diff options
author | Graeme Gregory <graeme.gregory@linaro.org> | 2016-05-17 12:41:13 +0100 |
---|---|---|
committer | Graeme Gregory <graeme.gregory@linaro.org> | 2016-05-17 12:41:13 +0100 |
commit | aa4f2e35a233a1bf805e0a09e080f62901b86e90 (patch) | |
tree | 87ae5361926e68957a6cfb2d386f9c8c19920676 | |
parent | e524f676b12e8288d74add07db3957184c0f45de (diff) | |
parent | 7e915347e666b7fe00d51a188152891956007b18 (diff) |
Merge branch 'topic-numa' into leg-kernel
34 files changed, 1442 insertions, 209 deletions
diff --git a/Documentation/devicetree/bindings/numa.txt b/Documentation/devicetree/bindings/numa.txt new file mode 100644 index 000000000000..21b35053ca5a --- /dev/null +++ b/Documentation/devicetree/bindings/numa.txt @@ -0,0 +1,275 @@ +============================================================================== +NUMA binding description. +============================================================================== + +============================================================================== +1 - Introduction +============================================================================== + +Systems employing a Non Uniform Memory Access (NUMA) architecture contain +collections of hardware resources including processors, memory, and I/O buses, +that comprise what is commonly known as a NUMA node. +Processor accesses to memory within the local NUMA node is generally faster +than processor accesses to memory outside of the local NUMA node. +DT defines interfaces that allow the platform to convey NUMA node +topology information to OS. + +============================================================================== +2 - numa-node-id +============================================================================== + +For the purpose of identification, each NUMA node is associated with a unique +token known as a node id. For the purpose of this binding +a node id is a 32-bit integer. + +A device node is associated with a NUMA node by the presence of a +numa-node-id property which contains the node id of the device. + +Example: + /* numa node 0 */ + numa-node-id = <0>; + + /* numa node 1 */ + numa-node-id = <1>; + +============================================================================== +3 - distance-map +============================================================================== + +The optional device tree node distance-map describes the relative +distance (memory latency) between all numa nodes. + +- compatible : Should at least contain "numa-distance-map-v1". + +- distance-matrix + This property defines a matrix to describe the relative distances + between all numa nodes. + It is represented as a list of node pairs and their relative distance. + + Note: + 1. Each entry represents distance from first node to second node. + The distances are equal in either direction. + 2. The distance from a node to self (local distance) is represented + with value 10 and all internode distance should be represented with + a value greater than 10. + 3. distance-matrix should have entries in lexicographical ascending + order of nodes. + 4. There must be only one device node distance-map which must + reside in the root node. + 5. If the distance-map node is not present, a default + distance-matrix is used. + +Example: + 4 nodes connected in mesh/ring topology as below, + + 0_______20______1 + | | + | | + 20 20 + | | + | | + |_______________| + 3 20 2 + + if relative distance for each hop is 20, + then internode distance would be, + 0 -> 1 = 20 + 1 -> 2 = 20 + 2 -> 3 = 20 + 3 -> 0 = 20 + 0 -> 2 = 40 + 1 -> 3 = 40 + + and dt presentation for this distance matrix is, + + distance-map { + compatible = "numa-distance-map-v1"; + distance-matrix = <0 0 10>, + <0 1 20>, + <0 2 40>, + <0 3 20>, + <1 0 20>, + <1 1 10>, + <1 2 20>, + <1 3 40>, + <2 0 40>, + <2 1 20>, + <2 2 10>, + <2 3 20>, + <3 0 20>, + <3 1 40>, + <3 2 20>, + <3 3 10>; + }; + +============================================================================== +4 - Example dts +============================================================================== + +Dual socket system consists of 2 boards connected through ccn bus and +each board having one socket/soc of 8 cpus, memory and pci bus. + + memory@c00000 { + device_type = "memory"; + reg = <0x0 0xc00000 0x0 0x80000000>; + /* node 0 */ + numa-node-id = <0>; + }; + + memory@10000000000 { + device_type = "memory"; + reg = <0x100 0x0 0x0 0x80000000>; + /* node 1 */ + numa-node-id = <1>; + }; + + cpus { + #address-cells = <2>; + #size-cells = <0>; + + cpu@0 { + device_type = "cpu"; + compatible = "arm,armv8"; + reg = <0x0 0x0>; + enable-method = "psci"; + /* node 0 */ + numa-node-id = <0>; + }; + cpu@1 { + device_type = "cpu"; + compatible = "arm,armv8"; + reg = <0x0 0x1>; + enable-method = "psci"; + numa-node-id = <0>; + }; + cpu@2 { + device_type = "cpu"; + compatible = "arm,armv8"; + reg = <0x0 0x2>; + enable-method = "psci"; + numa-node-id = <0>; + }; + cpu@3 { + device_type = "cpu"; + compatible = "arm,armv8"; + reg = <0x0 0x3>; + enable-method = "psci"; + numa-node-id = <0>; + }; + cpu@4 { + device_type = "cpu"; + compatible = "arm,armv8"; + reg = <0x0 0x4>; + enable-method = "psci"; + numa-node-id = <0>; + }; + cpu@5 { + device_type = "cpu"; + compatible = "arm,armv8"; + reg = <0x0 0x5>; + enable-method = "psci"; + numa-node-id = <0>; + }; + cpu@6 { + device_type = "cpu"; + compatible = "arm,armv8"; + reg = <0x0 0x6>; + enable-method = "psci"; + numa-node-id = <0>; + }; + cpu@7 { + device_type = "cpu"; + compatible = "arm,armv8"; + reg = <0x0 0x7>; + enable-method = "psci"; + numa-node-id = <0>; + }; + cpu@8 { + device_type = "cpu"; + compatible = "arm,armv8"; + reg = <0x0 0x8>; + enable-method = "psci"; + /* node 1 */ + numa-node-id = <1>; + }; + cpu@9 { + device_type = "cpu"; + compatible = "arm,armv8"; + reg = <0x0 0x9>; + enable-method = "psci"; + numa-node-id = <1>; + }; + cpu@a { + device_type = "cpu"; + compatible = "arm,armv8"; + reg = <0x0 0xa>; + enable-method = "psci"; + numa-node-id = <1>; + }; + cpu@b { + device_type = "cpu"; + compatible = "arm,armv8"; + reg = <0x0 0xb>; + enable-method = "psci"; + numa-node-id = <1>; + }; + cpu@c { + device_type = "cpu"; + compatible = "arm,armv8"; + reg = <0x0 0xc>; + enable-method = "psci"; + numa-node-id = <1>; + }; + cpu@d { + device_type = "cpu"; + compatible = "arm,armv8"; + reg = <0x0 0xd>; + enable-method = "psci"; + numa-node-id = <1>; + }; + cpu@e { + device_type = "cpu"; + compatible = "arm,armv8"; + reg = <0x0 0xe>; + enable-method = "psci"; + numa-node-id = <1>; + }; + cpu@f { + device_type = "cpu"; + compatible = "arm,armv8"; + reg = <0x0 0xf>; + enable-method = "psci"; + numa-node-id = <1>; + }; + }; + + pcie0: pcie0@848000000000 { + compatible = "arm,armv8"; + device_type = "pci"; + bus-range = <0 255>; + #size-cells = <2>; + #address-cells = <3>; + reg = <0x8480 0x00000000 0 0x10000000>; /* Configuration space */ + ranges = <0x03000000 0x8010 0x00000000 0x8010 0x00000000 0x70 0x00000000>; + /* node 0 */ + numa-node-id = <0>; + }; + + pcie1: pcie1@948000000000 { + compatible = "arm,armv8"; + device_type = "pci"; + bus-range = <0 255>; + #size-cells = <2>; + #address-cells = <3>; + reg = <0x9480 0x00000000 0 0x10000000>; /* Configuration space */ + ranges = <0x03000000 0x9010 0x00000000 0x9010 0x00000000 0x70 0x00000000>; + /* node 1 */ + numa-node-id = <1>; + }; + + distance-map { + compatible = "numa-distance-map-v1"; + distance-matrix = <0 0 10>, + <0 1 20>, + <1 1 10>; + }; diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 42ebcff9e754..0189dd5dc770 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -14,6 +14,7 @@ config ARM64 select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_USE_CMPXCHG_LOCKREF select ARCH_SUPPORTS_ATOMIC_RMW + select ARCH_SUPPORTS_NUMA_BALANCING select ARCH_WANT_OPTIONAL_GPIOLIB select ARCH_WANT_COMPAT_IPC_PARSE_VERSION select ARCH_WANT_FRAME_POINTERS @@ -79,6 +80,7 @@ config ARM64 select HAVE_HW_BREAKPOINT if PERF_EVENTS select HAVE_IRQ_TIME_ACCOUNTING select HAVE_MEMBLOCK + select HAVE_MEMBLOCK_NODE_MAP if NUMA select HAVE_PATA_PLATFORM select HAVE_PERF_EVENTS select HAVE_PERF_REGS @@ -101,6 +103,7 @@ config ARM64 select SYSCTL_EXCEPTION_TRACE select HAVE_CONTEXT_TRACKING select HAVE_ARM_SMCCC + select OF_NUMA if NUMA && OF help ARM 64-bit (AArch64) Linux support. @@ -549,6 +552,30 @@ config HOTPLUG_CPU Say Y here to experiment with turning CPUs off and on. CPUs can be controlled through /sys/devices/system/cpu. +# Common NUMA Features +config NUMA + bool "Numa Memory Allocation and Scheduler Support" + depends on SMP + help + Enable NUMA (Non Uniform Memory Access) support. + + The kernel will try to allocate memory used by a CPU on the + local memory of the CPU and add some more + NUMA awareness to the kernel. + +config NODES_SHIFT + int "Maximum NUMA Nodes (as a power of 2)" + range 1 10 + default "2" + depends on NEED_MULTIPLE_NODES + help + Specify the maximum number of NUMA Nodes available on the target + system. Increases memory reserved to accommodate various tables. + +config USE_PERCPU_NUMA_NODE_ID + def_bool y + depends on NUMA + source kernel/Kconfig.preempt source kernel/Kconfig.hz diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h index 4a6c959995cc..355a28fb7261 100644 --- a/arch/arm64/include/asm/acpi.h +++ b/arch/arm64/include/asm/acpi.h @@ -126,4 +126,13 @@ static inline void arch_apei_flush_tlb_one(unsigned long addr) flush_tlb_kernel_range(addr, addr + PAGE_SIZE); } #endif /* CONFIG_ACPI_APEI */ + +#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/mmu.h b/arch/arm64/include/asm/mmu.h index 990124a67eeb..97b1d8f26b9c 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -29,6 +29,7 @@ typedef struct { #define ASID(mm) ((mm)->context.id.counter & 0xffff) extern void paging_init(void); +extern void bootmem_init(void); extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt); extern void init_mem_pgprot(void); extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, diff --git a/arch/arm64/include/asm/mmzone.h b/arch/arm64/include/asm/mmzone.h new file mode 100644 index 000000000000..a0de9e6ba73f --- /dev/null +++ b/arch/arm64/include/asm/mmzone.h @@ -0,0 +1,12 @@ +#ifndef __ASM_MMZONE_H +#define __ASM_MMZONE_H + +#ifdef CONFIG_NUMA + +#include <asm/numa.h> + +extern struct pglist_data *node_data[]; +#define NODE_DATA(nid) (node_data[(nid)]) + +#endif /* CONFIG_NUMA */ +#endif /* __ASM_MMZONE_H */ diff --git a/arch/arm64/include/asm/numa.h b/arch/arm64/include/asm/numa.h new file mode 100644 index 000000000000..600887e491fd --- /dev/null +++ b/arch/arm64/include/asm/numa.h @@ -0,0 +1,47 @@ +#ifndef __ASM_NUMA_H +#define __ASM_NUMA_H + +#include <asm/topology.h> + +#ifdef CONFIG_NUMA + +#define NR_NODE_MEMBLKS (MAX_NUMNODES * 2) + +/* currently, arm64 implements flat NUMA topology */ +#define parent_node(node) (node) + +int __node_distance(int from, int to); +#define node_distance(a, b) __node_distance(a, b) + +extern nodemask_t numa_nodes_parsed __initdata; + +/* Mappings between node number and cpus on that node. */ +extern cpumask_var_t node_to_cpumask_map[MAX_NUMNODES]; +void numa_clear_node(unsigned int cpu); + +#ifdef CONFIG_DEBUG_PER_CPU_MAPS +const struct cpumask *cpumask_of_node(int node); +#else +/* Returns a pointer to the cpumask of CPUs on Node 'node'. */ +static inline const struct cpumask *cpumask_of_node(int node) +{ + return node_to_cpumask_map[node]; +} +#endif + +void __init arm64_numa_init(void); +int __init numa_add_memblk(int nodeid, u64 start, u64 end); +void __init numa_set_distance(int from, int to, int distance); +void __init numa_free_distance(void); +void __init early_map_cpu_to_node(unsigned int cpu, int nid); +void numa_store_cpu_info(unsigned int cpu); + +#else /* CONFIG_NUMA */ + +static inline void numa_store_cpu_info(unsigned int cpu) { } +static inline void arm64_numa_init(void) { } +static inline void early_map_cpu_to_node(unsigned int cpu, int nid) { } + +#endif /* CONFIG_NUMA */ + +#endif /* __ASM_NUMA_H */ diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 989fef16d461..89b8f205a14c 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -272,6 +272,21 @@ static inline pgprot_t mk_sect_prot(pgprot_t prot) return __pgprot(pgprot_val(prot) & ~PTE_TABLE_BIT); } +#ifdef CONFIG_NUMA_BALANCING +/* + * See the comment in include/asm-generic/pgtable.h + */ +static inline int pte_protnone(pte_t pte) +{ + return (pte_val(pte) & (PTE_VALID | PTE_PROT_NONE)) == PTE_PROT_NONE; +} + +static inline int pmd_protnone(pmd_t pmd) +{ + return pte_protnone(pmd_pte(pmd)); +} +#endif + /* * THP definitions. */ diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h index a3e9d6fdbf21..8b57339823e9 100644 --- a/arch/arm64/include/asm/topology.h +++ b/arch/arm64/include/asm/topology.h @@ -22,6 +22,16 @@ void init_cpu_topology(void); void store_cpu_topology(unsigned int cpuid); const struct cpumask *cpu_coregroup_mask(int cpu); +#ifdef CONFIG_NUMA + +struct pci_bus; +int pcibus_to_node(struct pci_bus *bus); +#define cpumask_of_pcibus(bus) (pcibus_to_node(bus) == -1 ? \ + cpu_all_mask : \ + cpumask_of_node(pcibus_to_node(bus))) + +#endif /* CONFIG_NUMA */ + #include <asm-generic/topology.h> #endif /* _ASM_ARM_TOPOLOGY_H */ diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 3793003e16a2..69569c6fa97f 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..94a6b35fab92 --- /dev/null +++ b/arch/arm64/kernel/acpi_numa.c @@ -0,0 +1,149 @@ +/* + * 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 <hanjun.guo@linaro.org> + * + * 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 <linux/acpi.h> +#include <linux/bitmap.h> +#include <linux/bootmem.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/memblock.h> +#include <linux/mmzone.h> +#include <linux/module.h> +#include <linux/topology.h> + +#include <acpi/processor.h> +#include <asm/numa.h> + +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; +} + +static int __init get_mpidr_in_madt(int acpi_id, u64 *mpidr) +{ + unsigned long madt_end, entry; + struct acpi_table_madt *madt; + acpi_size tbl_size; + + if (ACPI_FAILURE(acpi_get_table_with_size(ACPI_SIG_MADT, 0, + (struct acpi_table_header **)&madt, &tbl_size))) + return -ENODEV; + + entry = (unsigned long)madt; + madt_end = entry + madt->header.length; + + /* Parse all entries looking for a match. */ + entry += sizeof(struct acpi_table_madt); + while (entry + sizeof(struct acpi_subtable_header) < madt_end) { + struct acpi_subtable_header *header = + (struct acpi_subtable_header *)entry; + + if (header->type == ACPI_MADT_TYPE_GENERIC_INTERRUPT) { + struct acpi_madt_generic_interrupt *gicc = + container_of(header, + struct acpi_madt_generic_interrupt, header); + + if ((gicc->flags & ACPI_MADT_ENABLED) && + (gicc->uid == acpi_id)) { + *mpidr = gicc->arm_mpidr; + early_acpi_os_unmap_memory(madt, tbl_size); + return 0; + } + } + entry += header->length; + } + + early_acpi_os_unmap_memory(madt, tbl_size); + return -ENODEV; +} + +/* Callback for Proximity Domain -> ACPI processor UID mapping */ +void __init acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa) +{ + int pxm, node; + u64 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; + } + + if (get_mpidr_in_madt(pa->acpi_processor_uid, &mpidr)) { + 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/pci.c b/arch/arm64/kernel/pci.c index e484c9177456..ea120a847806 100644 --- a/arch/arm64/kernel/pci.c +++ b/arch/arm64/kernel/pci.c @@ -74,3 +74,13 @@ void pcibios_remove_bus(struct pci_bus *bus) { acpi_pci_remove_bus(bus); } + +#ifdef CONFIG_NUMA + +int pcibus_to_node(struct pci_bus *bus) +{ + return dev_to_node(&bus->dev); +} +EXPORT_SYMBOL(pcibus_to_node); + +#endif diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 9dc67769b6a4..0ad4b7770c05 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -53,6 +53,7 @@ #include <asm/cpufeature.h> #include <asm/cpu_ops.h> #include <asm/kasan.h> +#include <asm/numa.h> #include <asm/sections.h> #include <asm/setup.h> #include <asm/smp_plat.h> @@ -327,6 +328,12 @@ void __init setup_arch(char **cmdline_p) acpi_boot_table_init(); paging_init(); + + if (acpi_disabled) + unflatten_device_tree(); + + bootmem_init(); + relocate_initrd(); kasan_init(); @@ -335,12 +342,11 @@ void __init setup_arch(char **cmdline_p) early_ioremap_reset(); - if (acpi_disabled) { - unflatten_device_tree(); + if (acpi_disabled) psci_dt_init(); - } else { + else psci_acpi_init(); - } + xen_early_init(); cpu_read_bootcpu_ops(); @@ -379,6 +385,9 @@ static int __init topology_init(void) { int i; + for_each_online_node(i) + register_one_node(i); + for_each_possible_cpu(i) { struct cpu *cpu = &per_cpu(cpu_data.cpu, i); cpu->hotpluggable = 1; diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index b2d5f4ee9a1c..6c7ef8f25a90 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -45,6 +45,7 @@ #include <asm/cputype.h> #include <asm/cpu_ops.h> #include <asm/mmu_context.h> +#include <asm/numa.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> #include <asm/processor.h> @@ -166,6 +167,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) static void smp_store_cpu_info(unsigned int cpuid) { store_cpu_topology(cpuid); + numa_store_cpu_info(cpuid); } /* @@ -522,6 +524,8 @@ 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++; } @@ -595,6 +599,8 @@ static void __init of_parse_and_init_cpus(void) pr_debug("cpu logical map 0x%llx\n", hwid); cpu_logical_map(cpu_count) = hwid; + + early_map_cpu_to_node(cpu_count, of_node_to_nid(dn)); next: cpu_count++; } diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile index 57f57fde5722..54bb209cae8e 100644 --- a/arch/arm64/mm/Makefile +++ b/arch/arm64/mm/Makefile @@ -4,6 +4,7 @@ obj-y := dma-mapping.o extable.o fault.o init.o \ context.o proc.o pageattr.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o obj-$(CONFIG_ARM64_PTDUMP) += dump.o +obj-$(CONFIG_NUMA) += numa.o obj-$(CONFIG_KASAN) += kasan_init.o KASAN_SANITIZE_kasan_init.o := n diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index ea989d83ea9b..b1ff1511f472 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -40,6 +40,7 @@ #include <asm/kasan.h> #include <asm/kernel-pgtable.h> #include <asm/memory.h> +#include <asm/numa.h> #include <asm/sections.h> #include <asm/setup.h> #include <asm/sizes.h> @@ -86,6 +87,21 @@ static phys_addr_t __init max_zone_dma_phys(void) return min(offset + (1ULL << 32), memblock_end_of_DRAM()); } +#ifdef CONFIG_NUMA + +static void __init zone_sizes_init(unsigned long min, unsigned long max) +{ + unsigned long max_zone_pfns[MAX_NR_ZONES] = {0}; + + if (IS_ENABLED(CONFIG_ZONE_DMA)) + max_zone_pfns[ZONE_DMA] = PFN_DOWN(max_zone_dma_phys()); + max_zone_pfns[ZONE_NORMAL] = max; + + free_area_init_nodes(max_zone_pfns); +} + +#else + static void __init zone_sizes_init(unsigned long min, unsigned long max) { struct memblock_region *reg; @@ -126,6 +142,8 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) free_area_init_node(0, zone_size, min, zhole_size); } +#endif /* CONFIG_NUMA */ + #ifdef CONFIG_HAVE_ARCH_PFN_VALID int pfn_valid(unsigned long pfn) { @@ -142,10 +160,15 @@ static void __init arm64_memory_present(void) static void __init arm64_memory_present(void) { struct memblock_region *reg; + int nid = 0; - for_each_memblock(memory, reg) - memory_present(0, memblock_region_memory_base_pfn(reg), - memblock_region_memory_end_pfn(reg)); + for_each_memblock(memory, reg) { +#ifdef CONFIG_NUMA + nid = reg->nid; +#endif + memory_present(nid, memblock_region_memory_base_pfn(reg), + memblock_region_memory_end_pfn(reg)); + } } #endif @@ -245,7 +268,6 @@ void __init arm64_memblock_init(void) dma_contiguous_reserve(arm64_dma_phys_limit); memblock_allow_resize(); - memblock_dump_all(); } void __init bootmem_init(void) @@ -257,6 +279,9 @@ void __init bootmem_init(void) early_memtest(min << PAGE_SHIFT, max << PAGE_SHIFT); + max_pfn = max_low_pfn = max; + + arm64_numa_init(); /* * Sparsemem tries to allocate bootmem in memory_present(), so must be * done after the fixed reservations. @@ -267,7 +292,7 @@ void __init bootmem_init(void) zone_sizes_init(min, max); high_memory = __va((max << PAGE_SHIFT) - 1) + 1; - max_pfn = max_low_pfn = max; + memblock_dump_all(); } #ifndef CONFIG_SPARSEMEM_VMEMMAP diff --git a/arch/arm64/mm/mm.h b/arch/arm64/mm/mm.h index ef47d99b5cbc..71fe98985455 100644 --- a/arch/arm64/mm/mm.h +++ b/arch/arm64/mm/mm.h @@ -1,3 +1,2 @@ -extern void __init bootmem_init(void); void fixup_init(void); diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index f3e5c74233f3..267903b59ced 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -564,8 +564,6 @@ void __init paging_init(void) */ memblock_free(__pa(swapper_pg_dir) + PAGE_SIZE, SWAPPER_DIR_SIZE - PAGE_SIZE); - - bootmem_init(); } /* diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c new file mode 100644 index 000000000000..c7fe3ec70774 --- /dev/null +++ b/arch/arm64/mm/numa.c @@ -0,0 +1,402 @@ +/* + * NUMA support, based on the x86 implementation. + * + * Copyright (C) 2015 Cavium Inc. + * Author: Ganapatrao Kulkarni <gkulkarni@cavium.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include <linux/acpi.h> +#include <linux/bootmem.h> +#include <linux/memblock.h> +#include <linux/module.h> +#include <linux/of.h> + +struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; +EXPORT_SYMBOL(node_data); +nodemask_t numa_nodes_parsed __initdata; +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 bool numa_off; + +static __init int numa_parse_early_param(char *opt) +{ + if (!opt) + return -EINVAL; + if (!strncmp(opt, "off", 3)) { + pr_info("%s\n", "NUMA turned off"); + numa_off = true; + } + return 0; +} +early_param("numa", numa_parse_early_param); + +cpumask_var_t node_to_cpumask_map[MAX_NUMNODES]; +EXPORT_SYMBOL(node_to_cpumask_map); + +#ifdef CONFIG_DEBUG_PER_CPU_MAPS + +/* + * Returns a pointer to the bitmask of CPUs on Node 'node'. + */ +const struct cpumask *cpumask_of_node(int node) +{ + if (WARN_ON(node >= nr_node_ids)) + return cpu_none_mask; + + if (WARN_ON(node_to_cpumask_map[node] == NULL)) + return cpu_online_mask; + + return node_to_cpumask_map[node]; +} +EXPORT_SYMBOL(cpumask_of_node); + +#endif + +static void map_cpu_to_node(unsigned int cpu, int nid) +{ + set_cpu_numa_node(cpu, nid); + if (nid >= 0) + cpumask_set_cpu(cpu, node_to_cpumask_map[nid]); +} + +void numa_clear_node(unsigned int cpu) +{ + int nid = cpu_to_node(cpu); + + if (nid >= 0) + cpumask_clear_cpu(cpu, node_to_cpumask_map[nid]); + set_cpu_numa_node(cpu, NUMA_NO_NODE); +} + +/* + * Allocate node_to_cpumask_map based on number of available nodes + * Requires node_possible_map to be valid. + * + * Note: cpumask_of_node() is not valid until after this is done. + * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.) + */ +static void __init setup_node_to_cpumask_map(void) +{ + unsigned int cpu; + int node; + + /* setup nr_node_ids if not done yet */ + if (nr_node_ids == MAX_NUMNODES) + setup_nr_node_ids(); + + /* allocate and clear the mapping */ + for (node = 0; node < nr_node_ids; node++) { + alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]); + cpumask_clear(node_to_cpumask_map[node]); + } + + for_each_possible_cpu(cpu) + set_cpu_numa_node(cpu, NUMA_NO_NODE); + + /* cpumask_of_node() will now work */ + pr_debug("NUMA: Node to cpumask map for %d nodes\n", nr_node_ids); +} + +/* + * Set the cpu to node and mem mapping + */ +void numa_store_cpu_info(unsigned int cpu) +{ + map_cpu_to_node(cpu, numa_off ? 0 : cpu_to_node_map[cpu]); +} + +void __init early_map_cpu_to_node(unsigned int cpu, int nid) +{ + /* fallback to node 0 */ + if (nid < 0 || nid >= MAX_NUMNODES) + nid = 0; + + cpu_to_node_map[cpu] = nid; +} + +/** + * numa_add_memblk - Set node id to memblk + * @nid: NUMA node ID of the new memblk + * @start: Start address 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 end) +{ + int ret; + + 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, (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, (end - 1), nid); + return ret; +} + +/** + * Initialize NODE_DATA for a node on the local memory + */ +static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn) +{ + const size_t nd_size = roundup(sizeof(pg_data_t), SMP_CACHE_BYTES); + u64 nd_pa; + void *nd; + int tnid; + + pr_info("NUMA: Initmem setup node %d [mem %#010Lx-%#010Lx]\n", + nid, start_pfn << PAGE_SHIFT, + (end_pfn << PAGE_SHIFT) - 1); + + nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); + nd = __va(nd_pa); + + /* report and initialize */ + pr_info("NUMA: NODE_DATA [mem %#010Lx-%#010Lx]\n", + nd_pa, nd_pa + nd_size - 1); + tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT); + if (tnid != nid) + pr_info("NUMA: NODE_DATA(%d) on node %d\n", nid, tnid); + + node_data[nid] = nd; + memset(NODE_DATA(nid), 0, sizeof(pg_data_t)); + NODE_DATA(nid)->node_id = nid; + NODE_DATA(nid)->node_start_pfn = start_pfn; + NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn; +} + +/** + * numa_free_distance + * + * The current table is freed. + */ +void __init numa_free_distance(void) +{ + size_t size; + + if (!numa_distance) + return; + + size = numa_distance_cnt * numa_distance_cnt * + sizeof(numa_distance[0]); + + memblock_free(__pa(numa_distance), size); + numa_distance_cnt = 0; + numa_distance = NULL; +} + +/** + * + * Create a new NUMA distance table. + * + */ +static int __init numa_alloc_distance(void) +{ + size_t size; + u64 phys; + int i, j; + + size = nr_node_ids * nr_node_ids * sizeof(numa_distance[0]); + phys = memblock_find_in_range(0, PFN_PHYS(max_pfn), + size, PAGE_SIZE); + if (WARN_ON(!phys)) + return -ENOMEM; + + memblock_reserve(phys, size); + + numa_distance = __va(phys); + numa_distance_cnt = nr_node_ids; + + /* fill with the default distances */ + for (i = 0; i < numa_distance_cnt; i++) + for (j = 0; j < numa_distance_cnt; j++) + numa_distance[i * numa_distance_cnt + j] = i == j ? + LOCAL_DISTANCE : REMOTE_DISTANCE; + + pr_debug("NUMA: Initialized distance table, cnt=%d\n", + numa_distance_cnt); + + return 0; +} + +/** + * numa_set_distance - Set inter node NUMA distance from node to node. + * @from: the 'from' node to set distance + * @to: the 'to' node to set distance + * @distance: NUMA distance + * + * Set the distance from node @from to @to to @distance. + * If distance table doesn't exist, a warning is printed. + * + * If @from or @to is higher than the highest known node or lower than zero + * or @distance doesn't make sense, the call is ignored. + * + */ +void __init numa_set_distance(int from, int to, int distance) +{ + if (!numa_distance) { + pr_warn_once("NUMA: Warning: distance table not allocated yet\n"); + return; + } + + if (from >= numa_distance_cnt || to >= numa_distance_cnt || + from < 0 || to < 0) { + pr_warn_once("NUMA: Warning: node ids are out of bound, from=%d to=%d distance=%d\n", + from, to, distance); + return; + } + + if ((u8)distance != distance || + (from == to && distance != LOCAL_DISTANCE)) { + pr_warn_once("NUMA: Warning: invalid distance parameter, from=%d to=%d distance=%d\n", + from, to, distance); + return; + } + + numa_distance[from * numa_distance_cnt + to] = distance; +} + +/** + * Return NUMA distance @from to @to + */ +int __node_distance(int from, int to) +{ + if (from >= numa_distance_cnt || to >= numa_distance_cnt) + return from == to ? LOCAL_DISTANCE : REMOTE_DISTANCE; + return numa_distance[from * numa_distance_cnt + to]; +} +EXPORT_SYMBOL(__node_distance); + +static int __init numa_register_nodes(void) +{ + int nid; + struct memblock_region *mblk; + + /* Check that valid nid is set to memblks */ + for_each_memblock(memory, mblk) + if (mblk->nid == NUMA_NO_NODE || mblk->nid >= MAX_NUMNODES) { + pr_warn("NUMA: Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n", + mblk->nid, mblk->base, + mblk->base + mblk->size - 1); + return -EINVAL; + } + + /* Finally register nodes. */ + for_each_node_mask(nid, numa_nodes_parsed) { + unsigned long start_pfn, end_pfn; + + get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); + setup_node_data(nid, start_pfn, end_pfn); + node_set_online(nid); + } + + /* Setup online nodes to actual nodes*/ + node_possible_map = numa_nodes_parsed; + + return 0; +} + +static int __init numa_init(int (*init_func)(void)) +{ + int ret; + + nodes_clear(numa_nodes_parsed); + nodes_clear(node_possible_map); + nodes_clear(node_online_map); + numa_free_distance(); + + ret = numa_alloc_distance(); + if (ret < 0) + return ret; + + ret = init_func(); + if (ret < 0) + return ret; + + if (nodes_empty(numa_nodes_parsed)) + return -EINVAL; + + ret = numa_register_nodes(); + if (ret < 0) + return ret; + + setup_node_to_cpumask_map(); + + /* init boot processor */ + cpu_to_node_map[0] = 0; + map_cpu_to_node(0, 0); + + return 0; +} + +/** + * dummy_numa_init - Fallback dummy NUMA init + * + * Used if there's no underlying NUMA architecture, NUMA initialization + * fails, or NUMA is disabled on the command line. + * + * Must online at least one node (node 0) and add memory blocks that cover all + * allowed memory. It is unlikely that this function fails. + */ +static int __init dummy_numa_init(void) +{ + int ret; + struct memblock_region *mblk; + + 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->base + mblk->size); + if (!ret) + continue; + + pr_err("NUMA init failed\n"); + return ret; + } + + numa_off = true; + return 0; +} + +/** + * arm64_numa_init - Initialize NUMA + * + * Try each configured NUMA initialization method until one succeeds. The + * last fallback is dummy single node config encomapssing whole memory. + */ +void __init arm64_numa_init(void) +{ + if (!numa_off) { + if (!acpi_disabled && !numa_init(arm64_acpi_numa_init)) + return; + if (acpi_disabled && !numa_init(of_numa_init)) + return; + } + + numa_init(dummy_numa_init); +} 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 f70c1ff46125..57673f5cb120 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 <linux/acpi.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/string.h> @@ -15,7 +16,6 @@ #include <asm/e820.h> #include <asm/proto.h> #include <asm/dma.h> -#include <asm/acpi.h> #include <asm/amd_nb.h> #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 <linux/bitmap.h> #include <linux/module.h> #include <linux/topology.h> -#include <linux/bootmem.h> -#include <linux/memblock.h> #include <linux/mm.h> #include <asm/proto.h> #include <asm/numa.h> @@ -24,51 +22,6 @@ #include <asm/apic.h> #include <asm/uv/uv.h> -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 b6320a100f89..64d8fce05adb 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -297,8 +297,8 @@ 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 72b6e9ef0ae9..f6696ac45e41 100644 --- a/drivers/acpi/numa.c +++ b/drivers/acpi/numa.c @@ -18,22 +18,21 @@ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * */ + +#define pr_fmt(fmt) "ACPI: " fmt + #include <linux/module.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/types.h> #include <linux/errno.h> #include <linux/acpi.h> +#include <linux/bootmem.h> +#include <linux/memblock.h> #include <linux/numa.h> #include <linux/nodemask.h> #include <linux/topology.h> -#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. @@ -331,6 +449,8 @@ int __init acpi_numa_init(void) acpi_parse_x2apic_affinity, 0); acpi_table_parse_srat(ACPI_SRAT_TYPE_CPU_AFFINITY, acpi_parse_processor_affinity, 0); + acpi_table_parse_srat(ACPI_SRAT_TYPE_GICC_AFFINITY, + acpi_parse_gicc_affinity, 0); cnt = acpi_table_parse_srat(ACPI_SRAT_TYPE_MEMORY_AFFINITY, acpi_parse_memory_affinity, NR_NODE_MEMBLKS); @@ -339,8 +459,6 @@ 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/firmware/efi/arm-init.c b/drivers/firmware/efi/arm-init.c index 8714f8c271ba..434dd6065935 100644 --- a/drivers/firmware/efi/arm-init.c +++ b/drivers/firmware/efi/arm-init.c @@ -143,6 +143,14 @@ static __init void reserve_regions(void) if (efi_enabled(EFI_DBG)) pr_info("Processing EFI memory map:\n"); + /* + * Discard memblocks discovered so far: if there are any at this + * point, they originate from memory nodes in the DT, and UEFI + * uses its own memory map instead. + */ + memblock_dump_all(); + memblock_remove(0, ULLONG_MAX); + for_each_efi_memory_desc(&memmap, md) { paddr = md->phys_addr; npages = md->num_pages; diff --git a/drivers/firmware/efi/libstub/fdt.c b/drivers/firmware/efi/libstub/fdt.c index 6dba78aef337..e58abfa953cc 100644 --- a/drivers/firmware/efi/libstub/fdt.c +++ b/drivers/firmware/efi/libstub/fdt.c @@ -24,7 +24,7 @@ efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt, unsigned long map_size, unsigned long desc_size, u32 desc_ver) { - int node, prev, num_rsv; + int node, num_rsv; int status; u32 fdt_val32; u64 fdt_val64; @@ -54,28 +54,6 @@ efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt, goto fdt_set_fail; /* - * Delete any memory nodes present. We must delete nodes which - * early_init_dt_scan_memory may try to use. - */ - prev = 0; - for (;;) { - const char *type; - int len; - - node = fdt_next_node(fdt, prev, NULL); - if (node < 0) - break; - - type = fdt_getprop(fdt, node, "device_type", &len); - if (type && strncmp(type, "memory", len) == 0) { - fdt_del_node(fdt, node); - continue; - } - - prev = node; - } - - /* * Delete all memory reserve map entries. When booting via UEFI, * kernel will use the UEFI memory map to find reserved regions. */ diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig index e2a48415d969..b3bec3aaa45d 100644 --- a/drivers/of/Kconfig +++ b/drivers/of/Kconfig @@ -112,4 +112,7 @@ config OF_OVERLAY While this option is selected automatically when needed, you can enable it manually to improve device tree unit test coverage. +config OF_NUMA + bool + endif # OF diff --git a/drivers/of/Makefile b/drivers/of/Makefile index 156c072b3117..bee3fa96b981 100644 --- a/drivers/of/Makefile +++ b/drivers/of/Makefile @@ -14,5 +14,6 @@ obj-$(CONFIG_OF_MTD) += of_mtd.o obj-$(CONFIG_OF_RESERVED_MEM) += of_reserved_mem.o obj-$(CONFIG_OF_RESOLVE) += resolver.o obj-$(CONFIG_OF_OVERLAY) += overlay.o +obj-$(CONFIG_OF_NUMA) += of_numa.o obj-$(CONFIG_OF_UNITTEST) += unittest-data/ diff --git a/drivers/of/of_numa.c b/drivers/of/of_numa.c new file mode 100644 index 000000000000..ed5a097f0801 --- /dev/null +++ b/drivers/of/of_numa.c @@ -0,0 +1,211 @@ +/* + * OF NUMA Parsing support. + * + * Copyright (C) 2015 - 2016 Cavium Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/nodemask.h> + +#include <asm/numa.h> + +/* define default numa node to 0 */ +#define DEFAULT_NODE 0 + +/* + * Even though we connect cpus to numa domains later in SMP + * init, we need to know the node ids now for all cpus. +*/ +static void __init of_numa_parse_cpu_nodes(void) +{ + u32 nid; + int r; + struct device_node *cpus; + struct device_node *np = NULL; + + cpus = of_find_node_by_path("/cpus"); + if (!cpus) + return; + + for_each_child_of_node(cpus, np) { + /* Skip things that are not CPUs */ + if (of_node_cmp(np->type, "cpu") != 0) + continue; + + r = of_property_read_u32(np, "numa-node-id", &nid); + if (r) + continue; + + pr_debug("NUMA: CPU on %u\n", nid); + if (nid >= MAX_NUMNODES) + pr_warn("NUMA: Node id %u exceeds maximum value\n", + nid); + else + node_set(nid, numa_nodes_parsed); + } +} + +static int __init of_numa_parse_memory_nodes(void) +{ + struct device_node *np = NULL; + struct resource rsrc; + u32 nid; + int r = 0; + + for (;;) { + np = of_find_node_by_type(np, "memory"); + if (!np) + break; + + r = of_property_read_u32(np, "numa-node-id", &nid); + if (r == -EINVAL) + /* + * property doesn't exist if -EINVAL, continue + * looking for more memory nodes with + * "numa-node-id" property + */ + continue; + else if (r) + /* some other error */ + break; + + r = of_address_to_resource(np, 0, &rsrc); + if (r) { + pr_err("NUMA: bad reg property in memory node\n"); + break; + } + + 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 + 1); + if (r) + break; + } + of_node_put(np); + + return r; +} + +static int __init of_numa_parse_distance_map_v1(struct device_node *map) +{ + const __be32 *matrix; + int entry_count; + int i; + + pr_info("NUMA: parsing numa-distance-map-v1\n"); + + matrix = of_get_property(map, "distance-matrix", NULL); + if (!matrix) { + pr_err("NUMA: No distance-matrix property in distance-map\n"); + return -EINVAL; + } + + entry_count = of_property_count_u32_elems(map, "distance-matrix"); + if (entry_count <= 0) { + pr_err("NUMA: Invalid distance-matrix\n"); + return -EINVAL; + } + + for (i = 0; i + 2 < entry_count; i += 3) { + u32 nodea, nodeb, distance; + + nodea = of_read_number(matrix, 1); + matrix++; + nodeb = of_read_number(matrix, 1); + matrix++; + distance = of_read_number(matrix, 1); + matrix++; + + numa_set_distance(nodea, nodeb, distance); + pr_debug("NUMA: distance[node%d -> node%d] = %d\n", + nodea, nodeb, distance); + + /* Set default distance of node B->A same as A->B */ + if (nodeb > nodea) + numa_set_distance(nodeb, nodea, distance); + } + + return 0; +} + +static int __init of_numa_parse_distance_map(void) +{ + int ret = 0; + struct device_node *np; + + np = of_find_compatible_node(NULL, NULL, + "numa-distance-map-v1"); + if (np) + ret = of_numa_parse_distance_map_v1(np); + + of_node_put(np); + return ret; +} + +int of_node_to_nid(struct device_node *device) +{ + struct device_node *np; + u32 nid; + int r = -ENODATA; + + np = of_node_get(device); + + while (np) { + struct device_node *parent; + + r = of_property_read_u32(np, "numa-node-id", &nid); + /* + * -EINVAL indicates the property was not found, and + * we walk up the tree trying to find a parent with a + * "numa-node-id". Any other type of error indicates + * a bad device tree and we give up. + */ + if (r != -EINVAL) + break; + + parent = of_get_parent(np); + of_node_put(np); + np = parent; + } + if (np && r) + pr_warn("NUMA: Invalid \"numa-node-id\" property in node %s\n", + np->name); + of_node_put(np); + + if (!r) { + if (nid >= MAX_NUMNODES) + pr_warn("NUMA: Node id %u exceeds maximum value\n", + nid); + else + return nid; + } + + return NUMA_NO_NODE; +} +EXPORT_SYMBOL(of_node_to_nid); + +int __init of_numa_init(void) +{ + int r; + + of_numa_parse_cpu_nodes(); + r = of_numa_parse_memory_nodes(); + if (r) + return r; + return of_numa_parse_distance_map(); +} 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/linux/acpi.h b/include/linux/acpi.h index a1a5ba1c8f99..e7d04c241635 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -239,12 +239,26 @@ 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; diff --git a/include/linux/of.h b/include/linux/of.h index 31758036787c..77ddace575e8 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -685,6 +685,15 @@ static inline int of_node_to_nid(struct device_node *device) } #endif +#ifdef CONFIG_OF_NUMA +extern int of_numa_init(void); +#else +static inline int of_numa_init(void) +{ + return -ENOSYS; +} +#endif + static inline struct device_node *of_find_matching_node( struct device_node *from, const struct of_device_id *matches) |