21 files changed, 339 insertions, 183 deletions

diff --git a/arch/powerpc/mm/8xx_mmu.c b/arch/powerpc/mm/8xx_mmu.c
new file mode 100644
index 000000000..949100577
--- /dev/null
+++ b/arch/powerpc/mm/8xx_mmu.c
@@ -0,0 +1,141 @@
+/*
+ * This file contains the routines for initializing the MMU
+ * on the 8xx series of chips.
+ *  -- christophe
+ *
+ *  Derived from arch/powerpc/mm/40x_mmu.c:
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; either version
+ *  2 of the License, or (at your option) any later version.
+ *
+ */
+
+#include <linux/memblock.h>
+
+#include "mmu_decl.h"
+
+extern int __map_without_ltlbs;
+/*
+ * MMU_init_hw does the chip-specific initialization of the MMU hardware.
+ */
+void __init MMU_init_hw(void)
+{
+	/* Nothing to do for the time being but keep it similar to other PPC */
+}
+
+#define LARGE_PAGE_SIZE_4M	(1<<22)
+#define LARGE_PAGE_SIZE_8M	(1<<23)
+#define LARGE_PAGE_SIZE_64M	(1<<26)
+
+unsigned long __init mmu_mapin_ram(unsigned long top)
+{
+	unsigned long v, s, mapped;
+	phys_addr_t p;
+
+	v = KERNELBASE;
+	p = 0;
+	s = top;
+
+	if (__map_without_ltlbs)
+		return 0;
+
+#ifdef CONFIG_PPC_4K_PAGES
+	while (s >= LARGE_PAGE_SIZE_8M) {
+		pmd_t *pmdp;
+		unsigned long val = p | MD_PS8MEG;
+
+		pmdp = pmd_offset(pud_offset(pgd_offset_k(v), v), v);
+		*pmdp++ = __pmd(val);
+		*pmdp++ = __pmd(val + LARGE_PAGE_SIZE_4M);
+
+		v += LARGE_PAGE_SIZE_8M;
+		p += LARGE_PAGE_SIZE_8M;
+		s -= LARGE_PAGE_SIZE_8M;
+	}
+#else /* CONFIG_PPC_16K_PAGES */
+	while (s >= LARGE_PAGE_SIZE_64M) {
+		pmd_t *pmdp;
+		unsigned long val = p | MD_PS8MEG;
+
+		pmdp = pmd_offset(pud_offset(pgd_offset_k(v), v), v);
+		*pmdp++ = __pmd(val);
+
+		v += LARGE_PAGE_SIZE_64M;
+		p += LARGE_PAGE_SIZE_64M;
+		s -= LARGE_PAGE_SIZE_64M;
+	}
+#endif
+
+	mapped = top - s;
+
+	/* If the size of RAM is not an exact power of two, we may not
+	 * have covered RAM in its entirety with 8 MiB
+	 * pages. Consequently, restrict the top end of RAM currently
+	 * allocable so that calls to the MEMBLOCK to allocate PTEs for "tail"
+	 * coverage with normal-sized pages (or other reasons) do not
+	 * attempt to allocate outside the allowed range.
+	 */
+	memblock_set_current_limit(mapped);
+
+	return mapped;
+}
+
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+				phys_addr_t first_memblock_size)
+{
+	/* We don't currently support the first MEMBLOCK not mapping 0
+	 * physical on those processors
+	 */
+	BUG_ON(first_memblock_base != 0);
+
+#ifdef CONFIG_PIN_TLB
+	/* 8xx can only access 24MB at the moment */
+	memblock_set_current_limit(min_t(u64, first_memblock_size, 0x01800000));
+#else
+	/* 8xx can only access 8MB at the moment */
+	memblock_set_current_limit(min_t(u64, first_memblock_size, 0x00800000));
+#endif
+}
+
+/*
+ * Set up to use a given MMU context.
+ * id is context number, pgd is PGD pointer.
+ *
+ * We place the physical address of the new task page directory loaded
+ * into the MMU base register, and set the ASID compare register with
+ * the new "context."
+ */
+void set_context(unsigned long id, pgd_t *pgd)
+{
+	s16 offset = (s16)(__pa(swapper_pg_dir));
+
+#ifdef CONFIG_BDI_SWITCH
+	pgd_t	**ptr = *(pgd_t ***)(KERNELBASE + 0xf0);
+
+	/* Context switch the PTE pointer for the Abatron BDI2000.
+	 * The PGDIR is passed as second argument.
+	 */
+	*(ptr + 1) = pgd;
+#endif
+
+	/* Register M_TW will contain base address of level 1 table minus the
+	 * lower part of the kernel PGDIR base address, so that all accesses to
+	 * level 1 table are done relative to lower part of kernel PGDIR base
+	 * address.
+	 */
+	mtspr(SPRN_M_TW, __pa(pgd) - offset);
+
+	/* Update context */
+	mtspr(SPRN_M_CASID, id);
+	/* sync */
+	mb();
+}
+
+void flush_instruction_cache(void)
+{
+	isync();
+	mtspr(SPRN_IC_CST, IDC_INVALL);
+	isync();
+}
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index 1ffeda85c..adfee3f1a 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -25,6 +25,7 @@ obj-$(CONFIG_PPC_ICSWX)		+= icswx.o
 obj-$(CONFIG_PPC_ICSWX_PID)	+= icswx_pid.o
 obj-$(CONFIG_40x)		+= 40x_mmu.o
 obj-$(CONFIG_44x)		+= 44x_mmu.o
+obj-$(CONFIG_PPC_8xx)		+= 8xx_mmu.o
 obj-$(CONFIG_PPC_FSL_BOOK3E)	+= fsl_booke_mmu.o
 obj-$(CONFIG_NEED_MULTIPLE_NODES) += numa.o
 obj-$(CONFIG_PPC_SPLPAR)	+= vphn.o
diff --git a/arch/powerpc/mm/dma-noncoherent.c b/arch/powerpc/mm/dma-noncoherent.c
index 169aba446..2dc74e5c6 100644
--- a/arch/powerpc/mm/dma-noncoherent.c
+++ b/arch/powerpc/mm/dma-noncoherent.c
@@ -327,7 +327,7 @@ void __dma_sync(void *vaddr, size_t size, int direction)
 		 * invalidate only when cache-line aligned otherwise there is
 		 * the potential for discarding uncommitted data from the cache
 		 */
-		if ((start & (L1_CACHE_BYTES - 1)) || (size & (L1_CACHE_BYTES - 1)))
+		if ((start | end) & (L1_CACHE_BYTES - 1))
 			flush_dcache_range(start, end);
 		else
 			invalidate_dcache_range(start, end);
diff --git a/arch/powerpc/mm/fsl_booke_mmu.c b/arch/powerpc/mm/fsl_booke_mmu.c
index f3afe3d97..a1b2713f6 100644
--- a/arch/powerpc/mm/fsl_booke_mmu.c
+++ b/arch/powerpc/mm/fsl_booke_mmu.c
@@ -72,10 +72,11 @@ unsigned long tlbcam_sz(int idx)
 	return tlbcam_addrs[idx].limit - tlbcam_addrs[idx].start + 1;
 }
 
+#ifdef CONFIG_FSL_BOOKE
 /*
  * Return PA for this VA if it is mapped by a CAM, or 0
  */
-phys_addr_t v_mapped_by_tlbcam(unsigned long va)
+phys_addr_t v_block_mapped(unsigned long va)
 {
 	int b;
 	for (b = 0; b < tlbcam_index; ++b)
@@ -87,7 +88,7 @@ phys_addr_t v_mapped_by_tlbcam(unsigned long va)
 /*
  * Return VA for a given PA or 0 if not mapped
  */
-unsigned long p_mapped_by_tlbcam(phys_addr_t pa)
+unsigned long p_block_mapped(phys_addr_t pa)
 {
 	int b;
 	for (b = 0; b < tlbcam_index; ++b)
@@ -97,6 +98,7 @@ unsigned long p_mapped_by_tlbcam(phys_addr_t pa)
 			return tlbcam_addrs[b].start+(pa-tlbcam_addrs[b].phys);
 	return 0;
 }
+#endif
 
 /*
  * Set up a variable-size TLB entry (tlbcam). The parameters are not checked;
diff --git a/arch/powerpc/mm/hash64_4k.c b/arch/powerpc/mm/hash64_4k.c
index e7c04542b..47d1b26ef 100644
--- a/arch/powerpc/mm/hash64_4k.c
+++ b/arch/powerpc/mm/hash64_4k.c
@@ -44,7 +44,7 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 		 * a write access. Since this is 4K insert of 64K page size
 		 * also add _PAGE_COMBO
 		 */
-		new_pte = old_pte | _PAGE_BUSY | _PAGE_ACCESSED | _PAGE_HASHPTE;
+		new_pte = old_pte | _PAGE_BUSY | _PAGE_ACCESSED;
 		if (access & _PAGE_RW)
 			new_pte |= _PAGE_DIRTY;
 	} while (old_pte != __cmpxchg_u64((unsigned long *)ptep,
@@ -106,7 +106,7 @@ repeat:
 			}
 		}
 		/*
-		 * Hypervisor failure. Restore old pmd and return -1
+		 * Hypervisor failure. Restore old pte and return -1
 		 * similar to __hash_page_*
 		 */
 		if (unlikely(slot == -2)) {
diff --git a/arch/powerpc/mm/hash64_64k.c b/arch/powerpc/mm/hash64_64k.c
index edb09912f..b2d659cf5 100644
--- a/arch/powerpc/mm/hash64_64k.c
+++ b/arch/powerpc/mm/hash64_64k.c
@@ -188,7 +188,7 @@ repeat:
 		}
 	}
 	/*
-	 * Hypervisor failure. Restore old pmd and return -1
+	 * Hypervisor failure. Restore old pte and return -1
 	 * similar to __hash_page_*
 	 */
 	if (unlikely(slot == -2)) {
@@ -249,8 +249,7 @@ int __hash_page_64K(unsigned long ea, unsigned long access,
 			return 0;
 		/*
 		 * Try to lock the PTE, add ACCESSED and DIRTY if it was
-		 * a write access. Since this is 4K insert of 64K page size
-		 * also add _PAGE_COMBO
+		 * a write access.
 		 */
 		new_pte = old_pte | _PAGE_BUSY | _PAGE_ACCESSED;
 		if (access & _PAGE_RW)
@@ -311,7 +310,7 @@ repeat:
 			}
 		}
 		/*
-		 * Hypervisor failure. Restore old pmd and return -1
+		 * Hypervisor failure. Restore old pte and return -1
 		 * similar to __hash_page_*
 		 */
 		if (unlikely(slot == -2)) {
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index ba59d5977..7635b1c6b 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -168,11 +168,11 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags)
 		rflags |= HPTE_R_N;
 	/*
 	 * PP bits:
-	 * Linux use slb key 0 for kernel and 1 for user.
-	 * kernel areas are mapped by PP bits 00
-	 * and and there is no kernel RO (_PAGE_KERNEL_RO).
-	 * User area mapped by 0x2 and read only use by
-	 * 0x3.
+	 * Linux uses slb key 0 for kernel and 1 for user.
+	 * kernel areas are mapped with PP=00
+	 * and there is no kernel RO (_PAGE_KERNEL_RO).
+	 * User area is mapped with PP=0x2 for read/write
+	 * or PP=0x3 for read-only (including writeable but clean pages).
 	 */
 	if (pteflags & _PAGE_USER) {
 		rflags |= 0x2;
@@ -255,36 +255,42 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
 
 		if (ret < 0)
 			break;
+
 #ifdef CONFIG_DEBUG_PAGEALLOC
-		if ((paddr >> PAGE_SHIFT) < linear_map_hash_count)
+		if (debug_pagealloc_enabled() &&
+			(paddr >> PAGE_SHIFT) < linear_map_hash_count)
 			linear_map_hash_slots[paddr >> PAGE_SHIFT] = ret | 0x80;
 #endif /* CONFIG_DEBUG_PAGEALLOC */
 	}
 	return ret < 0 ? ret : 0;
 }
 
-#ifdef CONFIG_MEMORY_HOTPLUG
 int htab_remove_mapping(unsigned long vstart, unsigned long vend,
 		      int psize, int ssize)
 {
 	unsigned long vaddr;
 	unsigned int step, shift;
+	int rc;
+	int ret = 0;
 
 	shift = mmu_psize_defs[psize].shift;
 	step = 1 << shift;
 
-	if (!ppc_md.hpte_removebolted) {
-		printk(KERN_WARNING "Platform doesn't implement "
-				"hpte_removebolted\n");
-		return -EINVAL;
-	}
+	if (!ppc_md.hpte_removebolted)
+		return -ENODEV;
 
-	for (vaddr = vstart; vaddr < vend; vaddr += step)
-		ppc_md.hpte_removebolted(vaddr, psize, ssize);
+	for (vaddr = vstart; vaddr < vend; vaddr += step) {
+		rc = ppc_md.hpte_removebolted(vaddr, psize, ssize);
+		if (rc == -ENOENT) {
+			ret = -ENOENT;
+			continue;
+		}
+		if (rc < 0)
+			return rc;
+	}
 
-	return 0;
+	return ret;
 }
-#endif /* CONFIG_MEMORY_HOTPLUG */
 
 static int __init htab_dt_scan_seg_sizes(unsigned long node,
 					 const char *uname, int depth,
@@ -512,17 +518,17 @@ static void __init htab_init_page_sizes(void)
 	if (mmu_has_feature(MMU_FTR_16M_PAGE))
 		memcpy(mmu_psize_defs, mmu_psize_defaults_gp,
 		       sizeof(mmu_psize_defaults_gp));
- found:
-#ifndef CONFIG_DEBUG_PAGEALLOC
-	/*
-	 * Pick a size for the linear mapping. Currently, we only support
-	 * 16M, 1M and 4K which is the default
-	 */
-	if (mmu_psize_defs[MMU_PAGE_16M].shift)
-		mmu_linear_psize = MMU_PAGE_16M;
-	else if (mmu_psize_defs[MMU_PAGE_1M].shift)
-		mmu_linear_psize = MMU_PAGE_1M;
-#endif /* CONFIG_DEBUG_PAGEALLOC */
+found:
+	if (!debug_pagealloc_enabled()) {
+		/*
+		 * Pick a size for the linear mapping. Currently, we only
+		 * support 16M, 1M and 4K which is the default
+		 */
+		if (mmu_psize_defs[MMU_PAGE_16M].shift)
+			mmu_linear_psize = MMU_PAGE_16M;
+		else if (mmu_psize_defs[MMU_PAGE_1M].shift)
+			mmu_linear_psize = MMU_PAGE_1M;
+	}
 
 #ifdef CONFIG_PPC_64K_PAGES
 	/*
@@ -605,10 +611,28 @@ static int __init htab_dt_scan_pftsize(unsigned long node,
 	return 0;
 }
 
-static unsigned long __init htab_get_table_size(void)
+unsigned htab_shift_for_mem_size(unsigned long mem_size)
 {
-	unsigned long mem_size, rnd_mem_size, pteg_count, psize;
+	unsigned memshift = __ilog2(mem_size);
+	unsigned pshift = mmu_psize_defs[mmu_virtual_psize].shift;
+	unsigned pteg_shift;
 
+	/* round mem_size up to next power of 2 */
+	if ((1UL << memshift) < mem_size)
+		memshift += 1;
+
+	/* aim for 2 pages / pteg */
+	pteg_shift = memshift - (pshift + 1);
+
+	/*
+	 * 2^11 PTEGS of 128 bytes each, ie. 2^18 bytes is the minimum htab
+	 * size permitted by the architecture.
+	 */
+	return max(pteg_shift + 7, 18U);
+}
+
+static unsigned long __init htab_get_table_size(void)
+{
 	/* If hash size isn't already provided by the platform, we try to
 	 * retrieve it from the device-tree. If it's not there neither, we
 	 * calculate it now based on the total RAM size
@@ -618,31 +642,30 @@ static unsigned long __init htab_get_table_size(void)
 	if (ppc64_pft_size)
 		return 1UL << ppc64_pft_size;
 
-	/* round mem_size up to next power of 2 */
-	mem_size = memblock_phys_mem_size();
-	rnd_mem_size = 1UL << __ilog2(mem_size);
-	if (rnd_mem_size < mem_size)
-		rnd_mem_size <<= 1;
-
-	/* # pages / 2 */
-	psize = mmu_psize_defs[mmu_virtual_psize].shift;
-	pteg_count = max(rnd_mem_size >> (psize + 1), 1UL << 11);
-
-	return pteg_count << 7;
+	return 1UL << htab_shift_for_mem_size(memblock_phys_mem_size());
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
 int create_section_mapping(unsigned long start, unsigned long end)
 {
-	return htab_bolt_mapping(start, end, __pa(start),
-				 pgprot_val(PAGE_KERNEL), mmu_linear_psize,
-				 mmu_kernel_ssize);
+	int rc = htab_bolt_mapping(start, end, __pa(start),
+				   pgprot_val(PAGE_KERNEL), mmu_linear_psize,
+				   mmu_kernel_ssize);
+
+	if (rc < 0) {
+		int rc2 = htab_remove_mapping(start, end, mmu_linear_psize,
+					      mmu_kernel_ssize);
+		BUG_ON(rc2 && (rc2 != -ENOENT));
+	}
+	return rc;
 }
 
 int remove_section_mapping(unsigned long start, unsigned long end)
 {
-	return htab_remove_mapping(start, end, mmu_linear_psize,
-			mmu_kernel_ssize);
+	int rc = htab_remove_mapping(start, end, mmu_linear_psize,
+				     mmu_kernel_ssize);
+	WARN_ON(rc < 0);
+	return rc;
 }
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
@@ -721,10 +744,12 @@ static void __init htab_initialize(void)
 	prot = pgprot_val(PAGE_KERNEL);
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
-	linear_map_hash_count = memblock_end_of_DRAM() >> PAGE_SHIFT;
-	linear_map_hash_slots = __va(memblock_alloc_base(linear_map_hash_count,
-						    1, ppc64_rma_size));
-	memset(linear_map_hash_slots, 0, linear_map_hash_count);
+	if (debug_pagealloc_enabled()) {
+		linear_map_hash_count = memblock_end_of_DRAM() >> PAGE_SHIFT;
+		linear_map_hash_slots = __va(memblock_alloc_base(
+				linear_map_hash_count, 1, ppc64_rma_size));
+		memset(linear_map_hash_slots, 0, linear_map_hash_count);
+	}
 #endif /* CONFIG_DEBUG_PAGEALLOC */
 
 	/* On U3 based machines, we need to reserve the DART area and
diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c
index e2138c7ae..8555fce90 100644
--- a/arch/powerpc/mm/hugetlbpage-hash64.c
+++ b/arch/powerpc/mm/hugetlbpage-hash64.c
@@ -76,7 +76,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 		if (old_pte & _PAGE_F_SECOND)
 			hash = ~hash;
 		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
-		slot += (old_pte & _PAGE_F_GIX) >> 12;
+		slot += (old_pte & _PAGE_F_GIX) >> _PAGE_F_GIX_SHIFT;
 
 		if (ppc_md.hpte_updatepp(slot, rflags, vpn, mmu_psize,
 					 mmu_psize, ssize, flags) == -1)
@@ -105,7 +105,8 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 			return -1;
 		}
 
-		new_pte |= (slot << 12) & (_PAGE_F_SECOND | _PAGE_F_GIX);
+		new_pte |= (slot << _PAGE_F_GIX_SHIFT) &
+			(_PAGE_F_SECOND | _PAGE_F_GIX);
 	}
 
 	/*
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 4a811ca7a..d991b9e80 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -107,8 +107,7 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
 		kmem_cache_free(cachep, new);
 	else {
 #ifdef CONFIG_PPC_BOOK3S_64
-		hpdp->pd = (unsigned long)new |
-			    (shift_to_mmu_psize(pshift) << 2);
+		hpdp->pd = __pa(new) | (shift_to_mmu_psize(pshift) << 2);
 #else
 		hpdp->pd = ((unsigned long)new & ~PD_HUGE) | pshift;
 #endif
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index a10be665b..c899fe340 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -112,10 +112,10 @@ void __init MMU_setup(void)
 	if (strstr(boot_command_line, "noltlbs")) {
 		__map_without_ltlbs = 1;
 	}
-#ifdef CONFIG_DEBUG_PAGEALLOC
-	__map_without_bats = 1;
-	__map_without_ltlbs = 1;
-#endif
+	if (debug_pagealloc_enabled()) {
+		__map_without_bats = 1;
+		__map_without_ltlbs = 1;
+	}
 }
 
 /*
@@ -178,10 +178,6 @@ void __init MMU_init(void)
 	/* Initialize early top-down ioremap allocator */
 	ioremap_bot = IOREMAP_TOP;
 
-	/* Map in I/O resources */
-	if (ppc_md.progress)
-		ppc_md.progress("MMU:setio", 0x302);
-
 	if (ppc_md.progress)
 		ppc_md.progress("MMU:exit", 0x211);
 
@@ -193,22 +189,3 @@ void __init MMU_init(void)
 	/* Shortly after that, the entire linear mapping will be available */
 	memblock_set_current_limit(lowmem_end_addr);
 }
-
-#ifdef CONFIG_8xx /* No 8xx specific .c file to put that in ... */
-void setup_initial_memory_limit(phys_addr_t first_memblock_base,
-				phys_addr_t first_memblock_size)
-{
-	/* We don't currently support the first MEMBLOCK not mapping 0
-	 * physical on those processors
-	 */
-	BUG_ON(first_memblock_base != 0);
-
-#ifdef CONFIG_PIN_TLB
-	/* 8xx can only access 24MB at the moment */
-	memblock_set_current_limit(min_t(u64, first_memblock_size, 0x01800000));
-#else
-	/* 8xx can only access 8MB at the moment */
-	memblock_set_current_limit(min_t(u64, first_memblock_size, 0x00800000));
-#endif
-}
-#endif /* CONFIG_8xx */
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 379a6a906..ba6556661 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -85,6 +85,11 @@ static void pgd_ctor(void *addr)
 	memset(addr, 0, PGD_TABLE_SIZE);
 }
 
+static void pud_ctor(void *addr)
+{
+	memset(addr, 0, PUD_TABLE_SIZE);
+}
+
 static void pmd_ctor(void *addr)
 {
 	memset(addr, 0, PMD_TABLE_SIZE);
@@ -138,14 +143,18 @@ void pgtable_cache_init(void)
 {
 	pgtable_cache_add(PGD_INDEX_SIZE, pgd_ctor);
 	pgtable_cache_add(PMD_CACHE_INDEX, pmd_ctor);
+	/*
+	 * In all current configs, when the PUD index exists it's the
+	 * same size as either the pgd or pmd index except with THP enabled
+	 * on book3s 64
+	 */
+	if (PUD_INDEX_SIZE && !PGT_CACHE(PUD_INDEX_SIZE))
+		pgtable_cache_add(PUD_INDEX_SIZE, pud_ctor);
+
 	if (!PGT_CACHE(PGD_INDEX_SIZE) || !PGT_CACHE(PMD_CACHE_INDEX))
 		panic("Couldn't allocate pgtable caches");
-	/* In all current configs, when the PUD index exists it's the
-	 * same size as either the pgd or pmd index.  Verify that the
-	 * initialization above has also created a PUD cache.  This
-	 * will need re-examiniation if we add new possibilities for
-	 * the pagetable layout. */
-	BUG_ON(PUD_INDEX_SIZE && !PGT_CACHE(PUD_INDEX_SIZE));
+	if (PUD_INDEX_SIZE && !PGT_CACHE(PUD_INDEX_SIZE))
+		panic("Couldn't allocate pud pgtable caches");
 }
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
@@ -188,9 +197,9 @@ static int __meminit vmemmap_populated(unsigned long start, int page_size)
  */
 
 #ifdef CONFIG_PPC_BOOK3E
-static void __meminit vmemmap_create_mapping(unsigned long start,
-					     unsigned long page_size,
-					     unsigned long phys)
+static int __meminit vmemmap_create_mapping(unsigned long start,
+					    unsigned long page_size,
+					    unsigned long phys)
 {
 	/* Create a PTE encoding without page size */
 	unsigned long i, flags = _PAGE_PRESENT | _PAGE_ACCESSED |
@@ -208,6 +217,8 @@ static void __meminit vmemmap_create_mapping(unsigned long start,
 	 */
 	for (i = 0; i < page_size; i += PAGE_SIZE)
 		BUG_ON(map_kernel_page(start + i, phys, flags));
+
+	return 0;
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
@@ -217,25 +228,31 @@ static void vmemmap_remove_mapping(unsigned long start,
 }
 #endif
 #else /* CONFIG_PPC_BOOK3E */
-static void __meminit vmemmap_create_mapping(unsigned long start,
-					     unsigned long page_size,
-					     unsigned long phys)
+static int __meminit vmemmap_create_mapping(unsigned long start,
+					    unsigned long page_size,
+					    unsigned long phys)
 {
-	int  mapped = htab_bolt_mapping(start, start + page_size, phys,
-					pgprot_val(PAGE_KERNEL),
-					mmu_vmemmap_psize,
-					mmu_kernel_ssize);
-	BUG_ON(mapped < 0);
+	int rc = htab_bolt_mapping(start, start + page_size, phys,
+				   pgprot_val(PAGE_KERNEL),
+				   mmu_vmemmap_psize, mmu_kernel_ssize);
+	if (rc < 0) {
+		int rc2 = htab_remove_mapping(start, start + page_size,
+					      mmu_vmemmap_psize,
+					      mmu_kernel_ssize);
+		BUG_ON(rc2 && (rc2 != -ENOENT));
+	}
+	return rc;
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
 static void vmemmap_remove_mapping(unsigned long start,
 				   unsigned long page_size)
 {
-	int mapped = htab_remove_mapping(start, start + page_size,
-					 mmu_vmemmap_psize,
-					 mmu_kernel_ssize);
-	BUG_ON(mapped < 0);
+	int rc = htab_remove_mapping(start, start + page_size,
+				     mmu_vmemmap_psize,
+				     mmu_kernel_ssize);
+	BUG_ON((rc < 0) && (rc != -ENOENT));
+	WARN_ON(rc == -ENOENT);
 }
 #endif
 
@@ -303,6 +320,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 
 	for (; start < end; start += page_size) {
 		void *p;
+		int rc;
 
 		if (vmemmap_populated(start, page_size))
 			continue;
@@ -316,7 +334,13 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 		pr_debug("      * %016lx..%016lx allocated at %p\n",
 			 start, start + page_size, p);
 
-		vmemmap_create_mapping(start, page_size, __pa(p));
+		rc = vmemmap_create_mapping(start, page_size, __pa(p));
+		if (rc < 0) {
+			pr_warning(
+				"vmemmap_populate: Unable to create vmemmap mapping: %d\n",
+				rc);
+			return -EFAULT;
+		}
 	}
 
 	return 0;
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index d0f0a514b..ac79dbde1 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -119,12 +119,18 @@ int arch_add_memory(int nid, u64 start, u64 size, bool for_device)
 	struct zone *zone;
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
+	int rc;
 
 	pgdata = NODE_DATA(nid);
 
 	start = (unsigned long)__va(start);
-	if (create_section_mapping(start, start + size))
-		return -EINVAL;
+	rc = create_section_mapping(start, start + size);
+	if (rc) {
+		pr_warning(
+			"Unable to create mapping for hot added memory 0x%llx..0x%llx: %d\n",
+			start, start + size, rc);
+		return -EFAULT;
+	}
 
 	/* this should work for most non-highmem platforms */
 	zone = pgdata->node_zones +
@@ -541,7 +547,7 @@ static int __init add_system_ram_resources(void)
 			res->name = "System RAM";
 			res->start = base;
 			res->end = base + size - 1;
-			res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+			res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
 			WARN_ON(request_resource(&iomem_resource, res) < 0);
 		}
 	}
diff --git a/arch/powerpc/mm/mmu_context_hash64.c b/arch/powerpc/mm/mmu_context_hash64.c
index 4e4efbc26..9ca6fe16c 100644
--- a/arch/powerpc/mm/mmu_context_hash64.c
+++ b/arch/powerpc/mm/mmu_context_hash64.c
@@ -118,8 +118,7 @@ static void destroy_pagetable_page(struct mm_struct *mm)
 	/* drop all the pending references */
 	count = ((unsigned long)pte_frag & ~PAGE_MASK) >> PTE_FRAG_SIZE_SHIFT;
 	/* We allow PTE_FRAG_NR fragments from a PTE page */
-	count = atomic_sub_return(PTE_FRAG_NR - count, &page->_count);
-	if (!count) {
+	if (page_ref_sub_and_test(page, PTE_FRAG_NR - count)) {
 		pgtable_page_dtor(page);
 		free_hot_cold_page(page, 0);
 	}
diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h
index 9f58ff44a..bfb7c0bca 100644
--- a/arch/powerpc/mm/mmu_decl.h
+++ b/arch/powerpc/mm/mmu_decl.h
@@ -100,7 +100,6 @@ extern void setbat(int index, unsigned long virt, phys_addr_t phys,
 
 extern int __map_without_bats;
 extern int __allow_ioremap_reserved;
-extern unsigned long ioremap_base;
 extern unsigned int rtas_data, rtas_size;
 
 struct hash_pte;
@@ -110,7 +109,8 @@ extern unsigned long Hash_size, Hash_mask;
 #endif /* CONFIG_PPC32 */
 
 #ifdef CONFIG_PPC64
-extern int map_kernel_page(unsigned long ea, unsigned long pa, int flags);
+extern int map_kernel_page(unsigned long ea, unsigned long pa,
+			   unsigned long flags);
 #endif /* CONFIG_PPC64 */
 
 extern unsigned long ioremap_bot;
@@ -132,22 +132,17 @@ extern void wii_memory_fixups(void);
 /* ...and now those things that may be slightly different between processor
  * architectures.  -- Dan
  */
-#if defined(CONFIG_8xx)
-#define MMU_init_hw()		do { } while(0)
-#define mmu_mapin_ram(top)	(0UL)
-
-#elif defined(CONFIG_4xx)
+#ifdef CONFIG_PPC32
 extern void MMU_init_hw(void);
 extern unsigned long mmu_mapin_ram(unsigned long top);
+#endif
 
-#elif defined(CONFIG_PPC_FSL_BOOK3E)
+#ifdef CONFIG_PPC_FSL_BOOK3E
 extern unsigned long map_mem_in_cams(unsigned long ram, int max_cam_idx,
 				     bool dryrun);
 extern unsigned long calc_cam_sz(unsigned long ram, unsigned long virt,
 				 phys_addr_t phys);
 #ifdef CONFIG_PPC32
-extern void MMU_init_hw(void);
-extern unsigned long mmu_mapin_ram(unsigned long top);
 extern void adjust_total_lowmem(void);
 extern int switch_to_as1(void);
 extern void restore_to_as0(int esel, int offset, void *dt_ptr, int bootcpu);
@@ -162,8 +157,14 @@ struct tlbcam {
 	u32	MAS3;
 	u32	MAS7;
 };
-#elif defined(CONFIG_PPC32)
-/* anything 32-bit except 4xx or 8xx */
-extern void MMU_init_hw(void);
-extern unsigned long mmu_mapin_ram(unsigned long top);
+#endif
+
+#if defined(CONFIG_6xx) || defined(CONFIG_FSL_BOOKE)
+/* 6xx have BATS */
+/* FSL_BOOKE have TLBCAM */
+phys_addr_t v_block_mapped(unsigned long va);
+unsigned long p_block_mapped(phys_addr_t pa);
+#else
+static inline phys_addr_t v_block_mapped(unsigned long va) { return 0; }
+static inline unsigned long p_block_mapped(phys_addr_t pa) { return 0; }
 #endif
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index 83dfd7925..de37ff445 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -243,3 +243,11 @@ void assert_pte_locked(struct mm_struct *mm, unsigned long addr)
 }
 #endif /* CONFIG_DEBUG_VM */
 
+unsigned long vmalloc_to_phys(void *va)
+{
+	unsigned long pfn = vmalloc_to_pfn(va);
+
+	BUG_ON(!pfn);
+	return __pa(pfn_to_kaddr(pfn)) + offset_in_page(va);
+}
+EXPORT_SYMBOL_GPL(vmalloc_to_phys);
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 7692d1bb1..bf7bf32b5 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -37,35 +37,10 @@
 
 #include "mmu_decl.h"
 
-unsigned long ioremap_base;
 unsigned long ioremap_bot;
 EXPORT_SYMBOL(ioremap_bot);	/* aka VMALLOC_END */
 
-#ifdef CONFIG_6xx
-#define HAVE_BATS	1
-#endif
-
-#if defined(CONFIG_FSL_BOOKE)
-#define HAVE_TLBCAM	1
-#endif
-
-extern char etext[], _stext[];
-
-#ifdef HAVE_BATS
-extern phys_addr_t v_mapped_by_bats(unsigned long va);
-extern unsigned long p_mapped_by_bats(phys_addr_t pa);
-#else /* !HAVE_BATS */
-#define v_mapped_by_bats(x)	(0UL)
-#define p_mapped_by_bats(x)	(0UL)
-#endif /* HAVE_BATS */
-
-#ifdef HAVE_TLBCAM
-extern phys_addr_t v_mapped_by_tlbcam(unsigned long va);
-extern unsigned long p_mapped_by_tlbcam(phys_addr_t pa);
-#else /* !HAVE_TLBCAM */
-#define v_mapped_by_tlbcam(x)	(0UL)
-#define p_mapped_by_tlbcam(x)	(0UL)
-#endif /* HAVE_TLBCAM */
+extern char etext[], _stext[], _sinittext[], _einittext[];
 
 #define PGDIR_ORDER	(32 + PGD_T_LOG2 - PGDIR_SHIFT)
 
@@ -197,7 +172,7 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, unsigned long flags,
 	/*
 	 * Choose an address to map it to.
 	 * Once the vmalloc system is running, we use it.
-	 * Before then, we use space going down from ioremap_base
+	 * Before then, we use space going down from IOREMAP_TOP
 	 * (ioremap_bot records where we're up to).
 	 */
 	p = addr & PAGE_MASK;
@@ -228,19 +203,10 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, unsigned long flags,
 
 	/*
 	 * Is it already mapped?  Perhaps overlapped by a previous
-	 * BAT mapping.  If the whole area is mapped then we're done,
-	 * otherwise remap it since we want to keep the virt addrs for
-	 * each request contiguous.
-	 *
-	 * We make the assumption here that if the bottom and top
-	 * of the range we want are mapped then it's mapped to the
-	 * same virt address (and this is contiguous).
-	 *  -- Cort
+	 * mapping.
 	 */
-	if ((v = p_mapped_by_bats(p)) /*&& p_mapped_by_bats(p+size-1)*/ )
-		goto out;
-
-	if ((v = p_mapped_by_tlbcam(p)))
+	v = p_block_mapped(p);
+	if (v)
 		goto out;
 
 	if (slab_is_available()) {
@@ -278,7 +244,8 @@ void iounmap(volatile void __iomem *addr)
 	 * If mapped by BATs then there is nothing to do.
 	 * Calling vfree() generates a benign warning.
 	 */
-	if (v_mapped_by_bats((unsigned long)addr)) return;
+	if (v_block_mapped((unsigned long)addr))
+		return;
 
 	if (addr > high_memory && (unsigned long) addr < ioremap_bot)
 		vunmap((void *) (PAGE_MASK & (unsigned long)addr));
@@ -322,7 +289,8 @@ void __init __mapin_ram_chunk(unsigned long offset, unsigned long top)
 	v = PAGE_OFFSET + s;
 	p = memstart_addr + s;
 	for (; s < top; s += PAGE_SIZE) {
-		ktext = ((char *) v >= _stext && (char *) v < etext);
+		ktext = ((char *)v >= _stext && (char *)v < etext) ||
+			((char *)v >= _sinittext && (char *)v < _einittext);
 		f = ktext ? pgprot_val(PAGE_KERNEL_TEXT) : pgprot_val(PAGE_KERNEL);
 		map_page(v, p, f);
 #ifdef CONFIG_PPC_STD_MMU_32
@@ -403,7 +371,7 @@ static int __change_page_attr(struct page *page, pgprot_t prot)
 	BUG_ON(PageHighMem(page));
 	address = (unsigned long)page_address(page);
 
-	if (v_mapped_by_bats(address) || v_mapped_by_tlbcam(address))
+	if (v_block_mapped(address))
 		return 0;
 	if (!get_pteptr(&init_mm, address, &kpte, &kpmd))
 		return -EINVAL;
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index cdf2123d4..347106080 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -88,7 +88,7 @@ static __ref void *early_alloc_pgtable(unsigned long size)
  * map_kernel_page adds an entry to the ioremap page table
  * and adds an entry to the HPT, possibly bolting it
  */
-int map_kernel_page(unsigned long ea, unsigned long pa, int flags)
+int map_kernel_page(unsigned long ea, unsigned long pa, unsigned long flags)
 {
 	pgd_t *pgdp;
 	pud_t *pudp;
@@ -403,7 +403,7 @@ static pte_t *__alloc_for_cache(struct mm_struct *mm, int kernel)
 	 * count.
 	 */
 	if (likely(!mm->context.pte_frag)) {
-		atomic_set(&page->_count, PTE_FRAG_NR);
+		set_page_count(page, PTE_FRAG_NR);
 		mm->context.pte_frag = ret + PTE_FRAG_SIZE;
 	}
 	spin_unlock(&mm->page_table_lock);
@@ -749,7 +749,7 @@ pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot)
 {
 	unsigned long pmdv;
 
-	pmdv = pfn << PTE_RPN_SHIFT;
+	pmdv = (pfn << PTE_RPN_SHIFT) & PTE_RPN_MASK;
 	return pmd_set_protbits(__pmd(pmdv), pgprot);
 }
 
@@ -817,6 +817,13 @@ pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
 
 int has_transparent_hugepage(void)
 {
+
+	BUILD_BUG_ON_MSG((PMD_SHIFT - PAGE_SHIFT) >= MAX_ORDER,
+		"hugepages can't be allocated by the buddy allocator");
+
+	BUILD_BUG_ON_MSG((PMD_SHIFT - PAGE_SHIFT) < 2,
+			 "We need more than 2 pages to do deferred thp split");
+
 	if (!mmu_has_feature(MMU_FTR_16M_PAGE))
 		return 0;
 	/*
diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c
index 6b2f3e457..2a049fb85 100644
--- a/arch/powerpc/mm/ppc_mmu_32.c
+++ b/arch/powerpc/mm/ppc_mmu_32.c
@@ -49,7 +49,7 @@ struct batrange {		/* stores address ranges mapped by BATs */
 /*
  * Return PA for this VA if it is mapped by a BAT, or 0
  */
-phys_addr_t v_mapped_by_bats(unsigned long va)
+phys_addr_t v_block_mapped(unsigned long va)
 {
 	int b;
 	for (b = 0; b < 4; ++b)
@@ -61,7 +61,7 @@ phys_addr_t v_mapped_by_bats(unsigned long va)
 /*
  * Return VA for a given PA or 0 if not mapped
  */
-unsigned long p_mapped_by_bats(phys_addr_t pa)
+unsigned long p_block_mapped(phys_addr_t pa)
 {
 	int b;
 	for (b = 0; b < 4; ++b)
diff --git a/arch/powerpc/mm/tlb_low_64e.S b/arch/powerpc/mm/tlb_low_64e.S
index 29d6987c3..eb82d787d 100644
--- a/arch/powerpc/mm/tlb_low_64e.S
+++ b/arch/powerpc/mm/tlb_low_64e.S
@@ -895,7 +895,7 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_USE_PAIRED_MAS)
 BEGIN_MMU_FTR_SECTION
 virt_page_table_tlb_miss_done:
 
-	/* We have overriden MAS2:EPN but currently our primary TLB miss
+	/* We have overridden MAS2:EPN but currently our primary TLB miss
 	 * handler will always restore it so that should not be an issue,
 	 * if we ever optimize the primary handler to not write MAS2 on
 	 * some cases, we'll have to restore MAS2:EPN here based on the
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index bb04e4df3..f46684885 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -640,9 +640,7 @@ static void early_init_this_mmu(void)
 		 * transient mapping would cause problems.
 		 */
 #ifdef CONFIG_SMP
-		if (cpu != boot_cpuid &&
-		    (cpu != cpu_first_thread_sibling(cpu) ||
-		     cpu == cpu_first_thread_sibling(boot_cpuid)))
+		if (hweight32(get_tensr()) > 1)
 			map = false;
 #endif
 
diff --git a/arch/powerpc/mm/tlb_nohash_low.S b/arch/powerpc/mm/tlb_nohash_low.S
index 68c477592..eabecfcae 100644
--- a/arch/powerpc/mm/tlb_nohash_low.S
+++ b/arch/powerpc/mm/tlb_nohash_low.S
@@ -108,7 +108,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_47x)
 	blr
 2:
 #ifdef CONFIG_PPC_47x
-	oris	r7,r6,0x8000	/* specify way explicitely */
+	oris	r7,r6,0x8000	/* specify way explicitly */
 	clrrwi	r4,r3,12	/* get an EPN for the hashing with V = 0 */
 	ori	r4,r4,PPC47x_TLBE_SIZE
 	tlbwe   r4,r7,0		/* write it */
@@ -149,7 +149,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_47x)
 	li	r3,-1		/* Current set */
 	lis	r10,tlb_47x_boltmap@h
 	ori	r10,r10,tlb_47x_boltmap@l
-	lis	r7,0x8000	/* Specify way explicitely */
+	lis	r7,0x8000	/* Specify way explicitly */
 
 	b	9f		/* For each set */