Merge branch 'akpm' (patches from Andrew)

Merge first patchbomb from Andrew Morton:

 - arch/sh updates

 - ocfs2 updates

 - kernel/watchdog feature

 - about half of mm/

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (122 commits)
  Documentation: update arch list in the 'memtest' entry
  Kconfig: memtest: update number of test patterns up to 17
  arm: add support for memtest
  arm64: add support for memtest
  memtest: use phys_addr_t for physical addresses
  mm: move memtest under mm
  mm, hugetlb: abort __get_user_pages if current has been oom killed
  mm, mempool: do not allow atomic resizing
  memcg: print cgroup information when system panics due to panic_on_oom
  mm: numa: remove migrate_ratelimited
  mm: fold arch_randomize_brk into ARCH_HAS_ELF_RANDOMIZE
  mm: split ET_DYN ASLR from mmap ASLR
  s390: redefine randomize_et_dyn for ELF_ET_DYN_BASE
  mm: expose arch_mmap_rnd when available
  s390: standardize mmap_rnd() usage
  powerpc: standardize mmap_rnd() usage
  mips: extract logic for mmap_rnd()
  arm64: standardize mmap_rnd() usage
  x86: standardize mmap_rnd() usage
  arm: factor out mmap ASLR into mmap_rnd
  ...

Documentation/cma/debugfs.txt

@@ -0,0 +1,21 @@
+The CMA debugfs interface is useful to retrieve basic information out of the
+different CMA areas and to test allocation/release in each of the areas.
+
+Each CMA zone represents a directory under <debugfs>/cma/, indexed by the
+kernel's CMA index. So the first CMA zone would be:
+
+	<debugfs>/cma/cma-0
+
+The structure of the files created under that directory is as follows:
+
+ - [RO] base_pfn: The base PFN (Page Frame Number) of the zone.
+ - [RO] count: Amount of memory in the CMA area.
+ - [RO] order_per_bit: Order of pages represented by one bit.
+ - [RO] bitmap: The bitmap of page states in the zone.
+ - [WO] alloc: Allocate N pages from that CMA area. For example:
+
+	echo 5 > <debugfs>/cma/cma-2/alloc
+
+would try to allocate 5 pages from the cma-2 area.
+
+ - [WO] free: Free N pages from that CMA area, similar to the above.

Documentation/kernel-parameters.txt

@@ -1989,7 +1989,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			seconds.  Use this parameter to check at some
 			other rate.  0 disables periodic checking.
 
-	memtest=	[KNL,X86] Enable memtest
+	memtest=	[KNL,X86,ARM] Enable memtest
 			Format: <integer>
 			default : 0 <disable>
 			Specifies the number of memtest passes to be
@@ -2236,8 +2236,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	nmi_watchdog=	[KNL,BUGS=X86] Debugging features for SMP kernels
 			Format: [panic,][nopanic,][num]
-			Valid num: 0
+			Valid num: 0 or 1
 			0 - turn nmi_watchdog off
+			1 - turn nmi_watchdog on
 			When panic is specified, panic when an NMI watchdog
 			timeout occurs (or 'nopanic' to override the opposite
 			default).
@@ -2322,6 +2323,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			register save and restore. The kernel will only save
 			legacy floating-point registers on task switch.
 
+	nohugeiomap	[KNL,x86] Disable kernel huge I/O mappings.
+
 	noxsave		[BUGS=X86] Disables x86 extended register state save
 			and restore using xsave. The kernel will fallback to
 			enabling legacy floating-point and sse state.
@@ -2464,7 +2467,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	nousb		[USB] Disable the USB subsystem
 
-	nowatchdog	[KNL] Disable the lockup detector (NMI watchdog).
+	nowatchdog	[KNL] Disable both lockup detectors, i.e.
+                        soft-lockup and NMI watchdog (hard-lockup).
 
 	nowb		[ARM]
 

Documentation/sysctl/kernel.txt

@@ -77,12 +77,14 @@ show up in /proc/sys/kernel:
 - shmmax                      [ sysv ipc ]
 - shmmni
 - softlockup_all_cpu_backtrace
+- soft_watchdog
 - stop-a                      [ SPARC only ]
 - sysrq                       ==> Documentation/sysrq.txt
 - sysctl_writes_strict
 - tainted
 - threads-max
 - unknown_nmi_panic
+- watchdog
 - watchdog_thresh
 - version
 
@@ -417,16 +419,23 @@ successful IPC object allocation.
 
 nmi_watchdog:
 
-Enables/Disables the NMI watchdog on x86 systems. When the value is
-non-zero the NMI watchdog is enabled and will continuously test all
-online cpus to determine whether or not they are still functioning
-properly. Currently, passing "nmi_watchdog=" parameter at boot time is
-required for this function to work.
+This parameter can be used to control the NMI watchdog
+(i.e. the hard lockup detector) on x86 systems.
 
-If LAPIC NMI watchdog method is in use (nmi_watchdog=2 kernel
-parameter), the NMI watchdog shares registers with oprofile. By
-disabling the NMI watchdog, oprofile may have more registers to
-utilize.
+   0 - disable the hard lockup detector
+   1 - enable the hard lockup detector
+
+The hard lockup detector monitors each CPU for its ability to respond to
+timer interrupts. The mechanism utilizes CPU performance counter registers
+that are programmed to generate Non-Maskable Interrupts (NMIs) periodically
+while a CPU is busy. Hence, the alternative name 'NMI watchdog'.
+
+The NMI watchdog is disabled by default if the kernel is running as a guest
+in a KVM virtual machine. This default can be overridden by adding
+
+   nmi_watchdog=1
+
+to the guest kernel command line (see Documentation/kernel-parameters.txt).
 
 ==============================================================
 
@@ -816,6 +825,22 @@ NMI.
 
 ==============================================================
 
+soft_watchdog
+
+This parameter can be used to control the soft lockup detector.
+
+   0 - disable the soft lockup detector
+   1 - enable the soft lockup detector
+
+The soft lockup detector monitors CPUs for threads that are hogging the CPUs
+without rescheduling voluntarily, and thus prevent the 'watchdog/N' threads
+from running. The mechanism depends on the CPUs ability to respond to timer
+interrupts which are needed for the 'watchdog/N' threads to be woken up by
+the watchdog timer function, otherwise the NMI watchdog - if enabled - can
+detect a hard lockup condition.
+
+==============================================================
+
 tainted:
 
 Non-zero if the kernel has been tainted.  Numeric values, which
@@ -858,6 +883,25 @@ example.  If a system hangs up, try pressing the NMI switch.
 
 ==============================================================
 
+watchdog:
+
+This parameter can be used to disable or enable the soft lockup detector
+_and_ the NMI watchdog (i.e. the hard lockup detector) at the same time.
+
+   0 - disable both lockup detectors
+   1 - enable both lockup detectors
+
+The soft lockup detector and the NMI watchdog can also be disabled or
+enabled individually, using the soft_watchdog and nmi_watchdog parameters.
+If the watchdog parameter is read, for example by executing
+
+   cat /proc/sys/kernel/watchdog
+
+the output of this command (0 or 1) shows the logical OR of soft_watchdog
+and nmi_watchdog.
+
+==============================================================
+
 watchdog_thresh:
 
 This value can be used to control the frequency of hrtimer and NMI

Documentation/vm/cleancache.txt

@@ -28,9 +28,7 @@ IMPLEMENTATION OVERVIEW
 A cleancache "backend" that provides transcendent memory registers itself
 to the kernel's cleancache "frontend" by calling cleancache_register_ops,
 passing a pointer to a cleancache_ops structure with funcs set appropriately.
-Note that cleancache_register_ops returns the previous settings so that
-chaining can be performed if desired. The functions provided must conform to
-certain semantics as follows:
+The functions provided must conform to certain semantics as follows:
 
 Most important, cleancache is "ephemeral".  Pages which are copied into
 cleancache have an indefinite lifetime which is completely unknowable

Documentation/vm/unevictable-lru.txt

@@ -317,7 +317,7 @@ If the VMA passes some filtering as described in "Filtering Special Vmas"
 below, mlock_fixup() will attempt to merge the VMA with its neighbors or split
 off a subset of the VMA if the range does not cover the entire VMA.  Once the
 VMA has been merged or split or neither, mlock_fixup() will call
-__mlock_vma_pages_range() to fault in the pages via get_user_pages() and to
+populate_vma_page_range() to fault in the pages via get_user_pages() and to
 mark the pages as mlocked via mlock_vma_page().
 
 Note that the VMA being mlocked might be mapped with PROT_NONE.  In this case,
@@ -327,7 +327,7 @@ fault path or in vmscan.
 
 Also note that a page returned by get_user_pages() could be truncated or
 migrated out from under us, while we're trying to mlock it.  To detect this,
-__mlock_vma_pages_range() checks page_mapping() after acquiring the page lock.
+populate_vma_page_range() checks page_mapping() after acquiring the page lock.
 If the page is still associated with its mapping, we'll go ahead and call
 mlock_vma_page().  If the mapping is gone, we just unlock the page and move on.
 In the worst case, this will result in a page mapped in a VM_LOCKED VMA
@@ -392,7 +392,7 @@ ignored for munlock.
 
 If the VMA is VM_LOCKED, mlock_fixup() again attempts to merge or split off the
 specified range.  The range is then munlocked via the function
-__mlock_vma_pages_range() - the same function used to mlock a VMA range -
+populate_vma_page_range() - the same function used to mlock a VMA range -
 passing a flag to indicate that munlock() is being performed.
 
 Because the VMA access protections could have been changed to PROT_NONE after
@@ -402,7 +402,7 @@ get_user_pages() was enhanced to accept a flag to ignore the permissions when
 fetching the pages - all of which should be resident as a result of previous
 mlocking.
 
-For munlock(), __mlock_vma_pages_range() unlocks individual pages by calling
+For munlock(), populate_vma_page_range() unlocks individual pages by calling
 munlock_vma_page().  munlock_vma_page() unconditionally clears the PG_mlocked
 flag using TestClearPageMlocked().  As with mlock_vma_page(),
 munlock_vma_page() use the Test*PageMlocked() function to handle the case where
@@ -463,21 +463,11 @@ populate the page table.
 
 To mlock a range of memory under the unevictable/mlock infrastructure, the
 mmap() handler and task address space expansion functions call
-mlock_vma_pages_range() specifying the vma and the address range to mlock.
-mlock_vma_pages_range() filters VMAs like mlock_fixup(), as described above in
-"Filtering Special VMAs".  It will clear the VM_LOCKED flag, which will have
-already been set by the caller, in filtered VMAs.  Thus these VMA's need not be
-visited for munlock when the region is unmapped.
-
-For "normal" VMAs, mlock_vma_pages_range() calls __mlock_vma_pages_range() to
-fault/allocate the pages and mlock them.  Again, like mlock_fixup(),
-mlock_vma_pages_range() downgrades the mmap semaphore to read mode before
-attempting to fault/allocate and mlock the pages and "upgrades" the semaphore
-back to write mode before returning.
-
-The callers of mlock_vma_pages_range() will have already added the memory range
+populate_vma_page_range() specifying the vma and the address range to mlock.
+
+The callers of populate_vma_page_range() will have already added the memory range
 to be mlocked to the task's "locked_vm".  To account for filtered VMAs,
-mlock_vma_pages_range() returns the number of pages NOT mlocked.  All of the
+populate_vma_page_range() returns the number of pages NOT mlocked.  All of the
 callers then subtract a non-negative return value from the task's locked_vm.  A
 negative return value represent an error - for example, from get_user_pages()
 attempting to fault in a VMA with PROT_NONE access.  In this case, we leave the

arch/Kconfig

@@ -446,6 +446,9 @@ config HAVE_IRQ_TIME_ACCOUNTING
 config HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	bool
 
+config HAVE_ARCH_HUGE_VMAP
+	bool
+
 config HAVE_ARCH_SOFT_DIRTY
 	bool
 
@@ -484,6 +487,18 @@ config HAVE_IRQ_EXIT_ON_IRQ_STACK
 	  This spares a stack switch and improves cache usage on softirq
 	  processing.
 
+config PGTABLE_LEVELS
+	int
+	default 2
+
+config ARCH_HAS_ELF_RANDOMIZE
+	bool
+	help
+	  An architecture supports choosing randomized locations for
+	  stack, mmap, brk, and ET_DYN. Defined functions:
+	  - arch_mmap_rnd()
+	  - arch_randomize_brk()
+
 #
 # ABI hall of shame
 #

arch/alpha/Kconfig

@@ -76,6 +76,10 @@ config GENERIC_ISA_DMA
 	bool
 	default y
 
+config PGTABLE_LEVELS
+	int
+	default 3
+
 source "init/Kconfig"
 source "kernel/Kconfig.freezer"
 

arch/arm/Kconfig

@@ -1,8 +1,8 @@
 config ARM
 	bool
 	default y
-	select ARCH_BINFMT_ELF_RANDOMIZE_PIE
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
+	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAVE_CUSTOM_GPIO_H
 	select ARCH_HAS_GCOV_PROFILE_ALL
@@ -286,6 +286,11 @@ config GENERIC_BUG
 	def_bool y
 	depends on BUG
 
+config PGTABLE_LEVELS
+	int
+	default 3 if ARM_LPAE
+	default 2
+
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"

arch/arm/include/asm/elf.h

@@ -125,10 +125,6 @@ int dump_task_regs(struct task_struct *t, elf_gregset_t *elfregs);
 extern void elf_set_personality(const struct elf32_hdr *);
 #define SET_PERSONALITY(ex)	elf_set_personality(&(ex))
 
-struct mm_struct;
-extern unsigned long arch_randomize_brk(struct mm_struct *mm);
-#define arch_randomize_brk arch_randomize_brk
-
 #ifdef CONFIG_MMU
 #define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
 struct linux_binprm;

arch/arm/mm/init.c

@@ -335,6 +335,9 @@ void __init bootmem_init(void)
 
 	find_limits(&min, &max_low, &max_high);
 
+	early_memtest((phys_addr_t)min << PAGE_SHIFT,
+		      (phys_addr_t)max_low << PAGE_SHIFT);
+
 	/*
 	 * Sparsemem tries to allocate bootmem in memory_present(),
 	 * so must be done after the fixed reservations

arch/arm/mm/mmap.c

@@ -169,14 +169,22 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	return addr;
 }
 
+unsigned long arch_mmap_rnd(void)
+{
+	unsigned long rnd;
+
+	/* 8 bits of randomness in 20 address space bits */
+	rnd = (unsigned long)get_random_int() % (1 << 8);
+
+	return rnd << PAGE_SHIFT;
+}
+
 void arch_pick_mmap_layout(struct mm_struct *mm)
 {
 	unsigned long random_factor = 0UL;
 
-	/* 8 bits of randomness in 20 address space bits */
-	if ((current->flags & PF_RANDOMIZE) &&
-	    !(current->personality & ADDR_NO_RANDOMIZE))
-		random_factor = (get_random_int() % (1 << 8)) << PAGE_SHIFT;
+	if (current->flags & PF_RANDOMIZE)
+		random_factor = arch_mmap_rnd();
 
 	if (mmap_is_legacy()) {
 		mm->mmap_base = TASK_UNMAPPED_BASE + random_factor;

arch/arm64/Kconfig

@@ -1,7 +1,7 @@
 config ARM64
 	def_bool y
-	select ARCH_BINFMT_ELF_RANDOMIZE_PIE
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
+	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_SG_CHAIN
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
@@ -143,6 +143,13 @@ config KERNEL_MODE_NEON
 config FIX_EARLYCON_MEM
 	def_bool y
 
+config PGTABLE_LEVELS
+	int
+	default 2 if ARM64_64K_PAGES && ARM64_VA_BITS_42
+	default 3 if ARM64_64K_PAGES && ARM64_VA_BITS_48
+	default 3 if ARM64_4K_PAGES && ARM64_VA_BITS_39
+	default 4 if ARM64_4K_PAGES && ARM64_VA_BITS_48
+
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"
@@ -413,13 +420,6 @@ config ARM64_VA_BITS
 	default 42 if ARM64_VA_BITS_42
 	default 48 if ARM64_VA_BITS_48
 
-config ARM64_PGTABLE_LEVELS
-	int
-	default 2 if ARM64_64K_PAGES && ARM64_VA_BITS_42
-	default 3 if ARM64_64K_PAGES && ARM64_VA_BITS_48
-	default 3 if ARM64_4K_PAGES && ARM64_VA_BITS_39
-	default 4 if ARM64_4K_PAGES && ARM64_VA_BITS_48
-
 config CPU_BIG_ENDIAN
        bool "Build big-endian kernel"
        help

arch/arm64/include/asm/elf.h

@@ -125,7 +125,6 @@ typedef struct user_fpsimd_state elf_fpregset_t;
  * the loader.  We need to make sure that it is out of the way of the program
  * that it will "exec", and that there is sufficient room for the brk.
  */
-extern unsigned long randomize_et_dyn(unsigned long base);
 #define ELF_ET_DYN_BASE	(2 * TASK_SIZE_64 / 3)
 
 /*
@@ -157,10 +156,6 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm,
 #define STACK_RND_MASK			(0x3ffff >> (PAGE_SHIFT - 12))
 #endif
 
-struct mm_struct;
-extern unsigned long arch_randomize_brk(struct mm_struct *mm);
-#define arch_randomize_brk arch_randomize_brk
-
 #ifdef CONFIG_COMPAT
 
 #ifdef __AARCH64EB__

arch/arm64/include/asm/kvm_mmu.h

@@ -163,12 +163,12 @@ static inline bool kvm_s2pmd_readonly(pmd_t *pmd)
 /*
  * If we are concatenating first level stage-2 page tables, we would have less
  * than or equal to 16 pointers in the fake PGD, because that's what the
- * architecture allows.  In this case, (4 - CONFIG_ARM64_PGTABLE_LEVELS)
+ * architecture allows.  In this case, (4 - CONFIG_PGTABLE_LEVELS)
  * represents the first level for the host, and we add 1 to go to the next
  * level (which uses contatenation) for the stage-2 tables.
  */
 #if PTRS_PER_S2_PGD <= 16
-#define KVM_PREALLOC_LEVEL	(4 - CONFIG_ARM64_PGTABLE_LEVELS + 1)
+#define KVM_PREALLOC_LEVEL	(4 - CONFIG_PGTABLE_LEVELS + 1)
 #else
 #define KVM_PREALLOC_LEVEL	(0)
 #endif

arch/arm64/include/asm/page.h

@@ -36,9 +36,9 @@
  * for more information).
  */
 #ifdef CONFIG_ARM64_64K_PAGES
-#define SWAPPER_PGTABLE_LEVELS	(CONFIG_ARM64_PGTABLE_LEVELS)
+#define SWAPPER_PGTABLE_LEVELS	(CONFIG_PGTABLE_LEVELS)
 #else
-#define SWAPPER_PGTABLE_LEVELS	(CONFIG_ARM64_PGTABLE_LEVELS - 1)
+#define SWAPPER_PGTABLE_LEVELS	(CONFIG_PGTABLE_LEVELS - 1)
 #endif
 
 #define SWAPPER_DIR_SIZE	(SWAPPER_PGTABLE_LEVELS * PAGE_SIZE)

arch/arm64/include/asm/pgalloc.h

@@ -28,7 +28,7 @@
 
 #define PGALLOC_GFP	(GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
 
-#if CONFIG_ARM64_PGTABLE_LEVELS > 2
+#if CONFIG_PGTABLE_LEVELS > 2
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
@@ -46,9 +46,9 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 	set_pud(pud, __pud(__pa(pmd) | PMD_TYPE_TABLE));
 }
 
-#endif	/* CONFIG_ARM64_PGTABLE_LEVELS > 2 */
+#endif	/* CONFIG_PGTABLE_LEVELS > 2 */
 
-#if CONFIG_ARM64_PGTABLE_LEVELS > 3
+#if CONFIG_PGTABLE_LEVELS > 3
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
@@ -66,7 +66,7 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
 	set_pgd(pgd, __pgd(__pa(pud) | PUD_TYPE_TABLE));
 }
 
-#endif	/* CONFIG_ARM64_PGTABLE_LEVELS > 3 */
+#endif	/* CONFIG_PGTABLE_LEVELS > 3 */
 
 extern pgd_t *pgd_alloc(struct mm_struct *mm);
 extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);

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

@@ -21,7 +21,7 @@
 /*
  * PMD_SHIFT determines the size a level 2 page table entry can map.
  */
-#if CONFIG_ARM64_PGTABLE_LEVELS > 2
+#if CONFIG_PGTABLE_LEVELS > 2
 #define PMD_SHIFT		((PAGE_SHIFT - 3) * 2 + 3)
 #define PMD_SIZE		(_AC(1, UL) << PMD_SHIFT)
 #define PMD_MASK		(~(PMD_SIZE-1))
@@ -31,7 +31,7 @@
 /*
  * PUD_SHIFT determines the size a level 1 page table entry can map.
  */
-#if CONFIG_ARM64_PGTABLE_LEVELS > 3
+#if CONFIG_PGTABLE_LEVELS > 3
 #define PUD_SHIFT		((PAGE_SHIFT - 3) * 3 + 3)
 #define PUD_SIZE		(_AC(1, UL) << PUD_SHIFT)
 #define PUD_MASK		(~(PUD_SIZE-1))
@@ -42,7 +42,7 @@
  * PGDIR_SHIFT determines the size a top-level page table entry can map
  * (depending on the configuration, this level can be 0, 1 or 2).
  */
-#define PGDIR_SHIFT		((PAGE_SHIFT - 3) * CONFIG_ARM64_PGTABLE_LEVELS + 3)
+#define PGDIR_SHIFT		((PAGE_SHIFT - 3) * CONFIG_PGTABLE_LEVELS + 3)
 #define PGDIR_SIZE		(_AC(1, UL) << PGDIR_SHIFT)
 #define PGDIR_MASK		(~(PGDIR_SIZE-1))
 #define PTRS_PER_PGD		(1 << (VA_BITS - PGDIR_SHIFT))

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

@@ -38,13 +38,13 @@ typedef struct { pteval_t pte; } pte_t;
 #define pte_val(x)	((x).pte)
 #define __pte(x)	((pte_t) { (x) } )
 
-#if CONFIG_ARM64_PGTABLE_LEVELS > 2
+#if CONFIG_PGTABLE_LEVELS > 2
 typedef struct { pmdval_t pmd; } pmd_t;
 #define pmd_val(x)	((x).pmd)
 #define __pmd(x)	((pmd_t) { (x) } )
 #endif
 
-#if CONFIG_ARM64_PGTABLE_LEVELS > 3
+#if CONFIG_PGTABLE_LEVELS > 3
 typedef struct { pudval_t pud; } pud_t;
 #define pud_val(x)	((x).pud)
 #define __pud(x)	((pud_t) { (x) } )
@@ -64,13 +64,13 @@ typedef pteval_t pte_t;
 #define pte_val(x)	(x)
 #define __pte(x)	(x)
 
-#if CONFIG_ARM64_PGTABLE_LEVELS > 2
+#if CONFIG_PGTABLE_LEVELS > 2
 typedef pmdval_t pmd_t;
 #define pmd_val(x)	(x)
 #define __pmd(x)	(x)
 #endif
 
-#if CONFIG_ARM64_PGTABLE_LEVELS > 3
+#if CONFIG_PGTABLE_LEVELS > 3
 typedef pudval_t pud_t;
 #define pud_val(x)	(x)
 #define __pud(x)	(x)
@@ -86,9 +86,9 @@ typedef pteval_t pgprot_t;
 
 #endif /* STRICT_MM_TYPECHECKS */
 
-#if CONFIG_ARM64_PGTABLE_LEVELS == 2
+#if CONFIG_PGTABLE_LEVELS == 2
 #include <asm-generic/pgtable-nopmd.h>
-#elif CONFIG_ARM64_PGTABLE_LEVELS == 3
+#elif CONFIG_PGTABLE_LEVELS == 3
 #include <asm-generic/pgtable-nopud.h>
 #endif
 

arch/arm64/include/asm/pgtable.h

@@ -374,7 +374,7 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd)
  */
 #define mk_pte(page,prot)	pfn_pte(page_to_pfn(page),prot)
 
-#if CONFIG_ARM64_PGTABLE_LEVELS > 2
+#if CONFIG_PGTABLE_LEVELS > 2
 
 #define pmd_ERROR(pmd)		__pmd_error(__FILE__, __LINE__, pmd_val(pmd))
 
@@ -409,9 +409,9 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 
 #define pud_page(pud)		pfn_to_page(__phys_to_pfn(pud_val(pud) & PHYS_MASK))
 
-#endif	/* CONFIG_ARM64_PGTABLE_LEVELS > 2 */
+#endif	/* CONFIG_PGTABLE_LEVELS > 2 */
 
-#if CONFIG_ARM64_PGTABLE_LEVELS > 3
+#if CONFIG_PGTABLE_LEVELS > 3
 
 #define pud_ERROR(pud)		__pud_error(__FILE__, __LINE__, pud_val(pud))
 
@@ -445,7 +445,7 @@ static inline pud_t *pud_offset(pgd_t *pgd, unsigned long addr)
 
 #define pgd_page(pgd)		pfn_to_page(__phys_to_pfn(pgd_val(pgd) & PHYS_MASK))
 
-#endif  /* CONFIG_ARM64_PGTABLE_LEVELS > 3 */
+#endif  /* CONFIG_PGTABLE_LEVELS > 3 */
 
 #define pgd_ERROR(pgd)		__pgd_error(__FILE__, __LINE__, pgd_val(pgd))
 

arch/arm64/include/asm/tlb.h

@@ -53,7 +53,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 	tlb_remove_entry(tlb, pte);
 }
 
-#if CONFIG_ARM64_PGTABLE_LEVELS > 2
+#if CONFIG_PGTABLE_LEVELS > 2
 static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 				  unsigned long addr)
 {
@@ -62,7 +62,7 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 }
 #endif
 
-#if CONFIG_ARM64_PGTABLE_LEVELS > 3
+#if CONFIG_PGTABLE_LEVELS > 3
 static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp,
 				  unsigned long addr)
 {

arch/arm64/mm/init.c

@@ -190,6 +190,8 @@ void __init bootmem_init(void)
 	min = PFN_UP(memblock_start_of_DRAM());
 	max = PFN_DOWN(memblock_end_of_DRAM());
 
+	early_memtest(min << PAGE_SHIFT, max << PAGE_SHIFT);
+
 	/*
 	 * Sparsemem tries to allocate bootmem in memory_present(), so must be
 	 * done after the fixed reservations.

arch/arm64/mm/mmap.c

@@ -47,17 +47,16 @@ static int mmap_is_legacy(void)
 	return sysctl_legacy_va_layout;
 }
 
-static unsigned long mmap_rnd(void)
+unsigned long arch_mmap_rnd(void)
 {
-	unsigned long rnd = 0;
+	unsigned long rnd;
 
-	if (current->flags & PF_RANDOMIZE)
-		rnd = (long)get_random_int() & STACK_RND_MASK;
+	rnd = (unsigned long)get_random_int() & STACK_RND_MASK;
 
 	return rnd << PAGE_SHIFT;
 }
 
-static unsigned long mmap_base(void)
+static unsigned long mmap_base(unsigned long rnd)
 {
 	unsigned long gap = rlimit(RLIMIT_STACK);
 
@@ -66,7 +65,7 @@ static unsigned long mmap_base(void)
 	else if (gap > MAX_GAP)
 		gap = MAX_GAP;
 
-	return PAGE_ALIGN(STACK_TOP - gap - mmap_rnd());
+	return PAGE_ALIGN(STACK_TOP - gap - rnd);
 }
 
 /*
@@ -75,15 +74,20 @@ static unsigned long mmap_base(void)
  */
 void arch_pick_mmap_layout(struct mm_struct *mm)
 {
+	unsigned long random_factor = 0UL;
+
+	if (current->flags & PF_RANDOMIZE)
+		random_factor = arch_mmap_rnd();
+
 	/*
 	 * Fall back to the standard layout if the personality bit is set, or
 	 * if the expected stack growth is unlimited:
 	 */
 	if (mmap_is_legacy()) {
-		mm->mmap_base = TASK_UNMAPPED_BASE;
+		mm->mmap_base = TASK_UNMAPPED_BASE + random_factor;
 		mm->get_unmapped_area = arch_get_unmapped_area;
 	} else {
-		mm->mmap_base = mmap_base();
+		mm->mmap_base = mmap_base(random_factor);
 		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
 	}
 }

arch/arm64/mm/mmu.c

@@ -550,10 +550,10 @@ void vmemmap_free(unsigned long start, unsigned long end)
 #endif	/* CONFIG_SPARSEMEM_VMEMMAP */
 
 static pte_t bm_pte[PTRS_PER_PTE] __page_aligned_bss;
-#if CONFIG_ARM64_PGTABLE_LEVELS > 2
+#if CONFIG_PGTABLE_LEVELS > 2
 static pmd_t bm_pmd[PTRS_PER_PMD] __page_aligned_bss;
 #endif
-#if CONFIG_ARM64_PGTABLE_LEVELS > 3
+#if CONFIG_PGTABLE_LEVELS > 3
 static pud_t bm_pud[PTRS_PER_PUD] __page_aligned_bss;
 #endif
 

arch/ia64/Kconfig

@@ -1,3 +1,8 @@
+config PGTABLE_LEVELS
+	int "Page Table Levels" if !IA64_PAGE_SIZE_64KB
+	range 3 4 if !IA64_PAGE_SIZE_64KB
+	default 3
+
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"
@@ -286,19 +291,6 @@ config IA64_PAGE_SIZE_64KB
 
 endchoice
 
-choice
-	prompt "Page Table Levels"
-	default PGTABLE_3
-
-config PGTABLE_3
-	bool "3 Levels"
-
-config PGTABLE_4
-	depends on !IA64_PAGE_SIZE_64KB
-	bool "4 Levels"
-
-endchoice
-
 if IA64_HP_SIM
 config HZ
 	default 32

arch/ia64/include/asm/page.h

@@ -173,7 +173,7 @@ get_order (unsigned long size)
    */
   typedef struct { unsigned long pte; } pte_t;
   typedef struct { unsigned long pmd; } pmd_t;
-#ifdef CONFIG_PGTABLE_4
+#if CONFIG_PGTABLE_LEVELS == 4
   typedef struct { unsigned long pud; } pud_t;
 #endif
   typedef struct { unsigned long pgd; } pgd_t;
@@ -182,7 +182,7 @@ get_order (unsigned long size)
 
 # define pte_val(x)	((x).pte)
 # define pmd_val(x)	((x).pmd)
-#ifdef CONFIG_PGTABLE_4
+#if CONFIG_PGTABLE_LEVELS == 4
 # define pud_val(x)	((x).pud)
 #endif
 # define pgd_val(x)	((x).pgd)

arch/ia64/include/asm/pgalloc.h

@@ -32,7 +32,7 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 	quicklist_free(0, NULL, pgd);
 }
 
-#ifdef CONFIG_PGTABLE_4
+#if CONFIG_PGTABLE_LEVELS == 4
 static inline void
 pgd_populate(struct mm_struct *mm, pgd_t * pgd_entry, pud_t * pud)
 {
@@ -49,7 +49,7 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud)
 	quicklist_free(0, NULL, pud);
 }
 #define __pud_free_tlb(tlb, pud, address)	pud_free((tlb)->mm, pud)
-#endif /* CONFIG_PGTABLE_4 */
+#endif /* CONFIG_PGTABLE_LEVELS == 4 */
 
 static inline void
 pud_populate(struct mm_struct *mm, pud_t * pud_entry, pmd_t * pmd)

arch/ia64/include/asm/pgtable.h

@@ -99,7 +99,7 @@
 #define PMD_MASK	(~(PMD_SIZE-1))
 #define PTRS_PER_PMD	(1UL << (PTRS_PER_PTD_SHIFT))
 
-#ifdef CONFIG_PGTABLE_4
+#if CONFIG_PGTABLE_LEVELS == 4
 /*
  * Definitions for second level:
  *
@@ -117,7 +117,7 @@
  *
  * PGDIR_SHIFT determines what a first-level page table entry can map.
  */
-#ifdef CONFIG_PGTABLE_4
+#if CONFIG_PGTABLE_LEVELS == 4
 #define PGDIR_SHIFT		(PUD_SHIFT + (PTRS_PER_PTD_SHIFT))
 #else
 #define PGDIR_SHIFT		(PMD_SHIFT + (PTRS_PER_PTD_SHIFT))
@@ -180,7 +180,7 @@
 #define __S111	__pgprot(__ACCESS_BITS | _PAGE_PL_3 | _PAGE_AR_RWX)
 
 #define pgd_ERROR(e)	printk("%s:%d: bad pgd %016lx.\n", __FILE__, __LINE__, pgd_val(e))
-#ifdef CONFIG_PGTABLE_4
+#if CONFIG_PGTABLE_LEVELS == 4
 #define pud_ERROR(e)	printk("%s:%d: bad pud %016lx.\n", __FILE__, __LINE__, pud_val(e))
 #endif
 #define pmd_ERROR(e)	printk("%s:%d: bad pmd %016lx.\n", __FILE__, __LINE__, pmd_val(e))
@@ -281,7 +281,7 @@ extern unsigned long VMALLOC_END;
 #define pud_page_vaddr(pud)		((unsigned long) __va(pud_val(pud) & _PFN_MASK))
 #define pud_page(pud)			virt_to_page((pud_val(pud) + PAGE_OFFSET))
 
-#ifdef CONFIG_PGTABLE_4
+#if CONFIG_PGTABLE_LEVELS == 4
 #define pgd_none(pgd)			(!pgd_val(pgd))
 #define pgd_bad(pgd)			(!ia64_phys_addr_valid(pgd_val(pgd)))
 #define pgd_present(pgd)		(pgd_val(pgd) != 0UL)
@@ -384,7 +384,7 @@ pgd_offset (const struct mm_struct *mm, unsigned long address)
    here.  */
 #define pgd_offset_gate(mm, addr)	pgd_offset_k(addr)
 
-#ifdef CONFIG_PGTABLE_4
+#if CONFIG_PGTABLE_LEVELS == 4
 /* Find an entry in the second-level page table.. */
 #define pud_offset(dir,addr) \
 	((pud_t *) pgd_page_vaddr(*(dir)) + (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)))
@@ -586,7 +586,7 @@ extern struct page *zero_page_memmap_ptr;
 #define __HAVE_ARCH_PGD_OFFSET_GATE
 
 
-#ifndef CONFIG_PGTABLE_4
+#if CONFIG_PGTABLE_LEVELS == 3
 #include <asm-generic/pgtable-nopud.h>
 #endif
 #include <asm-generic/pgtable.h>

arch/ia64/kernel/ivt.S

@@ -146,7 +146,7 @@ ENTRY(vhpt_miss)
 (p6)	dep r17=r18,r19,3,(PAGE_SHIFT-3)	// r17=pgd_offset for region 5
 (p7)	dep r17=r18,r17,3,(PAGE_SHIFT-6)	// r17=pgd_offset for region[0-4]
 	cmp.eq p7,p6=0,r21			// unused address bits all zeroes?
-#ifdef CONFIG_PGTABLE_4
+#if CONFIG_PGTABLE_LEVELS == 4
 	shr.u r28=r22,PUD_SHIFT			// shift pud index into position
 #else
 	shr.u r18=r22,PMD_SHIFT			// shift pmd index into position
@@ -155,7 +155,7 @@ ENTRY(vhpt_miss)
 	ld8 r17=[r17]				// get *pgd (may be 0)
 	;;
 (p7)	cmp.eq p6,p7=r17,r0			// was pgd_present(*pgd) == NULL?
-#ifdef CONFIG_PGTABLE_4
+#if CONFIG_PGTABLE_LEVELS == 4
 	dep r28=r28,r17,3,(PAGE_SHIFT-3)	// r28=pud_offset(pgd,addr)
 	;;
 	shr.u r18=r22,PMD_SHIFT			// shift pmd index into position
@@ -222,13 +222,13 @@ ENTRY(vhpt_miss)
 	 */
 	ld8 r25=[r21]				// read *pte again
 	ld8 r26=[r17]				// read *pmd again
-#ifdef CONFIG_PGTABLE_4
+#if CONFIG_PGTABLE_LEVELS == 4
 	ld8 r19=[r28]				// read *pud again
 #endif
 	cmp.ne p6,p7=r0,r0
 	;;
 	cmp.ne.or.andcm p6,p7=r26,r20		// did *pmd change
-#ifdef CONFIG_PGTABLE_4
+#if CONFIG_PGTABLE_LEVELS == 4
 	cmp.ne.or.andcm p6,p7=r19,r29		// did *pud change
 #endif
 	mov r27=PAGE_SHIFT<<2
@@ -476,7 +476,7 @@ ENTRY(nested_dtlb_miss)
 (p6)	dep r17=r18,r19,3,(PAGE_SHIFT-3)	// r17=pgd_offset for region 5
 (p7)	dep r17=r18,r17,3,(PAGE_SHIFT-6)	// r17=pgd_offset for region[0-4]
 	cmp.eq p7,p6=0,r21			// unused address bits all zeroes?
-#ifdef CONFIG_PGTABLE_4
+#if CONFIG_PGTABLE_LEVELS == 4
 	shr.u r18=r22,PUD_SHIFT			// shift pud index into position
 #else
 	shr.u r18=r22,PMD_SHIFT			// shift pmd index into position
@@ -487,7 +487,7 @@ ENTRY(nested_dtlb_miss)
 (p7)	cmp.eq p6,p7=r17,r0			// was pgd_present(*pgd) == NULL?
 	dep r17=r18,r17,3,(PAGE_SHIFT-3)	// r17=p[u|m]d_offset(pgd,addr)
 	;;
-#ifdef CONFIG_PGTABLE_4
+#if CONFIG_PGTABLE_LEVELS == 4
 (p7)	ld8 r17=[r17]				// get *pud (may be 0)
 	shr.u r18=r22,PMD_SHIFT			// shift pmd index into position
 	;;

arch/ia64/kernel/machine_kexec.c

@@ -156,9 +156,9 @@ void arch_crash_save_vmcoreinfo(void)
 	VMCOREINFO_OFFSET(node_memblk_s, start_paddr);
 	VMCOREINFO_OFFSET(node_memblk_s, size);
 #endif
-#ifdef CONFIG_PGTABLE_3
+#if CONFIG_PGTABLE_LEVELS == 3
 	VMCOREINFO_CONFIG(PGTABLE_3);
-#elif defined(CONFIG_PGTABLE_4)
+#elif CONFIG_PGTABLE_LEVELS == 4
 	VMCOREINFO_CONFIG(PGTABLE_4);
 #endif
 }

arch/m68k/Kconfig

@@ -67,6 +67,10 @@ config HZ
 	default 1000 if CLEOPATRA
 	default 100
 
+config PGTABLE_LEVELS
+	default 2 if SUN3 || COLDFIRE
+	default 3
+
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"

arch/mips/Kconfig

@@ -23,7 +23,7 @@ config MIPS
 	select HAVE_KRETPROBES
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_SYSCALL_TRACEPOINTS
-	select ARCH_BINFMT_ELF_RANDOMIZE_PIE
+	select ARCH_HAS_ELF_RANDOMIZE
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE if CPU_SUPPORTS_HUGEPAGES && 64BIT
 	select RTC_LIB if !MACH_LOONGSON
 	select GENERIC_ATOMIC64 if !64BIT
@@ -2600,6 +2600,11 @@ config STACKTRACE_SUPPORT
 	bool
 	default y
 
+config PGTABLE_LEVELS
+	int
+	default 3 if 64BIT && !PAGE_SIZE_64KB
+	default 2
+
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"

arch/mips/include/asm/elf.h

@@ -410,10 +410,6 @@ struct linux_binprm;
 extern int arch_setup_additional_pages(struct linux_binprm *bprm,
 				       int uses_interp);
 
-struct mm_struct;
-extern unsigned long arch_randomize_brk(struct mm_struct *mm);
-#define arch_randomize_brk arch_randomize_brk
-
 struct arch_elf_state {
 	int fp_abi;
 	int interp_fp_abi;

arch/mips/mm/mmap.c

@@ -142,18 +142,26 @@ unsigned long arch_get_unmapped_area_topdown(struct file *filp,
 			addr0, len, pgoff, flags, DOWN);
 }
 
+unsigned long arch_mmap_rnd(void)
+{
+	unsigned long rnd;
+
+	rnd = (unsigned long)get_random_int();
+	rnd <<= PAGE_SHIFT;
+	if (TASK_IS_32BIT_ADDR)
+		rnd &= 0xfffffful;
+	else
+		rnd &= 0xffffffful;
+
+	return rnd;
+}
+
 void arch_pick_mmap_layout(struct mm_struct *mm)
 {
 	unsigned long random_factor = 0UL;
 
-	if (current->flags & PF_RANDOMIZE) {
-		random_factor = get_random_int();
-		random_factor = random_factor << PAGE_SHIFT;
-		if (TASK_IS_32BIT_ADDR)
-			random_factor &= 0xfffffful;
-		else
-			random_factor &= 0xffffffful;
-	}
+	if (current->flags & PF_RANDOMIZE)
+		random_factor = arch_mmap_rnd();
 
 	if (mmap_is_legacy()) {
 		mm->mmap_base = TASK_UNMAPPED_BASE + random_factor;

arch/parisc/Kconfig

@@ -103,6 +103,11 @@ config ARCH_MAY_HAVE_PC_FDC
 	depends on BROKEN
 	default y
 
+config PGTABLE_LEVELS
+	int
+	default 3 if 64BIT && PARISC_PAGE_SIZE_4KB
+	default 2
+
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"

arch/parisc/include/asm/pgalloc.h

@@ -51,7 +51,7 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 	free_pages((unsigned long)pgd, PGD_ALLOC_ORDER);
 }
 
-#if PT_NLEVELS == 3
+#if CONFIG_PGTABLE_LEVELS == 3
 
 /* Three Level Page Table Support for pmd's */
 

arch/parisc/include/asm/pgtable.h

@@ -68,13 +68,11 @@ extern void purge_tlb_entries(struct mm_struct *, unsigned long);
 #define KERNEL_INITIAL_ORDER	24	/* 0 to 1<<24 = 16MB */
 #define KERNEL_INITIAL_SIZE	(1 << KERNEL_INITIAL_ORDER)
 
-#if defined(CONFIG_64BIT) && defined(CONFIG_PARISC_PAGE_SIZE_4KB)
-#define PT_NLEVELS	3
+#if CONFIG_PGTABLE_LEVELS == 3
 #define PGD_ORDER	1 /* Number of pages per pgd */
 #define PMD_ORDER	1 /* Number of pages per pmd */
 #define PGD_ALLOC_ORDER	2 /* first pgd contains pmd */
 #else
-#define PT_NLEVELS	2
 #define PGD_ORDER	1 /* Number of pages per pgd */
 #define PGD_ALLOC_ORDER	PGD_ORDER
 #endif
@@ -93,7 +91,7 @@ extern void purge_tlb_entries(struct mm_struct *, unsigned long);
 #define PMD_SHIFT       (PLD_SHIFT + BITS_PER_PTE)
 #define PMD_SIZE	(1UL << PMD_SHIFT)
 #define PMD_MASK	(~(PMD_SIZE-1))
-#if PT_NLEVELS == 3
+#if CONFIG_PGTABLE_LEVELS == 3
 #define BITS_PER_PMD	(PAGE_SHIFT + PMD_ORDER - BITS_PER_PMD_ENTRY)
 #else
 #define __PAGETABLE_PMD_FOLDED
@@ -277,7 +275,7 @@ extern unsigned long *empty_zero_page;
 #define pgd_flag(x)	(pgd_val(x) & PxD_FLAG_MASK)
 #define pgd_address(x)	((unsigned long)(pgd_val(x) &~ PxD_FLAG_MASK) << PxD_VALUE_SHIFT)
 
-#if PT_NLEVELS == 3
+#if CONFIG_PGTABLE_LEVELS == 3
 /* The first entry of the permanent pmd is not there if it contains
  * the gateway marker */
 #define pmd_none(x)	(!pmd_val(x) || pmd_flag(x) == PxD_FLAG_ATTACHED)
@@ -287,7 +285,7 @@ extern unsigned long *empty_zero_page;
 #define pmd_bad(x)	(!(pmd_flag(x) & PxD_FLAG_VALID))
 #define pmd_present(x)	(pmd_flag(x) & PxD_FLAG_PRESENT)
 static inline void pmd_clear(pmd_t *pmd) {
-#if PT_NLEVELS == 3
+#if CONFIG_PGTABLE_LEVELS == 3
 	if (pmd_flag(*pmd) & PxD_FLAG_ATTACHED)
 		/* This is the entry pointing to the permanent pmd
 		 * attached to the pgd; cannot clear it */
@@ -299,7 +297,7 @@ static inline void pmd_clear(pmd_t *pmd) {
 
 
 
-#if PT_NLEVELS == 3
+#if CONFIG_PGTABLE_LEVELS == 3
 #define pgd_page_vaddr(pgd) ((unsigned long) __va(pgd_address(pgd)))
 #define pgd_page(pgd)	virt_to_page((void *)pgd_page_vaddr(pgd))
 
@@ -309,7 +307,7 @@ static inline void pmd_clear(pmd_t *pmd) {
 #define pgd_bad(x)      (!(pgd_flag(x) & PxD_FLAG_VALID))
 #define pgd_present(x)  (pgd_flag(x) & PxD_FLAG_PRESENT)
 static inline void pgd_clear(pgd_t *pgd) {
-#if PT_NLEVELS == 3
+#if CONFIG_PGTABLE_LEVELS == 3
 	if(pgd_flag(*pgd) & PxD_FLAG_ATTACHED)
 		/* This is the permanent pmd attached to the pgd; cannot
 		 * free it */
@@ -393,7 +391,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 
 /* Find an entry in the second-level page table.. */
 
-#if PT_NLEVELS == 3
+#if CONFIG_PGTABLE_LEVELS == 3
 #define pmd_offset(dir,address) \
 ((pmd_t *) pgd_page_vaddr(*(dir)) + (((address)>>PMD_SHIFT) & (PTRS_PER_PMD-1)))
 #else

arch/parisc/kernel/entry.S

@@ -398,7 +398,7 @@
 	 * can address up to 1TB
 	 */
 	.macro		L2_ptep	pmd,pte,index,va,fault
-#if PT_NLEVELS == 3
+#if CONFIG_PGTABLE_LEVELS == 3
 	extru		\va,31-ASM_PMD_SHIFT,ASM_BITS_PER_PMD,\index
 #else
 # if defined(CONFIG_64BIT)
@@ -436,7 +436,7 @@
 	 * all ILP32 processes and all the kernel for machines with
 	 * under 4GB of memory) */
 	.macro		L3_ptep pgd,pte,index,va,fault
-#if PT_NLEVELS == 3 /* we might have a 2-Level scheme, e.g. with 16kb page size */
+#if CONFIG_PGTABLE_LEVELS == 3 /* we might have a 2-Level scheme, e.g. with 16kb page size */
 	extrd,u		\va,63-ASM_PGDIR_SHIFT,ASM_BITS_PER_PGD,\index
 	copy		%r0,\pte
 	extrd,u,*=	\va,63-ASM_PGDIR_SHIFT,64-ASM_PGDIR_SHIFT,%r0

arch/parisc/kernel/head.S

@@ -74,7 +74,7 @@ $bss_loop:
 	mtctl		%r4,%cr24	/* Initialize kernel root pointer */
 	mtctl		%r4,%cr25	/* Initialize user root pointer */
 
-#if PT_NLEVELS == 3
+#if CONFIG_PGTABLE_LEVELS == 3
 	/* Set pmd in pgd */
 	load32		PA(pmd0),%r5
 	shrd            %r5,PxD_VALUE_SHIFT,%r3	
@@ -97,7 +97,7 @@ $bss_loop:
 	stw		%r3,0(%r4)
 	ldo		(PAGE_SIZE >> PxD_VALUE_SHIFT)(%r3),%r3
 	addib,>		-1,%r1,1b
-#if PT_NLEVELS == 3
+#if CONFIG_PGTABLE_LEVELS == 3
 	ldo             ASM_PMD_ENTRY_SIZE(%r4),%r4
 #else
 	ldo             ASM_PGD_ENTRY_SIZE(%r4),%r4

arch/parisc/mm/init.c

@@ -34,7 +34,7 @@
 extern int  data_start;
 extern void parisc_kernel_start(void);	/* Kernel entry point in head.S */
 
-#if PT_NLEVELS == 3
+#if CONFIG_PGTABLE_LEVELS == 3
 /* NOTE: This layout exactly conforms to the hybrid L2/L3 page table layout
  * with the first pmd adjacent to the pgd and below it. gcc doesn't actually
  * guarantee that global objects will be laid out in memory in the same order

arch/powerpc/Kconfig

@@ -88,7 +88,7 @@ config PPC
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select BINFMT_ELF
-	select ARCH_BINFMT_ELF_RANDOMIZE_PIE
+	select ARCH_HAS_ELF_RANDOMIZE
 	select OF
 	select OF_EARLY_FLATTREE
 	select OF_RESERVED_MEM
@@ -297,6 +297,12 @@ config ZONE_DMA32
 	bool
 	default y if PPC64
 
+config PGTABLE_LEVELS
+	int
+	default 2 if !PPC64
+	default 3 if PPC_64K_PAGES
+	default 4
+
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"

arch/powerpc/include/asm/elf.h

@@ -128,10 +128,6 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm,
 	(0x7ff >> (PAGE_SHIFT - 12)) : \
 	(0x3ffff >> (PAGE_SHIFT - 12)))
 
-extern unsigned long arch_randomize_brk(struct mm_struct *mm);
-#define arch_randomize_brk arch_randomize_brk
-
-
 #ifdef CONFIG_SPU_BASE
 /* Notes used in ET_CORE. Note name is "SPU/<fd>/<filename>". */
 #define NT_SPU		1

arch/powerpc/mm/mmap.c

@@ -53,21 +53,20 @@ static inline int mmap_is_legacy(void)
 	return sysctl_legacy_va_layout;
 }
 
-static unsigned long mmap_rnd(void)
+unsigned long arch_mmap_rnd(void)
 {
-	unsigned long rnd = 0;
+	unsigned long rnd;
+
+	/* 8MB for 32bit, 1GB for 64bit */
+	if (is_32bit_task())
+		rnd = (unsigned long)get_random_int() % (1<<(23-PAGE_SHIFT));
+	else
+		rnd = (unsigned long)get_random_int() % (1<<(30-PAGE_SHIFT));
 
-	if (current->flags & PF_RANDOMIZE) {
-		/* 8MB for 32bit, 1GB for 64bit */
-		if (is_32bit_task())
-			rnd = (long)(get_random_int() % (1<<(23-PAGE_SHIFT)));
-		else
-			rnd = (long)(get_random_int() % (1<<(30-PAGE_SHIFT)));
-	}
 	return rnd << PAGE_SHIFT;
 }
 
-static inline unsigned long mmap_base(void)
+static inline unsigned long mmap_base(unsigned long rnd)
 {
 	unsigned long gap = rlimit(RLIMIT_STACK);
 
@@ -76,7 +75,7 @@ static inline unsigned long mmap_base(void)
 	else if (gap > MAX_GAP)
 		gap = MAX_GAP;
 
-	return PAGE_ALIGN(TASK_SIZE - gap - mmap_rnd());
+	return PAGE_ALIGN(TASK_SIZE - gap - rnd);
 }
 
 /*
@@ -85,6 +84,11 @@ static inline unsigned long mmap_base(void)
  */
 void arch_pick_mmap_layout(struct mm_struct *mm)
 {
+	unsigned long random_factor = 0UL;
+
+	if (current->flags & PF_RANDOMIZE)
+		random_factor = arch_mmap_rnd();
+
 	/*
 	 * Fall back to the standard layout if the personality
 	 * bit is set, or if the expected stack growth is unlimited:
@@ -93,7 +97,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 		mm->mmap_base = TASK_UNMAPPED_BASE;
 		mm->get_unmapped_area = arch_get_unmapped_area;
 	} else {
-		mm->mmap_base = mmap_base();
+		mm->mmap_base = mmap_base(random_factor);
 		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
 	}
 }

arch/s390/Kconfig

@@ -65,6 +65,7 @@ config S390
 	def_bool y
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
+	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_SG_CHAIN
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
@@ -156,6 +157,11 @@ config S390
 config SCHED_OMIT_FRAME_POINTER
 	def_bool y
 
+config PGTABLE_LEVELS
+	int
+	default 4 if 64BIT
+	default 2
+
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"

arch/s390/include/asm/elf.h

@@ -161,10 +161,11 @@ extern unsigned int vdso_enabled;
 /* This is the location that an ET_DYN program is loaded if exec'ed.  Typical
    use of this is to invoke "./ld.so someprog" to test out a new version of
    the loader.  We need to make sure that it is out of the way of the program
-   that it will "exec", and that there is sufficient room for the brk.  */
-
-extern unsigned long randomize_et_dyn(void);
-#define ELF_ET_DYN_BASE		randomize_et_dyn()
+   that it will "exec", and that there is sufficient room for the brk. 64-bit
+   tasks are aligned to 4GB. */
+#define ELF_ET_DYN_BASE (is_32bit_task() ? \
+				(STACK_TOP / 3 * 2) : \
+				(STACK_TOP / 3 * 2) & ~((1UL << 32) - 1))
 
 /* This yields a mask that user programs can use to figure out what
    instruction set this CPU supports. */
@@ -225,9 +226,6 @@ struct linux_binprm;
 #define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
 int arch_setup_additional_pages(struct linux_binprm *, int);
 
-extern unsigned long arch_randomize_brk(struct mm_struct *mm);
-#define arch_randomize_brk arch_randomize_brk
-
 void *fill_cpu_elf_notes(void *ptr, struct save_area *sa, __vector128 *vxrs);
 
 #endif

arch/s390/mm/mmap.c

@@ -60,22 +60,20 @@ static inline int mmap_is_legacy(void)
 	return sysctl_legacy_va_layout;
 }
 
-static unsigned long mmap_rnd(void)
+unsigned long arch_mmap_rnd(void)
 {
-	if (!(current->flags & PF_RANDOMIZE))
-		return 0;
 	if (is_32bit_task())
 		return (get_random_int() & 0x7ff) << PAGE_SHIFT;
 	else
 		return (get_random_int() & mmap_rnd_mask) << PAGE_SHIFT;
 }
 
-static unsigned long mmap_base_legacy(void)
+static unsigned long mmap_base_legacy(unsigned long rnd)
 {
-	return TASK_UNMAPPED_BASE + mmap_rnd();
+	return TASK_UNMAPPED_BASE + rnd;
 }
 
-static inline unsigned long mmap_base(void)
+static inline unsigned long mmap_base(unsigned long rnd)
 {
 	unsigned long gap = rlimit(RLIMIT_STACK);
 
@@ -84,7 +82,7 @@ static inline unsigned long mmap_base(void)
 	else if (gap > MAX_GAP)
 		gap = MAX_GAP;
 	gap &= PAGE_MASK;
-	return STACK_TOP - stack_maxrandom_size() - mmap_rnd() - gap;
+	return STACK_TOP - stack_maxrandom_size() - rnd - gap;
 }
 
 unsigned long
@@ -179,17 +177,6 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	return addr;
 }
 
-unsigned long randomize_et_dyn(void)
-{
-	unsigned long base;
-
-	base = STACK_TOP / 3 * 2;
-	if (!is_32bit_task())
-		/* Align to 4GB */
-		base &= ~((1UL << 32) - 1);
-	return base + mmap_rnd();
-}
-
 #ifndef CONFIG_64BIT
 
 /*
@@ -198,15 +185,20 @@ unsigned long randomize_et_dyn(void)
  */
 void arch_pick_mmap_layout(struct mm_struct *mm)
 {
+	unsigned long random_factor = 0UL;
+
+	if (current->flags & PF_RANDOMIZE)
+		random_factor = arch_mmap_rnd();
+
 	/*
 	 * Fall back to the standard layout if the personality
 	 * bit is set, or if the expected stack growth is unlimited:
 	 */
 	if (mmap_is_legacy()) {
-		mm->mmap_base = mmap_base_legacy();
+		mm->mmap_base = mmap_base_legacy(random_factor);
 		mm->get_unmapped_area = arch_get_unmapped_area;
 	} else {
-		mm->mmap_base = mmap_base();
+		mm->mmap_base = mmap_base(random_factor);
 		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
 	}
 }
@@ -273,15 +265,20 @@ s390_get_unmapped_area_topdown(struct file *filp, const unsigned long addr,
  */
 void arch_pick_mmap_layout(struct mm_struct *mm)
 {
+	unsigned long random_factor = 0UL;
+
+	if (current->flags & PF_RANDOMIZE)
+		random_factor = arch_mmap_rnd();
+
 	/*
 	 * Fall back to the standard layout if the personality
 	 * bit is set, or if the expected stack growth is unlimited:
 	 */
 	if (mmap_is_legacy()) {
-		mm->mmap_base = mmap_base_legacy();
+		mm->mmap_base = mmap_base_legacy(random_factor);
 		mm->get_unmapped_area = s390_get_unmapped_area;
 	} else {
-		mm->mmap_base = mmap_base();
+		mm->mmap_base = mmap_base(random_factor);
 		mm->get_unmapped_area = s390_get_unmapped_area_topdown;
 	}
 }

arch/sh/Kconfig

@@ -162,6 +162,10 @@ config NEED_DMA_MAP_STATE
 config NEED_SG_DMA_LENGTH
 	def_bool y
 
+config PGTABLE_LEVELS
+	default 3 if X2TLB
+	default 2
+
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"

arch/sh/kernel/dwarf.c

@@ -993,7 +993,7 @@ static struct unwinder dwarf_unwinder = {
 	.rating = 150,
 };
 
-static void dwarf_unwinder_cleanup(void)
+static void __init dwarf_unwinder_cleanup(void)
 {
 	struct dwarf_fde *fde, *next_fde;
 	struct dwarf_cie *cie, *next_cie;
@@ -1009,6 +1009,10 @@ static void dwarf_unwinder_cleanup(void)
 	rbtree_postorder_for_each_entry_safe(cie, next_cie, &cie_root, node)
 		kfree(cie);
 
+	if (dwarf_reg_pool)
+		mempool_destroy(dwarf_reg_pool);
+	if (dwarf_frame_pool)
+		mempool_destroy(dwarf_frame_pool);
 	kmem_cache_destroy(dwarf_reg_cachep);
 	kmem_cache_destroy(dwarf_frame_cachep);
 }
@@ -1176,17 +1180,13 @@ static int __init dwarf_unwinder_init(void)
 			sizeof(struct dwarf_reg), 0,
 			SLAB_PANIC | SLAB_HWCACHE_ALIGN | SLAB_NOTRACK, NULL);
 
-	dwarf_frame_pool = mempool_create(DWARF_FRAME_MIN_REQ,
-					  mempool_alloc_slab,
-					  mempool_free_slab,
-					  dwarf_frame_cachep);
+	dwarf_frame_pool = mempool_create_slab_pool(DWARF_FRAME_MIN_REQ,
+						    dwarf_frame_cachep);
 	if (!dwarf_frame_pool)
 		goto out;
 
-	dwarf_reg_pool = mempool_create(DWARF_REG_MIN_REQ,
-					 mempool_alloc_slab,
-					 mempool_free_slab,
-					 dwarf_reg_cachep);
+	dwarf_reg_pool = mempool_create_slab_pool(DWARF_REG_MIN_REQ,
+						  dwarf_reg_cachep);
 	if (!dwarf_reg_pool)
 		goto out;
 

arch/sparc/Kconfig

@@ -146,6 +146,10 @@ config GENERIC_ISA_DMA
 config ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	def_bool y if SPARC64
 
+config PGTABLE_LEVELS
+	default 4 if 64BIT
+	default 3
+
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"

arch/sparc/kernel/mdesc.c

@@ -130,26 +130,26 @@ static struct mdesc_mem_ops memblock_mdesc_ops = {
 static struct mdesc_handle *mdesc_kmalloc(unsigned int mdesc_size)
 {
 	unsigned int handle_size;
+	struct mdesc_handle *hp;
+	unsigned long addr;
 	void *base;
 
 	handle_size = (sizeof(struct mdesc_handle) -
 		       sizeof(struct mdesc_hdr) +
 		       mdesc_size);
 
+	/*
+	 * Allocation has to succeed because mdesc update would be missed
+	 * and such events are not retransmitted.
+	 */
 	base = kmalloc(handle_size + 15, GFP_KERNEL | __GFP_NOFAIL);
-	if (base) {
-		struct mdesc_handle *hp;
-		unsigned long addr;
-
-		addr = (unsigned long)base;
-		addr = (addr + 15UL) & ~15UL;
-		hp = (struct mdesc_handle *) addr;
+	addr = (unsigned long)base;
+	addr = (addr + 15UL) & ~15UL;
+	hp = (struct mdesc_handle *) addr;
 
-		mdesc_handle_init(hp, handle_size, base);
-		return hp;
-	}
+	mdesc_handle_init(hp, handle_size, base);
 
-	return NULL;
+	return hp;
 }
 
 static void mdesc_kfree(struct mdesc_handle *hp)

arch/tile/Kconfig

@@ -147,6 +147,11 @@ config ARCH_DEFCONFIG
 	default "arch/tile/configs/tilepro_defconfig" if !TILEGX
 	default "arch/tile/configs/tilegx_defconfig" if TILEGX
 
+config PGTABLE_LEVELS
+	int
+	default 3 if 64BIT
+	default 2
+
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"

arch/um/Kconfig.um

@@ -155,3 +155,8 @@ config MMAPPER
 
 config NO_DMA
 	def_bool y
+
+config PGTABLE_LEVELS
+	int
+	default 3 if 3_LEVEL_PGTABLES
+	default 2

arch/x86/Kconfig

@@ -87,7 +87,7 @@ config X86
 	select HAVE_ARCH_KMEMCHECK
 	select HAVE_ARCH_KASAN if X86_64 && SPARSEMEM_VMEMMAP
 	select HAVE_USER_RETURN_NOTIFIER
-	select ARCH_BINFMT_ELF_RANDOMIZE_PIE
+	select ARCH_HAS_ELF_RANDOMIZE
 	select HAVE_ARCH_JUMP_LABEL
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select SPARSE_IRQ
@@ -99,6 +99,7 @@ config X86
 	select IRQ_FORCED_THREADING
 	select HAVE_BPF_JIT if X86_64
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
+	select HAVE_ARCH_HUGE_VMAP if X86_64 || (X86_32 && X86_PAE)
 	select ARCH_HAS_SG_CHAIN
 	select CLKEVT_I8253
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
@@ -277,6 +278,12 @@ config ARCH_SUPPORTS_UPROBES
 config FIX_EARLYCON_MEM
 	def_bool y
 
+config PGTABLE_LEVELS
+	int
+	default 4 if X86_64
+	default 3 if X86_PAE
+	default 2
+
 source "init/Kconfig"
 source "kernel/Kconfig.freezer"
 
@@ -714,17 +721,6 @@ endif #HYPERVISOR_GUEST
 config NO_BOOTMEM
 	def_bool y
 
-config MEMTEST
-	bool "Memtest"
-	---help---
-	  This option adds a kernel parameter 'memtest', which allows memtest
-	  to be set.
-	        memtest=0, mean disabled; -- default
-	        memtest=1, mean do 1 test pattern;
-	        ...
-	        memtest=4, mean do 4 test patterns.
-	  If you are unsure how to answer this question, answer N.
-
 source "arch/x86/Kconfig.cpu"
 
 config HPET_TIMER

arch/x86/include/asm/e820.h

@@ -40,14 +40,6 @@ static inline void e820_mark_nosave_regions(unsigned long limit_pfn)
 }
 #endif
 
-#ifdef CONFIG_MEMTEST
-extern void early_memtest(unsigned long start, unsigned long end);
-#else
-static inline void early_memtest(unsigned long start, unsigned long end)
-{
-}
-#endif
-
 extern unsigned long e820_end_of_ram_pfn(void);
 extern unsigned long e820_end_of_low_ram_pfn(void);
 extern u64 early_reserve_e820(u64 sizet, u64 align);

arch/x86/include/asm/elf.h

@@ -339,9 +339,6 @@ extern int compat_arch_setup_additional_pages(struct linux_binprm *bprm,
 					      int uses_interp);
 #define compat_arch_setup_additional_pages compat_arch_setup_additional_pages
 
-extern unsigned long arch_randomize_brk(struct mm_struct *mm);
-#define arch_randomize_brk arch_randomize_brk
-
 /*
  * True on X86_32 or when emulating IA32 on X86_64
  */

arch/x86/include/asm/page_types.h

@@ -40,8 +40,10 @@
 
 #ifdef CONFIG_X86_64
 #include <asm/page_64_types.h>
+#define IOREMAP_MAX_ORDER       (PUD_SHIFT)
 #else
 #include <asm/page_32_types.h>
+#define IOREMAP_MAX_ORDER       (PMD_SHIFT)
 #endif	/* CONFIG_X86_64 */
 
 #ifndef __ASSEMBLY__

arch/x86/include/asm/paravirt.h

@@ -545,7 +545,7 @@ static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
 		PVOP_VCALL2(pv_mmu_ops.set_pmd, pmdp, val);
 }
 
-#if PAGETABLE_LEVELS >= 3
+#if CONFIG_PGTABLE_LEVELS >= 3
 static inline pmd_t __pmd(pmdval_t val)
 {
 	pmdval_t ret;
@@ -585,7 +585,7 @@ static inline void set_pud(pud_t *pudp, pud_t pud)
 		PVOP_VCALL2(pv_mmu_ops.set_pud, pudp,
 			    val);
 }
-#if PAGETABLE_LEVELS == 4
+#if CONFIG_PGTABLE_LEVELS == 4
 static inline pud_t __pud(pudval_t val)
 {
 	pudval_t ret;
@@ -636,9 +636,9 @@ static inline void pud_clear(pud_t *pudp)
 	set_pud(pudp, __pud(0));
 }
 
-#endif	/* PAGETABLE_LEVELS == 4 */
+#endif	/* CONFIG_PGTABLE_LEVELS == 4 */
 
-#endif	/* PAGETABLE_LEVELS >= 3 */
+#endif	/* CONFIG_PGTABLE_LEVELS >= 3 */
 
 #ifdef CONFIG_X86_PAE
 /* Special-case pte-setting operations for PAE, which can't update a

arch/x86/include/asm/paravirt_types.h

@@ -294,7 +294,7 @@ struct pv_mmu_ops {
 	struct paravirt_callee_save pgd_val;
 	struct paravirt_callee_save make_pgd;
 
-#if PAGETABLE_LEVELS >= 3
+#if CONFIG_PGTABLE_LEVELS >= 3
 #ifdef CONFIG_X86_PAE
 	void (*set_pte_atomic)(pte_t *ptep, pte_t pteval);
 	void (*pte_clear)(struct mm_struct *mm, unsigned long addr,
@@ -308,13 +308,13 @@ struct pv_mmu_ops {
 	struct paravirt_callee_save pmd_val;
 	struct paravirt_callee_save make_pmd;
 
-#if PAGETABLE_LEVELS == 4
+#if CONFIG_PGTABLE_LEVELS == 4
 	struct paravirt_callee_save pud_val;
 	struct paravirt_callee_save make_pud;
 
 	void (*set_pgd)(pgd_t *pudp, pgd_t pgdval);
-#endif	/* PAGETABLE_LEVELS == 4 */
-#endif	/* PAGETABLE_LEVELS >= 3 */
+#endif	/* CONFIG_PGTABLE_LEVELS == 4 */
+#endif	/* CONFIG_PGTABLE_LEVELS >= 3 */
 
 	struct pv_lazy_ops lazy_mode;
 

arch/x86/include/asm/pgalloc.h

@@ -77,7 +77,7 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
 
 #define pmd_pgtable(pmd) pmd_page(pmd)
 
-#if PAGETABLE_LEVELS > 2
+#if CONFIG_PGTABLE_LEVELS > 2
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
 	struct page *page;
@@ -116,7 +116,7 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 }
 #endif	/* CONFIG_X86_PAE */
 
-#if PAGETABLE_LEVELS > 3
+#if CONFIG_PGTABLE_LEVELS > 3
 static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
 {
 	paravirt_alloc_pud(mm, __pa(pud) >> PAGE_SHIFT);
@@ -142,7 +142,7 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
 	___pud_free_tlb(tlb, pud);
 }
 
-#endif	/* PAGETABLE_LEVELS > 3 */
-#endif	/* PAGETABLE_LEVELS > 2 */
+#endif	/* CONFIG_PGTABLE_LEVELS > 3 */
+#endif	/* CONFIG_PGTABLE_LEVELS > 2 */
 
 #endif /* _ASM_X86_PGALLOC_H */

arch/x86/include/asm/pgtable-2level_types.h

@@ -17,7 +17,6 @@ typedef union {
 #endif	/* !__ASSEMBLY__ */
 
 #define SHARED_KERNEL_PMD	0
-#define PAGETABLE_LEVELS	2
 
 /*
  * traditional i386 two-level paging structure:

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

@@ -24,8 +24,6 @@ typedef union {
 #define SHARED_KERNEL_PMD	1
 #endif
 
-#define PAGETABLE_LEVELS	3
-
 /*
  * PGDIR_SHIFT determines what a top-level page table entry can map
  */

arch/x86/include/asm/pgtable.h

@@ -551,7 +551,7 @@ static inline unsigned long pages_to_mb(unsigned long npg)
 	return npg >> (20 - PAGE_SHIFT);
 }
 
-#if PAGETABLE_LEVELS > 2
+#if CONFIG_PGTABLE_LEVELS > 2
 static inline int pud_none(pud_t pud)
 {
 	return native_pud_val(pud) == 0;
@@ -594,9 +594,9 @@ static inline int pud_large(pud_t pud)
 {
 	return 0;
 }
-#endif	/* PAGETABLE_LEVELS > 2 */
+#endif	/* CONFIG_PGTABLE_LEVELS > 2 */
 
-#if PAGETABLE_LEVELS > 3
+#if CONFIG_PGTABLE_LEVELS > 3
 static inline int pgd_present(pgd_t pgd)
 {
 	return pgd_flags(pgd) & _PAGE_PRESENT;
@@ -633,7 +633,7 @@ static inline int pgd_none(pgd_t pgd)
 {
 	return !native_pgd_val(pgd);
 }
-#endif	/* PAGETABLE_LEVELS > 3 */
+#endif	/* CONFIG_PGTABLE_LEVELS > 3 */
 
 #endif	/* __ASSEMBLY__ */
 

arch/x86/include/asm/pgtable_64_types.h

@@ -20,7 +20,6 @@ typedef struct { pteval_t pte; } pte_t;
 #endif	/* !__ASSEMBLY__ */
 
 #define SHARED_KERNEL_PMD	0
-#define PAGETABLE_LEVELS	4
 
 /*
  * PGDIR_SHIFT determines what a top-level page table entry can map

arch/x86/include/asm/pgtable_types.h

@@ -234,7 +234,7 @@ static inline pgdval_t pgd_flags(pgd_t pgd)
 	return native_pgd_val(pgd) & PTE_FLAGS_MASK;
 }
 
-#if PAGETABLE_LEVELS > 3
+#if CONFIG_PGTABLE_LEVELS > 3
 typedef struct { pudval_t pud; } pud_t;
 
 static inline pud_t native_make_pud(pmdval_t val)
@@ -255,7 +255,7 @@ static inline pudval_t native_pud_val(pud_t pud)
 }
 #endif
 
-#if PAGETABLE_LEVELS > 2
+#if CONFIG_PGTABLE_LEVELS > 2
 typedef struct { pmdval_t pmd; } pmd_t;
 
 static inline pmd_t native_make_pmd(pmdval_t val)

arch/x86/kernel/kvm.c

@@ -513,7 +513,7 @@ void __init kvm_guest_init(void)
 	 * can get false positives too easily, for example if the host is
 	 * overcommitted.
 	 */
-	watchdog_enable_hardlockup_detector(false);
+	hardlockup_detector_disable();
 }
 
 static noinline uint32_t __kvm_cpuid_base(void)

arch/x86/kernel/paravirt.c

@@ -443,7 +443,7 @@ struct pv_mmu_ops pv_mmu_ops = {
 	.ptep_modify_prot_start = __ptep_modify_prot_start,
 	.ptep_modify_prot_commit = __ptep_modify_prot_commit,
 
-#if PAGETABLE_LEVELS >= 3
+#if CONFIG_PGTABLE_LEVELS >= 3
 #ifdef CONFIG_X86_PAE
 	.set_pte_atomic = native_set_pte_atomic,
 	.pte_clear = native_pte_clear,
@@ -454,13 +454,13 @@ struct pv_mmu_ops pv_mmu_ops = {
 	.pmd_val = PTE_IDENT,
 	.make_pmd = PTE_IDENT,
 
-#if PAGETABLE_LEVELS == 4
+#if CONFIG_PGTABLE_LEVELS == 4
 	.pud_val = PTE_IDENT,
 	.make_pud = PTE_IDENT,
 
 	.set_pgd = native_set_pgd,
 #endif
-#endif /* PAGETABLE_LEVELS >= 3 */
+#endif /* CONFIG_PGTABLE_LEVELS >= 3 */
 
 	.pte_val = PTE_IDENT,
 	.pgd_val = PTE_IDENT,

arch/x86/mm/Makefile

@@ -32,6 +32,4 @@ obj-$(CONFIG_AMD_NUMA)		+= amdtopology.o
 obj-$(CONFIG_ACPI_NUMA)		+= srat.o
 obj-$(CONFIG_NUMA_EMU)		+= numa_emulation.o
 
-obj-$(CONFIG_MEMTEST)		+= memtest.o
-
 obj-$(CONFIG_X86_INTEL_MPX)	+= mpx.o

arch/x86/mm/ioremap.c

@@ -67,8 +67,13 @@ static int __ioremap_check_ram(unsigned long start_pfn, unsigned long nr_pages,
 
 /*
  * Remap an arbitrary physical address space into the kernel virtual
- * address space. Needed when the kernel wants to access high addresses
- * directly.
+ * address space. It transparently creates kernel huge I/O mapping when
+ * the physical address is aligned by a huge page size (1GB or 2MB) and
+ * the requested size is at least the huge page size.
+ *
+ * NOTE: MTRRs can override PAT memory types with a 4KB granularity.
+ * Therefore, the mapping code falls back to use a smaller page toward 4KB
+ * when a mapping range is covered by non-WB type of MTRRs.
  *
  * NOTE! We need to allow non-page-aligned mappings too: we will obviously
  * have to convert them into an offset in a page-aligned mapping, but the
@@ -326,6 +331,20 @@ void iounmap(volatile void __iomem *addr)
 }
 EXPORT_SYMBOL(iounmap);
 
+int arch_ioremap_pud_supported(void)
+{
+#ifdef CONFIG_X86_64
+	return cpu_has_gbpages;
+#else
+	return 0;
+#endif
+}
+
+int arch_ioremap_pmd_supported(void)
+{
+	return cpu_has_pse;
+}
+
 /*
  * Convert a physical pointer to a virtual kernel pointer for /dev/mem
  * access

arch/x86/mm/mmap.c

@@ -65,24 +65,23 @@ static int mmap_is_legacy(void)
 	return sysctl_legacy_va_layout;
 }
 
-static unsigned long mmap_rnd(void)
+unsigned long arch_mmap_rnd(void)
 {
-	unsigned long rnd = 0;
+	unsigned long rnd;
 
 	/*
-	*  8 bits of randomness in 32bit mmaps, 20 address space bits
-	* 28 bits of randomness in 64bit mmaps, 40 address space bits
-	*/
-	if (current->flags & PF_RANDOMIZE) {
-		if (mmap_is_ia32())
-			rnd = get_random_int() % (1<<8);
-		else
-			rnd = get_random_int() % (1<<28);
-	}
+	 *  8 bits of randomness in 32bit mmaps, 20 address space bits
+	 * 28 bits of randomness in 64bit mmaps, 40 address space bits
+	 */
+	if (mmap_is_ia32())
+		rnd = (unsigned long)get_random_int() % (1<<8);
+	else
+		rnd = (unsigned long)get_random_int() % (1<<28);
+
 	return rnd << PAGE_SHIFT;
 }
 
-static unsigned long mmap_base(void)
+static unsigned long mmap_base(unsigned long rnd)
 {
 	unsigned long gap = rlimit(RLIMIT_STACK);
 
@@ -91,19 +90,19 @@ static unsigned long mmap_base(void)
 	else if (gap > MAX_GAP)
 		gap = MAX_GAP;
 
-	return PAGE_ALIGN(TASK_SIZE - gap - mmap_rnd());
+	return PAGE_ALIGN(TASK_SIZE - gap - rnd);
 }
 
 /*
  * Bottom-up (legacy) layout on X86_32 did not support randomization, X86_64
  * does, but not when emulating X86_32
  */
-static unsigned long mmap_legacy_base(void)
+static unsigned long mmap_legacy_base(unsigned long rnd)
 {
 	if (mmap_is_ia32())
 		return TASK_UNMAPPED_BASE;
 	else
-		return TASK_UNMAPPED_BASE + mmap_rnd();
+		return TASK_UNMAPPED_BASE + rnd;
 }
 
 /*
@@ -112,13 +111,18 @@ static unsigned long mmap_legacy_base(void)
  */
 void arch_pick_mmap_layout(struct mm_struct *mm)
 {
-	mm->mmap_legacy_base = mmap_legacy_base();
-	mm->mmap_base = mmap_base();
+	unsigned long random_factor = 0UL;
+
+	if (current->flags & PF_RANDOMIZE)
+		random_factor = arch_mmap_rnd();
+
+	mm->mmap_legacy_base = mmap_legacy_base(random_factor);
 
 	if (mmap_is_legacy()) {
 		mm->mmap_base = mm->mmap_legacy_base;
 		mm->get_unmapped_area = arch_get_unmapped_area;
 	} else {
+		mm->mmap_base = mmap_base(random_factor);
 		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
 	}
 }

arch/x86/mm/pgtable.c

@@ -4,6 +4,7 @@
 #include <asm/pgtable.h>
 #include <asm/tlb.h>
 #include <asm/fixmap.h>
+#include <asm/mtrr.h>
 
 #define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO
 
@@ -58,7 +59,7 @@ void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte)
 	tlb_remove_page(tlb, pte);
 }
 
-#if PAGETABLE_LEVELS > 2
+#if CONFIG_PGTABLE_LEVELS > 2
 void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd)
 {
 	struct page *page = virt_to_page(pmd);
@@ -74,14 +75,14 @@ void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd)
 	tlb_remove_page(tlb, page);
 }
 
-#if PAGETABLE_LEVELS > 3
+#if CONFIG_PGTABLE_LEVELS > 3
 void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud)
 {
 	paravirt_release_pud(__pa(pud) >> PAGE_SHIFT);
 	tlb_remove_page(tlb, virt_to_page(pud));
 }
-#endif	/* PAGETABLE_LEVELS > 3 */
-#endif	/* PAGETABLE_LEVELS > 2 */
+#endif	/* CONFIG_PGTABLE_LEVELS > 3 */
+#endif	/* CONFIG_PGTABLE_LEVELS > 2 */
 
 static inline void pgd_list_add(pgd_t *pgd)
 {
@@ -117,9 +118,9 @@ static void pgd_ctor(struct mm_struct *mm, pgd_t *pgd)
 	/* If the pgd points to a shared pagetable level (either the
 	   ptes in non-PAE, or shared PMD in PAE), then just copy the
 	   references from swapper_pg_dir. */
-	if (PAGETABLE_LEVELS == 2 ||
-	    (PAGETABLE_LEVELS == 3 && SHARED_KERNEL_PMD) ||
-	    PAGETABLE_LEVELS == 4) {
+	if (CONFIG_PGTABLE_LEVELS == 2 ||
+	    (CONFIG_PGTABLE_LEVELS == 3 && SHARED_KERNEL_PMD) ||
+	    CONFIG_PGTABLE_LEVELS == 4) {
 		clone_pgd_range(pgd + KERNEL_PGD_BOUNDARY,
 				swapper_pg_dir + KERNEL_PGD_BOUNDARY,
 				KERNEL_PGD_PTRS);
@@ -560,3 +561,67 @@ void native_set_fixmap(enum fixed_addresses idx, phys_addr_t phys,
 {
 	__native_set_fixmap(idx, pfn_pte(phys >> PAGE_SHIFT, flags));
 }
+
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
+{
+	u8 mtrr;
+
+	/*
+	 * Do not use a huge page when the range is covered by non-WB type
+	 * of MTRRs.
+	 */
+	mtrr = mtrr_type_lookup(addr, addr + PUD_SIZE);
+	if ((mtrr != MTRR_TYPE_WRBACK) && (mtrr != 0xFF))
+		return 0;
+
+	prot = pgprot_4k_2_large(prot);
+
+	set_pte((pte_t *)pud, pfn_pte(
+		(u64)addr >> PAGE_SHIFT,
+		__pgprot(pgprot_val(prot) | _PAGE_PSE)));
+
+	return 1;
+}
+
+int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
+{
+	u8 mtrr;
+
+	/*
+	 * Do not use a huge page when the range is covered by non-WB type
+	 * of MTRRs.
+	 */
+	mtrr = mtrr_type_lookup(addr, addr + PMD_SIZE);
+	if ((mtrr != MTRR_TYPE_WRBACK) && (mtrr != 0xFF))
+		return 0;
+
+	prot = pgprot_4k_2_large(prot);
+
+	set_pte((pte_t *)pmd, pfn_pte(
+		(u64)addr >> PAGE_SHIFT,
+		__pgprot(pgprot_val(prot) | _PAGE_PSE)));
+
+	return 1;
+}
+
+int pud_clear_huge(pud_t *pud)
+{
+	if (pud_large(*pud)) {
+		pud_clear(pud);
+		return 1;
+	}
+
+	return 0;
+}
+
+int pmd_clear_huge(pmd_t *pmd)
+{
+	if (pmd_large(*pmd)) {
+		pmd_clear(pmd);
+		return 1;
+	}
+
+	return 0;
+}
+#endif	/* CONFIG_HAVE_ARCH_HUGE_VMAP */

arch/x86/xen/mmu.c

@@ -502,7 +502,7 @@ __visible pmd_t xen_make_pmd(pmdval_t pmd)
 }
 PV_CALLEE_SAVE_REGS_THUNK(xen_make_pmd);
 
-#if PAGETABLE_LEVELS == 4
+#if CONFIG_PGTABLE_LEVELS == 4
 __visible pudval_t xen_pud_val(pud_t pud)
 {
 	return pte_mfn_to_pfn(pud.pud);
@@ -589,7 +589,7 @@ static void xen_set_pgd(pgd_t *ptr, pgd_t val)
 
 	xen_mc_issue(PARAVIRT_LAZY_MMU);
 }
-#endif	/* PAGETABLE_LEVELS == 4 */
+#endif	/* CONFIG_PGTABLE_LEVELS == 4 */
 
 /*
  * (Yet another) pagetable walker.  This one is intended for pinning a
@@ -1628,7 +1628,7 @@ static void xen_release_pmd(unsigned long pfn)
 	xen_release_ptpage(pfn, PT_PMD);
 }
 
-#if PAGETABLE_LEVELS == 4
+#if CONFIG_PGTABLE_LEVELS == 4
 static void xen_alloc_pud(struct mm_struct *mm, unsigned long pfn)
 {
 	xen_alloc_ptpage(mm, pfn, PT_PUD);
@@ -2046,7 +2046,7 @@ static void __init xen_post_allocator_init(void)
 	pv_mmu_ops.set_pte = xen_set_pte;
 	pv_mmu_ops.set_pmd = xen_set_pmd;
 	pv_mmu_ops.set_pud = xen_set_pud;
-#if PAGETABLE_LEVELS == 4
+#if CONFIG_PGTABLE_LEVELS == 4
 	pv_mmu_ops.set_pgd = xen_set_pgd;
 #endif
 
@@ -2056,7 +2056,7 @@ static void __init xen_post_allocator_init(void)
 	pv_mmu_ops.alloc_pmd = xen_alloc_pmd;
 	pv_mmu_ops.release_pte = xen_release_pte;
 	pv_mmu_ops.release_pmd = xen_release_pmd;
-#if PAGETABLE_LEVELS == 4
+#if CONFIG_PGTABLE_LEVELS == 4
 	pv_mmu_ops.alloc_pud = xen_alloc_pud;
 	pv_mmu_ops.release_pud = xen_release_pud;
 #endif
@@ -2122,14 +2122,14 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = {
 	.make_pmd = PV_CALLEE_SAVE(xen_make_pmd),
 	.pmd_val = PV_CALLEE_SAVE(xen_pmd_val),
 
-#if PAGETABLE_LEVELS == 4
+#if CONFIG_PGTABLE_LEVELS == 4
 	.pud_val = PV_CALLEE_SAVE(xen_pud_val),
 	.make_pud = PV_CALLEE_SAVE(xen_make_pud),
 	.set_pgd = xen_set_pgd_hyper,
 
 	.alloc_pud = xen_alloc_pmd_init,
 	.release_pud = xen_release_pmd_init,
-#endif	/* PAGETABLE_LEVELS == 4 */
+#endif	/* CONFIG_PGTABLE_LEVELS == 4 */
 
 	.activate_mm = xen_activate_mm,
 	.dup_mmap = xen_dup_mmap,

drivers/base/memory.c

@@ -219,6 +219,7 @@ static bool pages_correctly_reserved(unsigned long start_pfn)
 /*
  * MEMORY_HOTPLUG depends on SPARSEMEM in mm/Kconfig, so it is
  * OK to have direct references to sparsemem variables in here.
+ * Must already be protected by mem_hotplug_begin().
  */
 static int
 memory_block_action(unsigned long phys_index, unsigned long action, int online_type)
@@ -228,7 +229,7 @@ memory_block_action(unsigned long phys_index, unsigned long action, int online_t
 	struct page *first_page;
 	int ret;
 
-	start_pfn = phys_index << PFN_SECTION_SHIFT;
+	start_pfn = section_nr_to_pfn(phys_index);
 	first_page = pfn_to_page(start_pfn);
 
 	switch (action) {
@@ -286,6 +287,7 @@ static int memory_subsys_online(struct device *dev)
 	if (mem->online_type < 0)
 		mem->online_type = MMOP_ONLINE_KEEP;
 
+	/* Already under protection of mem_hotplug_begin() */
 	ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE);
 
 	/* clear online_type */
@@ -328,17 +330,19 @@ store_mem_state(struct device *dev,
 		goto err;
 	}
 
+	/*
+	 * Memory hotplug needs to hold mem_hotplug_begin() for probe to find
+	 * the correct memory block to online before doing device_online(dev),
+	 * which will take dev->mutex.  Take the lock early to prevent an
+	 * inversion, memory_subsys_online() callbacks will be implemented by
+	 * assuming it's already protected.
+	 */
+	mem_hotplug_begin();
+
 	switch (online_type) {
 	case MMOP_ONLINE_KERNEL:
 	case MMOP_ONLINE_MOVABLE:
 	case MMOP_ONLINE_KEEP:
-		/*
-		 * mem->online_type is not protected so there can be a
-		 * race here.  However, when racing online, the first
-		 * will succeed and the second will just return as the
-		 * block will already be online.  The online type
-		 * could be either one, but that is expected.
-		 */
 		mem->online_type = online_type;
 		ret = device_online(&mem->dev);
 		break;
@@ -349,6 +353,7 @@ store_mem_state(struct device *dev,
 		ret = -EINVAL; /* should never happen */
 	}
 
+	mem_hotplug_done();
 err:
 	unlock_device_hotplug();
 

drivers/s390/scsi/zfcp_erp.c

@@ -738,11 +738,11 @@ static int zfcp_erp_adapter_strategy_open_fsf(struct zfcp_erp_action *act)
 		return ZFCP_ERP_FAILED;
 
 	if (mempool_resize(act->adapter->pool.sr_data,
-			   act->adapter->stat_read_buf_num, GFP_KERNEL))
+			   act->adapter->stat_read_buf_num))
 		return ZFCP_ERP_FAILED;
 
 	if (mempool_resize(act->adapter->pool.status_read_req,
-			   act->adapter->stat_read_buf_num, GFP_KERNEL))
+			   act->adapter->stat_read_buf_num))
 		return ZFCP_ERP_FAILED;
 
 	atomic_set(&act->adapter->stat_miss, act->adapter->stat_read_buf_num);

drivers/staging/lustre/lustre/include/linux/lustre_patchless_compat.h

@@ -55,7 +55,9 @@ truncate_complete_page(struct address_space *mapping, struct page *page)
 	if (PagePrivate(page))
 		page->mapping->a_ops->invalidatepage(page, 0, PAGE_CACHE_SIZE);
 
-	cancel_dirty_page(page, PAGE_SIZE);
+	if (TestClearPageDirty(page))
+		account_page_cleaned(page, mapping);
+
 	ClearPageMappedToDisk(page);
 	ll_delete_from_page_cache(page);
 }

drivers/xen/tmem.c

@@ -397,13 +397,15 @@ static int __init xen_tmem_init(void)
 #ifdef CONFIG_CLEANCACHE
 	BUG_ON(sizeof(struct cleancache_filekey) != sizeof(struct tmem_oid));
 	if (tmem_enabled && cleancache) {
-		char *s = "";
-		struct cleancache_ops *old_ops =
-			cleancache_register_ops(&tmem_cleancache_ops);
-		if (old_ops)
-			s = " (WARNING: cleancache_ops overridden)";
-		pr_info("cleancache enabled, RAM provided by Xen Transcendent Memory%s\n",
-			s);
+		int err;
+
+		err = cleancache_register_ops(&tmem_cleancache_ops);
+		if (err)
+			pr_warn("xen-tmem: failed to enable cleancache: %d\n",
+				err);
+		else
+			pr_info("cleancache enabled, RAM provided by "
+				"Xen Transcendent Memory\n");
 	}
 #endif
 #ifdef CONFIG_XEN_SELFBALLOONING

fs/Kconfig.binfmt

@@ -27,9 +27,6 @@ config COMPAT_BINFMT_ELF
 	bool
 	depends on COMPAT && BINFMT_ELF
 
-config ARCH_BINFMT_ELF_RANDOMIZE_PIE
-	bool
-
 config ARCH_BINFMT_ELF_STATE
 	bool
 

fs/binfmt_elf.c

@@ -31,6 +31,7 @@
 #include <linux/security.h>
 #include <linux/random.h>
 #include <linux/elf.h>
+#include <linux/elf-randomize.h>
 #include <linux/utsname.h>
 #include <linux/coredump.h>
 #include <linux/sched.h>
@@ -862,6 +863,7 @@ static int load_elf_binary(struct linux_binprm *bprm)
 	    i < loc->elf_ex.e_phnum; i++, elf_ppnt++) {
 		int elf_prot = 0, elf_flags;
 		unsigned long k, vaddr;
+		unsigned long total_size = 0;
 
 		if (elf_ppnt->p_type != PT_LOAD)
 			continue;
@@ -909,25 +911,20 @@ static int load_elf_binary(struct linux_binprm *bprm)
 			 * default mmap base, as well as whatever program they
 			 * might try to exec.  This is because the brk will
 			 * follow the loader, and is not movable.  */
-#ifdef CONFIG_ARCH_BINFMT_ELF_RANDOMIZE_PIE
-			/* Memory randomization might have been switched off
-			 * in runtime via sysctl or explicit setting of
-			 * personality flags.
-			 * If that is the case, retain the original non-zero
-			 * load_bias value in order to establish proper
-			 * non-randomized mappings.
-			 */
+			load_bias = ELF_ET_DYN_BASE - vaddr;
 			if (current->flags & PF_RANDOMIZE)
-				load_bias = 0;
-			else
-				load_bias = ELF_PAGESTART(ELF_ET_DYN_BASE - vaddr);
-#else
-			load_bias = ELF_PAGESTART(ELF_ET_DYN_BASE - vaddr);
-#endif
+				load_bias += arch_mmap_rnd();
+			load_bias = ELF_PAGESTART(load_bias);
+			total_size = total_mapping_size(elf_phdata,
+							loc->elf_ex.e_phnum);
+			if (!total_size) {
+				error = -EINVAL;
+				goto out_free_dentry;
+			}
 		}
 
 		error = elf_map(bprm->file, load_bias + vaddr, elf_ppnt,
-				elf_prot, elf_flags, 0);
+				elf_prot, elf_flags, total_size);
 		if (BAD_ADDR(error)) {
 			retval = IS_ERR((void *)error) ?
 				PTR_ERR((void*)error) : -EINVAL;
@@ -1053,15 +1050,13 @@ static int load_elf_binary(struct linux_binprm *bprm)
 	current->mm->end_data = end_data;
 	current->mm->start_stack = bprm->p;
 
-#ifdef arch_randomize_brk
 	if ((current->flags & PF_RANDOMIZE) && (randomize_va_space > 1)) {
 		current->mm->brk = current->mm->start_brk =
 			arch_randomize_brk(current->mm);
-#ifdef CONFIG_COMPAT_BRK
+#ifdef compat_brk_randomized
 		current->brk_randomized = 1;
 #endif
 	}
-#endif
 
 	if (current->personality & MMAP_PAGE_ZERO) {
 		/* Why this, you ask???  Well SVr4 maps page 0 as read-only,

fs/buffer.c

@@ -3243,8 +3243,8 @@ int try_to_free_buffers(struct page *page)
 	 * to synchronise against __set_page_dirty_buffers and prevent the
 	 * dirty bit from being lost.
 	 */
-	if (ret)
-		cancel_dirty_page(page, PAGE_CACHE_SIZE);
+	if (ret && TestClearPageDirty(page))
+		account_page_cleaned(page, mapping);
 	spin_unlock(&mapping->private_lock);
 out:
 	if (buffers_to_free) {

fs/cifs/connect.c

@@ -773,8 +773,7 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server)
 
 	length = atomic_dec_return(&tcpSesAllocCount);
 	if (length > 0)
-		mempool_resize(cifs_req_poolp, length + cifs_min_rcv,
-				GFP_KERNEL);
+		mempool_resize(cifs_req_poolp, length + cifs_min_rcv);
 }
 
 static int
@@ -848,8 +847,7 @@ cifs_demultiplex_thread(void *p)
 
 	length = atomic_inc_return(&tcpSesAllocCount);
 	if (length > 1)
-		mempool_resize(cifs_req_poolp, length + cifs_min_rcv,
-				GFP_KERNEL);
+		mempool_resize(cifs_req_poolp, length + cifs_min_rcv);
 
 	set_freezable();
 	while (server->tcpStatus != CifsExiting) {

fs/hugetlbfs/inode.c

@@ -319,7 +319,7 @@ static int hugetlbfs_write_end(struct file *file, struct address_space *mapping,
 
 static void truncate_huge_page(struct page *page)
 {
-	cancel_dirty_page(page, /* No IO accounting for huge pages? */0);
+	ClearPageDirty(page);
 	ClearPageUptodate(page);
 	delete_from_page_cache(page);
 }

fs/nfs/write.c

@@ -1876,11 +1876,6 @@ int nfs_wb_page_cancel(struct inode *inode, struct page *page)
 		 * request from the inode / page_private pointer and
 		 * release it */
 		nfs_inode_remove_request(req);
-		/*
-		 * In case nfs_inode_remove_request has marked the
-		 * page as being dirty
-		 */
-		cancel_dirty_page(page, PAGE_CACHE_SIZE);
 		nfs_unlock_and_release_request(req);
 	}
 

fs/ocfs2/alloc.c

@@ -3370,7 +3370,7 @@ static int ocfs2_merge_rec_right(struct ocfs2_path *left_path,
 		ret = ocfs2_get_right_path(et, left_path, &right_path);
 		if (ret) {
 			mlog_errno(ret);
-			goto out;
+			return ret;
 		}
 
 		right_el = path_leaf_el(right_path);
@@ -3453,8 +3453,7 @@ static int ocfs2_merge_rec_right(struct ocfs2_path *left_path,
 					   subtree_index);
 	}
 out:
-	if (right_path)
-		ocfs2_free_path(right_path);
+	ocfs2_free_path(right_path);
 	return ret;
 }
 
@@ -3536,7 +3535,7 @@ static int ocfs2_merge_rec_left(struct ocfs2_path *right_path,
 		ret = ocfs2_get_left_path(et, right_path, &left_path);
 		if (ret) {
 			mlog_errno(ret);
-			goto out;
+			return ret;
 		}
 
 		left_el = path_leaf_el(left_path);
@@ -3647,8 +3646,7 @@ static int ocfs2_merge_rec_left(struct ocfs2_path *right_path,
 						   right_path, subtree_index);
 	}
 out:
-	if (left_path)
-		ocfs2_free_path(left_path);
+	ocfs2_free_path(left_path);
 	return ret;
 }
 
@@ -4334,17 +4332,17 @@ ocfs2_figure_merge_contig_type(struct ocfs2_extent_tree *et,
 	} else if (path->p_tree_depth > 0) {
 		status = ocfs2_find_cpos_for_left_leaf(sb, path, &left_cpos);
 		if (status)
-			goto out;
+			goto exit;
 
 		if (left_cpos != 0) {
 			left_path = ocfs2_new_path_from_path(path);
 			if (!left_path)
-				goto out;
+				goto exit;
 
 			status = ocfs2_find_path(et->et_ci, left_path,
 						 left_cpos);
 			if (status)
-				goto out;
+				goto free_left_path;
 
 			new_el = path_leaf_el(left_path);
 
@@ -4361,7 +4359,7 @@ ocfs2_figure_merge_contig_type(struct ocfs2_extent_tree *et,
 					    le16_to_cpu(new_el->l_next_free_rec),
 					    le16_to_cpu(new_el->l_count));
 				status = -EINVAL;
-				goto out;
+				goto free_left_path;
 			}
 			rec = &new_el->l_recs[
 				le16_to_cpu(new_el->l_next_free_rec) - 1];
@@ -4388,18 +4386,18 @@ ocfs2_figure_merge_contig_type(struct ocfs2_extent_tree *et,
 		 path->p_tree_depth > 0) {
 		status = ocfs2_find_cpos_for_right_leaf(sb, path, &right_cpos);
 		if (status)
-			goto out;
+			goto free_left_path;
 
 		if (right_cpos == 0)
-			goto out;
+			goto free_left_path;
 
 		right_path = ocfs2_new_path_from_path(path);
 		if (!right_path)
-			goto out;
+			goto free_left_path;
 
 		status = ocfs2_find_path(et->et_ci, right_path, right_cpos);
 		if (status)
-			goto out;
+			goto free_right_path;
 
 		new_el = path_leaf_el(right_path);
 		rec = &new_el->l_recs[0];
@@ -4413,7 +4411,7 @@ ocfs2_figure_merge_contig_type(struct ocfs2_extent_tree *et,
 					    (unsigned long long)le64_to_cpu(eb->h_blkno),
 					    le16_to_cpu(new_el->l_next_free_rec));
 				status = -EINVAL;
-				goto out;
+				goto free_right_path;
 			}
 			rec = &new_el->l_recs[1];
 		}
@@ -4430,12 +4428,11 @@ ocfs2_figure_merge_contig_type(struct ocfs2_extent_tree *et,
 			ret = contig_type;
 	}
 
-out:
-	if (left_path)
-		ocfs2_free_path(left_path);
-	if (right_path)
-		ocfs2_free_path(right_path);
-
+free_right_path:
+	ocfs2_free_path(right_path);
+free_left_path:
+	ocfs2_free_path(left_path);
+exit:
 	return ret;
 }
 
@@ -6858,13 +6855,13 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
 		if (pages == NULL) {
 			ret = -ENOMEM;
 			mlog_errno(ret);
-			goto out;
+			return ret;
 		}
 
 		ret = ocfs2_reserve_clusters(osb, 1, &data_ac);
 		if (ret) {
 			mlog_errno(ret);
-			goto out;
+			goto free_pages;
 		}
 	}
 
@@ -6996,9 +6993,8 @@ out_commit:
 out:
 	if (data_ac)
 		ocfs2_free_alloc_context(data_ac);
-	if (pages)
-		kfree(pages);
-
+free_pages:
+	kfree(pages);
 	return ret;
 }
 

fs/ocfs2/aops.c

@@ -664,6 +664,117 @@ static int ocfs2_is_overwrite(struct ocfs2_super *osb,
 	return 0;
 }
 
+static int ocfs2_direct_IO_zero_extend(struct ocfs2_super *osb,
+		struct inode *inode, loff_t offset,
+		u64 zero_len, int cluster_align)
+{
+	u32 p_cpos = 0;
+	u32 v_cpos = ocfs2_bytes_to_clusters(osb->sb, i_size_read(inode));
+	unsigned int num_clusters = 0;
+	unsigned int ext_flags = 0;
+	int ret = 0;
+
+	if (offset <= i_size_read(inode) || cluster_align)
+		return 0;
+
+	ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos, &num_clusters,
+			&ext_flags);
+	if (ret < 0) {
+		mlog_errno(ret);
+		return ret;
+	}
+
+	if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN)) {
+		u64 s = i_size_read(inode);
+		sector_t sector = (p_cpos << (osb->s_clustersize_bits - 9)) +
+			(do_div(s, osb->s_clustersize) >> 9);
+
+		ret = blkdev_issue_zeroout(osb->sb->s_bdev, sector,
+				zero_len >> 9, GFP_NOFS, false);
+		if (ret < 0)
+			mlog_errno(ret);
+	}
+
+	return ret;
+}
+
+static int ocfs2_direct_IO_extend_no_holes(struct ocfs2_super *osb,
+		struct inode *inode, loff_t offset)
+{
+	u64 zero_start, zero_len, total_zero_len;
+	u32 p_cpos = 0, clusters_to_add;
+	u32 v_cpos = ocfs2_bytes_to_clusters(osb->sb, i_size_read(inode));
+	unsigned int num_clusters = 0;
+	unsigned int ext_flags = 0;
+	u32 size_div, offset_div;
+	int ret = 0;
+
+	{
+		u64 o = offset;
+		u64 s = i_size_read(inode);
+
+		offset_div = do_div(o, osb->s_clustersize);
+		size_div = do_div(s, osb->s_clustersize);
+	}
+
+	if (offset <= i_size_read(inode))
+		return 0;
+
+	clusters_to_add = ocfs2_bytes_to_clusters(inode->i_sb, offset) -
+		ocfs2_bytes_to_clusters(inode->i_sb, i_size_read(inode));
+	total_zero_len = offset - i_size_read(inode);
+	if (clusters_to_add)
+		total_zero_len -= offset_div;
+
+	/* Allocate clusters to fill out holes, and this is only needed
+	 * when we add more than one clusters. Otherwise the cluster will
+	 * be allocated during direct IO */
+	if (clusters_to_add > 1) {
+		ret = ocfs2_extend_allocation(inode,
+				OCFS2_I(inode)->ip_clusters,
+				clusters_to_add - 1, 0);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+	}
+
+	while (total_zero_len) {
+		ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos, &num_clusters,
+				&ext_flags);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto out;
+		}
+
+		zero_start = ocfs2_clusters_to_bytes(osb->sb, p_cpos) +
+			size_div;
+		zero_len = ocfs2_clusters_to_bytes(osb->sb, num_clusters) -
+			size_div;
+		zero_len = min(total_zero_len, zero_len);
+
+		if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN)) {
+			ret = blkdev_issue_zeroout(osb->sb->s_bdev,
+					zero_start >> 9, zero_len >> 9,
+					GFP_NOFS, false);
+			if (ret < 0) {
+				mlog_errno(ret);
+				goto out;
+			}
+		}
+
+		total_zero_len -= zero_len;
+		v_cpos += ocfs2_bytes_to_clusters(osb->sb, zero_len + size_div);
+
+		/* Only at first iteration can be cluster not aligned.
+		 * So set size_div to 0 for the rest */
+		size_div = 0;
+	}
+
+out:
+	return ret;
+}
+
 static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
 		struct iov_iter *iter,
 		loff_t offset)
@@ -678,8 +789,8 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
 	struct buffer_head *di_bh = NULL;
 	size_t count = iter->count;
 	journal_t *journal = osb->journal->j_journal;
-	u32 zero_len;
-	int cluster_align;
+	u64 zero_len_head, zero_len_tail;
+	int cluster_align_head, cluster_align_tail;
 	loff_t final_size = offset + count;
 	int append_write = offset >= i_size_read(inode) ? 1 : 0;
 	unsigned int num_clusters = 0;
@@ -687,9 +798,16 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
 
 	{
 		u64 o = offset;
+		u64 s = i_size_read(inode);
+
+		zero_len_head = do_div(o, 1 << osb->s_clustersize_bits);
+		cluster_align_head = !zero_len_head;
 
-		zero_len = do_div(o, 1 << osb->s_clustersize_bits);
-		cluster_align = !zero_len;
+		zero_len_tail = osb->s_clustersize -
+			do_div(s, osb->s_clustersize);
+		if ((offset - i_size_read(inode)) < zero_len_tail)
+			zero_len_tail = offset - i_size_read(inode);
+		cluster_align_tail = !zero_len_tail;
 	}
 
 	/*
@@ -707,21 +825,23 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
 	}
 
 	if (append_write) {
-		ret = ocfs2_inode_lock(inode, &di_bh, 1);
+		ret = ocfs2_inode_lock(inode, NULL, 1);
 		if (ret < 0) {
 			mlog_errno(ret);
 			goto clean_orphan;
 		}
 
+		/* zeroing out the previously allocated cluster tail
+		 * that but not zeroed */
 		if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)))
-			ret = ocfs2_zero_extend(inode, di_bh, offset);
+			ret = ocfs2_direct_IO_zero_extend(osb, inode, offset,
+					zero_len_tail, cluster_align_tail);
 		else
-			ret = ocfs2_extend_no_holes(inode, di_bh, offset,
+			ret = ocfs2_direct_IO_extend_no_holes(osb, inode,
 					offset);
 		if (ret < 0) {
 			mlog_errno(ret);
 			ocfs2_inode_unlock(inode, 1);
-			brelse(di_bh);
 			goto clean_orphan;
 		}
 
@@ -729,13 +849,10 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
 		if (is_overwrite < 0) {
 			mlog_errno(is_overwrite);
 			ocfs2_inode_unlock(inode, 1);
-			brelse(di_bh);
 			goto clean_orphan;
 		}
 
 		ocfs2_inode_unlock(inode, 1);
-		brelse(di_bh);
-		di_bh = NULL;
 	}
 
 	written = __blockdev_direct_IO(WRITE, iocb, inode, inode->i_sb->s_bdev,
@@ -772,15 +889,23 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
 			if (ret < 0)
 				mlog_errno(ret);
 		}
-	} else if (written < 0 && append_write && !is_overwrite &&
-			!cluster_align) {
+	} else if (written > 0 && append_write && !is_overwrite &&
+			!cluster_align_head) {
+		/* zeroing out the allocated cluster head */
 		u32 p_cpos = 0;
 		u32 v_cpos = ocfs2_bytes_to_clusters(osb->sb, offset);
 
+		ret = ocfs2_inode_lock(inode, NULL, 0);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto clean_orphan;
+		}
+
 		ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos,
 				&num_clusters, &ext_flags);
 		if (ret < 0) {
 			mlog_errno(ret);
+			ocfs2_inode_unlock(inode, 0);
 			goto clean_orphan;
 		}
 
@@ -788,9 +913,11 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
 
 		ret = blkdev_issue_zeroout(osb->sb->s_bdev,
 				p_cpos << (osb->s_clustersize_bits - 9),
-				zero_len >> 9, GFP_KERNEL, false);
+				zero_len_head >> 9, GFP_NOFS, false);
 		if (ret < 0)
 			mlog_errno(ret);
+
+		ocfs2_inode_unlock(inode, 0);
 	}
 
 clean_orphan:

fs/ocfs2/cluster/heartbeat.c

@@ -1312,7 +1312,9 @@ static int o2hb_debug_init(void)
 	int ret = -ENOMEM;
 
 	o2hb_debug_dir = debugfs_create_dir(O2HB_DEBUG_DIR, NULL);
-	if (!o2hb_debug_dir) {
+	if (IS_ERR_OR_NULL(o2hb_debug_dir)) {
+		ret = o2hb_debug_dir ?
+			PTR_ERR(o2hb_debug_dir) : -ENOMEM;
 		mlog_errno(ret);
 		goto bail;
 	}
@@ -1325,7 +1327,9 @@ static int o2hb_debug_init(void)
 						 sizeof(o2hb_live_node_bitmap),
 						 O2NM_MAX_NODES,
 						 o2hb_live_node_bitmap);
-	if (!o2hb_debug_livenodes) {
+	if (IS_ERR_OR_NULL(o2hb_debug_livenodes)) {
+		ret = o2hb_debug_livenodes ?
+			PTR_ERR(o2hb_debug_livenodes) : -ENOMEM;
 		mlog_errno(ret);
 		goto bail;
 	}
@@ -1338,7 +1342,9 @@ static int o2hb_debug_init(void)
 						   sizeof(o2hb_live_region_bitmap),
 						   O2NM_MAX_REGIONS,
 						   o2hb_live_region_bitmap);
-	if (!o2hb_debug_liveregions) {
+	if (IS_ERR_OR_NULL(o2hb_debug_liveregions)) {
+		ret = o2hb_debug_liveregions ?
+			PTR_ERR(o2hb_debug_liveregions) : -ENOMEM;
 		mlog_errno(ret);
 		goto bail;
 	}
@@ -1352,7 +1358,9 @@ static int o2hb_debug_init(void)
 					  sizeof(o2hb_quorum_region_bitmap),
 					  O2NM_MAX_REGIONS,
 					  o2hb_quorum_region_bitmap);
-	if (!o2hb_debug_quorumregions) {
+	if (IS_ERR_OR_NULL(o2hb_debug_quorumregions)) {
+		ret = o2hb_debug_quorumregions ?
+			PTR_ERR(o2hb_debug_quorumregions) : -ENOMEM;
 		mlog_errno(ret);
 		goto bail;
 	}
@@ -1366,7 +1374,9 @@ static int o2hb_debug_init(void)
 					  sizeof(o2hb_failed_region_bitmap),
 					  O2NM_MAX_REGIONS,
 					  o2hb_failed_region_bitmap);
-	if (!o2hb_debug_failedregions) {
+	if (IS_ERR_OR_NULL(o2hb_debug_failedregions)) {
+		ret = o2hb_debug_failedregions ?
+			PTR_ERR(o2hb_debug_failedregions) : -ENOMEM;
 		mlog_errno(ret);
 		goto bail;
 	}
@@ -2000,7 +2010,8 @@ static int o2hb_debug_region_init(struct o2hb_region *reg, struct dentry *dir)
 
 	reg->hr_debug_dir =
 		debugfs_create_dir(config_item_name(&reg->hr_item), dir);
-	if (!reg->hr_debug_dir) {
+	if (IS_ERR_OR_NULL(reg->hr_debug_dir)) {
+		ret = reg->hr_debug_dir ? PTR_ERR(reg->hr_debug_dir) : -ENOMEM;
 		mlog_errno(ret);
 		goto bail;
 	}
@@ -2013,7 +2024,9 @@ static int o2hb_debug_region_init(struct o2hb_region *reg, struct dentry *dir)
 					  O2HB_DB_TYPE_REGION_LIVENODES,
 					  sizeof(reg->hr_live_node_bitmap),
 					  O2NM_MAX_NODES, reg);
-	if (!reg->hr_debug_livenodes) {
+	if (IS_ERR_OR_NULL(reg->hr_debug_livenodes)) {
+		ret = reg->hr_debug_livenodes ?
+			PTR_ERR(reg->hr_debug_livenodes) : -ENOMEM;
 		mlog_errno(ret);
 		goto bail;
 	}
@@ -2025,7 +2038,9 @@ static int o2hb_debug_region_init(struct o2hb_region *reg, struct dentry *dir)
 					  sizeof(*(reg->hr_db_regnum)),
 					  O2HB_DB_TYPE_REGION_NUMBER,
 					  0, O2NM_MAX_NODES, reg);
-	if (!reg->hr_debug_regnum) {
+	if (IS_ERR_OR_NULL(reg->hr_debug_regnum)) {
+		ret = reg->hr_debug_regnum ?
+			PTR_ERR(reg->hr_debug_regnum) : -ENOMEM;
 		mlog_errno(ret);
 		goto bail;
 	}
@@ -2037,7 +2052,9 @@ static int o2hb_debug_region_init(struct o2hb_region *reg, struct dentry *dir)
 					  sizeof(*(reg->hr_db_elapsed_time)),
 					  O2HB_DB_TYPE_REGION_ELAPSED_TIME,
 					  0, 0, reg);
-	if (!reg->hr_debug_elapsed_time) {
+	if (IS_ERR_OR_NULL(reg->hr_debug_elapsed_time)) {
+		ret = reg->hr_debug_elapsed_time ?
+			PTR_ERR(reg->hr_debug_elapsed_time) : -ENOMEM;
 		mlog_errno(ret);
 		goto bail;
 	}
@@ -2049,13 +2066,16 @@ static int o2hb_debug_region_init(struct o2hb_region *reg, struct dentry *dir)
 					  sizeof(*(reg->hr_db_pinned)),
 					  O2HB_DB_TYPE_REGION_PINNED,
 					  0, 0, reg);
-	if (!reg->hr_debug_pinned) {
+	if (IS_ERR_OR_NULL(reg->hr_debug_pinned)) {
+		ret = reg->hr_debug_pinned ?
+			PTR_ERR(reg->hr_debug_pinned) : -ENOMEM;
 		mlog_errno(ret);
 		goto bail;
 	}
 
-	ret = 0;
+	return 0;
 bail:
+	debugfs_remove_recursive(reg->hr_debug_dir);
 	return ret;
 }
 

fs/ocfs2/cluster/masklog.h

@@ -196,13 +196,14 @@ extern struct mlog_bits mlog_and_bits, mlog_not_bits;
 	}								\
 } while (0)
 
-#define mlog_errno(st) do {						\
+#define mlog_errno(st) ({						\
 	int _st = (st);							\
 	if (_st != -ERESTARTSYS && _st != -EINTR &&			\
 	    _st != AOP_TRUNCATED_PAGE && _st != -ENOSPC &&		\
 	    _st != -EDQUOT)						\
 		mlog(ML_ERROR, "status = %lld\n", (long long)_st);	\
-} while (0)
+	_st;								\
+})
 
 #define mlog_bug_on_msg(cond, fmt, args...) do {			\
 	if (cond) {							\

fs/ocfs2/dir.c

@@ -18,7 +18,7 @@
  *
  *   linux/fs/minix/dir.c
  *
- *   Copyright (C) 1991, 1992 Linux Torvalds
+ *   Copyright (C) 1991, 1992 Linus Torvalds
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public
@@ -2047,22 +2047,19 @@ int ocfs2_check_dir_for_entry(struct inode *dir,
 			      const char *name,
 			      int namelen)
 {
-	int ret;
+	int ret = 0;
 	struct ocfs2_dir_lookup_result lookup = { NULL, };
 
 	trace_ocfs2_check_dir_for_entry(
 		(unsigned long long)OCFS2_I(dir)->ip_blkno, namelen, name);
 
-	ret = -EEXIST;
-	if (ocfs2_find_entry(name, namelen, dir, &lookup) == 0)
-		goto bail;
+	if (ocfs2_find_entry(name, namelen, dir, &lookup) == 0) {
+		ret = -EEXIST;
+		mlog_errno(ret);
+	}
 
-	ret = 0;
-bail:
 	ocfs2_free_dir_lookup_result(&lookup);
 
-	if (ret)
-		mlog_errno(ret);
 	return ret;
 }
 

fs/ocfs2/dlmglue.c

@@ -1391,6 +1391,11 @@ static int __ocfs2_cluster_lock(struct ocfs2_super *osb,
 	int noqueue_attempted = 0;
 	int dlm_locked = 0;
 
+	if (!(lockres->l_flags & OCFS2_LOCK_INITIALIZED)) {
+		mlog_errno(-EINVAL);
+		return -EINVAL;
+	}
+
 	ocfs2_init_mask_waiter(&mw);
 
 	if (lockres->l_ops->flags & LOCK_TYPE_USES_LVB)
@@ -2954,7 +2959,7 @@ static int ocfs2_dlm_init_debug(struct ocfs2_super *osb)
 							 osb->osb_debug_root,
 							 osb,
 							 &ocfs2_dlm_debug_fops);
-	if (!dlm_debug->d_locking_state) {
+	if (IS_ERR_OR_NULL(dlm_debug->d_locking_state)) {
 		ret = -EINVAL;
 		mlog(ML_ERROR,
 		     "Unable to create locking state debugfs file.\n");

fs/ocfs2/export.c

@@ -82,7 +82,6 @@ static struct dentry *ocfs2_get_dentry(struct super_block *sb,
 	}
 
 	status = ocfs2_test_inode_bit(osb, blkno, &set);
-	trace_ocfs2_get_dentry_test_bit(status, set);
 	if (status < 0) {
 		if (status == -EINVAL) {
 			/*
@@ -96,6 +95,7 @@ static struct dentry *ocfs2_get_dentry(struct super_block *sb,
 		goto unlock_nfs_sync;
 	}
 
+	trace_ocfs2_get_dentry_test_bit(status, set);
 	/* If the inode allocator bit is clear, this inode must be stale */
 	if (!set) {
 		status = -ESTALE;

fs/ocfs2/inode.c

@@ -624,7 +624,7 @@ static int ocfs2_remove_inode(struct inode *inode,
 		ocfs2_get_system_file_inode(osb, INODE_ALLOC_SYSTEM_INODE,
 					    le16_to_cpu(di->i_suballoc_slot));
 	if (!inode_alloc_inode) {
-		status = -EEXIST;
+		status = -ENOENT;
 		mlog_errno(status);
 		goto bail;
 	}
@@ -742,7 +742,7 @@ static int ocfs2_wipe_inode(struct inode *inode,
 							       ORPHAN_DIR_SYSTEM_INODE,
 							       orphaned_slot);
 		if (!orphan_dir_inode) {
-			status = -EEXIST;
+			status = -ENOENT;
 			mlog_errno(status);
 			goto bail;
 		}

fs/ocfs2/localalloc.c

@@ -666,7 +666,7 @@ int ocfs2_reserve_local_alloc_bits(struct ocfs2_super *osb,
 	if (le32_to_cpu(alloc->id1.bitmap1.i_used) !=
 	    ocfs2_local_alloc_count_bits(alloc)) {
 		ocfs2_error(osb->sb, "local alloc inode %llu says it has "
-			    "%u free bits, but a count shows %u",
+			    "%u used bits, but a count shows %u",
 			    (unsigned long long)le64_to_cpu(alloc->i_blkno),
 			    le32_to_cpu(alloc->id1.bitmap1.i_used),
 			    ocfs2_local_alloc_count_bits(alloc));
@@ -839,7 +839,7 @@ static int ocfs2_local_alloc_find_clear_bits(struct ocfs2_super *osb,
 				     u32 *numbits,
 				     struct ocfs2_alloc_reservation *resv)
 {
-	int numfound, bitoff, left, startoff, lastzero;
+	int numfound = 0, bitoff, left, startoff, lastzero;
 	int local_resv = 0;
 	struct ocfs2_alloc_reservation r;
 	void *bitmap = NULL;

fs/ocfs2/namei.c

@@ -2322,10 +2322,10 @@ int ocfs2_orphan_del(struct ocfs2_super *osb,
 
 	trace_ocfs2_orphan_del(
 	     (unsigned long long)OCFS2_I(orphan_dir_inode)->ip_blkno,
-	     name, namelen);
+	     name, strlen(name));
 
 	/* find it's spot in the orphan directory */
-	status = ocfs2_find_entry(name, namelen, orphan_dir_inode,
+	status = ocfs2_find_entry(name, strlen(name), orphan_dir_inode,
 				  &lookup);
 	if (status) {
 		mlog_errno(status);
@@ -2808,7 +2808,7 @@ int ocfs2_mv_orphaned_inode_to_new(struct inode *dir,
 						       ORPHAN_DIR_SYSTEM_INODE,
 						       osb->slot_num);
 	if (!orphan_dir_inode) {
-		status = -EEXIST;
+		status = -ENOENT;
 		mlog_errno(status);
 		goto leave;
 	}

fs/ocfs2/refcounttree.c

@@ -4276,7 +4276,7 @@ static int ocfs2_reflink(struct dentry *old_dentry, struct inode *dir,
 	error = posix_acl_create(dir, &mode, &default_acl, &acl);
 	if (error) {
 		mlog_errno(error);
-		goto out;
+		return error;
 	}
 
 	error = ocfs2_create_inode_in_orphan(dir, mode,

fs/ocfs2/slot_map.c

@@ -427,7 +427,7 @@ int ocfs2_init_slot_info(struct ocfs2_super *osb)
 	if (!si) {
 		status = -ENOMEM;
 		mlog_errno(status);
-		goto bail;
+		return status;
 	}
 
 	si->si_extended = ocfs2_uses_extended_slot_map(osb);
@@ -452,7 +452,7 @@ int ocfs2_init_slot_info(struct ocfs2_super *osb)
 
 	osb->slot_info = (struct ocfs2_slot_info *)si;
 bail:
-	if (status < 0 && si)
+	if (status < 0)
 		__ocfs2_free_slot_info(si);
 
 	return status;

fs/ocfs2/stack_o2cb.c

@@ -295,7 +295,7 @@ static int o2cb_cluster_check(void)
 		set_bit(node_num, netmap);
 		if (!memcmp(hbmap, netmap, sizeof(hbmap)))
 			return 0;
-		if (i < O2CB_MAP_STABILIZE_COUNT)
+		if (i < O2CB_MAP_STABILIZE_COUNT - 1)
 			msleep(1000);
 	}
 

fs/ocfs2/stack_user.c

@@ -1004,10 +1004,8 @@ static int user_cluster_connect(struct ocfs2_cluster_connection *conn)
 	BUG_ON(conn == NULL);
 
 	lc = kzalloc(sizeof(struct ocfs2_live_connection), GFP_KERNEL);
-	if (!lc) {
-		rc = -ENOMEM;
-		goto out;
-	}
+	if (!lc)
+		return -ENOMEM;
 
 	init_waitqueue_head(&lc->oc_wait);
 	init_completion(&lc->oc_sync_wait);
@@ -1063,7 +1061,7 @@ static int user_cluster_connect(struct ocfs2_cluster_connection *conn)
 	}
 
 out:
-	if (rc && lc)
+	if (rc)
 		kfree(lc);
 	return rc;
 }

fs/ocfs2/suballoc.c

@@ -2499,6 +2499,8 @@ static int _ocfs2_free_suballoc_bits(handle_t *handle,
 					 alloc_bh, OCFS2_JOURNAL_ACCESS_WRITE);
 	if (status < 0) {
 		mlog_errno(status);
+		ocfs2_block_group_set_bits(handle, alloc_inode, group, group_bh,
+				start_bit, count);
 		goto bail;
 	}
 

fs/ocfs2/super.c

@@ -1112,7 +1112,7 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
 
 	osb->osb_debug_root = debugfs_create_dir(osb->uuid_str,
 						 ocfs2_debugfs_root);
-	if (!osb->osb_debug_root) {
+	if (IS_ERR_OR_NULL(osb->osb_debug_root)) {
 		status = -EINVAL;
 		mlog(ML_ERROR, "Unable to create per-mount debugfs root.\n");
 		goto read_super_error;
@@ -1122,7 +1122,7 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
 					    osb->osb_debug_root,
 					    osb,
 					    &ocfs2_osb_debug_fops);
-	if (!osb->osb_ctxt) {
+	if (IS_ERR_OR_NULL(osb->osb_ctxt)) {
 		status = -EINVAL;
 		mlog_errno(status);
 		goto read_super_error;
@@ -1606,8 +1606,9 @@ static int __init ocfs2_init(void)
 	}
 
 	ocfs2_debugfs_root = debugfs_create_dir("ocfs2", NULL);
-	if (!ocfs2_debugfs_root) {
-		status = -ENOMEM;
+	if (IS_ERR_OR_NULL(ocfs2_debugfs_root)) {
+		status = ocfs2_debugfs_root ?
+			PTR_ERR(ocfs2_debugfs_root) : -ENOMEM;
 		mlog(ML_ERROR, "Unable to create ocfs2 debugfs root.\n");
 		goto out4;
 	}
@@ -2069,6 +2070,8 @@ static int ocfs2_initialize_super(struct super_block *sb,
 	cbits = le32_to_cpu(di->id2.i_super.s_clustersize_bits);
 	bbits = le32_to_cpu(di->id2.i_super.s_blocksize_bits);
 	sb->s_maxbytes = ocfs2_max_file_offset(bbits, cbits);
+	memcpy(sb->s_uuid, di->id2.i_super.s_uuid,
+	       sizeof(di->id2.i_super.s_uuid));
 
 	osb->osb_dx_mask = (1 << (cbits - bbits)) - 1;
 
@@ -2333,7 +2336,7 @@ static int ocfs2_initialize_super(struct super_block *sb,
 		mlog_errno(status);
 		goto bail;
 	}
-	cleancache_init_shared_fs((char *)&di->id2.i_super.s_uuid, sb);
+	cleancache_init_shared_fs(sb);
 
 bail:
 	return status;
@@ -2563,22 +2566,22 @@ static void ocfs2_handle_error(struct super_block *sb)
 	ocfs2_set_ro_flag(osb, 0);
 }
 
-static char error_buf[1024];
-
-void __ocfs2_error(struct super_block *sb,
-		   const char *function,
-		   const char *fmt, ...)
+void __ocfs2_error(struct super_block *sb, const char *function,
+		  const char *fmt, ...)
 {
+	struct va_format vaf;
 	va_list args;
 
 	va_start(args, fmt);
-	vsnprintf(error_buf, sizeof(error_buf), fmt, args);
-	va_end(args);
+	vaf.fmt = fmt;
+	vaf.va = &args;
 
 	/* Not using mlog here because we want to show the actual
 	 * function the error came from. */
-	printk(KERN_CRIT "OCFS2: ERROR (device %s): %s: %s\n",
-	       sb->s_id, function, error_buf);
+	printk(KERN_CRIT "OCFS2: ERROR (device %s): %s: %pV\n",
+	       sb->s_id, function, &vaf);
+
+	va_end(args);
 
 	ocfs2_handle_error(sb);
 }
@@ -2586,18 +2589,21 @@ void __ocfs2_error(struct super_block *sb,
 /* Handle critical errors. This is intentionally more drastic than
  * ocfs2_handle_error, so we only use for things like journal errors,
  * etc. */
-void __ocfs2_abort(struct super_block* sb,
-		   const char *function,
+void __ocfs2_abort(struct super_block *sb, const char *function,
 		   const char *fmt, ...)
 {
+	struct va_format vaf;
 	va_list args;
 
 	va_start(args, fmt);
-	vsnprintf(error_buf, sizeof(error_buf), fmt, args);
-	va_end(args);
 
-	printk(KERN_CRIT "OCFS2: abort (device %s): %s: %s\n",
-	       sb->s_id, function, error_buf);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	printk(KERN_CRIT "OCFS2: abort (device %s): %s: %pV\n",
+	       sb->s_id, function, &vaf);
+
+	va_end(args);
 
 	/* We don't have the cluster support yet to go straight to
 	 * hard readonly in here. Until then, we want to keep

fs/ocfs2/xattr.c

@@ -1238,6 +1238,10 @@ static int ocfs2_xattr_block_get(struct inode *inode,
 								i,
 								&block_off,
 								&name_offset);
+			if (ret) {
+				mlog_errno(ret);
+				goto cleanup;
+			}
 			xs->base = bucket_block(xs->bucket, block_off);
 		}
 		if (ocfs2_xattr_is_local(xs->here)) {
@@ -5665,6 +5669,10 @@ static int ocfs2_delete_xattr_in_bucket(struct inode *inode,
 
 		ret = ocfs2_get_xattr_tree_value_root(inode->i_sb, bucket,
 						      i, &xv, NULL);
+		if (ret) {
+			mlog_errno(ret);
+			break;
+		}
 
 		ret = ocfs2_lock_xattr_remove_allocators(inode, xv,
 							 args->ref_ci,

fs/super.c

@@ -224,7 +224,7 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
 	s->s_maxbytes = MAX_NON_LFS;
 	s->s_op = &default_op;
 	s->s_time_gran = 1000000000;
-	s->cleancache_poolid = -1;
+	s->cleancache_poolid = CLEANCACHE_NO_POOL;
 
 	s->s_shrink.seeks = DEFAULT_SEEKS;
 	s->s_shrink.scan_objects = super_cache_scan;

include/asm-generic/pgtable.h

@@ -6,6 +6,12 @@
 
 #include <linux/mm_types.h>
 #include <linux/bug.h>
+#include <linux/errno.h>
+
+#if 4 - defined(__PAGETABLE_PUD_FOLDED) - defined(__PAGETABLE_PMD_FOLDED) != \
+	CONFIG_PGTABLE_LEVELS
+#error CONFIG_PGTABLE_LEVELS is not consistent with __PAGETABLE_{PUD,PMD}_FOLDED
+#endif
 
 /*
  * On almost all architectures and configurations, 0 can be used as the
@@ -691,6 +697,30 @@ static inline int pmd_protnone(pmd_t pmd)
 
 #endif /* CONFIG_MMU */
 
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot);
+int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot);
+int pud_clear_huge(pud_t *pud);
+int pmd_clear_huge(pmd_t *pmd);
+#else	/* !CONFIG_HAVE_ARCH_HUGE_VMAP */
+static inline int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
+{
+	return 0;
+}
+static inline int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
+{
+	return 0;
+}
+static inline int pud_clear_huge(pud_t *pud)
+{
+	return 0;
+}
+static inline int pmd_clear_huge(pmd_t *pmd)
+{
+	return 0;
+}
+#endif	/* CONFIG_HAVE_ARCH_HUGE_VMAP */
+
 #endif /* !__ASSEMBLY__ */
 
 #ifndef io_remap_pfn_range

include/linux/cleancache.h

@@ -5,6 +5,10 @@
 #include <linux/exportfs.h>
 #include <linux/mm.h>
 
+#define CLEANCACHE_NO_POOL		-1
+#define CLEANCACHE_NO_BACKEND		-2
+#define CLEANCACHE_NO_BACKEND_SHARED	-3
+
 #define CLEANCACHE_KEY_MAX 6
 
 /*
@@ -33,10 +37,9 @@ struct cleancache_ops {
 	void (*invalidate_fs)(int);
 };
 
-extern struct cleancache_ops *
-	cleancache_register_ops(struct cleancache_ops *ops);
+extern int cleancache_register_ops(struct cleancache_ops *ops);
 extern void __cleancache_init_fs(struct super_block *);
-extern void __cleancache_init_shared_fs(char *, struct super_block *);
+extern void __cleancache_init_shared_fs(struct super_block *);
 extern int  __cleancache_get_page(struct page *);
 extern void __cleancache_put_page(struct page *);
 extern void __cleancache_invalidate_page(struct address_space *, struct page *);
@@ -78,10 +81,10 @@ static inline void cleancache_init_fs(struct super_block *sb)
 		__cleancache_init_fs(sb);
 }
 
-static inline void cleancache_init_shared_fs(char *uuid, struct super_block *sb)
+static inline void cleancache_init_shared_fs(struct super_block *sb)
 {
 	if (cleancache_enabled)
-		__cleancache_init_shared_fs(uuid, sb);
+		__cleancache_init_shared_fs(sb);
 }
 
 static inline int cleancache_get_page(struct page *page)