1 files changed, 559 insertions, 22 deletions

diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 9559d360fde..f5510d889a2 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -1,11 +1,39 @@
 /* Common code for 32 and 64-bit NUMA */
-#include <linux/topology.h>
-#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <linux/init.h>
 #include <linux/bootmem.h>
-#include <asm/numa.h>
+#include <linux/memblock.h>
+#include <linux/mmzone.h>
+#include <linux/ctype.h>
+#include <linux/module.h>
+#include <linux/nodemask.h>
+#include <linux/sched.h>
+#include <linux/topology.h>
+
+#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"
 
 int __initdata 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
+#ifndef CONFIG_MEMORY_HOTPLUG
+__initdata
+#endif
+;
+
+static int numa_distance_cnt;
+static u8 *numa_distance;
 
 static __init int numa_setup(char *opt)
 {
@@ -32,6 +60,15 @@ s16 __apicid_to_node[MAX_LOCAL_APIC] __cpuinitdata = {
 	[0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
 };
 
+int __cpuinit numa_cpu_node(int cpu)
+{
+	int apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
+
+	if (apicid != BAD_APICID)
+		return __apicid_to_node[apicid];
+	return NUMA_NO_NODE;
+}
+
 cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
 EXPORT_SYMBOL(node_to_cpumask_map);
 
@@ -95,6 +132,407 @@ void __init setup_node_to_cpumask_map(void)
 	pr_debug("Node to cpumask map for %d 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_warning("NUMA: Warning: invalid memblk node %d (%Lx-%Lx)\n",
+			   nid, start, end);
+		return 0;
+	}
+
+	if (mi->nr_blks >= NR_NODE_MEMBLKS) {
+		pr_err("NUMA: 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_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);
+}
+
+/* Initialize NODE_DATA for a node on the local memory */
+static void __init setup_node_data(int nid, u64 start, u64 end)
+{
+	const u64 nd_low = PFN_PHYS(MAX_DMA_PFN);
+	const u64 nd_high = PFN_PHYS(max_pfn_mapped);
+	const size_t nd_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
+	bool remapped = false;
+	u64 nd_pa;
+	void *nd;
+	int tnid;
+
+	/*
+	 * Don't confuse VM with a node that doesn't have the
+	 * minimum amount of memory:
+	 */
+	if (end && (end - start) < NODE_MIN_SIZE)
+		return;
+
+	/* initialize remap allocator before aligning to ZONE_ALIGN */
+	init_alloc_remap(nid, start, end);
+
+	start = roundup(start, ZONE_ALIGN);
+
+	printk(KERN_INFO "Initmem setup node %d %016Lx-%016Lx\n",
+	       nid, start, end);
+
+	/*
+	 * Allocate node data.  Try remap allocator first, node-local
+	 * memory and then any node.  Never allocate in DMA zone.
+	 */
+	nd = alloc_remap(nid, nd_size);
+	if (nd) {
+		nd_pa = __pa(nd);
+		remapped = true;
+	} else {
+		nd_pa = memblock_x86_find_in_range_node(nid, nd_low, nd_high,
+						nd_size, SMP_CACHE_BYTES);
+		if (nd_pa == MEMBLOCK_ERROR)
+			nd_pa = memblock_find_in_range(nd_low, nd_high,
+						nd_size, SMP_CACHE_BYTES);
+		if (nd_pa == MEMBLOCK_ERROR) {
+			pr_err("Cannot find %zu bytes in node %d\n",
+			       nd_size, nid);
+			return;
+		}
+		memblock_x86_reserve_range(nd_pa, nd_pa + nd_size, "NODE_DATA");
+		nd = __va(nd_pa);
+	}
+
+	/* report and initialize */
+	printk(KERN_INFO "  NODE_DATA [%016Lx - %016Lx]%s\n",
+	       nd_pa, nd_pa + nd_size - 1, remapped ? " (remapped)" : "");
+	tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT);
+	if (!remapped && 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_DATA(nid)->node_id = nid;
+	NODE_DATA(nid)->node_start_pfn = start >> PAGE_SHIFT;
+	NODE_DATA(nid)->node_spanned_pages = (end - start) >> PAGE_SHIFT;
+
+	node_set_online(nid);
+}
+
+/**
+ * numa_cleanup_meminfo - Cleanup a numa_meminfo
+ * @mi: numa_meminfo to clean up
+ *
+ * Sanitize @mi by merging and removing unncessary 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];
+
+		/* make sure all blocks are inside the limits */
+		bi->start = max(bi->start, low);
+		bi->end = min(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("NUMA: node %d (%Lx-%Lx) overlaps with node %d (%Lx-%Lx)\n",
+					       bi->nid, bi->start, bi->end,
+					       bj->nid, bj->start, bj->end);
+					return -EINVAL;
+				}
+				pr_warning("NUMA: Warning: node %d (%Lx-%Lx) overlaps with itself (%Lx-%Lx)\n",
+					   bi->nid, bi->start, bi->end,
+					   bj->start, bj->end);
+			}
+
+			/*
+			 * 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 [%Lx,%Lx) + [%Lx,%Lx) -> [%Lx,%Lx)\n",
+			       bi->nid, bi->start, bi->end, bj->start, bj->end,
+			       start, end);
+			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)
+{
+	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_x86_free_range(__pa(numa_distance),
+					__pa(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_find_in_range(0, PFN_PHYS(max_pfn_mapped),
+				      size, PAGE_SIZE);
+	if (phys == MEMBLOCK_ERROR) {
+		pr_warning("NUMA: Warning: can't allocate distance table!\n");
+		/* don't retry until explicitly reset */
+		numa_distance = (void *)1LU;
+		return -ENOMEM;
+	}
+	memblock_x86_reserve_range(phys, phys + size, "NUMA DIST");
+
+	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 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) {
+		printk_once(KERN_DEBUG "NUMA: Debug: distance 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;
+}
+
+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 - (memblock_x86_hole_size(0,
+					PFN_PHYS(max_pfn)) >> PAGE_SHIFT);
+	/* 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;
+}
+
+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++)
+		memblock_x86_register_active_regions(mi->blk[i].nid,
+					mi->blk[i].start >> PAGE_SHIFT,
+					mi->blk[i].end >> PAGE_SHIFT);
+
+	/* for out of order entries */
+	sort_node_map();
+	if (!numa_meminfo_cover_memory(mi))
+		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)
+			setup_node_data(nid, start, end);
+	}
+
+	return 0;
+}
+
 /*
  * There are unfortunately some poorly designed mainboards around that
  * only connect memory to a single CPU. This breaks the 1:1 cpu->node
@@ -102,7 +540,7 @@ void __init setup_node_to_cpumask_map(void)
  * as the number of CPUs is not known yet. We round robin the existing
  * nodes.
  */
-void __init numa_init_array(void)
+static void __init numa_init_array(void)
 {
 	int rr, i;
 
@@ -117,6 +555,95 @@ void __init numa_init_array(void)
 	}
 }
 
+static int __init numa_init(int (*init_func)(void))
+{
+	int i;
+	int ret;
+
+	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));
+	remove_all_active_ranges();
+	numa_reset_distance();
+
+	ret = init_func();
+	if (ret < 0)
+		return ret;
+	ret = numa_cleanup_meminfo(&numa_meminfo);
+	if (ret < 0)
+		return ret;
+
+	numa_emulation(&numa_meminfo, numa_distance_cnt);
+
+	ret = numa_register_memblks(&numa_meminfo);
+	if (ret < 0)
+		return ret;
+
+	for (i = 0; i < nr_cpu_ids; i++) {
+		int nid = early_cpu_to_node(i);
+
+		if (nid == NUMA_NO_NODE)
+			continue;
+		if (!node_online(nid))
+			numa_clear_node(i);
+	}
+	numa_init_array();
+	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 and add memory blocks that cover all
+ * allowed memory.  This function must not fail.
+ */
+static int __init dummy_numa_init(void)
+{
+	printk(KERN_INFO "%s\n",
+	       numa_off ? "NUMA turned off" : "No NUMA configuration found");
+	printk(KERN_INFO "Faking a node at %016Lx-%016Lx\n",
+	       0LLU, PFN_PHYS(max_pfn));
+
+	node_set(0, numa_nodes_parsed);
+	numa_add_memblk(0, 0, PFN_PHYS(max_pfn));
+
+	return 0;
+}
+
+/**
+ * x86_numa_init - Initialize NUMA
+ *
+ * Try each configured NUMA initialization method until one succeeds.  The
+ * last fallback is dummy single node config encomapssing whole memory and
+ * never fails.
+ */
+void __init x86_numa_init(void)
+{
+	if (!numa_off) {
+#ifdef CONFIG_X86_NUMAQ
+		if (!numa_init(numaq_numa_init))
+			return;
+#endif
+#ifdef CONFIG_ACPI_NUMA
+		if (!numa_init(x86_acpi_numa_init))
+			return;
+#endif
+#ifdef CONFIG_AMD_NUMA
+		if (!numa_init(amd_numa_init))
+			return;
+#endif
+	}
+
+	numa_init(dummy_numa_init);
+}
+
 static __init int find_near_online_node(int node)
 {
 	int n, val;
@@ -213,53 +740,48 @@ int early_cpu_to_node(int cpu)
 	return per_cpu(x86_cpu_to_node_map, cpu);
 }
 
-struct cpumask __cpuinit *debug_cpumask_set_cpu(int cpu, int enable)
+void debug_cpumask_set_cpu(int cpu, int node, bool enable)
 {
-	int node = early_cpu_to_node(cpu);
 	struct cpumask *mask;
 	char buf[64];
 
 	if (node == NUMA_NO_NODE) {
 		/* early_cpu_to_node() already emits a warning and trace */
-		return NULL;
+		return;
 	}
 	mask = node_to_cpumask_map[node];
 	if (!mask) {
 		pr_err("node_to_cpumask_map[%i] NULL\n", node);
 		dump_stack();
-		return NULL;
+		return;
 	}
 
+	if (enable)
+		cpumask_set_cpu(cpu, mask);
+	else
+		cpumask_clear_cpu(cpu, mask);
+
 	cpulist_scnprintf(buf, sizeof(buf), mask);
 	printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n",
 		enable ? "numa_add_cpu" : "numa_remove_cpu",
 		cpu, node, buf);
-	return mask;
+	return;
 }
 
 # ifndef CONFIG_NUMA_EMU
-static void __cpuinit numa_set_cpumask(int cpu, int enable)
+static void __cpuinit numa_set_cpumask(int cpu, bool enable)
 {
-	struct cpumask *mask;
-
-	mask = debug_cpumask_set_cpu(cpu, enable);
-	if (!mask)
-		return;
-
-	if (enable)
-		cpumask_set_cpu(cpu, mask);
-	else
-		cpumask_clear_cpu(cpu, mask);
+	debug_cpumask_set_cpu(cpu, early_cpu_to_node(cpu), enable);
 }
 
 void __cpuinit numa_add_cpu(int cpu)
 {
-	numa_set_cpumask(cpu, 1);
+	numa_set_cpumask(cpu, true);
 }
 
 void __cpuinit numa_remove_cpu(int cpu)
 {
-	numa_set_cpumask(cpu, 0);
+	numa_set_cpumask(cpu, false);
 }
 # endif	/* !CONFIG_NUMA_EMU */
 
@@ -287,3 +809,18 @@ const struct cpumask *cpumask_of_node(int node)
 EXPORT_SYMBOL(cpumask_of_node);
 
 #endif	/* !CONFIG_DEBUG_PER_CPU_MAPS */
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+int memory_add_physaddr_to_nid(u64 start)
+{
+	struct numa_meminfo *mi = &numa_meminfo;
+	int nid = mi->blk[0].nid;
+	int i;
+
+	for (i = 0; i < mi->nr_blks; i++)
+		if (mi->blk[i].start <= start && mi->blk[i].end > start)
+			nid = mi->blk[i].nid;
+	return nid;
+}
+EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
+#endif