Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:

 - fsnotify fix

 - poll() timeout fix

 - a few scripts/ tweaks

 - debugobjects updates

 - the (small) ocfs2 queue

 - Minor fixes to kernel/padata.c

 - Maybe half of the MM queue

* emailed patches from Andrew Morton <[email protected]>: (117 commits)
  mm, page_alloc: restore the original nodemask if the fast path allocation failed
  mm, page_alloc: uninline the bad page part of check_new_page()
  mm, page_alloc: don't duplicate code in free_pcp_prepare
  mm, page_alloc: defer debugging checks of pages allocated from the PCP
  mm, page_alloc: defer debugging checks of freed pages until a PCP drain
  cpuset: use static key better and convert to new API
  mm, page_alloc: inline pageblock lookup in page free fast paths
  mm, page_alloc: remove unnecessary variable from free_pcppages_bulk
  mm, page_alloc: pull out side effects from free_pages_check
  mm, page_alloc: un-inline the bad part of free_pages_check
  mm, page_alloc: check multiple page fields with a single branch
  mm, page_alloc: remove field from alloc_context
  mm, page_alloc: avoid looking up the first zone in a zonelist twice
  mm, page_alloc: shortcut watermark checks for order-0 pages
  mm, page_alloc: reduce cost of fair zone allocation policy retry
  mm, page_alloc: shorten the page allocator fast path
  mm, page_alloc: check once if a zone has isolated pageblocks
  mm, page_alloc: move __GFP_HARDWALL modifications out of the fastpath
  mm, page_alloc: simplify last cpupid reset
  mm, page_alloc: remove unnecessary initialisation from __alloc_pages_nodemask()
  ...

Documentation/DocBook/debugobjects.tmpl

@@ -316,8 +316,8 @@
 	</itemizedlist>
       </para>
       <para>
-	The function returns 1 when the fixup was successful,
-	otherwise 0. The return value is used to update the
+	The function returns true when the fixup was successful,
+	otherwise false. The return value is used to update the
 	statistics.
       </para>
       <para>
@@ -341,8 +341,8 @@
 	</itemizedlist>
       </para>
       <para>
-	The function returns 1 when the fixup was successful,
-	otherwise 0. The return value is used to update the
+	The function returns true when the fixup was successful,
+	otherwise false. The return value is used to update the
 	statistics.
       </para>
       <para>
@@ -359,7 +359,8 @@
 	statically initialized object or not. In case it is it calls
 	debug_object_init() and debug_object_activate() to make the
 	object known to the tracker and marked active. In this case
-	the function should return 0 because this is not a real fixup.
+	the function should return false because this is not a real
+	fixup.
       </para>
     </sect1>
 
@@ -376,8 +377,8 @@
 	</itemizedlist>
       </para>
       <para>
-	The function returns 1 when the fixup was successful,
-	otherwise 0. The return value is used to update the
+	The function returns true when the fixup was successful,
+	otherwise false. The return value is used to update the
 	statistics.
       </para>
     </sect1>
@@ -397,8 +398,8 @@
 	</itemizedlist>
       </para>
       <para>
-	The function returns 1 when the fixup was successful,
-	otherwise 0. The return value is used to update the
+	The function returns true when the fixup was successful,
+	otherwise false. The return value is used to update the
 	statistics.
       </para>
     </sect1>
@@ -414,8 +415,8 @@
 	debug bucket.
       </para>
       <para>
-	The function returns 1 when the fixup was successful,
-	otherwise 0. The return value is used to update the
+	The function returns true when the fixup was successful,
+	otherwise false. The return value is used to update the
 	statistics.
       </para>
       <para>
@@ -427,7 +428,8 @@
 	case. The fixup function should check if this is a legitimate
 	case of a statically initialized object or not. In this case only
 	debug_object_init() should be called to make the object known to
-	the tracker. Then the function should return 0 because this is not
+	the tracker. Then the function should return false because this
+	is not
 	a real fixup.
       </para>
     </sect1>

Documentation/kernel-parameters.txt

@@ -2168,6 +2168,14 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			[KNL,SH] Allow user to override the default size for
 			per-device physically contiguous DMA buffers.
 
+        memhp_default_state=online/offline
+			[KNL] Set the initial state for the memory hotplug
+			onlining policy. If not specified, the default value is
+			set according to the
+			CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE kernel config
+			option.
+			See Documentation/memory-hotplug.txt.
+
 	memmap=exactmap	[KNL,X86] Enable setting of an exact
 			E820 memory map, as specified by the user.
 			Such memmap=exactmap lines can be constructed based on

Documentation/memory-hotplug.txt

@@ -261,10 +261,11 @@ it according to the policy which can be read from "auto_online_blocks" file:
 
 % cat /sys/devices/system/memory/auto_online_blocks
 
-The default is "offline" which means the newly added memory is not in a
-ready-to-use state and you have to "online" the newly added memory blocks
-manually. Automatic onlining can be requested by writing "online" to
-"auto_online_blocks" file:
+The default depends on the CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE kernel config
+option. If it is disabled the default is "offline" which means the newly added
+memory is not in a ready-to-use state and you have to "online" the newly added
+memory blocks manually. Automatic onlining can be requested by writing "online"
+to "auto_online_blocks" file:
 
 % echo online > /sys/devices/system/memory/auto_online_blocks
 

Documentation/sysctl/vm.txt

@@ -57,6 +57,7 @@ Currently, these files are in /proc/sys/vm:
 - panic_on_oom
 - percpu_pagelist_fraction
 - stat_interval
+- stat_refresh
 - swappiness
 - user_reserve_kbytes
 - vfs_cache_pressure
@@ -755,6 +756,19 @@ is 1 second.
 
 ==============================================================
 
+stat_refresh
+
+Any read or write (by root only) flushes all the per-cpu vm statistics
+into their global totals, for more accurate reports when testing
+e.g. cat /proc/sys/vm/stat_refresh /proc/meminfo
+
+As a side-effect, it also checks for negative totals (elsewhere reported
+as 0) and "fails" with EINVAL if any are found, with a warning in dmesg.
+(At time of writing, a few stats are known sometimes to be found negative,
+with no ill effects: errors and warnings on these stats are suppressed.)
+
+==============================================================
+
 swappiness
 
 This control is used to define how aggressive the kernel will swap

Documentation/vm/transhuge.txt

@@ -394,9 +394,9 @@ hugepage natively. Once finished you can drop the page table lock.
 Refcounting on THP is mostly consistent with refcounting on other compound
 pages:
 
-  - get_page()/put_page() and GUP operate in head page's ->_count.
+  - get_page()/put_page() and GUP operate in head page's ->_refcount.
 
-  - ->_count in tail pages is always zero: get_page_unless_zero() never
+  - ->_refcount in tail pages is always zero: get_page_unless_zero() never
     succeed on tail pages.
 
   - map/unmap of the pages with PTE entry increment/decrement ->_mapcount
@@ -426,15 +426,15 @@ requests to split pinned huge page: it expects page count to be equal to
 sum of mapcount of all sub-pages plus one (split_huge_page caller must
 have reference for head page).
 
-split_huge_page uses migration entries to stabilize page->_count and
+split_huge_page uses migration entries to stabilize page->_refcount and
 page->_mapcount.
 
 We safe against physical memory scanners too: the only legitimate way
 scanner can get reference to a page is get_page_unless_zero().
 
-All tail pages has zero ->_count until atomic_add(). It prevent scanner
+All tail pages has zero ->_refcount until atomic_add(). It prevent scanner
 from geting reference to tail page up to the point. After the atomic_add()
-we don't care about ->_count value.  We already known how many references
+we don't care about ->_refcount value.  We already known how many references
 with should uncharge from head page.
 
 For head page get_page_unless_zero() will succeed and we don't mind. It's

arch/arc/include/asm/hugepage.h

@@ -61,8 +61,6 @@ static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 extern void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
 				 pmd_t *pmd);
 
-#define has_transparent_hugepage() 1
-
 /* Generic variants assume pgtable_t is struct page *, hence need for these */
 #define __HAVE_ARCH_PGTABLE_DEPOSIT
 extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,

arch/arm/include/asm/pgtable-3level.h

@@ -281,11 +281,6 @@ static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 	flush_pmd_entry(pmdp);
 }
 
-static inline int has_transparent_hugepage(void)
-{
-	return 1;
-}
-
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_PGTABLE_3LEVEL_H */

arch/arm64/include/asm/pgtable.h

@@ -316,11 +316,6 @@ static inline int pmd_protnone(pmd_t pmd)
 
 #define set_pmd_at(mm, addr, pmdp, pmd)	set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd))
 
-static inline int has_transparent_hugepage(void)
-{
-	return 1;
-}
-
 #define __pgprot_modify(prot,mask,bits) \
 	__pgprot((pgprot_val(prot) & ~(mask)) | (bits))
 

arch/arm64/mm/hugetlbpage.c

@@ -307,6 +307,7 @@ static __init int setup_hugepagesz(char *opt)
 	} else if (ps == PUD_SIZE) {
 		hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
 	} else {
+		hugetlb_bad_size();
 		pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10);
 		return 0;
 	}

arch/metag/mm/hugetlbpage.c

@@ -239,6 +239,7 @@ static __init int setup_hugepagesz(char *opt)
 	if (ps == (1 << HPAGE_SHIFT)) {
 		hugetlb_add_hstate(HPAGE_SHIFT - PAGE_SHIFT);
 	} else {
+		hugetlb_bad_size();
 		pr_err("hugepagesz: Unsupported page size %lu M\n",
 		       ps >> 20);
 		return 0;

arch/mips/include/asm/pgtable.h

@@ -533,6 +533,7 @@ static inline int io_remap_pfn_range(struct vm_area_struct *vma,
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 
+#define has_transparent_hugepage has_transparent_hugepage
 extern int has_transparent_hugepage(void);
 
 static inline int pmd_trans_huge(pmd_t pmd)

arch/mips/mm/tlb-r4k.c

@@ -405,19 +405,20 @@ void add_wired_entry(unsigned long entrylo0, unsigned long entrylo1,
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 
-int __init has_transparent_hugepage(void)
+int has_transparent_hugepage(void)
 {
-	unsigned int mask;
-	unsigned long flags;
-
-	local_irq_save(flags);
-	write_c0_pagemask(PM_HUGE_MASK);
-	back_to_back_c0_hazard();
-	mask = read_c0_pagemask();
-	write_c0_pagemask(PM_DEFAULT_MASK);
+	static unsigned int mask = -1;
 
-	local_irq_restore(flags);
+	if (mask == -1) {	/* first call comes during __init */
+		unsigned long flags;
 
+		local_irq_save(flags);
+		write_c0_pagemask(PM_HUGE_MASK);
+		back_to_back_c0_hazard();
+		mask = read_c0_pagemask();
+		write_c0_pagemask(PM_DEFAULT_MASK);
+		local_irq_restore(flags);
+	}
 	return mask == PM_HUGE_MASK;
 }
 

arch/powerpc/include/asm/book3s/64/pgtable.h

@@ -219,6 +219,7 @@ extern void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 		       pmd_t *pmdp, pmd_t pmd);
 extern void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
 				 pmd_t *pmd);
+#define has_transparent_hugepage has_transparent_hugepage
 extern int has_transparent_hugepage(void);
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 

arch/powerpc/include/asm/pgtable.h

@@ -65,7 +65,6 @@ extern int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
 		       struct page **pages, int *nr);
 #ifndef CONFIG_TRANSPARENT_HUGEPAGE
 #define pmd_large(pmd)		0
-#define has_transparent_hugepage() 0
 #endif
 pte_t *__find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
 				   bool *is_thp, unsigned *shift);

arch/powerpc/mm/hugetlbpage.c

@@ -772,8 +772,10 @@ static int __init hugepage_setup_sz(char *str)
 
 	size = memparse(str, &str);
 
-	if (add_huge_page_size(size) != 0)
-		printk(KERN_WARNING "Invalid huge page size specified(%llu)\n", size);
+	if (add_huge_page_size(size) != 0) {
+		hugetlb_bad_size();
+		pr_err("Invalid huge page size specified(%llu)\n", size);
+	}
 
 	return 1;
 }

arch/s390/include/asm/pgtable.h

@@ -1223,6 +1223,7 @@ static inline int pmd_trans_huge(pmd_t pmd)
 	return pmd_val(pmd) & _SEGMENT_ENTRY_LARGE;
 }
 
+#define has_transparent_hugepage has_transparent_hugepage
 static inline int has_transparent_hugepage(void)
 {
 	return MACHINE_HAS_HPAGE ? 1 : 0;

arch/sparc/include/asm/pgtable_64.h

@@ -681,8 +681,6 @@ static inline unsigned long pmd_trans_huge(pmd_t pmd)
 	return pte_val(pte) & _PAGE_PMD_HUGE;
 }
 
-#define has_transparent_hugepage() 1
-
 static inline pmd_t pmd_mkold(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));

arch/tile/include/asm/pgtable.h

@@ -487,7 +487,6 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-#define has_transparent_hugepage() 1
 #define pmd_trans_huge pmd_huge_page
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 

arch/tile/kernel/setup.c

@@ -962,9 +962,7 @@ static void __init setup_numa_mapping(void)
 		cpumask_set_cpu(best_cpu, &node_2_cpu_mask[node]);
 		cpu_2_node[best_cpu] = node;
 		cpumask_clear_cpu(best_cpu, &unbound_cpus);
-		node = next_node(node, default_nodes);
-		if (node == MAX_NUMNODES)
-			node = first_node(default_nodes);
+		node = next_node_in(node, default_nodes);
 	}
 
 	/* Print out node assignments and set defaults for disabled cpus */

arch/tile/mm/hugetlbpage.c

@@ -308,11 +308,16 @@ static bool saw_hugepagesz;
 
 static __init int setup_hugepagesz(char *opt)
 {
+	int rc;
+
 	if (!saw_hugepagesz) {
 		saw_hugepagesz = true;
 		memset(huge_shift, 0, sizeof(huge_shift));
 	}
-	return __setup_hugepagesz(memparse(opt, NULL));
+	rc = __setup_hugepagesz(memparse(opt, NULL));
+	if (rc)
+		hugetlb_bad_size();
+	return rc;
 }
 __setup("hugepagesz=", setup_hugepagesz);
 

arch/tile/mm/init.c

@@ -679,7 +679,7 @@ static void __init init_free_pfn_range(unsigned long start, unsigned long end)
 			 * Hacky direct set to avoid unnecessary
 			 * lock take/release for EVERY page here.
 			 */
-			p->_count.counter = 0;
+			p->_refcount.counter = 0;
 			p->_mapcount.counter = -1;
 		}
 		init_page_count(page);

arch/x86/include/asm/pgtable.h

@@ -181,6 +181,7 @@ static inline int pmd_trans_huge(pmd_t pmd)
 	return (pmd_val(pmd) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE;
 }
 
+#define has_transparent_hugepage has_transparent_hugepage
 static inline int has_transparent_hugepage(void)
 {
 	return boot_cpu_has(X86_FEATURE_PSE);

arch/x86/mm/hugetlbpage.c

@@ -165,6 +165,7 @@ static __init int setup_hugepagesz(char *opt)
 	} else if (ps == PUD_SIZE && boot_cpu_has(X86_FEATURE_GBPAGES)) {
 		hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
 	} else {
+		hugetlb_bad_size();
 		printk(KERN_ERR "hugepagesz: Unsupported page size %lu M\n",
 			ps >> 20);
 		return 0;

arch/x86/mm/numa.c

@@ -617,9 +617,7 @@ static void __init numa_init_array(void)
 		if (early_cpu_to_node(i) != NUMA_NO_NODE)
 			continue;
 		numa_set_node(i, rr);
-		rr = next_node(rr, node_online_map);
-		if (rr == MAX_NUMNODES)
-			rr = first_node(node_online_map);
+		rr = next_node_in(rr, node_online_map);
 	}
 }
 

drivers/block/aoe/aoecmd.c

@@ -861,7 +861,7 @@ rqbiocnt(struct request *r)
  * discussion.
  *
  * We cannot use get_page in the workaround, because it insists on a
- * positive page count as a precondition.  So we use _count directly.
+ * positive page count as a precondition.  So we use _refcount directly.
  */
 static void
 bio_pageinc(struct bio *bio)

drivers/hwtracing/intel_th/msu.c

@@ -1164,7 +1164,7 @@ static void msc_mmap_close(struct vm_area_struct *vma)
 	if (!atomic_dec_and_mutex_lock(&msc->mmap_count, &msc->buf_mutex))
 		return;
 
-	/* drop page _counts */
+	/* drop page _refcounts */
 	for (pg = 0; pg < msc->nr_pages; pg++) {
 		struct page *page = msc_buffer_get_page(msc, pg);
 

drivers/media/usb/dvb-usb/dib0700_core.c

@@ -517,7 +517,7 @@ int dib0700_download_firmware(struct usb_device *udev, const struct firmware *fw
 	if (nb_packet_buffer_size < 1)
 		nb_packet_buffer_size = 1;
 
-	/* get the fimware version */
+	/* get the firmware version */
 	usb_control_msg(udev, usb_rcvctrlpipe(udev, 0),
 				  REQUEST_GET_VERSION,
 				  USB_TYPE_VENDOR | USB_DIR_IN, 0, 0,