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 <[email protected]>: (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__