Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:

 - misc fixes

 - ocfs2 updates

 - most of MM

* emailed patches from Andrew Morton <[email protected]>: (118 commits)
  mm: remove PG_highmem description
  tools, vm: new option to specify kpageflags file
  mm/swap.c: make functions and their kernel-doc agree
  mm, memory_hotplug: fix memmap initialization
  mm: correct comments regarding do_fault_around()
  mm: numa: do not trap faults on shared data section pages.
  hugetlb, mbind: fall back to default policy if vma is NULL
  hugetlb, mempolicy: fix the mbind hugetlb migration
  mm, hugetlb: further simplify hugetlb allocation API
  mm, hugetlb: get rid of surplus page accounting tricks
  mm, hugetlb: do not rely on overcommit limit during migration
  mm, hugetlb: integrate giga hugetlb more naturally to the allocation path
  mm, hugetlb: unify core page allocation accounting and initialization
  mm/memcontrol.c: try harder to decrease [memory,memsw].limit_in_bytes
  mm/memcontrol.c: make local symbol static
  mm/hmm: fix uninitialized use of 'entry' in hmm_vma_walk_pmd()
  include/linux/mmzone.h: fix explanation of lower bits in the SPARSEMEM mem_map pointer
  mm/compaction.c: fix comment for try_to_compact_pages()
  mm/page_ext.c: make page_ext_init a noop when CONFIG_PAGE_EXTENSION but nothing uses it
  zsmalloc: use U suffix for negative literals being shifted
  ...

Documentation/sysctl/vm.txt

@@ -30,7 +30,6 @@ Currently, these files are in /proc/sys/vm:
 - dirty_writeback_centisecs
 - drop_caches
 - extfrag_threshold
-- hugepages_treat_as_movable
 - hugetlb_shm_group
 - laptop_mode
 - legacy_va_layout
@@ -261,30 +260,6 @@ any throttling.
 
 ==============================================================
 
-hugepages_treat_as_movable
-
-This parameter controls whether we can allocate hugepages from ZONE_MOVABLE
-or not. If set to non-zero, hugepages can be allocated from ZONE_MOVABLE.
-ZONE_MOVABLE is created when kernel boot parameter kernelcore= is specified,
-so this parameter has no effect if used without kernelcore=.
-
-Hugepage migration is now available in some situations which depend on the
-architecture and/or the hugepage size. If a hugepage supports migration,
-allocation from ZONE_MOVABLE is always enabled for the hugepage regardless
-of the value of this parameter.
-IOW, this parameter affects only non-migratable hugepages.
-
-Assuming that hugepages are not migratable in your system, one usecase of
-this parameter is that users can make hugepage pool more extensible by
-enabling the allocation from ZONE_MOVABLE. This is because on ZONE_MOVABLE
-page reclaim/migration/compaction work more and you can get contiguous
-memory more likely. Note that using ZONE_MOVABLE for non-migratable
-hugepages can do harm to other features like memory hotremove (because
-memory hotremove expects that memory blocks on ZONE_MOVABLE are always
-removable,) so it's a trade-off responsible for the users.
-
-==============================================================
-
 hugetlb_shm_group
 
 hugetlb_shm_group contains group id that is allowed to create SysV

Documentation/vm/hugetlbpage.txt

@@ -20,19 +20,20 @@ options.
 
 The /proc/meminfo file provides information about the total number of
 persistent hugetlb pages in the kernel's huge page pool.  It also displays
-information about the number of free, reserved and surplus huge pages and the
-default huge page size.  The huge page size is needed for generating the
-proper alignment and size of the arguments to system calls that map huge page
-regions.
+default huge page size and information about the number of free, reserved
+and surplus huge pages in the pool of huge pages of default size.
+The huge page size is needed for generating the proper alignment and
+size of the arguments to system calls that map huge page regions.
 
 The output of "cat /proc/meminfo" will include lines like:
 
 .....
-HugePages_Total: vvv
-HugePages_Free:  www
-HugePages_Rsvd:  xxx
-HugePages_Surp:  yyy
-Hugepagesize:    zzz kB
+HugePages_Total: uuu
+HugePages_Free:  vvv
+HugePages_Rsvd:  www
+HugePages_Surp:  xxx
+Hugepagesize:    yyy kB
+Hugetlb:         zzz kB
 
 where:
 HugePages_Total is the size of the pool of huge pages.
@@ -47,6 +48,14 @@ HugePages_Surp  is short for "surplus," and is the number of huge pages in
                 the pool above the value in /proc/sys/vm/nr_hugepages. The
                 maximum number of surplus huge pages is controlled by
                 /proc/sys/vm/nr_overcommit_hugepages.
+Hugepagesize    is the default hugepage size (in Kb).
+Hugetlb         is the total amount of memory (in kB), consumed by huge
+                pages of all sizes.
+                If huge pages of different sizes are in use, this number
+                will exceed HugePages_Total * Hugepagesize. To get more
+                detailed information, please, refer to
+                /sys/kernel/mm/hugepages (described below).
+
 
 /proc/filesystems should also show a filesystem of type "hugetlbfs" configured
 in the kernel.

arch/arc/include/asm/hugepage.h

@@ -74,4 +74,7 @@ extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
 extern void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
 				unsigned long end);
 
+/* We don't have hardware dirty/accessed bits, generic_pmdp_establish is fine.*/
+#define pmdp_establish generic_pmdp_establish
+
 #endif

arch/arm/include/asm/pgtable-3level.h

@@ -249,6 +249,9 @@ PMD_BIT_FUNC(mkyoung,   |= PMD_SECT_AF);
 #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)
 
+/* No hardware dirty/accessed bits -- generic_pmdp_establish() fits */
+#define pmdp_establish generic_pmdp_establish
+
 /* represent a notpresent pmd by faulting entry, this is used by pmdp_invalidate */
 static inline pmd_t pmd_mknotpresent(pmd_t pmd)
 {

arch/arm64/include/asm/pgtable.h

@@ -706,6 +706,13 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
 {
 	ptep_set_wrprotect(mm, address, (pte_t *)pmdp);
 }
+
+#define pmdp_establish pmdp_establish
+static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
+		unsigned long address, pmd_t *pmdp, pmd_t pmd)
+{
+	return __pmd(xchg_relaxed(&pmd_val(*pmdp), pmd_val(pmd)));
+}
 #endif
 
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];

arch/m32r/kernel/traps.c

@@ -115,14 +115,6 @@ static void set_eit_vector_entries(void)
 	_flush_cache_copyback_all();
 }
 
-void abort(void)
-{
-	BUG();
-
-	/* if that doesn't kill us, halt */
-	panic("Oops failed to kill thread");
-}
-
 void __init trap_init(void)
 {
 	set_eit_vector_entries();

arch/mips/include/asm/pgtable.h

@@ -534,6 +534,9 @@ static inline int io_remap_pfn_range(struct vm_area_struct *vma,
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 
+/* We don't have hardware dirty/accessed bits, generic_pmdp_establish is fine.*/
+#define pmdp_establish generic_pmdp_establish
+
 #define has_transparent_hugepage has_transparent_hugepage
 extern int has_transparent_hugepage(void);
 

arch/powerpc/Kconfig

@@ -151,7 +151,6 @@ config PPC
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select ARCH_SUPPORTS_ATOMIC_RMW
-	select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF		if PPC64
 	select ARCH_WANT_IPC_PARSE_VERSION

arch/powerpc/include/asm/book3s/64/hash-4k.h

@@ -101,8 +101,6 @@ extern pmd_t hash__pmdp_collapse_flush(struct vm_area_struct *vma,
 extern void hash__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
 					 pgtable_t pgtable);
 extern pgtable_t hash__pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
-extern void hash__pmdp_huge_split_prepare(struct vm_area_struct *vma,
-				      unsigned long address, pmd_t *pmdp);
 extern pmd_t hash__pmdp_huge_get_and_clear(struct mm_struct *mm,
 				       unsigned long addr, pmd_t *pmdp);
 extern int hash__has_transparent_hugepage(void);

arch/powerpc/include/asm/book3s/64/hash-64k.h

@@ -203,8 +203,6 @@ extern pmd_t hash__pmdp_collapse_flush(struct vm_area_struct *vma,
 extern void hash__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
 					 pgtable_t pgtable);
 extern pgtable_t hash__pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
-extern void hash__pmdp_huge_split_prepare(struct vm_area_struct *vma,
-				      unsigned long address, pmd_t *pmdp);
 extern pmd_t hash__pmdp_huge_get_and_clear(struct mm_struct *mm,
 				       unsigned long addr, pmd_t *pmdp);
 extern int hash__has_transparent_hugepage(void);

arch/powerpc/include/asm/book3s/64/pgtable.h

@@ -1137,17 +1137,8 @@ static inline pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm,
 }
 
 #define __HAVE_ARCH_PMDP_INVALIDATE
-extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
-			    pmd_t *pmdp);
-
-#define __HAVE_ARCH_PMDP_HUGE_SPLIT_PREPARE
-static inline void pmdp_huge_split_prepare(struct vm_area_struct *vma,
-					   unsigned long address, pmd_t *pmdp)
-{
-	if (radix_enabled())
-		return radix__pmdp_huge_split_prepare(vma, address, pmdp);
-	return hash__pmdp_huge_split_prepare(vma, address, pmdp);
-}
+extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
+			     pmd_t *pmdp);
 
 #define pmd_move_must_withdraw pmd_move_must_withdraw
 struct spinlock;

arch/powerpc/include/asm/book3s/64/radix.h

@@ -269,12 +269,6 @@ static inline pmd_t radix__pmd_mkhuge(pmd_t pmd)
 		return __pmd(pmd_val(pmd) | _PAGE_PTE | R_PAGE_LARGE);
 	return __pmd(pmd_val(pmd) | _PAGE_PTE);
 }
-static inline void radix__pmdp_huge_split_prepare(struct vm_area_struct *vma,
-					    unsigned long address, pmd_t *pmdp)
-{
-	/* Nothing to do for radix. */
-	return;
-}
 
 extern unsigned long radix__pmd_hugepage_update(struct mm_struct *mm, unsigned long addr,
 					  pmd_t *pmdp, unsigned long clr,

arch/powerpc/mm/pgtable-book3s64.c

@@ -90,16 +90,19 @@ void serialize_against_pte_lookup(struct mm_struct *mm)
  * We use this to invalidate a pmdp entry before switching from a
  * hugepte to regular pmd entry.
  */
-void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
+pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 		     pmd_t *pmdp)
 {
-	pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, 0);
+	unsigned long old_pmd;
+
+	old_pmd = pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, 0);
 	flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 	/*
 	 * This ensures that generic code that rely on IRQ disabling
 	 * to prevent a parallel THP split work as expected.
 	 */
 	serialize_against_pte_lookup(vma->vm_mm);
+	return __pmd(old_pmd);
 }
 
 static pmd_t pmd_set_protbits(pmd_t pmd, pgprot_t pgprot)

arch/powerpc/mm/pgtable-hash64.c

@@ -296,28 +296,6 @@ pgtable_t hash__pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
 	return pgtable;
 }
 
-void hash__pmdp_huge_split_prepare(struct vm_area_struct *vma,
-			       unsigned long address, pmd_t *pmdp)
-{
-	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
-	VM_BUG_ON(REGION_ID(address) != USER_REGION_ID);
-	VM_BUG_ON(pmd_devmap(*pmdp));
-
-	/*
-	 * We can't mark the pmd none here, because that will cause a race
-	 * against exit_mmap. We need to continue mark pmd TRANS HUGE, while
-	 * we spilt, but at the same time we wan't rest of the ppc64 code
-	 * not to insert hash pte on this, because we will be modifying
-	 * the deposited pgtable in the caller of this function. Hence
-	 * clear the _PAGE_USER so that we move the fault handling to
-	 * higher level function and that will serialize against ptl.
-	 * We need to flush existing hash pte entries here even though,
-	 * the translation is still valid, because we will withdraw
-	 * pgtable_t after this.
-	 */
-	pmd_hugepage_update(vma->vm_mm, address, pmdp, 0, _PAGE_PRIVILEGED);
-}
-
 /*
  * A linux hugepage PMD was changed and the corresponding hash table entries
  * neesd to be flushed.

arch/s390/Kconfig

@@ -108,7 +108,6 @@ config S390
 	select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
 	select ARCH_SAVE_PAGE_KEYS if HIBERNATION
 	select ARCH_SUPPORTS_ATOMIC_RMW
-	select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
 	select ARCH_SUPPORTS_NUMA_BALANCING
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF

arch/s390/include/asm/pgtable.h

@@ -1505,12 +1505,12 @@ static inline pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma,
 }
 
 #define __HAVE_ARCH_PMDP_INVALIDATE
-static inline void pmdp_invalidate(struct vm_area_struct *vma,
+static inline pmd_t pmdp_invalidate(struct vm_area_struct *vma,
 				   unsigned long addr, pmd_t *pmdp)
 {
 	pmd_t pmd = __pmd(pmd_val(*pmdp) | _SEGMENT_ENTRY_INVALID);
 
-	pmdp_xchg_direct(vma->vm_mm, addr, pmdp, pmd);
+	return pmdp_xchg_direct(vma->vm_mm, addr, pmdp, pmd);
 }
 
 #define __HAVE_ARCH_PMDP_SET_WRPROTECT

arch/sparc/include/asm/pgtable_64.h

@@ -1010,7 +1010,7 @@ void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
 			  pmd_t *pmd);
 
 #define __HAVE_ARCH_PMDP_INVALIDATE
-extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
+extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 			    pmd_t *pmdp);
 
 #define __HAVE_ARCH_PGTABLE_DEPOSIT

arch/sparc/mm/tlb.c

@@ -219,17 +219,28 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 	}
 }
 
+static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
+		unsigned long address, pmd_t *pmdp, pmd_t pmd)
+{
+	pmd_t old;
+
+	do {
+		old = *pmdp;
+	} while (cmpxchg64(&pmdp->pmd, old.pmd, pmd.pmd) != old.pmd);
+
+	return old;
+}
+
 /*
  * This routine is only called when splitting a THP
  */
-void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
+pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 		     pmd_t *pmdp)
 {
-	pmd_t entry = *pmdp;
-
-	pmd_val(entry) &= ~_PAGE_VALID;
+	pmd_t old, entry;
 
-	set_pmd_at(vma->vm_mm, address, pmdp, entry);
+	entry = __pmd(pmd_val(*pmdp) & ~_PAGE_VALID);
+	old = pmdp_establish(vma, address, pmdp, entry);
 	flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 
 	/*
@@ -240,6 +251,8 @@ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 	if ((pmd_val(entry) & _PAGE_PMD_HUGE) &&
 	    !is_huge_zero_page(pmd_page(entry)))
 		(vma->vm_mm)->context.thp_pte_count--;
+
+	return old;
 }
 
 void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,

arch/x86/Kconfig

@@ -69,7 +69,6 @@ config X86
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select ARCH_SUPPORTS_ATOMIC_RMW
-	select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
 	select ARCH_SUPPORTS_NUMA_BALANCING	if X86_64
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_QUEUED_RWLOCKS

arch/x86/include/asm/pgtable-3level.h

@@ -158,14 +158,15 @@ static inline pte_t native_ptep_get_and_clear(pte_t *ptep)
 #define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp)
 #endif
 
-#ifdef CONFIG_SMP
 union split_pmd {
 	struct {
 		u32 pmd_low;
 		u32 pmd_high;
 	};
 	pmd_t pmd;
 };
+
+#ifdef CONFIG_SMP
 static inline pmd_t native_pmdp_get_and_clear(pmd_t *pmdp)
 {
 	union split_pmd res, *orig = (union split_pmd *)pmdp;
@@ -181,6 +182,40 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *pmdp)
 #define native_pmdp_get_and_clear(xp) native_local_pmdp_get_and_clear(xp)
 #endif
 
+#ifndef pmdp_establish
+#define pmdp_establish pmdp_establish
+static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
+		unsigned long address, pmd_t *pmdp, pmd_t pmd)
+{
+	pmd_t old;
+
+	/*
+	 * If pmd has present bit cleared we can get away without expensive
+	 * cmpxchg64: we can update pmdp half-by-half without racing with
+	 * anybody.
+	 */
+	if (!(pmd_val(pmd) & _PAGE_PRESENT)) {
+		union split_pmd old, new, *ptr;
+
+		ptr = (union split_pmd *)pmdp;
+
+		new.pmd = pmd;
+
+		/* xchg acts as a barrier before setting of the high bits */
+		old.pmd_low = xchg(&ptr->pmd_low, new.pmd_low);
+		old.pmd_high = ptr->pmd_high;
+		ptr->pmd_high = new.pmd_high;
+		return old.pmd;
+	}
+
+	do {
+		old = *pmdp;
+	} while (cmpxchg64(&pmdp->pmd, old.pmd, pmd.pmd) != old.pmd);
+
+	return old;
+}
+#endif
+
 #ifdef CONFIG_SMP
 union split_pud {
 	struct {