diff options
Diffstat (limited to 'arch/x86/mm/numa.c')
-rw-r--r-- | arch/x86/mm/numa.c | 600 |
1 files changed, 46 insertions, 554 deletions
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index e8b061557887..c24890c40138 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -3,6 +3,7 @@ #include <linux/acpi.h> #include <linux/kernel.h> #include <linux/mm.h> +#include <linux/of.h> #include <linux/string.h> #include <linux/init.h> #include <linux/memblock.h> @@ -11,25 +12,18 @@ #include <linux/nodemask.h> #include <linux/sched.h> #include <linux/topology.h> +#include <linux/sort.h> +#include <linux/numa_memblks.h> #include <asm/e820/api.h> #include <asm/proto.h> #include <asm/dma.h> -#include <asm/amd_nb.h> +#include <asm/numa.h> +#include <asm/amd/nb.h> -#include "numa_internal.h" +#include "mm_internal.h" int numa_off; -nodemask_t numa_nodes_parsed __initdata; - -struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; -EXPORT_SYMBOL(node_data); - -static struct numa_meminfo numa_meminfo __initdata_or_meminfo; -static struct numa_meminfo numa_reserved_meminfo __initdata_or_meminfo; - -static int numa_distance_cnt; -static u8 *numa_distance; static __init int numa_setup(char *opt) { @@ -56,7 +50,7 @@ s16 __apicid_to_node[MAX_LOCAL_APIC] = { int numa_cpu_node(int cpu) { - int apicid = early_per_cpu(x86_cpu_to_apicid, cpu); + u32 apicid = early_per_cpu(x86_cpu_to_apicid, cpu); if (apicid != BAD_APICID) return __apicid_to_node[apicid]; @@ -122,493 +116,27 @@ void __init setup_node_to_cpumask_map(void) pr_debug("Node to cpumask map for %u nodes\n", nr_node_ids); } -static int __init numa_add_memblk_to(int nid, u64 start, u64 end, - struct numa_meminfo *mi) -{ - /* ignore zero length blks */ - if (start == end) - return 0; - - /* whine about and ignore invalid blks */ - if (start > end || nid < 0 || nid >= MAX_NUMNODES) { - pr_warn("Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n", - nid, start, end - 1); - return 0; - } - - if (mi->nr_blks >= NR_NODE_MEMBLKS) { - pr_err("too many memblk ranges\n"); - return -EINVAL; - } - - mi->blk[mi->nr_blks].start = start; - mi->blk[mi->nr_blks].end = end; - mi->blk[mi->nr_blks].nid = nid; - mi->nr_blks++; - return 0; -} - -/** - * numa_remove_memblk_from - Remove one numa_memblk from a numa_meminfo - * @idx: Index of memblk to remove - * @mi: numa_meminfo to remove memblk from - * - * Remove @idx'th numa_memblk from @mi by shifting @mi->blk[] and - * decrementing @mi->nr_blks. - */ -void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi) -{ - mi->nr_blks--; - memmove(&mi->blk[idx], &mi->blk[idx + 1], - (mi->nr_blks - idx) * sizeof(mi->blk[0])); -} - -/** - * numa_move_tail_memblk - Move a numa_memblk from one numa_meminfo to another - * @dst: numa_meminfo to append block to - * @idx: Index of memblk to remove - * @src: numa_meminfo to remove memblk from - */ -static void __init numa_move_tail_memblk(struct numa_meminfo *dst, int idx, - struct numa_meminfo *src) -{ - dst->blk[dst->nr_blks++] = src->blk[idx]; - numa_remove_memblk_from(idx, src); -} - -/** - * numa_add_memblk - Add one numa_memblk to numa_meminfo - * @nid: NUMA node ID of the new memblk - * @start: Start address of the new memblk - * @end: End address of the new memblk - * - * Add a new memblk to the default numa_meminfo. - * - * RETURNS: - * 0 on success, -errno on failure. - */ -int __init numa_add_memblk(int nid, u64 start, u64 end) -{ - return numa_add_memblk_to(nid, start, end, &numa_meminfo); -} - -/* Allocate NODE_DATA for a node on the local memory */ -static void __init alloc_node_data(int nid) -{ - const size_t nd_size = roundup(sizeof(pg_data_t), PAGE_SIZE); - u64 nd_pa; - void *nd; - int tnid; - - /* - * Allocate node data. Try node-local memory and then any node. - * Never allocate in DMA zone. - */ - nd_pa = memblock_phys_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); - if (!nd_pa) { - pr_err("Cannot find %zu bytes in any node (initial node: %d)\n", - nd_size, nid); - return; - } - nd = __va(nd_pa); - - /* report and initialize */ - printk(KERN_INFO "NODE_DATA(%d) allocated [mem %#010Lx-%#010Lx]\n", nid, - nd_pa, nd_pa + nd_size - 1); - tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT); - if (tnid != nid) - printk(KERN_INFO " NODE_DATA(%d) on node %d\n", nid, tnid); - - node_data[nid] = nd; - memset(NODE_DATA(nid), 0, sizeof(pg_data_t)); - - node_set_online(nid); -} - -/** - * numa_cleanup_meminfo - Cleanup a numa_meminfo - * @mi: numa_meminfo to clean up - * - * Sanitize @mi by merging and removing unnecessary memblks. Also check for - * conflicts and clear unused memblks. - * - * RETURNS: - * 0 on success, -errno on failure. - */ -int __init numa_cleanup_meminfo(struct numa_meminfo *mi) -{ - const u64 low = 0; - const u64 high = PFN_PHYS(max_pfn); - int i, j, k; - - /* first, trim all entries */ - for (i = 0; i < mi->nr_blks; i++) { - struct numa_memblk *bi = &mi->blk[i]; - - /* move / save reserved memory ranges */ - if (!memblock_overlaps_region(&memblock.memory, - bi->start, bi->end - bi->start)) { - numa_move_tail_memblk(&numa_reserved_meminfo, i--, mi); - continue; - } - - /* make sure all non-reserved blocks are inside the limits */ - bi->start = max(bi->start, low); - - /* preserve info for non-RAM areas above 'max_pfn': */ - if (bi->end > high) { - numa_add_memblk_to(bi->nid, high, bi->end, - &numa_reserved_meminfo); - bi->end = high; - } - - /* and there's no empty block */ - if (bi->start >= bi->end) - numa_remove_memblk_from(i--, mi); - } - - /* merge neighboring / overlapping entries */ - for (i = 0; i < mi->nr_blks; i++) { - struct numa_memblk *bi = &mi->blk[i]; - - for (j = i + 1; j < mi->nr_blks; j++) { - struct numa_memblk *bj = &mi->blk[j]; - u64 start, end; - - /* - * See whether there are overlapping blocks. Whine - * about but allow overlaps of the same nid. They - * will be merged below. - */ - if (bi->end > bj->start && bi->start < bj->end) { - if (bi->nid != bj->nid) { - pr_err("node %d [mem %#010Lx-%#010Lx] overlaps with node %d [mem %#010Lx-%#010Lx]\n", - bi->nid, bi->start, bi->end - 1, - bj->nid, bj->start, bj->end - 1); - return -EINVAL; - } - pr_warn("Warning: node %d [mem %#010Lx-%#010Lx] overlaps with itself [mem %#010Lx-%#010Lx]\n", - bi->nid, bi->start, bi->end - 1, - bj->start, bj->end - 1); - } - - /* - * Join together blocks on the same node, holes - * between which don't overlap with memory on other - * nodes. - */ - if (bi->nid != bj->nid) - continue; - start = min(bi->start, bj->start); - end = max(bi->end, bj->end); - for (k = 0; k < mi->nr_blks; k++) { - struct numa_memblk *bk = &mi->blk[k]; - - if (bi->nid == bk->nid) - continue; - if (start < bk->end && end > bk->start) - break; - } - if (k < mi->nr_blks) - continue; - printk(KERN_INFO "NUMA: Node %d [mem %#010Lx-%#010Lx] + [mem %#010Lx-%#010Lx] -> [mem %#010Lx-%#010Lx]\n", - bi->nid, bi->start, bi->end - 1, bj->start, - bj->end - 1, start, end - 1); - bi->start = start; - bi->end = end; - numa_remove_memblk_from(j--, mi); - } - } - - /* clear unused ones */ - for (i = mi->nr_blks; i < ARRAY_SIZE(mi->blk); i++) { - mi->blk[i].start = mi->blk[i].end = 0; - mi->blk[i].nid = NUMA_NO_NODE; - } - - return 0; -} - -/* - * Set nodes, which have memory in @mi, in *@nodemask. - */ -static void __init numa_nodemask_from_meminfo(nodemask_t *nodemask, - const struct numa_meminfo *mi) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(mi->blk); i++) - if (mi->blk[i].start != mi->blk[i].end && - mi->blk[i].nid != NUMA_NO_NODE) - node_set(mi->blk[i].nid, *nodemask); -} - -/** - * numa_reset_distance - Reset NUMA distance table - * - * The current table is freed. The next numa_set_distance() call will - * create a new one. - */ -void __init numa_reset_distance(void) +static int __init numa_register_nodes(void) { - size_t size = numa_distance_cnt * numa_distance_cnt * sizeof(numa_distance[0]); - - /* numa_distance could be 1LU marking allocation failure, test cnt */ - if (numa_distance_cnt) - memblock_free(numa_distance, size); - numa_distance_cnt = 0; - numa_distance = NULL; /* enable table creation */ -} - -static int __init numa_alloc_distance(void) -{ - nodemask_t nodes_parsed; - size_t size; - int i, j, cnt = 0; - u64 phys; - - /* size the new table and allocate it */ - nodes_parsed = numa_nodes_parsed; - numa_nodemask_from_meminfo(&nodes_parsed, &numa_meminfo); - - for_each_node_mask(i, nodes_parsed) - cnt = i; - cnt++; - size = cnt * cnt * sizeof(numa_distance[0]); - - phys = memblock_phys_alloc_range(size, PAGE_SIZE, 0, - PFN_PHYS(max_pfn_mapped)); - if (!phys) { - pr_warn("Warning: can't allocate distance table!\n"); - /* don't retry until explicitly reset */ - numa_distance = (void *)1LU; - return -ENOMEM; - } - - numa_distance = __va(phys); - numa_distance_cnt = cnt; - - /* fill with the default distances */ - for (i = 0; i < cnt; i++) - for (j = 0; j < cnt; j++) - numa_distance[i * cnt + j] = i == j ? - LOCAL_DISTANCE : REMOTE_DISTANCE; - printk(KERN_DEBUG "NUMA: Initialized distance table, cnt=%d\n", cnt); - - return 0; -} - -/** - * numa_set_distance - Set NUMA distance from one NUMA to another - * @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, one which is large enough to accommodate all the currently - * known nodes will be created. - * - * If such table cannot be allocated, a warning is printed and further - * calls are ignored until the distance table is reset with - * numa_reset_distance(). - * - * If @from or @to is higher than the highest known node or lower than zero - * at the time of table creation or @distance doesn't make sense, the call - * is ignored. - * This is to allow simplification of specific NUMA config implementations. - */ -void __init numa_set_distance(int from, int to, int distance) -{ - if (!numa_distance && numa_alloc_distance() < 0) - return; - - if (from >= numa_distance_cnt || to >= numa_distance_cnt || - from < 0 || to < 0) { - pr_warn_once("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("Warning: invalid distance parameter, from=%d to=%d distance=%d\n", - from, to, distance); - return; - } - - numa_distance[from * numa_distance_cnt + to] = distance; -} - -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); - -/* - * Sanity check to catch more bad NUMA configurations (they are amazingly - * common). Make sure the nodes cover all memory. - */ -static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi) -{ - u64 numaram, e820ram; - int i; - - numaram = 0; - for (i = 0; i < mi->nr_blks; i++) { - u64 s = mi->blk[i].start >> PAGE_SHIFT; - u64 e = mi->blk[i].end >> PAGE_SHIFT; - numaram += e - s; - numaram -= __absent_pages_in_range(mi->blk[i].nid, s, e); - if ((s64)numaram < 0) - numaram = 0; - } - - e820ram = max_pfn - absent_pages_in_range(0, max_pfn); - - /* We seem to lose 3 pages somewhere. Allow 1M of slack. */ - if ((s64)(e820ram - numaram) >= (1 << (20 - PAGE_SHIFT))) { - printk(KERN_ERR "NUMA: nodes only cover %LuMB of your %LuMB e820 RAM. Not used.\n", - (numaram << PAGE_SHIFT) >> 20, - (e820ram << PAGE_SHIFT) >> 20); - return false; - } - return true; -} - -/* - * Mark all currently memblock-reserved physical memory (which covers the - * kernel's own memory ranges) as hot-unswappable. - */ -static void __init numa_clear_kernel_node_hotplug(void) -{ - nodemask_t reserved_nodemask = NODE_MASK_NONE; - struct memblock_region *mb_region; - int i; - - /* - * We have to do some preprocessing of memblock regions, to - * make them suitable for reservation. - * - * At this time, all memory regions reserved by memblock are - * used by the kernel, but those regions are not split up - * along node boundaries yet, and don't necessarily have their - * node ID set yet either. - * - * So iterate over all memory known to the x86 architecture, - * and use those ranges to set the nid in memblock.reserved. - * This will split up the memblock regions along node - * boundaries and will set the node IDs as well. - */ - for (i = 0; i < numa_meminfo.nr_blks; i++) { - struct numa_memblk *mb = numa_meminfo.blk + i; - int ret; - - ret = memblock_set_node(mb->start, mb->end - mb->start, &memblock.reserved, mb->nid); - WARN_ON_ONCE(ret); - } - - /* - * Now go over all reserved memblock regions, to construct a - * node mask of all kernel reserved memory areas. - * - * [ Note, when booting with mem=nn[kMG] or in a kdump kernel, - * numa_meminfo might not include all memblock.reserved - * memory ranges, because quirks such as trim_snb_memory() - * reserve specific pages for Sandy Bridge graphics. ] - */ - for_each_reserved_mem_region(mb_region) { - int nid = memblock_get_region_node(mb_region); - - if (nid != MAX_NUMNODES) - node_set(nid, reserved_nodemask); - } - - /* - * Finally, clear the MEMBLOCK_HOTPLUG flag for all memory - * belonging to the reserved node mask. - * - * Note that this will include memory regions that reside - * on nodes that contain kernel memory - entire nodes - * become hot-unpluggable: - */ - for (i = 0; i < numa_meminfo.nr_blks; i++) { - struct numa_memblk *mb = numa_meminfo.blk + i; - - if (!node_isset(mb->nid, reserved_nodemask)) - continue; - - memblock_clear_hotplug(mb->start, mb->end - mb->start); - } -} - -static int __init numa_register_memblks(struct numa_meminfo *mi) -{ - int i, nid; - - /* Account for nodes with cpus and no memory */ - node_possible_map = numa_nodes_parsed; - numa_nodemask_from_meminfo(&node_possible_map, mi); - if (WARN_ON(nodes_empty(node_possible_map))) - return -EINVAL; - - for (i = 0; i < mi->nr_blks; i++) { - struct numa_memblk *mb = &mi->blk[i]; - memblock_set_node(mb->start, mb->end - mb->start, - &memblock.memory, mb->nid); - } - - /* - * At very early time, the kernel have to use some memory such as - * loading the kernel image. We cannot prevent this anyway. So any - * node the kernel resides in should be un-hotpluggable. - * - * And when we come here, alloc node data won't fail. - */ - numa_clear_kernel_node_hotplug(); + int nid; - /* - * If sections array is gonna be used for pfn -> nid mapping, check - * whether its granularity is fine enough. - */ - if (IS_ENABLED(NODE_NOT_IN_PAGE_FLAGS)) { - unsigned long pfn_align = node_map_pfn_alignment(); - - if (pfn_align && pfn_align < PAGES_PER_SECTION) { - pr_warn("Node alignment %LuMB < min %LuMB, rejecting NUMA config\n", - PFN_PHYS(pfn_align) >> 20, - PFN_PHYS(PAGES_PER_SECTION) >> 20); - return -EINVAL; - } - } - if (!numa_meminfo_cover_memory(mi)) + if (!memblock_validate_numa_coverage(SZ_1M)) return -EINVAL; /* Finally register nodes. */ for_each_node_mask(nid, node_possible_map) { - u64 start = PFN_PHYS(max_pfn); - u64 end = 0; - - for (i = 0; i < mi->nr_blks; i++) { - if (nid != mi->blk[i].nid) - continue; - start = min(mi->blk[i].start, start); - end = max(mi->blk[i].end, end); - } - - if (start >= end) - continue; + unsigned long start_pfn, end_pfn; /* - * Don't confuse VM with a node that doesn't have the - * minimum amount of memory: + * Note, get_pfn_range_for_nid() depends on + * memblock_set_node() having already happened */ - if (end && (end - start) < NODE_MIN_SIZE) + get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); + if (start_pfn >= end_pfn) continue; alloc_node_data(nid); + node_set_online(nid); } /* Dump memblock with node info and return. */ @@ -644,39 +172,11 @@ static int __init numa_init(int (*init_func)(void)) for (i = 0; i < MAX_LOCAL_APIC; i++) set_apicid_to_node(i, NUMA_NO_NODE); - nodes_clear(numa_nodes_parsed); - nodes_clear(node_possible_map); - nodes_clear(node_online_map); - memset(&numa_meminfo, 0, sizeof(numa_meminfo)); - WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.memory, - MAX_NUMNODES)); - WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.reserved, - MAX_NUMNODES)); - /* In case that parsing SRAT failed. */ - WARN_ON(memblock_clear_hotplug(0, ULLONG_MAX)); - numa_reset_distance(); - - ret = init_func(); - if (ret < 0) - return ret; - - /* - * We reset memblock back to the top-down direction - * here because if we configured ACPI_NUMA, we have - * parsed SRAT in init_func(). It is ok to have the - * reset here even if we did't configure ACPI_NUMA - * or acpi numa init fails and fallbacks to dummy - * numa init. - */ - memblock_set_bottom_up(false); - - ret = numa_cleanup_meminfo(&numa_meminfo); + ret = numa_memblks_init(init_func, /* memblock_force_top_down */ true); if (ret < 0) return ret; - numa_emulation(&numa_meminfo, numa_distance_cnt); - - ret = numa_register_memblks(&numa_meminfo); + ret = numa_register_nodes(); if (ret < 0) return ret; @@ -733,6 +233,8 @@ void __init x86_numa_init(void) if (!numa_init(amd_numa_init)) return; #endif + if (acpi_disabled && !numa_init(of_numa_init)) + return; } numa_init(dummy_numa_init); @@ -786,7 +288,7 @@ void __init init_gi_nodes(void) void __init init_cpu_to_node(void) { int cpu; - u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid); + u32 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid); BUG_ON(cpu_to_apicid == NULL); @@ -815,12 +317,12 @@ void __init init_cpu_to_node(void) #ifndef CONFIG_DEBUG_PER_CPU_MAPS # ifndef CONFIG_NUMA_EMU -void numa_add_cpu(int cpu) +void numa_add_cpu(unsigned int cpu) { cpumask_set_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]); } -void numa_remove_cpu(int cpu) +void numa_remove_cpu(unsigned int cpu) { cpumask_clear_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]); } @@ -858,7 +360,7 @@ int early_cpu_to_node(int cpu) return per_cpu(x86_cpu_to_node_map, cpu); } -void debug_cpumask_set_cpu(int cpu, int node, bool enable) +void debug_cpumask_set_cpu(unsigned int cpu, int node, bool enable) { struct cpumask *mask; @@ -867,7 +369,7 @@ void debug_cpumask_set_cpu(int cpu, int node, bool enable) return; } mask = node_to_cpumask_map[node]; - if (!mask) { + if (!cpumask_available(mask)) { pr_err("node_to_cpumask_map[%i] NULL\n", node); dump_stack(); return; @@ -890,12 +392,12 @@ static void numa_set_cpumask(int cpu, bool enable) debug_cpumask_set_cpu(cpu, early_cpu_to_node(cpu), enable); } -void numa_add_cpu(int cpu) +void numa_add_cpu(unsigned int cpu) { numa_set_cpumask(cpu, true); } -void numa_remove_cpu(int cpu) +void numa_remove_cpu(unsigned int cpu) { numa_set_cpumask(cpu, false); } @@ -913,7 +415,7 @@ const struct cpumask *cpumask_of_node(int node) dump_stack(); return cpu_none_mask; } - if (node_to_cpumask_map[node] == NULL) { + if (!cpumask_available(node_to_cpumask_map[node])) { printk(KERN_WARNING "cpumask_of_node(%d): no node_to_cpumask_map!\n", node); @@ -926,39 +428,29 @@ EXPORT_SYMBOL(cpumask_of_node); #endif /* !CONFIG_DEBUG_PER_CPU_MAPS */ -#ifdef CONFIG_NUMA_KEEP_MEMINFO -static int meminfo_to_nid(struct numa_meminfo *mi, u64 start) -{ - int i; - - for (i = 0; i < mi->nr_blks; i++) - if (mi->blk[i].start <= start && mi->blk[i].end > start) - return mi->blk[i].nid; - return NUMA_NO_NODE; -} - -int phys_to_target_node(phys_addr_t start) +#ifdef CONFIG_NUMA_EMU +void __init numa_emu_update_cpu_to_node(int *emu_nid_to_phys, + unsigned int nr_emu_nids) { - int nid = meminfo_to_nid(&numa_meminfo, start); + int i, j; /* - * Prefer online nodes, but if reserved memory might be - * hot-added continue the search with reserved ranges. + * Transform __apicid_to_node table to use emulated nids by + * reverse-mapping phys_nid. The maps should always exist but fall + * back to zero just in case. */ - if (nid != NUMA_NO_NODE) - return nid; - - return meminfo_to_nid(&numa_reserved_meminfo, start); + for (i = 0; i < ARRAY_SIZE(__apicid_to_node); i++) { + if (__apicid_to_node[i] == NUMA_NO_NODE) + continue; + for (j = 0; j < nr_emu_nids; j++) + if (__apicid_to_node[i] == emu_nid_to_phys[j]) + break; + __apicid_to_node[i] = j < nr_emu_nids ? j : 0; + } } -EXPORT_SYMBOL_GPL(phys_to_target_node); -int memory_add_physaddr_to_nid(u64 start) +u64 __init numa_emu_dma_end(void) { - int nid = meminfo_to_nid(&numa_meminfo, start); - - if (nid == NUMA_NO_NODE) - nid = numa_meminfo.blk[0].nid; - return nid; + return PFN_PHYS(MAX_DMA32_PFN); } -EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); -#endif +#endif /* CONFIG_NUMA_EMU */ |