1 files changed, 340 insertions, 113 deletions

diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 7a9b788c6ce..16b58ff11e6 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -47,6 +47,7 @@
 #include <asm/prom.h>
 #include <asm/mdesc.h>
 #include <asm/cpudata.h>
+#include <asm/setup.h>
 #include <asm/irq.h>
 
 #include "init_64.h"
@@ -87,8 +88,8 @@ static unsigned long cpu_pgsz_mask;
 
 #define MAX_BANKS	32
 
-static struct linux_prom64_registers pavail[MAX_BANKS] __devinitdata;
-static int pavail_ents __devinitdata;
+static struct linux_prom64_registers pavail[MAX_BANKS];
+static int pavail_ents;
 
 static int cmp_p64(const void *a, const void *b)
 {
@@ -276,7 +277,6 @@ static inline void tsb_insert(struct tsb *ent, unsigned long tag, unsigned long
 }
 
 unsigned long _PAGE_ALL_SZ_BITS __read_mostly;
-unsigned long _PAGE_SZBITS __read_mostly;
 
 static void flush_dcache(unsigned long pfn)
 {
@@ -307,12 +307,39 @@ static void flush_dcache(unsigned long pfn)
 	}
 }
 
+/* mm->context.lock must be held */
+static void __update_mmu_tsb_insert(struct mm_struct *mm, unsigned long tsb_index,
+				    unsigned long tsb_hash_shift, unsigned long address,
+				    unsigned long tte)
+{
+	struct tsb *tsb = mm->context.tsb_block[tsb_index].tsb;
+	unsigned long tag;
+
+	if (unlikely(!tsb))
+		return;
+
+	tsb += ((address >> tsb_hash_shift) &
+		(mm->context.tsb_block[tsb_index].tsb_nentries - 1UL));
+	tag = (address >> 22UL);
+	tsb_insert(tsb, tag, tte);
+}
+
+#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
+static inline bool is_hugetlb_pte(pte_t pte)
+{
+	if ((tlb_type == hypervisor &&
+	     (pte_val(pte) & _PAGE_SZALL_4V) == _PAGE_SZHUGE_4V) ||
+	    (tlb_type != hypervisor &&
+	     (pte_val(pte) & _PAGE_SZALL_4U) == _PAGE_SZHUGE_4U))
+		return true;
+	return false;
+}
+#endif
+
 void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep)
 {
 	struct mm_struct *mm;
-	struct tsb *tsb;
-	unsigned long tag, flags;
-	unsigned long tsb_index, tsb_hash_shift;
+	unsigned long flags;
 	pte_t pte = *ptep;
 
 	if (tlb_type != hypervisor) {
@@ -324,28 +351,16 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *
 
 	mm = vma->vm_mm;
 
-	tsb_index = MM_TSB_BASE;
-	tsb_hash_shift = PAGE_SHIFT;
-
 	spin_lock_irqsave(&mm->context.lock, flags);
 
-#ifdef CONFIG_HUGETLB_PAGE
-	if (mm->context.tsb_block[MM_TSB_HUGE].tsb != NULL) {
-		if ((tlb_type == hypervisor &&
-		     (pte_val(pte) & _PAGE_SZALL_4V) == _PAGE_SZHUGE_4V) ||
-		    (tlb_type != hypervisor &&
-		     (pte_val(pte) & _PAGE_SZALL_4U) == _PAGE_SZHUGE_4U)) {
-			tsb_index = MM_TSB_HUGE;
-			tsb_hash_shift = HPAGE_SHIFT;
-		}
-	}
+#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
+	if (mm->context.huge_pte_count && is_hugetlb_pte(pte))
+		__update_mmu_tsb_insert(mm, MM_TSB_HUGE, REAL_HPAGE_SHIFT,
+					address, pte_val(pte));
+	else
 #endif
-
-	tsb = mm->context.tsb_block[tsb_index].tsb;
-	tsb += ((address >> tsb_hash_shift) &
-		(mm->context.tsb_block[tsb_index].tsb_nentries - 1UL));
-	tag = (address >> 22UL);
-	tsb_insert(tsb, tag, pte_val(pte));
+		__update_mmu_tsb_insert(mm, MM_TSB_BASE, PAGE_SHIFT,
+					address, pte_val(pte));
 
 	spin_unlock_irqrestore(&mm->context.lock, flags);
 }
@@ -574,7 +589,7 @@ static void __init remap_kernel(void)
 	int i, tlb_ent = sparc64_highest_locked_tlbent();
 
 	tte_vaddr = (unsigned long) KERNBASE;
-	phys_page = (prom_boot_mapping_phys_low >> 22UL) << 22UL;
+	phys_page = (prom_boot_mapping_phys_low >> ILOG2_4MB) << ILOG2_4MB;
 	tte_data = kern_large_tte(phys_page);
 
 	kern_locked_tte_data = tte_data;
@@ -616,7 +631,7 @@ static void __init inherit_prom_mappings(void)
 void prom_world(int enter)
 {
 	if (!enter)
-		set_fs((mm_segment_t) { get_thread_current_ds() });
+		set_fs(get_fs());
 
 	__asm__ __volatile__("flushw");
 }
@@ -667,10 +682,9 @@ void get_new_mmu_context(struct mm_struct *mm)
 {
 	unsigned long ctx, new_ctx;
 	unsigned long orig_pgsz_bits;
-	unsigned long flags;
 	int new_version;
 
-	spin_lock_irqsave(&ctx_alloc_lock, flags);
+	spin_lock(&ctx_alloc_lock);
 	orig_pgsz_bits = (mm->context.sparc64_ctx_val & CTX_PGSZ_MASK);
 	ctx = (tlb_context_cache + 1) & CTX_NR_MASK;
 	new_ctx = find_next_zero_bit(mmu_context_bmap, 1 << CTX_NR_BITS, ctx);
@@ -706,7 +720,7 @@ void get_new_mmu_context(struct mm_struct *mm)
 out:
 	tlb_context_cache = new_ctx;
 	mm->context.sparc64_ctx_val = new_ctx | orig_pgsz_bits;
-	spin_unlock_irqrestore(&ctx_alloc_lock, flags);
+	spin_unlock(&ctx_alloc_lock);
 
 	if (unlikely(new_version))
 		smp_new_mmu_context_version();
@@ -781,11 +795,11 @@ struct node_mem_mask {
 static struct node_mem_mask node_masks[MAX_NUMNODES];
 static int num_node_masks;
 
+#ifdef CONFIG_NEED_MULTIPLE_NODES
+
 int numa_cpu_lookup_table[NR_CPUS];
 cpumask_t numa_cpumask_lookup_table[MAX_NUMNODES];
 
-#ifdef CONFIG_NEED_MULTIPLE_NODES
-
 struct mdesc_mblock {
 	u64	base;
 	u64	size;
@@ -874,17 +888,21 @@ static void __init allocate_node_data(int nid)
 
 static void init_node_masks_nonnuma(void)
 {
+#ifdef CONFIG_NEED_MULTIPLE_NODES
 	int i;
+#endif
 
 	numadbg("Initializing tables for non-numa.\n");
 
 	node_masks[0].mask = node_masks[0].val = 0;
 	num_node_masks = 1;
 
+#ifdef CONFIG_NEED_MULTIPLE_NODES
 	for (i = 0; i < NR_CPUS; i++)
 		numa_cpu_lookup_table[i] = 0;
 
 	cpumask_setall(&numa_cpumask_lookup_table[0]);
+#endif
 }
 
 #ifdef CONFIG_NEED_MULTIPLE_NODES
@@ -1008,7 +1026,8 @@ static void __init add_node_ranges(void)
 				"start[%lx] end[%lx]\n",
 				nid, start, this_end);
 
-			memblock_set_node(start, this_end - start, nid);
+			memblock_set_node(start, this_end - start,
+					  &memblock.memory, nid);
 			start = this_end;
 		}
 	}
@@ -1085,7 +1104,14 @@ static int __init grab_mblocks(struct mdesc_handle *md)
 		m->size = *val;
 		val = mdesc_get_property(md, node,
 					 "address-congruence-offset", NULL);
-		m->offset = *val;
+
+		/* The address-congruence-offset property is optional.
+		 * Explicity zero it be identifty this.
+		 */
+		if (val)
+			m->offset = *val;
+		else
+			m->offset = 0UL;
 
 		numadbg("MBLOCK[%d]: base[%llx] size[%llx] offset[%llx]\n",
 			count - 1, m->base, m->size, m->offset);
@@ -1305,7 +1331,7 @@ static void __init bootmem_init_nonnuma(void)
 	       (top_of_ram - total_ram) >> 20);
 
 	init_node_masks_nonnuma();
-	memblock_set_node(0, (phys_addr_t)ULLONG_MAX, 0);
+	memblock_set_node(0, (phys_addr_t)ULLONG_MAX, &memblock.memory, 0);
 	allocate_node_data(0);
 	node_set_online(0);
 }
@@ -1537,6 +1563,96 @@ unsigned long __init find_ecache_flush_span(unsigned long size)
 	return ~0UL;
 }
 
+unsigned long PAGE_OFFSET;
+EXPORT_SYMBOL(PAGE_OFFSET);
+
+static void __init page_offset_shift_patch_one(unsigned int *insn, unsigned long phys_bits)
+{
+	unsigned long final_shift;
+	unsigned int val = *insn;
+	unsigned int cnt;
+
+	/* We are patching in ilog2(max_supported_phys_address), and
+	 * we are doing so in a manner similar to a relocation addend.
+	 * That is, we are adding the shift value to whatever value
+	 * is in the shift instruction count field already.
+	 */
+	cnt = (val & 0x3f);
+	val &= ~0x3f;
+
+	/* If we are trying to shift >= 64 bits, clear the destination
+	 * register.  This can happen when phys_bits ends up being equal
+	 * to MAX_PHYS_ADDRESS_BITS.
+	 */
+	final_shift = (cnt + (64 - phys_bits));
+	if (final_shift >= 64) {
+		unsigned int rd = (val >> 25) & 0x1f;
+
+		val = 0x80100000 | (rd << 25);
+	} else {
+		val |= final_shift;
+	}
+	*insn = val;
+
+	__asm__ __volatile__("flush	%0"
+			     : /* no outputs */
+			     : "r" (insn));
+}
+
+static void __init page_offset_shift_patch(unsigned long phys_bits)
+{
+	extern unsigned int __page_offset_shift_patch;
+	extern unsigned int __page_offset_shift_patch_end;
+	unsigned int *p;
+
+	p = &__page_offset_shift_patch;
+	while (p < &__page_offset_shift_patch_end) {
+		unsigned int *insn = (unsigned int *)(unsigned long)*p;
+
+		page_offset_shift_patch_one(insn, phys_bits);
+
+		p++;
+	}
+}
+
+static void __init setup_page_offset(void)
+{
+	unsigned long max_phys_bits = 40;
+
+	if (tlb_type == cheetah || tlb_type == cheetah_plus) {
+		max_phys_bits = 42;
+	} else if (tlb_type == hypervisor) {
+		switch (sun4v_chip_type) {
+		case SUN4V_CHIP_NIAGARA1:
+		case SUN4V_CHIP_NIAGARA2:
+			max_phys_bits = 39;
+			break;
+		case SUN4V_CHIP_NIAGARA3:
+			max_phys_bits = 43;
+			break;
+		case SUN4V_CHIP_NIAGARA4:
+		case SUN4V_CHIP_NIAGARA5:
+		case SUN4V_CHIP_SPARC64X:
+		default:
+			max_phys_bits = 47;
+			break;
+		}
+	}
+
+	if (max_phys_bits > MAX_PHYS_ADDRESS_BITS) {
+		prom_printf("MAX_PHYS_ADDRESS_BITS is too small, need %lu\n",
+			    max_phys_bits);
+		prom_halt();
+	}
+
+	PAGE_OFFSET = PAGE_OFFSET_BY_BITS(max_phys_bits);
+
+	pr_info("PAGE_OFFSET is 0x%016lx (max_phys_bits == %lu)\n",
+		PAGE_OFFSET, max_phys_bits);
+
+	page_offset_shift_patch(max_phys_bits);
+}
+
 static void __init tsb_phys_patch(void)
 {
 	struct tsb_ldquad_phys_patch_entry *pquad;
@@ -1674,7 +1790,7 @@ static void __init sun4v_ktsb_init(void)
 #endif
 }
 
-void __cpuinit sun4v_ktsb_register(void)
+void sun4v_ktsb_register(void)
 {
 	unsigned long pa, ret;
 
@@ -1702,7 +1818,7 @@ static void __init sun4v_linear_pte_xor_finalize(void)
 #ifndef CONFIG_DEBUG_PAGEALLOC
 	if (cpu_pgsz_mask & HV_PGSZ_MASK_256MB) {
 		kern_linear_pte_xor[1] = (_PAGE_VALID | _PAGE_SZ256MB_4V) ^
-			0xfffff80000000000UL;
+			PAGE_OFFSET;
 		kern_linear_pte_xor[1] |= (_PAGE_CP_4V | _PAGE_CV_4V |
 					   _PAGE_P_4V | _PAGE_W_4V);
 	} else {
@@ -1711,7 +1827,7 @@ static void __init sun4v_linear_pte_xor_finalize(void)
 
 	if (cpu_pgsz_mask & HV_PGSZ_MASK_2GB) {
 		kern_linear_pte_xor[2] = (_PAGE_VALID | _PAGE_SZ2GB_4V) ^
-			0xfffff80000000000UL;
+			PAGE_OFFSET;
 		kern_linear_pte_xor[2] |= (_PAGE_CP_4V | _PAGE_CV_4V |
 					   _PAGE_P_4V | _PAGE_W_4V);
 	} else {
@@ -1720,7 +1836,7 @@ static void __init sun4v_linear_pte_xor_finalize(void)
 
 	if (cpu_pgsz_mask & HV_PGSZ_MASK_16GB) {
 		kern_linear_pte_xor[3] = (_PAGE_VALID | _PAGE_SZ16GB_4V) ^
-			0xfffff80000000000UL;
+			PAGE_OFFSET;
 		kern_linear_pte_xor[3] |= (_PAGE_CP_4V | _PAGE_CV_4V |
 					   _PAGE_P_4V | _PAGE_W_4V);
 	} else {
@@ -1732,7 +1848,7 @@ static void __init sun4v_linear_pte_xor_finalize(void)
 /* paging_init() sets up the page tables */
 
 static unsigned long last_valid_pfn;
-pgd_t swapper_pg_dir[2048];
+pgd_t swapper_pg_dir[PTRS_PER_PGD];
 
 static void sun4u_pgprot_init(void);
 static void sun4v_pgprot_init(void);
@@ -1743,6 +1859,8 @@ void __init paging_init(void)
 	unsigned long real_end, i;
 	int node;
 
+	setup_page_offset();
+
 	/* These build time checkes make sure that the dcache_dirty_cpu()
 	 * page->flags usage will work.
 	 *
@@ -1768,7 +1886,7 @@ void __init paging_init(void)
 
 	BUILD_BUG_ON(NR_CPUS > 4096);
 
-	kern_base = (prom_boot_mapping_phys_low >> 22UL) << 22UL;
+	kern_base = (prom_boot_mapping_phys_low >> ILOG2_4MB) << ILOG2_4MB;
 	kern_size = (unsigned long)&_end - (unsigned long)KERNBASE;
 
 	/* Invalidate both kernel TSBs.  */
@@ -1824,7 +1942,7 @@ void __init paging_init(void)
 	shift = kern_base + PAGE_OFFSET - ((unsigned long)KERNBASE);
 
 	real_end = (unsigned long)_end;
-	num_kernel_image_mappings = DIV_ROUND_UP(real_end - KERNBASE, 1 << 22);
+	num_kernel_image_mappings = DIV_ROUND_UP(real_end - KERNBASE, 1 << ILOG2_4MB);
 	printk("Kernel: Using %d locked TLB entries for main kernel image.\n",
 	       num_kernel_image_mappings);
 
@@ -1923,7 +2041,7 @@ void __init paging_init(void)
 	printk("Booting Linux...\n");
 }
 
-int __devinit page_in_phys_avail(unsigned long paddr)
+int page_in_phys_avail(unsigned long paddr)
 {
 	int i;
 
@@ -1981,7 +2099,7 @@ static void __init setup_valid_addr_bitmap_from_pavail(unsigned long *bitmap)
 
 				if (new_start <= old_start &&
 				    new_end >= (old_start + PAGE_SIZE)) {
-					set_bit(old_start >> 22, bitmap);
+					set_bit(old_start >> ILOG2_4MB, bitmap);
 					goto do_next_page;
 				}
 			}
@@ -2013,15 +2131,24 @@ static void __init patch_tlb_miss_handler_bitmap(void)
 	flushi(&valid_addr_bitmap_insn[0]);
 }
 
+static void __init register_page_bootmem_info(void)
+{
+#ifdef CONFIG_NEED_MULTIPLE_NODES
+	int i;
+
+	for_each_online_node(i)
+		if (NODE_DATA(i)->node_spanned_pages)
+			register_page_bootmem_info_node(NODE_DATA(i));
+#endif
+}
 void __init mem_init(void)
 {
-	unsigned long codepages, datapages, initpages;
 	unsigned long addr, last;
 
 	addr = PAGE_OFFSET + kern_base;
 	last = PAGE_ALIGN(kern_size) + addr;
 	while (addr < last) {
-		set_bit(__pa(addr) >> 22, sparc64_valid_addr_bitmap);
+		set_bit(__pa(addr) >> ILOG2_4MB, sparc64_valid_addr_bitmap);
 		addr += PAGE_SIZE;
 	}
 
@@ -2030,26 +2157,8 @@ void __init mem_init(void)
 
 	high_memory = __va(last_valid_pfn << PAGE_SHIFT);
 
-#ifdef CONFIG_NEED_MULTIPLE_NODES
-	{
-		int i;
-		for_each_online_node(i) {
-			if (NODE_DATA(i)->node_spanned_pages != 0) {
-				totalram_pages +=
-					free_all_bootmem_node(NODE_DATA(i));
-			}
-		}
-		totalram_pages += free_low_memory_core_early(MAX_NUMNODES);
-	}
-#else
-	totalram_pages = free_all_bootmem();
-#endif
-
-	/* We subtract one to account for the mem_map_zero page
-	 * allocated below.
-	 */
-	totalram_pages -= 1;
-	num_physpages = totalram_pages;
+	register_page_bootmem_info();
+	free_all_bootmem();
 
 	/*
 	 * Set up the zero page, mark it reserved, so that page count
@@ -2060,21 +2169,9 @@ void __init mem_init(void)
 		prom_printf("paging_init: Cannot alloc zero page.\n");
 		prom_halt();
 	}
-	SetPageReserved(mem_map_zero);
-
-	codepages = (((unsigned long) _etext) - ((unsigned long) _start));
-	codepages = PAGE_ALIGN(codepages) >> PAGE_SHIFT;
-	datapages = (((unsigned long) _edata) - ((unsigned long) _etext));
-	datapages = PAGE_ALIGN(datapages) >> PAGE_SHIFT;
-	initpages = (((unsigned long) __init_end) - ((unsigned long) __init_begin));
-	initpages = PAGE_ALIGN(initpages) >> PAGE_SHIFT;
+	mark_page_reserved(mem_map_zero);
 
-	printk("Memory: %luk available (%ldk kernel code, %ldk data, %ldk init) [%016lx,%016lx]\n",
-	       nr_free_pages() << (PAGE_SHIFT-10),
-	       codepages << (PAGE_SHIFT-10),
-	       datapages << (PAGE_SHIFT-10), 
-	       initpages << (PAGE_SHIFT-10), 
-	       PAGE_OFFSET, (last_valid_pfn << PAGE_SHIFT));
+	mem_init_print_info(NULL);
 
 	if (tlb_type == cheetah || tlb_type == cheetah_plus)
 		cheetah_ecache_flush_init();
@@ -2100,39 +2197,22 @@ void free_initmem(void)
 	initend = (unsigned long)(__init_end) & PAGE_MASK;
 	for (; addr < initend; addr += PAGE_SIZE) {
 		unsigned long page;
-		struct page *p;
 
 		page = (addr +
 			((unsigned long) __va(kern_base)) -
 			((unsigned long) KERNBASE));
 		memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
 
-		if (do_free) {
-			p = virt_to_page(page);
-
-			ClearPageReserved(p);
-			init_page_count(p);
-			__free_page(p);
-			num_physpages++;
-			totalram_pages++;
-		}
+		if (do_free)
+			free_reserved_page(virt_to_page(page));
 	}
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	if (start < end)
-		printk ("Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
-	for (; start < end; start += PAGE_SIZE) {
-		struct page *p = virt_to_page(start);
-
-		ClearPageReserved(p);
-		init_page_count(p);
-		__free_page(p);
-		num_physpages++;
-		totalram_pages++;
-	}
+	free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM,
+			   "initrd");
 }
 #endif
 
@@ -2169,10 +2249,9 @@ unsigned long vmemmap_table[VMEMMAP_SIZE];
 static long __meminitdata addr_start, addr_end;
 static int __meminitdata node_start;
 
-int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node)
+int __meminit vmemmap_populate(unsigned long vstart, unsigned long vend,
+			       int node)
 {
-	unsigned long vstart = (unsigned long) start;
-	unsigned long vend = (unsigned long) (start + nr);
 	unsigned long phys_start = (vstart - VMEMMAP_BASE);
 	unsigned long phys_end = (vend - VMEMMAP_BASE);
 	unsigned long addr = phys_start & VMEMMAP_CHUNK_MASK;
@@ -2193,7 +2272,7 @@ int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node)
 		void *block;
 
 		if (!(*vmem_pp & _PAGE_VALID)) {
-			block = vmemmap_alloc_block(1UL << 22, node);
+			block = vmemmap_alloc_block(1UL << ILOG2_4MB, node);
 			if (!block)
 				return -ENOMEM;
 
@@ -2223,6 +2302,11 @@ void __meminit vmemmap_populate_print_last(void)
 		node_start = 0;
 	}
 }
+
+void vmemmap_free(unsigned long start, unsigned long end)
+{
+}
+
 #endif /* CONFIG_SPARSEMEM_VMEMMAP */
 
 static void prot_init_common(unsigned long page_none,
@@ -2275,11 +2359,10 @@ static void __init sun4u_pgprot_init(void)
 		     __ACCESS_BITS_4U | _PAGE_E_4U);
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
-	kern_linear_pte_xor[0] = (_PAGE_VALID | _PAGE_SZBITS_4U) ^
-		0xfffff80000000000UL;
+	kern_linear_pte_xor[0] = _PAGE_VALID ^ PAGE_OFFSET;
 #else
 	kern_linear_pte_xor[0] = (_PAGE_VALID | _PAGE_SZ4MB_4U) ^
-		0xfffff80000000000UL;
+		PAGE_OFFSET;
 #endif
 	kern_linear_pte_xor[0] |= (_PAGE_CP_4U | _PAGE_CV_4U |
 				   _PAGE_P_4U | _PAGE_W_4U);
@@ -2287,7 +2370,6 @@ static void __init sun4u_pgprot_init(void)
 	for (i = 1; i < 4; i++)
 		kern_linear_pte_xor[i] = kern_linear_pte_xor[0];
 
-	_PAGE_SZBITS = _PAGE_SZBITS_4U;
 	_PAGE_ALL_SZ_BITS =  (_PAGE_SZ4MB_4U | _PAGE_SZ512K_4U |
 			      _PAGE_SZ64K_4U | _PAGE_SZ8K_4U |
 			      _PAGE_SZ32MB_4U | _PAGE_SZ256MB_4U);
@@ -2324,11 +2406,10 @@ static void __init sun4v_pgprot_init(void)
 	_PAGE_CACHE = _PAGE_CACHE_4V;
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
-	kern_linear_pte_xor[0] = (_PAGE_VALID | _PAGE_SZBITS_4V) ^
-		0xfffff80000000000UL;
+	kern_linear_pte_xor[0] = _PAGE_VALID ^ PAGE_OFFSET;
 #else
 	kern_linear_pte_xor[0] = (_PAGE_VALID | _PAGE_SZ4MB_4V) ^
-		0xfffff80000000000UL;
+		PAGE_OFFSET;
 #endif
 	kern_linear_pte_xor[0] |= (_PAGE_CP_4V | _PAGE_CV_4V |
 				   _PAGE_P_4V | _PAGE_W_4V);
@@ -2339,7 +2420,6 @@ static void __init sun4v_pgprot_init(void)
 	pg_iobits = (_PAGE_VALID | _PAGE_PRESENT_4V | __DIRTY_BITS_4V |
 		     __ACCESS_BITS_4V | _PAGE_E_4V);
 
-	_PAGE_SZBITS = _PAGE_SZBITS_4V;
 	_PAGE_ALL_SZ_BITS = (_PAGE_SZ16GB_4V | _PAGE_SZ2GB_4V |
 			     _PAGE_SZ256MB_4V | _PAGE_SZ32MB_4V |
 			     _PAGE_SZ4MB_4V | _PAGE_SZ512K_4V |
@@ -2472,3 +2552,150 @@ void __flush_tlb_all(void)
 	__asm__ __volatile__("wrpr	%0, 0, %%pstate"
 			     : : "r" (pstate));
 }
+
+pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
+			    unsigned long address)
+{
+	struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK |
+				       __GFP_REPEAT | __GFP_ZERO);
+	pte_t *pte = NULL;
+
+	if (page)
+		pte = (pte_t *) page_address(page);
+
+	return pte;
+}
+
+pgtable_t pte_alloc_one(struct mm_struct *mm,
+			unsigned long address)
+{
+	struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK |
+				       __GFP_REPEAT | __GFP_ZERO);
+	if (!page)
+		return NULL;
+	if (!pgtable_page_ctor(page)) {
+		free_hot_cold_page(page, 0);
+		return NULL;
+	}
+	return (pte_t *) page_address(page);
+}
+
+void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+{
+	free_page((unsigned long)pte);
+}
+
+static void __pte_free(pgtable_t pte)
+{
+	struct page *page = virt_to_page(pte);
+
+	pgtable_page_dtor(page);
+	__free_page(page);
+}
+
+void pte_free(struct mm_struct *mm, pgtable_t pte)
+{
+	__pte_free(pte);
+}
+
+void pgtable_free(void *table, bool is_page)
+{
+	if (is_page)
+		__pte_free(table);
+	else
+		kmem_cache_free(pgtable_cache, table);
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
+			  pmd_t *pmd)
+{
+	unsigned long pte, flags;
+	struct mm_struct *mm;
+	pmd_t entry = *pmd;
+
+	if (!pmd_large(entry) || !pmd_young(entry))
+		return;
+
+	pte = pmd_val(entry);
+
+	/* We are fabricating 8MB pages using 4MB real hw pages.  */
+	pte |= (addr & (1UL << REAL_HPAGE_SHIFT));
+
+	mm = vma->vm_mm;
+
+	spin_lock_irqsave(&mm->context.lock, flags);
+
+	if (mm->context.tsb_block[MM_TSB_HUGE].tsb != NULL)
+		__update_mmu_tsb_insert(mm, MM_TSB_HUGE, REAL_HPAGE_SHIFT,
+					addr, pte);
+
+	spin_unlock_irqrestore(&mm->context.lock, flags);
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
+static void context_reload(void *__data)
+{
+	struct mm_struct *mm = __data;
+
+	if (mm == current->mm)
+		load_secondary_context(mm);
+}
+
+void hugetlb_setup(struct pt_regs *regs)
+{
+	struct mm_struct *mm = current->mm;
+	struct tsb_config *tp;
+
+	if (in_atomic() || !mm) {
+		const struct exception_table_entry *entry;
+
+		entry = search_exception_tables(regs->tpc);
+		if (entry) {
+			regs->tpc = entry->fixup;
+			regs->tnpc = regs->tpc + 4;
+			return;
+		}
+		pr_alert("Unexpected HugeTLB setup in atomic context.\n");
+		die_if_kernel("HugeTSB in atomic", regs);
+	}
+
+	tp = &mm->context.tsb_block[MM_TSB_HUGE];
+	if (likely(tp->tsb == NULL))
+		tsb_grow(mm, MM_TSB_HUGE, 0);
+
+	tsb_context_switch(mm);
+	smp_tsb_sync(mm);
+
+	/* On UltraSPARC-III+ and later, configure the second half of
+	 * the Data-TLB for huge pages.
+	 */
+	if (tlb_type == cheetah_plus) {
+		unsigned long ctx;
+
+		spin_lock(&ctx_alloc_lock);
+		ctx = mm->context.sparc64_ctx_val;
+		ctx &= ~CTX_PGSZ_MASK;
+		ctx |= CTX_PGSZ_BASE << CTX_PGSZ0_SHIFT;
+		ctx |= CTX_PGSZ_HUGE << CTX_PGSZ1_SHIFT;
+
+		if (ctx != mm->context.sparc64_ctx_val) {
+			/* When changing the page size fields, we
+			 * must perform a context flush so that no
+			 * stale entries match.  This flush must
+			 * occur with the original context register
+			 * settings.
+			 */
+			do_flush_tlb_mm(mm);
+
+			/* Reload the context register of all processors
+			 * also executing in this address space.
+			 */
+			mm->context.sparc64_ctx_val = ctx;
+			on_each_cpu(context_reload, mm, 0);
+		}
+		spin_unlock(&ctx_alloc_lock);
+	}
+}
+#endif