1 files changed, 51 insertions, 43 deletions

diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c
index ad091e4cff1..a8f90ce3ded 100644
--- a/arch/x86/mm/numa_emulation.c
+++ b/arch/x86/mm/numa_emulation.c
@@ -5,11 +5,12 @@
 #include <linux/errno.h>
 #include <linux/topology.h>
 #include <linux/memblock.h>
+#include <linux/bootmem.h>
 #include <asm/dma.h>
 
 #include "numa_internal.h"
 
-static int emu_nid_to_phys[MAX_NUMNODES] __cpuinitdata;
+static int emu_nid_to_phys[MAX_NUMNODES];
 static char *emu_cmdline __initdata;
 
 void __init numa_emu_cmdline(char *str)
@@ -27,6 +28,16 @@ static int __init emu_find_memblk_by_nid(int nid, const struct numa_meminfo *mi)
 	return -ENOENT;
 }
 
+static u64 __init mem_hole_size(u64 start, u64 end)
+{
+	unsigned long start_pfn = PFN_UP(start);
+	unsigned long end_pfn = PFN_DOWN(end);
+
+	if (start_pfn < end_pfn)
+		return PFN_PHYS(absent_pages_in_range(start_pfn, end_pfn));
+	return 0;
+}
+
 /*
  * Sets up nid to range from @start to @end.  The return value is -errno if
  * something went wrong, 0 otherwise.
@@ -49,7 +60,7 @@ static int __init emu_setup_memblk(struct numa_meminfo *ei,
 	eb->nid = nid;
 
 	if (emu_nid_to_phys[nid] == NUMA_NO_NODE)
-		emu_nid_to_phys[nid] = pb->nid;
+		emu_nid_to_phys[nid] = nid;
 
 	pb->start += size;
 	if (pb->start >= pb->end) {
@@ -57,8 +68,8 @@ static int __init emu_setup_memblk(struct numa_meminfo *ei,
 		numa_remove_memblk_from(phys_blk, pi);
 	}
 
-	printk(KERN_INFO "Faking node %d at %016Lx-%016Lx (%LuMB)\n", nid,
-	       eb->start, eb->end, (eb->end - eb->start) >> 20);
+	printk(KERN_INFO "Faking node %d at [mem %#018Lx-%#018Lx] (%LuMB)\n",
+	       nid, eb->start, eb->end - 1, (eb->end - eb->start) >> 20);
 	return 0;
 }
 
@@ -84,7 +95,13 @@ static int __init split_nodes_interleave(struct numa_meminfo *ei,
 		nr_nodes = MAX_NUMNODES;
 	}
 
-	size = (max_addr - addr - memblock_x86_hole_size(addr, max_addr)) / nr_nodes;
+	/*
+	 * Calculate target node size.  x86_32 freaks on __udivdi3() so do
+	 * the division in ulong number of pages and convert back.
+	 */
+	size = max_addr - addr - mem_hole_size(addr, max_addr);
+	size = PFN_PHYS((unsigned long)(size >> PAGE_SHIFT) / nr_nodes);
+
 	/*
 	 * Calculate the number of big nodes that can be allocated as a result
 	 * of consolidating the remainder.
@@ -128,8 +145,7 @@ static int __init split_nodes_interleave(struct numa_meminfo *ei,
 			 * Continue to add memory to this fake node if its
 			 * non-reserved memory is less than the per-node size.
 			 */
-			while (end - start -
-			       memblock_x86_hole_size(start, end) < size) {
+			while (end - start - mem_hole_size(start, end) < size) {
 				end += FAKE_NODE_MIN_SIZE;
 				if (end > limit) {
 					end = limit;
@@ -143,7 +159,7 @@ static int __init split_nodes_interleave(struct numa_meminfo *ei,
 			 * this one must extend to the boundary.
 			 */
 			if (end < dma32_end && dma32_end - end -
-			    memblock_x86_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
+			    mem_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
 				end = dma32_end;
 
 			/*
@@ -151,8 +167,7 @@ static int __init split_nodes_interleave(struct numa_meminfo *ei,
 			 * next node, this one must extend to the end of the
 			 * physical node.
 			 */
-			if (limit - end -
-			    memblock_x86_hole_size(end, limit) < size)
+			if (limit - end - mem_hole_size(end, limit) < size)
 				end = limit;
 
 			ret = emu_setup_memblk(ei, pi, nid++ % nr_nodes,
@@ -173,7 +188,7 @@ static u64 __init find_end_of_node(u64 start, u64 max_addr, u64 size)
 {
 	u64 end = start + size;
 
-	while (end - start - memblock_x86_hole_size(start, end) < size) {
+	while (end - start - mem_hole_size(start, end) < size) {
 		end += FAKE_NODE_MIN_SIZE;
 		if (end > max_addr) {
 			end = max_addr;
@@ -204,8 +219,7 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
 	 * creates a uniform distribution of node sizes across the entire
 	 * machine (but not necessarily over physical nodes).
 	 */
-	min_size = (max_addr - addr - memblock_x86_hole_size(addr, max_addr)) /
-						MAX_NUMNODES;
+	min_size = (max_addr - addr - mem_hole_size(addr, max_addr)) / MAX_NUMNODES;
 	min_size = max(min_size, FAKE_NODE_MIN_SIZE);
 	if ((min_size & FAKE_NODE_MIN_HASH_MASK) < min_size)
 		min_size = (min_size + FAKE_NODE_MIN_SIZE) &
@@ -226,7 +240,7 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
 	 */
 	while (nodes_weight(physnode_mask)) {
 		for_each_node_mask(i, physnode_mask) {
-			u64 dma32_end = MAX_DMA32_PFN << PAGE_SHIFT;
+			u64 dma32_end = PFN_PHYS(MAX_DMA32_PFN);
 			u64 start, limit, end;
 			int phys_blk;
 
@@ -245,7 +259,7 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
 			 * this one must extend to the boundary.
 			 */
 			if (end < dma32_end && dma32_end - end -
-			    memblock_x86_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
+			    mem_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
 				end = dma32_end;
 
 			/*
@@ -253,8 +267,7 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
 			 * next node, this one must extend to the end of the
 			 * physical node.
 			 */
-			if (limit - end -
-			    memblock_x86_hole_size(end, limit) < size)
+			if (limit - end - mem_hole_size(end, limit) < size)
 				end = limit;
 
 			ret = emu_setup_memblk(ei, pi, nid++ % MAX_NUMNODES,
@@ -298,7 +311,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 {
 	static struct numa_meminfo ei __initdata;
 	static struct numa_meminfo pi __initdata;
-	const u64 max_addr = max_pfn << PAGE_SHIFT;
+	const u64 max_addr = PFN_PHYS(max_pfn);
 	u8 *phys_dist = NULL;
 	size_t phys_size = numa_dist_cnt * numa_dist_cnt * sizeof(phys_dist[0]);
 	int max_emu_nid, dfl_phys_nid;
@@ -326,9 +339,11 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 	} else {
 		unsigned long n;
 
-		n = simple_strtoul(emu_cmdline, NULL, 0);
+		n = simple_strtoul(emu_cmdline, &emu_cmdline, 0);
 		ret = split_nodes_interleave(&ei, &pi, 0, max_addr, n);
 	}
+	if (*emu_cmdline == ':')
+		emu_cmdline++;
 
 	if (ret < 0)
 		goto no_emu;
@@ -342,14 +357,13 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 	if (numa_dist_cnt) {
 		u64 phys;
 
-		phys = memblock_find_in_range(0,
-					      (u64)max_pfn_mapped << PAGE_SHIFT,
+		phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
 					      phys_size, PAGE_SIZE);
-		if (phys == MEMBLOCK_ERROR) {
+		if (!phys) {
 			pr_warning("NUMA: Warning: can't allocate copy of distance table, disabling emulation\n");
 			goto no_emu;
 		}
-		memblock_x86_reserve_range(phys, phys + phys_size, "TMP NUMA DIST");
+		memblock_reserve(phys, phys_size);
 		phys_dist = __va(phys);
 
 		for (i = 0; i < numa_dist_cnt; i++)
@@ -406,7 +420,9 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 			int physj = emu_nid_to_phys[j];
 			int dist;
 
-			if (physi >= numa_dist_cnt || physj >= numa_dist_cnt)
+			if (get_option(&emu_cmdline, &dist) == 2)
+				;
+			else if (physi >= numa_dist_cnt || physj >= numa_dist_cnt)
 				dist = physi == physj ?
 					LOCAL_DISTANCE : REMOTE_DISTANCE;
 			else
@@ -418,7 +434,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 
 	/* free the copied physical distance table */
 	if (phys_dist)
-		memblock_x86_free_range(__pa(phys_dist), __pa(phys_dist) + phys_size);
+		memblock_free(__pa(phys_dist), phys_size);
 	return;
 
 no_emu:
@@ -428,7 +444,7 @@ no_emu:
 }
 
 #ifndef CONFIG_DEBUG_PER_CPU_MAPS
-void __cpuinit numa_add_cpu(int cpu)
+void numa_add_cpu(int cpu)
 {
 	int physnid, nid;
 
@@ -446,7 +462,7 @@ void __cpuinit numa_add_cpu(int cpu)
 			cpumask_set_cpu(cpu, node_to_cpumask_map[nid]);
 }
 
-void __cpuinit numa_remove_cpu(int cpu)
+void numa_remove_cpu(int cpu)
 {
 	int i;
 
@@ -454,10 +470,9 @@ void __cpuinit numa_remove_cpu(int cpu)
 		cpumask_clear_cpu(cpu, node_to_cpumask_map[i]);
 }
 #else	/* !CONFIG_DEBUG_PER_CPU_MAPS */
-static void __cpuinit numa_set_cpumask(int cpu, int enable)
+static void numa_set_cpumask(int cpu, bool enable)
 {
-	struct cpumask *mask;
-	int nid, physnid, i;
+	int nid, physnid;
 
 	nid = early_cpu_to_node(cpu);
 	if (nid == NUMA_NO_NODE) {
@@ -467,28 +482,21 @@ static void __cpuinit numa_set_cpumask(int cpu, int enable)
 
 	physnid = emu_nid_to_phys[nid];
 
-	for_each_online_node(i) {
+	for_each_online_node(nid) {
 		if (emu_nid_to_phys[nid] != physnid)
 			continue;
 
-		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, nid, enable);
 	}
 }
 
-void __cpuinit numa_add_cpu(int cpu)
+void numa_add_cpu(int cpu)
 {
-	numa_set_cpumask(cpu, 1);
+	numa_set_cpumask(cpu, true);
 }
 
-void __cpuinit numa_remove_cpu(int cpu)
+void numa_remove_cpu(int cpu)
 {
-	numa_set_cpumask(cpu, 0);
+	numa_set_cpumask(cpu, false);
 }
 #endif	/* !CONFIG_DEBUG_PER_CPU_MAPS */