{ + int pxm, node; + phys_cpuid_t mpidr; + + if (srat_disabled()) + return; + + if (pa->header.length < sizeof(struct acpi_srat_gicc_affinity)) { + pr_err("SRAT: Invalid SRAT header length: %d\n", + pa->header.length); + bad_srat(); + return; + } + + if (!(pa->flags & ACPI_SRAT_GICC_ENABLED)) + return; + + if (cpus_in_srat >= NR_CPUS) { + pr_warn_once("SRAT: cpu_to_node_map[%d] is too small, may not be able to use all cpus\n", + NR_CPUS); + return; + } + + pxm = pa->proximity_domain; + node = acpi_map_pxm_to_node(pxm); + + if (node == NUMA_NO_NODE || node >= MAX_NUMNODES) { + pr_err("SRAT: Too many proximity domains %d\n", pxm); + bad_srat(); + return; + } + + mpidr = acpi_map_madt_entry(pa->acpi_processor_uid); + if (mpidr == PHYS_CPUID_INVALID) { + pr_err("SRAT: PXM %d with ACPI ID %d has no valid MPIDR in MADT\n", + pxm, pa->acpi_processor_uid); + bad_srat(); + return; + } + + early_node_cpu_hwid[cpus_in_srat].node_id = node; + early_node_cpu_hwid[cpus_in_srat].cpu_hwid = mpidr; + node_set(node, numa_nodes_parsed); + cpus_in_srat++; + pr_info("SRAT: PXM %d -> MPIDR 0x%Lx -> Node %d\n", + pxm, mpidr, node); +} + +int __init arm64_acpi_numa_init(void) +{ + int ret; + + ret = acpi_numa_init(); + if (ret) + return ret; + + return srat_disabled() ? -EINVAL : 0; +} diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 62ff3c0622e2..a68e0ccd9f4b 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -560,6 +560,8 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor) */ acpi_set_mailbox_entry(cpu_count, processor); + early_map_cpu_to_node(cpu_count, acpi_numa_get_nid(cpu_count, hwid)); + cpu_count++; } diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c index 98dc1047f2a2..c7fe3ec70774 100644 --- a/arch/arm64/mm/numa.c +++ b/arch/arm64/mm/numa.c @@ -17,6 +17,7 @@ * along with this program. If not, see . */ +#include #include #include #include @@ -29,7 +30,7 @@ static int cpu_to_node_map[NR_CPUS] = { [0 ... NR_CPUS-1] = NUMA_NO_NODE }; static int numa_distance_cnt; static u8 *numa_distance; -static int numa_off; +static bool numa_off; static __init int numa_parse_early_param(char *opt) { @@ -37,7 +38,7 @@ static __init int numa_parse_early_param(char *opt) return -EINVAL; if (!strncmp(opt, "off", 3)) { pr_info("%s\n", "NUMA turned off"); - numa_off = 1; + numa_off = true; } return 0; } @@ -131,25 +132,25 @@ void __init early_map_cpu_to_node(unsigned int cpu, int nid) * numa_add_memblk - Set node id to memblk * @nid: NUMA node ID of the new memblk * @start: Start address of the new memblk - * @size: Size of the new memblk + * @end: End address of the new memblk * * RETURNS: * 0 on success, -errno on failure. */ -int __init numa_add_memblk(int nid, u64 start, u64 size) +int __init numa_add_memblk(int nid, u64 start, u64 end) { int ret; - ret = memblock_set_node(start, size, &memblock.memory, nid); + ret = memblock_set_node(start, (end - start), &memblock.memory, nid); if (ret < 0) { pr_err("NUMA: memblock [0x%llx - 0x%llx] failed to add on node %d\n", - start, (start + size - 1), nid); + start, (end - 1), nid); return ret; } node_set(nid, numa_nodes_parsed); pr_info("NUMA: Adding memblock [0x%llx - 0x%llx] on node %d\n", - start, (start + size - 1), nid); + start, (end - 1), nid); return ret; } @@ -362,12 +363,15 @@ static int __init dummy_numa_init(void) int ret; struct memblock_region *mblk; - pr_info("%s\n", "No NUMA configuration found"); + if (numa_off) + pr_info("NUMA disabled\n"); /* Forced off on command line. */ + else + pr_info("No NUMA configuration found\n"); pr_info("NUMA: Faking a node at [mem %#018Lx-%#018Lx]\n", 0LLU, PFN_PHYS(max_pfn) - 1); for_each_memblock(memory, mblk) { - ret = numa_add_memblk(0, mblk->base, mblk->size); + ret = numa_add_memblk(0, mblk->base, mblk->base + mblk->size); if (!ret) continue; @@ -375,7 +379,7 @@ static int __init dummy_numa_init(void) return ret; } - numa_off = 1; + numa_off = true; return 0; } @@ -388,7 +392,9 @@ static int __init dummy_numa_init(void) void __init arm64_numa_init(void) { if (!numa_off) { - if (!numa_init(of_numa_init)) + if (!acpi_disabled && !numa_init(arm64_acpi_numa_init)) + return; + if (acpi_disabled && !numa_init(of_numa_init)) return; } diff --git a/arch/ia64/include/asm/acpi.h b/arch/ia64/include/asm/acpi.h index aa0fdf125aba..a3d0211970e9 100644 --- a/arch/ia64/include/asm/acpi.h +++ b/arch/ia64/include/asm/acpi.h @@ -140,6 +140,9 @@ static inline void per_cpu_scan_finalize(int min_cpus, int reserve_cpus) } } } + +extern void acpi_numa_fixup(void); + #endif /* CONFIG_ACPI_NUMA */ #endif /*__KERNEL__*/ diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c index b1698bc042c8..92b7bc956795 100644 --- a/arch/ia64/kernel/acpi.c +++ b/arch/ia64/kernel/acpi.c @@ -524,7 +524,7 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) return 0; } -void __init acpi_numa_arch_fixup(void) +void __init acpi_numa_fixup(void) { int i, j, node_from, node_to; diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index 2029a38a72ae..afddb3e80a29 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -552,6 +552,7 @@ setup_arch (char **cmdline_p) early_acpi_boot_init(); # ifdef CONFIG_ACPI_NUMA acpi_numa_init(); + acpi_numa_fixup(); # ifdef CONFIG_ACPI_HOTPLUG_CPU prefill_possible_map(); # endif diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index 94c18ebfd68c..65f1e95cade9 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -145,7 +145,6 @@ static inline void disable_acpi(void) { } #define ARCH_HAS_POWER_INIT 1 #ifdef CONFIG_ACPI_NUMA -extern int acpi_numa; extern int x86_acpi_numa_init(void); #endif /* CONFIG_ACPI_NUMA */ diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 9c086c57105c..968ac028c34e 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -1,4 +1,5 @@ /* Common code for 32 and 64-bit NUMA */ +#include #include #include #include @@ -15,7 +16,6 @@ #include #include #include -#include #include #include "numa_internal.h" diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c index b5f821881465..b1ecff460a46 100644 --- a/arch/x86/mm/srat.c +++ b/arch/x86/mm/srat.c @@ -15,8 +15,6 @@ #include #include #include -#include -#include #include #include #include @@ -24,51 +22,6 @@ #include #include -int acpi_numa __initdata; - -static __init int setup_node(int pxm) -{ - return acpi_map_pxm_to_node(pxm); -} - -static __init void bad_srat(void) -{ - printk(KERN_ERR "SRAT: SRAT not used.\n"); - acpi_numa = -1; -} - -static __init inline int srat_disabled(void) -{ - return acpi_numa < 0; -} - -/* - * 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) -{ - int i, j; - - for (i = 0; i < slit->locality_count; i++) { - const int from_node = pxm_to_node(i); - - if (from_node == NUMA_NO_NODE) - continue; - - for (j = 0; j < slit->locality_count; j++) { - const int to_node = pxm_to_node(j); - - if (to_node == NUMA_NO_NODE) - continue; - - numa_set_distance(from_node, to_node, - slit->entry[slit->locality_count * i + j]); - } - } -} - /* Callback for Proximity Domain -> x2APIC mapping */ void __init acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa) @@ -91,7 +44,7 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa) pxm, apic_id); return; } - node = setup_node(pxm); + node = acpi_map_pxm_to_node(pxm); if (node < 0) { printk(KERN_ERR "SRAT: Too many proximity domains %x\n", pxm); bad_srat(); @@ -104,7 +57,6 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa) } set_apicid_to_node(apic_id, node); node_set(node, numa_nodes_parsed); - acpi_numa = 1; printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%04x -> Node %u\n", pxm, apic_id, node); } @@ -127,7 +79,7 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) pxm = pa->proximity_domain_lo; if (acpi_srat_revision >= 2) pxm |= *((unsigned int*)pa->proximity_domain_hi) << 8; - node = setup_node(pxm); + node = acpi_map_pxm_to_node(pxm); if (node < 0) { printk(KERN_ERR "SRAT: Too many proximity domains %x\n", pxm); bad_srat(); @@ -146,74 +98,10 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) set_apicid_to_node(apic_id, node); node_set(node, numa_nodes_parsed); - acpi_numa = 1; printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%02x -> Node %u\n", pxm, apic_id, node); } -#ifdef CONFIG_MEMORY_HOTPLUG -static inline int save_add_info(void) {return 1;} -#else -static inline int save_add_info(void) {return 0;} -#endif - -/* Callback for parsing of the Proximity Domain <-> Memory Area mappings */ -int __init -acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) -{ - u64 start, end; - u32 hotpluggable; - int node, pxm; - - if (srat_disabled()) - goto out_err; - if (ma->header.length != sizeof(struct acpi_srat_mem_affinity)) - goto out_err_bad_srat; - if ((ma->flags & ACPI_SRAT_MEM_ENABLED) == 0) - goto out_err; - hotpluggable = ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE; - if (hotpluggable && !save_add_info()) - goto out_err; - - start = ma->base_address; - end = start + ma->length; - pxm = ma->proximity_domain; - if (acpi_srat_revision <= 1) - pxm &= 0xff; - - node = setup_node(pxm); - if (node < 0) { - printk(KERN_ERR "SRAT: Too many proximity domains.\n"); - goto out_err_bad_srat; - } - - if (numa_add_memblk(node, start, end) < 0) - goto out_err_bad_srat; - - node_set(node, numa_nodes_parsed); - - pr_info("SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]%s%s\n", - node, pxm, - (unsigned long long) start, (unsigned long long) end - 1, - hotpluggable ? " hotplug" : "", - ma->flags & ACPI_SRAT_MEM_NON_VOLATILE ? " non-volatile" : ""); - - /* Mark hotplug range in memblock. */ - if (hotpluggable && memblock_mark_hotplug(start, ma->length)) - pr_warn("SRAT: Failed to mark hotplug range [mem %#010Lx-%#010Lx] in memblock\n", - (unsigned long long)start, (unsigned long long)end - 1); - - max_possible_pfn = max(max_possible_pfn, PFN_UP(end - 1)); - - return 0; -out_err_bad_srat: - bad_srat(); -out_err: - return -1; -} - -void __init acpi_numa_arch_fixup(void) {} - int __init x86_acpi_numa_init(void) { int ret; diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index b7e2e776397d..dd76b36c431f 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -291,8 +291,8 @@ config ACPI_THERMAL config ACPI_NUMA bool "NUMA support" depends on NUMA - depends on (X86 || IA64) - default y if IA64_GENERIC || IA64_SGI_SN2 + depends on (X86 || IA64 || ARM64) + default y if IA64_GENERIC || IA64_SGI_SN2 || ARM64 config ACPI_CUSTOM_DSDT_FILE string "Custom DSDT Table file to include" diff --git a/drivers/acpi/numa.c b/drivers/acpi/numa.c index d176e0ece470..ce3a7a16f03f 100644 --- a/drivers/acpi/numa.c +++ b/drivers/acpi/numa.c @@ -18,22 +18,21 @@ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * */ + +#define pr_fmt(fmt) "ACPI: " fmt + #include #include #include #include #include #include +#include +#include #include #include #include -#define PREFIX "ACPI: " - -#define ACPI_NUMA 0x80000000 -#define _COMPONENT ACPI_NUMA -ACPI_MODULE_NAME("numa"); - static nodemask_t nodes_found_map = NODE_MASK_NONE; /* maps to convert between proximity domain and logical node ID */ @@ -43,6 +42,7 @@ static int node_to_pxm_map[MAX_NUMNODES] = { [0 ... MAX_NUMNODES - 1] = PXM_INVAL }; unsigned char acpi_srat_revision __initdata; +int acpi_numa __initdata; int pxm_to_node(int pxm) { @@ -128,68 +128,63 @@ EXPORT_SYMBOL(acpi_map_pxm_to_online_node); static void __init acpi_table_print_srat_entry(struct acpi_subtable_header *header) { - - ACPI_FUNCTION_NAME("acpi_table_print_srat_entry"); - - if (!header) - return; - switch (header->type) { - case ACPI_SRAT_TYPE_CPU_AFFINITY: -#ifdef ACPI_DEBUG_OUTPUT { struct acpi_srat_cpu_affinity *p = (struct acpi_srat_cpu_affinity *)header; - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "SRAT Processor (id[0x%02x] eid[0x%02x]) in proximity domain %d %s\n", - p->apic_id, p->local_sapic_eid, - p->proximity_domain_lo, - (p->flags & ACPI_SRAT_CPU_ENABLED)? - "enabled" : "disabled")); + pr_debug("SRAT Processor (id[0x%02x] eid[0x%02x]) in proximity domain %d %s\n", + p->apic_id, p->local_sapic_eid, + p->proximity_domain_lo, + (p->flags & ACPI_SRAT_CPU_ENABLED) ? + "enabled" : "disabled"); } -#endif /* ACPI_DEBUG_OUTPUT */ break; case ACPI_SRAT_TYPE_MEMORY_AFFINITY: -#ifdef ACPI_DEBUG_OUTPUT { struct acpi_srat_mem_affinity *p = (struct acpi_srat_mem_affinity *)header; - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "SRAT Memory (0x%lx length 0x%lx) in proximity domain %d %s%s%s\n", - (unsigned long)p->base_address, - (unsigned long)p->length, - p->proximity_domain, - (p->flags & ACPI_SRAT_MEM_ENABLED)? - "enabled" : "disabled", - (p->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE)? - " hot-pluggable" : "", - (p->flags & ACPI_SRAT_MEM_NON_VOLATILE)? - " non-volatile" : "")); + pr_debug("SRAT Memory (0x%lx length 0x%lx) in proximity domain %d %s%s%s\n", + (unsigned long)p->base_address, + (unsigned long)p->length, + p->proximity_domain, + (p->flags & ACPI_SRAT_MEM_ENABLED) ? + "enabled" : "disabled", + (p->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) ? + " hot-pluggable" : "", + (p->flags & ACPI_SRAT_MEM_NON_VOLATILE) ? + " non-volatile" : ""); } -#endif /* ACPI_DEBUG_OUTPUT */ break; case ACPI_SRAT_TYPE_X2APIC_CPU_AFFINITY: -#ifdef ACPI_DEBUG_OUTPUT { struct acpi_srat_x2apic_cpu_affinity *p = (struct acpi_srat_x2apic_cpu_affinity *)header; - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "SRAT Processor (x2apicid[0x%08x]) in" - " proximity domain %d %s\n", - p->apic_id, - p->proximity_domain, - (p->flags & ACPI_SRAT_CPU_ENABLED) ? - "enabled" : "disabled")); + pr_debug("SRAT Processor (x2apicid[0x%08x]) in proximity domain %d %s\n", + p->apic_id, + p->proximity_domain, + (p->flags & ACPI_SRAT_CPU_ENABLED) ? + "enabled" : "disabled"); } -#endif /* ACPI_DEBUG_OUTPUT */ break; + + case ACPI_SRAT_TYPE_GICC_AFFINITY: + { + struct acpi_srat_gicc_affinity *p = + (struct acpi_srat_gicc_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_GICC_ENABLED) ? + "enabled" : "disabled"); + } + break; + default: - printk(KERN_WARNING PREFIX - "Found unsupported SRAT entry (type = 0x%x)\n", - header->type); + pr_warn("Found unsupported SRAT entry (type = 0x%x)\n", + header->type); break; } } @@ -217,12 +212,117 @@ static int __init slit_valid(struct acpi_table_slit *slit) return 1; } +void __init bad_srat(void) +{ + pr_err("SRAT: SRAT not used.\n"); + acpi_numa = -1; +} + +int __init srat_disabled(void) +{ + return acpi_numa < 0; +} + +#if defined(CONFIG_X86) || defined(CONFIG_ARM64) +/* + * 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) +{ + int i, j; + + for (i = 0; i < slit->locality_count; i++) { + const int from_node = pxm_to_node(i); + + if (from_node == NUMA_NO_NODE) + continue; + + for (j = 0; j < slit->locality_count; j++) { + const int to_node = pxm_to_node(j); + + if (to_node == NUMA_NO_NODE) + continue; + + numa_set_distance(from_node, to_node, + slit->entry[slit->locality_count * i + j]); + } + } +} + +/* + * Default callback for parsing of the Proximity Domain <-> Memory + * Area mappings + */ +int __init +acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) +{ + u64 start, end; + u32 hotpluggable; + int node, pxm; + + if (srat_disabled()) + goto out_err; + 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; + hotpluggable = ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE; + if (hotpluggable && !IS_ENABLED(CONFIG_MEMORY_HOTPLUG)) + goto out_err; + + start = ma->base_address; + end = start + ma->length; + pxm = ma->proximity_domain; + if (acpi_srat_revision <= 1) + pxm &= 0xff; + + node = acpi_map_pxm_to_node(pxm); + if (node == NUMA_NO_NODE || node >= MAX_NUMNODES) { + pr_err("SRAT: Too many proximity domains.\n"); + goto out_err_bad_srat; + } + + if (numa_add_memblk(node, start, end) < 0) { + pr_err("SRAT: Failed to add memblk to node %u [mem %#010Lx-%#010Lx]\n", + node, (unsigned long long) start, + (unsigned long long) end - 1); + goto out_err_bad_srat; + } + + node_set(node, numa_nodes_parsed); + + pr_info("SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]%s%s\n", + node, pxm, + (unsigned long long) start, (unsigned long long) end - 1, + hotpluggable ? " hotplug" : "", + ma->flags & ACPI_SRAT_MEM_NON_VOLATILE ? " non-volatile" : ""); + + /* Mark hotplug range in memblock. */ + if (hotpluggable && memblock_mark_hotplug(start, ma->length)) + pr_warn("SRAT: Failed to mark hotplug range [mem %#010Lx-%#010Lx] in memblock\n", + (unsigned long long)start, (unsigned long long)end - 1); + + max_possible_pfn = max(max_possible_pfn, PFN_UP(end - 1)); + + return 0; +out_err_bad_srat: + bad_srat(); +out_err: + return -EINVAL; +} +#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)) { - printk(KERN_INFO "ACPI: SLIT table looks invalid. Not used.\n"); + pr_info("SLIT table looks invalid. Not used.\n"); return -EINVAL; } acpi_numa_slit_init(slit); @@ -233,12 +333,9 @@ static int __init acpi_parse_slit(struct acpi_table_header *table) void __init __weak acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa) { - printk(KERN_WARNING PREFIX - "Found unsupported x2apic [0x%08x] SRAT entry\n", pa->apic_id); - return; + pr_warn("Found unsupported x2apic [0x%08x] SRAT entry\n", pa->apic_id); } - static int __init acpi_parse_x2apic_affinity(struct acpi_subtable_header *header, const unsigned long end) @@ -275,6 +372,24 @@ acpi_parse_processor_affinity(struct acpi_subtable_header *header, return 0; } +static int __init +acpi_parse_gicc_affinity(struct acpi_subtable_header *header, + const unsigned long end) +{ + struct acpi_srat_gicc_affinity *processor_affinity; + + processor_affinity = (struct acpi_srat_gicc_affinity *)header; + if (!processor_affinity) + return -EINVAL; + + acpi_table_print_srat_entry(header); + + /* let architecture-dependent part to do it */ + acpi_numa_gicc_affinity_init(processor_affinity); + + return 0; +} + static int __initdata parsed_numa_memblks; static int __init @@ -319,6 +434,9 @@ int __init acpi_numa_init(void) { int cnt = 0; + if (acpi_disabled) + return -EINVAL; + /* * Should not limit number with cpu num that is from NR_CPUS or nr_cpus= * SRAT cpu entries could have different order with that in MADT. @@ -327,13 +445,15 @@ int __init acpi_numa_init(void) /* SRAT: Static Resource Affinity Table */ if (!acpi_table_parse(ACPI_SIG_SRAT, acpi_parse_srat)) { - struct acpi_subtable_proc srat_proc[2]; + struct acpi_subtable_proc srat_proc[3]; memset(srat_proc, 0, sizeof(srat_proc)); srat_proc[0].id = ACPI_SRAT_TYPE_CPU_AFFINITY; srat_proc[0].handler = acpi_parse_processor_affinity; srat_proc[1].id = ACPI_SRAT_TYPE_X2APIC_CPU_AFFINITY; srat_proc[1].handler = acpi_parse_x2apic_affinity; + srat_proc[2].id = ACPI_SRAT_TYPE_GICC_AFFINITY; + srat_proc[2].handler = acpi_parse_gicc_affinity; acpi_table_parse_entries_array(ACPI_SIG_SRAT, sizeof(struct acpi_table_srat), @@ -347,8 +467,6 @@ int __init acpi_numa_init(void) /* SLIT: System Locality Information Table */ acpi_table_parse(ACPI_SIG_SLIT, acpi_parse_slit); - acpi_numa_arch_fixup(); - if (cnt < 0) return cnt; else if (!parsed_numa_memblks) diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c index 33a38d604630..9125d7d96372 100644 --- a/drivers/acpi/processor_core.c +++ b/drivers/acpi/processor_core.c @@ -108,13 +108,12 @@ static int map_gicc_mpidr(struct acpi_subtable_header *entry, return -EINVAL; } -static phys_cpuid_t map_madt_entry(int type, u32 acpi_id) +static phys_cpuid_t map_madt_entry(struct acpi_table_madt *madt, + int type, u32 acpi_id) { unsigned long madt_end, entry; phys_cpuid_t phys_id = PHYS_CPUID_INVALID; /* CPU hardware ID */ - struct acpi_table_madt *madt; - madt = get_madt_table(); if (!madt) return phys_id; @@ -145,6 +144,25 @@ static phys_cpuid_t map_madt_entry(int type, u32 acpi_id) return phys_id; } +phys_cpuid_t __init acpi_map_madt_entry(u32 acpi_id) +{ + struct acpi_table_madt *madt = NULL; + acpi_size tbl_size; + phys_cpuid_t rv; + + acpi_get_table_with_size(ACPI_SIG_MADT, 0, + (struct acpi_table_header **)&madt, + &tbl_size); + if (!madt) + return PHYS_CPUID_INVALID; + + rv = map_madt_entry(madt, 1, acpi_id); + + early_acpi_os_unmap_memory(madt, tbl_size); + + return rv; +} + static phys_cpuid_t map_mat_entry(acpi_handle handle, int type, u32 acpi_id) { struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; @@ -185,7 +203,7 @@ phys_cpuid_t acpi_get_phys_id(acpi_handle handle, int type, u32 acpi_id) phys_id = map_mat_entry(handle, type, acpi_id); if (invalid_phys_cpuid(phys_id)) - phys_id = map_madt_entry(type, acpi_id); + phys_id = map_madt_entry(get_madt_table(), type, acpi_id); return phys_id; } diff --git a/drivers/of/of_numa.c b/drivers/of/of_numa.c index 0f2784bc1874..ed5a097f0801 100644 --- a/drivers/of/of_numa.c +++ b/drivers/of/of_numa.c @@ -91,8 +91,8 @@ static int __init of_numa_parse_memory_nodes(void) pr_debug("NUMA: base = %llx len = %llx, node = %u\n", rsrc.start, rsrc.end - rsrc.start + 1, nid); - r = numa_add_memblk(nid, rsrc.start, - rsrc.end - rsrc.start + 1); + + r = numa_add_memblk(nid, rsrc.start, rsrc.end + 1); if (r) break; } diff --git a/include/acpi/acpi_numa.h b/include/acpi/acpi_numa.h index 94a37cd7fbda..d4b72944ccda 100644 --- a/include/acpi/acpi_numa.h +++ b/include/acpi/acpi_numa.h @@ -15,6 +15,10 @@ extern int pxm_to_node(int); extern int node_to_pxm(int); extern int acpi_map_pxm_to_node(int); extern unsigned char acpi_srat_revision; +extern int acpi_numa __initdata; + +extern void bad_srat(void); +extern int srat_disabled(void); #endif /* CONFIG_ACPI_NUMA */ #endif /* __ACP_NUMA_H */ diff --git a/include/acpi/processor.h b/include/acpi/processor.h index 6f1805dd5d3c..f473e6618339 100644 --- a/include/acpi/processor.h +++ b/include/acpi/processor.h @@ -309,6 +309,7 @@ static inline int acpi_processor_get_bios_limit(int cpu, unsigned int *limit) /* in processor_core.c */ phys_cpuid_t acpi_get_phys_id(acpi_handle, int type, u32 acpi_id); +phys_cpuid_t acpi_map_madt_entry(u32 acpi_id); int acpi_map_cpuid(phys_cpuid_t phys_id, u32 acpi_id); int acpi_get_cpuid(acpi_handle, int type, u32 acpi_id); diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 288fac5294f5..9515db6f03f0 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -232,12 +232,26 @@ int acpi_table_parse_madt(enum acpi_madt_type id, int acpi_parse_mcfg (struct acpi_table_header *header); void acpi_table_print_madt_entry (struct acpi_subtable_header *madt); -/* the following four functions are architecture-dependent */ +/* the following numa functions are architecture-dependent */ void acpi_numa_slit_init (struct acpi_table_slit *slit); + +#if defined(CONFIG_X86) || defined(CONFIG_IA64) void acpi_numa_processor_affinity_init (struct acpi_srat_cpu_affinity *pa); +#else +static inline void +acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) { } +#endif + void acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa); + +#ifdef CONFIG_ARM64 +void acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa); +#else +static inline void +acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa) { } +#endif + int acpi_numa_memory_affinity_init (struct acpi_srat_mem_affinity *ma); -void acpi_numa_arch_fixup(void); #ifndef PHYS_CPUID_INVALID typedef u32 phys_cpuid_t;