Merge tag 'powerpc-4.5-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Core:
   - Ground work for the new Power9 MMU from Aneesh Kumar K.V
   - Optimise FP/VMX/VSX context switching from Anton Blanchard

  Misc:
   - Various cleanups from Krzysztof Kozlowski, John Ogness, Rashmica
     Gupta, Russell Currey, Gavin Shan, Daniel Axtens, Michael Neuling,
     Andrew Donnellan
   - Allow wrapper to work on non-english system from Laurent Vivier
   - Add rN aliases to the pt_regs_offset table from Rashmica Gupta
   - Fix module autoload for rackmeter & axonram drivers from Luis de
     Bethencourt
   - Include KVM guest test in all interrupt vectors from Paul Mackerras
   - Fix DSCR inheritance over fork() from Anton Blanchard
   - Make value-returning atomics & {cmp}xchg* & their atomic_ versions
     fully ordered from Boqun Feng
   - Print MSR TM bits in oops messages from Michael Neuling
   - Add TM signal return & invalid stack selftests from Michael Neuling
   - Limit EPOW reset event warnings from Vipin K Parashar
   - Remove the Cell QPACE code from Rashmica Gupta
   - Append linux_banner to exception information in xmon from Rashmica
     Gupta
   - Add selftest to check if VSRs are corrupted from Rashmica Gupta
   - Remove broken GregorianDay() from Daniel Axtens
   - Import Anton's context_switch2 benchmark into selftests from
     Michael Ellerman
   - Add selftest script to test HMI functionality from Daniel Axtens
   - Remove obsolete OPAL v2 support from Stewart Smith
   - Make enter_rtas() private from Michael Ellerman
   - PPR exception cleanups from Michael Ellerman
   - Add page soft dirty tracking from Laurent Dufour
   - Add support for Nvlink NPUs from Alistair Popple
   - Add support for kexec on 476fpe from Alistair Popple
   - Enable kernel CPU dlpar from sysfs from Nathan Fontenot
   - Copy only required pieces of the mm_context_t to the paca from
     Michael Neuling
   - Add a kmsg_dumper that flushes OPAL console output on panic from
     Russell Currey
   - Implement save_stack_trace_regs() to enable kprobe stack tracing
     from Steven Rostedt
   - Add HWCAP bits for Power9 from Michael Ellerman
   - Fix _PAGE_PTE breaking swapoff from Aneesh Kumar K.V
   - Fix _PAGE_SWP_SOFT_DIRTY breaking swapoff from Hugh Dickins
   - scripts/recordmcount.pl: support data in text section on powerpc
     from Ulrich Weigand
   - Handle R_PPC64_ENTRY relocations in modules from Ulrich Weigand

  cxl:
   - cxl: Fix possible idr warning when contexts are released from
     Vaibhav Jain
   - cxl: use correct operator when writing pcie config space values
     from Andrew Donnellan
   - cxl: Fix DSI misses when the context owning task exits from Vaibhav
     Jain
   - cxl: fix build for GCC 4.6.x from Brian Norris
   - cxl: use -Werror only with CONFIG_PPC_WERROR from Brian Norris
   - cxl: Enable PCI device ID for future IBM CXL adapter from Uma
     Krishnan

  Freescale:
   - Freescale updates from Scott: Highlights include moving QE code out
     of arch/powerpc (to be shared with arm), device tree updates, and
     minor fixes"

* tag 'powerpc-4.5-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (149 commits)
  powerpc/module: Handle R_PPC64_ENTRY relocations
  scripts/recordmcount.pl: support data in text section on powerpc
  powerpc/powernv: Fix OPAL_CONSOLE_FLUSH prototype and usages
  powerpc/mm: fix _PAGE_SWP_SOFT_DIRTY breaking swapoff
  powerpc/mm: Fix _PAGE_PTE breaking swapoff
  cxl: Enable PCI device ID for future IBM CXL adapter
  cxl: use -Werror only with CONFIG_PPC_WERROR
  cxl: fix build for GCC 4.6.x
  powerpc: Add HWCAP bits for Power9
  powerpc/powernv: Reserve PE#0 on NPU
  powerpc/powernv: Change NPU PE# assignment
  powerpc/powernv: Fix update of NVLink DMA mask
  powerpc/powernv: Remove misleading comment in pci.c
  powerpc: Implement save_stack_trace_regs() to enable kprobe stack tracing
  powerpc: Fix build break due to paca mm_context_t changes
  cxl: Fix DSI misses when the context owning task exits
  MAINTAINERS: Update Scott Wood's e-mail address
  powerpc/powernv: Fix minor off-by-one error in opal_mce_check_early_recovery()
  powerpc: Fix style of self-test config prompts
  powerpc/powernv: Only delay opal_rtc_read() retry when necessary
  ...

7 files changed, 1852 insertions, 0 deletions

diff --git a/arch/powerpc/include/asm/book3s/32/hash.h b/arch/powerpc/include/asm/book3s/32/hash.h
new file mode 100644
index 000000000000..264b754d65b0
--- /dev/null
+++ b/arch/powerpc/include/asm/book3s/32/hash.h
@@ -0,0 +1,46 @@
+#ifndef _ASM_POWERPC_BOOK3S_32_HASH_H
+#define _ASM_POWERPC_BOOK3S_32_HASH_H
+#ifdef __KERNEL__
+
+/*
+ * The "classic" 32-bit implementation of the PowerPC MMU uses a hash
+ * table containing PTEs, together with a set of 16 segment registers,
+ * to define the virtual to physical address mapping.
+ *
+ * We use the hash table as an extended TLB, i.e. a cache of currently
+ * active mappings.  We maintain a two-level page table tree, much
+ * like that used by the i386, for the sake of the Linux memory
+ * management code.  Low-level assembler code in hash_low_32.S
+ * (procedure hash_page) is responsible for extracting ptes from the
+ * tree and putting them into the hash table when necessary, and
+ * updating the accessed and modified bits in the page table tree.
+ */
+
+#define _PAGE_PRESENT	0x001	/* software: pte contains a translation */
+#define _PAGE_HASHPTE	0x002	/* hash_page has made an HPTE for this pte */
+#define _PAGE_USER	0x004	/* usermode access allowed */
+#define _PAGE_GUARDED	0x008	/* G: prohibit speculative access */
+#define _PAGE_COHERENT	0x010	/* M: enforce memory coherence (SMP systems) */
+#define _PAGE_NO_CACHE	0x020	/* I: cache inhibit */
+#define _PAGE_WRITETHRU	0x040	/* W: cache write-through */
+#define _PAGE_DIRTY	0x080	/* C: page changed */
+#define _PAGE_ACCESSED	0x100	/* R: page referenced */
+#define _PAGE_RW	0x400	/* software: user write access allowed */
+#define _PAGE_SPECIAL	0x800	/* software: Special page */
+
+#ifdef CONFIG_PTE_64BIT
+/* We never clear the high word of the pte */
+#define _PTE_NONE_MASK	(0xffffffff00000000ULL | _PAGE_HASHPTE)
+#else
+#define _PTE_NONE_MASK	_PAGE_HASHPTE
+#endif
+
+#define _PMD_PRESENT	0
+#define _PMD_PRESENT_MASK (PAGE_MASK)
+#define _PMD_BAD	(~PAGE_MASK)
+
+/* Hash table based platforms need atomic updates of the linux PTE */
+#define PTE_ATOMIC_UPDATES	1
+
+#endif /* __KERNEL__ */
+#endif /* _ASM_POWERPC_BOOK3S_32_HASH_H */
diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
new file mode 100644
index 000000000000..38b33dcfcc9d
--- /dev/null
+++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
@@ -0,0 +1,482 @@
+#ifndef _ASM_POWERPC_BOOK3S_32_PGTABLE_H
+#define _ASM_POWERPC_BOOK3S_32_PGTABLE_H
+
+#include <asm-generic/pgtable-nopmd.h>
+
+#include <asm/book3s/32/hash.h>
+
+/* And here we include common definitions */
+#include <asm/pte-common.h>
+
+/*
+ * The normal case is that PTEs are 32-bits and we have a 1-page
+ * 1024-entry pgdir pointing to 1-page 1024-entry PTE pages.  -- paulus
+ *
+ * For any >32-bit physical address platform, we can use the following
+ * two level page table layout where the pgdir is 8KB and the MS 13 bits
+ * are an index to the second level table.  The combined pgdir/pmd first
+ * level has 2048 entries and the second level has 512 64-bit PTE entries.
+ * -Matt
+ */
+/* PGDIR_SHIFT determines what a top-level page table entry can map */
+#define PGDIR_SHIFT	(PAGE_SHIFT + PTE_SHIFT)
+#define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
+#define PGDIR_MASK	(~(PGDIR_SIZE-1))
+
+#define PTRS_PER_PTE	(1 << PTE_SHIFT)
+#define PTRS_PER_PMD	1
+#define PTRS_PER_PGD	(1 << (32 - PGDIR_SHIFT))
+
+#define USER_PTRS_PER_PGD	(TASK_SIZE / PGDIR_SIZE)
+/*
+ * This is the bottom of the PKMAP area with HIGHMEM or an arbitrary
+ * value (for now) on others, from where we can start layout kernel
+ * virtual space that goes below PKMAP and FIXMAP
+ */
+#ifdef CONFIG_HIGHMEM
+#define KVIRT_TOP	PKMAP_BASE
+#else
+#define KVIRT_TOP	(0xfe000000UL)	/* for now, could be FIXMAP_BASE ? */
+#endif
+
+/*
+ * ioremap_bot starts at that address. Early ioremaps move down from there,
+ * until mem_init() at which point this becomes the top of the vmalloc
+ * and ioremap space
+ */
+#ifdef CONFIG_NOT_COHERENT_CACHE
+#define IOREMAP_TOP	((KVIRT_TOP - CONFIG_CONSISTENT_SIZE) & PAGE_MASK)
+#else
+#define IOREMAP_TOP	KVIRT_TOP
+#endif
+
+/*
+ * Just any arbitrary offset to the start of the vmalloc VM area: the
+ * current 16MB value just means that there will be a 64MB "hole" after the
+ * physical memory until the kernel virtual memory starts.  That means that
+ * any out-of-bounds memory accesses will hopefully be caught.
+ * The vmalloc() routines leaves a hole of 4kB between each vmalloced
+ * area for the same reason. ;)
+ *
+ * We no longer map larger than phys RAM with the BATs so we don't have
+ * to worry about the VMALLOC_OFFSET causing problems.  We do have to worry
+ * about clashes between our early calls to ioremap() that start growing down
+ * from ioremap_base being run into the VM area allocations (growing upwards
+ * from VMALLOC_START).  For this reason we have ioremap_bot to check when
+ * we actually run into our mappings setup in the early boot with the VM
+ * system.  This really does become a problem for machines with good amounts
+ * of RAM.  -- Cort
+ */
+#define VMALLOC_OFFSET (0x1000000) /* 16M */
+#ifdef PPC_PIN_SIZE
+#define VMALLOC_START (((_ALIGN((long)high_memory, PPC_PIN_SIZE) + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1)))
+#else
+#define VMALLOC_START ((((long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1)))
+#endif
+#define VMALLOC_END	ioremap_bot
+
+#ifndef __ASSEMBLY__
+#include <linux/sched.h>
+#include <linux/threads.h>
+#include <asm/io.h>			/* For sub-arch specific PPC_PIN_SIZE */
+
+extern unsigned long ioremap_bot;
+
+/*
+ * entries per page directory level: our page-table tree is two-level, so
+ * we don't really have any PMD directory.
+ */
+#define PTE_TABLE_SIZE	(sizeof(pte_t) << PTE_SHIFT)
+#define PGD_TABLE_SIZE	(sizeof(pgd_t) << (32 - PGDIR_SHIFT))
+
+#define pte_ERROR(e) \
+	pr_err("%s:%d: bad pte %llx.\n", __FILE__, __LINE__, \
+		(unsigned long long)pte_val(e))
+#define pgd_ERROR(e) \
+	pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
+/*
+ * Bits in a linux-style PTE.  These match the bits in the
+ * (hardware-defined) PowerPC PTE as closely as possible.
+ */
+
+#define pte_clear(mm, addr, ptep) \
+	do { pte_update(ptep, ~_PAGE_HASHPTE, 0); } while (0)
+
+#define pmd_none(pmd)		(!pmd_val(pmd))
+#define	pmd_bad(pmd)		(pmd_val(pmd) & _PMD_BAD)
+#define	pmd_present(pmd)	(pmd_val(pmd) & _PMD_PRESENT_MASK)
+static inline void pmd_clear(pmd_t *pmdp)
+{
+	*pmdp = __pmd(0);
+}
+
+
+/*
+ * When flushing the tlb entry for a page, we also need to flush the hash
+ * table entry.  flush_hash_pages is assembler (for speed) in hashtable.S.
+ */
+extern int flush_hash_pages(unsigned context, unsigned long va,
+			    unsigned long pmdval, int count);
+
+/* Add an HPTE to the hash table */
+extern void add_hash_page(unsigned context, unsigned long va,
+			  unsigned long pmdval);
+
+/* Flush an entry from the TLB/hash table */
+extern void flush_hash_entry(struct mm_struct *mm, pte_t *ptep,
+			     unsigned long address);
+
+/*
+ * PTE updates. This function is called whenever an existing
+ * valid PTE is updated. This does -not- include set_pte_at()
+ * which nowadays only sets a new PTE.
+ *
+ * Depending on the type of MMU, we may need to use atomic updates
+ * and the PTE may be either 32 or 64 bit wide. In the later case,
+ * when using atomic updates, only the low part of the PTE is
+ * accessed atomically.
+ *
+ * In addition, on 44x, we also maintain a global flag indicating
+ * that an executable user mapping was modified, which is needed
+ * to properly flush the virtually tagged instruction cache of
+ * those implementations.
+ */
+#ifndef CONFIG_PTE_64BIT
+static inline unsigned long pte_update(pte_t *p,
+				       unsigned long clr,
+				       unsigned long set)
+{
+	unsigned long old, tmp;
+
+	__asm__ __volatile__("\
+1:	lwarx	%0,0,%3\n\
+	andc	%1,%0,%4\n\
+	or	%1,%1,%5\n"
+	PPC405_ERR77(0,%3)
+"	stwcx.	%1,0,%3\n\
+	bne-	1b"
+	: "=&r" (old), "=&r" (tmp), "=m" (*p)
+	: "r" (p), "r" (clr), "r" (set), "m" (*p)
+	: "cc" );
+
+	return old;
+}
+#else /* CONFIG_PTE_64BIT */
+static inline unsigned long long pte_update(pte_t *p,
+					    unsigned long clr,
+					    unsigned long set)
+{
+	unsigned long long old;
+	unsigned long tmp;
+
+	__asm__ __volatile__("\
+1:	lwarx	%L0,0,%4\n\
+	lwzx	%0,0,%3\n\
+	andc	%1,%L0,%5\n\
+	or	%1,%1,%6\n"
+	PPC405_ERR77(0,%3)
+"	stwcx.	%1,0,%4\n\
+	bne-	1b"
+	: "=&r" (old), "=&r" (tmp), "=m" (*p)
+	: "r" (p), "r" ((unsigned long)(p) + 4), "r" (clr), "r" (set), "m" (*p)
+	: "cc" );
+
+	return old;
+}
+#endif /* CONFIG_PTE_64BIT */
+
+/*
+ * 2.6 calls this without flushing the TLB entry; this is wrong
+ * for our hash-based implementation, we fix that up here.
+ */
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
+static inline int __ptep_test_and_clear_young(unsigned int context, unsigned long addr, pte_t *ptep)
+{
+	unsigned long old;
+	old = pte_update(ptep, _PAGE_ACCESSED, 0);
+	if (old & _PAGE_HASHPTE) {
+		unsigned long ptephys = __pa(ptep) & PAGE_MASK;
+		flush_hash_pages(context, addr, ptephys, 1);
+	}
+	return (old & _PAGE_ACCESSED) != 0;
+}
+#define ptep_test_and_clear_young(__vma, __addr, __ptep) \
+	__ptep_test_and_clear_young((__vma)->vm_mm->context.id, __addr, __ptep)
+
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
+static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+				       pte_t *ptep)
+{
+	return __pte(pte_update(ptep, ~_PAGE_HASHPTE, 0));
+}
+
+#define __HAVE_ARCH_PTEP_SET_WRPROTECT
+static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
+				      pte_t *ptep)
+{
+	pte_update(ptep, (_PAGE_RW | _PAGE_HWWRITE), _PAGE_RO);
+}
+static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
+					   unsigned long addr, pte_t *ptep)
+{
+	ptep_set_wrprotect(mm, addr, ptep);
+}
+
+
+static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry)
+{
+	unsigned long set = pte_val(entry) &
+		(_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC);
+	unsigned long clr = ~pte_val(entry) & _PAGE_RO;
+
+	pte_update(ptep, clr, set);
+}
+
+#define __HAVE_ARCH_PTE_SAME
+#define pte_same(A,B)	(((pte_val(A) ^ pte_val(B)) & ~_PAGE_HASHPTE) == 0)
+
+/*
+ * Note that on Book E processors, the pmd contains the kernel virtual
+ * (lowmem) address of the pte page.  The physical address is less useful
+ * because everything runs with translation enabled (even the TLB miss
+ * handler).  On everything else the pmd contains the physical address
+ * of the pte page.  -- paulus
+ */
+#ifndef CONFIG_BOOKE
+#define pmd_page_vaddr(pmd)	\
+	((unsigned long) __va(pmd_val(pmd) & PAGE_MASK))
+#define pmd_page(pmd)		\
+	pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT)
+#else
+#define pmd_page_vaddr(pmd)	\
+	((unsigned long) (pmd_val(pmd) & PAGE_MASK))
+#define pmd_page(pmd)		\
+	pfn_to_page((__pa(pmd_val(pmd)) >> PAGE_SHIFT))
+#endif
+
+/* to find an entry in a kernel page-table-directory */
+#define pgd_offset_k(address) pgd_offset(&init_mm, address)
+
+/* to find an entry in a page-table-directory */
+#define pgd_index(address)	 ((address) >> PGDIR_SHIFT)
+#define pgd_offset(mm, address)	 ((mm)->pgd + pgd_index(address))
+
+/* Find an entry in the third-level page table.. */
+#define pte_index(address)		\
+	(((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
+#define pte_offset_kernel(dir, addr)	\
+	((pte_t *) pmd_page_vaddr(*(dir)) + pte_index(addr))
+#define pte_offset_map(dir, addr)		\
+	((pte_t *) kmap_atomic(pmd_page(*(dir))) + pte_index(addr))
+#define pte_unmap(pte)		kunmap_atomic(pte)
+
+/*
+ * Encode and decode a swap entry.
+ * Note that the bits we use in a PTE for representing a swap entry
+ * must not include the _PAGE_PRESENT bit or the _PAGE_HASHPTE bit (if used).
+ *   -- paulus
+ */
+#define __swp_type(entry)		((entry).val & 0x1f)
+#define __swp_offset(entry)		((entry).val >> 5)
+#define __swp_entry(type, offset)	((swp_entry_t) { (type) | ((offset) << 5) })
+#define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val(pte) >> 3 })
+#define __swp_entry_to_pte(x)		((pte_t) { (x).val << 3 })
+
+#ifndef CONFIG_PPC_4K_PAGES
+void pgtable_cache_init(void);
+#else
+/*
+ * No page table caches to initialise
+ */
+#define pgtable_cache_init()	do { } while (0)
+#endif
+
+extern int get_pteptr(struct mm_struct *mm, unsigned long addr, pte_t **ptep,
+		      pmd_t **pmdp);
+
+/* Generic accessors to PTE bits */
+static inline int pte_write(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_RW);}
+static inline int pte_dirty(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_DIRTY); }
+static inline int pte_young(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_ACCESSED); }
+static inline int pte_special(pte_t pte)	{ return !!(pte_val(pte) & _PAGE_SPECIAL); }
+static inline int pte_none(pte_t pte)		{ return (pte_val(pte) & ~_PTE_NONE_MASK) == 0; }
+static inline pgprot_t pte_pgprot(pte_t pte)	{ return __pgprot(pte_val(pte) & PAGE_PROT_BITS); }
+
+static inline int pte_present(pte_t pte)
+{
+	return pte_val(pte) & _PAGE_PRESENT;
+}
+
+/* Conversion functions: convert a page and protection to a page entry,
+ * and a page entry and page directory to the page they refer to.
+ *
+ * Even if PTEs can be unsigned long long, a PFN is always an unsigned
+ * long for now.
+ */
+static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot)
+{
+	return __pte(((pte_basic_t)(pfn) << PTE_RPN_SHIFT) |
+		     pgprot_val(pgprot));
+}
+
+static inline unsigned long pte_pfn(pte_t pte)
+{
+	return pte_val(pte) >> PTE_RPN_SHIFT;
+}
+
+/* Generic modifiers for PTE bits */
+static inline pte_t pte_wrprotect(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~_PAGE_RW);
+}
+
+static inline pte_t pte_mkclean(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~_PAGE_DIRTY);
+}
+
+static inline pte_t pte_mkold(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~_PAGE_ACCESSED);
+}
+
+static inline pte_t pte_mkwrite(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_RW);
+}
+
+static inline pte_t pte_mkdirty(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_DIRTY);
+}
+
+static inline pte_t pte_mkyoung(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_ACCESSED);
+}
+
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_SPECIAL);
+}
+
+static inline pte_t pte_mkhuge(pte_t pte)
+{
+	return pte;
+}
+
+static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
+{
+	return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot));
+}
+
+
+
+/* This low level function performs the actual PTE insertion
+ * Setting the PTE depends on the MMU type and other factors. It's
+ * an horrible mess that I'm not going to try to clean up now but
+ * I'm keeping it in one place rather than spread around
+ */
+static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
+				pte_t *ptep, pte_t pte, int percpu)
+{
+#if defined(CONFIG_PPC_STD_MMU_32) && defined(CONFIG_SMP) && !defined(CONFIG_PTE_64BIT)
+	/* First case is 32-bit Hash MMU in SMP mode with 32-bit PTEs. We use the
+	 * helper pte_update() which does an atomic update. We need to do that
+	 * because a concurrent invalidation can clear _PAGE_HASHPTE. If it's a
+	 * per-CPU PTE such as a kmap_atomic, we do a simple update preserving
+	 * the hash bits instead (ie, same as the non-SMP case)
+	 */
+	if (percpu)
+		*ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE)
+			      | (pte_val(pte) & ~_PAGE_HASHPTE));
+	else
+		pte_update(ptep, ~_PAGE_HASHPTE, pte_val(pte));
+
+#elif defined(CONFIG_PPC32) && defined(CONFIG_PTE_64BIT)
+	/* Second case is 32-bit with 64-bit PTE.  In this case, we
+	 * can just store as long as we do the two halves in the right order
+	 * with a barrier in between. This is possible because we take care,
+	 * in the hash code, to pre-invalidate if the PTE was already hashed,
+	 * which synchronizes us with any concurrent invalidation.
+	 * In the percpu case, we also fallback to the simple update preserving
+	 * the hash bits
+	 */
+	if (percpu) {
+		*ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE)
+			      | (pte_val(pte) & ~_PAGE_HASHPTE));
+		return;
+	}
+	if (pte_val(*ptep) & _PAGE_HASHPTE)
+		flush_hash_entry(mm, ptep, addr);
+	__asm__ __volatile__("\
+		stw%U0%X0 %2,%0\n\
+		eieio\n\
+		stw%U0%X0 %L2,%1"
+	: "=m" (*ptep), "=m" (*((unsigned char *)ptep+4))
+	: "r" (pte) : "memory");
+
+#elif defined(CONFIG_PPC_STD_MMU_32)
+	/* Third case is 32-bit hash table in UP mode, we need to preserve
+	 * the _PAGE_HASHPTE bit since we may not have invalidated the previous
+	 * translation in the hash yet (done in a subsequent flush_tlb_xxx())
+	 * and see we need to keep track that this PTE needs invalidating
+	 */
+	*ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE)
+		      | (pte_val(pte) & ~_PAGE_HASHPTE));
+
+#else
+#error "Not supported "
+#endif
+}
+
+/*
+ * Macro to mark a page protection value as "uncacheable".
+ */
+
+#define _PAGE_CACHE_CTL	(_PAGE_COHERENT | _PAGE_GUARDED | _PAGE_NO_CACHE | \
+			 _PAGE_WRITETHRU)
+
+#define pgprot_noncached pgprot_noncached
+static inline pgprot_t pgprot_noncached(pgprot_t prot)
+{
+	return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) |
+			_PAGE_NO_CACHE | _PAGE_GUARDED);
+}
+
+#define pgprot_noncached_wc pgprot_noncached_wc
+static inline pgprot_t pgprot_noncached_wc(pgprot_t prot)
+{
+	return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) |
+			_PAGE_NO_CACHE);
+}
+
+#define pgprot_cached pgprot_cached
+static inline pgprot_t pgprot_cached(pgprot_t prot)
+{
+	return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) |
+			_PAGE_COHERENT);
+}
+
+#define pgprot_cached_wthru pgprot_cached_wthru
+static inline pgprot_t pgprot_cached_wthru(pgprot_t prot)
+{
+	return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) |
+			_PAGE_COHERENT | _PAGE_WRITETHRU);
+}
+
+#define pgprot_cached_noncoherent pgprot_cached_noncoherent
+static inline pgprot_t pgprot_cached_noncoherent(pgprot_t prot)
+{
+	return __pgprot(pgprot_val(prot) & ~_PAGE_CACHE_CTL);
+}
+
+#define pgprot_writecombine pgprot_writecombine
+static inline pgprot_t pgprot_writecombine(pgprot_t prot)
+{
+	return pgprot_noncached_wc(prot);
+}
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /*  _ASM_POWERPC_BOOK3S_32_PGTABLE_H */
diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
new file mode 100644
index 000000000000..ea0414d6659e
--- /dev/null
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -0,0 +1,132 @@
+#ifndef _ASM_POWERPC_BOOK3S_64_HASH_4K_H
+#define _ASM_POWERPC_BOOK3S_64_HASH_4K_H
+/*
+ * Entries per page directory level.  The PTE level must use a 64b record
+ * for each page table entry.  The PMD and PGD level use a 32b record for
+ * each entry by assuming that each entry is page aligned.
+ */
+#define PTE_INDEX_SIZE  9
+#define PMD_INDEX_SIZE  7
+#define PUD_INDEX_SIZE  9
+#define PGD_INDEX_SIZE  9
+
+#ifndef __ASSEMBLY__
+#define PTE_TABLE_SIZE	(sizeof(pte_t) << PTE_INDEX_SIZE)
+#define PMD_TABLE_SIZE	(sizeof(pmd_t) << PMD_INDEX_SIZE)
+#define PUD_TABLE_SIZE	(sizeof(pud_t) << PUD_INDEX_SIZE)
+#define PGD_TABLE_SIZE	(sizeof(pgd_t) << PGD_INDEX_SIZE)
+#endif	/* __ASSEMBLY__ */
+
+#define PTRS_PER_PTE	(1 << PTE_INDEX_SIZE)
+#define PTRS_PER_PMD	(1 << PMD_INDEX_SIZE)
+#define PTRS_PER_PUD	(1 << PUD_INDEX_SIZE)
+#define PTRS_PER_PGD	(1 << PGD_INDEX_SIZE)
+
+/* PMD_SHIFT determines what a second-level page table entry can map */
+#define PMD_SHIFT	(PAGE_SHIFT + PTE_INDEX_SIZE)
+#define PMD_SIZE	(1UL << PMD_SHIFT)
+#define PMD_MASK	(~(PMD_SIZE-1))
+
+/* With 4k base page size, hugepage PTEs go at the PMD level */
+#define MIN_HUGEPTE_SHIFT	PMD_SHIFT
+
+/* PUD_SHIFT determines what a third-level page table entry can map */
+#define PUD_SHIFT	(PMD_SHIFT + PMD_INDEX_SIZE)
+#define PUD_SIZE	(1UL << PUD_SHIFT)
+#define PUD_MASK	(~(PUD_SIZE-1))
+
+/* PGDIR_SHIFT determines what a fourth-level page table entry can map */
+#define PGDIR_SHIFT	(PUD_SHIFT + PUD_INDEX_SIZE)
+#define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
+#define PGDIR_MASK	(~(PGDIR_SIZE-1))
+
+/* Bits to mask out from a PMD to get to the PTE page */
+#define PMD_MASKED_BITS		0
+/* Bits to mask out from a PUD to get to the PMD page */
+#define PUD_MASKED_BITS		0
+/* Bits to mask out from a PGD to get to the PUD page */
+#define PGD_MASKED_BITS		0
+
+/* PTE flags to conserve for HPTE identification */
+#define _PAGE_HPTEFLAGS (_PAGE_BUSY | _PAGE_HASHPTE | \
+			 _PAGE_F_SECOND | _PAGE_F_GIX)
+
+/* shift to put page number into pte */
+#define PTE_RPN_SHIFT	(18)
+
+#define _PAGE_4K_PFN		0
+#ifndef __ASSEMBLY__
+/*
+ * 4-level page tables related bits
+ */
+
+#define pgd_none(pgd)		(!pgd_val(pgd))
+#define pgd_bad(pgd)		(pgd_val(pgd) == 0)
+#define pgd_present(pgd)	(pgd_val(pgd) != 0)
+#define pgd_page_vaddr(pgd)	(pgd_val(pgd) & ~PGD_MASKED_BITS)
+
+static inline void pgd_clear(pgd_t *pgdp)
+{
+	*pgdp = __pgd(0);
+}
+
+static inline pte_t pgd_pte(pgd_t pgd)
+{
+	return __pte(pgd_val(pgd));
+}
+
+static inline pgd_t pte_pgd(pte_t pte)
+{
+	return __pgd(pte_val(pte));
+}
+extern struct page *pgd_page(pgd_t pgd);
+
+#define pud_offset(pgdp, addr)	\
+  (((pud_t *) pgd_page_vaddr(*(pgdp))) + \
+    (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)))
+
+#define pud_ERROR(e) \
+	pr_err("%s:%d: bad pud %08lx.\n", __FILE__, __LINE__, pud_val(e))
+
+/*
+ * On all 4K setups, remap_4k_pfn() equates to remap_pfn_range() */
+#define remap_4k_pfn(vma, addr, pfn, prot)	\
+	remap_pfn_range((vma), (addr), (pfn), PAGE_SIZE, (prot))
+
+#ifdef CONFIG_HUGETLB_PAGE
+/*
+ * For 4k page size, we support explicit hugepage via hugepd
+ */
+static inline int pmd_huge(pmd_t pmd)
+{
+	return 0;
+}
+
+static inline int pud_huge(pud_t pud)
+{
+	return 0;
+}
+
+static inline int pgd_huge(pgd_t pgd)
+{
+	return 0;
+}
+#define pgd_huge pgd_huge
+
+static inline int hugepd_ok(hugepd_t hpd)
+{
+	/*
+	 * if it is not a pte and have hugepd shift mask
+	 * set, then it is a hugepd directory pointer
+	 */
+	if (!(hpd.pd & _PAGE_PTE) &&
+	    ((hpd.pd & HUGEPD_SHIFT_MASK) != 0))
+		return true;
+	return false;
+}
+#define is_hugepd(hpd)		(hugepd_ok(hpd))
+#endif
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* _ASM_POWERPC_BOOK3S_64_HASH_4K_H */
diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h
new file mode 100644
index 000000000000..9e55e3b1fef0
--- /dev/null
+++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h
@@ -0,0 +1,312 @@
+#ifndef _ASM_POWERPC_BOOK3S_64_HASH_64K_H
+#define _ASM_POWERPC_BOOK3S_64_HASH_64K_H
+
+#include <asm-generic/pgtable-nopud.h>
+
+#define PTE_INDEX_SIZE  8
+#define PMD_INDEX_SIZE  10
+#define PUD_INDEX_SIZE	0
+#define PGD_INDEX_SIZE  12
+
+#define PTRS_PER_PTE	(1 << PTE_INDEX_SIZE)
+#define PTRS_PER_PMD	(1 << PMD_INDEX_SIZE)
+#define PTRS_PER_PGD	(1 << PGD_INDEX_SIZE)
+
+/* With 4k base page size, hugepage PTEs go at the PMD level */
+#define MIN_HUGEPTE_SHIFT	PAGE_SHIFT
+
+/* PMD_SHIFT determines what a second-level page table entry can map */
+#define PMD_SHIFT	(PAGE_SHIFT + PTE_INDEX_SIZE)
+#define PMD_SIZE	(1UL << PMD_SHIFT)
+#define PMD_MASK	(~(PMD_SIZE-1))
+
+/* PGDIR_SHIFT determines what a third-level page table entry can map */
+#define PGDIR_SHIFT	(PMD_SHIFT + PMD_INDEX_SIZE)
+#define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
+#define PGDIR_MASK	(~(PGDIR_SIZE-1))
+
+#define _PAGE_COMBO	0x00040000 /* this is a combo 4k page */
+#define _PAGE_4K_PFN	0x00080000 /* PFN is for a single 4k page */
+/*
+ * Used to track subpage group valid if _PAGE_COMBO is set
+ * This overloads _PAGE_F_GIX and _PAGE_F_SECOND
+ */
+#define _PAGE_COMBO_VALID	(_PAGE_F_GIX | _PAGE_F_SECOND)
+
+/* PTE flags to conserve for HPTE identification */
+#define _PAGE_HPTEFLAGS (_PAGE_BUSY | _PAGE_F_SECOND | \
+			 _PAGE_F_GIX | _PAGE_HASHPTE | _PAGE_COMBO)
+
+/* Shift to put page number into pte.
+ *
+ * That gives us a max RPN of 34 bits, which means a max of 50 bits
+ * of addressable physical space, or 46 bits for the special 4k PFNs.
+ */
+#define PTE_RPN_SHIFT	(30)
+/*
+ * we support 16 fragments per PTE page of 64K size.
+ */
+#define PTE_FRAG_NR	16
+/*
+ * We use a 2K PTE page fragment and another 2K for storing
+ * real_pte_t hash index
+ */
+#define PTE_FRAG_SIZE_SHIFT  12
+#define PTE_FRAG_SIZE (1UL << PTE_FRAG_SIZE_SHIFT)
+
+/*
+ * Bits to mask out from a PMD to get to the PTE page
+ * PMDs point to PTE table fragments which are PTE_FRAG_SIZE aligned.
+ */
+#define PMD_MASKED_BITS		(PTE_FRAG_SIZE - 1)
+/* Bits to mask out from a PGD/PUD to get to the PMD page */
+#define PUD_MASKED_BITS		0x1ff
+
+#ifndef __ASSEMBLY__
+
+/*
+ * With 64K pages on hash table, we have a special PTE format that
+ * uses a second "half" of the page table to encode sub-page information
+ * in order to deal with 64K made of 4K HW pages. Thus we override the
+ * generic accessors and iterators here
+ */
+#define __real_pte __real_pte
+static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep)
+{
+	real_pte_t rpte;
+	unsigned long *hidxp;
+
+	rpte.pte = pte;
+	rpte.hidx = 0;
+	if (pte_val(pte) & _PAGE_COMBO) {
+		/*
+		 * Make sure we order the hidx load against the _PAGE_COMBO
+		 * check. The store side ordering is done in __hash_page_4K
+		 */
+		smp_rmb();
+		hidxp = (unsigned long *)(ptep + PTRS_PER_PTE);
+		rpte.hidx = *hidxp;
+	}
+	return rpte;
+}
+
+static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index)
+{
+	if ((pte_val(rpte.pte) & _PAGE_COMBO))
+		return (rpte.hidx >> (index<<2)) & 0xf;
+	return (pte_val(rpte.pte) >> _PAGE_F_GIX_SHIFT) & 0xf;
+}
+
+#define __rpte_to_pte(r)	((r).pte)
+extern bool __rpte_sub_valid(real_pte_t rpte, unsigned long index);
+/*
+ * Trick: we set __end to va + 64k, which happens works for
+ * a 16M page as well as we want only one iteration
+ */
+#define pte_iterate_hashed_subpages(rpte, psize, vpn, index, shift)	\
+	do {								\
+		unsigned long __end = vpn + (1UL << (PAGE_SHIFT - VPN_SHIFT));	\
+		unsigned __split = (psize == MMU_PAGE_4K ||		\
+				    psize == MMU_PAGE_64K_AP);		\
+		shift = mmu_psize_defs[psize].shift;			\
+		for (index = 0; vpn < __end; index++,			\
+			     vpn += (1L << (shift - VPN_SHIFT))) {	\
+			if (!__split || __rpte_sub_valid(rpte, index))	\
+				do {
+
+#define pte_iterate_hashed_end() } while(0); } } while(0)
+
+#define pte_pagesize_index(mm, addr, pte)	\
+	(((pte) & _PAGE_COMBO)? MMU_PAGE_4K: MMU_PAGE_64K)
+
+#define remap_4k_pfn(vma, addr, pfn, prot)				\
+	(WARN_ON(((pfn) >= (1UL << (64 - PTE_RPN_SHIFT)))) ? -EINVAL :	\
+		remap_pfn_range((vma), (addr), (pfn), PAGE_SIZE,	\
+			__pgprot(pgprot_val((prot)) | _PAGE_4K_PFN)))
+
+#define PTE_TABLE_SIZE	PTE_FRAG_SIZE
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define PMD_TABLE_SIZE	((sizeof(pmd_t) << PMD_INDEX_SIZE) + (sizeof(unsigned long) << PMD_INDEX_SIZE))
+#else
+#define PMD_TABLE_SIZE	(sizeof(pmd_t) << PMD_INDEX_SIZE)
+#endif
+#define PGD_TABLE_SIZE	(sizeof(pgd_t) << PGD_INDEX_SIZE)
+
+#define pgd_pte(pgd)	(pud_pte(((pud_t){ pgd })))
+#define pte_pgd(pte)	((pgd_t)pte_pud(pte))
+
+#ifdef CONFIG_HUGETLB_PAGE
+/*
+ * We have PGD_INDEX_SIZ = 12 and PTE_INDEX_SIZE = 8, so that we can have
+ * 16GB hugepage pte in PGD and 16MB hugepage pte at PMD;
+ *
+ * Defined in such a way that we can optimize away code block at build time
+ * if CONFIG_HUGETLB_PAGE=n.
+ */
+static inline int pmd_huge(pmd_t pmd)
+{
+	/*
+	 * leaf pte for huge page
+	 */
+	return !!(pmd_val(pmd) & _PAGE_PTE);
+}
+
+static inline int pud_huge(pud_t pud)
+{
+	/*
+	 * leaf pte for huge page
+	 */
+	return !!(pud_val(pud) & _PAGE_PTE);
+}
+
+static inline int pgd_huge(pgd_t pgd)
+{
+	/*
+	 * leaf pte for huge page
+	 */
+	return !!(pgd_val(pgd) & _PAGE_PTE);
+}
+#define pgd_huge pgd_huge
+
+#ifdef CONFIG_DEBUG_VM
+extern int hugepd_ok(hugepd_t hpd);
+#define is_hugepd(hpd)               (hugepd_ok(hpd))
+#else
+/*
+ * With 64k page size, we have hugepage ptes in the pgd and pmd entries. We don't
+ * need to setup hugepage directory for them. Our pte and page directory format
+ * enable us to have this enabled.
+ */
+static inline int hugepd_ok(hugepd_t hpd)
+{
+	return 0;
+}
+#define is_hugepd(pdep)			0
+#endif /* CONFIG_DEBUG_VM */
+
+#endif /* CONFIG_HUGETLB_PAGE */
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+extern unsigned long pmd_hugepage_update(struct mm_struct *mm,
+					 unsigned long addr,
+					 pmd_t *pmdp,
+					 unsigned long clr,
+					 unsigned long set);
+static inline char *get_hpte_slot_array(pmd_t *pmdp)
+{
+	/*
+	 * The hpte hindex is stored in the pgtable whose address is in the
+	 * second half of the PMD
+	 *
+	 * Order this load with the test for pmd_trans_huge in the caller
+	 */
+	smp_rmb();
+	return *(char **)(pmdp + PTRS_PER_PMD);
+
+
+}
+/*
+ * The linux hugepage PMD now include the pmd entries followed by the address
+ * to the stashed pgtable_t. The stashed pgtable_t contains the hpte bits.
+ * [ 1 bit secondary | 3 bit hidx | 1 bit valid | 000]. We use one byte per
+ * each HPTE entry. With 16MB hugepage and 64K HPTE we need 256 entries and
+ * with 4K HPTE we need 4096 entries. Both will fit in a 4K pgtable_t.
+ *
+ * The last three bits are intentionally left to zero. This memory location
+ * are also used as normal page PTE pointers. So if we have any pointers
+ * left around while we collapse a hugepage, we need to make sure
+ * _PAGE_PRESENT bit of that is zero when we look at them
+ */
+static inline unsigned int hpte_valid(unsigned char *hpte_slot_array, int index)
+{
+	return (hpte_slot_array[index] >> 3) & 0x1;
+}
+
+static inline unsigned int hpte_hash_index(unsigned char *hpte_slot_array,
+					   int index)
+{
+	return hpte_slot_array[index] >> 4;
+}
+
+static inline void mark_hpte_slot_valid(unsigned char *hpte_slot_array,
+					unsigned int index, unsigned int hidx)
+{
+	hpte_slot_array[index] = hidx << 4 | 0x1 << 3;
+}
+
+/*
+ *
+ * For core kernel code by design pmd_trans_huge is never run on any hugetlbfs
+ * page. The hugetlbfs page table walking and mangling paths are totally
+ * separated form the core VM paths and they're differentiated by
+ *  VM_HUGETLB being set on vm_flags well before any pmd_trans_huge could run.
+ *
+ * pmd_trans_huge() is defined as false at build time if
+ * CONFIG_TRANSPARENT_HUGEPAGE=n to optimize away code blocks at build
+ * time in such case.
+ *
+ * For ppc64 we need to differntiate from explicit hugepages from THP, because
+ * for THP we also track the subpage details at the pmd level. We don't do
+ * that for explicit huge pages.
+ *
+ */
+static inline int pmd_trans_huge(pmd_t pmd)
+{
+	return !!((pmd_val(pmd) & (_PAGE_PTE | _PAGE_THP_HUGE)) ==
+		  (_PAGE_PTE | _PAGE_THP_HUGE));
+}
+
+static inline int pmd_trans_splitting(pmd_t pmd)
+{
+	if (pmd_trans_huge(pmd))
+		return pmd_val(pmd) & _PAGE_SPLITTING;
+	return 0;
+}
+
+static inline int pmd_large(pmd_t pmd)
+{
+	return !!(pmd_val(pmd) & _PAGE_PTE);
+}
+
+static inline pmd_t pmd_mknotpresent(pmd_t pmd)
+{
+	return __pmd(pmd_val(pmd) & ~_PAGE_PRESENT);
+}
+
+static inline pmd_t pmd_mksplitting(pmd_t pmd)
+{
+	return __pmd(pmd_val(pmd) | _PAGE_SPLITTING);
+}
+
+#define __HAVE_ARCH_PMD_SAME
+static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
+{
+	return (((pmd_val(pmd_a) ^ pmd_val(pmd_b)) & ~_PAGE_HPTEFLAGS) == 0);
+}
+
+static inline int __pmdp_test_and_clear_young(struct mm_struct *mm,
+					      unsigned long addr, pmd_t *pmdp)
+{
+	unsigned long old;
+
+	if ((pmd_val(*pmdp) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0)
+		return 0;
+	old = pmd_hugepage_update(mm, addr, pmdp, _PAGE_ACCESSED, 0);
+	return ((old & _PAGE_ACCESSED) != 0);
+}
+
+#define __HAVE_ARCH_PMDP_SET_WRPROTECT
+static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr,
+				      pmd_t *pmdp)
+{
+
+	if ((pmd_val(*pmdp) & _PAGE_RW) == 0)
+		return;
+
+	pmd_hugepage_update(mm, addr, pmdp, _PAGE_RW, 0);
+}
+
+#endif /*  CONFIG_TRANSPARENT_HUGEPAGE */
+#endif	/* __ASSEMBLY__ */
+
+#endif /* _ASM_POWERPC_BOOK3S_64_HASH_64K_H */
diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h
new file mode 100644
index 000000000000..2ff8b3df553d
--- /dev/null
+++ b/arch/powerpc/include/asm/book3s/64/hash.h
@@ -0,0 +1,551 @@
+#ifndef _ASM_POWERPC_BOOK3S_64_HASH_H
+#define _ASM_POWERPC_BOOK3S_64_HASH_H
+#ifdef __KERNEL__
+
+/*
+ * Common bits between 4K and 64K pages in a linux-style PTE.
+ * These match the bits in the (hardware-defined) PowerPC PTE as closely
+ * as possible. Additional bits may be defined in pgtable-hash64-*.h
+ *
+ * Note: We only support user read/write permissions. Supervisor always
+ * have full read/write to pages above PAGE_OFFSET (pages below that
+ * always use the user access permissions).
+ *
+ * We could create separate kernel read-only if we used the 3 PP bits
+ * combinations that newer processors provide but we currently don't.
+ */
+#define _PAGE_PTE		0x00001
+#define _PAGE_PRESENT		0x00002 /* software: pte contains a translation */
+#define _PAGE_BIT_SWAP_TYPE	2
+#define _PAGE_USER		0x00004 /* matches one of the PP bits */
+#define _PAGE_EXEC		0x00008 /* No execute on POWER4 and newer (we invert) */
+#define _PAGE_GUARDED		0x00010
+/* We can derive Memory coherence from _PAGE_NO_CACHE */
+#define _PAGE_COHERENT		0x0
+#define _PAGE_NO_CACHE		0x00020 /* I: cache inhibit */
+#define _PAGE_WRITETHRU		0x00040 /* W: cache write-through */
+#define _PAGE_DIRTY		0x00080 /* C: page changed */
+#define _PAGE_ACCESSED		0x00100 /* R: page referenced */
+#define _PAGE_RW		0x00200 /* software: user write access allowed */
+#define _PAGE_HASHPTE		0x00400 /* software: pte has an associated HPTE */
+#define _PAGE_BUSY		0x00800 /* software: PTE & hash are busy */
+#define _PAGE_F_GIX		0x07000 /* full page: hidx bits */
+#define _PAGE_F_GIX_SHIFT	12
+#define _PAGE_F_SECOND		0x08000 /* Whether to use secondary hash or not */
+#define _PAGE_SPECIAL		0x10000 /* software: special page */
+
+#ifdef CONFIG_MEM_SOFT_DIRTY
+#define _PAGE_SOFT_DIRTY	0x20000 /* software: software dirty tracking */
+#else
+#define _PAGE_SOFT_DIRTY	0x00000
+#endif
+
+/*
+ * THP pages can't be special. So use the _PAGE_SPECIAL
+ */
+#define _PAGE_SPLITTING _PAGE_SPECIAL
+
+/*
+ * We need to differentiate between explicit huge page and THP huge
+ * page, since THP huge page also need to track real subpage details
+ */
+#define _PAGE_THP_HUGE  _PAGE_4K_PFN
+
+/*
+ * set of bits not changed in pmd_modify.
+ */
+#define _HPAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS |		\
+			 _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_SPLITTING | \
+			 _PAGE_THP_HUGE | _PAGE_PTE | _PAGE_SOFT_DIRTY)
+
+#ifdef CONFIG_PPC_64K_PAGES
+#include <asm/book3s/64/hash-64k.h>
+#else
+#include <asm/book3s/64/hash-4k.h>
+#endif
+
+/*
+ * Size of EA range mapped by our pagetables.
+ */
+#define PGTABLE_EADDR_SIZE	(PTE_INDEX_SIZE + PMD_INDEX_SIZE + \
+				 PUD_INDEX_SIZE + PGD_INDEX_SIZE + PAGE_SHIFT)
+#define PGTABLE_RANGE		(ASM_CONST(1) << PGTABLE_EADDR_SIZE)
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define PMD_CACHE_INDEX	(PMD_INDEX_SIZE + 1)
+#else
+#define PMD_CACHE_INDEX	PMD_INDEX_SIZE
+#endif
+/*
+ * Define the address range of the kernel non-linear virtual area
+ */
+#define KERN_VIRT_START ASM_CONST(0xD000000000000000)
+#define KERN_VIRT_SIZE	ASM_CONST(0x0000100000000000)
+
+/*
+ * The vmalloc space starts at the beginning of that region, and
+ * occupies half of it on hash CPUs and a quarter of it on Book3E
+ * (we keep a quarter for the virtual memmap)
+ */
+#define VMALLOC_START	KERN_VIRT_START
+#define VMALLOC_SIZE	(KERN_VIRT_SIZE >> 1)
+#define VMALLOC_END	(VMALLOC_START + VMALLOC_SIZE)
+
+/*
+ * Region IDs
+ */
+#define REGION_SHIFT		60UL
+#define REGION_MASK		(0xfUL << REGION_SHIFT)
+#define REGION_ID(ea)		(((unsigned long)(ea)) >> REGION_SHIFT)
+
+#define VMALLOC_REGION_ID	(REGION_ID(VMALLOC_START))
+#define KERNEL_REGION_ID	(REGION_ID(PAGE_OFFSET))
+#define VMEMMAP_REGION_ID	(0xfUL)	/* Server only */
+#define USER_REGION_ID		(0UL)
+
+/*
+ * Defines the address of the vmemap area, in its own region on
+ * hash table CPUs.
+ */
+#define VMEMMAP_BASE		(VMEMMAP_REGION_ID << REGION_SHIFT)
+
+#ifdef CONFIG_PPC_MM_SLICES
+#define HAVE_ARCH_UNMAPPED_AREA
+#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
+#endif /* CONFIG_PPC_MM_SLICES */
+
+/* No separate kernel read-only */
+#define _PAGE_KERNEL_RW		(_PAGE_RW | _PAGE_DIRTY) /* user access blocked by key */
+#define _PAGE_KERNEL_RO		 _PAGE_KERNEL_RW
+#define _PAGE_KERNEL_RWX	(_PAGE_DIRTY | _PAGE_RW | _PAGE_EXEC)
+
+/* Strong Access Ordering */
+#define _PAGE_SAO		(_PAGE_WRITETHRU | _PAGE_NO_CACHE | _PAGE_COHERENT)
+
+/* No page size encoding in the linux PTE */
+#define _PAGE_PSIZE		0
+
+/* PTEIDX nibble */
+#define _PTEIDX_SECONDARY	0x8
+#define _PTEIDX_GROUP_IX	0x7
+
+/* Hash table based platforms need atomic updates of the linux PTE */
+#define PTE_ATOMIC_UPDATES	1
+#define _PTE_NONE_MASK	_PAGE_HPTEFLAGS
+/*
+ * The mask convered by the RPN must be a ULL on 32-bit platforms with
+ * 64-bit PTEs
+ */
+#define PTE_RPN_MASK	(~((1UL << PTE_RPN_SHIFT) - 1))
+/*
+ * _PAGE_CHG_MASK masks of bits that are to be preserved across
+ * pgprot changes
+ */
+#define _PAGE_CHG_MASK	(PTE_RPN_MASK | _PAGE_HPTEFLAGS | _PAGE_DIRTY | \
+			 _PAGE_ACCESSED | _PAGE_SPECIAL | _PAGE_PTE | \
+			 _PAGE_SOFT_DIRTY)
+/*
+ * Mask of bits returned by pte_pgprot()
+ */
+#define PAGE_PROT_BITS	(_PAGE_GUARDED | _PAGE_COHERENT | _PAGE_NO_CACHE | \
+			 _PAGE_WRITETHRU | _PAGE_4K_PFN | \
+			 _PAGE_USER | _PAGE_ACCESSED |  \
+			 _PAGE_RW |  _PAGE_DIRTY | _PAGE_EXEC | \
+			 _PAGE_SOFT_DIRTY)
+/*
+ * We define 2 sets of base prot bits, one for basic pages (ie,
+ * cacheable kernel and user pages) and one for non cacheable
+ * pages. We always set _PAGE_COHERENT when SMP is enabled or
+ * the processor might need it for DMA coherency.
+ */
+#define _PAGE_BASE_NC	(_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_PSIZE)
+#define _PAGE_BASE	(_PAGE_BASE_NC | _PAGE_COHERENT)
+
+/* Permission masks used to generate the __P and __S table,
+ *
+ * Note:__pgprot is defined in arch/powerpc/include/asm/page.h
+ *
+ * Write permissions imply read permissions for now (we could make write-only
+ * pages on BookE but we don't bother for now). Execute permission control is
+ * possible on platforms that define _PAGE_EXEC
+ *
+ * Note due to the way vm flags are laid out, the bits are XWR
+ */
+#define PAGE_NONE	__pgprot(_PAGE_BASE)
+#define PAGE_SHARED	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW)
+#define PAGE_SHARED_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW | \
+				 _PAGE_EXEC)
+#define PAGE_COPY	__pgprot(_PAGE_BASE | _PAGE_USER )
+#define PAGE_COPY_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC)
+#define PAGE_READONLY	__pgprot(_PAGE_BASE | _PAGE_USER )
+#define PAGE_READONLY_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC)
+
+#define __P000	PAGE_NONE
+#define __P001	PAGE_READONLY
+#define __P010	PAGE_COPY
+#define __P011	PAGE_COPY
+#define __P100	PAGE_READONLY_X
+#define __P101	PAGE_READONLY_X
+#define __P110	PAGE_COPY_X
+#define __P111	PAGE_COPY_X
+
+#define __S000	PAGE_NONE
+#define __S001	PAGE_READONLY
+#define __S010	PAGE_SHARED
+#define __S011	PAGE_SHARED
+#define __S100	PAGE_READONLY_X
+#define __S101	PAGE_READONLY_X
+#define __S110	PAGE_SHARED_X
+#define __S111	PAGE_SHARED_X
+
+/* Permission masks used for kernel mappings */
+#define PAGE_KERNEL	__pgprot(_PAGE_BASE | _PAGE_KERNEL_RW)
+#define PAGE_KERNEL_NC	__pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | \
+				 _PAGE_NO_CACHE)
+#define PAGE_KERNEL_NCG	__pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | \
+				 _PAGE_NO_CACHE | _PAGE_GUARDED)
+#define PAGE_KERNEL_X	__pgprot(_PAGE_BASE | _PAGE_KERNEL_RWX)
+#define PAGE_KERNEL_RO	__pgprot(_PAGE_BASE | _PAGE_KERNEL_RO)
+#define PAGE_KERNEL_ROX	__pgprot(_PAGE_BASE | _PAGE_KERNEL_ROX)
+
+/* Protection used for kernel text. We want the debuggers to be able to
+ * set breakpoints anywhere, so don't write protect the kernel text
+ * on platforms where such control is possible.
+ */
+#if defined(CONFIG_KGDB) || defined(CONFIG_XMON) || defined(CONFIG_BDI_SWITCH) ||\
+	defined(CONFIG_KPROBES) || defined(CONFIG_DYNAMIC_FTRACE)
+#define PAGE_KERNEL_TEXT	PAGE_KERNEL_X
+#else
+#define PAGE_KERNEL_TEXT	PAGE_KERNEL_ROX
+#endif
+
+/* Make modules code happy. We don't set RO yet */
+#define PAGE_KERNEL_EXEC	PAGE_KERNEL_X
+#define PAGE_AGP		(PAGE_KERNEL_NC)
+
+#define PMD_BAD_BITS		(PTE_TABLE_SIZE-1)
+#define PUD_BAD_BITS		(PMD_TABLE_SIZE-1)
+
+#ifndef __ASSEMBLY__
+#define	pmd_bad(pmd)		(!is_kernel_addr(pmd_val(pmd)) \
+				 || (pmd_val(pmd) & PMD_BAD_BITS))
+#define pmd_page_vaddr(pmd)	(pmd_val(pmd) & ~PMD_MASKED_BITS)
+
+#define	pud_bad(pud)		(!is_kernel_addr(pud_val(pud)) \
+				 || (pud_val(pud) & PUD_BAD_BITS))
+#define pud_page_vaddr(pud)	(pud_val(pud) & ~PUD_MASKED_BITS)
+
+#define pgd_index(address) (((address) >> (PGDIR_SHIFT)) & (PTRS_PER_PGD - 1))
+#define pmd_index(address) (((address) >> (PMD_SHIFT)) & (PTRS_PER_PMD - 1))
+#define pte_index(address) (((address) >> (PAGE_SHIFT)) & (PTRS_PER_PTE - 1))
+
+extern void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
+			    pte_t *ptep, unsigned long pte, int huge);
+extern unsigned long htab_convert_pte_flags(unsigned long pteflags);
+/* Atomic PTE updates */
+static inline unsigned long pte_update(struct mm_struct *mm,
+				       unsigned long addr,
+				       pte_t *ptep, unsigned long clr,
+				       unsigned long set,
+				       int huge)
+{
+	unsigned long old, tmp;
+
+	__asm__ __volatile__(
+	"1:	ldarx	%0,0,%3		# pte_update\n\
+	andi.	%1,%0,%6\n\
+	bne-	1b \n\
+	andc	%1,%0,%4 \n\
+	or	%1,%1,%7\n\
+	stdcx.	%1,0,%3 \n\
+	bne-	1b"
+	: "=&r" (old), "=&r" (tmp), "=m" (*ptep)
+	: "r" (ptep), "r" (clr), "m" (*ptep), "i" (_PAGE_BUSY), "r" (set)
+	: "cc" );
+	/* huge pages use the old page table lock */
+	if (!huge)
+		assert_pte_locked(mm, addr);
+
+	if (old & _PAGE_HASHPTE)
+		hpte_need_flush(mm, addr, ptep, old, huge);
+
+	return old;
+}
+
+static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
+					      unsigned long addr, pte_t *ptep)
+{
+	unsigned long old;
+
+	if ((pte_val(*ptep) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0)
+		return 0;
+	old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0);
+	return (old & _PAGE_ACCESSED) != 0;
+}
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
+#define ptep_test_and_clear_young(__vma, __addr, __ptep)		   \
+({									   \
+	int __r;							   \
+	__r = __ptep_test_and_clear_young((__vma)->vm_mm, __addr, __ptep); \
+	__r;								   \
+})
+
+#define __HAVE_ARCH_PTEP_SET_WRPROTECT
+static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
+				      pte_t *ptep)
+{
+
+	if ((pte_val(*ptep) & _PAGE_RW) == 0)
+		return;
+
+	pte_update(mm, addr, ptep, _PAGE_RW, 0, 0);
+}
+
+static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
+					   unsigned long addr, pte_t *ptep)
+{
+	if ((pte_val(*ptep) & _PAGE_RW) == 0)
+		return;
+
+	pte_update(mm, addr, ptep, _PAGE_RW, 0, 1);
+}
+
+/*
+ * We currently remove entries from the hashtable regardless of whether
+ * the entry was young or dirty. The generic routines only flush if the
+ * entry was young or dirty which is not good enough.
+ *
+ * We should be more intelligent about this but for the moment we override
+ * these functions and force a tlb flush unconditionally
+ */
+#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
+#define ptep_clear_flush_young(__vma, __address, __ptep)		\
+({									\
+	int __young = __ptep_test_and_clear_young((__vma)->vm_mm, __address, \
+						  __ptep);		\
+	__young;							\
+})
+
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
+static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
+				       unsigned long addr, pte_t *ptep)
+{
+	unsigned long old = pte_update(mm, addr, ptep, ~0UL, 0, 0);
+	return __pte(old);
+}
+
+static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
+			     pte_t * ptep)
+{
+	pte_update(mm, addr, ptep, ~0UL, 0, 0);
+}
+
+
+/* Set the dirty and/or accessed bits atomically in a linux PTE, this
+ * function doesn't need to flush the hash entry
+ */
+static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry)
+{
+	unsigned long bits = pte_val(entry) &
+		(_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC |
+		 _PAGE_SOFT_DIRTY);
+
+	unsigned long old, tmp;
+
+	__asm__ __volatile__(
+	"1:	ldarx	%0,0,%4\n\
+		andi.	%1,%0,%6\n\
+		bne-	1b \n\
+		or	%0,%3,%0\n\
+		stdcx.	%0,0,%4\n\
+		bne-	1b"
+	:"=&r" (old), "=&r" (tmp), "=m" (*ptep)
+	:"r" (bits), "r" (ptep), "m" (*ptep), "i" (_PAGE_BUSY)
+	:"cc");
+}
+
+#define __HAVE_ARCH_PTE_SAME
+#define pte_same(A,B)	(((pte_val(A) ^ pte_val(B)) & ~_PAGE_HPTEFLAGS) == 0)
+
+/* Generic accessors to PTE bits */
+static inline int pte_write(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_RW);}
+static inline int pte_dirty(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_DIRTY); }
+static inline int pte_young(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_ACCESSED); }
+static inline int pte_special(pte_t pte)	{ return !!(pte_val(pte) & _PAGE_SPECIAL); }
+static inline int pte_none(pte_t pte)		{ return (pte_val(pte) & ~_PTE_NONE_MASK) == 0; }
+static inline pgprot_t pte_pgprot(pte_t pte)	{ return __pgprot(pte_val(pte) & PAGE_PROT_BITS); }
+
+#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
+static inline bool pte_soft_dirty(pte_t pte)
+{
+	return !!(pte_val(pte) & _PAGE_SOFT_DIRTY);
+}
+static inline pte_t pte_mksoft_dirty(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_SOFT_DIRTY);
+}
+
+static inline pte_t pte_clear_soft_dirty(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~_PAGE_SOFT_DIRTY);
+}
+#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */
+
+#ifdef CONFIG_NUMA_BALANCING
+/*
+ * These work without NUMA balancing but the kernel does not care. See the
+ * comment in include/asm-generic/pgtable.h . On powerpc, this will only
+ * work for user pages and always return true for kernel pages.
+ */
+static inline int pte_protnone(pte_t pte)
+{
+	return (pte_val(pte) &
+		(_PAGE_PRESENT | _PAGE_USER)) == _PAGE_PRESENT;
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
+static inline int pte_present(pte_t pte)
+{
+	return pte_val(pte) & _PAGE_PRESENT;
+}
+
+/* Conversion functions: convert a page and protection to a page entry,
+ * and a page entry and page directory to the page they refer to.
+ *
+ * Even if PTEs can be unsigned long long, a PFN is always an unsigned
+ * long for now.
+ */
+static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot)
+{
+	return __pte(((pte_basic_t)(pfn) << PTE_RPN_SHIFT) |
+		     pgprot_val(pgprot));
+}
+
+static inline unsigned long pte_pfn(pte_t pte)
+{
+	return pte_val(pte) >> PTE_RPN_SHIFT;
+}
+
+/* Generic modifiers for PTE bits */
+static inline pte_t pte_wrprotect(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~_PAGE_RW);
+}
+
+static inline pte_t pte_mkclean(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~_PAGE_DIRTY);
+}
+
+static inline pte_t pte_mkold(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~_PAGE_ACCESSED);
+}
+
+static inline pte_t pte_mkwrite(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_RW);
+}
+
+static inline pte_t pte_mkdirty(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_DIRTY | _PAGE_SOFT_DIRTY);
+}
+
+static inline pte_t pte_mkyoung(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_ACCESSED);
+}
+
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_SPECIAL);
+}
+
+static inline pte_t pte_mkhuge(pte_t pte)
+{
+	return pte;
+}
+
+static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
+{
+	return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot));
+}
+
+/* This low level function performs the actual PTE insertion
+ * Setting the PTE depends on the MMU type and other factors. It's
+ * an horrible mess that I'm not going to try to clean up now but
+ * I'm keeping it in one place rather than spread around
+ */
+static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
+				pte_t *ptep, pte_t pte, int percpu)
+{
+	/*
+	 * Anything else just stores the PTE normally. That covers all 64-bit
+	 * cases, and 32-bit non-hash with 32-bit PTEs.
+	 */
+	*ptep = pte;
+}
+
+/*
+ * Macro to mark a page protection value as "uncacheable".
+ */
+
+#define _PAGE_CACHE_CTL	(_PAGE_COHERENT | _PAGE_GUARDED | _PAGE_NO_CACHE | \
+			 _PAGE_WRITETHRU)
+
+#define pgprot_noncached pgprot_noncached
+static inline pgprot_t pgprot_noncached(pgprot_t prot)
+{
+	return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) |
+			_PAGE_NO_CACHE | _PAGE_GUARDED);
+}
+
+#define pgprot_noncached_wc pgprot_noncached_wc
+static inline pgprot_t pgprot_noncached_wc(pgprot_t prot)
+{
+	return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) |
+			_PAGE_NO_CACHE);
+}
+
+#define pgprot_cached pgprot_cached
+static inline pgprot_t pgprot_cached(pgprot_t prot)
+{
+	return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) |
+			_PAGE_COHERENT);
+}
+
+#define pgprot_cached_wthru pgprot_cached_wthru
+static inline pgprot_t pgprot_cached_wthru(pgprot_t prot)
+{
+	return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) |
+			_PAGE_COHERENT | _PAGE_WRITETHRU);
+}
+
+#define pgprot_cached_noncoherent pgprot_cached_noncoherent
+static inline pgprot_t pgprot_cached_noncoherent(pgprot_t prot)
+{
+	return __pgprot(pgprot_val(prot) & ~_PAGE_CACHE_CTL);
+}
+
+#define pgprot_writecombine pgprot_writecombine
+static inline pgprot_t pgprot_writecombine(pgprot_t prot)
+{
+	return pgprot_noncached_wc(prot);
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+extern void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
+				   pmd_t *pmdp, unsigned long old_pmd);
+#else
+static inline void hpte_do_hugepage_flush(struct mm_struct *mm,
+					  unsigned long addr, pmd_t *pmdp,
+					  unsigned long old_pmd)
+{
+	WARN(1, "%s called with THP disabled\n", __func__);
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+#endif /* !__ASSEMBLY__ */
+#endif /* __KERNEL__ */
+#endif /* _ASM_POWERPC_BOOK3S_64_HASH_H */
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
new file mode 100644
index 000000000000..b3a5badab69f
--- /dev/null
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -0,0 +1,300 @@
+#ifndef _ASM_POWERPC_BOOK3S_64_PGTABLE_H_
+#define _ASM_POWERPC_BOOK3S_64_PGTABLE_H_
+/*
+ * This file contains the functions and defines necessary to modify and use
+ * the ppc64 hashed page table.
+ */
+
+#include <asm/book3s/64/hash.h>
+#include <asm/barrier.h>
+
+/*
+ * The second half of the kernel virtual space is used for IO mappings,
+ * it's itself carved into the PIO region (ISA and PHB IO space) and
+ * the ioremap space
+ *
+ *  ISA_IO_BASE = KERN_IO_START, 64K reserved area
+ *  PHB_IO_BASE = ISA_IO_BASE + 64K to ISA_IO_BASE + 2G, PHB IO spaces
+ * IOREMAP_BASE = ISA_IO_BASE + 2G to VMALLOC_START + PGTABLE_RANGE
+ */
+#define KERN_IO_START	(KERN_VIRT_START + (KERN_VIRT_SIZE >> 1))
+#define FULL_IO_SIZE	0x80000000ul
+#define  ISA_IO_BASE	(KERN_IO_START)
+#define  ISA_IO_END	(KERN_IO_START + 0x10000ul)
+#define  PHB_IO_BASE	(ISA_IO_END)
+#define  PHB_IO_END	(KERN_IO_START + FULL_IO_SIZE)
+#define IOREMAP_BASE	(PHB_IO_END)
+#define IOREMAP_END	(KERN_VIRT_START + KERN_VIRT_SIZE)
+
+#define vmemmap			((struct page *)VMEMMAP_BASE)
+
+/* Advertise special mapping type for AGP */
+#define HAVE_PAGE_AGP
+
+/* Advertise support for _PAGE_SPECIAL */
+#define __HAVE_ARCH_PTE_SPECIAL
+
+#ifndef __ASSEMBLY__
+
+/*
+ * This is the default implementation of various PTE accessors, it's
+ * used in all cases except Book3S with 64K pages where we have a
+ * concept of sub-pages
+ */
+#ifndef __real_pte
+
+#ifdef CONFIG_STRICT_MM_TYPECHECKS
+#define __real_pte(e,p)		((real_pte_t){(e)})
+#define __rpte_to_pte(r)	((r).pte)
+#else
+#define __real_pte(e,p)		(e)
+#define __rpte_to_pte(r)	(__pte(r))
+#endif
+#define __rpte_to_hidx(r,index)	(pte_val(__rpte_to_pte(r)) >>_PAGE_F_GIX_SHIFT)
+
+#define pte_iterate_hashed_subpages(rpte, psize, va, index, shift)       \
+	do {							         \
+		index = 0;					         \
+		shift = mmu_psize_defs[psize].shift;		         \
+
+#define pte_iterate_hashed_end() } while(0)
+
+/*
+ * We expect this to be called only for user addresses or kernel virtual
+ * addresses other than the linear mapping.
+ */
+#define pte_pagesize_index(mm, addr, pte)	MMU_PAGE_4K
+
+#endif /* __real_pte */
+
+static inline void pmd_set(pmd_t *pmdp, unsigned long val)
+{
+	*pmdp = __pmd(val);
+}
+
+static inline void pmd_clear(pmd_t *pmdp)
+{
+	*pmdp = __pmd(0);
+}
+
+#define pmd_none(pmd)		(!pmd_val(pmd))
+#define	pmd_present(pmd)	(!pmd_none(pmd))
+
+static inline void pud_set(pud_t *pudp, unsigned long val)
+{
+	*pudp = __pud(val);
+}
+
+static inline void pud_clear(pud_t *pudp)
+{
+	*pudp = __pud(0);
+}
+
+#define pud_none(pud)		(!pud_val(pud))
+#define pud_present(pud)	(pud_val(pud) != 0)
+
+extern struct page *pud_page(pud_t pud);
+extern struct page *pmd_page(pmd_t pmd);
+static inline pte_t pud_pte(pud_t pud)
+{
+	return __pte(pud_val(pud));
+}
+
+static inline pud_t pte_pud(pte_t pte)
+{
+	return __pud(pte_val(pte));
+}
+#define pud_write(pud)		pte_write(pud_pte(pud))
+#define pgd_write(pgd)		pte_write(pgd_pte(pgd))
+static inline void pgd_set(pgd_t *pgdp, unsigned long val)
+{
+	*pgdp = __pgd(val);
+}
+
+/*
+ * Find an entry in a page-table-directory.  We combine the address region
+ * (the high order N bits) and the pgd portion of the address.
+ */
+
+#define pgd_offset(mm, address)	 ((mm)->pgd + pgd_index(address))
+
+#define pmd_offset(pudp,addr) \
+	(((pmd_t *) pud_page_vaddr(*(pudp))) + pmd_index(addr))
+
+#define pte_offset_kernel(dir,addr) \
+	(((pte_t *) pmd_page_vaddr(*(dir))) + pte_index(addr))
+
+#define pte_offset_map(dir,addr)	pte_offset_kernel((dir), (addr))
+#define pte_unmap(pte)			do { } while(0)
+
+/* to find an entry in a kernel page-table-directory */
+/* This now only contains the vmalloc pages */
+#define pgd_offset_k(address) pgd_offset(&init_mm, address)
+
+#define pte_ERROR(e) \
+	pr_err("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e))
+#define pmd_ERROR(e) \
+	pr_err("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e))
+#define pgd_ERROR(e) \
+	pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
+
+/* Encode and de-code a swap entry */
+#define MAX_SWAPFILES_CHECK() do { \
+	BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS); \
+	/*							\
+	 * Don't have overlapping bits with _PAGE_HPTEFLAGS	\
+	 * We filter HPTEFLAGS on set_pte.			\
+	 */							\
+	BUILD_BUG_ON(_PAGE_HPTEFLAGS & (0x1f << _PAGE_BIT_SWAP_TYPE)); \
+	BUILD_BUG_ON(_PAGE_HPTEFLAGS & _PAGE_SWP_SOFT_DIRTY);	\
+	} while (0)
+/*
+ * on pte we don't need handle RADIX_TREE_EXCEPTIONAL_SHIFT;
+ */
+#define SWP_TYPE_BITS 5
+#define __swp_type(x)		(((x).val >> _PAGE_BIT_SWAP_TYPE) \
+				& ((1UL << SWP_TYPE_BITS) - 1))
+#define __swp_offset(x)		((x).val >> PTE_RPN_SHIFT)
+#define __swp_entry(type, offset)	((swp_entry_t) { \
+					((type) << _PAGE_BIT_SWAP_TYPE) \
+					| ((offset) << PTE_RPN_SHIFT) })
+/*
+ * swp_entry_t must be independent of pte bits. We build a swp_entry_t from
+ * swap type and offset we get from swap and convert that to pte to find a
+ * matching pte in linux page table.
+ * Clear bits not found in swap entries here.
+ */
+#define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val((pte)) & ~_PAGE_PTE })
+#define __swp_entry_to_pte(x)	__pte((x).val | _PAGE_PTE)
+
+#ifdef CONFIG_MEM_SOFT_DIRTY
+#define _PAGE_SWP_SOFT_DIRTY   (1UL << (SWP_TYPE_BITS + _PAGE_BIT_SWAP_TYPE))
+#else
+#define _PAGE_SWP_SOFT_DIRTY	0UL
+#endif /* CONFIG_MEM_SOFT_DIRTY */
+
+#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
+static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_SWP_SOFT_DIRTY);
+}
+static inline bool pte_swp_soft_dirty(pte_t pte)
+{
+	return !!(pte_val(pte) & _PAGE_SWP_SOFT_DIRTY);
+}
+static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~_PAGE_SWP_SOFT_DIRTY);
+}
+#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */
+
+void pgtable_cache_add(unsigned shift, void (*ctor)(void *));
+void pgtable_cache_init(void);
+
+struct page *realmode_pfn_to_page(unsigned long pfn);
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+extern pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot);
+extern pmd_t mk_pmd(struct page *page, pgprot_t pgprot);
+extern pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot);
+extern void set_pmd_at(struct mm_struct *mm, unsigned long addr,
+		       pmd_t *pmdp, pmd_t pmd);
+extern void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
+				 pmd_t *pmd);
+extern int has_transparent_hugepage(void);
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+
+static inline pte_t pmd_pte(pmd_t pmd)
+{
+	return __pte(pmd_val(pmd));
+}
+
+static inline pmd_t pte_pmd(pte_t pte)
+{
+	return __pmd(pte_val(pte));
+}
+
+static inline pte_t *pmdp_ptep(pmd_t *pmd)
+{
+	return (pte_t *)pmd;
+}
+
+#define pmd_pfn(pmd)		pte_pfn(pmd_pte(pmd))
+#define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
+#define pmd_young(pmd)		pte_young(pmd_pte(pmd))
+#define pmd_mkold(pmd)		pte_pmd(pte_mkold(pmd_pte(pmd)))
+#define pmd_wrprotect(pmd)	pte_pmd(pte_wrprotect(pmd_pte(pmd)))
+#define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))
+#define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
+#define pmd_mkwrite(pmd)	pte_pmd(pte_mkwrite(pmd_pte(pmd)))
+
+#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
+#define pmd_soft_dirty(pmd)    pte_soft_dirty(pmd_pte(pmd))
+#define pmd_mksoft_dirty(pmd)  pte_pmd(pte_mksoft_dirty(pmd_pte(pmd)))
+#define pmd_clear_soft_dirty(pmd) pte_pmd(pte_clear_soft_dirty(pmd_pte(pmd)))
+#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */
+
+#ifdef CONFIG_NUMA_BALANCING
+static inline int pmd_protnone(pmd_t pmd)
+{
+	return pte_protnone(pmd_pte(pmd));
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
+#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write(pmd)		pte_write(pmd_pte(pmd))
+
+static inline pmd_t pmd_mkhuge(pmd_t pmd)
+{
+	return __pmd(pmd_val(pmd) | (_PAGE_PTE | _PAGE_THP_HUGE));
+}
+
+#define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
+extern int pmdp_set_access_flags(struct vm_area_struct *vma,
+				 unsigned long address, pmd_t *pmdp,
+				 pmd_t entry, int dirty);
+
+#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
+extern int pmdp_test_and_clear_young(struct vm_area_struct *vma,
+				     unsigned long address, pmd_t *pmdp);
+#define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH
+extern int pmdp_clear_flush_young(struct vm_area_struct *vma,
+				  unsigned long address, pmd_t *pmdp);
+
+#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
+extern pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
+				     unsigned long addr, pmd_t *pmdp);
+
+#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH
+extern void pmdp_splitting_flush(struct vm_area_struct *vma,
+				 unsigned long address, pmd_t *pmdp);
+
+extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
+				 unsigned long address, pmd_t *pmdp);
+#define pmdp_collapse_flush pmdp_collapse_flush
+
+#define __HAVE_ARCH_PGTABLE_DEPOSIT
+extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+				       pgtable_t pgtable);
+#define __HAVE_ARCH_PGTABLE_WITHDRAW
+extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
+
+#define __HAVE_ARCH_PMDP_INVALIDATE
+extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
+			    pmd_t *pmdp);
+
+#define pmd_move_must_withdraw pmd_move_must_withdraw
+struct spinlock;
+static inline int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl,
+					 struct spinlock *old_pmd_ptl)
+{
+	/*
+	 * Archs like ppc64 use pgtable to store per pmd
+	 * specific information. So when we switch the pmd,
+	 * we should also withdraw and deposit the pgtable
+	 */
+	return true;
+}
+#endif /* __ASSEMBLY__ */
+#endif /* _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ */
diff --git a/arch/powerpc/include/asm/book3s/pgtable.h b/arch/powerpc/include/asm/book3s/pgtable.h
new file mode 100644
index 000000000000..8b0f4a29259a
--- /dev/null
+++ b/arch/powerpc/include/asm/book3s/pgtable.h
@@ -0,0 +1,29 @@
+#ifndef _ASM_POWERPC_BOOK3S_PGTABLE_H
+#define _ASM_POWERPC_BOOK3S_PGTABLE_H
+
+#ifdef CONFIG_PPC64
+#include <asm/book3s/64/pgtable.h>
+#else
+#include <asm/book3s/32/pgtable.h>
+#endif
+
+#define FIRST_USER_ADDRESS	0UL
+#ifndef __ASSEMBLY__
+/* Insert a PTE, top-level function is out of line. It uses an inline
+ * low level function in the respective pgtable-* files
+ */
+extern void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+		       pte_t pte);
+
+
+#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address,
+				 pte_t *ptep, pte_t entry, int dirty);
+
+struct file;
+extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+				     unsigned long size, pgprot_t vma_prot);
+#define __HAVE_PHYS_MEM_ACCESS_PROT
+
+#endif /* __ASSEMBLY__ */
+#endif