Merge branch 'akpm' (patches from Andrew)

Merge first patchbomb from Andrew Morton:

 - a few misc things

 - ocfs2 udpates

 - kernel/watchdog.c feature work (took ages to get right)

 - most of MM.  A few tricky bits are held up and probably won't make 4.2.

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (91 commits)
  mm: kmemleak_alloc_percpu() should follow the gfp from per_alloc()
  mm, thp: respect MPOL_PREFERRED policy with non-local node
  tmpfs: truncate prealloc blocks past i_size
  mm/memory hotplug: print the last vmemmap region at the end of hot add memory
  mm/mmap.c: optimization of do_mmap_pgoff function
  mm: kmemleak: optimise kmemleak_lock acquiring during kmemleak_scan
  mm: kmemleak: avoid deadlock on the kmemleak object insertion error path
  mm: kmemleak: do not acquire scan_mutex in kmemleak_do_cleanup()
  mm: kmemleak: fix delete_object_*() race when called on the same memory block
  mm: kmemleak: allow safe memory scanning during kmemleak disabling
  memcg: convert mem_cgroup->under_oom from atomic_t to int
  memcg: remove unused mem_cgroup->oom_wakeups
  frontswap: allow multiple backends
  x86, mirror: x86 enabling - find mirrored memory ranges
  mm/memblock: allocate boot time data structures from mirrored memory
  mm/memblock: add extra "flags" to memblock to allow selection of memory based on attribute
  mm: do not ignore mapping_gfp_mask in page cache allocation paths
  mm/cma.c: fix typos in comments
  mm/oom_kill.c: print points as unsigned int
  mm/hugetlb: handle races in alloc_huge_page and hugetlb_reserve_pages
  ...

Documentation/lockup-watchdogs.txt

@@ -61,3 +61,21 @@ As explained above, a kernel knob is provided that allows
 administrators to configure the period of the hrtimer and the perf
 event. The right value for a particular environment is a trade-off
 between fast response to lockups and detection overhead.
+
+By default, the watchdog runs on all online cores.  However, on a
+kernel configured with NO_HZ_FULL, by default the watchdog runs only
+on the housekeeping cores, not the cores specified in the "nohz_full"
+boot argument.  If we allowed the watchdog to run by default on
+the "nohz_full" cores, we would have to run timer ticks to activate
+the scheduler, which would prevent the "nohz_full" functionality
+from protecting the user code on those cores from the kernel.
+Of course, disabling it by default on the nohz_full cores means that
+when those cores do enter the kernel, by default we will not be
+able to detect if they lock up.  However, allowing the watchdog
+to continue to run on the housekeeping (non-tickless) cores means
+that we will continue to detect lockups properly on those cores.
+
+In either case, the set of cores excluded from running the watchdog
+may be adjusted via the kernel.watchdog_cpumask sysctl.  For
+nohz_full cores, this may be useful for debugging a case where the
+kernel seems to be hanging on the nohz_full cores.

Documentation/sysctl/kernel.txt

@@ -923,6 +923,27 @@ and nmi_watchdog.
 
 ==============================================================
 
+watchdog_cpumask:
+
+This value can be used to control on which cpus the watchdog may run.
+The default cpumask is all possible cores, but if NO_HZ_FULL is
+enabled in the kernel config, and cores are specified with the
+nohz_full= boot argument, those cores are excluded by default.
+Offline cores can be included in this mask, and if the core is later
+brought online, the watchdog will be started based on the mask value.
+
+Typically this value would only be touched in the nohz_full case
+to re-enable cores that by default were not running the watchdog,
+if a kernel lockup was suspected on those cores.
+
+The argument value is the standard cpulist format for cpumasks,
+so for example to enable the watchdog on cores 0, 2, 3, and 4 you
+might say:
+
+  echo 0,2-4 > /proc/sys/kernel/watchdog_cpumask
+
+==============================================================
+
 watchdog_thresh:
 
 This value can be used to control the frequency of hrtimer and NMI

Documentation/vm/unevictable-lru.txt

@@ -467,7 +467,13 @@ mmap(MAP_LOCKED) SYSTEM CALL HANDLING
 
 In addition the mlock()/mlockall() system calls, an application can request
 that a region of memory be mlocked supplying the MAP_LOCKED flag to the mmap()
-call.  Furthermore, any mmap() call or brk() call that expands the heap by a
+call. There is one important and subtle difference here, though. mmap() + mlock()
+will fail if the range cannot be faulted in (e.g. because mm_populate fails)
+and returns with ENOMEM while mmap(MAP_LOCKED) will not fail. The mmaped
+area will still have properties of the locked area - aka. pages will not get
+swapped out - but major page faults to fault memory in might still happen.
+
+Furthermore, any mmap() call or brk() call that expands the heap by a
 task that has previously called mlockall() with the MCL_FUTURE flag will result
 in the newly mapped memory being mlocked.  Before the unevictable/mlock
 changes, the kernel simply called make_pages_present() to allocate pages and

arch/alpha/include/asm/mm-arch-hooks.h

+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_ALPHA_MM_ARCH_HOOKS_H
+#define _ASM_ALPHA_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_ALPHA_MM_ARCH_HOOKS_H */

arch/arc/include/asm/mm-arch-hooks.h

+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_ARC_MM_ARCH_HOOKS_H
+#define _ASM_ARC_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_ARC_MM_ARCH_HOOKS_H */

arch/arm/include/asm/hugetlb.h

@@ -53,10 +53,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	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);

arch/arm/include/asm/mm-arch-hooks.h

+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_ARM_MM_ARCH_HOOKS_H
+#define _ASM_ARM_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_ARM_MM_ARCH_HOOKS_H */

arch/arm/mm/hugetlbpage.c

@@ -41,11 +41,6 @@ int pud_huge(pud_t pud)
 	return 0;
 }
 
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
-{
-	return 0;
-}
-
 int pmd_huge(pmd_t pmd)
 {
 	return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT);

arch/arm64/include/asm/hugetlb.h

@@ -86,10 +86,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	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);

arch/arm64/include/asm/mm-arch-hooks.h

+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_ARM64_MM_ARCH_HOOKS_H
+#define _ASM_ARM64_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_ARM64_MM_ARCH_HOOKS_H */

arch/arm64/mm/hugetlbpage.c

@@ -31,13 +31,6 @@
 #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
-
 int pmd_huge(pmd_t pmd)
 {
 	return !(pmd_val(pmd) & PMD_TABLE_BIT);

arch/avr32/include/asm/mm-arch-hooks.h

+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_AVR32_MM_ARCH_HOOKS_H
+#define _ASM_AVR32_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_AVR32_MM_ARCH_HOOKS_H */

arch/blackfin/include/asm/mm-arch-hooks.h

+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_BLACKFIN_MM_ARCH_HOOKS_H
+#define _ASM_BLACKFIN_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_BLACKFIN_MM_ARCH_HOOKS_H */

arch/c6x/include/asm/mm-arch-hooks.h

+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_C6X_MM_ARCH_HOOKS_H
+#define _ASM_C6X_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_C6X_MM_ARCH_HOOKS_H */

arch/cris/include/asm/mm-arch-hooks.h

+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_CRIS_MM_ARCH_HOOKS_H
+#define _ASM_CRIS_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_CRIS_MM_ARCH_HOOKS_H */

arch/frv/include/asm/mm-arch-hooks.h

+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_FRV_MM_ARCH_HOOKS_H
+#define _ASM_FRV_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_FRV_MM_ARCH_HOOKS_H */

arch/hexagon/include/asm/mm-arch-hooks.h

+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_HEXAGON_MM_ARCH_HOOKS_H
+#define _ASM_HEXAGON_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_HEXAGON_MM_ARCH_HOOKS_H */

arch/ia64/include/asm/hugetlb.h

@@ -20,10 +20,6 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
 		REGION_NUMBER((addr)+(len)-1) == RGN_HPAGE);
 }
 
-static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm)
-{
-}
-
 static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 				   pte_t *ptep, pte_t pte)
 {

arch/ia64/include/asm/mm-arch-hooks.h

+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_IA64_MM_ARCH_HOOKS_H
+#define _ASM_IA64_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_IA64_MM_ARCH_HOOKS_H */

arch/ia64/mm/hugetlbpage.c

@@ -65,11 +65,6 @@ huge_pte_offset (struct mm_struct *mm, unsigned long addr)
 	return pte;
 }
 
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
-{
-	return 0;
-}
-
 #define mk_pte_huge(entry) { pte_val(entry) |= _PAGE_P; }
 
 /*

arch/m32r/include/asm/mm-arch-hooks.h

+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_M32R_MM_ARCH_HOOKS_H
+#define _ASM_M32R_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_M32R_MM_ARCH_HOOKS_H */

arch/m68k/include/asm/mm-arch-hooks.h

+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_M68K_MM_ARCH_HOOKS_H
+#define _ASM_M68K_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_M68K_MM_ARCH_HOOKS_H */

arch/metag/include/asm/dma-mapping.h

@@ -134,20 +134,24 @@ dma_sync_single_range_for_device(struct device *dev, dma_addr_t dma_handle,
 }
 
 static inline void
-dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems,
+dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sglist, int nelems,
 		    enum dma_data_direction direction)
 {
 	int i;
-	for (i = 0; i < nelems; i++, sg++)
+	struct scatterlist *sg;
+
+	for_each_sg(sglist, sg, nelems, i)
 		dma_sync_for_cpu(sg_virt(sg), sg->length, direction);
 }
 
 static inline void
-dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems,
-		       enum dma_data_direction direction)
+dma_sync_sg_for_device(struct device *dev, struct scatterlist *sglist,
+		       int nelems, enum dma_data_direction direction)
 {
 	int i;
-	for (i = 0; i < nelems; i++, sg++)
+	struct scatterlist *sg;
+
+	for_each_sg(sglist, sg, nelems, i)
 		dma_sync_for_device(sg_virt(sg), sg->length, direction);
 }
 

arch/metag/include/asm/hugetlb.h

@@ -14,10 +14,6 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
 int prepare_hugepage_range(struct file *file, unsigned long addr,
 						unsigned long len);
 
-static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm)
-{
-}
-
 static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 					  unsigned long addr, unsigned long end,
 					  unsigned long floor,

arch/metag/include/asm/mm-arch-hooks.h

+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_METAG_MM_ARCH_HOOKS_H
+#define _ASM_METAG_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_METAG_MM_ARCH_HOOKS_H */

arch/metag/mm/hugetlbpage.c

@@ -89,11 +89,6 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 	return pte;
 }
 
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
-{
-	return 0;
-}
-
 int pmd_huge(pmd_t pmd)
 {
 	return pmd_page_shift(pmd) > PAGE_SHIFT;

arch/microblaze/include/asm/mm-arch-hooks.h

+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_MICROBLAZE_MM_ARCH_HOOKS_H
+#define _ASM_MICROBLAZE_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_MICROBLAZE_MM_ARCH_HOOKS_H */

arch/mips/include/asm/hugetlb.h

@@ -38,10 +38,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm)
-{
-}
-
 static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 					  unsigned long addr,
 					  unsigned long end,

arch/mips/include/asm/mm-arch-hooks.h

+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_MIPS_MM_ARCH_HOOKS_H
+#define _ASM_MIPS_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_MIPS_MM_ARCH_HOOKS_H */

arch/mips/include/asm/pgtable.h

@@ -568,12 +568,12 @@ static inline pmd_t pmd_mknotpresent(pmd_t pmd)
 }
 
 /*
- * The generic version pmdp_get_and_clear uses a version of pmd_clear() with a
+ * The generic version pmdp_huge_get_and_clear uses a version of pmd_clear() with a
  * different prototype.
  */
-#define __HAVE_ARCH_PMDP_GET_AND_CLEAR
-static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
-				       unsigned long address, pmd_t *pmdp)
+#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
+static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
+					    unsigned long address, pmd_t *pmdp)
 {
 	pmd_t old = *pmdp;
 

arch/mips/mm/hugetlbpage.c

@@ -51,11 +51,6 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 	return (pte_t *) pmd;
 }
 
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
-{
-	return 0;
-}
-
 /*
  * This function checks for proper alignment of input addr and len parameters.
  */

arch/mn10300/include/asm/mm-arch-hooks.h

+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_MN10300_MM_ARCH_HOOKS_H
+#define _ASM_MN10300_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_MN10300_MM_ARCH_HOOKS_H */

arch/nios2/include/asm/mm-arch-hooks.h

+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_NIOS2_MM_ARCH_HOOKS_H
+#define _ASM_NIOS2_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_NIOS2_MM_ARCH_HOOKS_H */

arch/openrisc/include/asm/mm-arch-hooks.h

+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_OPENRISC_MM_ARCH_HOOKS_H
+#define _ASM_OPENRISC_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_OPENRISC_MM_ARCH_HOOKS_H */

arch/parisc/include/asm/mm-arch-hooks.h

+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_PARISC_MM_ARCH_HOOKS_H
+#define _ASM_PARISC_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_PARISC_MM_ARCH_HOOKS_H */

arch/parisc/kernel/pci-dma.c

@@ -478,14 +478,16 @@ static void pa11_dma_unmap_single(struct device *dev, dma_addr_t dma_handle, siz
 static int pa11_dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction)
 {
 	int i;
+	struct scatterlist *sg;
 
 	BUG_ON(direction == DMA_NONE);
 
-	for (i = 0; i < nents; i++, sglist++ ) {
-		unsigned long vaddr = (unsigned long)sg_virt(sglist);
-		sg_dma_address(sglist) = (dma_addr_t) virt_to_phys(vaddr);
-		sg_dma_len(sglist) = sglist->length;
-		flush_kernel_dcache_range(vaddr, sglist->length);
+	for_each_sg(sglist, sg, nents, i) {
+		unsigned long vaddr = (unsigned long)sg_virt(sg);
+
+		sg_dma_address(sg) = (dma_addr_t) virt_to_phys(vaddr);
+		sg_dma_len(sg) = sg->length;
+		flush_kernel_dcache_range(vaddr, sg->length);
 	}
 	return nents;
 }
@@ -493,6 +495,7 @@ static int pa11_dma_map_sg(struct device *dev, struct scatterlist *sglist, int n
 static void pa11_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction)
 {
 	int i;
+	struct scatterlist *sg;
 
 	BUG_ON(direction == DMA_NONE);
 
@@ -501,8 +504,8 @@ static void pa11_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, in
 
 	/* once we do combining we'll need to use phys_to_virt(sg_dma_address(sglist)) */
 
-	for (i = 0; i < nents; i++, sglist++ )
-		flush_kernel_vmap_range(sg_virt(sglist), sglist->length);
+	for_each_sg(sglist, sg, nents, i)
+		flush_kernel_vmap_range(sg_virt(sg), sg->length);
 	return;
 }
 
@@ -523,21 +526,23 @@ static void pa11_dma_sync_single_for_device(struct device *dev, dma_addr_t dma_h
 static void pa11_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction)
 {
 	int i;
+	struct scatterlist *sg;
 
 	/* once we do combining we'll need to use phys_to_virt(sg_dma_address(sglist)) */
 
-	for (i = 0; i < nents; i++, sglist++ )
-		flush_kernel_vmap_range(sg_virt(sglist), sglist->length);
+	for_each_sg(sglist, sg, nents, i)
+		flush_kernel_vmap_range(sg_virt(sg), sg->length);
 }
 
 static void pa11_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction)
 {
 	int i;
+	struct scatterlist *sg;
 
 	/* once we do combining we'll need to use phys_to_virt(sg_dma_address(sglist)) */
 
-	for (i = 0; i < nents; i++, sglist++ )
-		flush_kernel_vmap_range(sg_virt(sglist), sglist->length);
+	for_each_sg(sglist, sg, nents, i)
+		flush_kernel_vmap_range(sg_virt(sg), sg->length);
 }
 
 struct hppa_dma_ops pcxl_dma_ops = {

arch/powerpc/include/asm/hugetlb.h

@@ -112,11 +112,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm)
-{
-}
-
-
 static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 				   pte_t *ptep, pte_t pte)
 {

arch/powerpc/include/asm/mm-arch-hooks.h

+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_POWERPC_MM_ARCH_HOOKS_H
+#define _ASM_POWERPC_MM_ARCH_HOOKS_H
+
+static inline void arch_remap(struct mm_struct *mm,
+			      unsigned long old_start, unsigned long old_end,
+			      unsigned long new_start, unsigned long new_end)
+{
+	/*
+	 * mremap() doesn't allow moving multiple vmas so we can limit the
+	 * check to old_start == vdso_base.
+	 */
+	if (old_start == mm->context.vdso_base)
+		mm->context.vdso_base = new_start;
+}
+#define arch_remap arch_remap
+
+#endif /* _ASM_POWERPC_MM_ARCH_HOOKS_H */

arch/powerpc/include/asm/mmu_context.h

@@ -8,7 +8,6 @@
 #include <linux/spinlock.h>
 #include <asm/mmu.h>	
 #include <asm/cputable.h>
-#include <asm-generic/mm_hooks.h>
 #include <asm/cputhreads.h>
 
 /*
@@ -127,5 +126,27 @@ static inline void enter_lazy_tlb(struct mm_struct *mm,
 #endif
 }
 
+static inline void arch_dup_mmap(struct mm_struct *oldmm,
+				 struct mm_struct *mm)
+{
+}
+
+static inline void arch_exit_mmap(struct mm_struct *mm)
+{
+}
+
+static inline void arch_unmap(struct mm_struct *mm,
+			      struct vm_area_struct *vma,
+			      unsigned long start, unsigned long end)
+{
+	if (start <= mm->context.vdso_base && mm->context.vdso_base < end)
+		mm->context.vdso_base = 0;
+}
+
+static inline void arch_bprm_mm_init(struct mm_struct *mm,
+				     struct vm_area_struct *vma)
+{
+}
+
 #endif /* __KERNEL__ */
 #endif /* __ASM_POWERPC_MMU_CONTEXT_H */

arch/powerpc/include/asm/pgtable-ppc64.h

@@ -569,13 +569,9 @@ extern int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 extern int pmdp_clear_flush_young(struct vm_area_struct *vma,
 				  unsigned long address, pmd_t *pmdp);
 
-#define __HAVE_ARCH_PMDP_GET_AND_CLEAR
-extern pmd_t pmdp_get_and_clear(struct mm_struct *mm,
-				unsigned long addr, pmd_t *pmdp);
-
-#define __HAVE_ARCH_PMDP_CLEAR_FLUSH
-extern pmd_t pmdp_clear_flush(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_SET_WRPROTECT
 static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr,
@@ -592,6 +588,10 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 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);

arch/powerpc/kernel/vio.c

@@ -557,11 +557,11 @@ static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist,
 	struct vio_dev *viodev = to_vio_dev(dev);
 	struct iommu_table *tbl;
 	struct scatterlist *sgl;
-	int ret, count = 0;
+	int ret, count;
 	size_t alloc_size = 0;
 
 	tbl = get_iommu_table_base(dev);
-	for (sgl = sglist; count < nelems; count++, sgl++)
+	for_each_sg(sglist, sgl, nelems, count)
 		alloc_size += roundup(sgl->length, IOMMU_PAGE_SIZE(tbl));
 
 	if (vio_cmo_alloc(viodev, alloc_size)) {
@@ -577,7 +577,7 @@ static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist,
 		return ret;
 	}
 
-	for (sgl = sglist, count = 0; count < ret; count++, sgl++)
+	for_each_sg(sglist, sgl, ret, count)
 		alloc_size -= roundup(sgl->dma_length, IOMMU_PAGE_SIZE(tbl));
 	if (alloc_size)
 		vio_cmo_dealloc(viodev, alloc_size);
@@ -594,10 +594,10 @@ static void vio_dma_iommu_unmap_sg(struct device *dev,
 	struct iommu_table *tbl;
 	struct scatterlist *sgl;
 	size_t alloc_size = 0;
-	int count = 0;
+	int count;
 
 	tbl = get_iommu_table_base(dev);
-	for (sgl = sglist; count < nelems; count++, sgl++)
+	for_each_sg(sglist, sgl, nelems, count)
 		alloc_size += roundup(sgl->dma_length, IOMMU_PAGE_SIZE(tbl));
 
 	dma_iommu_ops.unmap_sg(dev, sglist, nelems, direction, attrs);

arch/powerpc/mm/hugetlbpage.c

@@ -439,11 +439,6 @@ int alloc_bootmem_huge_page(struct hstate *hstate)
 }
 #endif
 
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
-{
-	return 0;
-}
-
 #ifdef CONFIG_PPC_FSL_BOOK3E
 #define HUGEPD_FREELIST_SIZE \
 	((PAGE_SIZE - sizeof(struct hugepd_freelist)) / sizeof(pte_t))

arch/powerpc/mm/pgtable_64.c

@@ -554,47 +554,42 @@ unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr,
 	return old;
 }
 
-pmd_t pmdp_clear_flush(struct vm_area_struct *vma, unsigned long address,
-		       pmd_t *pmdp)
+pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address,
+			  pmd_t *pmdp)
 {
 	pmd_t pmd;
 
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
-	if (pmd_trans_huge(*pmdp)) {
-		pmd = pmdp_get_and_clear(vma->vm_mm, address, pmdp);
-	} else {
-		/*
-		 * khugepaged calls this for normal pmd
-		 */
-		pmd = *pmdp;
-		pmd_clear(pmdp);
-		/*
-		 * Wait for all pending hash_page to finish. This is needed
-		 * in case of subpage collapse. When we collapse normal pages
-		 * to hugepage, we first clear the pmd, then invalidate all
-		 * the PTE entries. The assumption here is that any low level
-		 * page fault will see a none pmd and take the slow path that
-		 * will wait on mmap_sem. But we could very well be in a
-		 * hash_page with local ptep pointer value. Such a hash page
-		 * can result in adding new HPTE entries for normal subpages.
-		 * That means we could be modifying the page content as we
-		 * copy them to a huge page. So wait for parallel hash_page
-		 * to finish before invalidating HPTE entries. We can do this
-		 * by sending an IPI to all the cpus and executing a dummy
-		 * function there.
-		 */
-		kick_all_cpus_sync();
-		/*
-		 * Now invalidate the hpte entries in the range
-		 * covered by pmd. This make sure we take a
-		 * fault and will find the pmd as none, which will
-		 * result in a major fault which takes mmap_sem and
-		 * hence wait for collapse to complete. Without this
-		 * the __collapse_huge_page_copy can result in copying
-		 * the old content.
-		 */
-		flush_tlb_pmd_range(vma->vm_mm, &pmd, address);
-	}
+	VM_BUG_ON(pmd_trans_huge(*pmdp));
+
+	pmd = *pmdp;
+	pmd_clear(pmdp);
+	/*
+	 * Wait for all pending hash_page to finish. This is needed
+	 * in case of subpage collapse. When we collapse normal pages
+	 * to hugepage, we first clear the pmd, then invalidate all
+	 * the PTE entries. The assumption here is that any low level
+	 * page fault will see a none pmd and take the slow path that
+	 * will wait on mmap_sem. But we could very well be in a
+	 * hash_page with local ptep pointer value. Such a hash page
+	 * can result in adding new HPTE entries for normal subpages.
+	 * That means we could be modifying the page content as we
+	 * copy them to a huge page. So wait for parallel hash_page
+	 * to finish before invalidating HPTE entries. We can do this
+	 * by sending an IPI to all the cpus and executing a dummy
+	 * function there.
+	 */
+	kick_all_cpus_sync();
+	/*
+	 * Now invalidate the hpte entries in the range
+	 * covered by pmd. This make sure we take a
+	 * fault and will find the pmd as none, which will
+	 * result in a major fault which takes mmap_sem and
+	 * hence wait for collapse to complete. Without this
+	 * the __collapse_huge_page_copy can result in copying
+	 * the old content.
+	 */
+	flush_tlb_pmd_range(vma->vm_mm, &pmd, address);
 	return pmd;
 }
 
@@ -817,8 +812,8 @@ void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
 	return;
 }
 
-pmd_t pmdp_get_and_clear(struct mm_struct *mm,
-			 unsigned long addr, pmd_t *pmdp)
+pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
+			      unsigned long addr, pmd_t *pmdp)
 {
 	pmd_t old_pmd;
 	pgtable_t pgtable;

arch/s390/include/asm/hugetlb.h

@@ -35,7 +35,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-#define hugetlb_prefault_arch_hook(mm)		do { } while (0)
 #define arch_clear_hugepage_flags(page)		do { } while (0)
 
 int arch_prepare_hugepage(struct page *page);

arch/s390/include/asm/mm-arch-hooks.h

+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_S390_MM_ARCH_HOOKS_H
+#define _ASM_S390_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_S390_MM_ARCH_HOOKS_H */

arch/s390/include/asm/pgtable.h

@@ -1498,9 +1498,9 @@ static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 	return pmd_young(pmd);
 }
 
-#define __HAVE_ARCH_PMDP_GET_AND_CLEAR
-static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
-				       unsigned long address, pmd_t *pmdp)
+#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
+static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
+					    unsigned long address, pmd_t *pmdp)
 {
 	pmd_t pmd = *pmdp;
 
@@ -1509,10 +1509,10 @@ static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
 	return pmd;
 }
 
-#define __HAVE_ARCH_PMDP_GET_AND_CLEAR_FULL
-static inline pmd_t pmdp_get_and_clear_full(struct mm_struct *mm,
-					    unsigned long address,
-					    pmd_t *pmdp, int full)
+#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR_FULL
+static inline pmd_t pmdp_huge_get_and_clear_full(struct mm_struct *mm,
+						 unsigned long address,
+						 pmd_t *pmdp, int full)
 {
 	pmd_t pmd = *pmdp;
 
@@ -1522,11 +1522,11 @@ static inline pmd_t pmdp_get_and_clear_full(struct mm_struct *mm,
 	return pmd;
 }
 
-#define __HAVE_ARCH_PMDP_CLEAR_FLUSH
-static inline pmd_t pmdp_clear_flush(struct vm_area_struct *vma,
-				     unsigned long address, pmd_t *pmdp)
+#define __HAVE_ARCH_PMDP_HUGE_CLEAR_FLUSH
+static inline pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma,
+					  unsigned long address, pmd_t *pmdp)
 {
-	return pmdp_get_and_clear(vma->vm_mm, address, pmdp);
+	return pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);
 }
 
 #define __HAVE_ARCH_PMDP_INVALIDATE
@@ -1548,6 +1548,14 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
 	}
 }
 
+static inline pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
+					unsigned long address,
+					pmd_t *pmdp)
+{
+	return pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);
+}
+#define pmdp_collapse_flush pmdp_collapse_flush
+
 #define pfn_pmd(pfn, pgprot)	mk_pmd_phys(__pa((pfn) << PAGE_SHIFT), (pgprot))
 #define mk_pmd(page, pgprot)	pfn_pmd(page_to_pfn(page), (pgprot))
 

arch/s390/kernel/crash_dump.c

@@ -33,11 +33,12 @@ static struct memblock_type oldmem_type = {
 };
 
 #define for_each_dump_mem_range(i, nid, p_start, p_end, p_nid)		\
-	for (i = 0, __next_mem_range(&i, nid, &memblock.physmem,	\
+	for (i = 0, __next_mem_range(&i, nid, MEMBLOCK_NONE,		\
+				     &memblock.physmem,			\
 				     &oldmem_type, p_start,		\
 				     p_end, p_nid);			\
 	     i != (u64)ULLONG_MAX;					\
-	     __next_mem_range(&i, nid, &memblock.physmem,		\
+	     __next_mem_range(&i, nid, MEMBLOCK_NONE, &memblock.physmem,\
 			      &oldmem_type,				\
 			      p_start, p_end, p_nid))
 

arch/s390/mm/hugetlbpage.c

@@ -193,11 +193,6 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 	return (pte_t *) pmdp;
 }
 
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
-{
-	return 0;
-}
-
 int pmd_huge(pmd_t pmd)
 {
 	if (!MACHINE_HAS_HPAGE)

arch/score/include/asm/mm-arch-hooks.h

+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_SCORE_MM_ARCH_HOOKS_H
+#define _ASM_SCORE_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_SCORE_MM_ARCH_HOOKS_H */

arch/sh/include/asm/hugetlb.h

@@ -26,9 +26,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm) {
-}
-
 static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 					  unsigned long addr, unsigned long end,
 					  unsigned long floor,

arch/sh/include/asm/mm-arch-hooks.h

+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_SH_MM_ARCH_HOOKS_H
+#define _ASM_SH_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_SH_MM_ARCH_HOOKS_H */

arch/sh/mm/hugetlbpage.c

@@ -62,11 +62,6 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 	return pte;
 }
 
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
-{
-	return 0;
-}
-
 int pmd_huge(pmd_t pmd)
 {
 	return 0;

arch/sparc/include/asm/hugetlb.h

@@ -11,10 +11,6 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep);
 
-static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm)
-{
-}
-
 static inline int is_hugepage_only_range(struct mm_struct *mm,
 					 unsigned long addr,
 					 unsigned long len) {

arch/sparc/include/asm/mm-arch-hooks.h

+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_SPARC_MM_ARCH_HOOKS_H
+#define _ASM_SPARC_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_SPARC_MM_ARCH_HOOKS_H */

arch/sparc/include/asm/pgtable_64.h

@@ -865,10 +865,10 @@ static inline unsigned long pud_pfn(pud_t pud)
 void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
 		   pte_t *ptep, pte_t orig, int fullmm);
 
-#define __HAVE_ARCH_PMDP_GET_AND_CLEAR
-static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
-				       unsigned long addr,
-				       pmd_t *pmdp)
+#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
+static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
+					    unsigned long addr,
+					    pmd_t *pmdp)
 {
 	pmd_t pmd = *pmdp;
 	set_pmd_at(mm, addr, pmdp, __pmd(0UL));

arch/sparc/kernel/ldc.c

@@ -2086,6 +2086,7 @@ int ldc_map_sg(struct ldc_channel *lp,
 	struct cookie_state state;
 	struct ldc_iommu *iommu;
 	int err;
+	struct scatterlist *s;
 
 	if (map_perm & ~LDC_MAP_ALL)
 		return -EINVAL;
@@ -2112,9 +2113,10 @@ int ldc_map_sg(struct ldc_channel *lp,
 	state.pte_idx = (base - iommu->page_table);
 	state.nc = 0;
 
-	for (i = 0; i < num_sg; i++)
-		fill_cookies(&state, page_to_pfn(sg_page(&sg[i])) << PAGE_SHIFT,
-			     sg[i].offset, sg[i].length);
+	for_each_sg(sg, s, num_sg, i) {
+		fill_cookies(&state, page_to_pfn(sg_page(s)) << PAGE_SHIFT,
+			     s->offset, s->length);
+	}
 
 	return state.nc;
 }

arch/sparc/mm/hugetlbpage.c

@@ -172,11 +172,6 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 	return pte;
 }
 
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
-{
-	return 0;
-}
-
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t entry)
 {

arch/sparc/mm/init_64.c

@@ -1966,7 +1966,8 @@ static phys_addr_t __init available_memory(void)
 	phys_addr_t pa_start, pa_end;
 	u64 i;
 
-	for_each_free_mem_range(i, NUMA_NO_NODE, &pa_start, &pa_end, NULL)
+	for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &pa_start,
+				&pa_end, NULL)
 		available = available + (pa_end  - pa_start);
 
 	return available;
@@ -1992,7 +1993,8 @@ static void __init reduce_memory(phys_addr_t limit_ram)
 	if (limit_ram >= avail_ram)
 		return;
 
-	for_each_free_mem_range(i, NUMA_NO_NODE, &pa_start, &pa_end, NULL) {
+	for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &pa_start,
+				&pa_end, NULL) {
 		phys_addr_t region_size = pa_end - pa_start;
 		phys_addr_t clip_start = pa_start;
 

arch/tile/include/asm/hugetlb.h

@@ -40,10 +40,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm)
-{
-}
-
 static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 					  unsigned long addr, unsigned long end,
 					  unsigned long floor,

arch/tile/include/asm/mm-arch-hooks.h

+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_TILE_MM_ARCH_HOOKS_H
+#define _ASM_TILE_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_TILE_MM_ARCH_HOOKS_H */

arch/tile/include/asm/pgtable.h

@@ -414,10 +414,10 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
 }
 
 
-#define __HAVE_ARCH_PMDP_GET_AND_CLEAR
-static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
-				       unsigned long address,
-				       pmd_t *pmdp)
+#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
+static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
+					    unsigned long address,
+					    pmd_t *pmdp)
 {
 	return pte_pmd(ptep_get_and_clear(mm, address, pmdp_ptep(pmdp)));
 }

arch/tile/mm/hugetlbpage.c

@@ -160,11 +160,6 @@ int pud_huge(pud_t pud)
 	return !!(pud_val(pud) & _PAGE_HUGE_PAGE);
 }
 
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
-{
-	return 0;
-}
-
 #ifdef HAVE_ARCH_HUGETLB_UNMAPPED_AREA
 static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
 		unsigned long addr, unsigned long len,

arch/um/include/asm/mm-arch-hooks.h

+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_UM_MM_ARCH_HOOKS_H
+#define _ASM_UM_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_UM_MM_ARCH_HOOKS_H */

arch/unicore32/include/asm/mm-arch-hooks.h

+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_UNICORE32_MM_ARCH_HOOKS_H
+#define _ASM_UNICORE32_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_UNICORE32_MM_ARCH_HOOKS_H */

arch/x86/include/asm/hugetlb.h

@@ -26,9 +26,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm) {
-}
-
 static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 					  unsigned long addr, unsigned long end,
 					  unsigned long floor,

arch/x86/include/asm/mm-arch-hooks.h

+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_X86_MM_ARCH_HOOKS_H
+#define _ASM_X86_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_X86_MM_ARCH_HOOKS_H */

arch/x86/include/asm/pgtable.h

@@ -805,8 +805,8 @@ static inline int pmd_write(pmd_t pmd)
 	return pmd_flags(pmd) & _PAGE_RW;
 }
 
-#define __HAVE_ARCH_PMDP_GET_AND_CLEAR
-static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm, unsigned long addr,
+#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
+static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr,
 				       pmd_t *pmdp)
 {
 	pmd_t pmd = native_pmdp_get_and_clear(pmdp);

arch/x86/kernel/check.c

@@ -91,7 +91,8 @@ void __init setup_bios_corruption_check(void)
 
 	corruption_check_size = round_up(corruption_check_size, PAGE_SIZE);
 
-	for_each_free_mem_range(i, NUMA_NO_NODE, &start, &end, NULL) {
+	for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end,
+				NULL) {
 		start = clamp_t(phys_addr_t, round_up(start, PAGE_SIZE),
 				PAGE_SIZE, corruption_check_size);
 		end = clamp_t(phys_addr_t, round_down(end, PAGE_SIZE),

arch/x86/kernel/e820.c

@@ -1123,7 +1123,8 @@ void __init memblock_find_dma_reserve(void)
 		nr_pages += end_pfn - start_pfn;
 	}
 
-	for_each_free_mem_range(u, NUMA_NO_NODE, &start, &end, NULL) {
+	for_each_free_mem_range(u, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end,
+				NULL) {
 		start_pfn = min_t(unsigned long, PFN_UP(start), MAX_DMA_PFN);
 		end_pfn = min_t(unsigned long, PFN_DOWN(end), MAX_DMA_PFN);
 		if (start_pfn < end_pfn)

arch/x86/kernel/setup.c

@@ -1105,6 +1105,9 @@ void __init setup_arch(char **cmdline_p)
 	memblock_set_current_limit(ISA_END_ADDRESS);
 	memblock_x86_fill();
 
+	if (efi_enabled(EFI_BOOT))
+		efi_find_mirror();
+
 	/*
 	 * The EFI specification says that boot service code won't be called
 	 * after ExitBootServices(). This is, in fact, a lie.

arch/x86/mm/init_32.c

@@ -433,7 +433,7 @@ void __init add_highpages_with_active_regions(int nid,
 	phys_addr_t start, end;
 	u64 i;
 
-	for_each_free_mem_range(i, nid, &start, &end, NULL) {
+	for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &start, &end, NULL) {
 		unsigned long pfn = clamp_t(unsigned long, PFN_UP(start),
 					    start_pfn, end_pfn);
 		unsigned long e_pfn = clamp_t(unsigned long, PFN_DOWN(end),

arch/x86/platform/efi/efi.c

@@ -117,6 +117,27 @@ void efi_get_time(struct timespec *now)
 	now->tv_nsec = 0;
 }
 
+void __init efi_find_mirror(void)
+{
+	void *p;
+	u64 mirror_size = 0, total_size = 0;
+
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		efi_memory_desc_t *md = p;
+		unsigned long long start = md->phys_addr;
+		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
+
+		total_size += size;
+		if (md->attribute & EFI_MEMORY_MORE_RELIABLE) {
+			memblock_mark_mirror(start, size);
+			mirror_size += size;
+		}
+	}
+	if (mirror_size)
+		pr_info("Memory: %lldM/%lldM mirrored memory\n",
+			mirror_size>>20, total_size>>20);
+}
+
 /*
  * Tell the kernel about the EFI memory map.  This might include
  * more than the max 128 entries that can fit in the e820 legacy

arch/xtensa/include/asm/dma-mapping.h

@@ -52,14 +52,15 @@ dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
 }
 
 static inline int
-dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
+dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents,
 	   enum dma_data_direction direction)
 {
 	int i;
+	struct scatterlist *sg;
 
 	BUG_ON(direction == DMA_NONE);
 
-	for (i = 0; i < nents; i++, sg++ ) {
+	for_each_sg(sglist, sg, nents, i) {
 		BUG_ON(!sg_page(sg));
 
 		sg->dma_address = sg_phys(sg);
@@ -124,20 +125,24 @@ dma_sync_single_range_for_device(struct device *dev, dma_addr_t dma_handle,
 	consistent_sync((void *)bus_to_virt(dma_handle)+offset,size,direction);
 }
 static inline void
-dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems,
+dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sglist, int nelems,
 		 enum dma_data_direction dir)
 {
 	int i;
-	for (i = 0; i < nelems; i++, sg++)
+	struct scatterlist *sg;
+
+	for_each_sg(sglist, sg, nelems, i)
 		consistent_sync(sg_virt(sg), sg->length, dir);
 }
 
 static inline void
-dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems,
-		 enum dma_data_direction dir)
+dma_sync_sg_for_device(struct device *dev, struct scatterlist *sglist,
+		       int nelems, enum dma_data_direction dir)
 {
 	int i;
-	for (i = 0; i < nelems; i++, sg++)
+	struct scatterlist *sg;
+
+	for_each_sg(sglist, sg, nelems, i)
 		consistent_sync(sg_virt(sg), sg->length, dir);
 }
 static inline int

arch/xtensa/include/asm/mm-arch-hooks.h

+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_XTENSA_MM_ARCH_HOOKS_H
+#define _ASM_XTENSA_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_XTENSA_MM_ARCH_HOOKS_H */

drivers/staging/android/lowmemorykiller.c

@@ -165,7 +165,7 @@ static unsigned long lowmem_scan(struct shrinker *s, struct shrink_control *sc)
 		 * infrastructure. There is no real reason why the selected
 		 * task should have access to the memory reserves.
 		 */
-		mark_tsk_oom_victim(selected);
+		mark_oom_victim(selected);
 		send_sig(SIGKILL, selected, 0);
 		rem += selected_tasksize;
 	}

drivers/tty/sysrq.c

@@ -353,9 +353,11 @@ static struct sysrq_key_op sysrq_term_op = {
 
 static void moom_callback(struct work_struct *ignored)
 {
+	mutex_lock(&oom_lock);
 	if (!out_of_memory(node_zonelist(first_memory_node, GFP_KERNEL),
 			   GFP_KERNEL, 0, NULL, true))
 		pr_info("OOM request ignored because killer is disabled\n");
+	mutex_unlock(&oom_lock);
 }
 
 static DECLARE_WORK(moom_work, moom_callback);

drivers/xen/tmem.c

@@ -381,15 +381,9 @@ static int __init xen_tmem_init(void)
 #ifdef CONFIG_FRONTSWAP
 	if (tmem_enabled && frontswap) {
 		char *s = "";
-		struct frontswap_ops *old_ops;
 
 		tmem_frontswap_poolid = -1;
-		old_ops = frontswap_register_ops(&tmem_frontswap_ops);
-		if (IS_ERR(old_ops) || old_ops) {
-			if (IS_ERR(old_ops))
-				return PTR_ERR(old_ops);
-			s = " (WARNING: frontswap_ops overridden)";
-		}
+		frontswap_register_ops(&tmem_frontswap_ops);
 		pr_info("frontswap enabled, RAM provided by Xen Transcendent Memory%s\n",
 			s);
 	}

fs/configfs/item.c

@@ -47,12 +47,11 @@ static void config_item_release(struct kref *kref);
  *	config_item_init - initialize item.
  *	@item:	item in question.
  */
-void config_item_init(struct config_item *item)
+static void config_item_init(struct config_item *item)
 {
 	kref_init(&item->ci_kref);
 	INIT_LIST_HEAD(&item->ci_entry);
 }
-EXPORT_SYMBOL(config_item_init);
 
 /**
  *	config_item_set_name - Set the name of an item

fs/hugetlbfs/inode.c

@@ -130,7 +130,6 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 		goto out;
 
 	ret = 0;
-	hugetlb_prefault_arch_hook(vma->vm_mm);
 	if (vma->vm_flags & VM_WRITE && inode->i_size < len)
 		inode->i_size = len;
 out:

fs/ntfs/file.c

@@ -525,7 +525,8 @@ static inline int __ntfs_grab_cache_pages(struct address_space *mapping,
 				}
 			}
 			err = add_to_page_cache_lru(*cached_page, mapping,
-					index, GFP_KERNEL);
+					index,
+					GFP_KERNEL & mapping_gfp_mask(mapping));
 			if (unlikely(err)) {
 				if (err == -EEXIST)
 					continue;

fs/ntfs/malloc.h

@@ -85,12 +85,7 @@ static inline void *ntfs_malloc_nofs_nofail(unsigned long size)
 
 static inline void ntfs_free(void *addr)
 {
-	if (!is_vmalloc_addr(addr)) {
-		kfree(addr);
-		/* free_page((unsigned long)addr); */
-		return;
-	}
-	vfree(addr);
+	kvfree(addr);
 }
 
 #endif /* _LINUX_NTFS_MALLOC_H */

fs/ocfs2/alloc.c

@@ -2925,7 +2925,8 @@ static int __ocfs2_rotate_tree_left(handle_t *handle,
 	struct ocfs2_path *right_path = NULL;
 	struct super_block *sb = ocfs2_metadata_cache_get_super(et->et_ci);
 
-	BUG_ON(!ocfs2_is_empty_extent(&(path_leaf_el(path)->l_recs[0])));
+	if (!ocfs2_is_empty_extent(&(path_leaf_el(path)->l_recs[0])))
+		return 0;
 
 	*empty_extent_path = NULL;
 
@@ -4311,13 +4312,13 @@ static int ocfs2_do_insert_extent(handle_t *handle,
 	return ret;
 }
 
-static enum ocfs2_contig_type
-ocfs2_figure_merge_contig_type(struct ocfs2_extent_tree *et,
+static int ocfs2_figure_merge_contig_type(struct ocfs2_extent_tree *et,
 			       struct ocfs2_path *path,
 			       struct ocfs2_extent_list *el, int index,
-			       struct ocfs2_extent_rec *split_rec)
+			       struct ocfs2_extent_rec *split_rec,
+			       struct ocfs2_merge_ctxt *ctxt)
 {
-	int status;
+	int status = 0;
 	enum ocfs2_contig_type ret = CONTIG_NONE;
 	u32 left_cpos, right_cpos;
 	struct ocfs2_extent_rec *rec = NULL;
@@ -4336,8 +4337,11 @@ ocfs2_figure_merge_contig_type(struct ocfs2_extent_tree *et,
 
 		if (left_cpos != 0) {
 			left_path = ocfs2_new_path_from_path(path);
-			if (!left_path)
+			if (!left_path) {
+				status = -ENOMEM;
+				mlog_errno(status);
 				goto exit;
+			}
 
 			status = ocfs2_find_path(et->et_ci, left_path,
 						 left_cpos);
@@ -4392,8 +4396,11 @@ ocfs2_figure_merge_contig_type(struct ocfs2_extent_tree *et,
 			goto free_left_path;
 
 		right_path = ocfs2_new_path_from_path(path);
-		if (!right_path)
+		if (!right_path) {
+			status = -ENOMEM;
+			mlog_errno(status);
 			goto free_left_path;
+		}
 
 		status = ocfs2_find_path(et->et_ci, right_path, right_cpos);
 		if (status)
@@ -4433,7 +4440,10 @@ ocfs2_figure_merge_contig_type(struct ocfs2_extent_tree *et,
 free_left_path:
 	ocfs2_free_path(left_path);
 exit:
-	return ret;
+	if (status == 0)
+		ctxt->c_contig_type = ret;
+
+	return status;
 }
 
 static void ocfs2_figure_contig_type(struct ocfs2_extent_tree *et,
@@ -5039,9 +5049,14 @@ int ocfs2_split_extent(handle_t *handle,
 		goto out;
 	}
 
-	ctxt.c_contig_type = ocfs2_figure_merge_contig_type(et, path, el,
-							    split_index,
-							    split_rec);
+	ret = ocfs2_figure_merge_contig_type(et, path, el,
+					     split_index,
+					     split_rec,
+					     &ctxt);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
 
 	/*
 	 * The core merge / split code wants to know how much room is

fs/ocfs2/aops.c

@@ -523,7 +523,7 @@ static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
 	unsigned char blocksize_bits = inode->i_sb->s_blocksize_bits;
 	unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits;
 	unsigned long len = bh_result->b_size;
-	unsigned int clusters_to_alloc = 0;
+	unsigned int clusters_to_alloc = 0, contig_clusters = 0;
 
 	cpos = ocfs2_blocks_to_clusters(inode->i_sb, iblock);
 
@@ -560,8 +560,10 @@ static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
 		/* fill hole, allocate blocks can't be larger than the size
 		 * of the hole */
 		clusters_to_alloc = ocfs2_clusters_for_bytes(inode->i_sb, len);
-		if (clusters_to_alloc > contig_blocks)
-			clusters_to_alloc = contig_blocks;
+		contig_clusters = ocfs2_clusters_for_blocks(inode->i_sb,
+				contig_blocks);
+		if (clusters_to_alloc > contig_clusters)
+			clusters_to_alloc = contig_clusters;
 
 		/* allocate extent and insert them into the extent tree */
 		ret = ocfs2_extend_allocation(inode, cpos,
@@ -619,9 +621,6 @@ static void ocfs2_dio_end_io(struct kiocb *iocb,
 	/* this io's submitter should not have unlocked this before we could */
 	BUG_ON(!ocfs2_iocb_is_rw_locked(iocb));
 
-	if (ocfs2_iocb_is_sem_locked(iocb))
-		ocfs2_iocb_clear_sem_locked(iocb);
-
 	if (ocfs2_iocb_is_unaligned_aio(iocb)) {
 		ocfs2_iocb_clear_unaligned_aio(iocb);
 
@@ -925,13 +924,23 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
 		int update_isize = written > 0 ? 1 : 0;
 		loff_t end = update_isize ? offset + written : 0;
 
-		tmp_ret = ocfs2_del_inode_from_orphan(osb, inode,
+		tmp_ret = ocfs2_inode_lock(inode, &di_bh, 1);
+		if (tmp_ret < 0) {
+			ret = tmp_ret;
+			mlog_errno(ret);
+			goto out;
+		}
+
+		tmp_ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh,
 				update_isize, end);
 		if (tmp_ret < 0) {
 			ret = tmp_ret;
+			mlog_errno(ret);
 			goto out;
 		}
 
+		ocfs2_inode_unlock(inode, 1);
+
 		tmp_ret = jbd2_journal_force_commit(journal);
 		if (tmp_ret < 0) {
 			ret = tmp_ret;

fs/ocfs2/aops.h

@@ -79,7 +79,6 @@ static inline void ocfs2_iocb_set_rw_locked(struct kiocb *iocb, int level)
 enum ocfs2_iocb_lock_bits {
 	OCFS2_IOCB_RW_LOCK = 0,
 	OCFS2_IOCB_RW_LOCK_LEVEL,
-	OCFS2_IOCB_SEM,
 	OCFS2_IOCB_UNALIGNED_IO,
 	OCFS2_IOCB_NUM_LOCKS
 };
@@ -88,12 +87,6 @@ enum ocfs2_iocb_lock_bits {
 	clear_bit(OCFS2_IOCB_RW_LOCK, (unsigned long *)&iocb->private)
 #define ocfs2_iocb_rw_locked_level(iocb) \
 	test_bit(OCFS2_IOCB_RW_LOCK_LEVEL, (unsigned long *)&iocb->private)
-#define ocfs2_iocb_set_sem_locked(iocb) \
-	set_bit(OCFS2_IOCB_SEM, (unsigned long *)&iocb->private)
-#define ocfs2_iocb_clear_sem_locked(iocb) \
-	clear_bit(OCFS2_IOCB_SEM, (unsigned long *)&iocb->private)
-#define ocfs2_iocb_is_sem_locked(iocb) \
-	test_bit(OCFS2_IOCB_SEM, (unsigned long *)&iocb->private)
 
 #define ocfs2_iocb_set_unaligned_aio(iocb) \
 	set_bit(OCFS2_IOCB_UNALIGNED_IO, (unsigned long *)&iocb->private)

fs/ocfs2/cluster/masklog.c

@@ -64,6 +64,40 @@ static ssize_t mlog_mask_store(u64 mask, const char *buf, size_t count)
 	return count;
 }
 
+void __mlog_printk(const u64 *mask, const char *func, int line,
+		   const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+	const char *level;
+	const char *prefix = "";
+
+	if (!__mlog_test_u64(*mask, mlog_and_bits) ||
+	    __mlog_test_u64(*mask, mlog_not_bits))
+		return;
+
+	if (*mask & ML_ERROR) {
+		level = KERN_ERR;
+		prefix = "ERROR: ";
+	} else if (*mask & ML_NOTICE) {
+		level = KERN_NOTICE;
+	} else {
+		level = KERN_INFO;
+	}
+
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	printk("%s(%s,%u,%u):%s:%d %s%pV",
+	       level, current->comm, task_pid_nr(current),
+	       raw_smp_processor_id(), func, line, prefix, &vaf);
+
+	va_end(args);
+}
+EXPORT_SYMBOL_GPL(__mlog_printk);
+
 struct mlog_attribute {
 	struct attribute attr;
 	u64 mask;

fs/ocfs2/cluster/masklog.h

@@ -162,38 +162,20 @@ extern struct mlog_bits mlog_and_bits, mlog_not_bits;
 
 #endif
 
-/*
- * smp_processor_id() "helpfully" screams when called outside preemptible
- * regions in current kernels.  sles doesn't have the variants that don't
- * scream.  just do this instead of trying to guess which we're building
- * against.. *sigh*.
- */
-#define __mlog_cpu_guess ({		\
-	unsigned long _cpu = get_cpu();	\
-	put_cpu();			\
-	_cpu;				\
-})
+__printf(4, 5)
+void __mlog_printk(const u64 *m, const char *func, int line,
+		   const char *fmt, ...);
 
-/* In the following two macros, the whitespace after the ',' just
- * before ##args is intentional. Otherwise, gcc 2.95 will eat the
- * previous token if args expands to nothing.
+/*
+ * Testing before the __mlog_printk call lets the compiler eliminate the
+ * call completely when (m & ML_ALLOWED_BITS) is 0.
  */
-#define __mlog_printk(level, fmt, args...)				\
-	printk(level "(%s,%u,%lu):%s:%d " fmt, current->comm,		\
-	       task_pid_nr(current), __mlog_cpu_guess,			\
-	       __PRETTY_FUNCTION__, __LINE__ , ##args)
-
-#define mlog(mask, fmt, args...) do {					\
-	u64 __m = MLOG_MASK_PREFIX | (mask);				\
-	if ((__m & ML_ALLOWED_BITS) &&					\
-	    __mlog_test_u64(__m, mlog_and_bits) &&			\
-	    !__mlog_test_u64(__m, mlog_not_bits)) {			\
-		if (__m & ML_ERROR)					\
-			__mlog_printk(KERN_ERR, "ERROR: "fmt , ##args);	\
-		else if (__m & ML_NOTICE)				\
-			__mlog_printk(KERN_NOTICE, fmt , ##args);	\
-		else __mlog_printk(KERN_INFO, fmt , ##args);		\
-	}								\
+#define mlog(mask, fmt, ...)						\
+do {									\
+	u64 _m = MLOG_MASK_PREFIX | (mask);				\
+	if (_m & ML_ALLOWED_BITS)					\
+		__mlog_printk(&_m, __func__, __LINE__, fmt,		\
+			      ##__VA_ARGS__);				\
 } while (0)
 
 #define mlog_errno(st) ({						\

fs/ocfs2/cluster/tcp.c

@@ -2204,7 +2204,7 @@ int o2net_init(void)
 	kfree(o2net_hand);
 	kfree(o2net_keep_req);
 	kfree(o2net_keep_resp);
-
+	o2net_debugfs_exit();
 	o2quo_exit();
 	return -ENOMEM;
 }

fs/ocfs2/dir.c

@@ -1617,7 +1617,7 @@ int __ocfs2_add_entry(handle_t *handle,
 	struct ocfs2_dir_entry *de, *de1;
 	struct ocfs2_dinode *di = (struct ocfs2_dinode *)parent_fe_bh->b_data;
 	struct super_block *sb = dir->i_sb;
-	int retval, status;
+	int retval;
 	unsigned int size = sb->s_blocksize;
 	struct buffer_head *insert_bh = lookup->dl_leaf_bh;
 	char *data_start = insert_bh->b_data;
@@ -1695,25 +1695,25 @@ int __ocfs2_add_entry(handle_t *handle,
 			}
 
 			if (insert_bh == parent_fe_bh)
-				status = ocfs2_journal_access_di(handle,
+				retval = ocfs2_journal_access_di(handle,
 								 INODE_CACHE(dir),
 								 insert_bh,
 								 OCFS2_JOURNAL_ACCESS_WRITE);
 			else {
-				status = ocfs2_journal_access_db(handle,
+				retval = ocfs2_journal_access_db(handle,
 								 INODE_CACHE(dir),
 								 insert_bh,
 					      OCFS2_JOURNAL_ACCESS_WRITE);
 
-				if (ocfs2_dir_indexed(dir)) {
-					status = ocfs2_dx_dir_insert(dir,
+				if (!retval && ocfs2_dir_indexed(dir))
+					retval = ocfs2_dx_dir_insert(dir,
 								handle,
 								lookup);
-					if (status) {
-						mlog_errno(status);
-						goto bail;
-					}
-				}
+			}
+
+			if (retval) {
+				mlog_errno(retval);
+				goto bail;
 			}
 
 			/* By now the buffer is marked for journaling */
@@ -3543,13 +3543,10 @@ static void dx_leaf_sort_swap(void *a, void *b, int size)
 {
 	struct ocfs2_dx_entry *entry1 = a;
 	struct ocfs2_dx_entry *entry2 = b;
-	struct ocfs2_dx_entry tmp;
 
 	BUG_ON(size != sizeof(*entry1));
 
-	tmp = *entry1;
-	*entry1 = *entry2;
-	*entry2 = tmp;
+	swap(*entry1, *entry2);
 }
 
 static int ocfs2_dx_leaf_same_major(struct ocfs2_dx_leaf *dx_leaf)

fs/ocfs2/dlm/dlmcommon.h

@@ -1014,7 +1014,6 @@ void dlm_move_lockres_to_recovery_list(struct dlm_ctxt *dlm,
 
 /* will exit holding res->spinlock, but may drop in function */
 void __dlm_wait_on_lockres_flags(struct dlm_lock_resource *res, int flags);
-void __dlm_wait_on_lockres_flags_set(struct dlm_lock_resource *res, int flags);
 
 /* will exit holding res->spinlock, but may drop in function */
 static inline void __dlm_wait_on_lockres(struct dlm_lock_resource *res)

fs/ocfs2/file.c

@@ -2250,7 +2250,7 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
 static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
 				    struct iov_iter *from)
 {
-	int direct_io, appending, rw_level, have_alloc_sem  = 0;
+	int direct_io, appending, rw_level;
 	int can_do_direct, has_refcount = 0;
 	ssize_t written = 0;
 	ssize_t ret;
@@ -2279,16 +2279,7 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
 
 	mutex_lock(&inode->i_mutex);
 
-	ocfs2_iocb_clear_sem_locked(iocb);
-
 relock:
-	/* to match setattr's i_mutex -> rw_lock ordering */
-	if (direct_io) {
-		have_alloc_sem = 1;
-		/* communicate with ocfs2_dio_end_io */
-		ocfs2_iocb_set_sem_locked(iocb);
-	}
-
 	/*
 	 * Concurrent O_DIRECT writes are allowed with
 	 * mount_option "coherency=buffered".
@@ -2298,7 +2289,7 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
 	ret = ocfs2_rw_lock(inode, rw_level);
 	if (ret < 0) {
 		mlog_errno(ret);
-		goto out_sems;
+		goto out_mutex;
 	}
 
 	/*
@@ -2347,7 +2338,6 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
 	if (direct_io && !can_do_direct) {
 		ocfs2_rw_unlock(inode, rw_level);
 
-		have_alloc_sem = 0;
 		rw_level = -1;
 
 		direct_io = 0;
@@ -2416,7 +2406,6 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
 	 */
 	if ((ret == -EIOCBQUEUED) || (!ocfs2_iocb_is_rw_locked(iocb))) {
 		rw_level = -1;
-		have_alloc_sem = 0;
 		unaligned_dio = 0;
 	}
 
@@ -2429,10 +2418,7 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
 	if (rw_level != -1)
 		ocfs2_rw_unlock(inode, rw_level);
 
-out_sems:
-	if (have_alloc_sem)
-		ocfs2_iocb_clear_sem_locked(iocb);
-
+out_mutex:
 	mutex_unlock(&inode->i_mutex);
 
 	if (written)
@@ -2473,7 +2459,7 @@ static ssize_t ocfs2_file_splice_read(struct file *in,
 static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
 				   struct iov_iter *to)
 {
-	int ret = 0, rw_level = -1, have_alloc_sem = 0, lock_level = 0;
+	int ret = 0, rw_level = -1, lock_level = 0;
 	struct file *filp = iocb->ki_filp;
 	struct inode *inode = file_inode(filp);
 
@@ -2490,16 +2476,11 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
 		goto bail;
 	}
 
-	ocfs2_iocb_clear_sem_locked(iocb);
-
 	/*
 	 * buffered reads protect themselves in ->readpage().  O_DIRECT reads
 	 * need locks to protect pending reads from racing with truncate.
 	 */
 	if (iocb->ki_flags & IOCB_DIRECT) {
-		have_alloc_sem = 1;
-		ocfs2_iocb_set_sem_locked(iocb);
-
 		ret = ocfs2_rw_lock(inode, 0);
 		if (ret < 0) {
 			mlog_errno(ret);
@@ -2535,13 +2516,9 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
 	/* see ocfs2_file_write_iter */
 	if (ret == -EIOCBQUEUED || !ocfs2_iocb_is_rw_locked(iocb)) {
 		rw_level = -1;
-		have_alloc_sem = 0;
 	}
 
 bail:
-	if (have_alloc_sem)
-		ocfs2_iocb_clear_sem_locked(iocb);
-
 	if (rw_level != -1)
 		ocfs2_rw_unlock(inode, rw_level);
 

fs/ocfs2/journal.c

@@ -108,7 +108,7 @@ struct ocfs2_replay_map {
 	unsigned char rm_replay_slots[0];
 };
 
-void ocfs2_replay_map_set_state(struct ocfs2_super *osb, int state)
+static void ocfs2_replay_map_set_state(struct ocfs2_super *osb, int state)
 {
 	if (!osb->replay_map)
 		return;
@@ -153,7 +153,7 @@ int ocfs2_compute_replay_slots(struct ocfs2_super *osb)
 	return 0;
 }
 
-void ocfs2_queue_replay_slots(struct ocfs2_super *osb,
+static void ocfs2_queue_replay_slots(struct ocfs2_super *osb,
 		enum ocfs2_orphan_reco_type orphan_reco_type)
 {
 	struct ocfs2_replay_map *replay_map = osb->replay_map;
@@ -173,7 +173,7 @@ void ocfs2_queue_replay_slots(struct ocfs2_super *osb,
 	replay_map->rm_state = REPLAY_DONE;
 }
 
-void ocfs2_free_replay_slots(struct ocfs2_super *osb)
+static void ocfs2_free_replay_slots(struct ocfs2_super *osb)
 {
 	struct ocfs2_replay_map *replay_map = osb->replay_map;
 
@@ -571,9 +571,7 @@ static void ocfs2_abort_trigger(struct jbd2_buffer_trigger_type *triggers,
 	     (unsigned long)bh,
 	     (unsigned long long)bh->b_blocknr);
 
-	/* We aren't guaranteed to have the superblock here - but if we
-	 * don't, it'll just crash. */
-	ocfs2_error(bh->b_assoc_map->host->i_sb,
+	ocfs2_error(bh->b_bdev->bd_super,
 		    "JBD2 has aborted our journal, ocfs2 cannot continue\n");
 }
 
@@ -775,7 +773,20 @@ void ocfs2_journal_dirty(handle_t *handle, struct buffer_head *bh)
 	trace_ocfs2_journal_dirty((unsigned long long)bh->b_blocknr);
 
 	status = jbd2_journal_dirty_metadata(handle, bh);
-	BUG_ON(status);
+	if (status) {
+		mlog_errno(status);
+		if (!is_handle_aborted(handle)) {
+			journal_t *journal = handle->h_transaction->t_journal;
+			struct super_block *sb = bh->b_bdev->bd_super;
+
+			mlog(ML_ERROR, "jbd2_journal_dirty_metadata failed. "
+					"Aborting transaction and journal.\n");
+			handle->h_err = status;
+			jbd2_journal_abort_handle(handle);
+			jbd2_journal_abort(journal, status);
+			ocfs2_abort(sb, "Journal already aborted.\n");
+		}
+	}
 }
 
 #define OCFS2_DEFAULT_COMMIT_INTERVAL	(HZ * JBD2_DEFAULT_MAX_COMMIT_AGE)
@@ -1884,7 +1895,7 @@ static inline unsigned long ocfs2_orphan_scan_timeout(void)
  * hasn't happened.  The node queues a scan and increments the
  * sequence number in the LVB.
  */
-void ocfs2_queue_orphan_scan(struct ocfs2_super *osb)
+static void ocfs2_queue_orphan_scan(struct ocfs2_super *osb)
 {
 	struct ocfs2_orphan_scan *os;
 	int status, i;
@@ -1933,7 +1944,7 @@ void ocfs2_queue_orphan_scan(struct ocfs2_super *osb)
 }
 
 /* Worker task that gets fired every ORPHAN_SCAN_SCHEDULE_TIMEOUT millsec */
-void ocfs2_orphan_scan_work(struct work_struct *work)
+static void ocfs2_orphan_scan_work(struct work_struct *work)
 {
 	struct ocfs2_orphan_scan *os;
 	struct ocfs2_super *osb;
@@ -2137,6 +2148,8 @@ static int ocfs2_recover_orphans(struct ocfs2_super *osb,
 	struct inode *inode = NULL;
 	struct inode *iter;
 	struct ocfs2_inode_info *oi;
+	struct buffer_head *di_bh = NULL;
+	struct ocfs2_dinode *di = NULL;
 
 	trace_ocfs2_recover_orphans(slot);
 
@@ -2157,16 +2170,22 @@ static int ocfs2_recover_orphans(struct ocfs2_super *osb,
 		iter = oi->ip_next_orphan;
 		oi->ip_next_orphan = NULL;
 
+		ret = ocfs2_rw_lock(inode, 1);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto next;
+		}
 		/*
 		 * We need to take and drop the inode lock to
 		 * force read inode from disk.
 		 */
-		ret = ocfs2_inode_lock(inode, NULL, 0);
+		ret = ocfs2_inode_lock(inode, &di_bh, 1);
 		if (ret) {
 			mlog_errno(ret);
-			goto next;
+			goto unlock_rw;
 		}
-		ocfs2_inode_unlock(inode, 0);
+
+		di = (struct ocfs2_dinode *)di_bh->b_data;
 
 		if (inode->i_nlink == 0) {
 			spin_lock(&oi->ip_lock);
@@ -2174,43 +2193,30 @@ static int ocfs2_recover_orphans(struct ocfs2_super *osb,
 			 * ocfs2_delete_inode. */
 			oi->ip_flags |= OCFS2_INODE_MAYBE_ORPHANED;
 			spin_unlock(&oi->ip_lock);
-		} else if (orphan_reco_type == ORPHAN_NEED_TRUNCATE) {
-			struct buffer_head *di_bh = NULL;
-
-			ret = ocfs2_rw_lock(inode, 1);
-			if (ret) {
-				mlog_errno(ret);
-				goto next;
-			}
-
-			ret = ocfs2_inode_lock(inode, &di_bh, 1);
-			if (ret < 0) {
-				ocfs2_rw_unlock(inode, 1);
-				mlog_errno(ret);
-				goto next;
-			}
-
+		} else if ((orphan_reco_type == ORPHAN_NEED_TRUNCATE) &&
+				(di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL))) {
 			ret = ocfs2_truncate_file(inode, di_bh,
 					i_size_read(inode));
-			ocfs2_inode_unlock(inode, 1);
-			ocfs2_rw_unlock(inode, 1);
-			brelse(di_bh);
 			if (ret < 0) {
 				if (ret != -ENOSPC)
 					mlog_errno(ret);
-				goto next;
+				goto unlock_inode;
 			}
 
-			ret = ocfs2_del_inode_from_orphan(osb, inode, 0, 0);
+			ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh, 0, 0);
 			if (ret)
 				mlog_errno(ret);
 
 			wake_up(&OCFS2_I(inode)->append_dio_wq);
 		} /* else if ORPHAN_NO_NEED_TRUNCATE, do nothing */
-
+unlock_inode:
+		ocfs2_inode_unlock(inode, 1);
+unlock_rw:
+		ocfs2_rw_unlock(inode, 1);
 next:
 		iput(inode);
-
+		brelse(di_bh);
+		di_bh = NULL;
 		inode = iter;
 	}
 

fs/ocfs2/namei.c

@@ -1116,8 +1116,6 @@ static int ocfs2_double_lock(struct ocfs2_super *osb,
 	int inode1_is_ancestor, inode2_is_ancestor;
 	struct ocfs2_inode_info *oi1 = OCFS2_I(inode1);
 	struct ocfs2_inode_info *oi2 = OCFS2_I(inode2);
-	struct buffer_head **tmpbh;
-	struct inode *tmpinode;
 
 	trace_ocfs2_double_lock((unsigned long long)oi1->ip_blkno,
 				(unsigned long long)oi2->ip_blkno);
@@ -1148,13 +1146,8 @@ static int ocfs2_double_lock(struct ocfs2_super *osb,
 				(oi1->ip_blkno < oi2->ip_blkno &&
 				inode2_is_ancestor == 0)) {
 			/* switch id1 and id2 around */
-			tmpbh = bh2;
-			bh2 = bh1;
-			bh1 = tmpbh;
-
-			tmpinode = inode2;
-			inode2 = inode1;
-			inode1 = tmpinode;
+			swap(bh2, bh1);
+			swap(inode2, inode1);
 		}
 		/* lock id2 */
 		status = ocfs2_inode_lock_nested(inode2, bh2, 1,
@@ -2670,30 +2663,22 @@ int ocfs2_add_inode_to_orphan(struct ocfs2_super *osb,
 }
 
 int ocfs2_del_inode_from_orphan(struct ocfs2_super *osb,
-		struct inode *inode, int update_isize,
-		loff_t end)
+		struct inode *inode, struct buffer_head *di_bh,
+		int update_isize, loff_t end)
 {
 	struct inode *orphan_dir_inode = NULL;
 	struct buffer_head *orphan_dir_bh = NULL;
-	struct buffer_head *di_bh = NULL;
-	struct ocfs2_dinode *di = NULL;
+	struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
 	handle_t *handle = NULL;
 	int status = 0;
 
-	status = ocfs2_inode_lock(inode, &di_bh, 1);
-	if (status < 0) {
-		mlog_errno(status);
-		goto bail;
-	}
-	di = (struct ocfs2_dinode *) di_bh->b_data;
-
 	orphan_dir_inode = ocfs2_get_system_file_inode(osb,
 			ORPHAN_DIR_SYSTEM_INODE,
 			le16_to_cpu(di->i_dio_orphaned_slot));
 	if (!orphan_dir_inode) {
 		status = -ENOENT;
 		mlog_errno(status);
-		goto bail_unlock_inode;
+		goto bail;
 	}
 
 	mutex_lock(&orphan_dir_inode->i_mutex);
@@ -2702,7 +2687,7 @@ int ocfs2_del_inode_from_orphan(struct ocfs2_super *osb,
 		mutex_unlock(&orphan_dir_inode->i_mutex);
 		iput(orphan_dir_inode);
 		mlog_errno(status);
-		goto bail_unlock_inode;
+		goto bail;
 	}
 
 	handle = ocfs2_start_trans(osb,
@@ -2749,10 +2734,6 @@ int ocfs2_del_inode_from_orphan(struct ocfs2_super *osb,
 	brelse(orphan_dir_bh);
 	iput(orphan_dir_inode);
 
-bail_unlock_inode:
-	ocfs2_inode_unlock(inode, 1);
-	brelse(di_bh);
-
 bail:
 	return status;
 }

fs/ocfs2/namei.h

@@ -42,8 +42,8 @@ int ocfs2_create_inode_in_orphan(struct inode *dir,
 int ocfs2_add_inode_to_orphan(struct ocfs2_super *osb,
 		struct inode *inode);
 int ocfs2_del_inode_from_orphan(struct ocfs2_super *osb,
-		struct inode *inode, int update_isize,
-		loff_t end);
+		struct inode *inode, struct buffer_head *di_bh,
+		int update_isize, loff_t end);
 int ocfs2_mv_orphaned_inode_to_new(struct inode *dir,
 				   struct inode *new_inode,
 				   struct dentry *new_dentry);

fs/ocfs2/ocfs2.h

@@ -717,6 +717,16 @@ static inline u64 ocfs2_clusters_to_blocks(struct super_block *sb,
 	return (u64)clusters << c_to_b_bits;
 }
 
+static inline u32 ocfs2_clusters_for_blocks(struct super_block *sb,
+		u64 blocks)
+{
+	int b_to_c_bits = OCFS2_SB(sb)->s_clustersize_bits -
+			sb->s_blocksize_bits;
+
+	blocks += (1 << b_to_c_bits) - 1;
+	return (u32)(blocks >> b_to_c_bits);
+}
+
 static inline u32 ocfs2_blocks_to_clusters(struct super_block *sb,
 					   u64 blocks)
 {

fs/ocfs2/refcounttree.c

@@ -1406,11 +1406,9 @@ static int cmp_refcount_rec_by_cpos(const void *a, const void *b)
 
 static void swap_refcount_rec(void *a, void *b, int size)
 {
-	struct ocfs2_refcount_rec *l = a, *r = b, tmp;
+	struct ocfs2_refcount_rec *l = a, *r = b;
 
-	tmp = *l;
-	*l = *r;
-	*r = tmp;
+	swap(*l, *r);
 }
 
 /*

fs/ocfs2/xattr.c

@@ -7271,7 +7271,7 @@ static int ocfs2_xattr_security_set(struct dentry *dentry, const char *name,
 			       name, value, size, flags);
 }
 
-int ocfs2_initxattrs(struct inode *inode, const struct xattr *xattr_array,
+static int ocfs2_initxattrs(struct inode *inode, const struct xattr *xattr_array,
 		     void *fs_info)
 {
 	const struct xattr *xattr;

fs/proc/array.c

@@ -126,6 +126,14 @@ static inline const char *get_task_state(struct task_struct *tsk)
 {
 	unsigned int state = (tsk->state | tsk->exit_state) & TASK_REPORT;
 
+	/*
+	 * Parked tasks do not run; they sit in __kthread_parkme().
+	 * Without this check, we would report them as running, which is
+	 * clearly wrong, so we report them as sleeping instead.
+	 */
+	if (tsk->state == TASK_PARKED)
+		state = TASK_INTERRUPTIBLE;
+
 	BUILD_BUG_ON(1 + ilog2(TASK_REPORT) != ARRAY_SIZE(task_state_array)-1);
 
 	return task_state_array[fls(state)];

fs/splice.c

@@ -360,7 +360,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos,
 				break;
 
 			error = add_to_page_cache_lru(page, mapping, index,
-						GFP_KERNEL);
+					GFP_KERNEL & mapping_gfp_mask(mapping));
 			if (unlikely(error)) {
 				page_cache_release(page);
 				if (error == -EEXIST)

include/asm-generic/pgtable.h

@@ -96,11 +96,11 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 }
 #endif
 
-#ifndef __HAVE_ARCH_PMDP_GET_AND_CLEAR
+#ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
-				       unsigned long address,
-				       pmd_t *pmdp)
+static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
+					    unsigned long address,
+					    pmd_t *pmdp)
 {
 	pmd_t pmd = *pmdp;
 	pmd_clear(pmdp);
@@ -109,13 +109,13 @@ static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif
 
-#ifndef __HAVE_ARCH_PMDP_GET_AND_CLEAR_FULL
+#ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR_FULL
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static inline pmd_t pmdp_get_and_clear_full(struct mm_struct *mm,
+static inline pmd_t pmdp_huge_get_and_clear_full(struct mm_struct *mm,
 					    unsigned long address, pmd_t *pmdp,
 					    int full)
 {
-	return pmdp_get_and_clear(mm, address, pmdp);
+	return pmdp_huge_get_and_clear(mm, address, pmdp);
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif
@@ -152,8 +152,8 @@ extern pte_t ptep_clear_flush(struct vm_area_struct *vma,
 			      pte_t *ptep);
 #endif
 
-#ifndef __HAVE_ARCH_PMDP_CLEAR_FLUSH
-extern pmd_t pmdp_clear_flush(struct vm_area_struct *vma,
+#ifndef __HAVE_ARCH_PMDP_HUGE_CLEAR_FLUSH
+extern pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma,
 			      unsigned long address,
 			      pmd_t *pmdp);
 #endif
@@ -189,6 +189,22 @@ extern void pmdp_splitting_flush(struct vm_area_struct *vma,
 				 unsigned long address, pmd_t *pmdp);
 #endif
 
+#ifndef pmdp_collapse_flush
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
+				 unsigned long address, pmd_t *pmdp);
+#else
+static inline pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
+					unsigned long address,
+					pmd_t *pmdp)
+{
+	BUILD_BUG();
+	return *pmdp;
+}
+#define pmdp_collapse_flush pmdp_collapse_flush
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif
+
 #ifndef __HAVE_ARCH_PGTABLE_DEPOSIT
 extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
 				       pgtable_t pgtable);

include/linux/bootmem.h

@@ -357,12 +357,12 @@ extern void *alloc_large_system_hash(const char *tablename,
 /* Only NUMA needs hash distribution. 64bit NUMA architectures have
  * sufficient vmalloc space.
  */
-#if defined(CONFIG_NUMA) && defined(CONFIG_64BIT)
-#define HASHDIST_DEFAULT 1
+#ifdef CONFIG_NUMA
+#define HASHDIST_DEFAULT IS_ENABLED(CONFIG_64BIT)
+extern int hashdist;		/* Distribute hashes across NUMA nodes? */
 #else
-#define HASHDIST_DEFAULT 0
+#define hashdist (0)
 #endif
-extern int hashdist;		/* Distribute hashes across NUMA nodes? */
 
 
 #endif /* _LINUX_BOOTMEM_H */