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