1 files changed, 61 insertions, 163 deletions

diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c
index 555aee3ee8e7..e18701676426 100644
--- a/drivers/base/arch_numa.c
+++ b/drivers/base/arch_numa.c
@@ -12,16 +12,12 @@
 #include <linux/memblock.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/numa_memblks.h>
 
 #include <asm/sections.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;
 bool numa_off;
 
 static __init int numa_parse_early_param(char *opt)
@@ -30,6 +26,8 @@ static __init int numa_parse_early_param(char *opt)
 		return -EINVAL;
 	if (str_has_prefix(opt, "off"))
 		numa_off = true;
+	if (!strncmp(opt, "fake=", 5))
+		return numa_emu_cmdline(opt + 5);
 
 	return 0;
 }
@@ -61,6 +59,7 @@ EXPORT_SYMBOL(cpumask_of_node);
 
 #endif
 
+#ifndef CONFIG_NUMA_EMU
 static void numa_update_cpu(unsigned int cpu, bool remove)
 {
 	int nid = cpu_to_node(cpu);
@@ -83,6 +82,7 @@ void numa_remove_cpu(unsigned int cpu)
 {
 	numa_update_cpu(cpu, true);
 }
+#endif
 
 void numa_clear_node(unsigned int cpu)
 {
@@ -144,7 +144,7 @@ void __init early_map_cpu_to_node(unsigned int cpu, int nid)
 unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
 EXPORT_SYMBOL(__per_cpu_offset);
 
-int __init early_cpu_to_node(int cpu)
+int early_cpu_to_node(int cpu)
 {
 	return cpu_to_node_map[cpu];
 }
@@ -189,174 +189,24 @@ void __init setup_per_cpu_areas(void)
 }
 #endif
 
-/**
- * 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("memblock [0x%llx - 0x%llx] failed to add on node %d\n",
-			start, (end - 1), nid);
-		return ret;
-	}
-
-	node_set(nid, numa_nodes_parsed);
-	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;
-
 	if (start_pfn >= end_pfn)
 		pr_info("Initmem setup node %d [<memory-less node>]\n", nid);
 
-	nd_pa = memblock_phys_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);
-	if (!nd_pa)
-		panic("Cannot allocate %zu bytes for node %d data\n",
-		      nd_size, nid);
+	alloc_node_data(nid);
 
-	nd = __va(nd_pa);
-
-	/* report and initialize */
-	pr_info("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("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(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;
-	int i, j;
-
-	size = nr_node_ids * nr_node_ids * sizeof(numa_distance[0]);
-	numa_distance = memblock_alloc(size, PAGE_SIZE);
-	if (WARN_ON(!numa_distance))
-		return -ENOMEM;
-
-	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("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("Warning: distance table not allocated yet\n");
-		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;
-}
-
-/*
- * 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_mem_region(mblk) {
-		int mblk_nid = memblock_get_region_node(mblk);
-		phys_addr_t start = mblk->base;
-		phys_addr_t end = mblk->base + mblk->size - 1;
-
-		if (mblk_nid == NUMA_NO_NODE || mblk_nid >= MAX_NUMNODES) {
-			pr_warn("Warning: invalid memblk node %d [mem %pap-%pap]\n",
-				mblk_nid, &start, &end);
-			return -EINVAL;
-		}
-	}
 
 	/* Finally register nodes. */
 	for_each_node_mask(nid, numa_nodes_parsed) {
@@ -381,11 +231,7 @@ static int __init numa_init(int (*init_func)(void))
 	nodes_clear(node_possible_map);
 	nodes_clear(node_online_map);
 
-	ret = numa_alloc_distance();
-	if (ret < 0)
-		return ret;
-
-	ret = init_func();
+	ret = numa_memblks_init(init_func, /* memblock_force_top_down */ false);
 	if (ret < 0)
 		goto out_free_distance;
 
@@ -403,7 +249,7 @@ static int __init numa_init(int (*init_func)(void))
 
 	return 0;
 out_free_distance:
-	numa_free_distance();
+	numa_reset_distance();
 	return ret;
 }
 
@@ -433,6 +279,7 @@ static int __init dummy_numa_init(void)
 		pr_err("NUMA init failed\n");
 		return ret;
 	}
+	node_set(0, numa_nodes_parsed);
 
 	numa_off = true;
 	return 0;
@@ -475,3 +322,54 @@ void __init arch_numa_init(void)
 
 	numa_init(dummy_numa_init);
 }
+
+#ifdef CONFIG_NUMA_EMU
+void __init numa_emu_update_cpu_to_node(int *emu_nid_to_phys,
+					unsigned int nr_emu_nids)
+{
+	int i, j;
+
+	/*
+	 * Transform cpu_to_node_map table to use emulated nids by
+	 * reverse-mapping phys_nid.  The maps should always exist but fall
+	 * back to zero just in case.
+	 */
+	for (i = 0; i < ARRAY_SIZE(cpu_to_node_map); i++) {
+		if (cpu_to_node_map[i] == NUMA_NO_NODE)
+			continue;
+		for (j = 0; j < nr_emu_nids; j++)
+			if (cpu_to_node_map[i] == emu_nid_to_phys[j])
+				break;
+		cpu_to_node_map[i] = j < nr_emu_nids ? j : 0;
+	}
+}
+
+u64 __init numa_emu_dma_end(void)
+{
+	return memblock_start_of_DRAM() + SZ_4G;
+}
+
+void debug_cpumask_set_cpu(unsigned int cpu, int node, bool enable)
+{
+	struct cpumask *mask;
+
+	if (node == NUMA_NO_NODE)
+		return;
+
+	mask = node_to_cpumask_map[node];
+	if (!cpumask_available(mask)) {
+		pr_err("node_to_cpumask_map[%i] NULL\n", node);
+		dump_stack();
+		return;
+	}
+
+	if (enable)
+		cpumask_set_cpu(cpu, mask);
+	else
+		cpumask_clear_cpu(cpu, mask);
+
+	pr_debug("%s cpu %d node %d: mask now %*pbl\n",
+		 enable ? "numa_add_cpu" : "numa_remove_cpu",
+		 cpu, node, cpumask_pr_args(mask));
+}
+#endif /* CONFIG_NUMA_EMU */