Merge branch 'akpm' (patches from Andrew)

Merge second patch-bomb from Andrew Morton:

 - a couple of hotfixes

 - the rest of MM

 - a new timer slack control in procfs

 - a couple of procfs fixes

 - a few misc things

 - some printk tweaks

 - lib/ updates, notably to radix-tree.

 - add my and Nick Piggin's old userspace radix-tree test harness to
   tools/testing/radix-tree/.  Matthew said it was a godsend during the
   radix-tree work he did.

 - a few code-size improvements, switching to __always_inline where gcc
   screwed up.

 - partially implement character sets in sscanf

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (118 commits)
  sscanf: implement basic character sets
  lib/bug.c: use common WARN helper
  param: convert some "on"/"off" users to strtobool
  lib: add "on"/"off" support to kstrtobool
  lib: update single-char callers of strtobool()
  lib: move strtobool() to kstrtobool()
  include/linux/unaligned: force inlining of byteswap operations
  include/uapi/linux/byteorder, swab: force inlining of some byteswap operations
  include/asm-generic/atomic-long.h: force inlining of some atomic_long operations
  usb: common: convert to use match_string() helper
  ide: hpt366: convert to use match_string() helper
  ata: hpt366: convert to use match_string() helper
  power: ab8500: convert to use match_string() helper
  power: charger_manager: convert to use match_string() helper
  drm/edid: convert to use match_string() helper
  pinctrl: convert to use match_string() helper
  device property: convert to use match_string() helper
  lib/string: introduce match_string() helper
  radix-tree tests: add test for radix_tree_iter_next
  radix-tree tests: add regression3 test
  ...

Documentation/cgroup-v1/cgroups.txt

@@ -8,7 +8,7 @@ Original copyright statements from cpusets.txt:
 Portions Copyright (C) 2004 BULL SA.
 Portions Copyright (c) 2004-2006 Silicon Graphics, Inc.
 Modified by Paul Jackson <pj@sgi.com>
-Modified by Christoph Lameter <clameter@sgi.com>
+Modified by Christoph Lameter <cl@linux.com>
 
 CONTENTS:
 =========

Documentation/cgroup-v1/cpusets.txt

@@ -6,7 +6,7 @@ Written by Simon.Derr@bull.net
 
 Portions Copyright (c) 2004-2006 Silicon Graphics, Inc.
 Modified by Paul Jackson <pj@sgi.com>
-Modified by Christoph Lameter <clameter@sgi.com>
+Modified by Christoph Lameter <cl@linux.com>
 Modified by Paul Menage <menage@google.com>
 Modified by Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
 

Documentation/cgroup-v2.txt

@@ -843,6 +843,15 @@ PAGE_SIZE multiple when read back.
 		Amount of memory used to cache filesystem data,
 		including tmpfs and shared memory.
 
+	  kernel_stack
+
+		Amount of memory allocated to kernel stacks.
+
+	  slab
+
+		Amount of memory used for storing in-kernel data
+		structures.
+
 	  sock
 
 		Amount of memory used in network transmission buffers
@@ -871,6 +880,16 @@ PAGE_SIZE multiple when read back.
 		on the internal memory management lists used by the
 		page reclaim algorithm
 
+	  slab_reclaimable
+
+		Part of "slab" that might be reclaimed, such as
+		dentries and inodes.
+
+	  slab_unreclaimable
+
+		Part of "slab" that cannot be reclaimed on memory
+		pressure.
+
 	  pgfault
 
 		Total number of page faults incurred
@@ -1368,6 +1387,12 @@ system than killing the group.  Otherwise, memory.max is there to
 limit this type of spillover and ultimately contain buggy or even
 malicious applications.
 
+Setting the original memory.limit_in_bytes below the current usage was
+subject to a race condition, where concurrent charges could cause the
+limit setting to fail. memory.max on the other hand will first set the
+limit to prevent new charges, and then reclaim and OOM kill until the
+new limit is met - or the task writing to memory.max is killed.
+
 The combined memory+swap accounting and limiting is replaced by real
 control over swap space.
 

Documentation/filesystems/proc.txt

@@ -43,6 +43,7 @@ Table of Contents
   3.7   /proc/<pid>/task/<tid>/children - Information about task children
   3.8   /proc/<pid>/fdinfo/<fd> - Information about opened file
   3.9   /proc/<pid>/map_files - Information about memory mapped files
+  3.10  /proc/<pid>/timerslack_ns - Task timerslack value
 
   4	Configuring procfs
   4.1	Mount options
@@ -1862,6 +1863,23 @@ time one can open(2) mappings from the listings of two processes and
 comparing their inode numbers to figure out which anonymous memory areas
 are actually shared.
 
+3.10	/proc/<pid>/timerslack_ns - Task timerslack value
+---------------------------------------------------------
+This file provides the value of the task's timerslack value in nanoseconds.
+This value specifies a amount of time that normal timers may be deferred
+in order to coalesce timers and avoid unnecessary wakeups.
+
+This allows a task's interactivity vs power consumption trade off to be
+adjusted.
+
+Writing 0 to the file will set the tasks timerslack to the default value.
+
+Valid values are from 0 - ULLONG_MAX
+
+An application setting the value must have PTRACE_MODE_ATTACH_FSCREDS level
+permissions on the task specified to change its timerslack_ns value.
+
+
 ------------------------------------------------------------------------------
 Configuring procfs
 ------------------------------------------------------------------------------

Documentation/sysctl/vm.txt

@@ -803,6 +803,24 @@ performance impact. Reclaim code needs to take various locks to find freeable
 directory and inode objects. With vfs_cache_pressure=1000, it will look for
 ten times more freeable objects than there are.
 
+=============================================================
+
+watermark_scale_factor:
+
+This factor controls the aggressiveness of kswapd. It defines the
+amount of memory left in a node/system before kswapd is woken up and
+how much memory needs to be free before kswapd goes back to sleep.
+
+The unit is in fractions of 10,000. The default value of 10 means the
+distances between watermarks are 0.1% of the available memory in the
+node/system. The maximum value is 1000, or 10% of memory.
+
+A high rate of threads entering direct reclaim (allocstall) or kswapd
+going to sleep prematurely (kswapd_low_wmark_hit_quickly) can indicate
+that the number of free pages kswapd maintains for latency reasons is
+too small for the allocation bursts occurring in the system. This knob
+can then be used to tune kswapd aggressiveness accordingly.
+
 ==============================================================
 
 zone_reclaim_mode:

Documentation/vm/transhuge.txt

@@ -113,9 +113,26 @@ guaranteed, but it may be more likely in case the allocation is for a
 MADV_HUGEPAGE region.
 
 echo always >/sys/kernel/mm/transparent_hugepage/defrag
+echo defer >/sys/kernel/mm/transparent_hugepage/defrag
 echo madvise >/sys/kernel/mm/transparent_hugepage/defrag
 echo never >/sys/kernel/mm/transparent_hugepage/defrag
 
+"always" means that an application requesting THP will stall on allocation
+failure and directly reclaim pages and compact memory in an effort to
+allocate a THP immediately. This may be desirable for virtual machines
+that benefit heavily from THP use and are willing to delay the VM start
+to utilise them.
+
+"defer" means that an application will wake kswapd in the background
+to reclaim pages and wake kcompact to compact memory so that THP is
+available in the near future. It's the responsibility of khugepaged
+to then install the THP pages later.
+
+"madvise" will enter direct reclaim like "always" but only for regions
+that are have used madvise(MADV_HUGEPAGE). This is the default behaviour.
+
+"never" should be self-explanatory.
+
 By default kernel tries to use huge zero page on read page fault.
 It's possible to disable huge zero page by writing 0 or enable it
 back by writing 1:
@@ -229,6 +246,11 @@ thp_split_page is incremented every time a huge page is split into base
 thp_split_page_failed is is incremented if kernel fails to split huge
 	page. This can happen if the page was pinned by somebody.
 
+thp_deferred_split_page is incremented when a huge page is put onto split
+	queue. This happens when a huge page is partially unmapped and
+	splitting it would free up some memory. Pages on split queue are
+	going to be split under memory pressure.
+
 thp_split_pmd is incremented every time a PMD split into table of PTEs.
 	This can happen, for instance, when application calls mprotect() or
 	munmap() on part of huge page. It doesn't split huge page, only

MAINTAINERS

@@ -8498,7 +8498,7 @@ F:	include/crypto/pcrypt.h
 
 PER-CPU MEMORY ALLOCATOR
 M:	Tejun Heo <tj@kernel.org>
-M:	Christoph Lameter <cl@linux-foundation.org>
+M:	Christoph Lameter <cl@linux.com>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu.git
 S:	Maintained
 F:	include/linux/percpu*.h
@@ -11296,7 +11296,6 @@ F:	include/linux/cdrom.h
 F:	include/uapi/linux/cdrom.h
 
 UNISYS S-PAR DRIVERS
-M:	Benjamin Romer <benjamin.romer@unisys.com>
 M:	David Kershner <david.kershner@unisys.com>
 L:	sparmaintainer@unisys.com (Unisys internal)
 S:	Supported

arch/arc/include/asm/hugepage.h

@@ -30,19 +30,16 @@ static inline pmd_t pte_pmd(pte_t pte)
 #define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
 #define pmd_mkhuge(pmd)		pte_pmd(pte_mkhuge(pmd_pte(pmd)))
 #define pmd_mknotpresent(pmd)	pte_pmd(pte_mknotpresent(pmd_pte(pmd)))
-#define pmd_mksplitting(pmd)	pte_pmd(pte_mkspecial(pmd_pte(pmd)))
 #define pmd_mkclean(pmd)	pte_pmd(pte_mkclean(pmd_pte(pmd)))
 
 #define pmd_write(pmd)		pte_write(pmd_pte(pmd))
 #define pmd_young(pmd)		pte_young(pmd_pte(pmd))
 #define pmd_pfn(pmd)		pte_pfn(pmd_pte(pmd))
 #define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
-#define pmd_special(pmd)	pte_special(pmd_pte(pmd))
 
 #define mk_pmd(page, prot)	pte_pmd(mk_pte(page, prot))
 
 #define pmd_trans_huge(pmd)	(pmd_val(pmd) & _PAGE_HW_SZ)
-#define pmd_trans_splitting(pmd)	(pmd_trans_huge(pmd) && pmd_special(pmd))
 
 #define pfn_pmd(pfn, prot)	(__pmd(((pfn) << PAGE_SHIFT) | pgprot_val(prot)))
 

arch/arm/mm/fault.c

@@ -346,7 +346,7 @@ retry:
 	up_read(&mm->mmap_sem);
 
 	/*
-	 * Handle the "normal" case first - VM_FAULT_MAJOR / VM_FAULT_MINOR
+	 * Handle the "normal" case first - VM_FAULT_MAJOR
 	 */
 	if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP | VM_FAULT_BADACCESS))))
 		return 0;

arch/arm/mm/mmu.c

@@ -732,7 +732,7 @@ static void *__init late_alloc(unsigned long sz)
 	return ptr;
 }
 
-static pte_t * __init pte_alloc(pmd_t *pmd, unsigned long addr,
+static pte_t * __init arm_pte_alloc(pmd_t *pmd, unsigned long addr,
 				unsigned long prot,
 				void *(*alloc)(unsigned long sz))
 {
@@ -747,7 +747,7 @@ static pte_t * __init pte_alloc(pmd_t *pmd, unsigned long addr,
 static pte_t * __init early_pte_alloc(pmd_t *pmd, unsigned long addr,
 				      unsigned long prot)
 {
-	return pte_alloc(pmd, addr, prot, early_alloc);
+	return arm_pte_alloc(pmd, addr, prot, early_alloc);
 }
 
 static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr,
@@ -756,7 +756,7 @@ static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr,
 				  void *(*alloc)(unsigned long sz),
 				  bool ng)
 {
-	pte_t *pte = pte_alloc(pmd, addr, type->prot_l1, alloc);
+	pte_t *pte = arm_pte_alloc(pmd, addr, type->prot_l1, alloc);
 	do {
 		set_pte_ext(pte, pfn_pte(pfn, __pgprot(type->prot_pte)),
 			    ng ? PTE_EXT_NG : 0);

arch/arm/mm/pgd.c

@@ -80,7 +80,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 		if (!new_pmd)
 			goto no_pmd;
 
-		new_pte = pte_alloc_map(mm, NULL, new_pmd, 0);
+		new_pte = pte_alloc_map(mm, new_pmd, 0);
 		if (!new_pte)
 			goto no_pte;
 

arch/arm64/mm/fault.c

@@ -304,7 +304,7 @@ retry:
 	up_read(&mm->mmap_sem);
 
 	/*
-	 * Handle the "normal" case first - VM_FAULT_MAJOR / VM_FAULT_MINOR
+	 * Handle the "normal" case first - VM_FAULT_MAJOR
 	 */
 	if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP |
 			      VM_FAULT_BADACCESS))))

arch/arm64/mm/hugetlbpage.c

@@ -124,7 +124,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 		 * will be no pte_unmap() to correspond with this
 		 * pte_alloc_map().
 		 */
-		pte = pte_alloc_map(mm, NULL, pmd, addr);
+		pte = pte_alloc_map(mm, pmd, addr);
 	} else if (sz == PMD_SIZE) {
 		if (IS_ENABLED(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) &&
 		    pud_none(*pud))

arch/c6x/Kconfig

@@ -36,6 +36,7 @@ config GENERIC_HWEIGHT
 
 config GENERIC_BUG
 	def_bool y
+	depends on BUG
 
 config C6X_BIG_KERNEL
 	bool "Build a big kernel"

arch/ia64/include/asm/io.h

@@ -433,6 +433,7 @@ static inline void __iomem * ioremap_cache (unsigned long phys_addr, unsigned lo
 	return ioremap(phys_addr, size);
 }
 #define ioremap_cache ioremap_cache
+#define ioremap_uc ioremap_nocache
 
 
 /*

arch/ia64/include/asm/rwsem.h

@@ -3,7 +3,7 @@
  *
  * Copyright (C) 2003 Ken Chen <kenneth.w.chen@intel.com>
  * Copyright (C) 2003 Asit Mallick <asit.k.mallick@intel.com>
- * Copyright (C) 2005 Christoph Lameter <clameter@sgi.com>
+ * Copyright (C) 2005 Christoph Lameter <cl@linux.com>
  *
  * Based on asm-i386/rwsem.h and other architecture implementation.
  *

arch/ia64/mm/hugetlbpage.c

@@ -38,7 +38,7 @@ huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz)
 	if (pud) {
 		pmd = pmd_alloc(mm, pud, taddr);
 		if (pmd)
-			pte = pte_alloc_map(mm, NULL, pmd, taddr);
+			pte = pte_alloc_map(mm, pmd, taddr);
 	}
 	return pte;
 }

arch/metag/mm/hugetlbpage.c

@@ -67,7 +67,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 	pgd = pgd_offset(mm, addr);
 	pud = pud_offset(pgd, addr);
 	pmd = pmd_offset(pud, addr);
-	pte = pte_alloc_map(mm, NULL, pmd, addr);
+	pte = pte_alloc_map(mm, pmd, addr);
 	pgd->pgd &= ~_PAGE_SZ_MASK;
 	pgd->pgd |= _PAGE_SZHUGE;
 

arch/mips/mm/gup.c

@@ -64,7 +64,7 @@ static inline void get_head_page_multiple(struct page *page, int nr)
 {
 	VM_BUG_ON(page != compound_head(page));
 	VM_BUG_ON(page_count(page) == 0);
-	atomic_add(nr, &page->_count);
+	page_ref_add(page, nr);
 	SetPageReferenced(page);
 }
 

arch/mn10300/Kconfig

@@ -53,6 +53,7 @@ config GENERIC_HWEIGHT
 
 config GENERIC_BUG
 	def_bool y
+	depends on BUG
 
 config QUICKLIST
 	def_bool y

arch/mn10300/kernel/fpu-nofpu.c

@@ -9,6 +9,7 @@
  * 2 of the Licence, or (at your option) any later version.
  */
 #include <asm/fpu.h>
+#include <asm/elf.h>
 
 /*
  * handle an FPU operational exception

arch/parisc/mm/hugetlbpage.c

@@ -63,7 +63,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 	if (pud) {
 		pmd = pmd_alloc(mm, pud, addr);
 		if (pmd)
-			pte = pte_alloc_map(mm, NULL, pmd, addr);
+			pte = pte_alloc_map(mm, pmd, addr);
 	}
 	return pte;
 }

arch/powerpc/Kconfig

@@ -158,6 +158,7 @@ config PPC
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select HAVE_ARCH_SECCOMP_FILTER
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
+	select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
 
 config GENERIC_CSUM
 	def_bool CPU_LITTLE_ENDIAN

arch/powerpc/kernel/rtasd.c

@@ -49,7 +49,7 @@ static unsigned int rtas_error_log_buffer_max;
 static unsigned int event_scan;
 static unsigned int rtas_event_scan_rate;
 
-static int full_rtas_msgs = 0;
+static bool full_rtas_msgs;
 
 /* Stop logging to nvram after first fatal error */
 static int logging_enabled; /* Until we initialize everything,
@@ -592,11 +592,6 @@ __setup("surveillance=", surveillance_setup);
 
 static int __init rtasmsgs_setup(char *str)
 {
-	if (strcmp(str, "on") == 0)
-		full_rtas_msgs = 1;
-	else if (strcmp(str, "off") == 0)
-		full_rtas_msgs = 0;
-
-	return 1;
+	return (kstrtobool(str, &full_rtas_msgs) == 0);
 }
 __setup("rtasmsgs=", rtasmsgs_setup);

arch/powerpc/kernel/traps.c

@@ -203,9 +203,8 @@ static int __kprobes __die(const char *str, struct pt_regs *regs, long err)
 #ifdef CONFIG_SMP
 	printk("SMP NR_CPUS=%d ", NR_CPUS);
 #endif
-#ifdef CONFIG_DEBUG_PAGEALLOC
-	printk("DEBUG_PAGEALLOC ");
-#endif
+	if (debug_pagealloc_enabled())
+		printk("DEBUG_PAGEALLOC ");
 #ifdef CONFIG_NUMA
 	printk("NUMA ");
 #endif

arch/powerpc/mm/hash_utils_64.c

@@ -255,8 +255,10 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
 
 		if (ret < 0)
 			break;
+
 #ifdef CONFIG_DEBUG_PAGEALLOC
-		if ((paddr >> PAGE_SHIFT) < linear_map_hash_count)
+		if (debug_pagealloc_enabled() &&
+			(paddr >> PAGE_SHIFT) < linear_map_hash_count)
 			linear_map_hash_slots[paddr >> PAGE_SHIFT] = ret | 0x80;
 #endif /* CONFIG_DEBUG_PAGEALLOC */
 	}
@@ -512,17 +514,17 @@ static void __init htab_init_page_sizes(void)
 	if (mmu_has_feature(MMU_FTR_16M_PAGE))
 		memcpy(mmu_psize_defs, mmu_psize_defaults_gp,
 		       sizeof(mmu_psize_defaults_gp));
- found:
-#ifndef CONFIG_DEBUG_PAGEALLOC
-	/*
-	 * Pick a size for the linear mapping. Currently, we only support
-	 * 16M, 1M and 4K which is the default
-	 */
-	if (mmu_psize_defs[MMU_PAGE_16M].shift)
-		mmu_linear_psize = MMU_PAGE_16M;
-	else if (mmu_psize_defs[MMU_PAGE_1M].shift)
-		mmu_linear_psize = MMU_PAGE_1M;
-#endif /* CONFIG_DEBUG_PAGEALLOC */
+found:
+	if (!debug_pagealloc_enabled()) {
+		/*
+		 * Pick a size for the linear mapping. Currently, we only
+		 * support 16M, 1M and 4K which is the default
+		 */
+		if (mmu_psize_defs[MMU_PAGE_16M].shift)
+			mmu_linear_psize = MMU_PAGE_16M;
+		else if (mmu_psize_defs[MMU_PAGE_1M].shift)
+			mmu_linear_psize = MMU_PAGE_1M;
+	}
 
 #ifdef CONFIG_PPC_64K_PAGES
 	/*
@@ -721,10 +723,12 @@ static void __init htab_initialize(void)
 	prot = pgprot_val(PAGE_KERNEL);
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
-	linear_map_hash_count = memblock_end_of_DRAM() >> PAGE_SHIFT;
-	linear_map_hash_slots = __va(memblock_alloc_base(linear_map_hash_count,
-						    1, ppc64_rma_size));
-	memset(linear_map_hash_slots, 0, linear_map_hash_count);
+	if (debug_pagealloc_enabled()) {
+		linear_map_hash_count = memblock_end_of_DRAM() >> PAGE_SHIFT;
+		linear_map_hash_slots = __va(memblock_alloc_base(
+				linear_map_hash_count, 1, ppc64_rma_size));
+		memset(linear_map_hash_slots, 0, linear_map_hash_count);
+	}
 #endif /* CONFIG_DEBUG_PAGEALLOC */
 
 	/* On U3 based machines, we need to reserve the DART area and

arch/powerpc/mm/init_32.c

@@ -112,10 +112,10 @@ void __init MMU_setup(void)
 	if (strstr(boot_command_line, "noltlbs")) {
 		__map_without_ltlbs = 1;
 	}
-#ifdef CONFIG_DEBUG_PAGEALLOC
-	__map_without_bats = 1;
-	__map_without_ltlbs = 1;
-#endif
+	if (debug_pagealloc_enabled()) {
+		__map_without_bats = 1;
+		__map_without_ltlbs = 1;
+	}
 }
 
 /*

arch/powerpc/mm/mmu_context_hash64.c

@@ -118,8 +118,7 @@ static void destroy_pagetable_page(struct mm_struct *mm)
 	/* drop all the pending references */
 	count = ((unsigned long)pte_frag & ~PAGE_MASK) >> PTE_FRAG_SIZE_SHIFT;
 	/* We allow PTE_FRAG_NR fragments from a PTE page */
-	count = atomic_sub_return(PTE_FRAG_NR - count, &page->_count);
-	if (!count) {
+	if (page_ref_sub_and_test(page, PTE_FRAG_NR - count)) {
 		pgtable_page_dtor(page);
 		free_hot_cold_page(page, 0);
 	}

arch/powerpc/mm/pgtable_64.c

@@ -403,7 +403,7 @@ static pte_t *__alloc_for_cache(struct mm_struct *mm, int kernel)
 	 * count.
 	 */
 	if (likely(!mm->context.pte_frag)) {
-		atomic_set(&page->_count, PTE_FRAG_NR);
+		set_page_count(page, PTE_FRAG_NR);
 		mm->context.pte_frag = ret + PTE_FRAG_SIZE;
 	}
 	spin_unlock(&mm->page_table_lock);

arch/powerpc/platforms/512x/mpc512x_shared.c

@@ -188,7 +188,7 @@ static struct fsl_diu_shared_fb __attribute__ ((__aligned__(8))) diu_shared_fb;
 static inline void mpc512x_free_bootmem(struct page *page)
 {
 	BUG_ON(PageTail(page));
-	BUG_ON(atomic_read(&page->_count) > 1);
+	BUG_ON(page_ref_count(page) > 1);
 	free_reserved_page(page);
 }
 

arch/powerpc/platforms/pseries/hotplug-cpu.c

@@ -47,20 +47,14 @@ static DEFINE_PER_CPU(enum cpu_state_vals, current_state) = CPU_STATE_OFFLINE;
 
 static enum cpu_state_vals default_offline_state = CPU_STATE_OFFLINE;
 
-static int cede_offline_enabled __read_mostly = 1;
+static bool cede_offline_enabled __read_mostly = true;
 
 /*
  * Enable/disable cede_offline when available.
  */
 static int __init setup_cede_offline(char *str)
 {
-	if (!strcmp(str, "off"))
-		cede_offline_enabled = 0;
-	else if (!strcmp(str, "on"))
-		cede_offline_enabled = 1;
-	else
-		return 0;
-	return 1;
+	return (kstrtobool(str, &cede_offline_enabled) == 0);
 }
 
 __setup("cede_offline=", setup_cede_offline);

arch/s390/kernel/time.c

@@ -1432,7 +1432,7 @@ device_initcall(etr_init_sysfs);
 /*
  * Server Time Protocol (STP) code.
  */
-static int stp_online;
+static bool stp_online;
 static struct stp_sstpi stp_info;
 static void *stp_page;
 
@@ -1443,11 +1443,7 @@ static struct timer_list stp_timer;
 
 static int __init early_parse_stp(char *p)
 {
-	if (strncmp(p, "off", 3) == 0)
-		stp_online = 0;
-	else if (strncmp(p, "on", 2) == 0)
-		stp_online = 1;
-	return 0;
+	return kstrtobool(p, &stp_online);
 }
 early_param("stp", early_parse_stp);
 

arch/s390/kernel/topology.c

@@ -37,7 +37,7 @@ static void set_topology_timer(void);
 static void topology_work_fn(struct work_struct *work);
 static struct sysinfo_15_1_x *tl_info;
 
-static int topology_enabled = 1;
+static bool topology_enabled = true;
 static DECLARE_WORK(topology_work, topology_work_fn);
 
 /*
@@ -444,10 +444,7 @@ static const struct cpumask *cpu_book_mask(int cpu)
 
 static int __init early_parse_topology(char *p)
 {
-	if (strncmp(p, "off", 3))
-		return 0;
-	topology_enabled = 0;
-	return 0;
+	return kstrtobool(p, &topology_enabled);
 }
 early_param("topology", early_parse_topology);
 

arch/sh/mm/hugetlbpage.c

@@ -35,7 +35,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 		if (pud) {
 			pmd = pmd_alloc(mm, pud, addr);
 			if (pmd)
-				pte = pte_alloc_map(mm, NULL, pmd, addr);
+				pte = pte_alloc_map(mm, pmd, addr);
 		}
 	}
 

arch/sparc/mm/hugetlbpage.c

@@ -146,7 +146,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 	if (pud) {
 		pmd = pmd_alloc(mm, pud, addr);
 		if (pmd)
-			pte = pte_alloc_map(mm, NULL, pmd, addr);
+			pte = pte_alloc_map(mm, pmd, addr);
 	}
 	return pte;
 }

arch/tile/mm/hugetlbpage.c

@@ -77,7 +77,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 		else {
 			if (sz != PAGE_SIZE << huge_shift[HUGE_SHIFT_PAGE])
 				panic("Unexpected page size %#lx\n", sz);
-			return pte_alloc_map(mm, NULL, pmd, addr);
+			return pte_alloc_map(mm, pmd, addr);
 		}
 	}
 #else

arch/tile/mm/init.c

@@ -896,17 +896,15 @@ void __init pgtable_cache_init(void)
 		panic("pgtable_cache_init(): Cannot create pgd cache");
 }
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
-static long __write_once initfree;
-#else
 static long __write_once initfree = 1;
-#endif
+static bool __write_once set_initfree_done;
 
 /* Select whether to free (1) or mark unusable (0) the __init pages. */
 static int __init set_initfree(char *str)
 {
 	long val;
 	if (kstrtol(str, 0, &val) == 0) {
+		set_initfree_done = true;
 		initfree = val;
 		pr_info("initfree: %s free init pages\n",
 			initfree ? "will" : "won't");
@@ -919,6 +917,11 @@ static void free_init_pages(char *what, unsigned long begin, unsigned long end)
 {
 	unsigned long addr = (unsigned long) begin;
 
+	/* Prefer user request first */
+	if (!set_initfree_done) {
+		if (debug_pagealloc_enabled())
+			initfree = 0;
+	}
 	if (kdata_huge && !initfree) {
 		pr_warn("Warning: ignoring initfree=0: incompatible with kdata=huge\n");
 		initfree = 1;

arch/um/kernel/skas/mmu.c

@@ -31,7 +31,7 @@ static int init_stub_pte(struct mm_struct *mm, unsigned long proc,
 	if (!pmd)
 		goto out_pmd;
 
-	pte = pte_alloc_map(mm, NULL, pmd, proc);
+	pte = pte_alloc_map(mm, pmd, proc);
 	if (!pte)
 		goto out_pte;
 

arch/unicore32/mm/fault.c

@@ -276,7 +276,7 @@ retry:
 	up_read(&mm->mmap_sem);
 
 	/*
-	 * Handle the "normal" case first - VM_FAULT_MAJOR / VM_FAULT_MINOR
+	 * Handle the "normal" case first - VM_FAULT_MAJOR
 	 */
 	if (likely(!(fault &
 	       (VM_FAULT_ERROR | VM_FAULT_BADMAP | VM_FAULT_BADACCESS))))

arch/unicore32/mm/pgd.c

@@ -54,7 +54,7 @@ pgd_t *get_pgd_slow(struct mm_struct *mm)
 		if (!new_pmd)
 			goto no_pmd;
 
-		new_pte = pte_alloc_map(mm, NULL, new_pmd, 0);
+		new_pte = pte_alloc_map(mm, new_pmd, 0);
 		if (!new_pte)
 			goto no_pte;
 

arch/x86/kernel/aperture_64.c

@@ -227,19 +227,11 @@ static u32 __init search_agp_bridge(u32 *order, int *valid_agp)
 	return 0;
 }
 
-static int gart_fix_e820 __initdata = 1;
+static bool gart_fix_e820 __initdata = true;
 
 static int __init parse_gart_mem(char *p)
 {
-	if (!p)
-		return -EINVAL;
-
-	if (!strncmp(p, "off", 3))
-		gart_fix_e820 = 0;
-	else if (!strncmp(p, "on", 2))
-		gart_fix_e820 = 1;
-
-	return 0;
+	return kstrtobool(p, &gart_fix_e820);
 }
 early_param("gart_fix_e820", parse_gart_mem);
 

arch/x86/kernel/tboot.c

@@ -135,7 +135,7 @@ static int map_tboot_page(unsigned long vaddr, unsigned long pfn,
 	pmd = pmd_alloc(&tboot_mm, pud, vaddr);
 	if (!pmd)
 		return -1;
-	pte = pte_alloc_map(&tboot_mm, NULL, pmd, vaddr);
+	pte = pte_alloc_map(&tboot_mm, pmd, vaddr);
 	if (!pte)
 		return -1;
 	set_pte_at(&tboot_mm, vaddr, pte, pfn_pte(pfn, prot));

arch/x86/mm/gup.c

@@ -131,7 +131,7 @@ static inline void get_head_page_multiple(struct page *page, int nr)
 {
 	VM_BUG_ON_PAGE(page != compound_head(page), page);
 	VM_BUG_ON_PAGE(page_count(page) == 0, page);
-	atomic_add(nr, &page->_count);
+	page_ref_add(page, nr);
 	SetPageReferenced(page);
 }
 

arch/xtensa/mm/fault.c

@@ -146,7 +146,7 @@ good_area:
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 	if (flags & VM_FAULT_MAJOR)
 		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address);
-	else if (flags & VM_FAULT_MINOR)
+	else
 		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address);
 
 	return;

crypto/async_tx/async_pq.c

@@ -444,7 +444,7 @@ static int __init async_pq_init(void)
 
 static void __exit async_pq_exit(void)
 {
-	put_page(pq_scribble_page);
+	__free_page(pq_scribble_page);
 }
 
 module_init(async_pq_init);

drivers/ata/pata_hpt366.c

@@ -176,17 +176,14 @@ static int hpt_dma_blacklisted(const struct ata_device *dev, char *modestr,
 			       const char * const list[])
 {
 	unsigned char model_num[ATA_ID_PROD_LEN + 1];
-	int i = 0;
+	int i;
 
 	ata_id_c_string(dev->id, model_num, ATA_ID_PROD, sizeof(model_num));
 
-	while (list[i] != NULL) {
-		if (!strcmp(list[i], model_num)) {
-			pr_warn("%s is not supported for %s\n",
-				modestr, list[i]);
-			return 1;
-		}
-		i++;
+	i = match_string(list, -1, model_num);
+	if (i >= 0) {
+		pr_warn("%s is not supported for %s\n", modestr, list[i]);
+		return 1;
 	}
 	return 0;
 }

drivers/base/property.c

@@ -651,7 +651,7 @@ int fwnode_property_match_string(struct fwnode_handle *fwnode,
 	const char *propname, const char *string)
 {
 	const char **values;
-	int nval, ret, i;
+	int nval, ret;
 
 	nval = fwnode_property_read_string_array(fwnode, propname, NULL, 0);
 	if (nval < 0)
@@ -668,13 +668,9 @@ int fwnode_property_match_string(struct fwnode_handle *fwnode,
 	if (ret < 0)
 		goto out;
 
-	ret = -ENODATA;
-	for (i = 0; i < nval; i++) {
-		if (!strcmp(values[i], string)) {
-			ret = i;
-			break;
-		}
-	}
+	ret = match_string(values, nval, string);
+	if (ret < 0)
+		ret = -ENODATA;
 out:
 	kfree(values);
 	return ret;

drivers/block/aoe/aoecmd.c

@@ -875,7 +875,7 @@ bio_pageinc(struct bio *bio)
 		 * compound pages is no longer allowed by the kernel.
 		 */
 		page = compound_head(bv.bv_page);
-		atomic_inc(&page->_count);
+		page_ref_inc(page);
 	}
 }
 
@@ -888,7 +888,7 @@ bio_pagedec(struct bio *bio)
 
 	bio_for_each_segment(bv, bio, iter) {
 		page = compound_head(bv.bv_page);
-		atomic_dec(&page->_count);
+		page_ref_dec(page);
 	}
 }
 

drivers/firmware/broadcom/bcm47xx_nvram.c

@@ -94,15 +94,14 @@ static int nvram_find_and_copy(void __iomem *iobase, u32 lim)
 
 found:
 	__ioread32_copy(nvram_buf, header, sizeof(*header) / 4);
-	header = (struct nvram_header *)nvram_buf;
-	nvram_len = header->len;
+	nvram_len = ((struct nvram_header *)(nvram_buf))->len;
 	if (nvram_len > size) {
 		pr_err("The nvram size according to the header seems to be bigger than the partition on flash\n");
 		nvram_len = size;
 	}
 	if (nvram_len >= NVRAM_SPACE) {
 		pr_err("nvram on flash (%i bytes) is bigger than the reserved space in memory, will just copy the first %i bytes\n",
-		       header->len, NVRAM_SPACE - 1);
+		       nvram_len, NVRAM_SPACE - 1);
 		nvram_len = NVRAM_SPACE - 1;
 	}
 	/* proceed reading data after header */

drivers/gpu/drm/drm_edid_load.c

@@ -170,16 +170,11 @@ static void *edid_load(struct drm_connector *connector, const char *name,
 	int i, valid_extensions = 0;
 	bool print_bad_edid = !connector->bad_edid_counter || (drm_debug & DRM_UT_KMS);
 
-	builtin = 0;
-	for (i = 0; i < GENERIC_EDIDS; i++) {
-		if (strcmp(name, generic_edid_name[i]) == 0) {
-			fwdata = generic_edid[i];
-			fwsize = sizeof(generic_edid[i]);
-			builtin = 1;
-			break;
-		}
-	}
-	if (!builtin) {
+	builtin = match_string(generic_edid_name, GENERIC_EDIDS, name);
+	if (builtin >= 0) {
+		fwdata = generic_edid[builtin];
+		fwsize = sizeof(generic_edid[builtin]);
+	} else {
 		struct platform_device *pdev;
 		int err;
 
@@ -252,7 +247,7 @@ static void *edid_load(struct drm_connector *connector, const char *name,
 	}
 
 	DRM_INFO("Got %s EDID base block and %d extension%s from "
-	    "\"%s\" for connector \"%s\"\n", builtin ? "built-in" :
+	    "\"%s\" for connector \"%s\"\n", (builtin >= 0) ? "built-in" :
 	    "external", valid_extensions, valid_extensions == 1 ? "" : "s",
 	    name, connector_name);
 

drivers/ide/hpt366.c

@@ -531,14 +531,9 @@ static const struct hpt_info hpt371n = {
 	.timings	= &hpt37x_timings
 };
 
-static int check_in_drive_list(ide_drive_t *drive, const char **list)
+static bool check_in_drive_list(ide_drive_t *drive, const char **list)
 {
-	char *m = (char *)&drive->id[ATA_ID_PROD];
-
-	while (*list)
-		if (!strcmp(*list++, m))
-			return 1;
-	return 0;
+	return match_string(list, -1, (char *)&drive->id[ATA_ID_PROD]) >= 0;
 }
 
 static struct hpt_info *hpt3xx_get_info(struct device *dev)

drivers/net/ethernet/freescale/gianfar.c

@@ -2944,7 +2944,7 @@ static bool gfar_add_rx_frag(struct gfar_rx_buff *rxb, u32 lstatus,
 	/* change offset to the other half */
 	rxb->page_offset ^= GFAR_RXB_TRUESIZE;
 
-	atomic_inc(&page->_count);
+	page_ref_inc(page);
 
 	return true;
 }

drivers/net/ethernet/intel/fm10k/fm10k_main.c

@@ -243,7 +243,7 @@ static bool fm10k_can_reuse_rx_page(struct fm10k_rx_buffer *rx_buffer,
 	/* Even if we own the page, we are not allowed to use atomic_set()
 	 * This would break get_page_unless_zero() users.
 	 */
-	atomic_inc(&page->_count);
+	page_ref_inc(page);
 
 	return true;
 }

drivers/net/ethernet/intel/igb/igb_main.c

@@ -6630,7 +6630,7 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer,
 	/* Even if we own the page, we are not allowed to use atomic_set()
 	 * This would break get_page_unless_zero() users.
 	 */
-	atomic_inc(&page->_count);
+	page_ref_inc(page);
 
 	return true;
 }

drivers/net/ethernet/intel/ixgbe/ixgbe_main.c

@@ -1942,7 +1942,7 @@ static bool ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring,
 	/* Even if we own the page, we are not allowed to use atomic_set()
 	 * This would break get_page_unless_zero() users.
 	 */
-	atomic_inc(&page->_count);
+	page_ref_inc(page);
 
 	return true;
 }

drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c

@@ -837,7 +837,7 @@ add_tail_frag:
 	/* Even if we own the page, we are not allowed to use atomic_set()
 	 * This would break get_page_unless_zero() users.
 	 */
-	atomic_inc(&page->_count);
+	page_ref_inc(page);
 
 	return true;
 }

drivers/net/ethernet/mellanox/mlx4/en_rx.c

@@ -82,8 +82,7 @@ static int mlx4_alloc_pages(struct mlx4_en_priv *priv,
 	/* Not doing get_page() for each frag is a big win
 	 * on asymetric workloads. Note we can not use atomic_set().
 	 */
-	atomic_add(page_alloc->page_size / frag_info->frag_stride - 1,
-		   &page->_count);
+	page_ref_add(page, page_alloc->page_size / frag_info->frag_stride - 1);
 	return 0;
 }
 
@@ -127,7 +126,7 @@ out:
 			dma_unmap_page(priv->ddev, page_alloc[i].dma,
 				page_alloc[i].page_size, PCI_DMA_FROMDEVICE);
 			page = page_alloc[i].page;
-			atomic_set(&page->_count, 1);
+			set_page_count(page, 1);
 			put_page(page);
 		}
 	}
@@ -165,7 +164,7 @@ static int mlx4_en_init_allocator(struct mlx4_en_priv *priv,
 
 		en_dbg(DRV, priv, "  frag %d allocator: - size:%d frags:%d\n",
 		       i, ring->page_alloc[i].page_size,
-		       atomic_read(&ring->page_alloc[i].page->_count));
+		       page_ref_count(ring->page_alloc[i].page));
 	}
 	return 0;
 
@@ -177,7 +176,7 @@ out:
 		dma_unmap_page(priv->ddev, page_alloc->dma,
 			       page_alloc->page_size, PCI_DMA_FROMDEVICE);
 		page = page_alloc->page;
-		atomic_set(&page->_count, 1);
+		set_page_count(page, 1);
 		put_page(page);
 		page_alloc->page = NULL;
 	}

drivers/net/ethernet/sun/niu.c

@@ -3341,7 +3341,7 @@ static int niu_rbr_add_page(struct niu *np, struct rx_ring_info *rp,
 
 	niu_hash_page(rp, page, addr);
 	if (rp->rbr_blocks_per_page > 1)
-		atomic_add(rp->rbr_blocks_per_page - 1, &page->_count);
+		page_ref_add(page, rp->rbr_blocks_per_page - 1);
 
 	for (i = 0; i < rp->rbr_blocks_per_page; i++) {
 		__le32 *rbr = &rp->rbr[start_index + i];

drivers/net/wireless/marvell/mwifiex/debugfs.c

@@ -880,14 +880,12 @@ mwifiex_reset_write(struct file *file,
 {
 	struct mwifiex_private *priv = file->private_data;
 	struct mwifiex_adapter *adapter = priv->adapter;
-	char cmd;
 	bool result;
+	int rc;
 
-	if (copy_from_user(&cmd, ubuf, sizeof(cmd)))
-		return -EFAULT;
-
-	if (strtobool(&cmd, &result))
-		return -EINVAL;
+	rc = kstrtobool_from_user(ubuf, count, &result);
+	if (rc)
+		return rc;
 
 	if (!result)
 		return -EINVAL;

drivers/pinctrl/pinmux.c

@@ -334,7 +334,6 @@ int pinmux_map_to_setting(struct pinctrl_map const *map,
 	unsigned num_groups;
 	int ret;
 	const char *group;
-	int i;
 
 	if (!pmxops) {
 		dev_err(pctldev->dev, "does not support mux function\n");
@@ -363,19 +362,13 @@ int pinmux_map_to_setting(struct pinctrl_map const *map,
 		return -EINVAL;
 	}
 	if (map->data.mux.group) {
-		bool found = false;
 		group = map->data.mux.group;
-		for (i = 0; i < num_groups; i++) {
-			if (!strcmp(group, groups[i])) {
-				found = true;
-				break;
-			}
-		}
-		if (!found) {
+		ret = match_string(groups, num_groups, group);
+		if (ret < 0) {
 			dev_err(pctldev->dev,
 				"invalid group \"%s\" for function \"%s\"\n",
 				group, map->data.mux.function);
-			return -EINVAL;
+			return ret;
 		}
 	} else {
 		group = groups[0];

drivers/power/ab8500_btemp.c

@@ -906,26 +906,21 @@ static int ab8500_btemp_get_property(struct power_supply *psy,
 static int ab8500_btemp_get_ext_psy_data(struct device *dev, void *data)
 {
 	struct power_supply *psy;
-	struct power_supply *ext;
+	struct power_supply *ext = dev_get_drvdata(dev);
+	const char **supplicants = (const char **)ext->supplied_to;
 	struct ab8500_btemp *di;
 	union power_supply_propval ret;
-	int i, j;
-	bool psy_found = false;
+	int j;
 
 	psy = (struct power_supply *)data;
-	ext = dev_get_drvdata(dev);
 	di = power_supply_get_drvdata(psy);
 
 	/*
 	 * For all psy where the name of your driver
 	 * appears in any supplied_to
 	 */
-	for (i = 0; i < ext->num_supplicants; i++) {
-		if (!strcmp(ext->supplied_to[i], psy->desc->name))
-			psy_found = true;
-	}
-
-	if (!psy_found)
+	j = match_string(supplicants, ext->num_supplicants, psy->desc->name);
+	if (j < 0)
 		return 0;
 
 	/* Go through all properties for the psy */

drivers/power/ab8500_charger.c

@@ -1929,11 +1929,11 @@ static int ab8540_charger_usb_pre_chg_enable(struct ux500_charger *charger,
 static int ab8500_charger_get_ext_psy_data(struct device *dev, void *data)
 {
 	struct power_supply *psy;
-	struct power_supply *ext;
+	struct power_supply *ext = dev_get_drvdata(dev);
+	const char **supplicants = (const char **)ext->supplied_to;
 	struct ab8500_charger *di;
 	union power_supply_propval ret;
-	int i, j;
-	bool psy_found = false;
+	int j;
 	struct ux500_charger *usb_chg;
 
 	usb_chg = (struct ux500_charger *)data;
@@ -1941,15 +1941,9 @@ static int ab8500_charger_get_ext_psy_data(struct device *dev, void *data)
 
 	di = to_ab8500_charger_usb_device_info(usb_chg);
 
-	ext = dev_get_drvdata(dev);
-
 	/* For all psy where the driver name appears in any supplied_to */
-	for (i = 0; i < ext->num_supplicants; i++) {
-		if (!strcmp(ext->supplied_to[i], psy->desc->name))
-			psy_found = true;
-	}
-
-	if (!psy_found)
+	j = match_string(supplicants, ext->num_supplicants, psy->desc->name);
+	if (j < 0)
 		return 0;
 
 	/* Go through all properties for the psy */

drivers/power/ab8500_fg.c

@@ -2168,26 +2168,21 @@ static int ab8500_fg_get_property(struct power_supply *psy,
 static int ab8500_fg_get_ext_psy_data(struct device *dev, void *data)
 {
 	struct power_supply *psy;
-	struct power_supply *ext;
+	struct power_supply *ext = dev_get_drvdata(dev);
+	const char **supplicants = (const char **)ext->supplied_to;
 	struct ab8500_fg *di;
 	union power_supply_propval ret;
-	int i, j;
-	bool psy_found = false;
+	int j;
 
 	psy = (struct power_supply *)data;
-	ext = dev_get_drvdata(dev);
 	di = power_supply_get_drvdata(psy);
 
 	/*
 	 * For all psy where the name of your driver
 	 * appears in any supplied_to
 	 */
-	for (i = 0; i < ext->num_supplicants; i++) {
-		if (!strcmp(ext->supplied_to[i], psy->desc->name))
-			psy_found = true;
-	}
-
-	if (!psy_found)
+	j = match_string(supplicants, ext->num_supplicants, psy->desc->name);
+	if (j < 0)
 		return 0;
 
 	/* Go through all properties for the psy */

drivers/power/abx500_chargalg.c

@@ -975,22 +975,18 @@ static void handle_maxim_chg_curr(struct abx500_chargalg *di)
 static int abx500_chargalg_get_ext_psy_data(struct device *dev, void *data)
 {
 	struct power_supply *psy;
-	struct power_supply *ext;
+	struct power_supply *ext = dev_get_drvdata(dev);
+	const char **supplicants = (const char **)ext->supplied_to;
 	struct abx500_chargalg *di;
 	union power_supply_propval ret;
-	int i, j;
-	bool psy_found = false;
+	int j;
 	bool capacity_updated = false;
 
 	psy = (struct power_supply *)data;
-	ext = dev_get_drvdata(dev);
 	di = power_supply_get_drvdata(psy);
 	/* For all psy where the driver name appears in any supplied_to */
-	for (i = 0; i < ext->num_supplicants; i++) {
-		if (!strcmp(ext->supplied_to[i], psy->desc->name))
-			psy_found = true;
-	}
-	if (!psy_found)
+	j = match_string(supplicants, ext->num_supplicants, psy->desc->name);
+	if (j < 0)
 		return 0;
 
 	/*

drivers/power/charger-manager.c

@@ -2019,27 +2019,6 @@ static void __exit charger_manager_cleanup(void)
 }
 module_exit(charger_manager_cleanup);
 
-/**
- * find_power_supply - find the associated power_supply of charger
- * @cm: the Charger Manager representing the battery
- * @psy: pointer to instance of charger's power_supply
- */
-static bool find_power_supply(struct charger_manager *cm,
-			struct power_supply *psy)
-{
-	int i;
-	bool found = false;
-
-	for (i = 0; cm->desc->psy_charger_stat[i]; i++) {
-		if (!strcmp(psy->desc->name, cm->desc->psy_charger_stat[i])) {
-			found = true;
-			break;
-		}
-	}
-
-	return found;
-}
-
 /**
  * cm_notify_event - charger driver notify Charger Manager of charger event
  * @psy: pointer to instance of charger's power_supply
@@ -2057,9 +2036,11 @@ void cm_notify_event(struct power_supply *psy, enum cm_event_types type,
 
 	mutex_lock(&cm_list_mtx);
 	list_for_each_entry(cm, &cm_list, entry) {
-		found_power_supply = find_power_supply(cm, psy);
-		if (found_power_supply)
+		if (match_string(cm->desc->psy_charger_stat, -1,
+				 psy->desc->name) >= 0) {
+			found_power_supply = true;
 			break;
+		}
 	}
 	mutex_unlock(&cm_list_mtx);
 

drivers/usb/common/common.c

@@ -65,18 +65,15 @@ EXPORT_SYMBOL_GPL(usb_speed_string);
 enum usb_device_speed usb_get_maximum_speed(struct device *dev)
 {
 	const char *maximum_speed;
-	int err;
-	int i;
+	int ret;
 
-	err = device_property_read_string(dev, "maximum-speed", &maximum_speed);
-	if (err < 0)
+	ret = device_property_read_string(dev, "maximum-speed", &maximum_speed);
+	if (ret < 0)
 		return USB_SPEED_UNKNOWN;
 
-	for (i = 0; i < ARRAY_SIZE(speed_names); i++)
-		if (strcmp(maximum_speed, speed_names[i]) == 0)
-			return i;
+	ret = match_string(speed_names, ARRAY_SIZE(speed_names), maximum_speed);
 
-	return USB_SPEED_UNKNOWN;
+	return (ret < 0) ? USB_SPEED_UNKNOWN : ret;
 }
 EXPORT_SYMBOL_GPL(usb_get_maximum_speed);
 
@@ -110,13 +107,10 @@ static const char *const usb_dr_modes[] = {
 
 static enum usb_dr_mode usb_get_dr_mode_from_string(const char *str)
 {
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(usb_dr_modes); i++)
-		if (!strcmp(usb_dr_modes[i], str))
-			return i;
+	int ret;
 
-	return USB_DR_MODE_UNKNOWN;
+	ret = match_string(usb_dr_modes, ARRAY_SIZE(usb_dr_modes), str);
+	return (ret < 0) ? USB_DR_MODE_UNKNOWN : ret;
 }
 
 enum usb_dr_mode usb_get_dr_mode(struct device *dev)

drivers/virtio/virtio_balloon.c

@@ -30,6 +30,7 @@
 #include <linux/balloon_compaction.h>
 #include <linux/oom.h>
 #include <linux/wait.h>
+#include <linux/mm.h>
 
 /*
  * Balloon device works in 4K page units.  So each page is pointed to by
@@ -229,10 +230,13 @@ static void update_balloon_stats(struct virtio_balloon *vb)
 	unsigned long events[NR_VM_EVENT_ITEMS];
 	struct sysinfo i;
 	int idx = 0;
+	long available;
 
 	all_vm_events(events);
 	si_meminfo(&i);
 
+	available = si_mem_available();
+
 	update_stat(vb, idx++, VIRTIO_BALLOON_S_SWAP_IN,
 				pages_to_bytes(events[PSWPIN]));
 	update_stat(vb, idx++, VIRTIO_BALLOON_S_SWAP_OUT,
@@ -243,6 +247,8 @@ static void update_balloon_stats(struct virtio_balloon *vb)
 				pages_to_bytes(i.freeram));
 	update_stat(vb, idx++, VIRTIO_BALLOON_S_MEMTOT,
 				pages_to_bytes(i.totalram));
+	update_stat(vb, idx++, VIRTIO_BALLOON_S_AVAIL,
+				pages_to_bytes(available));
 }
 
 /*

fs/btrfs/tests/btrfs-tests.c

@@ -137,7 +137,6 @@ static void btrfs_free_dummy_fs_info(struct btrfs_fs_info *fs_info)
 	void **slot;
 
 	spin_lock(&fs_info->buffer_lock);
-restart:
 	radix_tree_for_each_slot(slot, &fs_info->buffer_radix, &iter, 0) {
 		struct extent_buffer *eb;
 
@@ -147,7 +146,7 @@ restart:
 		/* Shouldn't happen but that kind of thinking creates CVE's */
 		if (radix_tree_exception(eb)) {
 			if (radix_tree_deref_retry(eb))
-				goto restart;
+				slot = radix_tree_iter_retry(&iter);
 			continue;
 		}
 		spin_unlock(&fs_info->buffer_lock);

fs/cifs/cifs_debug.c

@@ -255,7 +255,6 @@ static const struct file_operations cifs_debug_data_proc_fops = {
 static ssize_t cifs_stats_proc_write(struct file *file,
 		const char __user *buffer, size_t count, loff_t *ppos)
 {
-	char c;
 	bool bv;
 	int rc;
 	struct list_head *tmp1, *tmp2, *tmp3;
@@ -263,11 +262,8 @@ static ssize_t cifs_stats_proc_write(struct file *file,
 	struct cifs_ses *ses;
 	struct cifs_tcon *tcon;
 
-	rc = get_user(c, buffer);
-	if (rc)
-		return rc;
-
-	if (strtobool(&c, &bv) == 0) {
+	rc = kstrtobool_from_user(buffer, count, &bv);
+	if (rc == 0) {
 #ifdef CONFIG_CIFS_STATS2
 		atomic_set(&totBufAllocCount, 0);
 		atomic_set(&totSmBufAllocCount, 0);
@@ -290,6 +286,8 @@ static ssize_t cifs_stats_proc_write(struct file *file,
 			}
 		}
 		spin_unlock(&cifs_tcp_ses_lock);
+	} else {
+		return rc;
 	}
 
 	return count;
@@ -433,17 +431,17 @@ static int cifsFYI_proc_open(struct inode *inode, struct file *file)
 static ssize_t cifsFYI_proc_write(struct file *file, const char __user *buffer,
 		size_t count, loff_t *ppos)
 {
-	char c;
+	char c[2] = { '\0' };
 	bool bv;
 	int rc;
 
-	rc = get_user(c, buffer);
+	rc = get_user(c[0], buffer);
 	if (rc)
 		return rc;
-	if (strtobool(&c, &bv) == 0)
+	if (strtobool(c, &bv) == 0)
 		cifsFYI = bv;
-	else if ((c > '1') && (c <= '9'))
-		cifsFYI = (int) (c - '0'); /* see cifs_debug.h for meanings */
+	else if ((c[0] > '1') && (c[0] <= '9'))
+		cifsFYI = (int) (c[0] - '0'); /* see cifs_debug.h for meanings */
 
 	return count;
 }
@@ -471,20 +469,12 @@ static int cifs_linux_ext_proc_open(struct inode *inode, struct file *file)
 static ssize_t cifs_linux_ext_proc_write(struct file *file,
 		const char __user *buffer, size_t count, loff_t *ppos)
 {
-	char c;
-	bool bv;
 	int rc;
 
-	rc = get_user(c, buffer);
+	rc = kstrtobool_from_user(buffer, count, &linuxExtEnabled);
 	if (rc)
 		return rc;
 
-	rc = strtobool(&c, &bv);
-	if (rc)
-		return rc;
-
-	linuxExtEnabled = bv;
-
 	return count;
 }
 
@@ -511,20 +501,12 @@ static int cifs_lookup_cache_proc_open(struct inode *inode, struct file *file)
 static ssize_t cifs_lookup_cache_proc_write(struct file *file,
 		const char __user *buffer, size_t count, loff_t *ppos)
 {
-	char c;
-	bool bv;
 	int rc;
 
-	rc = get_user(c, buffer);
+	rc = kstrtobool_from_user(buffer, count, &lookupCacheEnabled);
 	if (rc)
 		return rc;
 
-	rc = strtobool(&c, &bv);
-	if (rc)
-		return rc;
-
-	lookupCacheEnabled = bv;
-
 	return count;
 }
 
@@ -551,20 +533,12 @@ static int traceSMB_proc_open(struct inode *inode, struct file *file)
 static ssize_t traceSMB_proc_write(struct file *file, const char __user *buffer,
 		size_t count, loff_t *ppos)
 {
-	char c;
-	bool bv;
 	int rc;
 
-	rc = get_user(c, buffer);
+	rc = kstrtobool_from_user(buffer, count, &traceSMB);
 	if (rc)
 		return rc;
 
-	rc = strtobool(&c, &bv);
-	if (rc)
-		return rc;
-
-	traceSMB = bv;
-
 	return count;
 }
 
@@ -622,7 +596,6 @@ static ssize_t cifs_security_flags_proc_write(struct file *file,
 	int rc;
 	unsigned int flags;
 	char flags_string[12];
-	char c;
 	bool bv;
 
 	if ((count < 1) || (count > 11))
@@ -635,11 +608,10 @@ static ssize_t cifs_security_flags_proc_write(struct file *file,
 
 	if (count < 3) {
 		/* single char or single char followed by null */
-		c = flags_string[0];
-		if (strtobool(&c, &bv) == 0) {
+		if (strtobool(flags_string, &bv) == 0) {
 			global_secflags = bv ? CIFSSEC_MAX : CIFSSEC_DEF;
 			return count;
-		} else if (!isdigit(c)) {
+		} else if (!isdigit(flags_string[0])) {
 			cifs_dbg(VFS, "Invalid SecurityFlags: %s\n",
 					flags_string);
 			return -EINVAL;

fs/cifs/cifs_debug.h

@@ -25,7 +25,7 @@
 void cifs_dump_mem(char *label, void *data, int length);
 void cifs_dump_detail(void *);
 void cifs_dump_mids(struct TCP_Server_Info *);
-extern int traceSMB;		/* flag which enables the function below */
+extern bool traceSMB;		/* flag which enables the function below */
 void dump_smb(void *, int);
 #define CIFS_INFO	0x01
 #define CIFS_RC		0x02

fs/cifs/cifsfs.c

@@ -54,10 +54,10 @@
 #endif
 
 int cifsFYI = 0;
-int traceSMB = 0;
+bool traceSMB;
 bool enable_oplocks = true;
-unsigned int linuxExtEnabled = 1;
-unsigned int lookupCacheEnabled = 1;
+bool linuxExtEnabled = true;
+bool lookupCacheEnabled = true;
 unsigned int global_secflags = CIFSSEC_DEF;
 /* unsigned int ntlmv2_support = 0; */
 unsigned int sign_CIFS_PDUs = 1;

fs/cifs/cifsglob.h

@@ -1596,11 +1596,11 @@ GLOBAL_EXTERN atomic_t midCount;
 
 /* Misc globals */
 GLOBAL_EXTERN bool enable_oplocks; /* enable or disable oplocks */
-GLOBAL_EXTERN unsigned int lookupCacheEnabled;
+GLOBAL_EXTERN bool lookupCacheEnabled;
 GLOBAL_EXTERN unsigned int global_secflags;	/* if on, session setup sent
 				with more secure ntlmssp2 challenge/resp */
 GLOBAL_EXTERN unsigned int sign_CIFS_PDUs;  /* enable smb packet signing */
-GLOBAL_EXTERN unsigned int linuxExtEnabled;/*enable Linux/Unix CIFS extensions*/
+GLOBAL_EXTERN bool linuxExtEnabled;/*enable Linux/Unix CIFS extensions*/
 GLOBAL_EXTERN unsigned int CIFSMaxBufSize;  /* max size not including hdr */
 GLOBAL_EXTERN unsigned int cifs_min_rcv;    /* min size of big ntwrk buf pool */
 GLOBAL_EXTERN unsigned int cifs_min_small;  /* min size of small buf pool */

fs/eventpoll.c

@@ -1616,7 +1616,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 {
 	int res = 0, eavail, timed_out = 0;
 	unsigned long flags;
-	long slack = 0;
+	u64 slack = 0;
 	wait_queue_t wait;
 	ktime_t expires, *to = NULL;
 

fs/nilfs2/page.c

@@ -180,7 +180,7 @@ void nilfs_page_bug(struct page *page)
 
 	printk(KERN_CRIT "NILFS_PAGE_BUG(%p): cnt=%d index#=%llu flags=0x%lx "
 	       "mapping=%p ino=%lu\n",
-	       page, atomic_read(&page->_count),
+	       page, page_ref_count(page),
 	       (unsigned long long)page->index, page->flags, m, ino);
 
 	if (page_has_buffers(page)) {

fs/proc/base.c

@@ -434,7 +434,7 @@ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns,
 			&& !lookup_symbol_name(wchan, symname))
 		seq_printf(m, "%s", symname);
 	else
-		seq_putc(m, '0');
+		seq_puts(m, "0\n");
 
 	return 0;
 }
@@ -2158,6 +2158,7 @@ static const struct file_operations proc_map_files_operations = {
 	.llseek		= default_llseek,
 };
 
+#ifdef CONFIG_CHECKPOINT_RESTORE
 struct timers_private {
 	struct pid *pid;
 	struct task_struct *task;
@@ -2256,6 +2257,73 @@ static const struct file_operations proc_timers_operations = {
 	.llseek		= seq_lseek,
 	.release	= seq_release_private,
 };
+#endif
+
+static ssize_t timerslack_ns_write(struct file *file, const char __user *buf,
+					size_t count, loff_t *offset)
+{
+	struct inode *inode = file_inode(file);
+	struct task_struct *p;
+	u64 slack_ns;
+	int err;
+
+	err = kstrtoull_from_user(buf, count, 10, &slack_ns);
+	if (err < 0)
+		return err;
+
+	p = get_proc_task(inode);
+	if (!p)
+		return -ESRCH;
+
+	if (ptrace_may_access(p, PTRACE_MODE_ATTACH_FSCREDS)) {
+		task_lock(p);
+		if (slack_ns == 0)
+			p->timer_slack_ns = p->default_timer_slack_ns;
+		else
+			p->timer_slack_ns = slack_ns;
+		task_unlock(p);
+	} else
+		count = -EPERM;
+
+	put_task_struct(p);
+
+	return count;
+}
+
+static int timerslack_ns_show(struct seq_file *m, void *v)
+{
+	struct inode *inode = m->private;
+	struct task_struct *p;
+	int err =  0;
+
+	p = get_proc_task(inode);
+	if (!p)
+		return -ESRCH;
+
+	if (ptrace_may_access(p, PTRACE_MODE_ATTACH_FSCREDS)) {
+		task_lock(p);
+		seq_printf(m, "%llu\n", p->timer_slack_ns);
+		task_unlock(p);
+	} else
+		err = -EPERM;
+
+	put_task_struct(p);
+
+	return err;
+}
+
+static int timerslack_ns_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, timerslack_ns_show, inode);
+}
+
+static const struct file_operations proc_pid_set_timerslack_ns_operations = {
+	.open		= timerslack_ns_open,
+	.read		= seq_read,
+	.write		= timerslack_ns_write,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
 
 static int proc_pident_instantiate(struct inode *dir,
 	struct dentry *dentry, struct task_struct *task, const void *ptr)
@@ -2831,6 +2899,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 #ifdef CONFIG_CHECKPOINT_RESTORE
 	REG("timers",	  S_IRUGO, proc_timers_operations),
 #endif
+	REG("timerslack_ns", S_IRUGO|S_IWUGO, proc_pid_set_timerslack_ns_operations),
 };
 
 static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx)

fs/proc/meminfo.c

@@ -29,10 +29,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 	unsigned long committed;
 	long cached;
 	long available;
-	unsigned long pagecache;
-	unsigned long wmark_low = 0;
 	unsigned long pages[NR_LRU_LISTS];
-	struct zone *zone;
 	int lru;
 
 /*
@@ -51,33 +48,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 	for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
 		pages[lru] = global_page_state(NR_LRU_BASE + lru);
 
-	for_each_zone(zone)
-		wmark_low += zone->watermark[WMARK_LOW];
-
-	/*
-	 * Estimate the amount of memory available for userspace allocations,
-	 * without causing swapping.
-	 */
-	available = i.freeram - totalreserve_pages;
-
-	/*
-	 * Not all the page cache can be freed, otherwise the system will
-	 * start swapping. Assume at least half of the page cache, or the
-	 * low watermark worth of cache, needs to stay.
-	 */
-	pagecache = pages[LRU_ACTIVE_FILE] + pages[LRU_INACTIVE_FILE];
-	pagecache -= min(pagecache / 2, wmark_low);
-	available += pagecache;
-
-	/*
-	 * Part of the reclaimable slab consists of items that are in use,
-	 * and cannot be freed. Cap this estimate at the low watermark.
-	 */
-	available += global_page_state(NR_SLAB_RECLAIMABLE) -
-		     min(global_page_state(NR_SLAB_RECLAIMABLE) / 2, wmark_low);
-
-	if (available < 0)
-		available = 0;
+	available = si_mem_available();
 
 	/*
 	 * Tagged format, for easy grepping and expansion.

fs/proc/page.c

@@ -103,9 +103,9 @@ u64 stable_page_flags(struct page *page)
 	 * pseudo flags for the well known (anonymous) memory mapped pages
 	 *
 	 * Note that page->_mapcount is overloaded in SLOB/SLUB/SLQB, so the
-	 * simple test in page_mapcount() is not enough.
+	 * simple test in page_mapped() is not enough.
 	 */
-	if (!PageSlab(page) && page_mapcount(page))
+	if (!PageSlab(page) && page_mapped(page))
 		u |= 1 << KPF_MMAP;
 	if (PageAnon(page))
 		u |= 1 << KPF_ANON;
@@ -148,6 +148,8 @@ u64 stable_page_flags(struct page *page)
 	 */
 	if (PageBuddy(page))
 		u |= 1 << KPF_BUDDY;
+	else if (page_count(page) == 0 && is_free_buddy_page(page))
+		u |= 1 << KPF_BUDDY;
 
 	if (PageBalloon(page))
 		u |= 1 << KPF_BALLOON;
@@ -158,6 +160,8 @@ u64 stable_page_flags(struct page *page)
 	u |= kpf_copy_bit(k, KPF_LOCKED,	PG_locked);
 
 	u |= kpf_copy_bit(k, KPF_SLAB,		PG_slab);
+	if (PageTail(page) && PageSlab(compound_head(page)))
+		u |= 1 << KPF_SLAB;
 
 	u |= kpf_copy_bit(k, KPF_ERROR,		PG_error);
 	u |= kpf_copy_bit(k, KPF_DIRTY,		PG_dirty);

fs/proc/vmcore.c

@@ -231,7 +231,9 @@ static ssize_t __read_vmcore(char *buffer, size_t buflen, loff_t *fpos,
 
 	list_for_each_entry(m, &vmcore_list, list) {
 		if (*fpos < m->offset + m->size) {
-			tsz = min_t(size_t, m->offset + m->size - *fpos, buflen);
+			tsz = (size_t)min_t(unsigned long long,
+					    m->offset + m->size - *fpos,
+					    buflen);
 			start = m->paddr + *fpos - m->offset;
 			tmp = read_from_oldmem(buffer, tsz, &start, userbuf);
 			if (tmp < 0)
@@ -461,7 +463,8 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
 		if (start < m->offset + m->size) {
 			u64 paddr = 0;
 
-			tsz = min_t(size_t, m->offset + m->size - start, size);
+			tsz = (size_t)min_t(unsigned long long,
+					    m->offset + m->size - start, size);
 			paddr = m->paddr + start - m->offset;
 			if (vmcore_remap_oldmem_pfn(vma, vma->vm_start + len,
 						    paddr >> PAGE_SHIFT, tsz,

fs/select.c

@@ -70,9 +70,9 @@ static long __estimate_accuracy(struct timespec *tv)
 	return slack;
 }
 
-long select_estimate_accuracy(struct timespec *tv)
+u64 select_estimate_accuracy(struct timespec *tv)
 {
-	unsigned long ret;
+	u64 ret;
 	struct timespec now;
 
 	/*
@@ -402,7 +402,7 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
 	struct poll_wqueues table;
 	poll_table *wait;
 	int retval, i, timed_out = 0;
-	unsigned long slack = 0;
+	u64 slack = 0;
 	unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0;
 	unsigned long busy_end = 0;
 
@@ -784,7 +784,7 @@ static int do_poll(struct poll_list *list, struct poll_wqueues *wait,
 	poll_table* pt = &wait->pt;
 	ktime_t expire, *to = NULL;
 	int timed_out = 0, count = 0;
-	unsigned long slack = 0;
+	u64 slack = 0;
 	unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0;
 	unsigned long busy_end = 0;
 

include/asm-generic/atomic-long.h

@@ -98,14 +98,14 @@ ATOMIC_LONG_ADD_SUB_OP(sub, _release)
 #define atomic_long_xchg(v, new) \
 	(ATOMIC_LONG_PFX(_xchg)((ATOMIC_LONG_PFX(_t) *)(v), (new)))
 
-static inline void atomic_long_inc(atomic_long_t *l)
+static __always_inline void atomic_long_inc(atomic_long_t *l)
 {
 	ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l;
 
 	ATOMIC_LONG_PFX(_inc)(v);
 }
 
-static inline void atomic_long_dec(atomic_long_t *l)
+static __always_inline void atomic_long_dec(atomic_long_t *l)
 {
 	ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l;
 
@@ -113,7 +113,7 @@ static inline void atomic_long_dec(atomic_long_t *l)
 }
 
 #define ATOMIC_LONG_OP(op)						\
-static inline void							\
+static __always_inline void						\
 atomic_long_##op(long i, atomic_long_t *l)				\
 {									\
 	ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l;		\

include/asm-generic/bug.h

@@ -81,6 +81,12 @@ extern void warn_slowpath_null(const char *file, const int line);
 	do { printk(arg); __WARN_TAINT(taint); } while (0)
 #endif
 
+/* used internally by panic.c */
+struct warn_args;
+
+void __warn(const char *file, int line, void *caller, unsigned taint,
+	    struct pt_regs *regs, struct warn_args *args);
+
 #ifndef WARN_ON
 #define WARN_ON(condition) ({						\
 	int __ret_warn_on = !!(condition);				\
@@ -110,9 +116,10 @@ extern void warn_slowpath_null(const char *file, const int line);
 	static bool __section(.data.unlikely) __warned;		\
 	int __ret_warn_once = !!(condition);			\
 								\
-	if (unlikely(__ret_warn_once))				\
-		if (WARN_ON(!__warned)) 			\
-			__warned = true;			\
+	if (unlikely(__ret_warn_once && !__warned)) {		\
+		__warned = true;				\
+		WARN_ON(1);					\
+	}							\
 	unlikely(__ret_warn_once);				\
 })
 
@@ -120,9 +127,10 @@ extern void warn_slowpath_null(const char *file, const int line);
 	static bool __section(.data.unlikely) __warned;		\
 	int __ret_warn_once = !!(condition);			\
 								\
-	if (unlikely(__ret_warn_once))				\
-		if (WARN(!__warned, format)) 			\
-			__warned = true;			\
+	if (unlikely(__ret_warn_once && !__warned)) {		\
+		__warned = true;				\
+		WARN(1, format);				\
+	}							\
 	unlikely(__ret_warn_once);				\
 })
 
@@ -130,9 +138,10 @@ extern void warn_slowpath_null(const char *file, const int line);
 	static bool __section(.data.unlikely) __warned;		\
 	int __ret_warn_once = !!(condition);			\
 								\
-	if (unlikely(__ret_warn_once))				\
-		if (WARN_TAINT(!__warned, taint, format))	\
-			__warned = true;			\
+	if (unlikely(__ret_warn_once && !__warned)) {		\
+		__warned = true;				\
+		WARN_TAINT(1, taint, format);			\
+	}							\
 	unlikely(__ret_warn_once);				\
 })
 

include/asm-generic/pgtable.h

@@ -783,6 +783,23 @@ static inline int pmd_clear_huge(pmd_t *pmd)
 }
 #endif	/* CONFIG_HAVE_ARCH_HUGE_VMAP */
 
+#ifndef __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+/*
+ * ARCHes with special requirements for evicting THP backing TLB entries can
+ * implement this. Otherwise also, it can help optimize normal TLB flush in
+ * THP regime. stock flush_tlb_range() typically has optimization to nuke the
+ * entire TLB TLB if flush span is greater than a threshold, which will
+ * likely be true for a single huge page. Thus a single thp flush will
+ * invalidate the entire TLB which is not desitable.
+ * e.g. see arch/arc: flush_pmd_tlb_range
+ */
+#define flush_pmd_tlb_range(vma, addr, end)	flush_tlb_range(vma, addr, end)
+#else
+#define flush_pmd_tlb_range(vma, addr, end)	BUILD_BUG()
+#endif
+#endif
+
 #endif /* !__ASSEMBLY__ */
 
 #ifndef io_remap_pfn_range

include/linux/buffer_head.h

@@ -82,15 +82,15 @@ struct buffer_head {
  * and buffer_foo() functions.
  */
 #define BUFFER_FNS(bit, name)						\
-static inline void set_buffer_##name(struct buffer_head *bh)		\
+static __always_inline void set_buffer_##name(struct buffer_head *bh)	\
 {									\
 	set_bit(BH_##bit, &(bh)->b_state);				\
 }									\
-static inline void clear_buffer_##name(struct buffer_head *bh)		\
+static __always_inline void clear_buffer_##name(struct buffer_head *bh)	\
 {									\
 	clear_bit(BH_##bit, &(bh)->b_state);				\
 }									\
-static inline int buffer_##name(const struct buffer_head *bh)		\
+static __always_inline int buffer_##name(const struct buffer_head *bh)	\
 {									\
 	return test_bit(BH_##bit, &(bh)->b_state);			\
 }
@@ -99,11 +99,11 @@ static inline int buffer_##name(const struct buffer_head *bh)		\
  * test_set_buffer_foo() and test_clear_buffer_foo()
  */
 #define TAS_BUFFER_FNS(bit, name)					\
-static inline int test_set_buffer_##name(struct buffer_head *bh)	\
+static __always_inline int test_set_buffer_##name(struct buffer_head *bh) \
 {									\
 	return test_and_set_bit(BH_##bit, &(bh)->b_state);		\
 }									\
-static inline int test_clear_buffer_##name(struct buffer_head *bh)	\
+static __always_inline int test_clear_buffer_##name(struct buffer_head *bh) \
 {									\
 	return test_and_clear_bit(BH_##bit, &(bh)->b_state);		\
 }									\

include/linux/compaction.h

@@ -52,6 +52,10 @@ extern void compaction_defer_reset(struct zone *zone, int order,
 				bool alloc_success);
 extern bool compaction_restarting(struct zone *zone, int order);
 
+extern int kcompactd_run(int nid);
+extern void kcompactd_stop(int nid);
+extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx);
+
 #else
 static inline unsigned long try_to_compact_pages(gfp_t gfp_mask,
 			unsigned int order, int alloc_flags,
@@ -84,6 +88,18 @@ static inline bool compaction_deferred(struct zone *zone, int order)
 	return true;
 }
 
+static inline int kcompactd_run(int nid)
+{
+	return 0;
+}
+static inline void kcompactd_stop(int nid)
+{
+}
+
+static inline void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx)
+{
+}
+
 #endif /* CONFIG_COMPACTION */
 
 #if defined(CONFIG_COMPACTION) && defined(CONFIG_SYSFS) && defined(CONFIG_NUMA)

include/linux/freezer.h

@@ -231,7 +231,7 @@ static inline long freezable_schedule_timeout_killable_unsafe(long timeout)
  * call this with locks held.
  */
 static inline int freezable_schedule_hrtimeout_range(ktime_t *expires,
-		unsigned long delta, const enum hrtimer_mode mode)
+		u64 delta, const enum hrtimer_mode mode)
 {
 	int __retval;
 	freezer_do_not_count();

include/linux/gfp.h

@@ -105,8 +105,6 @@ struct vm_area_struct;
  *
  * __GFP_NOMEMALLOC is used to explicitly forbid access to emergency reserves.
  *   This takes precedence over the __GFP_MEMALLOC flag if both are set.
- *
- * __GFP_NOACCOUNT ignores the accounting for kmemcg limit enforcement.
  */
 #define __GFP_ATOMIC	((__force gfp_t)___GFP_ATOMIC)
 #define __GFP_HIGH	((__force gfp_t)___GFP_HIGH)
@@ -259,7 +257,7 @@ struct vm_area_struct;
 #define GFP_HIGHUSER_MOVABLE	(GFP_HIGHUSER | __GFP_MOVABLE)
 #define GFP_TRANSHUGE	((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \
 			 __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN) & \
-			 ~__GFP_KSWAPD_RECLAIM)
+			 ~__GFP_RECLAIM)
 
 /* Convert GFP flags to their corresponding migrate type */
 #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE)
@@ -333,22 +331,29 @@ static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags)
  *       0xe    => BAD (MOVABLE+DMA32+HIGHMEM)
  *       0xf    => BAD (MOVABLE+DMA32+HIGHMEM+DMA)
  *
- * ZONES_SHIFT must be <= 2 on 32 bit platforms.
+ * GFP_ZONES_SHIFT must be <= 2 on 32 bit platforms.
  */
 
-#if 16 * ZONES_SHIFT > BITS_PER_LONG
-#error ZONES_SHIFT too large to create GFP_ZONE_TABLE integer
+#if defined(CONFIG_ZONE_DEVICE) && (MAX_NR_ZONES-1) <= 4
+/* ZONE_DEVICE is not a valid GFP zone specifier */
+#define GFP_ZONES_SHIFT 2
+#else
+#define GFP_ZONES_SHIFT ZONES_SHIFT
+#endif
+
+#if 16 * GFP_ZONES_SHIFT > BITS_PER_LONG
+#error GFP_ZONES_SHIFT too large to create GFP_ZONE_TABLE integer
 #endif
 
 #define GFP_ZONE_TABLE ( \
-	(ZONE_NORMAL << 0 * ZONES_SHIFT)				      \
-	| (OPT_ZONE_DMA << ___GFP_DMA * ZONES_SHIFT)			      \
-	| (OPT_ZONE_HIGHMEM << ___GFP_HIGHMEM * ZONES_SHIFT)		      \
-	| (OPT_ZONE_DMA32 << ___GFP_DMA32 * ZONES_SHIFT)		      \
-	| (ZONE_NORMAL << ___GFP_MOVABLE * ZONES_SHIFT)			      \
-	| (OPT_ZONE_DMA << (___GFP_MOVABLE | ___GFP_DMA) * ZONES_SHIFT)	      \
-	| (ZONE_MOVABLE << (___GFP_MOVABLE | ___GFP_HIGHMEM) * ZONES_SHIFT)   \
-	| (OPT_ZONE_DMA32 << (___GFP_MOVABLE | ___GFP_DMA32) * ZONES_SHIFT)   \
+	(ZONE_NORMAL << 0 * GFP_ZONES_SHIFT)				       \
+	| (OPT_ZONE_DMA << ___GFP_DMA * GFP_ZONES_SHIFT)		       \
+	| (OPT_ZONE_HIGHMEM << ___GFP_HIGHMEM * GFP_ZONES_SHIFT)	       \
+	| (OPT_ZONE_DMA32 << ___GFP_DMA32 * GFP_ZONES_SHIFT)		       \
+	| (ZONE_NORMAL << ___GFP_MOVABLE * GFP_ZONES_SHIFT)		       \
+	| (OPT_ZONE_DMA << (___GFP_MOVABLE | ___GFP_DMA) * GFP_ZONES_SHIFT)    \
+	| (ZONE_MOVABLE << (___GFP_MOVABLE | ___GFP_HIGHMEM) * GFP_ZONES_SHIFT)\
+	| (OPT_ZONE_DMA32 << (___GFP_MOVABLE | ___GFP_DMA32) * GFP_ZONES_SHIFT)\
 )
 
 /*
@@ -373,8 +378,8 @@ static inline enum zone_type gfp_zone(gfp_t flags)
 	enum zone_type z;
 	int bit = (__force int) (flags & GFP_ZONEMASK);
 
-	z = (GFP_ZONE_TABLE >> (bit * ZONES_SHIFT)) &
-					 ((1 << ZONES_SHIFT) - 1);
+	z = (GFP_ZONE_TABLE >> (bit * GFP_ZONES_SHIFT)) &
+					 ((1 << GFP_ZONES_SHIFT) - 1);
 	VM_BUG_ON((GFP_ZONE_BAD >> bit) & 1);
 	return z;
 }

include/linux/hrtimer.h

@@ -220,7 +220,7 @@ static inline void hrtimer_set_expires_range(struct hrtimer *timer, ktime_t time
 	timer->node.expires = ktime_add_safe(time, delta);
 }
 
-static inline void hrtimer_set_expires_range_ns(struct hrtimer *timer, ktime_t time, unsigned long delta)
+static inline void hrtimer_set_expires_range_ns(struct hrtimer *timer, ktime_t time, u64 delta)
 {
 	timer->_softexpires = time;
 	timer->node.expires = ktime_add_safe(time, ns_to_ktime(delta));
@@ -378,7 +378,7 @@ static inline void destroy_hrtimer_on_stack(struct hrtimer *timer) { }
 
 /* Basic timer operations: */
 extern void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
-			unsigned long range_ns, const enum hrtimer_mode mode);
+				   u64 range_ns, const enum hrtimer_mode mode);
 
 /**
  * hrtimer_start - (re)start an hrtimer on the current CPU
@@ -399,7 +399,7 @@ extern int hrtimer_try_to_cancel(struct hrtimer *timer);
 static inline void hrtimer_start_expires(struct hrtimer *timer,
 					 enum hrtimer_mode mode)
 {
-	unsigned long delta;
+	u64 delta;
 	ktime_t soft, hard;
 	soft = hrtimer_get_softexpires(timer);
 	hard = hrtimer_get_expires(timer);
@@ -477,10 +477,12 @@ extern long hrtimer_nanosleep_restart(struct restart_block *restart_block);
 extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl,
 				 struct task_struct *tsk);
 
-extern int schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
+extern int schedule_hrtimeout_range(ktime_t *expires, u64 delta,
 						const enum hrtimer_mode mode);
 extern int schedule_hrtimeout_range_clock(ktime_t *expires,
-		unsigned long delta, const enum hrtimer_mode mode, int clock);
+					  u64 delta,
+					  const enum hrtimer_mode mode,
+					  int clock);
 extern int schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode);
 
 /* Soft interrupt function to run the hrtimer queues: */

include/linux/huge_mm.h

@@ -41,7 +41,8 @@ int vmf_insert_pfn_pmd(struct vm_area_struct *, unsigned long addr, pmd_t *,
 enum transparent_hugepage_flag {
 	TRANSPARENT_HUGEPAGE_FLAG,
 	TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
-	TRANSPARENT_HUGEPAGE_DEFRAG_FLAG,
+	TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG,
+	TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG,
 	TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG,
 	TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG,
 	TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG,
@@ -71,12 +72,6 @@ extern bool is_vma_temporary_stack(struct vm_area_struct *vma);
 	   ((__vma)->vm_flags & VM_HUGEPAGE))) &&			\
 	 !((__vma)->vm_flags & VM_NOHUGEPAGE) &&			\
 	 !is_vma_temporary_stack(__vma))
-#define transparent_hugepage_defrag(__vma)				\
-	((transparent_hugepage_flags &					\
-	  (1<<TRANSPARENT_HUGEPAGE_DEFRAG_FLAG)) ||			\
-	 (transparent_hugepage_flags &					\
-	  (1<<TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG) &&		\
-	  (__vma)->vm_flags & VM_HUGEPAGE))
 #define transparent_hugepage_use_zero_page()				\
 	(transparent_hugepage_flags &					\
 	 (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG))
@@ -101,16 +96,21 @@ static inline int split_huge_page(struct page *page)
 void deferred_split_huge_page(struct page *page);
 
 void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
-		unsigned long address);
+		unsigned long address, bool freeze);
 
 #define split_huge_pmd(__vma, __pmd, __address)				\
 	do {								\
 		pmd_t *____pmd = (__pmd);				\
 		if (pmd_trans_huge(*____pmd)				\
 					|| pmd_devmap(*____pmd))	\
-			__split_huge_pmd(__vma, __pmd, __address);	\
+			__split_huge_pmd(__vma, __pmd, __address,	\
+						false);			\
 	}  while (0)
 
+
+void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address,
+		bool freeze, struct page *page);
+
 #if HPAGE_PMD_ORDER >= MAX_ORDER
 #error "hugepages can't be allocated by the buddy allocator"
 #endif
@@ -178,6 +178,10 @@ static inline int split_huge_page(struct page *page)
 static inline void deferred_split_huge_page(struct page *page) {}
 #define split_huge_pmd(__vma, __pmd, __address)	\
 	do { } while (0)
+
+static inline void split_huge_pmd_address(struct vm_area_struct *vma,
+		unsigned long address, bool freeze, struct page *page) {}
+
 static inline int hugepage_madvise(struct vm_area_struct *vma,
 				   unsigned long *vm_flags, int advice)
 {

include/linux/kernel.h

@@ -357,6 +357,7 @@ int __must_check kstrtou16(const char *s, unsigned int base, u16 *res);
 int __must_check kstrtos16(const char *s, unsigned int base, s16 *res);
 int __must_check kstrtou8(const char *s, unsigned int base, u8 *res);
 int __must_check kstrtos8(const char *s, unsigned int base, s8 *res);
+int __must_check kstrtobool(const char *s, bool *res);
 
 int __must_check kstrtoull_from_user(const char __user *s, size_t count, unsigned int base, unsigned long long *res);
 int __must_check kstrtoll_from_user(const char __user *s, size_t count, unsigned int base, long long *res);
@@ -368,6 +369,7 @@ int __must_check kstrtou16_from_user(const char __user *s, size_t count, unsigne
 int __must_check kstrtos16_from_user(const char __user *s, size_t count, unsigned int base, s16 *res);
 int __must_check kstrtou8_from_user(const char __user *s, size_t count, unsigned int base, u8 *res);
 int __must_check kstrtos8_from_user(const char __user *s, size_t count, unsigned int base, s8 *res);
+int __must_check kstrtobool_from_user(const char __user *s, size_t count, bool *res);
 
 static inline int __must_check kstrtou64_from_user(const char __user *s, size_t count, unsigned int base, u64 *res)
 {

include/linux/list_bl.h

@@ -48,7 +48,7 @@ static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h)
 
 #define hlist_bl_entry(ptr, type, member) container_of(ptr,type,member)
 
-static inline int hlist_bl_unhashed(const struct hlist_bl_node *h)
+static inline bool  hlist_bl_unhashed(const struct hlist_bl_node *h)
 {
 	return !h->pprev;
 }
@@ -68,7 +68,7 @@ static inline void hlist_bl_set_first(struct hlist_bl_head *h,
 	h->first = (struct hlist_bl_node *)((unsigned long)n | LIST_BL_LOCKMASK);
 }
 
-static inline int hlist_bl_empty(const struct hlist_bl_head *h)
+static inline bool hlist_bl_empty(const struct hlist_bl_head *h)
 {
 	return !((unsigned long)READ_ONCE(h->first) & ~LIST_BL_LOCKMASK);
 }

include/linux/memcontrol.h

@@ -52,7 +52,10 @@ enum mem_cgroup_stat_index {
 	MEM_CGROUP_STAT_SWAP,		/* # of pages, swapped out */
 	MEM_CGROUP_STAT_NSTATS,
 	/* default hierarchy stats */
-	MEMCG_SOCK = MEM_CGROUP_STAT_NSTATS,
+	MEMCG_KERNEL_STACK = MEM_CGROUP_STAT_NSTATS,
+	MEMCG_SLAB_RECLAIMABLE,
+	MEMCG_SLAB_UNRECLAIMABLE,
+	MEMCG_SOCK,
 	MEMCG_NR_STAT,
 };
 
@@ -400,6 +403,9 @@ int mem_cgroup_select_victim_node(struct mem_cgroup *memcg);
 void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
 		int nr_pages);
 
+unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
+					   int nid, unsigned int lru_mask);
+
 static inline
 unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru)
 {
@@ -658,6 +664,13 @@ mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
 {
 }
 
+static inline unsigned long
+mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
+			     int nid, unsigned int lru_mask)
+{
+	return 0;
+}
+
 static inline void
 mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 {
@@ -792,11 +805,6 @@ static inline bool memcg_kmem_enabled(void)
 	return static_branch_unlikely(&memcg_kmem_enabled_key);
 }
 
-static inline bool memcg_kmem_online(struct mem_cgroup *memcg)
-{
-	return memcg->kmem_state == KMEM_ONLINE;
-}
-
 /*
  * In general, we'll do everything in our power to not incur in any overhead
  * for non-memcg users for the kmem functions. Not even a function call, if we
@@ -883,6 +891,20 @@ static __always_inline void memcg_kmem_put_cache(struct kmem_cache *cachep)
 	if (memcg_kmem_enabled())
 		__memcg_kmem_put_cache(cachep);
 }
+
+/**
+ * memcg_kmem_update_page_stat - update kmem page state statistics
+ * @page: the page
+ * @idx: page state item to account
+ * @val: number of pages (positive or negative)
+ */
+static inline void memcg_kmem_update_page_stat(struct page *page,
+				enum mem_cgroup_stat_index idx, int val)
+{
+	if (memcg_kmem_enabled() && page->mem_cgroup)
+		this_cpu_add(page->mem_cgroup->stat->count[idx], val);
+}
+
 #else
 #define for_each_memcg_cache_index(_idx)	\
 	for (; NULL; )
@@ -892,11 +914,6 @@ static inline bool memcg_kmem_enabled(void)
 	return false;
 }
 
-static inline bool memcg_kmem_online(struct mem_cgroup *memcg)
-{
-	return false;
-}
-
 static inline int memcg_kmem_charge(struct page *page, gfp_t gfp, int order)
 {
 	return 0;
@@ -928,6 +945,11 @@ memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
 static inline void memcg_kmem_put_cache(struct kmem_cache *cachep)
 {
 }
+
+static inline void memcg_kmem_update_page_stat(struct page *page,
+				enum mem_cgroup_stat_index idx, int val)
+{
+}
 #endif /* CONFIG_MEMCG && !CONFIG_SLOB */
 
 #endif /* _LINUX_MEMCONTROL_H */

include/linux/mm.h

@@ -22,6 +22,7 @@
 #include <linux/resource.h>
 #include <linux/page_ext.h>
 #include <linux/err.h>
+#include <linux/page_ref.h>
 
 struct mempolicy;
 struct anon_vma;
@@ -82,6 +83,27 @@ extern int mmap_rnd_compat_bits __read_mostly;
 #define mm_forbids_zeropage(X)	(0)
 #endif
 
+/*
+ * Default maximum number of active map areas, this limits the number of vmas
+ * per mm struct. Users can overwrite this number by sysctl but there is a
+ * problem.
+ *
+ * When a program's coredump is generated as ELF format, a section is created
+ * per a vma. In ELF, the number of sections is represented in unsigned short.
+ * This means the number of sections should be smaller than 65535 at coredump.
+ * Because the kernel adds some informative sections to a image of program at
+ * generating coredump, we need some margin. The number of extra sections is
+ * 1-3 now and depends on arch. We use "5" as safe margin, here.
+ *
+ * ELF extended numbering allows more than 65535 sections, so 16-bit bound is
+ * not a hard limit any more. Although some userspace tools can be surprised by
+ * that.
+ */
+#define MAPCOUNT_ELF_CORE_MARGIN	(5)
+#define DEFAULT_MAX_MAP_COUNT	(USHRT_MAX - MAPCOUNT_ELF_CORE_MARGIN)
+
+extern int sysctl_max_map_count;
+
 extern unsigned long sysctl_user_reserve_kbytes;
 extern unsigned long sysctl_admin_reserve_kbytes;
 
@@ -122,6 +144,7 @@ extern unsigned int kobjsize(const void *objp);
 
 /*
  * vm_flags in vm_area_struct, see mm_types.h.
+ * When changing, update also include/trace/events/mmflags.h
  */
 #define VM_NONE		0x00000000
 
@@ -364,8 +387,8 @@ static inline int pmd_devmap(pmd_t pmd)
  */
 static inline int put_page_testzero(struct page *page)
 {
-	VM_BUG_ON_PAGE(atomic_read(&page->_count) == 0, page);
-	return atomic_dec_and_test(&page->_count);
+	VM_BUG_ON_PAGE(page_ref_count(page) == 0, page);
+	return page_ref_dec_and_test(page);
 }
 
 /*
@@ -376,7 +399,7 @@ static inline int put_page_testzero(struct page *page)
  */
 static inline int get_page_unless_zero(struct page *page)
 {
-	return atomic_inc_not_zero(&page->_count);
+	return page_ref_add_unless(page, 1, 0);
 }
 
 extern int page_is_ram(unsigned long pfn);
@@ -464,11 +487,6 @@ static inline int total_mapcount(struct page *page)
 }
 #endif
 
-static inline int page_count(struct page *page)
-{
-	return atomic_read(&compound_head(page)->_count);
-}
-
 static inline struct page *virt_to_head_page(const void *x)
 {
 	struct page *page = virt_to_page(x);
@@ -476,15 +494,6 @@ static inline struct page *virt_to_head_page(const void *x)
 	return compound_head(page);
 }
 
-/*
- * Setup the page count before being freed into the page allocator for
- * the first time (boot or memory hotplug)
- */
-static inline void init_page_count(struct page *page)
-{
-	atomic_set(&page->_count, 1);
-}
-
 void __put_page(struct page *page);
 
 void put_pages_list(struct list_head *pages);
@@ -694,8 +703,8 @@ static inline void get_page(struct page *page)
 	 * Getting a normal page or the head of a compound page
 	 * requires to already have an elevated page->_count.
 	 */
-	VM_BUG_ON_PAGE(atomic_read(&page->_count) <= 0, page);
-	atomic_inc(&page->_count);
+	VM_BUG_ON_PAGE(page_ref_count(page) <= 0, page);
+	page_ref_inc(page);
 
 	if (unlikely(is_zone_device_page(page)))
 		get_zone_device_page(page);
@@ -1043,8 +1052,6 @@ static inline void clear_page_pfmemalloc(struct page *page)
  * just gets major/minor fault counters bumped up.
  */
 
-#define VM_FAULT_MINOR	0 /* For backwards compat. Remove me quickly. */
-
 #define VM_FAULT_OOM	0x0001
 #define VM_FAULT_SIGBUS	0x0002
 #define VM_FAULT_MAJOR	0x0004
@@ -1523,8 +1530,7 @@ static inline void mm_dec_nr_pmds(struct mm_struct *mm)
 }
 #endif
 
-int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
-		pmd_t *pmd, unsigned long address);
+int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address);
 int __pte_alloc_kernel(pmd_t *pmd, unsigned long address);
 
 /*
@@ -1650,15 +1656,15 @@ static inline void pgtable_page_dtor(struct page *page)
 	pte_unmap(pte);					\
 } while (0)
 
-#define pte_alloc_map(mm, vma, pmd, address)				\
-	((unlikely(pmd_none(*(pmd))) && __pte_alloc(mm, vma,	\
-							pmd, address))?	\
-	 NULL: pte_offset_map(pmd, address))
+#define pte_alloc(mm, pmd, address)			\
+	(unlikely(pmd_none(*(pmd))) && __pte_alloc(mm, pmd, address))
+
+#define pte_alloc_map(mm, pmd, address)			\
+	(pte_alloc(mm, pmd, address) ? NULL : pte_offset_map(pmd, address))
 
 #define pte_alloc_map_lock(mm, pmd, address, ptlp)	\
-	((unlikely(pmd_none(*(pmd))) && __pte_alloc(mm, NULL,	\
-							pmd, address))?	\
-		NULL: pte_offset_map_lock(mm, pmd, address, ptlp))
+	(pte_alloc(mm, pmd, address) ?			\
+		 NULL : pte_offset_map_lock(mm, pmd, address, ptlp))
 
 #define pte_alloc_kernel(pmd, address)			\
 	((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd, address))? \
@@ -1853,6 +1859,7 @@ extern int __meminit init_per_zone_wmark_min(void);
 extern void mem_init(void);
 extern void __init mmap_init(void);
 extern void show_mem(unsigned int flags);
+extern long si_mem_available(void);
 extern void si_meminfo(struct sysinfo * val);
 extern void si_meminfo_node(struct sysinfo *val, int nid);
 
@@ -1867,6 +1874,7 @@ extern void zone_pcp_reset(struct zone *zone);
 
 /* page_alloc.c */
 extern int min_free_kbytes;
+extern int watermark_scale_factor;
 
 /* nommu.c */
 extern atomic_long_t mmap_pages_allocated;

include/linux/mmzone.h

@@ -668,6 +668,12 @@ typedef struct pglist_data {
 					   mem_hotplug_begin/end() */
 	int kswapd_max_order;
 	enum zone_type classzone_idx;
+#ifdef CONFIG_COMPACTION
+	int kcompactd_max_order;
+	enum zone_type kcompactd_classzone_idx;
+	wait_queue_head_t kcompactd_wait;
+	struct task_struct *kcompactd;
+#endif
 #ifdef CONFIG_NUMA_BALANCING
 	/* Lock serializing the migrate rate limiting window */
 	spinlock_t numabalancing_migrate_lock;
@@ -835,6 +841,8 @@ static inline int is_highmem(struct zone *zone)
 struct ctl_table;
 int min_free_kbytes_sysctl_handler(struct ctl_table *, int,
 					void __user *, size_t *, loff_t *);
+int watermark_scale_factor_sysctl_handler(struct ctl_table *, int,
+					void __user *, size_t *, loff_t *);
 extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1];
 int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int,
 					void __user *, size_t *, loff_t *);

include/linux/page-flags-layout.h

@@ -17,6 +17,8 @@
 #define ZONES_SHIFT 1
 #elif MAX_NR_ZONES <= 4
 #define ZONES_SHIFT 2
+#elif MAX_NR_ZONES <= 8
+#define ZONES_SHIFT 3
 #else
 #error ZONES_SHIFT -- too many zones configured adjust calculation
 #endif

include/linux/page-flags.h

@@ -144,12 +144,12 @@ static inline struct page *compound_head(struct page *page)
 	return page;
 }
 
-static inline int PageTail(struct page *page)
+static __always_inline int PageTail(struct page *page)
 {
 	return READ_ONCE(page->compound_head) & 1;
 }
 
-static inline int PageCompound(struct page *page)
+static __always_inline int PageCompound(struct page *page)
 {
 	return test_bit(PG_head, &page->flags) || PageTail(page);
 }
@@ -184,31 +184,31 @@ static inline int PageCompound(struct page *page)
  * Macros to create function definitions for page flags
  */
 #define TESTPAGEFLAG(uname, lname, policy)				\
-static inline int Page##uname(struct page *page)			\
+static __always_inline int Page##uname(struct page *page)		\
 	{ return test_bit(PG_##lname, &policy(page, 0)->flags); }
 
 #define SETPAGEFLAG(uname, lname, policy)				\
-static inline void SetPage##uname(struct page *page)			\
+static __always_inline void SetPage##uname(struct page *page)		\
 	{ set_bit(PG_##lname, &policy(page, 1)->flags); }
 
 #define CLEARPAGEFLAG(uname, lname, policy)				\
-static inline void ClearPage##uname(struct page *page)			\
+static __always_inline void ClearPage##uname(struct page *page)		\
 	{ clear_bit(PG_##lname, &policy(page, 1)->flags); }
 
 #define __SETPAGEFLAG(uname, lname, policy)				\
-static inline void __SetPage##uname(struct page *page)			\
+static __always_inline void __SetPage##uname(struct page *page)		\
 	{ __set_bit(PG_##lname, &policy(page, 1)->flags); }
 
 #define __CLEARPAGEFLAG(uname, lname, policy)				\
-static inline void __ClearPage##uname(struct page *page)		\
+static __always_inline void __ClearPage##uname(struct page *page)	\
 	{ __clear_bit(PG_##lname, &policy(page, 1)->flags); }
 
 #define TESTSETFLAG(uname, lname, policy)				\
-static inline int TestSetPage##uname(struct page *page)			\
+static __always_inline int TestSetPage##uname(struct page *page)	\
 	{ return test_and_set_bit(PG_##lname, &policy(page, 1)->flags); }
 
 #define TESTCLEARFLAG(uname, lname, policy)				\
-static inline int TestClearPage##uname(struct page *page)		\
+static __always_inline int TestClearPage##uname(struct page *page)	\
 	{ return test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); }
 
 #define PAGEFLAG(uname, lname, policy)					\
@@ -371,7 +371,7 @@ PAGEFLAG(Idle, idle, PF_ANY)
 #define PAGE_MAPPING_KSM	2
 #define PAGE_MAPPING_FLAGS	(PAGE_MAPPING_ANON | PAGE_MAPPING_KSM)
 
-static inline int PageAnon(struct page *page)
+static __always_inline int PageAnon(struct page *page)
 {
 	page = compound_head(page);
 	return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0;
@@ -384,7 +384,7 @@ static inline int PageAnon(struct page *page)
  * is found in VM_MERGEABLE vmas.  It's a PageAnon page, pointing not to any
  * anon_vma, but to that page's node of the stable tree.
  */
-static inline int PageKsm(struct page *page)
+static __always_inline int PageKsm(struct page *page)
 {
 	page = compound_head(page);
 	return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) ==
@@ -415,14 +415,14 @@ static inline int PageUptodate(struct page *page)
 	return ret;
 }
 
-static inline void __SetPageUptodate(struct page *page)
+static __always_inline void __SetPageUptodate(struct page *page)
 {
 	VM_BUG_ON_PAGE(PageTail(page), page);
 	smp_wmb();
 	__set_bit(PG_uptodate, &page->flags);
 }
 
-static inline void SetPageUptodate(struct page *page)
+static __always_inline void SetPageUptodate(struct page *page)
 {
 	VM_BUG_ON_PAGE(PageTail(page), page);
 	/*
@@ -456,12 +456,12 @@ static inline void set_page_writeback_keepwrite(struct page *page)
 
 __PAGEFLAG(Head, head, PF_ANY) CLEARPAGEFLAG(Head, head, PF_ANY)
 
-static inline void set_compound_head(struct page *page, struct page *head)
+static __always_inline void set_compound_head(struct page *page, struct page *head)
 {
 	WRITE_ONCE(page->compound_head, (unsigned long)head + 1);
 }
 
-static inline void clear_compound_head(struct page *page)
+static __always_inline void clear_compound_head(struct page *page)
 {
 	WRITE_ONCE(page->compound_head, 0);
 }
@@ -593,6 +593,8 @@ static inline void __ClearPageBuddy(struct page *page)
 	atomic_set(&page->_mapcount, -1);
 }
 
+extern bool is_free_buddy_page(struct page *page);
+
 #define PAGE_BALLOON_MAPCOUNT_VALUE (-256)
 
 static inline int PageBalloon(struct page *page)

include/linux/page_ref.h

@@ -0,0 +1,173 @@
+#ifndef _LINUX_PAGE_REF_H
+#define _LINUX_PAGE_REF_H
+
+#include <linux/atomic.h>
+#include <linux/mm_types.h>
+#include <linux/page-flags.h>
+#include <linux/tracepoint-defs.h>
+
+extern struct tracepoint __tracepoint_page_ref_set;
+extern struct tracepoint __tracepoint_page_ref_mod;
+extern struct tracepoint __tracepoint_page_ref_mod_and_test;
+extern struct tracepoint __tracepoint_page_ref_mod_and_return;
+extern struct tracepoint __tracepoint_page_ref_mod_unless;
+extern struct tracepoint __tracepoint_page_ref_freeze;
+extern struct tracepoint __tracepoint_page_ref_unfreeze;
+
+#ifdef CONFIG_DEBUG_PAGE_REF
+
+/*
+ * Ideally we would want to use the trace_<tracepoint>_enabled() helper
+ * functions. But due to include header file issues, that is not
+ * feasible. Instead we have to open code the static key functions.
+ *
+ * See trace_##name##_enabled(void) in include/linux/tracepoint.h
+ */
+#define page_ref_tracepoint_active(t) static_key_false(&(t).key)
+
+extern void __page_ref_set(struct page *page, int v);
+extern void __page_ref_mod(struct page *page, int v);
+extern void __page_ref_mod_and_test(struct page *page, int v, int ret);
+extern void __page_ref_mod_and_return(struct page *page, int v, int ret);
+extern void __page_ref_mod_unless(struct page *page, int v, int u);
+extern void __page_ref_freeze(struct page *page, int v, int ret);
+extern void __page_ref_unfreeze(struct page *page, int v);
+
+#else
+
+#define page_ref_tracepoint_active(t) false
+
+static inline void __page_ref_set(struct page *page, int v)
+{
+}
+static inline void __page_ref_mod(struct page *page, int v)
+{
+}
+static inline void __page_ref_mod_and_test(struct page *page, int v, int ret)
+{
+}
+static inline void __page_ref_mod_and_return(struct page *page, int v, int ret)
+{
+}
+static inline void __page_ref_mod_unless(struct page *page, int v, int u)
+{
+}
+static inline void __page_ref_freeze(struct page *page, int v, int ret)
+{
+}
+static inline void __page_ref_unfreeze(struct page *page, int v)
+{
+}
+
+#endif
+
+static inline int page_ref_count(struct page *page)
+{
+	return atomic_read(&page->_count);
+}
+
+static inline int page_count(struct page *page)
+{
+	return atomic_read(&compound_head(page)->_count);
+}
+
+static inline void set_page_count(struct page *page, int v)
+{
+	atomic_set(&page->_count, v);
+	if (page_ref_tracepoint_active(__tracepoint_page_ref_set))
+		__page_ref_set(page, v);
+}
+
+/*
+ * Setup the page count before being freed into the page allocator for
+ * the first time (boot or memory hotplug)
+ */
+static inline void init_page_count(struct page *page)
+{
+	set_page_count(page, 1);
+}
+
+static inline void page_ref_add(struct page *page, int nr)
+{
+	atomic_add(nr, &page->_count);
+	if (page_ref_tracepoint_active(__tracepoint_page_ref_mod))
+		__page_ref_mod(page, nr);
+}
+
+static inline void page_ref_sub(struct page *page, int nr)
+{
+	atomic_sub(nr, &page->_count);
+	if (page_ref_tracepoint_active(__tracepoint_page_ref_mod))
+		__page_ref_mod(page, -nr);
+}
+
+static inline void page_ref_inc(struct page *page)
+{
+	atomic_inc(&page->_count);
+	if (page_ref_tracepoint_active(__tracepoint_page_ref_mod))
+		__page_ref_mod(page, 1);
+}
+
+static inline void page_ref_dec(struct page *page)
+{
+	atomic_dec(&page->_count);
+	if (page_ref_tracepoint_active(__tracepoint_page_ref_mod))
+		__page_ref_mod(page, -1);
+}
+
+static inline int page_ref_sub_and_test(struct page *page, int nr)
+{
+	int ret = atomic_sub_and_test(nr, &page->_count);
+
+	if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_test))
+		__page_ref_mod_and_test(page, -nr, ret);
+	return ret;
+}
+
+static inline int page_ref_dec_and_test(struct page *page)
+{
+	int ret = atomic_dec_and_test(&page->_count);
+
+	if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_test))
+		__page_ref_mod_and_test(page, -1, ret);
+	return ret;
+}
+
+static inline int page_ref_dec_return(struct page *page)
+{
+	int ret = atomic_dec_return(&page->_count);
+
+	if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_return))
+		__page_ref_mod_and_return(page, -1, ret);
+	return ret;
+}
+
+static inline int page_ref_add_unless(struct page *page, int nr, int u)
+{
+	int ret = atomic_add_unless(&page->_count, nr, u);
+
+	if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_unless))
+		__page_ref_mod_unless(page, nr, ret);
+	return ret;
+}
+
+static inline int page_ref_freeze(struct page *page, int count)
+{
+	int ret = likely(atomic_cmpxchg(&page->_count, count, 0) == count);
+
+	if (page_ref_tracepoint_active(__tracepoint_page_ref_freeze))
+		__page_ref_freeze(page, count, ret);
+	return ret;
+}
+
+static inline void page_ref_unfreeze(struct page *page, int count)
+{
+	VM_BUG_ON_PAGE(page_count(page) != 0, page);
+	VM_BUG_ON(count == 0);
+
+	atomic_set(&page->_count, count);
+	if (page_ref_tracepoint_active(__tracepoint_page_ref_unfreeze))
+		__page_ref_unfreeze(page, count);
+}
+
+#endif

include/linux/pagemap.h

@@ -165,7 +165,7 @@ static inline int page_cache_get_speculative(struct page *page)
 	 * SMP requires.
 	 */
 	VM_BUG_ON_PAGE(page_count(page) == 0, page);
-	atomic_inc(&page->_count);
+	page_ref_inc(page);
 
 #else
 	if (unlikely(!get_page_unless_zero(page))) {
@@ -194,10 +194,10 @@ static inline int page_cache_add_speculative(struct page *page, int count)
 	VM_BUG_ON(!in_atomic());
 # endif
 	VM_BUG_ON_PAGE(page_count(page) == 0, page);
-	atomic_add(count, &page->_count);
+	page_ref_add(page, count);
 
 #else
-	if (unlikely(!atomic_add_unless(&page->_count, count, 0)))
+	if (unlikely(!page_ref_add_unless(page, count, 0)))
 		return 0;
 #endif
 	VM_BUG_ON_PAGE(PageCompound(page) && page != compound_head(page), page);
@@ -205,19 +205,6 @@ static inline int page_cache_add_speculative(struct page *page, int count)
 	return 1;
 }
 
-static inline int page_freeze_refs(struct page *page, int count)
-{
-	return likely(atomic_cmpxchg(&page->_count, count, 0) == count);
-}
-
-static inline void page_unfreeze_refs(struct page *page, int count)
-{
-	VM_BUG_ON_PAGE(page_count(page) != 0, page);
-	VM_BUG_ON(count == 0);
-
-	atomic_set(&page->_count, count);
-}
-
 #ifdef CONFIG_NUMA
 extern struct page *__page_cache_alloc(gfp_t gfp);
 #else

include/linux/poll.h

@@ -96,7 +96,7 @@ extern void poll_initwait(struct poll_wqueues *pwq);
 extern void poll_freewait(struct poll_wqueues *pwq);
 extern int poll_schedule_timeout(struct poll_wqueues *pwq, int state,
 				 ktime_t *expires, unsigned long slack);
-extern long select_estimate_accuracy(struct timespec *tv);
+extern u64 select_estimate_accuracy(struct timespec *tv);
 
 
 static inline int poll_schedule(struct poll_wqueues *pwq, int state)

include/linux/quicklist.h

@@ -5,7 +5,7 @@
  * as needed after allocation when they are freed. Per cpu lists of pages
  * are kept that only contain node local pages.
  *
- * (C) 2007, SGI. Christoph Lameter <clameter@sgi.com>
+ * (C) 2007, SGI. Christoph Lameter <cl@linux.com>
  */
 #include <linux/kernel.h>
 #include <linux/gfp.h>

include/linux/radix-tree.h

@@ -21,6 +21,7 @@
 #ifndef _LINUX_RADIX_TREE_H
 #define _LINUX_RADIX_TREE_H
 
+#include <linux/bitops.h>
 #include <linux/preempt.h>
 #include <linux/types.h>
 #include <linux/bug.h>
@@ -270,8 +271,15 @@ static inline void radix_tree_replace_slot(void **pslot, void *item)
 }
 
 int __radix_tree_create(struct radix_tree_root *root, unsigned long index,
-			struct radix_tree_node **nodep, void ***slotp);
-int radix_tree_insert(struct radix_tree_root *, unsigned long, void *);
+			unsigned order, struct radix_tree_node **nodep,
+			void ***slotp);
+int __radix_tree_insert(struct radix_tree_root *, unsigned long index,
+			unsigned order, void *);
+static inline int radix_tree_insert(struct radix_tree_root *root,
+			unsigned long index, void *entry)
+{
+	return __radix_tree_insert(root, index, 0, entry);
+}
 void *__radix_tree_lookup(struct radix_tree_root *root, unsigned long index,
 			  struct radix_tree_node **nodep, void ***slotp);
 void *radix_tree_lookup(struct radix_tree_root *, unsigned long);
@@ -394,6 +402,22 @@ void **radix_tree_iter_retry(struct radix_tree_iter *iter)
 	return NULL;
 }
 
+/**
+ * radix_tree_iter_next - resume iterating when the chunk may be invalid
+ * @iter:	iterator state
+ *
+ * If the iterator needs to release then reacquire a lock, the chunk may
+ * have been invalidated by an insertion or deletion.  Call this function
+ * to continue the iteration from the next index.
+ */
+static inline __must_check
+void **radix_tree_iter_next(struct radix_tree_iter *iter)
+{
+	iter->next_index = iter->index + 1;
+	iter->tags = 0;
+	return NULL;
+}
+
 /**
  * radix_tree_chunk_size - get current chunk size
  *