Merge branch 'akpm' (patch-bomb from Andrew Morton)

Merge patches from Andrew Morton:
 - memstick fixes

 - the rest of MM

 - various misc bits that were awaiting merges from linux-next into
   mainline: seq_file, printk, rtc, completions, w1, softirqs, llist,
   kfifo, hfsplus

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (72 commits)
  cmdline-parser: fix build
  hfsplus: Fix undefined __divdi3 in hfsplus_init_header_node()
  kfifo API type safety
  kfifo: kfifo_copy_{to,from}_user: fix copied bytes calculation
  sound/core/memalloc.c: use gen_pool_dma_alloc() to allocate iram buffer
  llists-move-llist_reverse_order-from-raid5-to-llistc-fix
  llists: move llist_reverse_order from raid5 to llist.c
  kernel: fix generic_exec_single indentation
  kernel-provide-a-__smp_call_function_single-stub-for-config_smp-fix
  kernel: provide a __smp_call_function_single stub for !CONFIG_SMP
  kernel: remove CONFIG_USE_GENERIC_SMP_HELPERS
  revert "softirq: Add support for triggering softirq work on softirqs"
  drivers/w1/masters/w1-gpio.c: use dev_get_platdata()
  sched: remove INIT_COMPLETION
  tree-wide: use reinit_completion instead of INIT_COMPLETION
  sched: replace INIT_COMPLETION with reinit_completion
  drivers/rtc/rtc-hid-sensor-time.c: enable HID input processing early
  drivers/rtc/rtc-hid-sensor-time.c: use dev_get_platdata()
  vsprintf: ignore %n again
  seq_file: remove "%n" usage from seq_file users
  ...

13 files changed, 230 insertions, 119 deletions

diff --git a/include/linux/cmdline-parser.h b/include/linux/cmdline-parser.h
index 98e892ef6d5a..a0f9280421ec 100644
--- a/include/linux/cmdline-parser.h
+++ b/include/linux/cmdline-parser.h
@@ -8,6 +8,8 @@
 #define CMDLINEPARSEH
 
 #include <linux/blkdev.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
 
 /* partition flags */
 #define PF_RDONLY                   0x01 /* Device is read only */
diff --git a/include/linux/completion.h b/include/linux/completion.h
index 22c33e35bcb2..5d5aaae3af43 100644
--- a/include/linux/completion.h
+++ b/include/linux/completion.h
@@ -19,8 +19,8 @@
  *
  * See also:  complete(), wait_for_completion() (and friends _timeout,
  * _interruptible, _interruptible_timeout, and _killable), init_completion(),
- * and macros DECLARE_COMPLETION(), DECLARE_COMPLETION_ONSTACK(), and
- * INIT_COMPLETION().
+ * reinit_completion(), and macros DECLARE_COMPLETION(),
+ * DECLARE_COMPLETION_ONSTACK().
  */
 struct completion {
 	unsigned int done;
@@ -65,7 +65,7 @@ struct completion {
 
 /**
  * init_completion - Initialize a dynamically allocated completion
- * @x:  completion structure that is to be initialized
+ * @x:  pointer to completion structure that is to be initialized
  *
  * This inline function will initialize a dynamically created completion
  * structure.
@@ -76,6 +76,18 @@ static inline void init_completion(struct completion *x)
 	init_waitqueue_head(&x->wait);
 }
 
+/**
+ * reinit_completion - reinitialize a completion structure
+ * @x:  pointer to completion structure that is to be reinitialized
+ *
+ * This inline function should be used to reinitialize a completion structure so it can
+ * be reused. This is especially important after complete_all() is used.
+ */
+static inline void reinit_completion(struct completion *x)
+{
+	x->done = 0;
+}
+
 extern void wait_for_completion(struct completion *);
 extern void wait_for_completion_io(struct completion *);
 extern int wait_for_completion_interruptible(struct completion *x);
@@ -94,14 +106,4 @@ extern bool completion_done(struct completion *x);
 extern void complete(struct completion *);
 extern void complete_all(struct completion *);
 
-/**
- * INIT_COMPLETION - reinitialize a completion structure
- * @x:  completion structure to be reinitialized
- *
- * This macro should be used to reinitialize a completion structure so it can
- * be reused. This is especially important after complete_all() is used.
- */
-#define INIT_COMPLETION(x)	((x).done = 0)
-
-
 #endif
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 3935428c57cf..91672e2deec3 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -54,7 +54,8 @@ enum page_check_address_pmd_flag {
 extern pmd_t *page_check_address_pmd(struct page *page,
 				     struct mm_struct *mm,
 				     unsigned long address,
-				     enum page_check_address_pmd_flag flag);
+				     enum page_check_address_pmd_flag flag,
+				     spinlock_t **ptl);
 
 #define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT)
 #define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
@@ -129,15 +130,15 @@ extern void __vma_adjust_trans_huge(struct vm_area_struct *vma,
 				    unsigned long start,
 				    unsigned long end,
 				    long adjust_next);
-extern int __pmd_trans_huge_lock(pmd_t *pmd,
-				 struct vm_area_struct *vma);
+extern int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
+		spinlock_t **ptl);
 /* mmap_sem must be held on entry */
-static inline int pmd_trans_huge_lock(pmd_t *pmd,
-				      struct vm_area_struct *vma)
+static inline int pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
+		spinlock_t **ptl)
 {
 	VM_BUG_ON(!rwsem_is_locked(&vma->vm_mm->mmap_sem));
 	if (pmd_trans_huge(*pmd))
-		return __pmd_trans_huge_lock(pmd, vma);
+		return __pmd_trans_huge_lock(pmd, vma, ptl);
 	else
 		return 0;
 }
@@ -215,8 +216,8 @@ static inline void vma_adjust_trans_huge(struct vm_area_struct *vma,
 					 long adjust_next)
 {
 }
-static inline int pmd_trans_huge_lock(pmd_t *pmd,
-				      struct vm_area_struct *vma)
+static inline int pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
+		spinlock_t **ptl)
 {
 	return 0;
 }
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 0393270466c3..acd2010328f3 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -392,6 +392,15 @@ static inline int hugepage_migration_support(struct hstate *h)
 	return pmd_huge_support() && (huge_page_shift(h) == PMD_SHIFT);
 }
 
+static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
+					   struct mm_struct *mm, pte_t *pte)
+{
+	if (huge_page_size(h) == PMD_SIZE)
+		return pmd_lockptr(mm, (pmd_t *) pte);
+	VM_BUG_ON(huge_page_size(h) == PAGE_SIZE);
+	return &mm->page_table_lock;
+}
+
 #else	/* CONFIG_HUGETLB_PAGE */
 struct hstate {};
 #define alloc_huge_page_node(h, nid) NULL
@@ -401,6 +410,7 @@ struct hstate {};
 #define hstate_sizelog(s) NULL
 #define hstate_vma(v) NULL
 #define hstate_inode(i) NULL
+#define page_hstate(page) NULL
 #define huge_page_size(h) PAGE_SIZE
 #define huge_page_mask(h) PAGE_MASK
 #define vma_kernel_pagesize(v) PAGE_SIZE
@@ -421,6 +431,22 @@ static inline pgoff_t basepage_index(struct page *page)
 #define dissolve_free_huge_pages(s, e)	do {} while (0)
 #define pmd_huge_support()	0
 #define hugepage_migration_support(h)	0
+
+static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
+					   struct mm_struct *mm, pte_t *pte)
+{
+	return &mm->page_table_lock;
+}
 #endif	/* CONFIG_HUGETLB_PAGE */
 
+static inline spinlock_t *huge_pte_lock(struct hstate *h,
+					struct mm_struct *mm, pte_t *pte)
+{
+	spinlock_t *ptl;
+
+	ptl = huge_pte_lockptr(h, mm, pte);
+	spin_lock(ptl);
+	return ptl;
+}
+
 #endif /* _LINUX_HUGETLB_H */
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index c9e831dc80bc..db43b58a3355 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -11,8 +11,6 @@
 #include <linux/irqnr.h>
 #include <linux/hardirq.h>
 #include <linux/irqflags.h>
-#include <linux/smp.h>
-#include <linux/percpu.h>
 #include <linux/hrtimer.h>
 #include <linux/kref.h>
 #include <linux/workqueue.h>
@@ -392,15 +390,6 @@ extern void __raise_softirq_irqoff(unsigned int nr);
 extern void raise_softirq_irqoff(unsigned int nr);
 extern void raise_softirq(unsigned int nr);
 
-/* This is the worklist that queues up per-cpu softirq work.
- *
- * send_remote_sendirq() adds work to these lists, and
- * the softirq handler itself dequeues from them.  The queues
- * are protected by disabling local cpu interrupts and they must
- * only be accessed by the local cpu that they are for.
- */
-DECLARE_PER_CPU(struct list_head [NR_SOFTIRQS], softirq_work_list);
-
 DECLARE_PER_CPU(struct task_struct *, ksoftirqd);
 
 static inline struct task_struct *this_cpu_ksoftirqd(void)
@@ -408,17 +397,6 @@ static inline struct task_struct *this_cpu_ksoftirqd(void)
 	return this_cpu_read(ksoftirqd);
 }
 
-/* Try to send a softirq to a remote cpu.  If this cannot be done, the
- * work will be queued to the local cpu.
- */
-extern void send_remote_softirq(struct call_single_data *cp, int cpu, int softirq);
-
-/* Like send_remote_softirq(), but the caller must disable local cpu interrupts
- * and compute the current cpu, passed in as 'this_cpu'.
- */
-extern void __send_remote_softirq(struct call_single_data *cp, int cpu,
-				  int this_cpu, int softirq);
-
 /* Tasklets --- multithreaded analogue of BHs.
 
    Main feature differing them of generic softirqs: tasklet
diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h
index 10308c6a3d1c..552d51efb429 100644
--- a/include/linux/kfifo.h
+++ b/include/linux/kfifo.h
@@ -1,7 +1,7 @@
 /*
  * A generic kernel FIFO implementation
  *
- * Copyright (C) 2009/2010 Stefani Seibold <stefani@seibold.net>
+ * Copyright (C) 2013 Stefani Seibold <stefani@seibold.net>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -67,9 +67,10 @@ struct __kfifo {
 	union { \
 		struct __kfifo	kfifo; \
 		datatype	*type; \
+		const datatype	*const_type; \
 		char		(*rectype)[recsize]; \
 		ptrtype		*ptr; \
-		const ptrtype	*ptr_const; \
+		ptrtype const	*ptr_const; \
 	}
 
 #define __STRUCT_KFIFO(type, size, recsize, ptrtype) \
@@ -386,16 +387,12 @@ __kfifo_int_must_check_helper( \
 #define	kfifo_put(fifo, val) \
 ({ \
 	typeof((fifo) + 1) __tmp = (fifo); \
-	typeof((val) + 1) __val = (val); \
+	typeof(*__tmp->const_type) __val = (val); \
 	unsigned int __ret; \
-	const size_t __recsize = sizeof(*__tmp->rectype); \
+	size_t __recsize = sizeof(*__tmp->rectype); \
 	struct __kfifo *__kfifo = &__tmp->kfifo; \
-	if (0) { \
-		typeof(__tmp->ptr_const) __dummy __attribute__ ((unused)); \
-		__dummy = (typeof(__val))NULL; \
-	} \
 	if (__recsize) \
-		__ret = __kfifo_in_r(__kfifo, __val, sizeof(*__val), \
+		__ret = __kfifo_in_r(__kfifo, &__val, sizeof(__val), \
 			__recsize); \
 	else { \
 		__ret = !kfifo_is_full(__tmp); \
@@ -404,7 +401,7 @@ __kfifo_int_must_check_helper( \
 			((typeof(__tmp->type))__kfifo->data) : \
 			(__tmp->buf) \
 			)[__kfifo->in & __tmp->kfifo.mask] = \
-				*(typeof(__tmp->type))__val; \
+				(typeof(*__tmp->type))__val; \
 			smp_wmb(); \
 			__kfifo->in++; \
 		} \
@@ -415,7 +412,7 @@ __kfifo_int_must_check_helper( \
 /**
  * kfifo_get - get data from the fifo
  * @fifo: address of the fifo to be used
- * @val: the var where to store the data to be added
+ * @val: address where to store the data
  *
  * This macro reads the data from the fifo.
  * It returns 0 if the fifo was empty. Otherwise it returns the number
@@ -428,12 +425,10 @@ __kfifo_int_must_check_helper( \
 __kfifo_uint_must_check_helper( \
 ({ \
 	typeof((fifo) + 1) __tmp = (fifo); \
-	typeof((val) + 1) __val = (val); \
+	typeof(__tmp->ptr) __val = (val); \
 	unsigned int __ret; \
 	const size_t __recsize = sizeof(*__tmp->rectype); \
 	struct __kfifo *__kfifo = &__tmp->kfifo; \
-	if (0) \
-		__val = (typeof(__tmp->ptr))0; \
 	if (__recsize) \
 		__ret = __kfifo_out_r(__kfifo, __val, sizeof(*__val), \
 			__recsize); \
@@ -456,7 +451,7 @@ __kfifo_uint_must_check_helper( \
 /**
  * kfifo_peek - get data from the fifo without removing
  * @fifo: address of the fifo to be used
- * @val: the var where to store the data to be added
+ * @val: address where to store the data
  *
  * This reads the data from the fifo without removing it from the fifo.
  * It returns 0 if the fifo was empty. Otherwise it returns the number
@@ -469,12 +464,10 @@ __kfifo_uint_must_check_helper( \
 __kfifo_uint_must_check_helper( \
 ({ \
 	typeof((fifo) + 1) __tmp = (fifo); \
-	typeof((val) + 1) __val = (val); \
+	typeof(__tmp->ptr) __val = (val); \
 	unsigned int __ret; \
 	const size_t __recsize = sizeof(*__tmp->rectype); \
 	struct __kfifo *__kfifo = &__tmp->kfifo; \
-	if (0) \
-		__val = (typeof(__tmp->ptr))NULL; \
 	if (__recsize) \
 		__ret = __kfifo_out_peek_r(__kfifo, __val, sizeof(*__val), \
 			__recsize); \
@@ -508,14 +501,10 @@ __kfifo_uint_must_check_helper( \
 #define	kfifo_in(fifo, buf, n) \
 ({ \
 	typeof((fifo) + 1) __tmp = (fifo); \
-	typeof((buf) + 1) __buf = (buf); \
+	typeof(__tmp->ptr_const) __buf = (buf); \
 	unsigned long __n = (n); \
 	const size_t __recsize = sizeof(*__tmp->rectype); \
 	struct __kfifo *__kfifo = &__tmp->kfifo; \
-	if (0) { \
-		typeof(__tmp->ptr_const) __dummy __attribute__ ((unused)); \
-		__dummy = (typeof(__buf))NULL; \
-	} \
 	(__recsize) ?\
 	__kfifo_in_r(__kfifo, __buf, __n, __recsize) : \
 	__kfifo_in(__kfifo, __buf, __n); \
@@ -561,14 +550,10 @@ __kfifo_uint_must_check_helper( \
 __kfifo_uint_must_check_helper( \
 ({ \
 	typeof((fifo) + 1) __tmp = (fifo); \
-	typeof((buf) + 1) __buf = (buf); \
+	typeof(__tmp->ptr) __buf = (buf); \
 	unsigned long __n = (n); \
 	const size_t __recsize = sizeof(*__tmp->rectype); \
 	struct __kfifo *__kfifo = &__tmp->kfifo; \
-	if (0) { \
-		typeof(__tmp->ptr) __dummy = NULL; \
-		__buf = __dummy; \
-	} \
 	(__recsize) ?\
 	__kfifo_out_r(__kfifo, __buf, __n, __recsize) : \
 	__kfifo_out(__kfifo, __buf, __n); \
@@ -773,14 +758,10 @@ __kfifo_uint_must_check_helper( \
 __kfifo_uint_must_check_helper( \
 ({ \
 	typeof((fifo) + 1) __tmp = (fifo); \
-	typeof((buf) + 1) __buf = (buf); \
+	typeof(__tmp->ptr) __buf = (buf); \
 	unsigned long __n = (n); \
 	const size_t __recsize = sizeof(*__tmp->rectype); \
 	struct __kfifo *__kfifo = &__tmp->kfifo; \
-	if (0) { \
-		typeof(__tmp->ptr) __dummy __attribute__ ((unused)) = NULL; \
-		__buf = __dummy; \
-	} \
 	(__recsize) ? \
 	__kfifo_out_peek_r(__kfifo, __buf, __n, __recsize) : \
 	__kfifo_out_peek(__kfifo, __buf, __n); \
diff --git a/include/linux/llist.h b/include/linux/llist.h
index 8828a78dec9a..fbf10a0bc095 100644
--- a/include/linux/llist.h
+++ b/include/linux/llist.h
@@ -195,4 +195,6 @@ static inline struct llist_node *llist_del_all(struct llist_head *head)
 
 extern struct llist_node *llist_del_first(struct llist_head *head);
 
+struct llist_node *llist_reverse_order(struct llist_node *head);
+
 #endif /* LLIST_H */
diff --git a/include/linux/lockref.h b/include/linux/lockref.h
index 13dfd36a3294..c8929c3832db 100644
--- a/include/linux/lockref.h
+++ b/include/linux/lockref.h
@@ -15,10 +15,15 @@
  */
 
 #include <linux/spinlock.h>
+#include <generated/bounds.h>
+
+#define USE_CMPXCHG_LOCKREF \
+	(IS_ENABLED(CONFIG_ARCH_USE_CMPXCHG_LOCKREF) && \
+	 IS_ENABLED(CONFIG_SMP) && !BLOATED_SPINLOCKS)
 
 struct lockref {
 	union {
-#ifdef CONFIG_CMPXCHG_LOCKREF
+#if USE_CMPXCHG_LOCKREF
 		aligned_u64 lock_count;
 #endif
 		struct {
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 42a35d94b82c..0548eb201e05 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1316,32 +1316,85 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a
 }
 #endif /* CONFIG_MMU && !__ARCH_HAS_4LEVEL_HACK */
 
-#if USE_SPLIT_PTLOCKS
-/*
- * We tuck a spinlock to guard each pagetable page into its struct page,
- * at page->private, with BUILD_BUG_ON to make sure that this will not
- * overflow into the next struct page (as it might with DEBUG_SPINLOCK).
- * When freeing, reset page->mapping so free_pages_check won't complain.
- */
-#define __pte_lockptr(page)	&((page)->ptl)
-#define pte_lock_init(_page)	do {					\
-	spin_lock_init(__pte_lockptr(_page));				\
-} while (0)
-#define pte_lock_deinit(page)	((page)->mapping = NULL)
-#define pte_lockptr(mm, pmd)	({(void)(mm); __pte_lockptr(pmd_page(*(pmd)));})
-#else	/* !USE_SPLIT_PTLOCKS */
+#if USE_SPLIT_PTE_PTLOCKS
+#if BLOATED_SPINLOCKS
+void __init ptlock_cache_init(void);
+extern bool ptlock_alloc(struct page *page);
+extern void ptlock_free(struct page *page);
+
+static inline spinlock_t *ptlock_ptr(struct page *page)
+{
+	return page->ptl;
+}
+#else /* BLOATED_SPINLOCKS */
+static inline void ptlock_cache_init(void) {}
+static inline bool ptlock_alloc(struct page *page)
+{
+	return true;
+}
+
+static inline void ptlock_free(struct page *page)
+{
+}
+
+static inline spinlock_t *ptlock_ptr(struct page *page)
+{
+	return &page->ptl;
+}
+#endif /* BLOATED_SPINLOCKS */
+
+static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd)
+{
+	return ptlock_ptr(pmd_page(*pmd));
+}
+
+static inline bool ptlock_init(struct page *page)
+{
+	/*
+	 * prep_new_page() initialize page->private (and therefore page->ptl)
+	 * with 0. Make sure nobody took it in use in between.
+	 *
+	 * It can happen if arch try to use slab for page table allocation:
+	 * slab code uses page->slab_cache and page->first_page (for tail
+	 * pages), which share storage with page->ptl.
+	 */
+	VM_BUG_ON(*(unsigned long *)&page->ptl);
+	if (!ptlock_alloc(page))
+		return false;
+	spin_lock_init(ptlock_ptr(page));
+	return true;
+}
+
+/* Reset page->mapping so free_pages_check won't complain. */
+static inline void pte_lock_deinit(struct page *page)
+{
+	page->mapping = NULL;
+	ptlock_free(page);
+}
+
+#else	/* !USE_SPLIT_PTE_PTLOCKS */
 /*
  * We use mm->page_table_lock to guard all pagetable pages of the mm.
  */
-#define pte_lock_init(page)	do {} while (0)
-#define pte_lock_deinit(page)	do {} while (0)
-#define pte_lockptr(mm, pmd)	({(void)(pmd); &(mm)->page_table_lock;})
-#endif /* USE_SPLIT_PTLOCKS */
+static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd)
+{
+	return &mm->page_table_lock;
+}
+static inline void ptlock_cache_init(void) {}
+static inline bool ptlock_init(struct page *page) { return true; }
+static inline void pte_lock_deinit(struct page *page) {}
+#endif /* USE_SPLIT_PTE_PTLOCKS */
+
+static inline void pgtable_init(void)
+{
+	ptlock_cache_init();
+	pgtable_cache_init();
+}
 
-static inline void pgtable_page_ctor(struct page *page)
+static inline bool pgtable_page_ctor(struct page *page)
 {
-	pte_lock_init(page);
 	inc_zone_page_state(page, NR_PAGETABLE);
+	return ptlock_init(page);
 }
 
 static inline void pgtable_page_dtor(struct page *page)
@@ -1378,6 +1431,52 @@ static inline void pgtable_page_dtor(struct page *page)
 	((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd, address))? \
 		NULL: pte_offset_kernel(pmd, address))
 
+#if USE_SPLIT_PMD_PTLOCKS
+
+static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd)
+{
+	return ptlock_ptr(virt_to_page(pmd));
+}
+
+static inline bool pgtable_pmd_page_ctor(struct page *page)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	page->pmd_huge_pte = NULL;
+#endif
+	return ptlock_init(page);
+}
+
+static inline void pgtable_pmd_page_dtor(struct page *page)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	VM_BUG_ON(page->pmd_huge_pte);
+#endif
+	ptlock_free(page);
+}
+
+#define pmd_huge_pte(mm, pmd) (virt_to_page(pmd)->pmd_huge_pte)
+
+#else
+
+static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd)
+{
+	return &mm->page_table_lock;
+}
+
+static inline bool pgtable_pmd_page_ctor(struct page *page) { return true; }
+static inline void pgtable_pmd_page_dtor(struct page *page) {}
+
+#define pmd_huge_pte(mm, pmd) ((mm)->pmd_huge_pte)
+
+#endif
+
+static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd)
+{
+	spinlock_t *ptl = pmd_lockptr(mm, pmd);
+	spin_lock(ptl);
+	return ptl;
+}
+
 extern void free_area_init(unsigned long * zones_size);
 extern void free_area_init_node(int nid, unsigned long * zones_size,
 		unsigned long zone_start_pfn, unsigned long *zholes_size);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index a3198e5aaf4e..10f5a7272b80 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -23,7 +23,9 @@
 
 struct address_space;
 
-#define USE_SPLIT_PTLOCKS	(NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS)
+#define USE_SPLIT_PTE_PTLOCKS	(NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS)
+#define USE_SPLIT_PMD_PTLOCKS	(USE_SPLIT_PTE_PTLOCKS && \
+		IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK))
 
 /*
  * Each physical page in the system has a struct page associated with
@@ -63,6 +65,9 @@ struct page {
 						 * this page is only used to
 						 * free other pages.
 						 */
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && USE_SPLIT_PMD_PTLOCKS
+		pgtable_t pmd_huge_pte; /* protected by page->ptl */
+#endif
 		};
 
 		union {
@@ -141,9 +146,13 @@ struct page {
 						 * indicates order in the buddy
 						 * system if PG_buddy is set.
 						 */
-#if USE_SPLIT_PTLOCKS
+#if USE_SPLIT_PTE_PTLOCKS
+#if BLOATED_SPINLOCKS
+		spinlock_t *ptl;
+#else
 		spinlock_t ptl;
 #endif
+#endif
 		struct kmem_cache *slab_cache;	/* SL[AU]B: Pointer to slab */
 		struct page *first_page;	/* Compound tail pages */
 	};
@@ -309,14 +318,14 @@ enum {
 	NR_MM_COUNTERS
 };
 
-#if USE_SPLIT_PTLOCKS && defined(CONFIG_MMU)
+#if USE_SPLIT_PTE_PTLOCKS && defined(CONFIG_MMU)
 #define SPLIT_RSS_COUNTING
 /* per-thread cached information, */
 struct task_rss_stat {
 	int events;	/* for synchronization threshold */
 	int count[NR_MM_COUNTERS];
 };
-#endif /* USE_SPLIT_PTLOCKS */
+#endif /* USE_SPLIT_PTE_PTLOCKS */
 
 struct mm_rss_stat {
 	atomic_long_t count[NR_MM_COUNTERS];
@@ -339,6 +348,7 @@ struct mm_struct {
 	pgd_t * pgd;
 	atomic_t mm_users;			/* How many users with user space? */
 	atomic_t mm_count;			/* How many references to "struct mm_struct" (users count as 1) */
+	atomic_long_t nr_ptes;			/* Page table pages */
 	int map_count;				/* number of VMAs */
 
 	spinlock_t page_table_lock;		/* Protects page tables and some counters */
@@ -360,7 +370,6 @@ struct mm_struct {
 	unsigned long exec_vm;		/* VM_EXEC & ~VM_WRITE */
 	unsigned long stack_vm;		/* VM_GROWSUP/DOWN */
 	unsigned long def_flags;
-	unsigned long nr_ptes;		/* Page table pages */
 	unsigned long start_code, end_code, start_data, end_data;
 	unsigned long start_brk, brk, start_stack;
 	unsigned long arg_start, arg_end, env_start, env_end;
@@ -406,7 +415,7 @@ struct mm_struct {
 #ifdef CONFIG_MMU_NOTIFIER
 	struct mmu_notifier_mm *mmu_notifier_mm;
 #endif
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
 	pgtable_t pmd_huge_pte; /* protected by page_table_lock */
 #endif
 #ifdef CONFIG_CPUMASK_OFFSTACK
diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h
index 4e32edc8f506..52e0097f61f0 100644
--- a/include/linux/seq_file.h
+++ b/include/linux/seq_file.h
@@ -20,6 +20,7 @@ struct seq_file {
 	size_t size;
 	size_t from;
 	size_t count;
+	size_t pad_until;
 	loff_t index;
 	loff_t read_pos;
 	u64 version;
@@ -79,6 +80,20 @@ static inline void seq_commit(struct seq_file *m, int num)
 	}
 }
 
+/**
+ * seq_setwidth - set padding width
+ * @m: the seq_file handle
+ * @size: the max number of bytes to pad.
+ *
+ * Call seq_setwidth() for setting max width, then call seq_printf() etc. and
+ * finally call seq_pad() to pad the remaining bytes.
+ */
+static inline void seq_setwidth(struct seq_file *m, size_t size)
+{
+	m->pad_until = m->count + size;
+}
+void seq_pad(struct seq_file *m, char c);
+
 char *mangle_path(char *s, const char *p, const char *esc);
 int seq_open(struct file *, const struct seq_operations *);
 ssize_t seq_read(struct file *, char __user *, size_t, loff_t *);
diff --git a/include/linux/smp.h b/include/linux/smp.h
index 731f5237d5f4..5da22ee42e16 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -49,6 +49,9 @@ void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
 		smp_call_func_t func, void *info, bool wait,
 		gfp_t gfp_flags);
 
+void __smp_call_function_single(int cpuid, struct call_single_data *data,
+				int wait);
+
 #ifdef CONFIG_SMP
 
 #include <linux/preempt.h>
@@ -95,9 +98,6 @@ int smp_call_function(smp_call_func_t func, void *info, int wait);
 void smp_call_function_many(const struct cpumask *mask,
 			    smp_call_func_t func, void *info, bool wait);
 
-void __smp_call_function_single(int cpuid, struct call_single_data *data,
-				int wait);
-
 int smp_call_function_any(const struct cpumask *mask,
 			  smp_call_func_t func, void *info, int wait);
 
@@ -106,14 +106,10 @@ void kick_all_cpus_sync(void);
 /*
  * Generic and arch helpers
  */
-#ifdef CONFIG_USE_GENERIC_SMP_HELPERS
 void __init call_function_init(void);
 void generic_smp_call_function_single_interrupt(void);
 #define generic_smp_call_function_interrupt \
 	generic_smp_call_function_single_interrupt
-#else
-static inline void call_function_init(void) { }
-#endif
 
 /*
  * Mark the boot cpu "online" so that it can call console drivers in
@@ -155,12 +151,6 @@ smp_call_function_any(const struct cpumask *mask, smp_call_func_t func,
 
 static inline void kick_all_cpus_sync(void) {  }
 
-static inline void __smp_call_function_single(int cpuid,
-		struct call_single_data *data, int wait)
-{
-	on_each_cpu(data->func, data->info, wait);
-}
-
 #endif /* !SMP */
 
 /*
diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index 8d4fa82bfb91..c0f75261a728 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -139,7 +139,8 @@ static inline void make_migration_entry_read(swp_entry_t *entry)
 
 extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
 					unsigned long address);
-extern void migration_entry_wait_huge(struct mm_struct *mm, pte_t *pte);
+extern void migration_entry_wait_huge(struct vm_area_struct *vma,
+		struct mm_struct *mm, pte_t *pte);
 #else
 
 #define make_migration_entry(page, write) swp_entry(0, 0)
@@ -151,8 +152,8 @@ static inline int is_migration_entry(swp_entry_t swp)
 static inline void make_migration_entry_read(swp_entry_t *entryp) { }
 static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
 					 unsigned long address) { }
-static inline void migration_entry_wait_huge(struct mm_struct *mm,
-					pte_t *pte) { }
+static inline void migration_entry_wait_huge(struct vm_area_struct *vma,
+		struct mm_struct *mm, pte_t *pte) { }
 static inline int is_write_migration_entry(swp_entry_t entry)
 {
 	return 0;