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
  ...

Documentation/vm/split_page_table_lock

@@ -0,0 +1,94 @@
+Split page table lock
+=====================
+
+Originally, mm->page_table_lock spinlock protected all page tables of the
+mm_struct. But this approach leads to poor page fault scalability of
+multi-threaded applications due high contention on the lock. To improve
+scalability, split page table lock was introduced.
+
+With split page table lock we have separate per-table lock to serialize
+access to the table. At the moment we use split lock for PTE and PMD
+tables. Access to higher level tables protected by mm->page_table_lock.
+
+There are helpers to lock/unlock a table and other accessor functions:
+ - pte_offset_map_lock()
+	maps pte and takes PTE table lock, returns pointer to the taken
+	lock;
+ - pte_unmap_unlock()
+	unlocks and unmaps PTE table;
+ - pte_alloc_map_lock()
+	allocates PTE table if needed and take the lock, returns pointer
+	to taken lock or NULL if allocation failed;
+ - pte_lockptr()
+	returns pointer to PTE table lock;
+ - pmd_lock()
+	takes PMD table lock, returns pointer to taken lock;
+ - pmd_lockptr()
+	returns pointer to PMD table lock;
+
+Split page table lock for PTE tables is enabled compile-time if
+CONFIG_SPLIT_PTLOCK_CPUS (usually 4) is less or equal to NR_CPUS.
+If split lock is disabled, all tables guaded by mm->page_table_lock.
+
+Split page table lock for PMD tables is enabled, if it's enabled for PTE
+tables and the architecture supports it (see below).
+
+Hugetlb and split page table lock
+---------------------------------
+
+Hugetlb can support several page sizes. We use split lock only for PMD
+level, but not for PUD.
+
+Hugetlb-specific helpers:
+ - huge_pte_lock()
+	takes pmd split lock for PMD_SIZE page, mm->page_table_lock
+	otherwise;
+ - huge_pte_lockptr()
+	returns pointer to table lock;
+
+Support of split page table lock by an architecture
+---------------------------------------------------
+
+There's no need in special enabling of PTE split page table lock:
+everything required is done by pgtable_page_ctor() and pgtable_page_dtor(),
+which must be called on PTE table allocation / freeing.
+
+Make sure the architecture doesn't use slab allocator for page table
+allocation: slab uses page->slab_cache and page->first_page for its pages.
+These fields share storage with page->ptl.
+
+PMD split lock only makes sense if you have more than two page table
+levels.
+
+PMD split lock enabling requires pgtable_pmd_page_ctor() call on PMD table
+allocation and pgtable_pmd_page_dtor() on freeing.
+
+Allocation usually happens in pmd_alloc_one(), freeing in pmd_free(), but
+make sure you cover all PMD table allocation / freeing paths: i.e X86_PAE
+preallocate few PMDs on pgd_alloc().
+
+With everything in place you can set CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK.
+
+NOTE: pgtable_page_ctor() and pgtable_pmd_page_ctor() can fail -- it must
+be handled properly.
+
+page->ptl
+---------
+
+page->ptl is used to access split page table lock, where 'page' is struct
+page of page containing the table. It shares storage with page->private
+(and few other fields in union).
+
+To avoid increasing size of struct page and have best performance, we use a
+trick:
+ - if spinlock_t fits into long, we use page->ptr as spinlock, so we
+   can avoid indirect access and save a cache line.
+ - if size of spinlock_t is bigger then size of long, we use page->ptl as
+   pointer to spinlock_t and allocate it dynamically. This allows to use
+   split lock with enabled DEBUG_SPINLOCK or DEBUG_LOCK_ALLOC, but costs
+   one more cache line for indirect access;
+
+The spinlock_t allocated in pgtable_page_ctor() for PTE table and in
+pgtable_pmd_page_ctor() for PMD table.
+
+Please, never access page->ptl directly -- use appropriate helper.

arch/Kconfig

@@ -207,9 +207,6 @@ config HAVE_DMA_ATTRS
 config HAVE_DMA_CONTIGUOUS
 	bool
 
-config USE_GENERIC_SMP_HELPERS
-	bool
-
 config GENERIC_SMP_IDLE_THREAD
        bool
 

arch/alpha/Kconfig

@@ -522,7 +522,6 @@ config ARCH_MAY_HAVE_PC_FDC
 config SMP
 	bool "Symmetric multi-processing support"
 	depends on ALPHA_SABLE || ALPHA_LYNX || ALPHA_RAWHIDE || ALPHA_DP264 || ALPHA_WILDFIRE || ALPHA_TITAN || ALPHA_GENERIC || ALPHA_SHARK || ALPHA_MARVEL
-	select USE_GENERIC_SMP_HELPERS
 	---help---
 	  This enables support for systems with more than one CPU. If you have
 	  a system with only one CPU, like most personal computers, say N. If

arch/alpha/include/asm/pgalloc.h

@@ -72,7 +72,10 @@ pte_alloc_one(struct mm_struct *mm, unsigned long address)
 	if (!pte)
 		return NULL;
 	page = virt_to_page(pte);
-	pgtable_page_ctor(page);
+	if (!pgtable_page_ctor(page)) {
+		__free_page(page);
+		return NULL;
+	}
 	return page;
 }
 

arch/arc/Kconfig

@@ -125,7 +125,6 @@ config ARC_PLAT_NEEDS_CPU_TO_DMA
 config SMP
 	bool "Symmetric Multi-Processing (Incomplete)"
 	default n
-	select USE_GENERIC_SMP_HELPERS
 	help
 	  This enables support for systems with more than one CPU. If you have
 	  a system with only one CPU, like most personal computers, say N. If

arch/arc/include/asm/pgalloc.h

@@ -105,11 +105,16 @@ static inline pgtable_t
 pte_alloc_one(struct mm_struct *mm, unsigned long address)
 {
 	pgtable_t pte_pg;
+	struct page *page;
 
 	pte_pg = __get_free_pages(GFP_KERNEL | __GFP_REPEAT, __get_order_pte());
-	if (pte_pg) {
+	if (!pte_pg)
+		return 0;
 	memzero((void *)pte_pg, PTRS_PER_PTE * 4);
-		pgtable_page_ctor(virt_to_page(pte_pg));
+	page = virt_to_page(pte_pg);
+	if (!pgtable_page_ctor(page)) {
+		__free_page(page);
+		return 0;
 	}
 
 	return pte_pg;

arch/arm/Kconfig

@@ -1432,7 +1432,6 @@ config SMP
 	depends on GENERIC_CLOCKEVENTS
 	depends on HAVE_SMP
 	depends on MMU || ARM_MPU
-	select USE_GENERIC_SMP_HELPERS
 	help
 	  This enables support for systems with more than one CPU. If you have
 	  a system with only one CPU, like most personal computers, say N. If

arch/arm/include/asm/pgalloc.h

@@ -102,12 +102,14 @@ pte_alloc_one(struct mm_struct *mm, unsigned long addr)
 #else
 	pte = alloc_pages(PGALLOC_GFP, 0);
 #endif
-	if (pte) {
+	if (!pte)
+		return NULL;
 	if (!PageHighMem(pte))
 		clean_pte_table(page_address(pte));
-		pgtable_page_ctor(pte);
+	if (!pgtable_page_ctor(pte)) {
+		__free_page(pte);
+		return NULL;
 	}
-
 	return pte;
 }
 

arch/arm/mach-tegra/apbio.c

@@ -114,7 +114,7 @@ static int do_dma_transfer(unsigned long apb_add,
 	dma_desc->callback = apb_dma_complete;
 	dma_desc->callback_param = NULL;
 
-	INIT_COMPLETION(tegra_apb_wait);
+	reinit_completion(&tegra_apb_wait);
 
 	dmaengine_submit(dma_desc);
 	dma_async_issue_pending(tegra_apb_dma_chan);

arch/arm/mm/fault-armv.c

@@ -65,7 +65,7 @@ static int do_adjust_pte(struct vm_area_struct *vma, unsigned long address,
 	return ret;
 }
 
-#if USE_SPLIT_PTLOCKS
+#if USE_SPLIT_PTE_PTLOCKS
 /*
  * If we are using split PTE locks, then we need to take the page
  * lock here.  Otherwise we are using shared mm->page_table_lock
@@ -84,10 +84,10 @@ static inline void do_pte_unlock(spinlock_t *ptl)
 {
 	spin_unlock(ptl);
 }
-#else /* !USE_SPLIT_PTLOCKS */
+#else /* !USE_SPLIT_PTE_PTLOCKS */
 static inline void do_pte_lock(spinlock_t *ptl) {}
 static inline void do_pte_unlock(spinlock_t *ptl) {}
-#endif /* USE_SPLIT_PTLOCKS */
+#endif /* USE_SPLIT_PTE_PTLOCKS */
 
 static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
 	unsigned long pfn)

arch/arm64/Kconfig

@@ -143,7 +143,6 @@ config CPU_BIG_ENDIAN
 
 config SMP
 	bool "Symmetric Multi-Processing"
-	select USE_GENERIC_SMP_HELPERS
 	help
 	  This enables support for systems with more than one CPU.  If
 	  you say N here, the kernel will run on single and

arch/arm64/include/asm/pgalloc.h

@@ -63,9 +63,12 @@ pte_alloc_one(struct mm_struct *mm, unsigned long addr)
 	struct page *pte;
 
 	pte = alloc_pages(PGALLOC_GFP, 0);
-	if (pte)
-		pgtable_page_ctor(pte);
-
+	if (!pte)
+		return NULL;
+	if (!pgtable_page_ctor(pte)) {
+		__free_page(pte);
+		return NULL;
+	}
 	return pte;
 }
 

arch/avr32/include/asm/pgalloc.h

@@ -68,7 +68,10 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
 		return NULL;
 
 	page = virt_to_page(pg);
-	pgtable_page_ctor(page);
+	if (!pgtable_page_ctor(page)) {
+		quicklist_free(QUICK_PT, NULL, pg);
+		return NULL;
+	}
 
 	return page;
 }

arch/blackfin/Kconfig

@@ -34,7 +34,6 @@ config BLACKFIN
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select GENERIC_ATOMIC64
 	select GENERIC_IRQ_PROBE
-	select USE_GENERIC_SMP_HELPERS if SMP
 	select HAVE_NMI_WATCHDOG if NMI_WATCHDOG
 	select GENERIC_SMP_IDLE_THREAD
 	select ARCH_USES_GETTIMEOFFSET if !GENERIC_CLOCKEVENTS

arch/cris/include/asm/pgalloc.h

@@ -32,7 +32,12 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long addres
 {
 	struct page *pte;
 	pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0);
-	pgtable_page_ctor(pte);
+	if (!pte)
+		return NULL;
+	if (!pgtable_page_ctor(pte)) {
+		__free_page(pte);
+		return NULL;
+	}
 	return pte;
 }
 

arch/frv/mm/pgalloc.c

@@ -37,11 +37,15 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
 #else
 	page = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0);
 #endif
-	if (page) {
+	if (!page)
+		return NULL;
+
 	clear_highpage(page);
-		pgtable_page_ctor(page);
-		flush_dcache_page(page);
+	if (!pgtable_page_ctor(page)) {
+		__free_page(page);
+		return NULL;
 	}
+	flush_dcache_page(page);
 	return page;
 }
 

arch/hexagon/Kconfig

@@ -4,7 +4,6 @@ comment "Linux Kernel Configuration for Hexagon"
 config HEXAGON
 	def_bool y
 	select HAVE_OPROFILE
-	select USE_GENERIC_SMP_HELPERS if SMP
 	# Other pending projects/to-do items.
 	# select HAVE_REGS_AND_STACK_ACCESS_API
 	# select HAVE_HW_BREAKPOINT if PERF_EVENTS

arch/hexagon/include/asm/pgalloc.h

@@ -65,10 +65,12 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm,
 	struct page *pte;
 
 	pte = alloc_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
-
-	if (pte)
-		pgtable_page_ctor(pte);
-
+	if (!pte)
+		return NULL;
+	if (!pgtable_page_ctor(pte)) {
+		__free_page(pte);
+		return NULL;
+	}
 	return pte;
 }
 

arch/ia64/Kconfig

@@ -343,7 +343,6 @@ config FORCE_MAX_ZONEORDER
 
 config SMP
 	bool "Symmetric multi-processing support"
-	select USE_GENERIC_SMP_HELPERS
 	help
 	  This enables support for systems with more than one CPU. If you have
 	  a system with only one CPU, say N.  If you have a system with more

arch/ia64/include/asm/pgalloc.h

@@ -91,7 +91,10 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long addr)
 	if (!pg)
 		return NULL;
 	page = virt_to_page(pg);
-	pgtable_page_ctor(page);
+	if (!pgtable_page_ctor(page)) {
+		quicklist_free(0, NULL, pg);
+		return NULL;
+	}
 	return page;
 }
 

arch/m32r/Kconfig

@@ -275,7 +275,6 @@ source "kernel/Kconfig.preempt"
 
 config SMP
 	bool "Symmetric multi-processing support"
-	select USE_GENERIC_SMP_HELPERS
 	---help---
 	  This enables support for systems with more than one CPU. If you have
 	  a system with only one CPU, like most personal computers, say N. If

arch/m32r/include/asm/pgalloc.h

@@ -43,7 +43,12 @@ static __inline__ pgtable_t pte_alloc_one(struct mm_struct *mm,
 {
 	struct page *pte = alloc_page(GFP_KERNEL|__GFP_ZERO);
 
-	pgtable_page_ctor(pte);
+	if (!pte)
+		return NULL;
+	if (!pgtable_page_ctor(pte)) {
+		__free_page(pte);
+		return NULL;
+	}
 	return pte;
 }
 

arch/m68k/include/asm/mcf_pgalloc.h

@@ -56,6 +56,10 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm,
 
 	if (!page)
 		return NULL;
+	if (!pgtable_page_ctor(page)) {
+		__free_page(page);
+		return NULL;
+	}
 
 	pte = kmap(page);
 	if (pte) {

arch/m68k/include/asm/motorola_pgalloc.h

@@ -29,18 +29,22 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
 
 static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
 {
-	struct page *page = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0);
+	struct page *page;
 	pte_t *pte;
 
+	page = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0);
 	if(!page)
 		return NULL;
+	if (!pgtable_page_ctor(page)) {
+		__free_page(page);
+		return NULL;
+	}
 
 	pte = kmap(page);
 	__flush_page_to_ram(pte);
 	flush_tlb_kernel_page(pte);
 	nocache_page(pte);
 	kunmap(page);
-	pgtable_page_ctor(page);
 	return page;
 }
 

arch/m68k/include/asm/sun3_pgalloc.h

@@ -59,7 +59,10 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
 		return NULL;
 
 	clear_highpage(page);
-	pgtable_page_ctor(page);
+	if (!pgtable_page_ctor(page)) {
+		__free_page(page);
+		return NULL;
+	}
 	return page;
 
 }

arch/metag/Kconfig

@@ -111,7 +111,6 @@ config METAG_META21
 config SMP
 	bool "Symmetric multi-processing support"
 	depends on METAG_META21 && METAG_META21_MMU
-	select USE_GENERIC_SMP_HELPERS
 	help
 	  This enables support for systems with more than one thread running
 	  Linux. If you have a system with only one thread running Linux,

arch/metag/include/asm/pgalloc.h

@@ -52,8 +52,12 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
 {
 	struct page *pte;
 	pte = alloc_pages(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO, 0);
-	if (pte)
-		pgtable_page_ctor(pte);
+	if (!pte)
+		return NULL;
+	if (!pgtable_page_ctor(pte)) {
+		__free_page(pte);
+		return NULL;
+	}
 	return pte;
 }
 

arch/microblaze/include/asm/pgalloc.h

@@ -122,8 +122,13 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm,
 #endif
 
 	ptepage = alloc_pages(flags, 0);
-	if (ptepage)
+	if (!ptepage)
+		return NULL;
 	clear_highpage(ptepage);
+	if (!pgtable_page_ctor(ptepage)) {
+		__free_page(ptepage);
+		return NULL;
+	}
 	return ptepage;
 }
 
@@ -158,8 +163,9 @@ extern inline void pte_free_slow(struct page *ptepage)
 	__free_page(ptepage);
 }
 
-extern inline void pte_free(struct mm_struct *mm, struct page *ptepage)
+static inline void pte_free(struct mm_struct *mm, struct page *ptepage)
 {
+	pgtable_page_dtor(ptepage);
 	__free_page(ptepage);
 }
 

arch/mips/Kconfig

@@ -2125,7 +2125,6 @@ source "mm/Kconfig"
 config SMP
 	bool "Multi-Processing support"
 	depends on SYS_SUPPORTS_SMP
-	select USE_GENERIC_SMP_HELPERS
 	help
 	  This enables support for systems with more than one CPU. If you have
 	  a system with only one CPU, like most personal computers, say N. If

arch/mips/include/asm/pgalloc.h

@@ -80,9 +80,12 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm,
 	struct page *pte;
 
 	pte = alloc_pages(GFP_KERNEL | __GFP_REPEAT, PTE_ORDER);
-	if (pte) {
+	if (!pte)
+		return NULL;
 	clear_highpage(pte);
-		pgtable_page_ctor(pte);
+	if (!pgtable_page_ctor(pte)) {
+		__free_page(pte);
+		return NULL;
 	}
 	return pte;
 }

arch/mn10300/Kconfig

@@ -181,7 +181,6 @@ endmenu
 config SMP
 	bool "Symmetric multi-processing support"
 	default y
-	select USE_GENERIC_SMP_HELPERS
 	depends on MN10300_PROC_MN2WS0038 || MN10300_PROC_MN2WS0050
 	---help---
 	  This enables support for systems with more than one CPU. If you have

arch/mn10300/include/asm/pgalloc.h

@@ -46,6 +46,7 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
 
 static inline void pte_free(struct mm_struct *mm, struct page *pte)
 {
+	pgtable_page_dtor(pte);
 	__free_page(pte);
 }
 

arch/mn10300/mm/pgtable.c

@@ -78,8 +78,13 @@ struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address)
 #else
 	pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0);
 #endif
-	if (pte)
+	if (!pte)
+		return NULL;
 	clear_highpage(pte);
+	if (!pgtable_page_ctor(pte)) {
+		__free_page(pte);
+		return NULL;
+	}
 	return pte;
 }
 

arch/openrisc/include/asm/pgalloc.h

@@ -78,8 +78,13 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm,
 {
 	struct page *pte;
 	pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0);
-	if (pte)
+	if (!pte)
+		return NULL;
 	clear_page(page_address(pte));
+	if (!pgtable_page_ctor(pte)) {
+		__free_page(pte);
+		return NULL;
+	}
 	return pte;
 }
 
@@ -90,6 +95,7 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
 
 static inline void pte_free(struct mm_struct *mm, struct page *pte)
 {
+	pgtable_page_dtor(pte);
 	__free_page(pte);
 }
 

arch/parisc/Kconfig

@@ -226,7 +226,6 @@ endchoice
 
 config SMP
 	bool "Symmetric multi-processing support"
-	select USE_GENERIC_SMP_HELPERS
 	---help---
 	  This enables support for systems with more than one CPU. If you have
 	  a system with only one CPU, like most personal computers, say N. If

arch/parisc/include/asm/pgalloc.h

@@ -121,8 +121,12 @@ static inline pgtable_t
 pte_alloc_one(struct mm_struct *mm, unsigned long address)
 {
 	struct page *page = alloc_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
-	if (page)
-		pgtable_page_ctor(page);
+	if (!page)
+		return NULL;
+	if (!pgtable_page_ctor(page)) {
+		__free_page(page);
+		return NULL;
+	}
 	return page;
 }
 

arch/powerpc/Kconfig

@@ -106,7 +106,6 @@ config PPC
 	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_DMA_ATTRS
 	select HAVE_DMA_API_DEBUG
-	select USE_GENERIC_SMP_HELPERS if SMP
 	select HAVE_OPROFILE
 	select HAVE_DEBUG_KMEMLEAK
 	select GENERIC_ATOMIC64 if PPC32

arch/powerpc/include/asm/pgalloc-64.h

@@ -91,7 +91,10 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
 	if (!pte)
 		return NULL;
 	page = virt_to_page(pte);
-	pgtable_page_ctor(page);
+	if (!pgtable_page_ctor(page)) {
+		__free_page(page);
+		return NULL;
+	}
 	return page;
 }
 

arch/powerpc/mm/pgtable_32.c

@@ -121,7 +121,10 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
 	ptepage = alloc_pages(flags, 0);
 	if (!ptepage)
 		return NULL;
-	pgtable_page_ctor(ptepage);
+	if (!pgtable_page_ctor(ptepage)) {
+		__free_page(ptepage);
+		return NULL;
+	}
 	return ptepage;
 }
 

arch/powerpc/mm/pgtable_64.c

@@ -378,6 +378,10 @@ static pte_t *__alloc_for_cache(struct mm_struct *mm, int kernel)
 				       __GFP_REPEAT | __GFP_ZERO);
 	if (!page)
 		return NULL;
+	if (!kernel && !pgtable_page_ctor(page)) {
+		__free_page(page);
+		return NULL;
+	}
 
 	ret = page_address(page);
 	spin_lock(&mm->page_table_lock);
@@ -392,9 +396,6 @@ static pte_t *__alloc_for_cache(struct mm_struct *mm, int kernel)
 	}
 	spin_unlock(&mm->page_table_lock);
 
-	if (!kernel)
-		pgtable_page_ctor(page);
-
 	return (pte_t *)ret;
 }
 

arch/powerpc/platforms/powermac/low_i2c.c

@@ -452,7 +452,7 @@ static int kw_i2c_xfer(struct pmac_i2c_bus *bus, u8 addrdir, int subsize,
 	 */
 	if (use_irq) {
 		/* Clear completion */
-		INIT_COMPLETION(host->complete);
+		reinit_completion(&host->complete);
 		/* Ack stale interrupts */
 		kw_write_reg(reg_isr, kw_read_reg(reg_isr));
 		/* Arm timeout */
@@ -717,7 +717,7 @@ static int pmu_i2c_xfer(struct pmac_i2c_bus *bus, u8 addrdir, int subsize,
 			return -EINVAL;
 		}
 
-		INIT_COMPLETION(comp);
+		reinit_completion(&comp);
 		req->data[0] = PMU_I2C_CMD;
 		req->reply[0] = 0xff;
 		req->nbytes = sizeof(struct pmu_i2c_hdr) + 1;
@@ -748,7 +748,7 @@ static int pmu_i2c_xfer(struct pmac_i2c_bus *bus, u8 addrdir, int subsize,
 
 		hdr->bus = PMU_I2C_BUS_STATUS;
 
-		INIT_COMPLETION(comp);
+		reinit_completion(&comp);
 		req->data[0] = PMU_I2C_CMD;
 		req->reply[0] = 0xff;
 		req->nbytes = 2;

arch/powerpc/platforms/pseries/suspend.c

@@ -106,7 +106,7 @@ static int pseries_prepare_late(void)
 	atomic_set(&suspend_data.done, 0);
 	atomic_set(&suspend_data.error, 0);
 	suspend_data.complete = &suspend_work;
-	INIT_COMPLETION(suspend_work);
+	reinit_completion(&suspend_work);
 	return 0;
 }
 

arch/s390/Kconfig

@@ -141,7 +141,6 @@ config S390
 	select OLD_SIGACTION
 	select OLD_SIGSUSPEND3
 	select SYSCTL_EXCEPTION_TRACE
-	select USE_GENERIC_SMP_HELPERS if SMP
 	select VIRT_CPU_ACCOUNTING
 	select VIRT_TO_BUS
 

arch/s390/mm/pgtable.c

@@ -772,7 +772,11 @@ static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm,
 		__free_page(page);
 		return NULL;
 	}
-	pgtable_page_ctor(page);
+	if (!pgtable_page_ctor(page)) {
+		kfree(mp);
+		__free_page(page);
+		return NULL;
+	}
 	mp->vmaddr = vmaddr & PMD_MASK;
 	INIT_LIST_HEAD(&mp->mapper);
 	page->index = (unsigned long) mp;
@@ -902,7 +906,10 @@ unsigned long *page_table_alloc(struct mm_struct *mm, unsigned long vmaddr)
 		page = alloc_page(GFP_KERNEL|__GFP_REPEAT);
 		if (!page)
 			return NULL;
-		pgtable_page_ctor(page);
+		if (!pgtable_page_ctor(page)) {
+			__free_page(page);
+			return NULL;
+		}
 		atomic_set(&page->_mapcount, 1);
 		table = (unsigned long *) page_to_phys(page);
 		clear_table(table, _PAGE_INVALID, PAGE_SIZE);
@@ -1244,11 +1251,11 @@ void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
 	assert_spin_locked(&mm->page_table_lock);
 
 	/* FIFO */
-	if (!mm->pmd_huge_pte)
+	if (!pmd_huge_pte(mm, pmdp))
 		INIT_LIST_HEAD(lh);
 	else
-		list_add(lh, (struct list_head *) mm->pmd_huge_pte);
-	mm->pmd_huge_pte = pgtable;
+		list_add(lh, (struct list_head *) pmd_huge_pte(mm, pmdp));
+	pmd_huge_pte(mm, pmdp) = pgtable;
 }
 
 pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
@@ -1260,12 +1267,12 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
 	assert_spin_locked(&mm->page_table_lock);
 
 	/* FIFO */
-	pgtable = mm->pmd_huge_pte;
+	pgtable = pmd_huge_pte(mm, pmdp);
 	lh = (struct list_head *) pgtable;
 	if (list_empty(lh))
-		mm->pmd_huge_pte = NULL;
+		pmd_huge_pte(mm, pmdp) = NULL;
 	else {
-		mm->pmd_huge_pte = (pgtable_t) lh->next;
+		pmd_huge_pte(mm, pmdp) = (pgtable_t) lh->next;
 		list_del(lh);
 	}
 	ptep = (pte_t *) pgtable;

arch/score/include/asm/pgalloc.h

@@ -54,9 +54,12 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm,
 	struct page *pte;
 
 	pte = alloc_pages(GFP_KERNEL | __GFP_REPEAT, PTE_ORDER);
-	if (pte) {
+	if (!pte)
+		return NULL;
 	clear_highpage(pte);
-		pgtable_page_ctor(pte);
+	if (!pgtable_page_ctor(pte)) {
+		__free_page(pte);
+		return NULL;
 	}
 	return pte;
 }

arch/sh/Kconfig

@@ -711,7 +711,6 @@ config CC_STACKPROTECTOR
 config SMP
 	bool "Symmetric multi-processing support"
 	depends on SYS_SUPPORTS_SMP
-	select USE_GENERIC_SMP_HELPERS
 	---help---
 	  This enables support for systems with more than one CPU. If you have
 	  a system with only one CPU, like most personal computers, say N. If

arch/sh/include/asm/pgalloc.h

@@ -47,7 +47,10 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
 	if (!pg)
 		return NULL;
 	page = virt_to_page(pg);
-	pgtable_page_ctor(page);
+	if (!pgtable_page_ctor(page)) {
+		quicklist_free(QUICK_PT, NULL, pg);
+		return NULL;
+	}
 	return page;
 }
 

arch/sparc/Kconfig

@@ -28,7 +28,6 @@ config SPARC
 	select HAVE_ARCH_JUMP_LABEL
 	select GENERIC_IRQ_SHOW
 	select ARCH_WANT_IPC_PARSE_VERSION
-	select USE_GENERIC_SMP_HELPERS if SMP
 	select GENERIC_PCI_IOMAP
 	select HAVE_NMI_WATCHDOG if SPARC64
 	select HAVE_BPF_JIT

arch/sparc/mm/init_64.c

@@ -2519,12 +2519,13 @@ pgtable_t pte_alloc_one(struct mm_struct *mm,
 		return pte;
 
 	page = __alloc_for_cache(mm);
-	if (page) {
-		pgtable_page_ctor(page);
-		pte = (pte_t *) page_address(page);
+	if (!page)
+		return NULL;
+	if (!pgtable_page_ctor(page)) {
+		free_hot_cold_page(page, 0);
+		return NULL;
 	}
-
-	return pte;
+	return (pte_t *) page_address(page);
 }
 
 void pte_free_kernel(struct mm_struct *mm, pte_t *pte)

arch/sparc/mm/srmmu.c

@@ -345,7 +345,10 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
 	if ((pte = (unsigned long)pte_alloc_one_kernel(mm, address)) == 0)
 		return NULL;
 	page = pfn_to_page(__nocache_pa(pte) >> PAGE_SHIFT);
-	pgtable_page_ctor(page);
+	if (!pgtable_page_ctor(page)) {
+		__free_page(page);
+		return NULL;
+	}
 	return page;
 }
 

arch/sparc/mm/tlb.c

@@ -196,11 +196,11 @@ void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
 	assert_spin_locked(&mm->page_table_lock);
 
 	/* FIFO */
-	if (!mm->pmd_huge_pte)
+	if (!pmd_huge_pte(mm, pmdp))
 		INIT_LIST_HEAD(lh);
 	else
-		list_add(lh, (struct list_head *) mm->pmd_huge_pte);
-	mm->pmd_huge_pte = pgtable;
+		list_add(lh, (struct list_head *) pmd_huge_pte(mm, pmdp));
+	pmd_huge_pte(mm, pmdp) = pgtable;
 }
 
 pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
@@ -211,12 +211,12 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
 	assert_spin_locked(&mm->page_table_lock);
 
 	/* FIFO */
-	pgtable = mm->pmd_huge_pte;
+	pgtable = pmd_huge_pte(mm, pmdp);
 	lh = (struct list_head *) pgtable;
 	if (list_empty(lh))
-		mm->pmd_huge_pte = NULL;
+		pmd_huge_pte(mm, pmdp) = NULL;
 	else {
-		mm->pmd_huge_pte = (pgtable_t) lh->next;
+		pmd_huge_pte(mm, pmdp) = (pgtable_t) lh->next;
 		list_del(lh);
 	}
 	pte_val(pgtable[0]) = 0;

arch/tile/Kconfig

@@ -8,7 +8,6 @@ config TILE
 	select HAVE_KVM if !TILEGX
 	select GENERIC_FIND_FIRST_BIT
 	select SYSCTL_EXCEPTION_TRACE
-	select USE_GENERIC_SMP_HELPERS
 	select CC_OPTIMIZE_FOR_SIZE
 	select HAVE_DEBUG_KMEMLEAK
 	select GENERIC_IRQ_PROBE

arch/tile/mm/pgtable.c

@@ -241,6 +241,11 @@ struct page *pgtable_alloc_one(struct mm_struct *mm, unsigned long address,
 	if (p == NULL)
 		return NULL;
 
+	if (!pgtable_page_ctor(p)) {
+		__free_pages(p, L2_USER_PGTABLE_ORDER);
+		return NULL;
+	}
+
 	/*
 	 * Make every page have a page_count() of one, not just the first.
 	 * We don't use __GFP_COMP since it doesn't look like it works
@@ -251,7 +256,6 @@ struct page *pgtable_alloc_one(struct mm_struct *mm, unsigned long address,
 		inc_zone_page_state(p+i, NR_PAGETABLE);
 	}
 
-	pgtable_page_ctor(p);
 	return p;
 }
 

arch/um/kernel/mem.c

@@ -279,8 +279,12 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
 	struct page *pte;
 
 	pte = alloc_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
-	if (pte)
-		pgtable_page_ctor(pte);
+	if (!pte)
+		return NULL;
+	if (!pgtable_page_ctor(pte)) {
+		__free_page(pte);
+		return NULL;
+	}
 	return pte;
 }
 

arch/unicore32/include/asm/pgalloc.h

@@ -51,12 +51,14 @@ pte_alloc_one(struct mm_struct *mm, unsigned long addr)
 	struct page *pte;
 
 	pte = alloc_pages(PGALLOC_GFP, 0);
-	if (pte) {
+	if (!pte)
+		return NULL;
 	if (!PageHighMem(pte)) {
 		void *page = page_address(pte);
 		clean_dcache_area(page, PTRS_PER_PTE * sizeof(pte_t));
 	}
-		pgtable_page_ctor(pte);
+	if (!pgtable_page_ctor(pte)) {
+		__free_page(pte);
 	}
 
 	return pte;

arch/x86/Kconfig

@@ -90,7 +90,6 @@ config X86
 	select GENERIC_IRQ_SHOW
 	select GENERIC_CLOCKEVENTS_MIN_ADJUST
 	select IRQ_FORCED_THREADING
-	select USE_GENERIC_SMP_HELPERS if SMP
 	select HAVE_BPF_JIT if X86_64
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select CLKEVT_I8253
@@ -1885,6 +1884,10 @@ config USE_PERCPU_NUMA_NODE_ID
 	def_bool y
 	depends on NUMA
 
+config ARCH_ENABLE_SPLIT_PMD_PTLOCK
+	def_bool y
+	depends on X86_64 || X86_PAE
+
 menu "Power management and ACPI options"
 
 config ARCH_HIBERNATION_HEADER

arch/x86/include/asm/pgalloc.h

@@ -80,12 +80,21 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
 #if PAGETABLE_LEVELS > 2
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return (pmd_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
+	struct page *page;
+	page = alloc_pages(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO, 0);
+	if (!page)
+		return NULL;
+	if (!pgtable_pmd_page_ctor(page)) {
+		__free_pages(page, 0);
+		return NULL;
+	}
+	return (pmd_t *)page_address(page);
 }
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 {
 	BUG_ON((unsigned long)pmd & (PAGE_SIZE-1));
+	pgtable_pmd_page_dtor(virt_to_page(pmd));
 	free_page((unsigned long)pmd);
 }
 

arch/x86/mm/pgtable.c

@@ -25,8 +25,12 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
 	struct page *pte;
 
 	pte = alloc_pages(__userpte_alloc_gfp, 0);
-	if (pte)
-		pgtable_page_ctor(pte);
+	if (!pte)
+		return NULL;
+	if (!pgtable_page_ctor(pte)) {
+		__free_page(pte);
+		return NULL;
+	}
 	return pte;
 }
 
@@ -189,8 +193,10 @@ static void free_pmds(pmd_t *pmds[])
 	int i;
 
 	for(i = 0; i < PREALLOCATED_PMDS; i++)
-		if (pmds[i])
+		if (pmds[i]) {
+			pgtable_pmd_page_dtor(virt_to_page(pmds[i]));
 			free_page((unsigned long)pmds[i]);
+		}
 }
 
 static int preallocate_pmds(pmd_t *pmds[])
@@ -200,8 +206,13 @@ static int preallocate_pmds(pmd_t *pmds[])
 
 	for(i = 0; i < PREALLOCATED_PMDS; i++) {
 		pmd_t *pmd = (pmd_t *)__get_free_page(PGALLOC_GFP);
-		if (pmd == NULL)
+		if (!pmd)
 			failed = true;
+		if (pmd && !pgtable_pmd_page_ctor(virt_to_page(pmd))) {
+			free_page((unsigned long)pmds[i]);
+			pmd = NULL;
+			failed = true;
+		}
 		pmds[i] = pmd;
 	}
 

arch/x86/xen/mmu.c

@@ -796,8 +796,8 @@ static spinlock_t *xen_pte_lock(struct page *page, struct mm_struct *mm)
 {
 	spinlock_t *ptl = NULL;
 
-#if USE_SPLIT_PTLOCKS
-	ptl = __pte_lockptr(page);
+#if USE_SPLIT_PTE_PTLOCKS
+	ptl = ptlock_ptr(page);
 	spin_lock_nest_lock(ptl, &mm->page_table_lock);
 #endif
 
@@ -1637,7 +1637,7 @@ static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn,
 
 			__set_pfn_prot(pfn, PAGE_KERNEL_RO);
 
-			if (level == PT_PTE && USE_SPLIT_PTLOCKS)
+			if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS)
 				__pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
 
 			xen_mc_issue(PARAVIRT_LAZY_MMU);
@@ -1671,7 +1671,7 @@ static inline void xen_release_ptpage(unsigned long pfn, unsigned level)
 		if (!PageHighMem(page)) {
 			xen_mc_batch();
 
-			if (level == PT_PTE && USE_SPLIT_PTLOCKS)
+			if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS)
 				__pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
 
 			__set_pfn_prot(pfn, PAGE_KERNEL);

arch/xtensa/include/asm/pgalloc.h

@@ -38,35 +38,46 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 	free_page((unsigned long)pgd);
 }
 
-/* Use a slab cache for the pte pages (see also sparc64 implementation) */
-
-extern struct kmem_cache *pgtable_cache;
-
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 					 unsigned long address)
 {
-	return kmem_cache_alloc(pgtable_cache, GFP_KERNEL|__GFP_REPEAT);
+	pte_t *ptep;
+	int i;
+
+	ptep = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT);
+	if (!ptep)
+		return NULL;
+	for (i = 0; i < 1024; i++)
+		pte_clear(NULL, 0, ptep + i);
+	return ptep;
 }
 
 static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
 					unsigned long addr)
 {
+	pte_t *pte;
 	struct page *page;
 
-	page = virt_to_page(pte_alloc_one_kernel(mm, addr));
-	pgtable_page_ctor(page);
+	pte = pte_alloc_one_kernel(mm, addr);
+	if (!pte)
+		return NULL;
+	page = virt_to_page(pte);
+	if (!pgtable_page_ctor(page)) {
+		__free_page(page);
+		return NULL;
+	}
 	return page;
 }
 
 static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
 {
-	kmem_cache_free(pgtable_cache, pte);
+	free_page((unsigned long)pte);
 }
 
 static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
 {
 	pgtable_page_dtor(pte);
-	kmem_cache_free(pgtable_cache, page_address(pte));
+	__free_page(pte);
 }
 #define pmd_pgtable(pmd) pmd_page(pmd)
 

arch/xtensa/include/asm/pgtable.h

@@ -220,12 +220,11 @@ extern unsigned long empty_zero_page[1024];
 #ifdef CONFIG_MMU
 extern pgd_t swapper_pg_dir[PAGE_SIZE/sizeof(pgd_t)];
 extern void paging_init(void);
-extern void pgtable_cache_init(void);
 #else
 # define swapper_pg_dir NULL
 static inline void paging_init(void) { }
-static inline void pgtable_cache_init(void) { }
 #endif
+static inline void pgtable_cache_init(void) { }
 
 /*
  * The pmd contains the kernel virtual address of the pte page.

arch/xtensa/mm/mmu.c

@@ -50,23 +50,3 @@ void __init init_mmu(void)
 	 */
 	set_ptevaddr_register(PGTABLE_START);
 }
-
-struct kmem_cache *pgtable_cache __read_mostly;
-
-static void pgd_ctor(void *addr)
-{
-	pte_t *ptep = (pte_t *)addr;
-	int i;
-
-	for (i = 0; i < 1024; i++, ptep++)
-		pte_clear(NULL, 0, ptep);
-
-}
-
-void __init pgtable_cache_init(void)
-{
-	pgtable_cache = kmem_cache_create("pgd",
-			PAGE_SIZE, PAGE_SIZE,
-			SLAB_HWCACHE_ALIGN,
-			pgd_ctor);
-}

block/blk-mq.c

@@ -319,7 +319,7 @@ void __blk_mq_end_io(struct request *rq, int error)
 		blk_mq_complete_request(rq, error);
 }
 
-#if defined(CONFIG_SMP) && defined(CONFIG_USE_GENERIC_SMP_HELPERS)
+#if defined(CONFIG_SMP)
 
 /*
  * Called with interrupts disabled.
@@ -361,7 +361,7 @@ static int ipi_remote_cpu(struct blk_mq_ctx *ctx, const int cpu,
 
 	return true;
 }
-#else /* CONFIG_SMP && CONFIG_USE_GENERIC_SMP_HELPERS */
+#else /* CONFIG_SMP */
 static int ipi_remote_cpu(struct blk_mq_ctx *ctx, const int cpu,
 			  struct request *rq, const int error)
 {

block/blk-softirq.c

@@ -36,7 +36,7 @@ static void blk_done_softirq(struct softirq_action *h)
 	}
 }
 
-#if defined(CONFIG_SMP) && defined(CONFIG_USE_GENERIC_SMP_HELPERS)
+#ifdef CONFIG_SMP
 static void trigger_softirq(void *data)
 {
 	struct request *rq = data;
@@ -71,7 +71,7 @@ static int raise_blk_irq(int cpu, struct request *rq)
 
 	return 1;
 }
-#else /* CONFIG_SMP && CONFIG_USE_GENERIC_SMP_HELPERS */
+#else /* CONFIG_SMP */
 static int raise_blk_irq(int cpu, struct request *rq)
 {
 	return 1;

block/blk-sysfs.c

@@ -288,7 +288,7 @@ static ssize_t
 queue_rq_affinity_store(struct request_queue *q, const char *page, size_t count)
 {
 	ssize_t ret = -EINVAL;
-#if defined(CONFIG_USE_GENERIC_SMP_HELPERS)
+#ifdef CONFIG_SMP
 	unsigned long val;
 
 	ret = queue_var_store(&val, page, count);

crypto/af_alg.c

@@ -434,7 +434,7 @@ int af_alg_wait_for_completion(int err, struct af_alg_completion *completion)
 	case -EINPROGRESS:
 	case -EBUSY:
 		wait_for_completion(&completion->completion);
-		INIT_COMPLETION(completion->completion);
+		reinit_completion(&completion->completion);
 		err = completion->err;
 		break;
 	};

crypto/tcrypt.c

@@ -493,7 +493,7 @@ static inline int do_one_ahash_op(struct ahash_request *req, int ret)
 		ret = wait_for_completion_interruptible(&tr->completion);
 		if (!ret)
 			ret = tr->err;
-		INIT_COMPLETION(tr->completion);
+		reinit_completion(&tr->completion);
 	}
 	return ret;
 }
@@ -721,7 +721,7 @@ static inline int do_one_acipher_op(struct ablkcipher_request *req, int ret)
 		ret = wait_for_completion_interruptible(&tr->completion);
 		if (!ret)
 			ret = tr->err;
-		INIT_COMPLETION(tr->completion);
+		reinit_completion(&tr->completion);
 	}
 
 	return ret;

crypto/testmgr.c

@@ -179,7 +179,7 @@ static int do_one_async_hash_op(struct ahash_request *req,
 		ret = wait_for_completion_interruptible(&tr->completion);
 		if (!ret)
 			ret = tr->err;
-		INIT_COMPLETION(tr->completion);
+		reinit_completion(&tr->completion);
 	}
 	return ret;
 }
@@ -336,7 +336,7 @@ static int __test_hash(struct crypto_ahash *tfm, struct hash_testvec *template,
 				ret = wait_for_completion_interruptible(
 					&tresult.completion);
 				if (!ret && !(ret = tresult.err)) {
-					INIT_COMPLETION(tresult.completion);
+					reinit_completion(&tresult.completion);
 					break;
 				}
 				/* fall through */
@@ -543,7 +543,7 @@ static int __test_aead(struct crypto_aead *tfm, int enc,
 				ret = wait_for_completion_interruptible(
 					&result.completion);
 				if (!ret && !(ret = result.err)) {
-					INIT_COMPLETION(result.completion);
+					reinit_completion(&result.completion);
 					break;
 				}
 			case -EBADMSG:
@@ -697,7 +697,7 @@ static int __test_aead(struct crypto_aead *tfm, int enc,
 				ret = wait_for_completion_interruptible(
 					&result.completion);
 				if (!ret && !(ret = result.err)) {
-					INIT_COMPLETION(result.completion);
+					reinit_completion(&result.completion);
 					break;
 				}
 			case -EBADMSG:
@@ -983,7 +983,7 @@ static int __test_skcipher(struct crypto_ablkcipher *tfm, int enc,
 				ret = wait_for_completion_interruptible(
 					&result.completion);
 				if (!ret && !((ret = result.err))) {
-					INIT_COMPLETION(result.completion);
+					reinit_completion(&result.completion);
 					break;
 				}
 				/* fall through */
@@ -1086,7 +1086,7 @@ static int __test_skcipher(struct crypto_ablkcipher *tfm, int enc,
 				ret = wait_for_completion_interruptible(
 					&result.completion);
 				if (!ret && !((ret = result.err))) {
-					INIT_COMPLETION(result.completion);
+					reinit_completion(&result.completion);
 					break;
 				}
 				/* fall through */

drivers/ata/libata-eh.c

@@ -3017,7 +3017,7 @@ static inline void ata_eh_pull_park_action(struct ata_port *ap)
 	 * ourselves at the beginning of each pass over the loop.
 	 *
 	 * Additionally, all write accesses to &ap->park_req_pending
-	 * through INIT_COMPLETION() (see below) or complete_all()
+	 * through reinit_completion() (see below) or complete_all()
 	 * (see ata_scsi_park_store()) are protected by the host lock.
 	 * As a result we have that park_req_pending.done is zero on
 	 * exit from this function, i.e. when ATA_EH_PARK actions for
@@ -3031,7 +3031,7 @@ static inline void ata_eh_pull_park_action(struct ata_port *ap)
 	 */
 
 	spin_lock_irqsave(ap->lock, flags);
-	INIT_COMPLETION(ap->park_req_pending);
+	reinit_completion(&ap->park_req_pending);
 	ata_for_each_link(link, ap, EDGE) {
 		ata_for_each_dev(dev, link, ALL) {
 			struct ata_eh_info *ehi = &link->eh_info;

drivers/base/power/main.c

@@ -757,7 +757,7 @@ void dpm_resume(pm_message_t state)
 	async_error = 0;
 
 	list_for_each_entry(dev, &dpm_suspended_list, power.entry) {
-		INIT_COMPLETION(dev->power.completion);
+		reinit_completion(&dev->power.completion);
 		if (is_async(dev)) {
 			get_device(dev);
 			async_schedule(async_resume, dev);
@@ -1237,7 +1237,7 @@ static void async_suspend(void *data, async_cookie_t cookie)
 
 static int device_suspend(struct device *dev)
 {
-	INIT_COMPLETION(dev->power.completion);
+	reinit_completion(&dev->power.completion);
 
 	if (pm_async_enabled && dev->power.async_suspend) {
 		get_device(dev);

drivers/block/amiflop.c

@@ -343,7 +343,7 @@ static int fd_motor_on(int nr)
 		unit[nr].motor = 1;
 		fd_select(nr);
 
-		INIT_COMPLETION(motor_on_completion);
+		reinit_completion(&motor_on_completion);
 		motor_on_timer.data = nr;
 		mod_timer(&motor_on_timer, jiffies + HZ/2);
 

drivers/block/cciss.c

@@ -2808,7 +2808,7 @@ resend_cmd2:
 		/* erase the old error information */
 		memset(c->err_info, 0, sizeof(ErrorInfo_struct));
 		return_status = IO_OK;
-		INIT_COMPLETION(wait);
+		reinit_completion(&wait);
 		goto resend_cmd2;
 	}
 
@@ -3669,7 +3669,7 @@ static int add_to_scan_list(struct ctlr_info *h)
 		}
 	}
 	if (!found && !h->busy_scanning) {
-		INIT_COMPLETION(h->scan_wait);
+		reinit_completion(&h->scan_wait);
 		list_add_tail(&h->scan_list, &scan_q);
 		ret = 1;
 	}

drivers/char/hw_random/timeriomem-rng.c

@@ -79,7 +79,7 @@ static int timeriomem_rng_data_read(struct hwrng *rng, u32 *data)
 	priv->expires = cur + delay;
 	priv->present = 0;
 
-	INIT_COMPLETION(priv->completion);
+	reinit_completion(&priv->completion);
 	mod_timer(&priv->timer, priv->expires);
 
 	return 4;

drivers/crypto/tegra-aes.c

@@ -268,7 +268,7 @@ static int aes_start_crypt(struct tegra_aes_dev *dd, u32 in_addr, u32 out_addr,
 	aes_writel(dd, value, TEGRA_AES_SECURE_INPUT_SELECT);
 
 	aes_writel(dd, out_addr, TEGRA_AES_SECURE_DEST_ADDR);
-	INIT_COMPLETION(dd->op_complete);
+	reinit_completion(&dd->op_complete);
 
 	for (i = 0; i < AES_HW_MAX_ICQ_LENGTH - 1; i++) {
 		do {

drivers/firewire/core-transaction.c

@@ -477,7 +477,7 @@ void fw_send_phy_config(struct fw_card *card,
 	phy_config_packet.header[1] = data;
 	phy_config_packet.header[2] = ~data;
 	phy_config_packet.generation = generation;
-	INIT_COMPLETION(phy_config_done);
+	reinit_completion(&phy_config_done);
 
 	card->driver->send_request(card, &phy_config_packet);
 	wait_for_completion_timeout(&phy_config_done, timeout);

drivers/gpu/drm/drm_flip_work.c

@@ -34,7 +34,7 @@
  */
 void drm_flip_work_queue(struct drm_flip_work *work, void *val)
 {
-	if (kfifo_put(&work->fifo, (const void **)&val)) {
+	if (kfifo_put(&work->fifo, val)) {
 		atomic_inc(&work->pending);
 	} else {
 		DRM_ERROR("%s fifo full!\n", work->name);

drivers/gpu/drm/gma500/oaktrail_hdmi_i2c.c

@@ -99,7 +99,7 @@ static int xfer_read(struct i2c_adapter *adap, struct i2c_msg *pmsg)
 	i2c_dev->status = I2C_STAT_INIT;
 	i2c_dev->msg = pmsg;
 	i2c_dev->buf_offset = 0;
-	INIT_COMPLETION(i2c_dev->complete);
+	reinit_completion(&i2c_dev->complete);
 
 	/* Enable I2C transaction */
 	temp = ((pmsg->len) << 20) | HI2C_EDID_READ | HI2C_ENABLE_TRANSACTION;

drivers/hid/hid-wiimote.h

@@ -327,7 +327,7 @@ static inline void wiimote_cmd_acquire_noint(struct wiimote_data *wdata)
 static inline void wiimote_cmd_set(struct wiimote_data *wdata, int cmd,
 								__u32 opt)
 {
-	INIT_COMPLETION(wdata->state.ready);
+	reinit_completion(&wdata->state.ready);
 	wdata->state.cmd = cmd;
 	wdata->state.opt = opt;
 }

drivers/hwmon/jz4740-hwmon.c

@@ -66,7 +66,7 @@ static ssize_t jz4740_hwmon_read_adcin(struct device *dev,
 
 	mutex_lock(&hwmon->lock);
 
-	INIT_COMPLETION(*completion);
+	reinit_completion(completion);
 
 	enable_irq(hwmon->irq);
 	hwmon->cell->enable(to_platform_device(dev));

drivers/i2c/busses/i2c-at91.c

@@ -371,7 +371,7 @@ static int at91_do_twi_transfer(struct at91_twi_dev *dev)
 	dev_dbg(dev->dev, "transfer: %s %d bytes.\n",
 		(dev->msg->flags & I2C_M_RD) ? "read" : "write", dev->buf_len);
 
-	INIT_COMPLETION(dev->cmd_complete);
+	reinit_completion(&dev->cmd_complete);
 	dev->transfer_status = 0;
 
 	if (!dev->buf_len) {

drivers/i2c/busses/i2c-bcm2835.c

@@ -151,7 +151,7 @@ static int bcm2835_i2c_xfer_msg(struct bcm2835_i2c_dev *i2c_dev,
 
 	i2c_dev->msg_buf = msg->buf;
 	i2c_dev->msg_buf_remaining = msg->len;
-	INIT_COMPLETION(i2c_dev->completion);
+	reinit_completion(&i2c_dev->completion);
 
 	bcm2835_i2c_writel(i2c_dev, BCM2835_I2C_C, BCM2835_I2C_C_CLEAR);
 

drivers/i2c/busses/i2c-davinci.c

@@ -323,7 +323,7 @@ i2c_davinci_xfer_msg(struct i2c_adapter *adap, struct i2c_msg *msg, int stop)
 
 	davinci_i2c_write_reg(dev, DAVINCI_I2C_CNT_REG, dev->buf_len);
 
-	INIT_COMPLETION(dev->cmd_complete);
+	reinit_completion(&dev->cmd_complete);
 	dev->cmd_err = 0;
 
 	/* Take I2C out of reset and configure it as master */

drivers/i2c/busses/i2c-designware-core.c

@@ -613,7 +613,7 @@ i2c_dw_xfer(struct i2c_adapter *adap, struct i2c_msg msgs[], int num)
 	mutex_lock(&dev->lock);
 	pm_runtime_get_sync(dev->dev);
 
-	INIT_COMPLETION(dev->cmd_complete);
+	reinit_completion(&dev->cmd_complete);
 	dev->msgs = msgs;
 	dev->msgs_num = num;
 	dev->cmd_err = 0;

drivers/i2c/busses/i2c-ismt.c

@@ -541,7 +541,7 @@ static int ismt_access(struct i2c_adapter *adap, u16 addr,
 		desc->dptr_high = upper_32_bits(dma_addr);
 	}
 
-	INIT_COMPLETION(priv->cmp);
+	reinit_completion(&priv->cmp);
 
 	/* Add the descriptor */
 	ismt_submit_desc(priv);

drivers/i2c/busses/i2c-mxs.c

@@ -505,7 +505,7 @@ static int mxs_i2c_xfer_msg(struct i2c_adapter *adap, struct i2c_msg *msg,
 				return err;
 		}
 	} else {
-		INIT_COMPLETION(i2c->cmd_complete);
+		reinit_completion(&i2c->cmd_complete);
 		ret = mxs_i2c_dma_setup_xfer(adap, msg, flags);
 		if (ret)
 			return ret;

drivers/i2c/busses/i2c-omap.c

@@ -543,7 +543,7 @@ static int omap_i2c_xfer_msg(struct i2c_adapter *adap,
 	w |= OMAP_I2C_BUF_RXFIF_CLR | OMAP_I2C_BUF_TXFIF_CLR;
 	omap_i2c_write_reg(dev, OMAP_I2C_BUF_REG, w);
 
-	INIT_COMPLETION(dev->cmd_complete);
+	reinit_completion(&dev->cmd_complete);
 	dev->cmd_err = 0;
 
 	w = OMAP_I2C_CON_EN | OMAP_I2C_CON_MST | OMAP_I2C_CON_STT;

drivers/i2c/busses/i2c-tegra.c

@@ -544,7 +544,7 @@ static int tegra_i2c_xfer_msg(struct tegra_i2c_dev *i2c_dev,
 	i2c_dev->msg_buf_remaining = msg->len;
 	i2c_dev->msg_err = I2C_ERR_NONE;
 	i2c_dev->msg_read = (msg->flags & I2C_M_RD);
-	INIT_COMPLETION(i2c_dev->msg_complete);
+	reinit_completion(&i2c_dev->msg_complete);
 
 	packet_header = (0 << PACKET_HEADER0_HEADER_SIZE_SHIFT) |
 			PACKET_HEADER0_PROTOCOL_I2C |

drivers/i2c/busses/i2c-wmt.c

@@ -158,7 +158,7 @@ static int wmt_i2c_write(struct i2c_adapter *adap, struct i2c_msg *pmsg,
 		writew(val, i2c_dev->base + REG_CR);
 	}
 
-	INIT_COMPLETION(i2c_dev->complete);
+	reinit_completion(&i2c_dev->complete);
 
 	if (i2c_dev->mode == I2C_MODE_STANDARD)
 		tcr_val = TCR_STANDARD_MODE;
@@ -247,7 +247,7 @@ static int wmt_i2c_read(struct i2c_adapter *adap, struct i2c_msg *pmsg,
 		writew(val, i2c_dev->base + REG_CR);
 	}
 
-	INIT_COMPLETION(i2c_dev->complete);
+	reinit_completion(&i2c_dev->complete);
 
 	if (i2c_dev->mode == I2C_MODE_STANDARD)
 		tcr_val = TCR_STANDARD_MODE;

drivers/iio/adc/ad_sigma_delta.c

@@ -188,7 +188,7 @@ static int ad_sd_calibrate(struct ad_sigma_delta *sigma_delta,
 
 	spi_bus_lock(sigma_delta->spi->master);
 	sigma_delta->bus_locked = true;
-	INIT_COMPLETION(sigma_delta->completion);
+	reinit_completion(&sigma_delta->completion);
 
 	ret = ad_sigma_delta_set_mode(sigma_delta, mode);
 	if (ret < 0)
@@ -259,7 +259,7 @@ int ad_sigma_delta_single_conversion(struct iio_dev *indio_dev,
 
 	spi_bus_lock(sigma_delta->spi->master);
 	sigma_delta->bus_locked = true;
-	INIT_COMPLETION(sigma_delta->completion);
+	reinit_completion(&sigma_delta->completion);
 
 	ad_sigma_delta_set_mode(sigma_delta, AD_SD_MODE_SINGLE);
 
@@ -343,7 +343,7 @@ static int ad_sd_buffer_postdisable(struct iio_dev *indio_dev)
 {
 	struct ad_sigma_delta *sigma_delta = iio_device_get_drvdata(indio_dev);
 
-	INIT_COMPLETION(sigma_delta->completion);
+	reinit_completion(&sigma_delta->completion);
 	wait_for_completion_timeout(&sigma_delta->completion, HZ);
 
 	if (!sigma_delta->irq_dis) {

drivers/iio/adc/nau7802.c

@@ -190,7 +190,7 @@ static int nau7802_read_irq(struct iio_dev *indio_dev,
 	struct nau7802_state *st = iio_priv(indio_dev);
 	int ret;
 
-	INIT_COMPLETION(st->value_ok);
+	reinit_completion(&st->value_ok);
 	enable_irq(st->client->irq);
 
 	nau7802_sync(st);

drivers/iio/industrialio-event.c

@@ -56,7 +56,7 @@ int iio_push_event(struct iio_dev *indio_dev, u64 ev_code, s64 timestamp)
 		ev.id = ev_code;
 		ev.timestamp = timestamp;
 
-		copied = kfifo_put(&ev_int->det_events, &ev);
+		copied = kfifo_put(&ev_int->det_events, ev);
 		if (copied != 0)
 			wake_up_locked_poll(&ev_int->wait, POLLIN);
 	}

drivers/input/touchscreen/cyttsp_core.c

@@ -242,7 +242,7 @@ static int cyttsp_soft_reset(struct cyttsp *ts)
 	int retval;
 
 	/* wait for interrupt to set ready completion */
-	INIT_COMPLETION(ts->bl_ready);
+	reinit_completion(&ts->bl_ready);
 	ts->state = CY_BL_STATE;
 
 	enable_irq(ts->irq);

drivers/iommu/arm-smmu.c

@@ -1212,7 +1212,10 @@ static int arm_smmu_alloc_init_pte(struct arm_smmu_device *smmu, pmd_t *pmd,
 
 		arm_smmu_flush_pgtable(smmu, page_address(table),
 				       ARM_SMMU_PTE_HWTABLE_SIZE);
-		pgtable_page_ctor(table);
+		if (!pgtable_page_ctor(table)) {
+			__free_page(table);
+			return -ENOMEM;
+		}
 		pmd_populate(NULL, pmd, table);
 		arm_smmu_flush_pgtable(smmu, pmd, sizeof(*pmd));
 	}

drivers/md/dm-crypt.c

@@ -950,7 +950,7 @@ static int crypt_convert(struct crypt_config *cc,
 		/* async */
 		case -EBUSY:
 			wait_for_completion(&ctx->restart);
-			INIT_COMPLETION(ctx->restart);
+			reinit_completion(&ctx->restart);
 			/* fall through*/
 		case -EINPROGRESS:
 			this_cc->req = NULL;

drivers/md/raid5.c

@@ -293,20 +293,6 @@ static void __release_stripe(struct r5conf *conf, struct stripe_head *sh)
 		do_release_stripe(conf, sh);
 }
 
-static struct llist_node *llist_reverse_order(struct llist_node *head)
-{
-	struct llist_node *new_head = NULL;
-
-	while (head) {
-		struct llist_node *tmp = head;
-		head = head->next;
-		tmp->next = new_head;
-		new_head = tmp;
-	}
-
-	return new_head;
-}
-
 /* should hold conf->device_lock already */
 static int release_stripe_list(struct r5conf *conf)
 {

drivers/media/platform/blackfin/bfin_capture.c

@@ -422,7 +422,7 @@ static int bcap_start_streaming(struct vb2_queue *vq, unsigned int count)
 		return ret;
 	}
 
-	INIT_COMPLETION(bcap_dev->comp);
+	reinit_completion(&bcap_dev->comp);
 	bcap_dev->stop = false;
 	return 0;
 }

drivers/media/radio/radio-wl1273.c

@@ -375,7 +375,7 @@ static int wl1273_fm_set_tx_freq(struct wl1273_device *radio, unsigned int freq)
 	if (r)
 		return r;
 
-	INIT_COMPLETION(radio->busy);
+	reinit_completion(&radio->busy);
 
 	/* wait for the FR IRQ */
 	r = wait_for_completion_timeout(&radio->busy, msecs_to_jiffies(2000));
@@ -389,7 +389,7 @@ static int wl1273_fm_set_tx_freq(struct wl1273_device *radio, unsigned int freq)
 	if (r)
 		return r;
 
-	INIT_COMPLETION(radio->busy);
+	reinit_completion(&radio->busy);
 
 	/* wait for the POWER_ENB IRQ */
 	r = wait_for_completion_timeout(&radio->busy, msecs_to_jiffies(1000));
@@ -444,7 +444,7 @@ static int wl1273_fm_set_rx_freq(struct wl1273_device *radio, unsigned int freq)
 		goto err;
 	}
 
-	INIT_COMPLETION(radio->busy);
+	reinit_completion(&radio->busy);
 
 	r = wait_for_completion_timeout(&radio->busy, msecs_to_jiffies(2000));
 	if (!r) {
@@ -805,7 +805,7 @@ static int wl1273_fm_set_seek(struct wl1273_device *radio,
 	if (level < SCHAR_MIN || level > SCHAR_MAX)
 		return -EINVAL;
 
-	INIT_COMPLETION(radio->busy);
+	reinit_completion(&radio->busy);
 	dev_dbg(radio->dev, "%s: BUSY\n", __func__);
 
 	r = core->write(core, WL1273_INT_MASK_SET, radio->irq_flags);
@@ -847,7 +847,7 @@ static int wl1273_fm_set_seek(struct wl1273_device *radio,
 	if (r)
 		goto out;
 
-	INIT_COMPLETION(radio->busy);
+	reinit_completion(&radio->busy);
 	dev_dbg(radio->dev, "%s: BUSY\n", __func__);
 
 	r = core->write(core, WL1273_TUNER_MODE_SET, TUNER_MODE_AUTO_SEEK);

drivers/media/radio/si470x/radio-si470x-common.c

@@ -218,7 +218,7 @@ static int si470x_set_chan(struct si470x_device *radio, unsigned short chan)
 		goto done;
 
 	/* wait till tune operation has completed */
-	INIT_COMPLETION(radio->completion);
+	reinit_completion(&radio->completion);
 	retval = wait_for_completion_timeout(&radio->completion,
 			msecs_to_jiffies(tune_timeout));
 	if (!retval)
@@ -341,7 +341,7 @@ static int si470x_set_seek(struct si470x_device *radio,
 		return retval;
 
 	/* wait till tune operation has completed */
-	INIT_COMPLETION(radio->completion);
+	reinit_completion(&radio->completion);
 	retval = wait_for_completion_timeout(&radio->completion,
 			msecs_to_jiffies(seek_timeout));
 	if (!retval)

drivers/media/rc/iguanair.c

@@ -207,7 +207,7 @@ static int iguanair_send(struct iguanair *ir, unsigned size)
 {
 	int rc;
 
-	INIT_COMPLETION(ir->completion);
+	reinit_completion(&ir->completion);
 
 	ir->urb_out->transfer_buffer_length = size;
 	rc = usb_submit_urb(ir->urb_out, GFP_KERNEL);

drivers/memstick/core/memstick.c

@@ -253,7 +253,7 @@ void memstick_new_req(struct memstick_host *host)
 {
 	if (host->card) {
 		host->retries = cmd_retries;
-		INIT_COMPLETION(host->card->mrq_complete);
+		reinit_completion(&host->card->mrq_complete);
 		host->request(host);
 	}
 }