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 024acab588f..f60e006d90c 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 bdca46e0838..991ee813d2a 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 b42f76c4948..329be36c0a8 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 ad35f66c69e..5efe8c96d37 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 f7802c8bba0..66a6fd38e9c 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 fec13200868..d7efdbf640c 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 dfd764896db..90039bc6411 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 26b2872b3d0..2d282186cb4 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 00000000000..343ad0b8726
--- /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 0b9a5c1901b..8558b572e55 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