Merge branch 'for-next/hugepages' of...

Merge branch 'for-next/hugepages' of git://git.linaro.org/people/stevecapper/linux into upstream-hugepages

* 'for-next/hugepages' of git://git.linaro.org/people/stevecapper/linux:
  ARM64: mm: THP support.
  ARM64: mm: Raise MAX_ORDER for 64KB pages and THP.
  ARM64: mm: HugeTLB support.
  ARM64: mm: Move PTE_PROT_NONE bit.
  ARM64: mm: Make PAGE_NONE pages read only and no-execute.
  ARM64: mm: Restore memblock limit when map_mem finished.
  mm: thp: Correct the HPAGE_PMD_ORDER check.
  x86: mm: Remove general hugetlb code from x86.
  mm: hugetlb: Copy general hugetlb code from x86 to mm.
  x86: mm: Remove x86 version of huge_pmd_share.
  mm: hugetlb: Copy huge_pmd_share from x86 to mm.

Conflicts:
	arch/arm64/Kconfig
	arch/arm64/include/asm/pgtable-hwdef.h
	arch/arm64/include/asm/pgtable.h

arch/arm64/Kconfig

@@ -188,6 +188,18 @@ config HW_PERF_EVENTS
 	  Enable hardware performance counter support for perf events. If
 	  disabled, perf events will use software events only.
 
+config SYS_SUPPORTS_HUGETLBFS
+	def_bool y
+
+config ARCH_WANT_GENERAL_HUGETLB
+	def_bool y
+
+config ARCH_WANT_HUGE_PMD_SHARE
+	def_bool y if !ARM64_64K_PAGES
+
+config HAVE_ARCH_TRANSPARENT_HUGEPAGE
+	def_bool y
+
 source "mm/Kconfig"
 
 config XEN_DOM0
@@ -200,6 +212,11 @@ config XEN
 	help
 	  Say Y if you want to run Linux in a Virtual Machine on Xen on ARM64.
 
+config FORCE_MAX_ZONEORDER
+	int
+	default "14" if (ARM64_64K_PAGES && TRANSPARENT_HUGEPAGE)
+	default "11"
+
 endmenu
 
 menu "Boot options"

arch/arm64/include/asm/hugetlb.h

+/*
+ * arch/arm64/include/asm/hugetlb.h
+ *
+ * Copyright (C) 2013 Linaro Ltd.
+ *
+ * Based on arch/x86/include/asm/hugetlb.h
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#ifndef __ASM_HUGETLB_H
+#define __ASM_HUGETLB_H
+
+#include <asm-generic/hugetlb.h>
+#include <asm/page.h>
+
+static inline pte_t huge_ptep_get(pte_t *ptep)
+{
+	return *ptep;
+}
+
+static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+				   pte_t *ptep, pte_t pte)
+{
+	set_pte_at(mm, addr, ptep, pte);
+}
+
+static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep)
+{
+	ptep_clear_flush(vma, addr, ptep);
+}
+
+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 pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+					    unsigned long addr, pte_t *ptep)
+{
+	return ptep_get_and_clear(mm, addr, ptep);
+}
+
+static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+					     unsigned long addr, pte_t *ptep,
+					     pte_t pte, int dirty)
+{
+	return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
+}
+
+static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
+					  unsigned long addr, unsigned long end,
+					  unsigned long floor,
+					  unsigned long ceiling)
+{
+	free_pgd_range(tlb, addr, end, floor, ceiling);
+}
+
+static inline int is_hugepage_only_range(struct mm_struct *mm,
+					 unsigned long addr, unsigned long len)
+{
+	return 0;
+}
+
+static inline int prepare_hugepage_range(struct file *file,
+					 unsigned long addr, unsigned long len)
+{
+	struct hstate *h = hstate_file(file);
+	if (len & ~huge_page_mask(h))
+		return -EINVAL;
+	if (addr & ~huge_page_mask(h))
+		return -EINVAL;
+	return 0;
+}
+
+static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm)
+{
+}
+
+static inline int huge_pte_none(pte_t pte)
+{
+	return pte_none(pte);
+}
+
+static inline pte_t huge_pte_wrprotect(pte_t pte)
+{
+	return pte_wrprotect(pte);
+}
+
+static inline int arch_prepare_hugepage(struct page *page)
+{
+	return 0;
+}
+
+static inline void arch_release_hugepage(struct page *page)
+{
+}
+
+static inline void arch_clear_hugepage_flags(struct page *page)
+{
+	clear_bit(PG_dcache_clean, &page->flags);
+}
+
+#endif /* __ASM_HUGETLB_H */

arch/arm64/include/asm/pgtable-hwdef.h

@@ -25,17 +25,27 @@
 /*
  * Hardware page table definitions.
  *
+ * Level 1 descriptor (PUD).
+ */
+
+#define PUD_TABLE_BIT		(_AT(pgdval_t, 1) << 1)
+
+/*
  * Level 2 descriptor (PMD).
  */
 #define PMD_TYPE_MASK		(_AT(pmdval_t, 3) << 0)
 #define PMD_TYPE_FAULT		(_AT(pmdval_t, 0) << 0)
 #define PMD_TYPE_TABLE		(_AT(pmdval_t, 3) << 0)
 #define PMD_TYPE_SECT		(_AT(pmdval_t, 1) << 0)
+#define PMD_TABLE_BIT		(_AT(pmdval_t, 1) << 1)
 
 /*
  * Section
  */
-#define PMD_SECT_USER		(_AT(pteval_t, 1) << 6)		/* AP[1] */
+#define PMD_SECT_VALID		(_AT(pmdval_t, 1) << 0)
+#define PMD_SECT_PROT_NONE	(_AT(pmdval_t, 1) << 2)
+#define PMD_SECT_USER		(_AT(pmdval_t, 1) << 6)		/* AP[1] */
+#define PMD_SECT_RDONLY		(_AT(pmdval_t, 1) << 7)		/* AP[2] */
 #define PMD_SECT_S		(_AT(pmdval_t, 3) << 8)
 #define PMD_SECT_AF		(_AT(pmdval_t, 1) << 10)
 #define PMD_SECT_NG		(_AT(pmdval_t, 1) << 11)
@@ -54,6 +64,7 @@
 #define PTE_TYPE_MASK		(_AT(pteval_t, 3) << 0)
 #define PTE_TYPE_FAULT		(_AT(pteval_t, 0) << 0)
 #define PTE_TYPE_PAGE		(_AT(pteval_t, 3) << 0)
+#define PTE_TABLE_BIT		(_AT(pteval_t, 1) << 1)
 #define PTE_USER		(_AT(pteval_t, 1) << 6)		/* AP[1] */
 #define PTE_RDONLY		(_AT(pteval_t, 1) << 7)		/* AP[2] */
 #define PTE_SHARED		(_AT(pteval_t, 3) << 8)		/* SH[1:0], inner shareable */

arch/arm64/include/asm/pgtable.h

@@ -25,8 +25,8 @@
  * Software defined PTE bits definition.
  */
 #define PTE_VALID		(_AT(pteval_t, 1) << 0)
-#define PTE_PROT_NONE		(_AT(pteval_t, 1) << 1)	/* only when !PTE_VALID */
-#define PTE_FILE		(_AT(pteval_t, 1) << 2)	/* only when !pte_present() */
+#define PTE_PROT_NONE		(_AT(pteval_t, 1) << 2)	/* only when !PTE_VALID */
+#define PTE_FILE		(_AT(pteval_t, 1) << 3)	/* only when !pte_present() */
 #define PTE_DIRTY		(_AT(pteval_t, 1) << 55)
 #define PTE_SPECIAL		(_AT(pteval_t, 1) << 56)
 
@@ -66,7 +66,7 @@ extern pgprot_t pgprot_default;
 
 #define _MOD_PROT(p, b)		__pgprot_modify(p, 0, b)
 
-#define PAGE_NONE		__pgprot_modify(pgprot_default, PTE_TYPE_MASK, PTE_PROT_NONE)
+#define PAGE_NONE		__pgprot_modify(pgprot_default, PTE_TYPE_MASK, PTE_PROT_NONE | PTE_RDONLY | PTE_PXN | PTE_UXN)
 #define PAGE_SHARED		_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
 #define PAGE_SHARED_EXEC	_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN)
 #define PAGE_COPY		_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_RDONLY)
@@ -82,7 +82,7 @@ extern pgprot_t pgprot_default;
 #define PAGE_S2			__pgprot_modify(pgprot_default, PTE_S2_MEMATTR_MASK, PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY)
 #define PAGE_S2_DEVICE		__pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDWR | PTE_UXN)
 
-#define __PAGE_NONE		__pgprot(((_PAGE_DEFAULT) & ~PTE_TYPE_MASK) | PTE_PROT_NONE)
+#define __PAGE_NONE		__pgprot(((_PAGE_DEFAULT) & ~PTE_TYPE_MASK) | PTE_PROT_NONE | PTE_RDONLY | PTE_PXN | PTE_UXN)
 #define __PAGE_SHARED		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
 #define __PAGE_SHARED_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN)
 #define __PAGE_COPY		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_RDONLY)
@@ -179,11 +179,75 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 /*
  * Huge pte definitions.
  */
-#define pte_huge(pte)		((pte_val(pte) & PTE_TYPE_MASK) == PTE_TYPE_HUGEPAGE)
-#define pte_mkhuge(pte)		(__pte((pte_val(pte) & ~PTE_TYPE_MASK) | PTE_TYPE_HUGEPAGE))
+#define pte_huge(pte)		(!(pte_val(pte) & PTE_TABLE_BIT))
+#define pte_mkhuge(pte)		(__pte(pte_val(pte) & ~PTE_TABLE_BIT))
+
+/*
+ * Hugetlb definitions.
+ */
+#define HUGE_MAX_HSTATE		2
+#define HPAGE_SHIFT		PMD_SHIFT
+#define HPAGE_SIZE		(_AC(1, UL) << HPAGE_SHIFT)
+#define HPAGE_MASK		(~(HPAGE_SIZE - 1))
+#define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
 
 #define __HAVE_ARCH_PTE_SPECIAL
 
+/*
+ * Software PMD bits for THP
+ */
+
+#define PMD_SECT_DIRTY		(_AT(pmdval_t, 1) << 55)
+#define PMD_SECT_SPLITTING	(_AT(pmdval_t, 1) << 57)
+
+/*
+ * THP definitions.
+ */
+#define pmd_young(pmd)		(pmd_val(pmd) & PMD_SECT_AF)
+
+#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write(pmd)		(!(pmd_val(pmd) & PMD_SECT_RDONLY))
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define pmd_trans_huge(pmd)	(pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT))
+#define pmd_trans_splitting(pmd) (pmd_val(pmd) & PMD_SECT_SPLITTING)
+#endif
+
+#define PMD_BIT_FUNC(fn,op) \
+static inline pmd_t pmd_##fn(pmd_t pmd) { pmd_val(pmd) op; return pmd; }
+
+PMD_BIT_FUNC(wrprotect,	|= PMD_SECT_RDONLY);
+PMD_BIT_FUNC(mkold,	&= ~PMD_SECT_AF);
+PMD_BIT_FUNC(mksplitting, |= PMD_SECT_SPLITTING);
+PMD_BIT_FUNC(mkwrite,   &= ~PMD_SECT_RDONLY);
+PMD_BIT_FUNC(mkdirty,   |= PMD_SECT_DIRTY);
+PMD_BIT_FUNC(mkyoung,   |= PMD_SECT_AF);
+PMD_BIT_FUNC(mknotpresent, &= ~PMD_TYPE_MASK);
+
+#define pmd_mkhuge(pmd)		(__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))
+
+#define pmd_pfn(pmd)		(((pmd_val(pmd) & PMD_MASK) & PHYS_MASK) >> PAGE_SHIFT)
+#define pfn_pmd(pfn,prot)	(__pmd(((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)))
+#define mk_pmd(page,prot)	pfn_pmd(page_to_pfn(page),prot)
+
+#define pmd_page(pmd)           pfn_to_page(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK))
+
+static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
+{
+	const pmdval_t mask = PMD_SECT_USER | PMD_SECT_PXN | PMD_SECT_UXN |
+			      PMD_SECT_RDONLY | PMD_SECT_PROT_NONE |
+			      PMD_SECT_VALID;
+	pmd_val(pmd) = (pmd_val(pmd) & ~mask) | (pgprot_val(newprot) & mask);
+	return pmd;
+}
+
+#define set_pmd_at(mm, addr, pmdp, pmd)	set_pmd(pmdp, pmd)
+
+static inline int has_transparent_hugepage(void)
+{
+	return 1;
+}
+
 /*
  * Mark the prot value as uncacheable and unbufferable.
  */
@@ -293,12 +357,12 @@ extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
 
 /*
  * Encode and decode a swap entry:
- *	bits 0-1:	present (must be zero)
- *	bit  2:		PTE_FILE
- *	bits 3-8:	swap type
+ *	bits 0, 2:	present (must both be zero)
+ *	bit  3:		PTE_FILE
+ *	bits 4-8:	swap type
  *	bits 9-63:	swap offset
  */
-#define __SWP_TYPE_SHIFT	3
+#define __SWP_TYPE_SHIFT	4
 #define __SWP_TYPE_BITS		6
 #define __SWP_TYPE_MASK		((1 << __SWP_TYPE_BITS) - 1)
 #define __SWP_OFFSET_SHIFT	(__SWP_TYPE_BITS + __SWP_TYPE_SHIFT)
@@ -318,15 +382,15 @@ extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
 
 /*
  * Encode and decode a file entry:
- *	bits 0-1:	present (must be zero)
- *	bit  2:		PTE_FILE
- *	bits 3-63:	file offset / PAGE_SIZE
+ *	bits 0, 2:	present (must both be zero)
+ *	bit  3:		PTE_FILE
+ *	bits 4-63:	file offset / PAGE_SIZE
  */
 #define pte_file(pte)		(pte_val(pte) & PTE_FILE)
-#define pte_to_pgoff(x)		(pte_val(x) >> 3)
-#define pgoff_to_pte(x)		__pte(((x) << 3) | PTE_FILE)
+#define pte_to_pgoff(x)		(pte_val(x) >> 4)
+#define pgoff_to_pte(x)		__pte(((x) << 4) | PTE_FILE)
 
-#define PTE_FILE_MAX_BITS	61
+#define PTE_FILE_MAX_BITS	60
 
 extern int kern_addr_valid(unsigned long addr);
 

arch/arm64/include/asm/tlb.h

@@ -187,4 +187,10 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 
 #define tlb_migrate_finish(mm)		do { } while (0)
 
+static inline void
+tlb_remove_pmd_tlb_entry(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr)
+{
+	tlb_add_flush(tlb, addr);
+}
+
 #endif

arch/arm64/include/asm/tlbflush.h

@@ -117,6 +117,8 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
 	dsb();
 }
 
+#define update_mmu_cache_pmd(vma, address, pmd) do { } while (0)
+
 #endif
 
 #endif

arch/arm64/mm/Makefile

@@ -2,3 +2,4 @@ obj-y				:= dma-mapping.o extable.o fault.o init.o \
 				   cache.o copypage.o flush.o \
 				   ioremap.o mmap.o pgd.o mmu.o \
 				   context.o tlb.o proc.o
+obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o

arch/arm64/mm/fault.c

@@ -364,17 +364,6 @@ static int __kprobes do_translation_fault(unsigned long addr,
 	return 0;
 }
 
-/*
- * Some section permission faults need to be handled gracefully.  They can
- * happen due to a __{get,put}_user during an oops.
- */
-static int do_sect_fault(unsigned long addr, unsigned int esr,
-			 struct pt_regs *regs)
-{
-	do_bad_area(addr, esr, regs);
-	return 0;
-}
-
 /*
  * This abort handler always returns "fault".
  */
@@ -398,12 +387,12 @@ static struct fault_info {
 	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 2 translation fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_MAPERR,	"level 3 translation fault"	},
 	{ do_bad,		SIGBUS,  0,		"reserved access flag fault"	},
-	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"level 1 access flag fault"	},
-	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"level 2 access flag fault"	},
+	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 1 access flag fault"	},
+	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 access flag fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 access flag fault"	},
 	{ do_bad,		SIGBUS,  0,		"reserved permission fault"	},
-	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"level 1 permission fault"	},
-	{ do_sect_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 permission fault"	},
+	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 1 permission fault"	},
+	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 permission fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 permission fault"	},
 	{ do_bad,		SIGBUS,  0,		"synchronous external abort"	},
 	{ do_bad,		SIGBUS,  0,		"asynchronous external abort"	},

arch/arm64/mm/hugetlbpage.c

+/*
+ * arch/arm64/mm/hugetlbpage.c
+ *
+ * Copyright (C) 2013 Linaro Ltd.
+ *
+ * Based on arch/x86/mm/hugetlbpage.c.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+#include <linux/pagemap.h>
+#include <linux/err.h>
+#include <linux/sysctl.h>
+#include <asm/mman.h>
+#include <asm/tlb.h>
+#include <asm/tlbflush.h>
+#include <asm/pgalloc.h>
+
+#ifndef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
+int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
+{
+	return 0;
+}
+#endif
+
+struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
+			      int write)
+{
+	return ERR_PTR(-EINVAL);
+}
+
+int pmd_huge(pmd_t pmd)
+{
+	return !(pmd_val(pmd) & PMD_TABLE_BIT);
+}
+
+int pud_huge(pud_t pud)
+{
+	return !(pud_val(pud) & PUD_TABLE_BIT);
+}
+
+static __init int setup_hugepagesz(char *opt)
+{
+	unsigned long ps = memparse(opt, &opt);
+	if (ps == PMD_SIZE) {
+		hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
+	} else if (ps == PUD_SIZE) {
+		hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
+	} else {
+		pr_err("hugepagesz: Unsupported page size %lu M\n", ps >> 20);
+		return 0;
+	}
+	return 1;
+}
+__setup("hugepagesz=", setup_hugepagesz);

arch/arm64/mm/mmu.c

@@ -297,6 +297,16 @@ static void __init map_mem(void)
 {
 	struct memblock_region *reg;
 
+	/*
+	 * Temporarily limit the memblock range. We need to do this as
+	 * create_mapping requires puds, pmds and ptes to be allocated from
+	 * memory addressable from the initial direct kernel mapping.
+	 *
+	 * The initial direct kernel mapping, located at swapper_pg_dir,
+	 * gives us PGDIR_SIZE memory starting from PHYS_OFFSET (aligned).
+	 */
+	memblock_set_current_limit((PHYS_OFFSET & PGDIR_MASK) + PGDIR_SIZE);
+
 	/* map all the memory banks */
 	for_each_memblock(memory, reg) {
 		phys_addr_t start = reg->base;
@@ -307,6 +317,9 @@ static void __init map_mem(void)
 
 		create_mapping(start, __phys_to_virt(start), end - start);
 	}
+
+	/* Limit no longer required. */
+	memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE);
 }
 
 /*
@@ -317,12 +330,6 @@ void __init paging_init(void)
 {
 	void *zero_page;
 
-	/*
-	 * Maximum PGDIR_SIZE addressable via the initial direct kernel
-	 * mapping in swapper_pg_dir.
-	 */
-	memblock_set_current_limit((PHYS_OFFSET & PGDIR_MASK) + PGDIR_SIZE);
-
 	init_mem_pgprot();
 	map_mem();
 

arch/x86/Kconfig

@@ -207,6 +207,12 @@ config ARCH_HIBERNATION_POSSIBLE
 config ARCH_SUSPEND_POSSIBLE
 	def_bool y
 
+config ARCH_WANT_HUGE_PMD_SHARE
+	def_bool y
+
+config ARCH_WANT_GENERAL_HUGETLB
+	def_bool y
+
 config ZONE_DMA32
 	bool
 	default X86_64

arch/x86/mm/hugetlbpage.c

@@ -16,169 +16,6 @@
 #include <asm/tlbflush.h>
 #include <asm/pgalloc.h>
 
-static unsigned long page_table_shareable(struct vm_area_struct *svma,
-				struct vm_area_struct *vma,
-				unsigned long addr, pgoff_t idx)
-{
-	unsigned long saddr = ((idx - svma->vm_pgoff) << PAGE_SHIFT) +
-				svma->vm_start;
-	unsigned long sbase = saddr & PUD_MASK;
-	unsigned long s_end = sbase + PUD_SIZE;
-
-	/* Allow segments to share if only one is marked locked */
-	unsigned long vm_flags = vma->vm_flags & ~VM_LOCKED;
-	unsigned long svm_flags = svma->vm_flags & ~VM_LOCKED;
-
-	/*
-	 * match the virtual addresses, permission and the alignment of the
-	 * page table page.
-	 */
-	if (pmd_index(addr) != pmd_index(saddr) ||
-	    vm_flags != svm_flags ||
-	    sbase < svma->vm_start || svma->vm_end < s_end)
-		return 0;
-
-	return saddr;
-}
-
-static int vma_shareable(struct vm_area_struct *vma, unsigned long addr)
-{
-	unsigned long base = addr & PUD_MASK;
-	unsigned long end = base + PUD_SIZE;
-
-	/*
-	 * check on proper vm_flags and page table alignment
-	 */
-	if (vma->vm_flags & VM_MAYSHARE &&
-	    vma->vm_start <= base && end <= vma->vm_end)
-		return 1;
-	return 0;
-}
-
-/*
- * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc()
- * and returns the corresponding pte. While this is not necessary for the
- * !shared pmd case because we can allocate the pmd later as well, it makes the
- * code much cleaner. pmd allocation is essential for the shared case because
- * pud has to be populated inside the same i_mmap_mutex section - otherwise
- * racing tasks could either miss the sharing (see huge_pte_offset) or select a
- * bad pmd for sharing.
- */
-static pte_t *
-huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
-{
-	struct vm_area_struct *vma = find_vma(mm, addr);
-	struct address_space *mapping = vma->vm_file->f_mapping;
-	pgoff_t idx = ((addr - vma->vm_start) >> PAGE_SHIFT) +
-			vma->vm_pgoff;
-	struct vm_area_struct *svma;
-	unsigned long saddr;
-	pte_t *spte = NULL;
-	pte_t *pte;
-
-	if (!vma_shareable(vma, addr))
-		return (pte_t *)pmd_alloc(mm, pud, addr);
-
-	mutex_lock(&mapping->i_mmap_mutex);
-	vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) {
-		if (svma == vma)
-			continue;
-
-		saddr = page_table_shareable(svma, vma, addr, idx);
-		if (saddr) {
-			spte = huge_pte_offset(svma->vm_mm, saddr);
-			if (spte) {
-				get_page(virt_to_page(spte));
-				break;
-			}
-		}
-	}
-
-	if (!spte)
-		goto out;
-
-	spin_lock(&mm->page_table_lock);
-	if (pud_none(*pud))
-		pud_populate(mm, pud, (pmd_t *)((unsigned long)spte & PAGE_MASK));
-	else
-		put_page(virt_to_page(spte));
-	spin_unlock(&mm->page_table_lock);
-out:
-	pte = (pte_t *)pmd_alloc(mm, pud, addr);
-	mutex_unlock(&mapping->i_mmap_mutex);
-	return pte;
-}
-
-/*
- * unmap huge page backed by shared pte.
- *
- * Hugetlb pte page is ref counted at the time of mapping.  If pte is shared
- * indicated by page_count > 1, unmap is achieved by clearing pud and
- * decrementing the ref count. If count == 1, the pte page is not shared.
- *
- * called with vma->vm_mm->page_table_lock held.
- *
- * returns: 1 successfully unmapped a shared pte page
- *	    0 the underlying pte page is not shared, or it is the last user
- */
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
-{
-	pgd_t *pgd = pgd_offset(mm, *addr);
-	pud_t *pud = pud_offset(pgd, *addr);
-
-	BUG_ON(page_count(virt_to_page(ptep)) == 0);
-	if (page_count(virt_to_page(ptep)) == 1)
-		return 0;
-
-	pud_clear(pud);
-	put_page(virt_to_page(ptep));
-	*addr = ALIGN(*addr, HPAGE_SIZE * PTRS_PER_PTE) - HPAGE_SIZE;
-	return 1;
-}
-
-pte_t *huge_pte_alloc(struct mm_struct *mm,
-			unsigned long addr, unsigned long sz)
-{
-	pgd_t *pgd;
-	pud_t *pud;
-	pte_t *pte = NULL;
-
-	pgd = pgd_offset(mm, addr);
-	pud = pud_alloc(mm, pgd, addr);
-	if (pud) {
-		if (sz == PUD_SIZE) {
-			pte = (pte_t *)pud;
-		} else {
-			BUG_ON(sz != PMD_SIZE);
-			if (pud_none(*pud))
-				pte = huge_pmd_share(mm, addr, pud);
-			else
-				pte = (pte_t *)pmd_alloc(mm, pud, addr);
-		}
-	}
-	BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte));
-
-	return pte;
-}
-
-pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
-{
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd = NULL;
-
-	pgd = pgd_offset(mm, addr);
-	if (pgd_present(*pgd)) {
-		pud = pud_offset(pgd, addr);
-		if (pud_present(*pud)) {
-			if (pud_large(*pud))
-				return (pte_t *)pud;
-			pmd = pmd_offset(pud, addr);
-		}
-	}
-	return (pte_t *) pmd;
-}
-
 #if 0	/* This is just for testing */
 struct page *
 follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
@@ -240,30 +77,6 @@ int pud_huge(pud_t pud)
 	return !!(pud_val(pud) & _PAGE_PSE);
 }
 
-struct page *
-follow_huge_pmd(struct mm_struct *mm, unsigned long address,
-		pmd_t *pmd, int write)
-{
-	struct page *page;
-
-	page = pte_page(*(pte_t *)pmd);
-	if (page)
-		page += ((address & ~PMD_MASK) >> PAGE_SHIFT);
-	return page;
-}
-
-struct page *
-follow_huge_pud(struct mm_struct *mm, unsigned long address,
-		pud_t *pud, int write)
-{
-	struct page *page;
-
-	page = pte_page(*(pte_t *)pud);
-	if (page)
-		page += ((address & ~PUD_MASK) >> PAGE_SHIFT);
-	return page;
-}
-
 #endif
 
 /* x86_64 also uses this file */

include/linux/huge_mm.h

@@ -123,7 +123,7 @@ extern void __split_huge_page_pmd(struct vm_area_struct *vma,
 	} while (0)
 extern void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address,
 		pmd_t *pmd);
-#if HPAGE_PMD_ORDER > MAX_ORDER
+#if HPAGE_PMD_ORDER >= MAX_ORDER
 #error "hugepages can't be allocated by the buddy allocator"
 #endif
 extern int hugepage_madvise(struct vm_area_struct *vma,

include/linux/hugetlb.h

@@ -69,6 +69,10 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed);
 int dequeue_hwpoisoned_huge_page(struct page *page);
 void copy_huge_page(struct page *dst, struct page *src);
 
+#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
+pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud);
+#endif
+
 extern unsigned long hugepages_treat_as_movable;
 extern const unsigned long hugetlb_zero, hugetlb_infinity;
 extern int sysctl_hugetlb_shm_group;

mm/hugetlb.c

@@ -2931,15 +2931,6 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	return ret;
 }
 
-/* Can be overriden by architectures */
-__attribute__((weak)) struct page *
-follow_huge_pud(struct mm_struct *mm, unsigned long address,
-	       pud_t *pud, int write)
-{
-	BUG();
-	return NULL;
-}
-
 long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			 struct page **pages, struct vm_area_struct **vmas,
 			 unsigned long *position, unsigned long *nr_pages,
@@ -3169,6 +3160,216 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
 	hugetlb_acct_memory(h, -(chg - freed));
 }
 
+#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
+static unsigned long page_table_shareable(struct vm_area_struct *svma,
+				struct vm_area_struct *vma,
+				unsigned long addr, pgoff_t idx)
+{
+	unsigned long saddr = ((idx - svma->vm_pgoff) << PAGE_SHIFT) +
+				svma->vm_start;
+	unsigned long sbase = saddr & PUD_MASK;
+	unsigned long s_end = sbase + PUD_SIZE;
+
+	/* Allow segments to share if only one is marked locked */
+	unsigned long vm_flags = vma->vm_flags & ~VM_LOCKED;
+	unsigned long svm_flags = svma->vm_flags & ~VM_LOCKED;
+
+	/*
+	 * match the virtual addresses, permission and the alignment of the
+	 * page table page.
+	 */
+	if (pmd_index(addr) != pmd_index(saddr) ||
+	    vm_flags != svm_flags ||
+	    sbase < svma->vm_start || svma->vm_end < s_end)
+		return 0;
+
+	return saddr;
+}
+
+static int vma_shareable(struct vm_area_struct *vma, unsigned long addr)
+{
+	unsigned long base = addr & PUD_MASK;
+	unsigned long end = base + PUD_SIZE;
+
+	/*
+	 * check on proper vm_flags and page table alignment
+	 */
+	if (vma->vm_flags & VM_MAYSHARE &&
+	    vma->vm_start <= base && end <= vma->vm_end)
+		return 1;
+	return 0;
+}
+
+/*
+ * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc()
+ * and returns the corresponding pte. While this is not necessary for the
+ * !shared pmd case because we can allocate the pmd later as well, it makes the
+ * code much cleaner. pmd allocation is essential for the shared case because
+ * pud has to be populated inside the same i_mmap_mutex section - otherwise
+ * racing tasks could either miss the sharing (see huge_pte_offset) or select a
+ * bad pmd for sharing.
+ */
+pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
+{
+	struct vm_area_struct *vma = find_vma(mm, addr);
+	struct address_space *mapping = vma->vm_file->f_mapping;
+	pgoff_t idx = ((addr - vma->vm_start) >> PAGE_SHIFT) +
+			vma->vm_pgoff;
+	struct vm_area_struct *svma;
+	unsigned long saddr;
+	pte_t *spte = NULL;
+	pte_t *pte;
+
+	if (!vma_shareable(vma, addr))
+		return (pte_t *)pmd_alloc(mm, pud, addr);
+
+	mutex_lock(&mapping->i_mmap_mutex);
+	vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) {
+		if (svma == vma)
+			continue;
+
+		saddr = page_table_shareable(svma, vma, addr, idx);
+		if (saddr) {
+			spte = huge_pte_offset(svma->vm_mm, saddr);
+			if (spte) {
+				get_page(virt_to_page(spte));
+				break;
+			}
+		}
+	}
+
+	if (!spte)
+		goto out;
+
+	spin_lock(&mm->page_table_lock);
+	if (pud_none(*pud))
+		pud_populate(mm, pud,
+				(pmd_t *)((unsigned long)spte & PAGE_MASK));
+	else
+		put_page(virt_to_page(spte));
+	spin_unlock(&mm->page_table_lock);
+out:
+	pte = (pte_t *)pmd_alloc(mm, pud, addr);
+	mutex_unlock(&mapping->i_mmap_mutex);
+	return pte;
+}
+
+/*
+ * unmap huge page backed by shared pte.
+ *
+ * Hugetlb pte page is ref counted at the time of mapping.  If pte is shared
+ * indicated by page_count > 1, unmap is achieved by clearing pud and
+ * decrementing the ref count. If count == 1, the pte page is not shared.
+ *
+ * called with vma->vm_mm->page_table_lock held.
+ *
+ * returns: 1 successfully unmapped a shared pte page
+ *	    0 the underlying pte page is not shared, or it is the last user
+ */
+int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
+{
+	pgd_t *pgd = pgd_offset(mm, *addr);
+	pud_t *pud = pud_offset(pgd, *addr);
+
+	BUG_ON(page_count(virt_to_page(ptep)) == 0);
+	if (page_count(virt_to_page(ptep)) == 1)
+		return 0;
+
+	pud_clear(pud);
+	put_page(virt_to_page(ptep));
+	*addr = ALIGN(*addr, HPAGE_SIZE * PTRS_PER_PTE) - HPAGE_SIZE;
+	return 1;
+}
+#define want_pmd_share()	(1)
+#else /* !CONFIG_ARCH_WANT_HUGE_PMD_SHARE */
+pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
+{
+	return NULL;
+}
+#define want_pmd_share()	(0)
+#endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */
+
+#ifdef CONFIG_ARCH_WANT_GENERAL_HUGETLB
+pte_t *huge_pte_alloc(struct mm_struct *mm,
+			unsigned long addr, unsigned long sz)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pte_t *pte = NULL;
+
+	pgd = pgd_offset(mm, addr);
+	pud = pud_alloc(mm, pgd, addr);
+	if (pud) {
+		if (sz == PUD_SIZE) {
+			pte = (pte_t *)pud;
+		} else {
+			BUG_ON(sz != PMD_SIZE);
+			if (want_pmd_share() && pud_none(*pud))
+				pte = huge_pmd_share(mm, addr, pud);
+			else
+				pte = (pte_t *)pmd_alloc(mm, pud, addr);
+		}
+	}
+	BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte));
+
+	return pte;
+}
+
+pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd = NULL;
+
+	pgd = pgd_offset(mm, addr);
+	if (pgd_present(*pgd)) {
+		pud = pud_offset(pgd, addr);
+		if (pud_present(*pud)) {
+			if (pud_huge(*pud))
+				return (pte_t *)pud;
+			pmd = pmd_offset(pud, addr);
+		}
+	}
+	return (pte_t *) pmd;
+}
+
+struct page *
+follow_huge_pmd(struct mm_struct *mm, unsigned long address,
+		pmd_t *pmd, int write)
+{
+	struct page *page;
+
+	page = pte_page(*(pte_t *)pmd);
+	if (page)
+		page += ((address & ~PMD_MASK) >> PAGE_SHIFT);
+	return page;
+}
+
+struct page *
+follow_huge_pud(struct mm_struct *mm, unsigned long address,
+		pud_t *pud, int write)
+{
+	struct page *page;
+
+	page = pte_page(*(pte_t *)pud);
+	if (page)
+		page += ((address & ~PUD_MASK) >> PAGE_SHIFT);
+	return page;
+}
+
+#else /* !CONFIG_ARCH_WANT_GENERAL_HUGETLB */
+
+/* Can be overriden by architectures */
+__attribute__((weak)) struct page *
+follow_huge_pud(struct mm_struct *mm, unsigned long address,
+	       pud_t *pud, int write)
+{
+	BUG();
+	return NULL;
+}
+
+#endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */
+
 #ifdef CONFIG_MEMORY_FAILURE
 
 /* Should be called in hugetlb_lock */