Merge branch 'master' into x86/memblock

Conflicts & resolutions:

* arch/x86/xen/setup.c

	dc91c728fd "xen: allow extra memory to be in multiple regions"
	24aa07882b "memblock, x86: Replace memblock_x86_reserve/free..."

	conflicted on xen_add_extra_mem() updates.  The resolution is
	trivial as the latter just want to replace
	memblock_x86_reserve_range() with memblock_reserve().

* drivers/pci/intel-iommu.c

	166e9278a3f "x86/ia64: intel-iommu: move to drivers/iommu/"
	5dfe8660a3d "bootmem: Replace work_with_active_regions() with..."

	conflicted as the former moved the file under drivers/iommu/.
	Resolved by applying the chnages from the latter on the moved
	file.

* mm/Kconfig

	6661672053a "memblock: add NO_BOOTMEM config symbol"
	c378ddd53f9 "memblock, x86: Make ARCH_DISCARD_MEMBLOCK a config option"

	conflicted trivially.  Both added config options.  Just
	letting both add their own options resolves the conflict.

* mm/memblock.c

	d1f0ece6cdc "mm/memblock.c: small function definition fixes"
	ed7b56a799c "memblock: Remove memblock_memory_can_coalesce()"

	confliected.  The former updates function removed by the
	latter.  Resolution is trivial.

Signed-off-by: Tejun Heo <tj@kernel.org>

24 files changed, 984 insertions, 203 deletions

diff --git a/arch/powerpc/mm/44x_mmu.c b/arch/powerpc/mm/44x_mmu.c
index 024acab..f60e006 100644
--- a/arch/powerpc/mm/44x_mmu.c
+++ b/arch/powerpc/mm/44x_mmu.c
@@ -186,10 +186,11 @@ void __init MMU_init_hw(void)
 unsigned long __init mmu_mapin_ram(unsigned long top)
 {
 	unsigned long addr;
+	unsigned long memstart = memstart_addr & ~(PPC_PIN_SIZE - 1);
 
 	/* Pin in enough TLBs to cover any lowmem not covered by the
 	 * initial 256M mapping established in head_44x.S */
-	for (addr = PPC_PIN_SIZE; addr < lowmem_end_addr;
+	for (addr = memstart + PPC_PIN_SIZE; addr < lowmem_end_addr;
 	     addr += PPC_PIN_SIZE) {
 		if (mmu_has_feature(MMU_FTR_TYPE_47x))
 			ppc47x_pin_tlb(addr + PAGE_OFFSET, addr);
@@ -218,19 +219,25 @@ unsigned long __init mmu_mapin_ram(unsigned long top)
 void setup_initial_memory_limit(phys_addr_t first_memblock_base,
 				phys_addr_t first_memblock_size)
 {
+	u64 size;
+
+#ifndef CONFIG_RELOCATABLE
 	/* We don't currently support the first MEMBLOCK not mapping 0
 	 * physical on those processors
 	 */
 	BUG_ON(first_memblock_base != 0);
+#endif
 
 	/* 44x has a 256M TLB entry pinned at boot */
-	memblock_set_current_limit(min_t(u64, first_memblock_size, PPC_PIN_SIZE));
+	size = (min_t(u64, first_memblock_size, PPC_PIN_SIZE));
+	memblock_set_current_limit(first_memblock_base + size);
 }
 
 #ifdef CONFIG_SMP
 void __cpuinit mmu_init_secondary(int cpu)
 {
 	unsigned long addr;
+	unsigned long memstart = memstart_addr & ~(PPC_PIN_SIZE - 1);
 
 	/* Pin in enough TLBs to cover any lowmem not covered by the
 	 * initial 256M mapping established in head_44x.S
@@ -241,7 +248,7 @@ void __cpuinit mmu_init_secondary(int cpu)
 	 * stack. current (r2) isn't initialized, smp_processor_id()
 	 * will not work, current thread info isn't accessible, ...
 	 */
-	for (addr = PPC_PIN_SIZE; addr < lowmem_end_addr;
+	for (addr = memstart + PPC_PIN_SIZE; addr < lowmem_end_addr;
 	     addr += PPC_PIN_SIZE) {
 		if (mmu_has_feature(MMU_FTR_TYPE_47x))
 			ppc47x_pin_tlb(addr + PAGE_OFFSET, addr);
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index bdca46e..991ee81 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -29,6 +29,7 @@ obj-$(CONFIG_PPC_MM_SLICES)	+= slice.o
 ifeq ($(CONFIG_HUGETLB_PAGE),y)
 obj-y				+= hugetlbpage.o
 obj-$(CONFIG_PPC_STD_MMU_64)	+= hugetlbpage-hash64.o
+obj-$(CONFIG_PPC_BOOK3E_MMU)	+= hugetlbpage-book3e.o
 endif
 obj-$(CONFIG_PPC_SUBPAGE_PROT)	+= subpage-prot.o
 obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-noncoherent.o
diff --git a/arch/powerpc/mm/dma-noncoherent.c b/arch/powerpc/mm/dma-noncoherent.c
index b42f76c..329be36 100644
--- a/arch/powerpc/mm/dma-noncoherent.c
+++ b/arch/powerpc/mm/dma-noncoherent.c
@@ -30,6 +30,7 @@
 #include <linux/types.h>
 #include <linux/highmem.h>
 #include <linux/dma-mapping.h>
+#include <linux/export.h>
 
 #include <asm/tlbflush.h>
 
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index ad35f66..5efe8c9 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -174,7 +174,7 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 		die("Weird page fault", regs, SIGSEGV);
 	}
 
-	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address);
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 
 	/* When running in the kernel we expect faults to occur only to
 	 * addresses in user space.  All other faults represent errors in the
@@ -320,7 +320,7 @@ good_area:
 	}
 	if (ret & VM_FAULT_MAJOR) {
 		current->maj_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0,
+		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
 				     regs, address);
 #ifdef CONFIG_PPC_SMLPAR
 		if (firmware_has_feature(FW_FEATURE_CMO)) {
@@ -331,7 +331,7 @@ good_area:
 #endif
 	} else {
 		current->min_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0,
+		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
 				     regs, address);
 	}
 	up_read(&mm->mmap_sem);
diff --git a/arch/powerpc/mm/fsl_booke_mmu.c b/arch/powerpc/mm/fsl_booke_mmu.c
index f7802c8..66a6fd3 100644
--- a/arch/powerpc/mm/fsl_booke_mmu.c
+++ b/arch/powerpc/mm/fsl_booke_mmu.c
@@ -101,17 +101,17 @@ unsigned long p_mapped_by_tlbcam(phys_addr_t pa)
 
 /*
  * Set up a variable-size TLB entry (tlbcam). The parameters are not checked;
- * in particular size must be a power of 4 between 4k and 256M (or 1G, for cpus
- * that support extended page sizes).  Note that while some cpus support a
- * page size of 4G, we don't allow its use here.
+ * in particular size must be a power of 4 between 4k and the max supported by
+ * an implementation; max may further be limited by what can be represented in
+ * an unsigned long (for example, 32-bit implementations cannot support a 4GB
+ * size).
  */
 static void settlbcam(int index, unsigned long virt, phys_addr_t phys,
 		unsigned long size, unsigned long flags, unsigned int pid)
 {
-	unsigned int tsize, lz;
+	unsigned int tsize;
 
-	asm (PPC_CNTLZL "%0,%1" : "=r" (lz) : "r" (size));
-	tsize = 21 - lz;
+	tsize = __ilog2(size) - 10;
 
 #ifdef CONFIG_SMP
 	if ((flags & _PAGE_NO_CACHE) == 0)
@@ -146,29 +146,36 @@ static void settlbcam(int index, unsigned long virt, phys_addr_t phys,
 	loadcam_entry(index);
 }
 
+unsigned long calc_cam_sz(unsigned long ram, unsigned long virt,
+			  phys_addr_t phys)
+{
+	unsigned int camsize = __ilog2(ram) & ~1U;
+	unsigned int align = __ffs(virt | phys) & ~1U;
+	unsigned long max_cam = (mfspr(SPRN_TLB1CFG) >> 16) & 0xf;
+
+	/* Convert (4^max) kB to (2^max) bytes */
+	max_cam = max_cam * 2 + 10;
+
+	if (camsize > align)
+		camsize = align;
+	if (camsize > max_cam)
+		camsize = max_cam;
+
+	return 1UL << camsize;
+}
+
 unsigned long map_mem_in_cams(unsigned long ram, int max_cam_idx)
 {
 	int i;
 	unsigned long virt = PAGE_OFFSET;
 	phys_addr_t phys = memstart_addr;
 	unsigned long amount_mapped = 0;
-	unsigned long max_cam = (mfspr(SPRN_TLB1CFG) >> 16) & 0xf;
-
-	/* Convert (4^max) kB to (2^max) bytes */
-	max_cam = max_cam * 2 + 10;
 
 	/* Calculate CAM values */
 	for (i = 0; ram && i < max_cam_idx; i++) {
-		unsigned int camsize = __ilog2(ram) & ~1U;
-		unsigned int align = __ffs(virt | phys) & ~1U;
 		unsigned long cam_sz;
 
-		if (camsize > align)
-			camsize = align;
-		if (camsize > max_cam)
-			camsize = max_cam;
-
-		cam_sz = 1UL << camsize;
+		cam_sz = calc_cam_sz(ram, virt, phys);
 		settlbcam(i, virt, phys, cam_sz, PAGE_KERNEL_X, 0);
 
 		ram -= cam_sz;
diff --git a/arch/powerpc/mm/gup.c b/arch/powerpc/mm/gup.c
index fec1320..d7efdbf 100644
--- a/arch/powerpc/mm/gup.c
+++ b/arch/powerpc/mm/gup.c
@@ -16,16 +16,6 @@
 
 #ifdef __HAVE_ARCH_PTE_SPECIAL
 
-static inline void get_huge_page_tail(struct page *page)
-{
-	/*
-	 * __split_huge_page_refcount() cannot run
-	 * from under us.
-	 */
-	VM_BUG_ON(atomic_read(&page->_count) < 0);
-	atomic_inc(&page->_count);
-}
-
 /*
  * The performance critical leaf functions are made noinline otherwise gcc
  * inlines everything into a single function which results in too much
@@ -57,8 +47,6 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 			put_page(page);
 			return 0;
 		}
-		if (PageTail(page))
-			get_huge_page_tail(page);
 		pages[*nr] = page;
 		(*nr)++;
 
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index dfd7648..90039bc 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -37,7 +37,7 @@
 
 #define HPTE_LOCK_BIT 3
 
-static DEFINE_RAW_SPINLOCK(native_tlbie_lock);
+DEFINE_RAW_SPINLOCK(native_tlbie_lock);
 
 static inline void __tlbie(unsigned long va, int psize, int ssize)
 {
@@ -51,7 +51,7 @@ static inline void __tlbie(unsigned long va, int psize, int ssize)
 		va &= ~0xffful;
 		va |= ssize << 8;
 		asm volatile(ASM_FTR_IFCLR("tlbie %0,0", PPC_TLBIE(%1,%0), %2)
-			     : : "r" (va), "r"(0), "i" (CPU_FTR_HVMODE_206)
+			     : : "r" (va), "r"(0), "i" (CPU_FTR_ARCH_206)
 			     : "memory");
 		break;
 	default:
@@ -61,7 +61,7 @@ static inline void __tlbie(unsigned long va, int psize, int ssize)
 		va |= ssize << 8;
 		va |= 1; /* L */
 		asm volatile(ASM_FTR_IFCLR("tlbie %0,1", PPC_TLBIE(%1,%0), %2)
-			     : : "r" (va), "r"(0), "i" (CPU_FTR_HVMODE_206)
+			     : : "r" (va), "r"(0), "i" (CPU_FTR_ARCH_206)
 			     : "memory");
 		break;
 	}
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 26b2872..2d28218 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -27,6 +27,7 @@
 #include <linux/proc_fs.h>
 #include <linux/stat.h>
 #include <linux/sysctl.h>
+#include <linux/export.h>
 #include <linux/ctype.h>
 #include <linux/cache.h>
 #include <linux/init.h>
@@ -105,9 +106,6 @@ int mmu_kernel_ssize = MMU_SEGSIZE_256M;
 int mmu_highuser_ssize = MMU_SEGSIZE_256M;
 u16 mmu_slb_size = 64;
 EXPORT_SYMBOL_GPL(mmu_slb_size);
-#ifdef CONFIG_HUGETLB_PAGE
-unsigned int HPAGE_SHIFT;
-#endif
 #ifdef CONFIG_PPC_64K_PAGES
 int mmu_ci_restrictions;
 #endif
@@ -534,11 +532,11 @@ static unsigned long __init htab_get_table_size(void)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-void create_section_mapping(unsigned long start, unsigned long end)
+int create_section_mapping(unsigned long start, unsigned long end)
 {
-	BUG_ON(htab_bolt_mapping(start, end, __pa(start),
+	return htab_bolt_mapping(start, end, __pa(start),
 				 pgprot_val(PAGE_KERNEL), mmu_linear_psize,
-				 mmu_kernel_ssize));
+				 mmu_kernel_ssize);
 }
 
 int remove_section_mapping(unsigned long start, unsigned long end)
diff --git a/arch/powerpc/mm/hugetlbpage-book3e.c b/arch/powerpc/mm/hugetlbpage-book3e.c
new file mode 100644
index 0000000..343ad0b
--- /dev/null
+++ b/arch/powerpc/mm/hugetlbpage-book3e.c
@@ -0,0 +1,121 @@
+/*
+ * PPC Huge TLB Page Support for Book3E MMU
+ *
+ * Copyright (C) 2009 David Gibson, IBM Corporation.
+ * Copyright (C) 2011 Becky Bruce, Freescale Semiconductor
+ *
+ */
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+
+static inline int mmu_get_tsize(int psize)
+{
+	return mmu_psize_defs[psize].enc;
+}
+
+static inline int book3e_tlb_exists(unsigned long ea, unsigned long pid)
+{
+	int found = 0;
+
+	mtspr(SPRN_MAS6, pid << 16);
+	if (mmu_has_feature(MMU_FTR_USE_TLBRSRV)) {
+		asm volatile(
+			"li	%0,0\n"
+			"tlbsx.	0,%1\n"
+			"bne	1f\n"
+			"li	%0,1\n"
+			"1:\n"
+			: "=&r"(found) : "r"(ea));
+	} else {
+		asm volatile(
+			"tlbsx	0,%1\n"
+			"mfspr	%0,0x271\n"
+			"srwi	%0,%0,31\n"
+			: "=&r"(found) : "r"(ea));
+	}
+
+	return found;
+}
+
+void book3e_hugetlb_preload(struct mm_struct *mm, unsigned long ea, pte_t pte)
+{
+	unsigned long mas1, mas2;
+	u64 mas7_3;
+	unsigned long psize, tsize, shift;
+	unsigned long flags;
+
+#ifdef CONFIG_PPC_FSL_BOOK3E
+	int index, lz, ncams;
+	struct vm_area_struct *vma;
+#endif
+
+	if (unlikely(is_kernel_addr(ea)))
+		return;
+
+#ifdef CONFIG_PPC_MM_SLICES
+	psize = mmu_get_tsize(get_slice_psize(mm, ea));
+	tsize = mmu_get_psize(psize);
+	shift = mmu_psize_defs[psize].shift;
+#else
+	vma = find_vma(mm, ea);
+	psize = vma_mmu_pagesize(vma);	/* returns actual size in bytes */
+	asm (PPC_CNTLZL "%0,%1" : "=r" (lz) : "r" (psize));
+	shift = 31 - lz;
+	tsize = 21 - lz;
+#endif
+
+	/*
+	 * We can't be interrupted while we're setting up the MAS
+	 * regusters or after we've confirmed that no tlb exists.
+	 */
+	local_irq_save(flags);
+
+	if (unlikely(book3e_tlb_exists(ea, mm->context.id))) {
+		local_irq_restore(flags);
+		return;
+	}
+
+#ifdef CONFIG_PPC_FSL_BOOK3E
+	ncams = mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY;
+
+	/* We have to use the CAM(TLB1) on FSL parts for hugepages */
+	index = __get_cpu_var(next_tlbcam_idx);
+	mtspr(SPRN_MAS0, MAS0_ESEL(index) | MAS0_TLBSEL(1));
+
+	/* Just round-robin the entries and wrap when we hit the end */
+	if (unlikely(index == ncams - 1))
+		__get_cpu_var(next_tlbcam_idx) = tlbcam_index;
+	else
+		__get_cpu_var(next_tlbcam_idx)++;
+#endif
+	mas1 = MAS1_VALID | MAS1_TID(mm->context.id) | MAS1_TSIZE(tsize);
+	mas2 = ea & ~((1UL << shift) - 1);
+	mas2 |= (pte_val(pte) >> PTE_WIMGE_SHIFT) & MAS2_WIMGE_MASK;
+	mas7_3 = (u64)pte_pfn(pte) << PAGE_SHIFT;
+	mas7_3 |= (pte_val(pte) >> PTE_BAP_SHIFT) & MAS3_BAP_MASK;
+	if (!pte_dirty(pte))
+		mas7_3 &= ~(MAS3_SW|MAS3_UW);
+
+	mtspr(SPRN_MAS1, mas1);
+	mtspr(SPRN_MAS2, mas2);
+
+	if (mmu_has_feature(MMU_FTR_USE_PAIRED_MAS)) {
+		mtspr(SPRN_MAS7_MAS3, mas7_3);
+	} else {
+		mtspr(SPRN_MAS7, upper_32_bits(mas7_3));
+		mtspr(SPRN_MAS3, lower_32_bits(mas7_3));
+	}
+
+	asm volatile ("tlbwe");
+
+	local_irq_restore(flags);
+}
+
+void flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
+{
+	struct hstate *hstate = hstate_file(vma->vm_file);
+	unsigned long tsize = huge_page_shift(hstate) - 10;
+
+	__flush_tlb_page(vma ? vma->vm_mm : NULL, vmaddr, tsize, 0);
+
+}
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 0b9a5c1..8558b57 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -1,7 +1,8 @@
 /*
- * PPC64 (POWER4) Huge TLB Page Support for Kernel.
+ * PPC Huge TLB Page Support for Kernel.
  *
  * Copyright (C) 2003 David Gibson, IBM Corporation.
+ * Copyright (C) 2011 Becky Bruce, Freescale Semiconductor
  *
  * Based on the IA-32 version:
  * Copyright (C) 2002, Rohit Seth <rohit.seth@intel.com>
@@ -11,24 +12,40 @@
 #include <linux/io.h>
 #include <linux/slab.h>
 #include <linux/hugetlb.h>
+#include <linux/of_fdt.h>
+#include <linux/memblock.h>
+#include <linux/bootmem.h>
+#include <linux/moduleparam.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
+#include <asm/setup.h>
 
 #define PAGE_SHIFT_64K	16
 #define PAGE_SHIFT_16M	24
 #define PAGE_SHIFT_16G	34
 
-#define MAX_NUMBER_GPAGES	1024
+unsigned int HPAGE_SHIFT;
 
-/* Tracks the 16G pages after the device tree is scanned and before the
- * huge_boot_pages list is ready.  */
-static unsigned long gpage_freearray[MAX_NUMBER_GPAGES];
+/*
+ * Tracks gpages after the device tree is scanned and before the
+ * huge_boot_pages list is ready.  On 64-bit implementations, this is
+ * just used to track 16G pages and so is a single array.  32-bit
+ * implementations may have more than one gpage size due to limitations
+ * of the memory allocators, so we need multiple arrays
+ */
+#ifdef CONFIG_PPC64
+#define MAX_NUMBER_GPAGES	1024
+static u64 gpage_freearray[MAX_NUMBER_GPAGES];
 static unsigned nr_gpages;
-
-/* Flag to mark huge PD pointers.  This means pmd_bad() and pud_bad()
- * will choke on pointers to hugepte tables, which is handy for
- * catching screwups early. */
+#else
+#define MAX_NUMBER_GPAGES	128
+struct psize_gpages {
+	u64 gpage_list[MAX_NUMBER_GPAGES];
+	unsigned int nr_gpages;
+};
+static struct psize_gpages gpage_freearray[MMU_PAGE_COUNT];
+#endif
 
 static inline int shift_to_mmu_psize(unsigned int shift)
 {
@@ -49,25 +66,6 @@ static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize)
 
 #define hugepd_none(hpd)	((hpd).pd == 0)
 
-static inline pte_t *hugepd_page(hugepd_t hpd)
-{
-	BUG_ON(!hugepd_ok(hpd));
-	return (pte_t *)((hpd.pd & ~HUGEPD_SHIFT_MASK) | 0xc000000000000000);
-}
-
-static inline unsigned int hugepd_shift(hugepd_t hpd)
-{
-	return hpd.pd & HUGEPD_SHIFT_MASK;
-}
-
-static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr, unsigned pdshift)
-{
-	unsigned long idx = (addr & ((1UL << pdshift) - 1)) >> hugepd_shift(*hpdp);
-	pte_t *dir = hugepd_page(*hpdp);
-
-	return dir + idx;
-}
-
 pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift)
 {
 	pgd_t *pg;
@@ -93,7 +91,7 @@ pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift
 			if (is_hugepd(pm))
 				hpdp = (hugepd_t *)pm;
 			else if (!pmd_none(*pm)) {
-				return pte_offset_map(pm, ea);
+				return pte_offset_kernel(pm, ea);
 			}
 		}
 	}
@@ -114,8 +112,18 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
 			   unsigned long address, unsigned pdshift, unsigned pshift)
 {
-	pte_t *new = kmem_cache_zalloc(PGT_CACHE(pdshift - pshift),
-				       GFP_KERNEL|__GFP_REPEAT);
+	struct kmem_cache *cachep;
+	pte_t *new;
+
+#ifdef CONFIG_PPC64
+	cachep = PGT_CACHE(pdshift - pshift);
+#else
+	int i;
+	int num_hugepd = 1 << (pshift - pdshift);
+	cachep = hugepte_cache;
+#endif
+
+	new = kmem_cache_zalloc(cachep, GFP_KERNEL|__GFP_REPEAT);
 
 	BUG_ON(pshift > HUGEPD_SHIFT_MASK);
 	BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK);
@@ -124,10 +132,31 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
 		return -ENOMEM;
 
 	spin_lock(&mm->page_table_lock);
+#ifdef CONFIG_PPC64
 	if (!hugepd_none(*hpdp))
-		kmem_cache_free(PGT_CACHE(pdshift - pshift), new);
+		kmem_cache_free(cachep, new);
 	else
-		hpdp->pd = ((unsigned long)new & ~0x8000000000000000) | pshift;
+		hpdp->pd = ((unsigned long)new & ~PD_HUGE) | pshift;
+#else
+	/*
+	 * We have multiple higher-level entries that point to the same
+	 * actual pte location.  Fill in each as we go and backtrack on error.
+	 * We need all of these so the DTLB pgtable walk code can find the
+	 * right higher-level entry without knowing if it's a hugepage or not.
+	 */
+	for (i = 0; i < num_hugepd; i++, hpdp++) {
+		if (unlikely(!hugepd_none(*hpdp)))
+			break;
+		else
+			hpdp->pd = ((unsigned long)new & ~PD_HUGE) | pshift;
+	}
+	/* If we bailed from the for loop early, an error occurred, clean up */
+	if (i < num_hugepd) {
+		for (i = i - 1 ; i >= 0; i--, hpdp--)
+			hpdp->pd = 0;
+		kmem_cache_free(cachep, new);
+	}
+#endif
 	spin_unlock(&mm->page_table_lock);
 	return 0;
 }
@@ -169,11 +198,132 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz
 	return hugepte_offset(hpdp, addr, pdshift);
 }
 
+#ifdef CONFIG_PPC32
+/* Build list of addresses of gigantic pages.  This function is used in early
+ * boot before the buddy or bootmem allocator is setup.
+ */
+void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages)
+{
+	unsigned int idx = shift_to_mmu_psize(__ffs(page_size));
+	int i;
+
+	if (addr == 0)
+		return;
+
+	gpage_freearray[idx].nr_gpages = number_of_pages;
+
+	for (i = 0; i < number_of_pages; i++) {
+		gpage_freearray[idx].gpage_list[i] = addr;
+		addr += page_size;
+	}
+}
+
+/*
+ * Moves the gigantic page addresses from the temporary list to the
+ * huge_boot_pages list.
+ */
+int alloc_bootmem_huge_page(struct hstate *hstate)
+{
+	struct huge_bootmem_page *m;
+	int idx = shift_to_mmu_psize(hstate->order + PAGE_SHIFT);
+	int nr_gpages = gpage_freearray[idx].nr_gpages;
+
+	if (nr_gpages == 0)
+		return 0;
+
+#ifdef CONFIG_HIGHMEM
+	/*
+	 * If gpages can be in highmem we can't use the trick of storing the
+	 * data structure in the page; allocate space for this
+	 */
+	m = alloc_bootmem(sizeof(struct huge_bootmem_page));
+	m->phys = gpage_freearray[idx].gpage_list[--nr_gpages];
+#else
+	m = phys_to_virt(gpage_freearray[idx].gpage_list[--nr_gpages]);
+#endif
+
+	list_add(&m->list, &huge_boot_pages);
+	gpage_freearray[idx].nr_gpages = nr_gpages;
+	gpage_freearray[idx].gpage_list[nr_gpages] = 0;
+	m->hstate = hstate;
+
+	return 1;
+}
+/*
+ * Scan the command line hugepagesz= options for gigantic pages; store those in
+ * a list that we use to allocate the memory once all options are parsed.
+ */
+
+unsigned long gpage_npages[MMU_PAGE_COUNT];
+
+static int __init do_gpage_early_setup(char *param, char *val)
+{
+	static phys_addr_t size;
+	unsigned long npages;
+
+	/*
+	 * The hugepagesz and hugepages cmdline options are interleaved.  We
+	 * use the size variable to keep track of whether or not this was done
+	 * properly and skip over instances where it is incorrect.  Other
+	 * command-line parsing code will issue warnings, so we don't need to.
+	 *
+	 */
+	if ((strcmp(param, "default_hugepagesz") == 0) ||
+	    (strcmp(param, "hugepagesz") == 0)) {
+		size = memparse(val, NULL);
+	} else if (strcmp(param, "hugepages") == 0) {
+		if (size != 0) {
+			if (sscanf(val, "%lu", &npages) <= 0)
+				npages = 0;
+			gpage_npages[shift_to_mmu_psize(__ffs(size))] = npages;
+			size = 0;
+		}
+	}
+	return 0;
+}
+
+
+/*
+ * This function allocates physical space for pages that are larger than the
+ * buddy allocator can handle.  We want to allocate these in highmem because
+ * the amount of lowmem is limited.  This means that this function MUST be
+ * called before lowmem_end_addr is set up in MMU_init() in order for the lmb
+ * allocate to grab highmem.
+ */
+void __init reserve_hugetlb_gpages(void)
+{
+	static __initdata char cmdline[COMMAND_LINE_SIZE];
+	phys_addr_t size, base;
+	int i;
+
+	strlcpy(cmdline, boot_command_line, COMMAND_LINE_SIZE);
+	parse_args("hugetlb gpages", cmdline, NULL, 0, &do_gpage_early_setup);
+
+	/*
+	 * Walk gpage list in reverse, allocating larger page sizes first.
+	 * Skip over unsupported sizes, or sizes that have 0 gpages allocated.
+	 * When we reach the point in the list where pages are no longer
+	 * considered gpages, we're done.
+	 */
+	for (i = MMU_PAGE_COUNT-1; i >= 0; i--) {
+		if (mmu_psize_defs[i].shift == 0 || gpage_npages[i] == 0)
+			continue;
+		else if (mmu_psize_to_shift(i) < (MAX_ORDER + PAGE_SHIFT))
+			break;
+
+		size = (phys_addr_t)(1ULL << mmu_psize_to_shift(i));
+		base = memblock_alloc_base(size * gpage_npages[i], size,
+					   MEMBLOCK_ALLOC_ANYWHERE);
+		add_gpage(base, size, gpage_npages[i]);
+	}
+}
+
+#else /* PPC64 */
+
 /* Build list of addresses of gigantic pages.  This function is used in early
  * boot before the buddy or bootmem allocator is setup.
  */
-void add_gpage(unsigned long addr, unsigned long page_size,
-	unsigned long number_of_pages)
+void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages)
 {
 	if (!addr)
 		return;
@@ -199,19 +349,79 @@ int alloc_bootmem_huge_page(struct hstate *hstate)
 	m->hstate = hstate;
 	return 1;
 }
+#endif
 
 int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
 {
 	return 0;
 }
 
+#ifdef CONFIG_PPC32
+#define HUGEPD_FREELIST_SIZE \
+	((PAGE_SIZE - sizeof(struct hugepd_freelist)) / sizeof(pte_t))
+
+struct hugepd_freelist {
+	struct rcu_head	rcu;
+	unsigned int index;
+	void *ptes[0];
+};
+
+static DEFINE_PER_CPU(struct hugepd_freelist *, hugepd_freelist_cur);
+
+static void hugepd_free_rcu_callback(struct rcu_head *head)
+{
+	struct hugepd_freelist *batch =
+		container_of(head, struct hugepd_freelist, rcu);
+	unsigned int i;
+
+	for (i = 0; i < batch->index; i++)
+		kmem_cache_free(hugepte_cache, batch->ptes[i]);
+
+	free_page((unsigned long)batch);
+}
+
+static void hugepd_free(struct mmu_gather *tlb, void *hugepte)
+{
+	struct hugepd_freelist **batchp;
+
+	batchp = &__get_cpu_var(hugepd_freelist_cur);
+
+	if (atomic_read(&tlb->mm->mm_users) < 2 ||
+	    cpumask_equal(mm_cpumask(tlb->mm),
+			  cpumask_of(smp_processor_id()))) {
+		kmem_cache_free(hugepte_cache, hugepte);
+		return;
+	}
+
+	if (*batchp == NULL) {
+		*batchp = (struct hugepd_freelist *)__get_free_page(GFP_ATOMIC);
+		(*batchp)->index = 0;
+	}
+
+	(*batchp)->ptes[(*batchp)->index++] = hugepte;
+	if ((*batchp)->index == HUGEPD_FREELIST_SIZE) {
+		call_rcu_sched(&(*batchp)->rcu, hugepd_free_rcu_callback);
+		*batchp = NULL;
+	}
+}
+#endif
+
 static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshift,
 			      unsigned long start, unsigned long end,
 			      unsigned long floor, unsigned long ceiling)
 {
 	pte_t *hugepte = hugepd_page(*hpdp);
-	unsigned shift = hugepd_shift(*hpdp);
+	int i;
+
 	unsigned long pdmask = ~((1UL << pdshift) - 1);
+	unsigned int num_hugepd = 1;
+
+#ifdef CONFIG_PPC64
+	unsigned int shift = hugepd_shift(*hpdp);
+#else
+	/* Note: On 32-bit the hpdp may be the first of several */
+	num_hugepd = (1 << (hugepd_shift(*hpdp) - pdshift));
+#endif
 
 	start &= pdmask;
 	if (start < floor)
@@ -224,9 +434,15 @@ static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshif
 	if (end - 1 > ceiling - 1)
 		return;
 
-	hpdp->pd = 0;
+	for (i = 0; i < num_hugepd; i++, hpdp++)
+		hpdp->pd = 0;
+
 	tlb->need_flush = 1;
+#ifdef CONFIG_PPC64
 	pgtable_free_tlb(tlb, hugepte, pdshift - shift);
+#else
+	hugepd_free(tlb, hugepte);
+#endif
 }
 
 static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
@@ -331,18 +547,27 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 	 * too.
 	 */
 
-	pgd = pgd_offset(tlb->mm, addr);
 	do {
 		next = pgd_addr_end(addr, end);
+		pgd = pgd_offset(tlb->mm, addr);
 		if (!is_hugepd(pgd)) {
 			if (pgd_none_or_clear_bad(pgd))
 				continue;
 			hugetlb_free_pud_range(tlb, pgd, addr, next, floor, ceiling);
 		} else {
+#ifdef CONFIG_PPC32
+			/*
+			 * Increment next by the size of the huge mapping since
+			 * on 32-bit there may be more than one entry at the pgd
+			 * level for a single hugepage, but all of them point to
+			 * the same kmem cache that holds the hugepte.
+			 */
+			next = addr + (1 << hugepd_shift(*(hugepd_t *)pgd));
+#endif
 			free_hugepd_range(tlb, (hugepd_t *)pgd, PGDIR_SHIFT,
 					  addr, next, floor, ceiling);
 		}
-	} while (pgd++, addr = next, addr != end);
+	} while (addr = next, addr != end);
 }
 
 struct page *
@@ -390,7 +615,7 @@ static noinline int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long add
 {
 	unsigned long mask;
 	unsigned long pte_end;
-	struct page *head, *page;
+	struct page *head, *page, *tail;
 	pte_t pte;
 	int refs;
 
@@ -413,6 +638,7 @@ static noinline int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long add
 	head = pte_page(pte);
 
 	page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
+	tail = page;
 	do {
 		VM_BUG_ON(compound_head(page) != head);
 		pages[*nr] = page;
@@ -428,10 +654,20 @@ static noinline int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long add
 
 	if (unlikely(pte_val(pte) != pte_val(*ptep))) {
 		/* Could be optimized better */
-		while (*nr) {
-			put_page(page);
-			(*nr)--;
-		}
+		*nr -= refs;
+		while (refs--)
+			put_page(head);
+		return 0;
+	}
+
+	/*
+	 * Any tail page need their mapcount reference taken before we
+	 * return.
+	 */
+	while (refs--) {
+		if (PageTail(tail))
+			get_huge_page_tail(tail);
+		tail++;
 	}
 
 	return 1;
@@ -466,17 +702,35 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 					unsigned long len, unsigned long pgoff,
 					unsigned long flags)
 {
+#ifdef CONFIG_PPC_MM_SLICES
 	struct hstate *hstate = hstate_file(file);
 	int mmu_psize = shift_to_mmu_psize(huge_page_shift(hstate));
 
 	return slice_get_unmapped_area(addr, len, flags, mmu_psize, 1, 0);
+#else
+	return get_unmapped_area(file, addr, len, pgoff, flags);
+#endif
 }
 
 unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
 {
+#ifdef CONFIG_PPC_MM_SLICES
 	unsigned int psize = get_slice_psize(vma->vm_mm, vma->vm_start);
 
 	return 1UL << mmu_psize_to_shift(psize);
+#else
+	if (!is_vm_hugetlb_page(vma))
+		return PAGE_SIZE;
+
+	return huge_page_size(hstate_vma(vma));
+#endif
+}
+
+static inline bool is_power_of_4(unsigned long x)
+{
+	if (is_power_of_2(x))
+		return (__ilog2(x) % 2) ? false : true;
+	return false;
 }
 
 static int __init add_huge_page_size(unsigned long long size)
@@ -486,9 +740,14 @@ static int __init add_huge_page_size(unsigned long long size)
 
 	/* Check that it is a page size supported by the hardware and
 	 * that it fits within pagetable and slice limits. */
+#ifdef CONFIG_PPC_FSL_BOOK3E
+	if ((size < PAGE_SIZE) || !is_power_of_4(size))
+		return -EINVAL;
+#else
 	if (!is_power_of_2(size)
 	    || (shift > SLICE_HIGH_SHIFT) || (shift <= PAGE_SHIFT))
 		return -EINVAL;
+#endif
 
 	if ((mmu_psize = shift_to_mmu_psize(shift)) < 0)
 		return -EINVAL;
@@ -525,6 +784,46 @@ static int __init hugepage_setup_sz(char *str)
 }
 __setup("hugepagesz=", hugepage_setup_sz);
 
+#ifdef CONFIG_FSL_BOOKE
+struct kmem_cache *hugepte_cache;
+static int __init hugetlbpage_init(void)
+{
+	int psize;
+
+	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
+		unsigned shift;
+
+		if (!mmu_psize_defs[psize].shift)
+			continue;
+
+		shift = mmu_psize_to_shift(psize);
+
+		/* Don't treat normal page sizes as huge... */
+		if (shift != PAGE_SHIFT)
+			if (add_huge_page_size(1ULL << shift) < 0)
+				continue;
+	}
+
+	/*
+	 * Create a kmem cache for hugeptes.  The bottom bits in the pte have
+	 * size information encoded in them, so align them to allow this
+	 */
+	hugepte_cache =  kmem_cache_create("hugepte-cache", sizeof(pte_t),
+					   HUGEPD_SHIFT_MASK + 1, 0, NULL);
+	if (hugepte_cache == NULL)
+		panic("%s: Unable to create kmem cache for hugeptes\n",
+		      __func__);
+
+	/* Default hpage size = 4M */
+	if (mmu_psize_defs[MMU_PAGE_4M].shift)
+		HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_4M].shift;
+	else
+		panic("%s: Unable to set default huge page size\n", __func__);
+
+
+	return 0;
+}
+#else
 static int __init hugetlbpage_init(void)
 {
 	int psize;
@@ -567,15 +866,23 @@ static int __init hugetlbpage_init(void)
 
 	return 0;
 }
-
+#endif
 module_init(hugetlbpage_init);
 
 void flush_dcache_icache_hugepage(struct page *page)
 {
 	int i;
+	void *start;
 
 	BUG_ON(!PageCompound(page));
 
-	for (i = 0; i < (1UL << compound_order(page)); i++)
-		__flush_dcache_icache(page_address(page+i));
+	for (i = 0; i < (1UL << compound_order(page)); i++) {
+		if (!PageHighMem(page)) {
+			__flush_dcache_icache(page_address(page+i));
+		} else {
+			start = kmap_atomic(page+i, KM_PPC_SYNC_ICACHE);
+			__flush_dcache_icache(start);
+			kunmap_atomic(start, KM_PPC_SYNC_ICACHE);
+		}
+	}
 }
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index 5de0f25..161cefd 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -32,6 +32,8 @@
 #include <linux/pagemap.h>
 #include <linux/memblock.h>
 #include <linux/gfp.h>
+#include <linux/slab.h>
+#include <linux/hugetlb.h>
 
 #include <asm/pgalloc.h>
 #include <asm/prom.h>
@@ -44,6 +46,7 @@
 #include <asm/tlb.h>
 #include <asm/sections.h>
 #include <asm/system.h>
+#include <asm/hugetlb.h>
 
 #include "mmu_decl.h"
 
@@ -123,6 +126,12 @@ void __init MMU_init(void)
 	/* parse args from command line */
 	MMU_setup();
 
+	/*
+	 * Reserve gigantic pages for hugetlb.  This MUST occur before
+	 * lowmem_end_addr is initialized below.
+	 */
+	reserve_hugetlb_gpages();
+
 	if (memblock.memory.cnt > 1) {
 #ifndef CONFIG_WII
 		memblock.memory.cnt = 1;
@@ -191,38 +200,6 @@ void __init *early_get_page(void)
 		return __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE));
 }
 
-/* Free up now-unused memory */
-static void free_sec(unsigned long start, unsigned long end, const char *name)
-{
-	unsigned long cnt = 0;
-
-	while (start < end) {
-		ClearPageReserved(virt_to_page(start));
-		init_page_count(virt_to_page(start));
-		free_page(start);
-		cnt++;
-		start += PAGE_SIZE;
- 	}
-	if (cnt) {
-		printk(" %ldk %s", cnt << (PAGE_SHIFT - 10), name);
-		totalram_pages += cnt;
-	}
-}
-
-void free_initmem(void)
-{
-#define FREESEC(TYPE) \
-	free_sec((unsigned long)(&__ ## TYPE ## _begin), \
-		 (unsigned long)(&__ ## TYPE ## _end), \
-		 #TYPE);
-
-	printk ("Freeing unused kernel memory:");
-	FREESEC(init);
- 	printk("\n");
-	ppc_md.progress = NULL;
-#undef FREESEC
-}
-
 #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)
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index f6dbb4c..e94b57f 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -83,22 +83,6 @@ EXPORT_SYMBOL_GPL(memstart_addr);
 phys_addr_t kernstart_addr;
 EXPORT_SYMBOL_GPL(kernstart_addr);
 
-void free_initmem(void)
-{
-	unsigned long addr;
-
-	addr = (unsigned long)__init_begin;
-	for (; addr < (unsigned long)__init_end; addr += PAGE_SIZE) {
-		memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
-		ClearPageReserved(virt_to_page(addr));
-		init_page_count(virt_to_page(addr));
-		free_page(addr);
-		totalram_pages++;
-	}
-	printk ("Freeing unused kernel memory: %luk freed\n",
-		((unsigned long)__init_end - (unsigned long)__init_begin) >> 10);
-}
-
 static void pgd_ctor(void *addr)
 {
 	memset(addr, 0, PGD_TABLE_SIZE);
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 29d4dde..2dd6bdd 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -17,7 +17,7 @@
  *
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
@@ -34,6 +34,7 @@
 #include <linux/suspend.h>
 #include <linux/memblock.h>
 #include <linux/hugetlb.h>
+#include <linux/slab.h>
 
 #include <asm/pgalloc.h>
 #include <asm/prom.h>
@@ -123,7 +124,8 @@ int arch_add_memory(int nid, u64 start, u64 size)
 	pgdata = NODE_DATA(nid);
 
 	start = (unsigned long)__va(start);
-	create_section_mapping(start, start + size);
+	if (create_section_mapping(start, start + size))
+		return -EINVAL;
 
 	/* this should work for most non-highmem platforms */
 	zone = pgdata->node_zones;
@@ -249,7 +251,7 @@ static int __init mark_nonram_nosave(void)
  */
 void __init paging_init(void)
 {
-	unsigned long total_ram = memblock_phys_mem_size();
+	unsigned long long total_ram = memblock_phys_mem_size();
 	phys_addr_t top_of_ram = memblock_end_of_DRAM();
 	unsigned long max_zone_pfns[MAX_NR_ZONES];
 
@@ -269,7 +271,7 @@ void __init paging_init(void)
 	kmap_prot = PAGE_KERNEL;
 #endif /* CONFIG_HIGHMEM */
 
-	printk(KERN_DEBUG "Top of RAM: 0x%llx, Total RAM: 0x%lx\n",
+	printk(KERN_DEBUG "Top of RAM: 0x%llx, Total RAM: 0x%llx\n",
 	       (unsigned long long)top_of_ram, total_ram);
 	printk(KERN_DEBUG "Memory hole size: %ldMB\n",
 	       (long int)((top_of_ram - total_ram) >> 20));
@@ -337,8 +339,9 @@ void __init mem_init(void)
 
 		highmem_mapnr = lowmem_end_addr >> PAGE_SHIFT;
 		for (pfn = highmem_mapnr; pfn < max_mapnr; ++pfn) {
+			phys_addr_t paddr = (phys_addr_t)pfn << PAGE_SHIFT;
 			struct page *page = pfn_to_page(pfn);
-			if (memblock_is_reserved(pfn << PAGE_SHIFT))
+			if (memblock_is_reserved(paddr))
 				continue;
 			ClearPageReserved(page);
 			init_page_count(page);
@@ -352,6 +355,15 @@ void __init mem_init(void)
 	}
 #endif /* CONFIG_HIGHMEM */
 
+#if defined(CONFIG_PPC_FSL_BOOK3E) && !defined(CONFIG_SMP)
+	/*
+	 * If smp is enabled, next_tlbcam_idx is initialized in the cpu up
+	 * functions.... do it here for the non-smp case.
+	 */
+	per_cpu(next_tlbcam_idx, smp_processor_id()) =
+		(mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) - 1;
+#endif
+
 	printk(KERN_INFO "Memory: %luk/%luk available (%luk kernel code, "
 	       "%luk reserved, %luk data, %luk bss, %luk init)\n",
 		nr_free_pages() << (PAGE_SHIFT-10),
@@ -382,6 +394,25 @@ void __init mem_init(void)
 	mem_init_done = 1;
 }
 
+void free_initmem(void)
+{
+	unsigned long addr;
+
+	ppc_md.progress = ppc_printk_progress;
+
+	addr = (unsigned long)__init_begin;
+	for (; addr < (unsigned long)__init_end; addr += PAGE_SIZE) {
+		memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
+		ClearPageReserved(virt_to_page(addr));
+		init_page_count(virt_to_page(addr));
+		free_page(addr);
+		totalram_pages++;
+	}
+	pr_info("Freeing unused kernel memory: %luk freed\n",
+		((unsigned long)__init_end -
+		(unsigned long)__init_begin) >> 10);
+}
+
 #ifdef CONFIG_BLK_DEV_INITRD
 void __init free_initrd_mem(unsigned long start, unsigned long end)
 {
@@ -519,4 +550,38 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
 		return;
 	hash_preload(vma->vm_mm, address, access, trap);
 #endif /* CONFIG_PPC_STD_MMU */
+#if (defined(CONFIG_PPC_BOOK3E_64) || defined(CONFIG_PPC_FSL_BOOK3E)) \
+	&& defined(CONFIG_HUGETLB_PAGE)
+	if (is_vm_hugetlb_page(vma))
+		book3e_hugetlb_preload(vma->vm_mm, address, *ptep);
+#endif
+}
+
+/*
+ * System memory should not be in /proc/iomem but various tools expect it
+ * (eg kdump).
+ */
+static int add_system_ram_resources(void)
+{
+	struct memblock_region *reg;
+
+	for_each_memblock(memory, reg) {
+		struct resource *res;
+		unsigned long base = reg->base;
+		unsigned long size = reg->size;
+
+		res = kzalloc(sizeof(struct resource), GFP_KERNEL);
+		WARN_ON(!res);
+
+		if (res) {
+			res->name = "System RAM";
+			res->start = base;
+			res->end = base + size - 1;
+			res->flags = IORESOURCE_MEM;
+			WARN_ON(request_resource(&iomem_resource, res) < 0);
+		}
+	}
+
+	return 0;
 }
+subsys_initcall(add_system_ram_resources);
diff --git a/arch/powerpc/mm/mmu_context_hash32.c b/arch/powerpc/mm/mmu_context_hash32.c
index d0ee554..78fef67 100644
--- a/arch/powerpc/mm/mmu_context_hash32.c
+++ b/arch/powerpc/mm/mmu_context_hash32.c
@@ -24,6 +24,7 @@
 
 #include <linux/mm.h>
 #include <linux/init.h>
+#include <linux/export.h>
 
 #include <asm/mmu_context.h>
 #include <asm/tlbflush.h>
diff --git a/arch/powerpc/mm/mmu_context_hash64.c b/arch/powerpc/mm/mmu_context_hash64.c
index 3bafc3d..ca988a3 100644
--- a/arch/powerpc/mm/mmu_context_hash64.c
+++ b/arch/powerpc/mm/mmu_context_hash64.c
@@ -18,7 +18,7 @@
 #include <linux/mm.h>
 #include <linux/spinlock.h>
 #include <linux/idr.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/gfp.h>
 #include <linux/slab.h>
 
@@ -136,8 +136,8 @@ int use_cop(unsigned long acop, struct mm_struct *mm)
 	if (!mm || !acop)
 		return -EINVAL;
 
-	/* We need to make sure mm_users doesn't change */
-	down_read(&mm->mmap_sem);
+	/* The page_table_lock ensures mm_users won't change under us */
+	spin_lock(&mm->page_table_lock);
 	spin_lock(mm->context.cop_lockp);
 
 	if (mm->context.cop_pid == COP_PID_NONE) {
@@ -164,7 +164,7 @@ int use_cop(unsigned long acop, struct mm_struct *mm)
 
 out:
 	spin_unlock(mm->context.cop_lockp);
-	up_read(&mm->mmap_sem);
+	spin_unlock(&mm->page_table_lock);
 
 	return ret;
 }
@@ -185,8 +185,8 @@ void drop_cop(unsigned long acop, struct mm_struct *mm)
 	if (WARN_ON_ONCE(!mm))
 		return;
 
-	/* We need to make sure mm_users doesn't change */
-	down_read(&mm->mmap_sem);
+	/* The page_table_lock ensures mm_users won't change under us */
+	spin_lock(&mm->page_table_lock);
 	spin_lock(mm->context.cop_lockp);
 
 	mm->context.acop &= ~acop;
@@ -213,7 +213,7 @@ void drop_cop(unsigned long acop, struct mm_struct *mm)
 	}
 
 	spin_unlock(mm->context.cop_lockp);
-	up_read(&mm->mmap_sem);
+	spin_unlock(&mm->page_table_lock);
 }
 EXPORT_SYMBOL_GPL(drop_cop);
 
diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c
index 336807d..5b63bd3 100644
--- a/arch/powerpc/mm/mmu_context_nohash.c
+++ b/arch/powerpc/mm/mmu_context_nohash.c
@@ -292,6 +292,11 @@ int init_new_context(struct task_struct *t, struct mm_struct *mm)
 	mm->context.id = MMU_NO_CONTEXT;
 	mm->context.active = 0;
 
+#ifdef CONFIG_PPC_MM_SLICES
+	if (slice_mm_new_context(mm))
+		slice_set_user_psize(mm, mmu_virtual_psize);
+#endif
+
 	return 0;
 }
 
diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h
index dd0a258..83eb5d5 100644
--- a/arch/powerpc/mm/mmu_decl.h
+++ b/arch/powerpc/mm/mmu_decl.h
@@ -142,6 +142,8 @@ extern unsigned long mmu_mapin_ram(unsigned long top);
 
 #elif defined(CONFIG_PPC_FSL_BOOK3E)
 extern unsigned long map_mem_in_cams(unsigned long ram, int max_cam_idx);
+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);
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 6f06ea5..261adbd 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -13,7 +13,7 @@
 #include <linux/init.h>
 #include <linux/mm.h>
 #include <linux/mmzone.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/nodemask.h>
 #include <linux/cpu.h>
 #include <linux/notifier.h>
@@ -295,7 +295,10 @@ static int __init find_min_common_depth(void)
 	struct device_node *root;
 	const char *vec5;
 
-	root = of_find_node_by_path("/rtas");
+	if (firmware_has_feature(FW_FEATURE_OPAL))
+		root = of_find_node_by_path("/ibm,opal");
+	else
+		root = of_find_node_by_path("/rtas");
 	if (!root)
 		root = of_find_node_by_path("/");
 
@@ -324,12 +327,19 @@ static int __init find_min_common_depth(void)
 
 #define VEC5_AFFINITY_BYTE	5
 #define VEC5_AFFINITY		0x80
-	chosen = of_find_node_by_path("/chosen");
-	if (chosen) {
-		vec5 = of_get_property(chosen, "ibm,architecture-vec-5", NULL);
-		if (vec5 && (vec5[VEC5_AFFINITY_BYTE] & VEC5_AFFINITY)) {
-			dbg("Using form 1 affinity\n");
-			form1_affinity = 1;
+
+	if (firmware_has_feature(FW_FEATURE_OPAL))
+		form1_affinity = 1;
+	else {
+		chosen = of_find_node_by_path("/chosen");
+		if (chosen) {
+			vec5 = of_get_property(chosen,
+					       "ibm,architecture-vec-5", NULL);
+			if (vec5 && (vec5[VEC5_AFFINITY_BYTE] &
+							VEC5_AFFINITY)) {
+				dbg("Using form 1 affinity\n");
+				form1_affinity = 1;
+			}
 		}
 	}
 
@@ -689,8 +699,7 @@ static void __init parse_drconf_memory(struct device_node *memory)
 
 static int __init parse_numa_properties(void)
 {
-	struct device_node *cpu = NULL;
-	struct device_node *memory = NULL;
+	struct device_node *memory;
 	int default_nid = 0;
 	unsigned long i;
 
@@ -712,6 +721,7 @@ static int __init parse_numa_properties(void)
 	 * each node to be onlined must have NODE_DATA etc backing it.
 	 */
 	for_each_present_cpu(i) {
+		struct device_node *cpu;
 		int nid;
 
 		cpu = of_get_cpu_node(i, NULL);
@@ -730,8 +740,8 @@ static int __init parse_numa_properties(void)
 	}
 
 	get_n_mem_cells(&n_mem_addr_cells, &n_mem_size_cells);
-	memory = NULL;
-	while ((memory = of_find_node_by_type(memory, "memory")) != NULL) {
+
+	for_each_node_by_type(memory, "memory") {
 		unsigned long start;
 		unsigned long size;
 		int nid;
@@ -780,8 +790,9 @@ new_range:
 	}
 
 	/*
-	 * Now do the same thing for each MEMBLOCK listed in the ibm,dynamic-memory
-	 * property in the ibm,dynamic-reconfiguration-memory node.
+	 * Now do the same thing for each MEMBLOCK listed in the
+	 * ibm,dynamic-memory property in the
+	 * ibm,dynamic-reconfiguration-memory node.
 	 */
 	memory = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
 	if (memory)
@@ -1167,10 +1178,10 @@ static int hot_add_drconf_scn_to_nid(struct device_node *memory,
  */
 int hot_add_node_scn_to_nid(unsigned long scn_addr)
 {
-	struct device_node *memory = NULL;
+	struct device_node *memory;
 	int nid = -1;
 
-	while ((memory = of_find_node_by_type(memory, "memory")) != NULL) {
+	for_each_node_by_type(memory, "memory") {
 		unsigned long start, size;
 		int ranges;
 		const unsigned int *memcell_buf;
@@ -1194,11 +1205,12 @@ int hot_add_node_scn_to_nid(unsigned long scn_addr)
 			break;
 		}
 
-		of_node_put(memory);
 		if (nid >= 0)
 			break;
 	}
 
+	of_node_put(memory);
+
 	return nid;
 }
 
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index af40c87..214130a 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -27,6 +27,7 @@
 #include <linux/init.h>
 #include <linux/percpu.h>
 #include <linux/hardirq.h>
+#include <linux/hugetlb.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 #include <asm/tlb.h>
@@ -212,7 +213,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address,
 	entry = set_access_flags_filter(entry, vma, dirty);
 	changed = !pte_same(*(ptep), entry);
 	if (changed) {
-		if (!(vma->vm_flags & VM_HUGETLB))
+		if (!is_vm_hugetlb_page(vma))
 			assert_pte_locked(vma->vm_mm, address);
 		__ptep_set_access_flags(ptep, entry);
 		flush_tlb_page_nohash(vma, address);
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 6e595f6..ad36ede4 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -26,6 +26,7 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/string.h>
+#include <linux/export.h>
 #include <linux/types.h>
 #include <linux/mman.h>
 #include <linux/mm.h>
diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
index ba51948..73709f7 100644
--- a/arch/powerpc/mm/slice.c
+++ b/arch/powerpc/mm/slice.c
@@ -29,7 +29,7 @@
 #include <linux/pagemap.h>
 #include <linux/err.h>
 #include <linux/spinlock.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <asm/mman.h>
 #include <asm/mmu.h>
 #include <asm/spu.h>
diff --git a/arch/powerpc/mm/tlb_hash32.c b/arch/powerpc/mm/tlb_hash32.c
index 27b863c..558e30c 100644
--- a/arch/powerpc/mm/tlb_hash32.c
+++ b/arch/powerpc/mm/tlb_hash32.c
@@ -27,6 +27,7 @@
 #include <linux/init.h>
 #include <linux/highmem.h>
 #include <linux/pagemap.h>
+#include <linux/export.h>
 
 #include <asm/tlbflush.h>
 #include <asm/tlb.h>
@@ -177,3 +178,7 @@ void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 	flush_range(vma->vm_mm, start, end);
 }
 EXPORT_SYMBOL(flush_tlb_range);
+
+void __init early_init_mmu(void)
+{
+}
diff --git a/arch/powerpc/mm/tlb_low_64e.S b/arch/powerpc/mm/tlb_low_64e.S
index af08922..dc4a5f3 100644
--- a/arch/powerpc/mm/tlb_low_64e.S
+++ b/arch/powerpc/mm/tlb_low_64e.S
@@ -30,6 +30,212 @@
 #define VPTE_PGD_SHIFT	(VPTE_PUD_SHIFT + PUD_INDEX_SIZE)
 #define VPTE_INDEX_SIZE (VPTE_PGD_SHIFT + PGD_INDEX_SIZE)
 
+/**********************************************************************
+ *                                                                    *
+ * TLB miss handling for Book3E with a bolted linear mapping          *
+ * No virtual page table, no nested TLB misses                        *
+ *                                                                    *
+ **********************************************************************/
+
+.macro tlb_prolog_bolted addr
+	mtspr	SPRN_SPRG_TLB_SCRATCH,r13
+	mfspr	r13,SPRN_SPRG_PACA
+	std	r10,PACA_EXTLB+EX_TLB_R10(r13)
+	mfcr	r10
+	std	r11,PACA_EXTLB+EX_TLB_R11(r13)
+	std	r16,PACA_EXTLB+EX_TLB_R16(r13)
+	mfspr	r16,\addr		/* get faulting address */
+	std	r14,PACA_EXTLB+EX_TLB_R14(r13)
+	ld	r14,PACAPGD(r13)
+	std	r15,PACA_EXTLB+EX_TLB_R15(r13)
+	std	r10,PACA_EXTLB+EX_TLB_CR(r13)
+	TLB_MISS_PROLOG_STATS_BOLTED
+.endm
+
+.macro tlb_epilog_bolted
+	ld	r14,PACA_EXTLB+EX_TLB_CR(r13)
+	ld	r10,PACA_EXTLB+EX_TLB_R10(r13)
+	ld	r11,PACA_EXTLB+EX_TLB_R11(r13)
+	mtcr	r14
+	ld	r14,PACA_EXTLB+EX_TLB_R14(r13)
+	ld	r15,PACA_EXTLB+EX_TLB_R15(r13)
+	TLB_MISS_RESTORE_STATS_BOLTED
+	ld	r16,PACA_EXTLB+EX_TLB_R16(r13)
+	mfspr	r13,SPRN_SPRG_TLB_SCRATCH
+.endm
+
+/* Data TLB miss */
+	START_EXCEPTION(data_tlb_miss_bolted)
+	tlb_prolog_bolted SPRN_DEAR
+
+	/* We need _PAGE_PRESENT and  _PAGE_ACCESSED set */
+
+	/* We do the user/kernel test for the PID here along with the RW test
+	 */
+	/* We pre-test some combination of permissions to avoid double
+	 * faults:
+	 *
+	 * We move the ESR:ST bit into the position of _PAGE_BAP_SW in the PTE
+	 * ESR_ST   is 0x00800000
+	 * _PAGE_BAP_SW is 0x00000010
+	 * So the shift is >> 19. This tests for supervisor writeability.
+	 * If the page happens to be supervisor writeable and not user
+	 * writeable, we will take a new fault later, but that should be
+	 * a rare enough case.
+	 *
+	 * We also move ESR_ST in _PAGE_DIRTY position
+	 * _PAGE_DIRTY is 0x00001000 so the shift is >> 11
+	 *
+	 * MAS1 is preset for all we need except for TID that needs to
+	 * be cleared for kernel translations
+	 */
+
+	mfspr	r11,SPRN_ESR
+
+	srdi	r15,r16,60		/* get region */
+	rldicl.	r10,r16,64-PGTABLE_EADDR_SIZE,PGTABLE_EADDR_SIZE+4
+	bne-	dtlb_miss_fault_bolted
+
+	rlwinm	r10,r11,32-19,27,27
+	rlwimi	r10,r11,32-16,19,19
+	cmpwi	r15,0
+	ori	r10,r10,_PAGE_PRESENT
+	oris	r11,r10,_PAGE_ACCESSED@h
+
+	TLB_MISS_STATS_SAVE_INFO_BOLTED
+	bne	tlb_miss_kernel_bolted
+
+tlb_miss_common_bolted:
+/*
+ * This is the guts of the TLB miss handler for bolted-linear.
+ * We are entered with:
+ *
+ * r16 = faulting address
+ * r15 = crap (free to use)
+ * r14 = page table base
+ * r13 = PACA
+ * r11 = PTE permission mask
+ * r10 = crap (free to use)
+ */
+	rldicl	r15,r16,64-PGDIR_SHIFT+3,64-PGD_INDEX_SIZE-3
+	cmpldi	cr0,r14,0
+	clrrdi	r15,r15,3
+	beq	tlb_miss_fault_bolted
+
+BEGIN_MMU_FTR_SECTION
+	/* Set the TLB reservation and search for existing entry. Then load
+	 * the entry.
+	 */
+	PPC_TLBSRX_DOT(0,r16)
+	ldx	r14,r14,r15
+	beq	normal_tlb_miss_done
+MMU_FTR_SECTION_ELSE
+	ldx	r14,r14,r15
+ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_USE_TLBRSRV)
+
+#ifndef CONFIG_PPC_64K_PAGES
+	rldicl	r15,r16,64-PUD_SHIFT+3,64-PUD_INDEX_SIZE-3
+	clrrdi	r15,r15,3
+
+	cmpldi	cr0,r14,0
+	beq	tlb_miss_fault_bolted
+
+	ldx	r14,r14,r15
+#endif /* CONFIG_PPC_64K_PAGES */
+
+	rldicl	r15,r16,64-PMD_SHIFT+3,64-PMD_INDEX_SIZE-3
+	clrrdi	r15,r15,3
+
+	cmpldi	cr0,r14,0
+	beq	tlb_miss_fault_bolted
+
+	ldx	r14,r14,r15
+
+	rldicl	r15,r16,64-PAGE_SHIFT+3,64-PTE_INDEX_SIZE-3
+	clrrdi	r15,r15,3
+
+	cmpldi	cr0,r14,0
+	beq	tlb_miss_fault_bolted
+
+	ldx	r14,r14,r15
+
+	/* Check if required permissions are met */
+	andc.	r15,r11,r14
+	rldicr	r15,r14,64-(PTE_RPN_SHIFT-PAGE_SHIFT),63-PAGE_SHIFT
+	bne-	tlb_miss_fault_bolted
+
+	/* Now we build the MAS:
+	 *
+	 * MAS 0   :	Fully setup with defaults in MAS4 and TLBnCFG
+	 * MAS 1   :	Almost fully setup
+	 *               - PID already updated by caller if necessary
+	 *               - TSIZE need change if !base page size, not
+	 *                 yet implemented for now
+	 * MAS 2   :	Defaults not useful, need to be redone
+	 * MAS 3+7 :	Needs to be done
+	 */
+	clrrdi	r11,r16,12		/* Clear low crap in EA */
+	clrldi	r15,r15,12		/* Clear crap at the top */
+	rlwimi	r11,r14,32-19,27,31	/* Insert WIMGE */
+	rlwimi	r15,r14,32-8,22,25	/* Move in U bits */
+	mtspr	SPRN_MAS2,r11
+	andi.	r11,r14,_PAGE_DIRTY
+	rlwimi	r15,r14,32-2,26,31	/* Move in BAP bits */
+
+	/* Mask out SW and UW if !DIRTY (XXX optimize this !) */
+	bne	1f
+	li	r11,MAS3_SW|MAS3_UW
+	andc	r15,r15,r11
+1:
+	mtspr	SPRN_MAS7_MAS3,r15
+	tlbwe
+
+	TLB_MISS_STATS_X(MMSTAT_TLB_MISS_NORM_OK)
+	tlb_epilog_bolted
+	rfi
+
+itlb_miss_kernel_bolted:
+	li	r11,_PAGE_PRESENT|_PAGE_BAP_SX	/* Base perm */
+	oris	r11,r11,_PAGE_ACCESSED@h
+tlb_miss_kernel_bolted:
+	mfspr	r10,SPRN_MAS1
+	ld	r14,PACA_KERNELPGD(r13)
+	cmpldi	cr0,r15,8		/* Check for vmalloc region */
+	rlwinm	r10,r10,0,16,1		/* Clear TID */
+	mtspr	SPRN_MAS1,r10
+	beq+	tlb_miss_common_bolted
+
+tlb_miss_fault_bolted:
+	/* We need to check if it was an instruction miss */
+	andi.	r10,r11,_PAGE_EXEC|_PAGE_BAP_SX
+	bne	itlb_miss_fault_bolted
+dtlb_miss_fault_bolted:
+	TLB_MISS_STATS_D(MMSTAT_TLB_MISS_NORM_FAULT)
+	tlb_epilog_bolted
+	b	exc_data_storage_book3e
+itlb_miss_fault_bolted:
+	TLB_MISS_STATS_I(MMSTAT_TLB_MISS_NORM_FAULT)
+	tlb_epilog_bolted
+	b	exc_instruction_storage_book3e
+
+/* Instruction TLB miss */
+	START_EXCEPTION(instruction_tlb_miss_bolted)
+	tlb_prolog_bolted SPRN_SRR0
+
+	rldicl.	r10,r16,64-PGTABLE_EADDR_SIZE,PGTABLE_EADDR_SIZE+4
+	srdi	r15,r16,60		/* get region */
+	TLB_MISS_STATS_SAVE_INFO_BOLTED
+	bne-	itlb_miss_fault_bolted
+
+	li	r11,_PAGE_PRESENT|_PAGE_EXEC	/* Base perm */
+
+	/* We do the user/kernel test for the PID here along with the RW test
+	 */
+
+	cmpldi	cr0,r15,0			/* Check for user region */
+	oris	r11,r11,_PAGE_ACCESSED@h
+	beq	tlb_miss_common_bolted
+	b	itlb_miss_kernel_bolted
 
 /**********************************************************************
  *                                                                    *
@@ -347,24 +553,24 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_TLBRSRV)
 	rldicl	r11,r16,64-VPTE_PGD_SHIFT,64-PGD_INDEX_SIZE-3
 	clrrdi	r10,r11,3
 	ldx	r15,r10,r15
-	cmpldi	cr0,r15,0
-	beq	virt_page_table_tlb_miss_fault
+	cmpdi	cr0,r15,0
+	bge	virt_page_table_tlb_miss_fault
 
 #ifndef CONFIG_PPC_64K_PAGES
 	/* Get to PUD entry */
 	rldicl	r11,r16,64-VPTE_PUD_SHIFT,64-PUD_INDEX_SIZE-3
 	clrrdi	r10,r11,3
 	ldx	r15,r10,r15
-	cmpldi	cr0,r15,0
-	beq	virt_page_table_tlb_miss_fault
+	cmpdi	cr0,r15,0
+	bge	virt_page_table_tlb_miss_fault
 #endif /* CONFIG_PPC_64K_PAGES */
 
 	/* Get to PMD entry */
 	rldicl	r11,r16,64-VPTE_PMD_SHIFT,64-PMD_INDEX_SIZE-3
 	clrrdi	r10,r11,3
 	ldx	r15,r10,r15
-	cmpldi	cr0,r15,0
-	beq	virt_page_table_tlb_miss_fault
+	cmpdi	cr0,r15,0
+	bge	virt_page_table_tlb_miss_fault
 
 	/* Ok, we're all right, we can now create a kernel translation for
 	 * a 4K or 64K page from r16 -> r15.
@@ -596,24 +802,24 @@ htw_tlb_miss:
 	rldicl	r11,r16,64-(PGDIR_SHIFT-3),64-PGD_INDEX_SIZE-3
 	clrrdi	r10,r11,3
 	ldx	r15,r10,r15
-	cmpldi	cr0,r15,0
-	beq	htw_tlb_miss_fault
+	cmpdi	cr0,r15,0
+	bge	htw_tlb_miss_fault
 
 #ifndef CONFIG_PPC_64K_PAGES
 	/* Get to PUD entry */
 	rldicl	r11,r16,64-(PUD_SHIFT-3),64-PUD_INDEX_SIZE-3
 	clrrdi	r10,r11,3
 	ldx	r15,r10,r15
-	cmpldi	cr0,r15,0
-	beq	htw_tlb_miss_fault
+	cmpdi	cr0,r15,0
+	bge	htw_tlb_miss_fault
 #endif /* CONFIG_PPC_64K_PAGES */
 
 	/* Get to PMD entry */
 	rldicl	r11,r16,64-(PMD_SHIFT-3),64-PMD_INDEX_SIZE-3
 	clrrdi	r10,r11,3
 	ldx	r15,r10,r15
-	cmpldi	cr0,r15,0
-	beq	htw_tlb_miss_fault
+	cmpdi	cr0,r15,0
+	bge	htw_tlb_miss_fault
 
 	/* Ok, we're all right, we can now create an indirect entry for
 	 * a 1M or 256M page.
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index 0bdad3a..4e13d6f 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -28,6 +28,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/export.h>
 #include <linux/mm.h>
 #include <linux/init.h>
 #include <linux/highmem.h>
@@ -35,14 +36,50 @@
 #include <linux/preempt.h>
 #include <linux/spinlock.h>
 #include <linux/memblock.h>
+#include <linux/of_fdt.h>
+#include <linux/hugetlb.h>
 
 #include <asm/tlbflush.h>
 #include <asm/tlb.h>
 #include <asm/code-patching.h>
+#include <asm/hugetlb.h>
 
 #include "mmu_decl.h"
 
-#ifdef CONFIG_PPC_BOOK3E
+/*
+ * This struct lists the sw-supported page sizes.  The hardawre MMU may support
+ * other sizes not listed here.   The .ind field is only used on MMUs that have
+ * indirect page table entries.
+ */
+#ifdef CONFIG_PPC_BOOK3E_MMU
+#ifdef CONFIG_FSL_BOOKE
+struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = {
+	[MMU_PAGE_4K] = {
+		.shift	= 12,
+		.enc	= BOOK3E_PAGESZ_4K,
+	},
+	[MMU_PAGE_4M] = {
+		.shift	= 22,
+		.enc	= BOOK3E_PAGESZ_4M,
+	},
+	[MMU_PAGE_16M] = {
+		.shift	= 24,
+		.enc	= BOOK3E_PAGESZ_16M,
+	},
+	[MMU_PAGE_64M] = {
+		.shift	= 26,
+		.enc	= BOOK3E_PAGESZ_64M,
+	},
+	[MMU_PAGE_256M] = {
+		.shift	= 28,
+		.enc	= BOOK3E_PAGESZ_256M,
+	},
+	[MMU_PAGE_1G] = {
+		.shift	= 30,
+		.enc	= BOOK3E_PAGESZ_1GB,
+	},
+};
+#else
 struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = {
 	[MMU_PAGE_4K] = {
 		.shift	= 12,
@@ -76,6 +113,8 @@ struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = {
 		.enc	= BOOK3E_PAGESZ_1GB,
 	},
 };
+#endif /* CONFIG_FSL_BOOKE */
+
 static inline int mmu_get_tsize(int psize)
 {
 	return mmu_psize_defs[psize].enc;
@@ -86,7 +125,7 @@ static inline int mmu_get_tsize(int psize)
 	/* This isn't used on !Book3E for now */
 	return 0;
 }
-#endif
+#endif /* CONFIG_PPC_BOOK3E_MMU */
 
 /* The variables below are currently only used on 64-bit Book3E
  * though this will probably be made common with other nohash
@@ -102,6 +141,12 @@ unsigned long linear_map_top;	/* Top of linear mapping */
 
 #endif /* CONFIG_PPC64 */
 
+#ifdef CONFIG_PPC_FSL_BOOK3E
+/* next_tlbcam_idx is used to round-robin tlbcam entry assignment */
+DEFINE_PER_CPU(int, next_tlbcam_idx);
+EXPORT_PER_CPU_SYMBOL(next_tlbcam_idx);
+#endif
+
 /*
  * Base TLB flushing operations:
  *
@@ -259,6 +304,11 @@ void __flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
 
 void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
 {
+#ifdef CONFIG_HUGETLB_PAGE
+	if (is_vm_hugetlb_page(vma))
+		flush_hugetlb_page(vma, vmaddr);
+#endif
+
 	__flush_tlb_page(vma ? vma->vm_mm : NULL, vmaddr,
 			 mmu_get_tsize(mmu_virtual_psize), 0);
 }
@@ -266,6 +316,17 @@ EXPORT_SYMBOL(flush_tlb_page);
 
 #endif /* CONFIG_SMP */
 
+#ifdef CONFIG_PPC_47x
+void __init early_init_mmu_47x(void)
+{
+#ifdef CONFIG_SMP
+	unsigned long root = of_get_flat_dt_root();
+	if (of_get_flat_dt_prop(root, "cooperative-partition", NULL))
+		mmu_clear_feature(MMU_FTR_USE_TLBIVAX_BCAST);
+#endif /* CONFIG_SMP */
+}
+#endif /* CONFIG_PPC_47x */
+
 /*
  * Flush kernel TLB entries in the given range
  */
@@ -443,14 +504,27 @@ static void setup_page_sizes(void)
 	}
 }
 
-static void setup_mmu_htw(void)
+static void __patch_exception(int exc, unsigned long addr)
 {
 	extern unsigned int interrupt_base_book3e;
-	extern unsigned int exc_data_tlb_miss_htw_book3e;
-	extern unsigned int exc_instruction_tlb_miss_htw_book3e;
+ 	unsigned int *ibase = &interrupt_base_book3e;
+ 
+	/* Our exceptions vectors start with a NOP and -then- a branch
+	 * to deal with single stepping from userspace which stops on
+	 * the second instruction. Thus we need to patch the second
+	 * instruction of the exception, not the first one
+	 */
+
+	patch_branch(ibase + (exc / 4) + 1, addr, 0);
+}
 
-	unsigned int *ibase = &interrupt_base_book3e;
+#define patch_exception(exc, name) do { \
+	extern unsigned int name; \
+	__patch_exception((exc), (unsigned long)&name); \
+} while (0)
 
+static void setup_mmu_htw(void)
+{
 	/* Check if HW tablewalk is present, and if yes, enable it by:
 	 *
 	 * - patching the TLB miss handlers to branch to the
@@ -462,19 +536,12 @@ static void setup_mmu_htw(void)
 
 	if ((tlb0cfg & TLBnCFG_IND) &&
 	    (tlb0cfg & TLBnCFG_PT)) {
-		/* Our exceptions vectors start with a NOP and -then- a branch
-		 * to deal with single stepping from userspace which stops on
-		 * the second instruction. Thus we need to patch the second
-		 * instruction of the exception, not the first one
-		 */
-		patch_branch(ibase + (0x1c0 / 4) + 1,
-			     (unsigned long)&exc_data_tlb_miss_htw_book3e, 0);
-		patch_branch(ibase + (0x1e0 / 4) + 1,
-			     (unsigned long)&exc_instruction_tlb_miss_htw_book3e, 0);
+		patch_exception(0x1c0, exc_data_tlb_miss_htw_book3e);
+		patch_exception(0x1e0, exc_instruction_tlb_miss_htw_book3e);
 		book3e_htw_enabled = 1;
 	}
-	pr_info("MMU: Book3E Page Tables %s\n",
-		book3e_htw_enabled ? "Enabled" : "Disabled");
+	pr_info("MMU: Book3E HW tablewalk %s\n",
+		book3e_htw_enabled ? "enabled" : "not supported");
 }
 
 /*
@@ -549,6 +616,9 @@ static void __early_init_mmu(int boot_cpu)
 		/* limit memory so we dont have linear faults */
 		memblock_enforce_memory_limit(linear_map_top);
 		memblock_analyze();
+
+		patch_exception(0x1c0, exc_data_tlb_miss_bolted_book3e);
+		patch_exception(0x1e0, exc_instruction_tlb_miss_bolted_book3e);
 	}
 #endif
 
@@ -573,15 +643,37 @@ void __cpuinit early_init_mmu_secondary(void)
 void setup_initial_memory_limit(phys_addr_t first_memblock_base,
 				phys_addr_t first_memblock_size)
 {
-	/* On Embedded 64-bit, we adjust the RMA size to match
+	/* On non-FSL Embedded 64-bit, we adjust the RMA size to match
 	 * the bolted TLB entry. We know for now that only 1G
 	 * entries are supported though that may eventually
-	 * change. We crop it to the size of the first MEMBLOCK to
+	 * change.
+	 *
+	 * on FSL Embedded 64-bit, we adjust the RMA size to match the
+	 * first bolted TLB entry size.  We still limit max to 1G even if
+	 * the TLB could cover more.  This is due to what the early init
+	 * code is setup to do.
+	 *
+	 * We crop it to the size of the first MEMBLOCK to
 	 * avoid going over total available memory just in case...
 	 */
-	ppc64_rma_size = min_t(u64, first_memblock_size, 0x40000000);
+#ifdef CONFIG_PPC_FSL_BOOK3E
+	if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) {
+		unsigned long linear_sz;
+		linear_sz = calc_cam_sz(first_memblock_size, PAGE_OFFSET,
+					first_memblock_base);
+		ppc64_rma_size = min_t(u64, linear_sz, 0x40000000);
+	} else
+#endif
+		ppc64_rma_size = min_t(u64, first_memblock_size, 0x40000000);
 
 	/* Finally limit subsequent allocations */
 	memblock_set_current_limit(first_memblock_base + ppc64_rma_size);
 }
+#else /* ! CONFIG_PPC64 */
+void __init early_init_mmu(void)
+{
+#ifdef CONFIG_PPC_47x
+	early_init_mmu_47x();
+#endif
+}
 #endif /* CONFIG_PPC64 */