Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:

 - most of the rest of MM

 - a small number of misc things

 - lib/ updates

 - checkpatch

 - autofs updates

 - ipc/ updates

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (126 commits)
  ipc: optimize semget/shmget/msgget for lots of keys
  ipc/sem: play nicer with large nsops allocations
  ipc/sem: drop sem_checkid helper
  ipc: convert kern_ipc_perm.refcount from atomic_t to refcount_t
  ipc: convert sem_undo_list.refcnt from atomic_t to refcount_t
  ipc: convert ipc_namespace.count from atomic_t to refcount_t
  kcov: support compat processes
  sh: defconfig: cleanup from old Kconfig options
  mn10300: defconfig: cleanup from old Kconfig options
  m32r: defconfig: cleanup from old Kconfig options
  drivers/pps: use surrounding "if PPS" to remove numerous dependency checks
  drivers/pps: aesthetic tweaks to PPS-related content
  cpumask: make cpumask_next() out-of-line
  kmod: move #ifdef CONFIG_MODULES wrapper to Makefile
  kmod: split off umh headers into its own file
  MAINTAINERS: clarify kmod is just a kernel module loader
  kmod: split out umh code into its own file
  test_kmod: flip INT checks to be consistent
  test_kmod: remove paranoid UINT_MAX check on uint range processing
  vfat: deduplicate hex2bin()
  ...

10 files changed, 119 insertions, 18 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 4b278a33ccbb..a3e6e6136a47 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2323,6 +2323,10 @@ source "kernel/livepatch/Kconfig"
 
 endmenu
 
+config ARCH_HAS_ADD_PAGES
+	def_bool y
+	depends on X86_64 && ARCH_ENABLE_MEMORY_HOTPLUG
+
 config ARCH_ENABLE_MEMORY_HOTPLUG
 	def_bool y
 	depends on X86_64 || (X86_32 && HIGHMEM)
@@ -2343,6 +2347,10 @@ config ARCH_ENABLE_HUGEPAGE_MIGRATION
 	def_bool y
 	depends on X86_64 && HUGETLB_PAGE && MIGRATION
 
+config ARCH_ENABLE_THP_MIGRATION
+	def_bool y
+	depends on X86_64 && TRANSPARENT_HUGEPAGE
+
 menu "Power management and ACPI options"
 
 config ARCH_HIBERNATION_HEADER
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index bbeae4a2bd01..5b4c44d419c5 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1172,6 +1172,23 @@ static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
 {
 	return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY);
 }
+
+#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
+static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd)
+{
+	return pmd_set_flags(pmd, _PAGE_SWP_SOFT_DIRTY);
+}
+
+static inline int pmd_swp_soft_dirty(pmd_t pmd)
+{
+	return pmd_flags(pmd) & _PAGE_SWP_SOFT_DIRTY;
+}
+
+static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd)
+{
+	return pmd_clear_flags(pmd, _PAGE_SWP_SOFT_DIRTY);
+}
+#endif
 #endif
 
 #define PKRU_AD_BIT 0x1
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 2160c1fee920..972a4698c530 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -180,15 +180,21 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
 /*
  * Encode and de-code a swap entry
  *
- * |     ...            | 11| 10|  9|8|7|6|5| 4| 3|2|1|0| <- bit number
- * |     ...            |SW3|SW2|SW1|G|L|D|A|CD|WT|U|W|P| <- bit names
- * | OFFSET (14->63) | TYPE (9-13)  |0|X|X|X| X| X|X|X|0| <- swp entry
+ * |     ...            | 11| 10|  9|8|7|6|5| 4| 3|2| 1|0| <- bit number
+ * |     ...            |SW3|SW2|SW1|G|L|D|A|CD|WT|U| W|P| <- bit names
+ * | OFFSET (14->63) | TYPE (9-13)  |0|0|X|X| X| X|X|SD|0| <- swp entry
  *
  * G (8) is aliased and used as a PROT_NONE indicator for
  * !present ptes.  We need to start storing swap entries above
  * there.  We also need to avoid using A and D because of an
  * erratum where they can be incorrectly set by hardware on
  * non-present PTEs.
+ *
+ * SD (1) in swp entry is used to store soft dirty bit, which helps us
+ * remember soft dirty over page migration
+ *
+ * Bit 7 in swp entry should be 0 because pmd_present checks not only P,
+ * but also L and G.
  */
 #define SWP_TYPE_FIRST_BIT (_PAGE_BIT_PROTNONE + 1)
 #define SWP_TYPE_BITS 5
@@ -204,7 +210,9 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
 					 ((type) << (SWP_TYPE_FIRST_BIT)) \
 					 | ((offset) << SWP_OFFSET_FIRST_BIT) })
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val((pte)) })
+#define __pmd_to_swp_entry(pmd)		((swp_entry_t) { pmd_val((pmd)) })
 #define __swp_entry_to_pte(x)		((pte_t) { .pte = (x).val })
+#define __swp_entry_to_pmd(x)		((pmd_t) { .pmd = (x).val })
 
 extern int kern_addr_valid(unsigned long addr);
 extern void cleanup_highmap(void);
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 399261ce904c..f1492473f10e 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -99,15 +99,15 @@
 /*
  * 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
- * into swap entry computation, but bit 6 is used for nonlinear
- * file mapping, so we borrow bit 7 for soft dirty tracking.
+ * with swap entry format. On x86 bits 1-4 are *not* involved
+ * into swap entry computation, but bit 7 is used for thp migration,
+ * so we borrow bit 1 for soft dirty tracking.
  *
  * Please note that this bit must be treated as swap dirty page
- * mark if and only if the PTE has present bit clear!
+ * mark if and only if the PTE/PMD has present bit clear!
  */
 #ifdef CONFIG_MEM_SOFT_DIRTY
-#define _PAGE_SWP_SOFT_DIRTY	_PAGE_PSE
+#define _PAGE_SWP_SOFT_DIRTY	_PAGE_RW
 #else
 #define _PAGE_SWP_SOFT_DIRTY	(_AT(pteval_t, 0))
 #endif
diff --git a/arch/x86/include/asm/string_32.h b/arch/x86/include/asm/string_32.h
index e9ee84873de5..e371e7229042 100644
--- a/arch/x86/include/asm/string_32.h
+++ b/arch/x86/include/asm/string_32.h
@@ -340,6 +340,30 @@ extern void *memset(void *, int, size_t);
 #endif
 #endif /* !CONFIG_FORTIFY_SOURCE */
 
+#define __HAVE_ARCH_MEMSET16
+static inline void *memset16(uint16_t *s, uint16_t v, size_t n)
+{
+	int d0, d1;
+	asm volatile("rep\n\t"
+		     "stosw"
+		     : "=&c" (d0), "=&D" (d1)
+		     : "a" (v), "1" (s), "0" (n)
+		     : "memory");
+	return s;
+}
+
+#define __HAVE_ARCH_MEMSET32
+static inline void *memset32(uint32_t *s, uint32_t v, size_t n)
+{
+	int d0, d1;
+	asm volatile("rep\n\t"
+		     "stosl"
+		     : "=&c" (d0), "=&D" (d1)
+		     : "a" (v), "1" (s), "0" (n)
+		     : "memory");
+	return s;
+}
+
 /*
  * find the first occurrence of byte 'c', or 1 past the area if none
  */
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index 2a8c822de1fc..f372a70a523f 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -58,6 +58,42 @@ extern void *__memcpy(void *to, const void *from, size_t len);
 void *memset(void *s, int c, size_t n);
 void *__memset(void *s, int c, size_t n);
 
+#define __HAVE_ARCH_MEMSET16
+static inline void *memset16(uint16_t *s, uint16_t v, size_t n)
+{
+	long d0, d1;
+	asm volatile("rep\n\t"
+		     "stosw"
+		     : "=&c" (d0), "=&D" (d1)
+		     : "a" (v), "1" (s), "0" (n)
+		     : "memory");
+	return s;
+}
+
+#define __HAVE_ARCH_MEMSET32
+static inline void *memset32(uint32_t *s, uint32_t v, size_t n)
+{
+	long d0, d1;
+	asm volatile("rep\n\t"
+		     "stosl"
+		     : "=&c" (d0), "=&D" (d1)
+		     : "a" (v), "1" (s), "0" (n)
+		     : "memory");
+	return s;
+}
+
+#define __HAVE_ARCH_MEMSET64
+static inline void *memset64(uint64_t *s, uint64_t v, size_t n)
+{
+	long d0, d1;
+	asm volatile("rep\n\t"
+		     "stosq"
+		     : "=&c" (d0), "=&D" (d1)
+		     : "a" (v), "1" (s), "0" (n)
+		     : "memory");
+	return s;
+}
+
 #define __HAVE_ARCH_MEMMOVE
 void *memmove(void *dest, const void *src, size_t count);
 void *__memmove(void *dest, const void *src, size_t count);
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 7834f73efbf1..8315e2f517a7 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -2097,7 +2097,7 @@ static int allocate_logical_cpuid(int apicid)
 
 	/* Allocate a new cpuid. */
 	if (nr_logical_cpuids >= nr_cpu_ids) {
-		WARN_ONCE(1, "APIC: NR_CPUS/possible_cpus limit of %i reached. "
+		WARN_ONCE(1, "APIC: NR_CPUS/possible_cpus limit of %u reached. "
 			     "Processor %d/0x%x and the rest are ignored.\n",
 			     nr_cpu_ids, nr_logical_cpuids, apicid);
 		return -EINVAL;
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 6e8fcb6f7e1e..28dafed6c682 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -168,7 +168,7 @@ void __init setup_per_cpu_areas(void)
 	unsigned long delta;
 	int rc;
 
-	pr_info("NR_CPUS:%d nr_cpumask_bits:%d nr_cpu_ids:%d nr_node_ids:%d\n",
+	pr_info("NR_CPUS:%d nr_cpumask_bits:%d nr_cpu_ids:%u nr_node_ids:%d\n",
 		NR_CPUS, nr_cpumask_bits, nr_cpu_ids, nr_node_ids);
 
 	/*
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 54b9e89d4d6b..cd6622c3204e 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1461,7 +1461,7 @@ __init void prefill_possible_map(void)
 
 	/* nr_cpu_ids could be reduced via nr_cpus= */
 	if (possible > nr_cpu_ids) {
-		pr_warn("%d Processors exceeds NR_CPUS limit of %d\n",
+		pr_warn("%d Processors exceeds NR_CPUS limit of %u\n",
 			possible, nr_cpu_ids);
 		possible = nr_cpu_ids;
 	}
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 136422d7d539..048fbe8fc274 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -761,7 +761,7 @@ void __init paging_init(void)
  * After memory hotplug the variables max_pfn, max_low_pfn and high_memory need
  * updating.
  */
-static void  update_end_of_memory_vars(u64 start, u64 size)
+static void update_end_of_memory_vars(u64 start, u64 size)
 {
 	unsigned long end_pfn = PFN_UP(start + size);
 
@@ -772,22 +772,30 @@ static void  update_end_of_memory_vars(u64 start, u64 size)
 	}
 }
 
-int arch_add_memory(int nid, u64 start, u64 size, bool want_memblock)
+int add_pages(int nid, unsigned long start_pfn,
+	      unsigned long nr_pages, bool want_memblock)
 {
-	unsigned long start_pfn = start >> PAGE_SHIFT;
-	unsigned long nr_pages = size >> PAGE_SHIFT;
 	int ret;
 
-	init_memory_mapping(start, start + size);
-
 	ret = __add_pages(nid, start_pfn, nr_pages, want_memblock);
 	WARN_ON_ONCE(ret);
 
 	/* update max_pfn, max_low_pfn and high_memory */
-	update_end_of_memory_vars(start, size);
+	update_end_of_memory_vars(start_pfn << PAGE_SHIFT,
+				  nr_pages << PAGE_SHIFT);
 
 	return ret;
 }
+
+int arch_add_memory(int nid, u64 start, u64 size, bool want_memblock)
+{
+	unsigned long start_pfn = start >> PAGE_SHIFT;
+	unsigned long nr_pages = size >> PAGE_SHIFT;
+
+	init_memory_mapping(start, start + size);
+
+	return add_pages(nid, start_pfn, nr_pages, want_memblock);
+}
 EXPORT_SYMBOL_GPL(arch_add_memory);
 
 #define PAGE_INUSE 0xFD