diff --git a/arch/x86/kernel/e820_64.c b/arch/x86/kernel/e820_64.c
index b74e83b..9f65b4c 100644
--- a/arch/x86/kernel/e820_64.c
+++ b/arch/x86/kernel/e820_64.c
@@ -171,12 +171,13 @@
 }
 
 /*
- * Find a free area in a specific range.
+ * Find a free area with specified alignment in a specific range.
  */
 unsigned long __init find_e820_area(unsigned long start, unsigned long end,
-				    unsigned size)
+				    unsigned size, unsigned long align)
 {
 	int i;
+	unsigned long mask = ~(align - 1);
 
 	for (i = 0; i < e820.nr_map; i++) {
 		struct e820entry *ei = &e820.map[i];
@@ -190,7 +191,8 @@
 			continue;
 		while (bad_addr(&addr, size) && addr+size <= ei->addr+ei->size)
 			;
-		last = PAGE_ALIGN(addr) + size;
+		addr = (addr + align - 1) & mask;
+		last = addr + size;
 		if (last > ei->addr + ei->size)
 			continue;
 		if (last > end)
diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c
index 77fb87b..18df70c 100644
--- a/arch/x86/kernel/setup_64.c
+++ b/arch/x86/kernel/setup_64.c
@@ -182,7 +182,8 @@
 	unsigned long bootmap_size, bootmap;
 
 	bootmap_size = bootmem_bootmap_pages(end_pfn)<<PAGE_SHIFT;
-	bootmap = find_e820_area(0, end_pfn<<PAGE_SHIFT, bootmap_size);
+	bootmap = find_e820_area(0, end_pfn<<PAGE_SHIFT, bootmap_size,
+				 PAGE_SIZE);
 	if (bootmap == -1L)
 		panic("Cannot find bootmem map of size %ld\n", bootmap_size);
 	bootmap_size = init_bootmem(bootmap >> PAGE_SHIFT, end_pfn);
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 9a471be..eabcaed 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -354,17 +354,10 @@
 	 * need roughly 0.5KB per GB.
 	 */
 	start = 0x8000;
-	table_start = find_e820_area(start, end, tables);
+	table_start = find_e820_area(start, end, tables, PAGE_SIZE);
 	if (table_start == -1UL)
 		panic("Cannot find space for the kernel page tables");
 
-	/*
-	 * When you have a lot of RAM like 256GB, early_table will not fit
-	 * into 0x8000 range, find_e820_area() will find area after kernel
-	 * bss but the table_start is not page aligned, so need to round it
-	 * up to avoid overlap with bss:
-	 */
-	table_start = round_up(table_start, PAGE_SIZE);
 	table_start >>= PAGE_SHIFT;
 	table_end = table_start;
 
@@ -420,7 +413,9 @@
 		mmu_cr4_features = read_cr4();
 	__flush_tlb_all();
 
-	reserve_early(table_start << PAGE_SHIFT, table_end << PAGE_SHIFT, "PGTABLE");
+	if (!after_bootmem)
+		reserve_early(table_start << PAGE_SHIFT,
+				 table_end << PAGE_SHIFT, "PGTABLE");
 }
 
 #ifndef CONFIG_NUMA
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index d339548..9f533de 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -84,25 +84,23 @@
 
 static int __init allocate_cachealigned_memnodemap(void)
 {
-	unsigned long pad, pad_addr;
+	unsigned long addr;
 
 	memnodemap = memnode.embedded_map;
 	if (memnodemapsize <= ARRAY_SIZE(memnode.embedded_map))
 		return 0;
 
-	pad = L1_CACHE_BYTES - 1;
-	pad_addr = 0x8000;
-	nodemap_size = pad + sizeof(s16) * memnodemapsize;
-	nodemap_addr = find_e820_area(pad_addr, end_pfn<<PAGE_SHIFT,
-				      nodemap_size);
+	addr = 0x8000;
+	nodemap_size = round_up(sizeof(s16) * memnodemapsize, L1_CACHE_BYTES);
+	nodemap_addr = find_e820_area(addr, end_pfn<<PAGE_SHIFT,
+				      nodemap_size, L1_CACHE_BYTES);
 	if (nodemap_addr == -1UL) {
 		printk(KERN_ERR
 		       "NUMA: Unable to allocate Memory to Node hash map\n");
 		nodemap_addr = nodemap_size = 0;
 		return -1;
 	}
-	pad_addr = (nodemap_addr + pad) & ~pad;
-	memnodemap = phys_to_virt(pad_addr);
+	memnodemap = phys_to_virt(nodemap_addr);
 	reserve_early(nodemap_addr, nodemap_addr + nodemap_size, "MEMNODEMAP");
 
 	printk(KERN_DEBUG "NUMA: Allocated memnodemap from %lx - %lx\n",
@@ -164,15 +162,17 @@
 }
 
 static void * __init early_node_mem(int nodeid, unsigned long start,
-				    unsigned long end, unsigned long size)
+				    unsigned long end, unsigned long size,
+				    unsigned long align)
 {
-	unsigned long mem = find_e820_area(start, end, size);
+	unsigned long mem = find_e820_area(start, end, size, align);
 	void *ptr;
 
-	if (mem != -1L)
+	if (mem != -1L) {
+		mem = round_up(mem, align);
 		return __va(mem);
-	ptr = __alloc_bootmem_nopanic(size,
-				SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS));
+	}
+	ptr = __alloc_bootmem_nopanic(size, align, __pa(MAX_DMA_ADDRESS));
 	if (ptr == NULL) {
 		printk(KERN_ERR "Cannot find %lu bytes in node %d\n",
 		       size, nodeid);
@@ -198,7 +198,8 @@
 	start_pfn = start >> PAGE_SHIFT;
 	end_pfn = end >> PAGE_SHIFT;
 
-	node_data[nodeid] = early_node_mem(nodeid, start, end, pgdat_size);
+	node_data[nodeid] = early_node_mem(nodeid, start, end, pgdat_size,
+					   SMP_CACHE_BYTES);
 	if (node_data[nodeid] == NULL)
 		return;
 	nodedata_phys = __pa(node_data[nodeid]);
@@ -211,8 +212,12 @@
 	/* Find a place for the bootmem map */
 	bootmap_pages = bootmem_bootmap_pages(end_pfn - start_pfn);
 	bootmap_start = round_up(nodedata_phys + pgdat_size, PAGE_SIZE);
+	/*
+	 * SMP_CAHCE_BYTES could be enough, but init_bootmem_node like
+	 * to use that to align to PAGE_SIZE
+	 */
 	bootmap = early_node_mem(nodeid, bootmap_start, end,
-					bootmap_pages<<PAGE_SHIFT);
+				 bootmap_pages<<PAGE_SHIFT, PAGE_SIZE);
 	if (bootmap == NULL)  {
 		if (nodedata_phys < start || nodedata_phys >= end)
 			free_bootmem((unsigned long)node_data[nodeid],
diff --git a/include/asm-x86/e820_64.h b/include/asm-x86/e820_64.h
index cc09469..a560c4f 100644
--- a/include/asm-x86/e820_64.h
+++ b/include/asm-x86/e820_64.h
@@ -15,7 +15,7 @@
 
 #ifndef __ASSEMBLY__
 extern unsigned long find_e820_area(unsigned long start, unsigned long end, 
-				    unsigned size);
+				    unsigned size, unsigned long align);
 extern void add_memory_region(unsigned long start, unsigned long size, 
 			      int type);
 extern void setup_memory_region(void);