Merge branch 'akpm' (patchbomb from Andrew) into next

Merge misc updates from Andrew Morton:

 - a few fixes for 3.16.  Cc'ed to stable so they'll get there somehow.

 - various misc fixes and cleanups

 - most of the ocfs2 queue.  Review is slow...

 - most of MM.  The MM queue is pretty huge this time, but not much in
   the way of feature work.

 - some tweaks under kernel/

 - printk maintenance work

 - updates to lib/

 - checkpatch updates

 - tweaks to init/

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (276 commits)
  fs/autofs4/dev-ioctl.c: add __init to autofs_dev_ioctl_init
  fs/ncpfs/getopt.c: replace simple_strtoul by kstrtoul
  init/main.c: remove an ifdef
  kthreads: kill CLONE_KERNEL, change kernel_thread(kernel_init) to avoid CLONE_SIGHAND
  init/main.c: add initcall_blacklist kernel parameter
  init/main.c: don't use pr_debug()
  fs/binfmt_flat.c: make old_reloc() static
  fs/binfmt_elf.c: fix bool assignements
  fs/efs: convert printk(KERN_DEBUG to pr_debug
  fs/efs: add pr_fmt / use __func__
  fs/efs: convert printk to pr_foo()
  scripts/checkpatch.pl: device_initcall is not the only __initcall substitute
  checkpatch: check stable email address
  checkpatch: warn on unnecessary void function return statements
  checkpatch: prefer kstrto<foo> to sscanf(buf, "%<lhuidx>", &bar);
  checkpatch: add warning for kmalloc/kzalloc with multiply
  checkpatch: warn on #defines ending in semicolon
  checkpatch: make --strict a default for files in drivers/net and net/
  checkpatch: always warn on missing blank line after variable declaration block
  checkpatch: fix wildcard DT compatible string checking
  ...

20 files changed, 123 insertions, 141 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 7a01d4335029..272b493ea1bf 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -26,7 +26,7 @@ config X86
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select HAVE_AOUT if X86_32
 	select HAVE_UNSTABLE_SCHED_CLOCK
-	select ARCH_SUPPORTS_NUMA_BALANCING
+	select ARCH_SUPPORTS_NUMA_BALANCING if X86_64
 	select ARCH_SUPPORTS_INT128 if X86_64
 	select ARCH_WANTS_PROT_NUMA_PROT_NONE
 	select HAVE_IDE
@@ -41,7 +41,7 @@ config X86
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select ARCH_WANT_FRAME_POINTERS
 	select HAVE_DMA_ATTRS
-	select HAVE_DMA_CONTIGUOUS if !SWIOTLB
+	select HAVE_DMA_CONTIGUOUS
 	select HAVE_KRETPROBES
 	select GENERIC_EARLY_IOREMAP
 	select HAVE_OPTPROBES
@@ -105,7 +105,7 @@ config X86
 	select HAVE_ARCH_SECCOMP_FILTER
 	select BUILDTIME_EXTABLE_SORT
 	select GENERIC_CMOS_UPDATE
-	select HAVE_ARCH_SOFT_DIRTY
+	select HAVE_ARCH_SOFT_DIRTY if X86_64
 	select CLOCKSOURCE_WATCHDOG
 	select GENERIC_CLOCKEVENTS
 	select ARCH_CLOCKSOURCE_DATA
@@ -1874,6 +1874,10 @@ config ARCH_ENABLE_SPLIT_PMD_PTLOCK
 	def_bool y
 	depends on X86_64 || X86_PAE
 
+config ARCH_ENABLE_HUGEPAGE_MIGRATION
+	def_bool y
+	depends on X86_64 && HUGETLB_PAGE && MIGRATION
+
 menu "Power management and ACPI options"
 
 config ARCH_HIBERNATION_HEADER
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 6e4ce2df87cf..958b90f761e5 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -176,8 +176,6 @@ int mce_available(struct cpuinfo_x86 *c);
 DECLARE_PER_CPU(unsigned, mce_exception_count);
 DECLARE_PER_CPU(unsigned, mce_poll_count);
 
-extern atomic_t mce_entry;
-
 typedef DECLARE_BITMAP(mce_banks_t, MAX_NR_BANKS);
 DECLARE_PER_CPU(mce_banks_t, mce_poll_banks);
 
diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h
index 0d193e234647..206a87fdd22d 100644
--- a/arch/x86/include/asm/pgtable-2level.h
+++ b/arch/x86/include/asm/pgtable-2level.h
@@ -62,66 +62,14 @@ static inline unsigned long pte_bitop(unsigned long value, unsigned int rightshi
 	return ((value >> rightshift) & mask) << leftshift;
 }
 
-#ifdef CONFIG_MEM_SOFT_DIRTY
-
-/*
- * Bits _PAGE_BIT_PRESENT, _PAGE_BIT_FILE, _PAGE_BIT_SOFT_DIRTY and
- * _PAGE_BIT_PROTNONE are taken, split up the 28 bits of offset
- * into this range.
- */
-#define PTE_FILE_MAX_BITS	28
-#define PTE_FILE_SHIFT1		(_PAGE_BIT_PRESENT + 1)
-#define PTE_FILE_SHIFT2		(_PAGE_BIT_FILE + 1)
-#define PTE_FILE_SHIFT3		(_PAGE_BIT_PROTNONE + 1)
-#define PTE_FILE_SHIFT4		(_PAGE_BIT_SOFT_DIRTY + 1)
-#define PTE_FILE_BITS1		(PTE_FILE_SHIFT2 - PTE_FILE_SHIFT1 - 1)
-#define PTE_FILE_BITS2		(PTE_FILE_SHIFT3 - PTE_FILE_SHIFT2 - 1)
-#define PTE_FILE_BITS3		(PTE_FILE_SHIFT4 - PTE_FILE_SHIFT3 - 1)
-
-#define PTE_FILE_MASK1		((1U << PTE_FILE_BITS1) - 1)
-#define PTE_FILE_MASK2		((1U << PTE_FILE_BITS2) - 1)
-#define PTE_FILE_MASK3		((1U << PTE_FILE_BITS3) - 1)
-
-#define PTE_FILE_LSHIFT2	(PTE_FILE_BITS1)
-#define PTE_FILE_LSHIFT3	(PTE_FILE_BITS1 + PTE_FILE_BITS2)
-#define PTE_FILE_LSHIFT4	(PTE_FILE_BITS1 + PTE_FILE_BITS2 + PTE_FILE_BITS3)
-
-static __always_inline pgoff_t pte_to_pgoff(pte_t pte)
-{
-	return (pgoff_t)
-		(pte_bitop(pte.pte_low, PTE_FILE_SHIFT1, PTE_FILE_MASK1,  0)		    +
-		 pte_bitop(pte.pte_low, PTE_FILE_SHIFT2, PTE_FILE_MASK2,  PTE_FILE_LSHIFT2) +
-		 pte_bitop(pte.pte_low, PTE_FILE_SHIFT3, PTE_FILE_MASK3,  PTE_FILE_LSHIFT3) +
-		 pte_bitop(pte.pte_low, PTE_FILE_SHIFT4,           -1UL,  PTE_FILE_LSHIFT4));
-}
-
-static __always_inline pte_t pgoff_to_pte(pgoff_t off)
-{
-	return (pte_t){
-		.pte_low =
-			pte_bitop(off,                0, PTE_FILE_MASK1,  PTE_FILE_SHIFT1) +
-			pte_bitop(off, PTE_FILE_LSHIFT2, PTE_FILE_MASK2,  PTE_FILE_SHIFT2) +
-			pte_bitop(off, PTE_FILE_LSHIFT3, PTE_FILE_MASK3,  PTE_FILE_SHIFT3) +
-			pte_bitop(off, PTE_FILE_LSHIFT4,           -1UL,  PTE_FILE_SHIFT4) +
-			_PAGE_FILE,
-	};
-}
-
-#else /* CONFIG_MEM_SOFT_DIRTY */
-
 /*
  * Bits _PAGE_BIT_PRESENT, _PAGE_BIT_FILE and _PAGE_BIT_PROTNONE are taken,
  * split up the 29 bits of offset into this range.
  */
 #define PTE_FILE_MAX_BITS	29
 #define PTE_FILE_SHIFT1		(_PAGE_BIT_PRESENT + 1)
-#if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE
 #define PTE_FILE_SHIFT2		(_PAGE_BIT_FILE + 1)
 #define PTE_FILE_SHIFT3		(_PAGE_BIT_PROTNONE + 1)
-#else
-#define PTE_FILE_SHIFT2		(_PAGE_BIT_PROTNONE + 1)
-#define PTE_FILE_SHIFT3		(_PAGE_BIT_FILE + 1)
-#endif
 #define PTE_FILE_BITS1		(PTE_FILE_SHIFT2 - PTE_FILE_SHIFT1 - 1)
 #define PTE_FILE_BITS2		(PTE_FILE_SHIFT3 - PTE_FILE_SHIFT2 - 1)
 
@@ -150,16 +98,9 @@ static __always_inline pte_t pgoff_to_pte(pgoff_t off)
 	};
 }
 
-#endif /* CONFIG_MEM_SOFT_DIRTY */
-
 /* Encode and de-code a swap entry */
-#if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE
 #define SWP_TYPE_BITS (_PAGE_BIT_FILE - _PAGE_BIT_PRESENT - 1)
 #define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 1)
-#else
-#define SWP_TYPE_BITS (_PAGE_BIT_PROTNONE - _PAGE_BIT_PRESENT - 1)
-#define SWP_OFFSET_SHIFT (_PAGE_BIT_FILE + 1)
-#endif
 
 #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS)
 
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index b459ddf27d64..0ec056012618 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -131,7 +131,8 @@ static inline int pte_exec(pte_t pte)
 
 static inline int pte_special(pte_t pte)
 {
-	return pte_flags(pte) & _PAGE_SPECIAL;
+	return (pte_flags(pte) & (_PAGE_PRESENT|_PAGE_SPECIAL)) ==
+				 (_PAGE_PRESENT|_PAGE_SPECIAL);
 }
 
 static inline unsigned long pte_pfn(pte_t pte)
@@ -296,6 +297,7 @@ static inline pmd_t pmd_mknotpresent(pmd_t pmd)
 	return pmd_clear_flags(pmd, _PAGE_PRESENT);
 }
 
+#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
 static inline int pte_soft_dirty(pte_t pte)
 {
 	return pte_flags(pte) & _PAGE_SOFT_DIRTY;
@@ -331,6 +333,8 @@ static inline int pte_file_soft_dirty(pte_t pte)
 	return pte_flags(pte) & _PAGE_SOFT_DIRTY;
 }
 
+#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */
+
 /*
  * Mask out unsupported bits in a present pgprot.  Non-present pgprots
  * can use those bits for other purposes, so leave them be.
@@ -452,6 +456,12 @@ static inline int pte_present(pte_t a)
 			       _PAGE_NUMA);
 }
 
+#define pte_present_nonuma pte_present_nonuma
+static inline int pte_present_nonuma(pte_t a)
+{
+	return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE);
+}
+
 #define pte_accessible pte_accessible
 static inline bool pte_accessible(struct mm_struct *mm, pte_t a)
 {
@@ -858,23 +868,25 @@ static inline void update_mmu_cache_pmd(struct vm_area_struct *vma,
 {
 }
 
+#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
 static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
 {
-	VM_BUG_ON(pte_present(pte));
+	VM_BUG_ON(pte_present_nonuma(pte));
 	return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY);
 }
 
 static inline int pte_swp_soft_dirty(pte_t pte)
 {
-	VM_BUG_ON(pte_present(pte));
+	VM_BUG_ON(pte_present_nonuma(pte));
 	return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY;
 }
 
 static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
 {
-	VM_BUG_ON(pte_present(pte));
+	VM_BUG_ON(pte_present_nonuma(pte));
 	return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY);
 }
+#endif
 
 #include <asm-generic/pgtable.h>
 #endif	/* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index e22c1dbf7feb..5be9063545d2 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -143,12 +143,12 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
 #define pte_unmap(pte) ((void)(pte))/* NOP */
 
 /* Encode and de-code a swap entry */
-#if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE
 #define SWP_TYPE_BITS (_PAGE_BIT_FILE - _PAGE_BIT_PRESENT - 1)
-#define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 1)
+#ifdef CONFIG_NUMA_BALANCING
+/* Automatic NUMA balancing needs to be distinguishable from swap entries */
+#define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 2)
 #else
-#define SWP_TYPE_BITS (_PAGE_BIT_PROTNONE - _PAGE_BIT_PRESENT - 1)
-#define SWP_OFFSET_SHIFT (_PAGE_BIT_FILE + 1)
+#define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 1)
 #endif
 
 #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS)
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index eb3d44945133..f216963760e5 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -16,15 +16,26 @@
 #define _PAGE_BIT_PSE		7	/* 4 MB (or 2MB) page */
 #define _PAGE_BIT_PAT		7	/* on 4KB pages */
 #define _PAGE_BIT_GLOBAL	8	/* Global TLB entry PPro+ */
-#define _PAGE_BIT_UNUSED1	9	/* available for programmer */
-#define _PAGE_BIT_IOMAP		10	/* flag used to indicate IO mapping */
-#define _PAGE_BIT_HIDDEN	11	/* hidden by kmemcheck */
+#define _PAGE_BIT_SOFTW1	9	/* available for programmer */
+#define _PAGE_BIT_SOFTW2	10	/* " */
+#define _PAGE_BIT_SOFTW3	11	/* " */
 #define _PAGE_BIT_PAT_LARGE	12	/* On 2MB or 1GB pages */
-#define _PAGE_BIT_SPECIAL	_PAGE_BIT_UNUSED1
-#define _PAGE_BIT_CPA_TEST	_PAGE_BIT_UNUSED1
-#define _PAGE_BIT_SPLITTING	_PAGE_BIT_UNUSED1 /* only valid on a PSE pmd */
+#define _PAGE_BIT_SPECIAL	_PAGE_BIT_SOFTW1
+#define _PAGE_BIT_CPA_TEST	_PAGE_BIT_SOFTW1
+#define _PAGE_BIT_SPLITTING	_PAGE_BIT_SOFTW2 /* only valid on a PSE pmd */
+#define _PAGE_BIT_IOMAP		_PAGE_BIT_SOFTW2 /* flag used to indicate IO mapping */
+#define _PAGE_BIT_HIDDEN	_PAGE_BIT_SOFTW3 /* hidden by kmemcheck */
+#define _PAGE_BIT_SOFT_DIRTY	_PAGE_BIT_SOFTW3 /* software dirty tracking */
 #define _PAGE_BIT_NX           63       /* No execute: only valid after cpuid check */
 
+/*
+ * Swap offsets on configurations that allow automatic NUMA balancing use the
+ * bits after _PAGE_BIT_GLOBAL. To uniquely distinguish NUMA hinting PTEs from
+ * swap entries, we use the first bit after _PAGE_BIT_GLOBAL and shrink the
+ * maximum possible swap space from 16TB to 8TB.
+ */
+#define _PAGE_BIT_NUMA		(_PAGE_BIT_GLOBAL+1)
+
 /* If _PAGE_BIT_PRESENT is clear, we use these: */
 /* - if the user mapped it with PROT_NONE; pte_present gives true */
 #define _PAGE_BIT_PROTNONE	_PAGE_BIT_GLOBAL
@@ -40,7 +51,7 @@
 #define _PAGE_DIRTY	(_AT(pteval_t, 1) << _PAGE_BIT_DIRTY)
 #define _PAGE_PSE	(_AT(pteval_t, 1) << _PAGE_BIT_PSE)
 #define _PAGE_GLOBAL	(_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL)
-#define _PAGE_UNUSED1	(_AT(pteval_t, 1) << _PAGE_BIT_UNUSED1)
+#define _PAGE_SOFTW1	(_AT(pteval_t, 1) << _PAGE_BIT_SOFTW1)
 #define _PAGE_IOMAP	(_AT(pteval_t, 1) << _PAGE_BIT_IOMAP)
 #define _PAGE_PAT	(_AT(pteval_t, 1) << _PAGE_BIT_PAT)
 #define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE)
@@ -61,8 +72,6 @@
  * they do not conflict with each other.
  */
 
-#define _PAGE_BIT_SOFT_DIRTY	_PAGE_BIT_HIDDEN
-
 #ifdef CONFIG_MEM_SOFT_DIRTY
 #define _PAGE_SOFT_DIRTY	(_AT(pteval_t, 1) << _PAGE_BIT_SOFT_DIRTY)
 #else
@@ -70,6 +79,21 @@
 #endif
 
 /*
+ * _PAGE_NUMA distinguishes between a numa hinting minor fault and a page
+ * that is not present. The hinting fault gathers numa placement statistics
+ * (see pte_numa()). The bit is always zero when the PTE is not present.
+ *
+ * The bit picked must be always zero when the pmd is present and not
+ * present, so that we don't lose information when we set it while
+ * atomically clearing the present bit.
+ */
+#ifdef CONFIG_NUMA_BALANCING
+#define _PAGE_NUMA	(_AT(pteval_t, 1) << _PAGE_BIT_NUMA)
+#else
+#define _PAGE_NUMA	(_AT(pteval_t, 0))
+#endif
+
+/*
  * Tracking soft dirty bit when a page goes to a swap is tricky.
  * We need a bit which can be stored in pte _and_ not conflict
  * with swap entry format. On x86 bits 6 and 7 are *not* involved
@@ -94,26 +118,6 @@
 #define _PAGE_FILE	(_AT(pteval_t, 1) << _PAGE_BIT_FILE)
 #define _PAGE_PROTNONE	(_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE)
 
-/*
- * _PAGE_NUMA indicates that this page will trigger a numa hinting
- * minor page fault to gather numa placement statistics (see
- * pte_numa()). The bit picked (8) is within the range between
- * _PAGE_FILE (6) and _PAGE_PROTNONE (8) bits. Therefore, it doesn't
- * require changes to the swp entry format because that bit is always
- * zero when the pte is not present.
- *
- * The bit picked must be always zero when the pmd is present and not
- * present, so that we don't lose information when we set it while
- * atomically clearing the present bit.
- *
- * Because we shared the same bit (8) with _PAGE_PROTNONE this can be
- * interpreted as _PAGE_NUMA only in places that _PAGE_PROTNONE
- * couldn't reach, like handle_mm_fault() (see access_error in
- * arch/x86/mm/fault.c, the vma protection must not be PROT_NONE for
- * handle_mm_fault() to be invoked).
- */
-#define _PAGE_NUMA	_PAGE_PROTNONE
-
 #define _PAGE_TABLE	(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |	\
 			 _PAGE_ACCESSED | _PAGE_DIRTY)
 #define _KERNPG_TABLE	(_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED |	\
@@ -122,8 +126,8 @@
 /* Set of bits not changed in pte_modify */
 #define _PAGE_CHG_MASK	(PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT |		\
 			 _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY |	\
-			 _PAGE_SOFT_DIRTY)
-#define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE)
+			 _PAGE_SOFT_DIRTY | _PAGE_NUMA)
+#define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE | _PAGE_NUMA)
 
 #define _PAGE_CACHE_MASK	(_PAGE_PCD | _PAGE_PWT)
 #define _PAGE_CACHE_WB		(0)
diff --git a/arch/x86/include/asm/swiotlb.h b/arch/x86/include/asm/swiotlb.h
index 977f1761a25d..ab05d73e2bb7 100644
--- a/arch/x86/include/asm/swiotlb.h
+++ b/arch/x86/include/asm/swiotlb.h
@@ -29,4 +29,11 @@ static inline void pci_swiotlb_late_init(void)
 
 static inline void dma_mark_clean(void *addr, size_t size) {}
 
+extern void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
+					dma_addr_t *dma_handle, gfp_t flags,
+					struct dma_attrs *attrs);
+extern void x86_swiotlb_free_coherent(struct device *dev, size_t size,
+					void *vaddr, dma_addr_t dma_addr,
+					struct dma_attrs *attrs);
+
 #endif /* _ASM_X86_SWIOTLB_H */
diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h
index 3f556c6a0157..2b19caa4081c 100644
--- a/arch/x86/include/asm/unistd.h
+++ b/arch/x86/include/asm/unistd.h
@@ -41,7 +41,6 @@
 # define __ARCH_WANT_SYS_OLD_GETRLIMIT
 # define __ARCH_WANT_SYS_OLD_UNAME
 # define __ARCH_WANT_SYS_PAUSE
-# define __ARCH_WANT_SYS_SGETMASK
 # define __ARCH_WANT_SYS_SIGNAL
 # define __ARCH_WANT_SYS_SIGPENDING
 # define __ARCH_WANT_SYS_SIGPROCMASK
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index b574b295a2f9..8e3842fc8bea 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -512,7 +512,7 @@ gart_free_coherent(struct device *dev, size_t size, void *vaddr,
 		   dma_addr_t dma_addr, struct dma_attrs *attrs)
 {
 	gart_unmap_page(dev, dma_addr, size, DMA_BIDIRECTIONAL, NULL);
-	free_pages((unsigned long)vaddr, get_order(size));
+	dma_generic_free_coherent(dev, size, vaddr, dma_addr, attrs);
 }
 
 static int gart_mapping_error(struct device *dev, dma_addr_t dma_addr)
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 6cc800381d14..bb92f38153b2 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -60,8 +60,6 @@ static DEFINE_MUTEX(mce_chrdev_read_mutex);
 
 #define SPINUNIT 100	/* 100ns */
 
-atomic_t mce_entry;
-
 DEFINE_PER_CPU(unsigned, mce_exception_count);
 
 struct mce_bank *mce_banks __read_mostly;
@@ -1040,8 +1038,6 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
 	char *msg = "Unknown";
 
-	atomic_inc(&mce_entry);
-
 	this_cpu_inc(mce_exception_count);
 
 	if (!cfg->banks)
@@ -1171,7 +1167,6 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 		mce_report_event(regs);
 	mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
 out:
-	atomic_dec(&mce_entry);
 	sync_core();
 }
 EXPORT_SYMBOL_GPL(do_machine_check);
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 068054f4bf20..eda1a865641e 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -172,7 +172,7 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
 	 */
 	load_ucode_bsp();
 
-	if (console_loglevel == 10)
+	if (console_loglevel >= CONSOLE_LOGLEVEL_DEBUG)
 		early_printk("Kernel alive\n");
 
 	clear_page(init_level4_pgt);
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index f7d0672481fd..a25e202bb319 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -97,12 +97,17 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size,
 
 	dma_mask = dma_alloc_coherent_mask(dev, flag);
 
-	flag |= __GFP_ZERO;
+	flag &= ~__GFP_ZERO;
 again:
 	page = NULL;
 	/* CMA can be used only in the context which permits sleeping */
-	if (flag & __GFP_WAIT)
+	if (flag & __GFP_WAIT) {
 		page = dma_alloc_from_contiguous(dev, count, get_order(size));
+		if (page && page_to_phys(page) + size > dma_mask) {
+			dma_release_from_contiguous(dev, page, count);
+			page = NULL;
+		}
+	}
 	/* fallback */
 	if (!page)
 		page = alloc_pages_node(dev_to_node(dev), flag, get_order(size));
@@ -120,7 +125,7 @@ again:
 
 		return NULL;
 	}
-
+	memset(page_address(page), 0, size);
 	*dma_addr = addr;
 	return page_address(page);
 }
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index 6c483ba98b9c..77dd0ad58be4 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -14,7 +14,7 @@
 #include <asm/iommu_table.h>
 int swiotlb __read_mostly;
 
-static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
+void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 					dma_addr_t *dma_handle, gfp_t flags,
 					struct dma_attrs *attrs)
 {
@@ -28,11 +28,14 @@ static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 	return swiotlb_alloc_coherent(hwdev, size, dma_handle, flags);
 }
 
-static void x86_swiotlb_free_coherent(struct device *dev, size_t size,
+void x86_swiotlb_free_coherent(struct device *dev, size_t size,
 				      void *vaddr, dma_addr_t dma_addr,
 				      struct dma_attrs *attrs)
 {
-	swiotlb_free_coherent(dev, size, vaddr, dma_addr);
+	if (is_swiotlb_buffer(dma_to_phys(dev, dma_addr)))
+		swiotlb_free_coherent(dev, size, vaddr, dma_addr);
+	else
+		dma_generic_free_coherent(dev, size, vaddr, dma_addr, attrs);
 }
 
 static struct dma_map_ops swiotlb_dma_ops = {
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 09c76d265550..78a0e6298922 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1119,7 +1119,7 @@ void __init setup_arch(char **cmdline_p)
 	setup_real_mode();
 
 	memblock_set_current_limit(get_max_mapped());
-	dma_contiguous_reserve(0);
+	dma_contiguous_reserve(max_pfn_mapped << PAGE_SHIFT);
 
 	/*
 	 * NOTE: On x86-32, only from this point on, fixmaps are ready for use.
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 8c9f647ff9e1..8b977ebf9388 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -58,11 +58,6 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 {
 	return NULL;
 }
-
-int pmd_huge_support(void)
-{
-	return 0;
-}
 #else
 
 struct page *
@@ -80,11 +75,6 @@ int pud_huge(pud_t pud)
 {
 	return !!(pud_val(pud) & _PAGE_PSE);
 }
-
-int pmd_huge_support(void)
-{
-	return 1;
-}
 #endif
 
 #ifdef CONFIG_HUGETLB_PAGE
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index f35c66c5959a..b92591fa8970 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1230,17 +1230,43 @@ const char *arch_vma_name(struct vm_area_struct *vma)
 	return NULL;
 }
 
-#ifdef CONFIG_X86_UV
-unsigned long memory_block_size_bytes(void)
+static unsigned long probe_memory_block_size(void)
 {
+	/* start from 2g */
+	unsigned long bz = 1UL<<31;
+
+#ifdef CONFIG_X86_UV
 	if (is_uv_system()) {
 		printk(KERN_INFO "UV: memory block size 2GB\n");
 		return 2UL * 1024 * 1024 * 1024;
 	}
-	return MIN_MEMORY_BLOCK_SIZE;
-}
 #endif
 
+	/* less than 64g installed */
+	if ((max_pfn << PAGE_SHIFT) < (16UL << 32))
+		return MIN_MEMORY_BLOCK_SIZE;
+
+	/* get the tail size */
+	while (bz > MIN_MEMORY_BLOCK_SIZE) {
+		if (!((max_pfn << PAGE_SHIFT) & (bz - 1)))
+			break;
+		bz >>= 1;
+	}
+
+	printk(KERN_DEBUG "memory block size : %ldMB\n", bz >> 20);
+
+	return bz;
+}
+
+static unsigned long memory_block_size_probed;
+unsigned long memory_block_size_bytes(void)
+{
+	if (!memory_block_size_probed)
+		memory_block_size_probed = probe_memory_block_size();
+
+	return memory_block_size_probed;
+}
+
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 /*
  * Initialise the sparsemem vmemmap using huge-pages at the PMD level.
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 1d045f9c390f..a32b706c401a 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -559,7 +559,7 @@ static void __init numa_clear_kernel_node_hotplug(void)
 	int i, nid;
 	nodemask_t numa_kernel_nodes = NODE_MASK_NONE;
 	unsigned long start, end;
-	struct memblock_type *type = &memblock.reserved;
+	struct memblock_region *r;
 
 	/*
 	 * At this time, all memory regions reserved by memblock are
@@ -573,8 +573,8 @@ static void __init numa_clear_kernel_node_hotplug(void)
 	}
 
 	/* Mark all kernel nodes. */
-	for (i = 0; i < type->cnt; i++)
-		node_set(type->regions[i].nid, numa_kernel_nodes);
+	for_each_memblock(reserved, r)
+		node_set(r->nid, numa_kernel_nodes);
 
 	/* Clear MEMBLOCK_HOTPLUG flag for memory in kernel nodes. */
 	for (i = 0; i < numa_meminfo.nr_blks; i++) {
diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c
index 461bc8289024..6629f397b467 100644
--- a/arch/x86/mm/pageattr-test.c
+++ b/arch/x86/mm/pageattr-test.c
@@ -35,7 +35,7 @@ enum {
 
 static int pte_testbit(pte_t pte)
 {
-	return pte_flags(pte) & _PAGE_UNUSED1;
+	return pte_flags(pte) & _PAGE_SOFTW1;
 }
 
 struct split_state {
diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c
index 9d8a509c9730..5ceda85b8687 100644
--- a/arch/x86/pci/sta2x11-fixup.c
+++ b/arch/x86/pci/sta2x11-fixup.c
@@ -173,9 +173,7 @@ static void *sta2x11_swiotlb_alloc_coherent(struct device *dev,
 {
 	void *vaddr;
 
-	vaddr = dma_generic_alloc_coherent(dev, size, dma_handle, flags, attrs);
-	if (!vaddr)
-		vaddr = swiotlb_alloc_coherent(dev, size, dma_handle, flags);
+	vaddr = x86_swiotlb_alloc_coherent(dev, size, dma_handle, flags, attrs);
 	*dma_handle = p2a(*dma_handle, to_pci_dev(dev));
 	return vaddr;
 }
@@ -183,7 +181,7 @@ static void *sta2x11_swiotlb_alloc_coherent(struct device *dev,
 /* We have our own dma_ops: the same as swiotlb but from alloc (above) */
 static struct dma_map_ops sta2x11_dma_ops = {
 	.alloc = sta2x11_swiotlb_alloc_coherent,
-	.free = swiotlb_free_coherent,
+	.free = x86_swiotlb_free_coherent,
 	.map_page = swiotlb_map_page,
 	.unmap_page = swiotlb_unmap_page,
 	.map_sg = swiotlb_map_sg_attrs,
diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c
index be27da60dc8f..c89c93320c12 100644
--- a/arch/x86/platform/uv/uv_nmi.c
+++ b/arch/x86/platform/uv/uv_nmi.c
@@ -85,7 +85,7 @@ static cpumask_var_t uv_nmi_cpu_mask;
  * Default is all stack dumps go to the console and buffer.
  * Lower level to send to log buffer only.
  */
-static int uv_nmi_loglevel = 7;
+static int uv_nmi_loglevel = CONSOLE_LOGLEVEL_DEFAULT;
 module_param_named(dump_loglevel, uv_nmi_loglevel, int, 0644);
 
 /*