Merge branch 'akpm' (patches from Andrew)

Merge fixes from Andrew Morton:
 "20 fixes"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  Documentation/sysctl/vm.txt: update numa_zonelist_order description
  lib/stackdepot.c: allow the stack trace hash to be zero
  rapidio: fix potential NULL pointer dereference
  mm/memory-failure: fix race with compound page split/merge
  ocfs2/dlm: return zero if deref_done message is successfully handled
  Ananth has moved
  kcov: don't profile branches in kcov
  kcov: don't trace the code coverage code
  mm: wake kcompactd before kswapd's short sleep
  .mailmap: add Frank Rowand
  mm/hwpoison: fix wrong num_poisoned_pages accounting
  mm: call swap_slot_free_notify() with page lock held
  mm: vmscan: reclaim highmem zone if buffer_heads is over limit
  numa: fix /proc/<pid>/numa_maps for THP
  mm/huge_memory: replace VM_NO_THP VM_BUG_ON with actual VMA check
  mailmap: fix Krzysztof Kozlowski's misspelled name
  thp: keep huge zero page pinned until tlb flush
  mm: exclude HugeTLB pages from THP page_mapped() logic
  kexec: export OFFSET(page.compound_head) to find out compound tail page
  kexec: update VMCOREINFO for compound_order/dtor

18 files changed, 151 insertions, 47 deletions

diff --git a/.mailmap b/.mailmap
index 90c0aefc276d..c156a8b4d845 100644
--- a/.mailmap
+++ b/.mailmap
@@ -48,6 +48,9 @@ Felix Kuhling <fxkuehl@gmx.de>
 Felix Moeller <felix@derklecks.de>
 Filipe Lautert <filipe@icewall.org>
 Franck Bui-Huu <vagabon.xyz@gmail.com>
+Frank Rowand <frowand.list@gmail.com> <frowand@mvista.com>
+Frank Rowand <frowand.list@gmail.com> <frank.rowand@am.sony.com>
+Frank Rowand <frowand.list@gmail.com> <frank.rowand@sonymobile.com>
 Frank Zago <fzago@systemfabricworks.com>
 Greg Kroah-Hartman <greg@echidna.(none)>
 Greg Kroah-Hartman <gregkh@suse.de>
@@ -79,6 +82,7 @@ Kay Sievers <kay.sievers@vrfy.org>
 Kenneth W Chen <kenneth.w.chen@intel.com>
 Konstantin Khlebnikov <koct9i@gmail.com> <k.khlebnikov@samsung.com>
 Koushik <raghavendra.koushik@neterion.com>
+Krzysztof Kozlowski <krzk@kernel.org> <k.kozlowski.k@gmail.com>
 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
 Leonid I Ananiev <leonid.i.ananiev@intel.com>
 Linas Vepstas <linas@austin.ibm.com>
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index cb0368459da3..34a5fece3121 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -581,15 +581,16 @@ Specify "[Nn]ode" for node order
 "Zone Order" orders the zonelists by zone type, then by node within each
 zone.  Specify "[Zz]one" for zone order.
 
-Specify "[Dd]efault" to request automatic configuration.  Autoconfiguration
-will select "node" order in following case.
-(1) if the DMA zone does not exist or
-(2) if the DMA zone comprises greater than 50% of the available memory or
-(3) if any node's DMA zone comprises greater than 70% of its local memory and
-    the amount of local memory is big enough.
-
-Otherwise, "zone" order will be selected. Default order is recommended unless
-this is causing problems for your system/application.
+Specify "[Dd]efault" to request automatic configuration.
+
+On 32-bit, the Normal zone needs to be preserved for allocations accessible
+by the kernel, so "zone" order will be selected.
+
+On 64-bit, devices that require DMA32/DMA are relatively rare, so "node"
+order will be selected.
+
+Default order is recommended unless this is causing problems for your
+system/application.
 
 ==============================================================
 
diff --git a/MAINTAINERS b/MAINTAINERS
index 849133608da7..7f72d54f065d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6400,7 +6400,7 @@ F:	mm/kmemleak.c
 F:	mm/kmemleak-test.c
 
 KPROBES
-M:	Ananth N Mavinakayanahalli <ananth@in.ibm.com>
+M:	Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
 M:	Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
 M:	"David S. Miller" <davem@davemloft.net>
 M:	Masami Hiramatsu <mhiramat@kernel.org>
diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c
index 5d4d91846357..96168b819044 100644
--- a/drivers/rapidio/devices/rio_mport_cdev.c
+++ b/drivers/rapidio/devices/rio_mport_cdev.c
@@ -2669,9 +2669,9 @@ static int __init mport_init(void)
 
 	/* Create device class needed by udev */
 	dev_class = class_create(THIS_MODULE, DRV_NAME);
-	if (!dev_class) {
+	if (IS_ERR(dev_class)) {
 		rmcd_error("Unable to create " DRV_NAME " class");
-		return -EINVAL;
+		return PTR_ERR(dev_class);
 	}
 
 	ret = alloc_chrdev_region(&dev_number, 0, RIO_MAX_MPORTS, DRV_NAME);
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 9aed6e202201..13719d3f35f8 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -2455,6 +2455,8 @@ int dlm_deref_lockres_done_handler(struct o2net_msg *msg, u32 len, void *data,
 
 	spin_unlock(&dlm->spinlock);
 
+	ret = 0;
+
 done:
 	dlm_put(dlm);
 	return ret;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 229cb546bee0..541583510cfb 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1518,6 +1518,32 @@ static struct page *can_gather_numa_stats(pte_t pte, struct vm_area_struct *vma,
 	return page;
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static struct page *can_gather_numa_stats_pmd(pmd_t pmd,
+					      struct vm_area_struct *vma,
+					      unsigned long addr)
+{
+	struct page *page;
+	int nid;
+
+	if (!pmd_present(pmd))
+		return NULL;
+
+	page = vm_normal_page_pmd(vma, addr, pmd);
+	if (!page)
+		return NULL;
+
+	if (PageReserved(page))
+		return NULL;
+
+	nid = page_to_nid(page);
+	if (!node_isset(nid, node_states[N_MEMORY]))
+		return NULL;
+
+	return page;
+}
+#endif
+
 static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 		unsigned long end, struct mm_walk *walk)
 {
@@ -1527,14 +1553,14 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 	pte_t *orig_pte;
 	pte_t *pte;
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	ptl = pmd_trans_huge_lock(pmd, vma);
 	if (ptl) {
-		pte_t huge_pte = *(pte_t *)pmd;
 		struct page *page;
 
-		page = can_gather_numa_stats(huge_pte, vma, addr);
+		page = can_gather_numa_stats_pmd(*pmd, vma, addr);
 		if (page)
-			gather_stats(page, md, pte_dirty(huge_pte),
+			gather_stats(page, md, pmd_dirty(*pmd),
 				     HPAGE_PMD_SIZE/PAGE_SIZE);
 		spin_unlock(ptl);
 		return 0;
@@ -1542,6 +1568,7 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 
 	if (pmd_trans_unstable(pmd))
 		return 0;
+#endif
 	orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
 	do {
 		struct page *page = can_gather_numa_stats(*pte, vma, addr);
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 7008623e24b1..d7b9e5346fba 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -152,6 +152,7 @@ static inline bool is_huge_zero_pmd(pmd_t pmd)
 }
 
 struct page *get_huge_zero_page(void);
+void put_huge_zero_page(void);
 
 #else /* CONFIG_TRANSPARENT_HUGEPAGE */
 #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; })
@@ -208,6 +209,10 @@ static inline bool is_huge_zero_page(struct page *page)
 	return false;
 }
 
+static inline void put_huge_zero_page(void)
+{
+	BUILD_BUG();
+}
 
 static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma,
 		unsigned long addr, pmd_t *pmd, int flags)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a55e5be0894f..864d7221de84 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1031,6 +1031,8 @@ static inline bool page_mapped(struct page *page)
 	page = compound_head(page);
 	if (atomic_read(compound_mapcount_ptr(page)) >= 0)
 		return true;
+	if (PageHuge(page))
+		return false;
 	for (i = 0; i < hpage_nr_pages(page); i++) {
 		if (atomic_read(&page[i]._mapcount) >= 0)
 			return true;
@@ -1138,6 +1140,8 @@ struct zap_details {
 
 struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
 		pte_t pte);
+struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,
+				pmd_t pmd);
 
 int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
 		unsigned long size);
diff --git a/kernel/kcov.c b/kernel/kcov.c
index 3efbee0834a8..a02f2dddd1d7 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -1,5 +1,6 @@
 #define pr_fmt(fmt) "kcov: " fmt
 
+#define DISABLE_BRANCH_PROFILING
 #include <linux/compiler.h>
 #include <linux/types.h>
 #include <linux/file.h>
@@ -43,7 +44,7 @@ struct kcov {
  * Entry point from instrumented code.
  * This is called once per basic-block/edge.
  */
-void __sanitizer_cov_trace_pc(void)
+void notrace __sanitizer_cov_trace_pc(void)
 {
 	struct task_struct *t;
 	enum kcov_mode mode;
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index 8d34308ea449..1391d3ee3b86 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -1415,6 +1415,9 @@ static int __init crash_save_vmcoreinfo_init(void)
 	VMCOREINFO_OFFSET(page, lru);
 	VMCOREINFO_OFFSET(page, _mapcount);
 	VMCOREINFO_OFFSET(page, private);
+	VMCOREINFO_OFFSET(page, compound_dtor);
+	VMCOREINFO_OFFSET(page, compound_order);
+	VMCOREINFO_OFFSET(page, compound_head);
 	VMCOREINFO_OFFSET(pglist_data, node_zones);
 	VMCOREINFO_OFFSET(pglist_data, nr_zones);
 #ifdef CONFIG_FLAT_NODE_MEM_MAP
@@ -1447,8 +1450,8 @@ static int __init crash_save_vmcoreinfo_init(void)
 #ifdef CONFIG_X86
 	VMCOREINFO_NUMBER(KERNEL_IMAGE_SIZE);
 #endif
-#ifdef CONFIG_HUGETLBFS
-	VMCOREINFO_SYMBOL(free_huge_page);
+#ifdef CONFIG_HUGETLB_PAGE
+	VMCOREINFO_NUMBER(HUGETLB_PAGE_DTOR);
 #endif
 
 	arch_crash_save_vmcoreinfo();
diff --git a/lib/stackdepot.c b/lib/stackdepot.c
index 654c9d87e83a..9e0b0315a724 100644
--- a/lib/stackdepot.c
+++ b/lib/stackdepot.c
@@ -210,10 +210,6 @@ depot_stack_handle_t depot_save_stack(struct stack_trace *trace,
 		goto fast_exit;
 
 	hash = hash_stack(trace->entries, trace->nr_entries);
-	/* Bad luck, we won't store this stack. */
-	if (hash == 0)
-		goto exit;
-
 	bucket = &stack_table[hash & STACK_HASH_MASK];
 
 	/*
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 86f9f8b82f8e..df67b53ae3c5 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -232,7 +232,7 @@ retry:
 	return READ_ONCE(huge_zero_page);
 }
 
-static void put_huge_zero_page(void)
+void put_huge_zero_page(void)
 {
 	/*
 	 * Counter should never go to zero here. Only shrinker can put
@@ -1684,12 +1684,12 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	if (vma_is_dax(vma)) {
 		spin_unlock(ptl);
 		if (is_huge_zero_pmd(orig_pmd))
-			put_huge_zero_page();
+			tlb_remove_page(tlb, pmd_page(orig_pmd));
 	} else if (is_huge_zero_pmd(orig_pmd)) {
 		pte_free(tlb->mm, pgtable_trans_huge_withdraw(tlb->mm, pmd));
 		atomic_long_dec(&tlb->mm->nr_ptes);
 		spin_unlock(ptl);
-		put_huge_zero_page();
+		tlb_remove_page(tlb, pmd_page(orig_pmd));
 	} else {
 		struct page *page = pmd_page(orig_pmd);
 		page_remove_rmap(page, true);
@@ -1960,10 +1960,9 @@ int khugepaged_enter_vma_merge(struct vm_area_struct *vma,
 		 * page fault if needed.
 		 */
 		return 0;
-	if (vma->vm_ops)
+	if (vma->vm_ops || (vm_flags & VM_NO_THP))
 		/* khugepaged not yet working on file or special mappings */
 		return 0;
-	VM_BUG_ON_VMA(vm_flags & VM_NO_THP, vma);
 	hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
 	hend = vma->vm_end & HPAGE_PMD_MASK;
 	if (hstart < hend)
@@ -2352,8 +2351,7 @@ static bool hugepage_vma_check(struct vm_area_struct *vma)
 		return false;
 	if (is_vma_temporary_stack(vma))
 		return false;
-	VM_BUG_ON_VMA(vma->vm_flags & VM_NO_THP, vma);
-	return true;
+	return !(vma->vm_flags & VM_NO_THP);
 }
 
 static void collapse_huge_page(struct mm_struct *mm,
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 78f5f2641b91..ca5acee53b7a 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -888,7 +888,15 @@ int get_hwpoison_page(struct page *page)
 		}
 	}
 
-	return get_page_unless_zero(head);
+	if (get_page_unless_zero(head)) {
+		if (head == compound_head(page))
+			return 1;
+
+		pr_info("MCE: %#lx cannot catch tail\n", page_to_pfn(page));
+		put_page(head);
+	}
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(get_hwpoison_page);
 
diff --git a/mm/memory.c b/mm/memory.c
index 93897f23cc11..305537fc8640 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -789,6 +789,46 @@ out:
 	return pfn_to_page(pfn);
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,
+				pmd_t pmd)
+{
+	unsigned long pfn = pmd_pfn(pmd);
+
+	/*
+	 * There is no pmd_special() but there may be special pmds, e.g.
+	 * in a direct-access (dax) mapping, so let's just replicate the
+	 * !HAVE_PTE_SPECIAL case from vm_normal_page() here.
+	 */
+	if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) {
+		if (vma->vm_flags & VM_MIXEDMAP) {
+			if (!pfn_valid(pfn))
+				return NULL;
+			goto out;
+		} else {
+			unsigned long off;
+			off = (addr - vma->vm_start) >> PAGE_SHIFT;
+			if (pfn == vma->vm_pgoff + off)
+				return NULL;
+			if (!is_cow_mapping(vma->vm_flags))
+				return NULL;
+		}
+	}
+
+	if (is_zero_pfn(pfn))
+		return NULL;
+	if (unlikely(pfn > highest_memmap_pfn))
+		return NULL;
+
+	/*
+	 * NOTE! We still have PageReserved() pages in the page tables.
+	 * eg. VDSO mappings can cause them to exist.
+	 */
+out:
+	return pfn_to_page(pfn);
+}
+#endif
+
 /*
  * copy one vm_area from one task to the other. Assumes the page tables
  * already present in the new task to be cleared in the whole range
diff --git a/mm/migrate.c b/mm/migrate.c
index 6c822a7b27e0..f9dfb18a4eba 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -975,7 +975,13 @@ out:
 		dec_zone_page_state(page, NR_ISOLATED_ANON +
 				page_is_file_cache(page));
 		/* Soft-offlined page shouldn't go through lru cache list */
-		if (reason == MR_MEMORY_FAILURE) {
+		if (reason == MR_MEMORY_FAILURE && rc == MIGRATEPAGE_SUCCESS) {
+			/*
+			 * With this release, we free successfully migrated
+			 * page and set PG_HWPoison on just freed page
+			 * intentionally. Although it's rather weird, it's how
+			 * HWPoison flag works at the moment.
+			 */
 			put_page(page);
 			if (!test_set_page_hwpoison(page))
 				num_poisoned_pages_inc();
diff --git a/mm/page_io.c b/mm/page_io.c
index cd92e3d67a32..985f23cfa79b 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -353,7 +353,11 @@ int swap_readpage(struct page *page)
 
 	ret = bdev_read_page(sis->bdev, swap_page_sector(page), page);
 	if (!ret) {
-		swap_slot_free_notify(page);
+		if (trylock_page(page)) {
+			swap_slot_free_notify(page);
+			unlock_page(page);
+		}
+
 		count_vm_event(PSWPIN);
 		return 0;
 	}
diff --git a/mm/swap.c b/mm/swap.c
index a0bc206b4ac6..03aacbcb013f 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -728,6 +728,11 @@ void release_pages(struct page **pages, int nr, bool cold)
 			zone = NULL;
 		}
 
+		if (is_huge_zero_page(page)) {
+			put_huge_zero_page();
+			continue;
+		}
+
 		page = compound_head(page);
 		if (!put_page_testzero(page))
 			continue;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b934223eaa45..142cb61f4822 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2553,7 +2553,7 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 		sc->gfp_mask |= __GFP_HIGHMEM;
 
 	for_each_zone_zonelist_nodemask(zone, z, zonelist,
-					requested_highidx, sc->nodemask) {
+					gfp_zone(sc->gfp_mask), sc->nodemask) {
 		enum zone_type classzone_idx;
 
 		if (!populated_zone(zone))
@@ -3318,6 +3318,20 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
 	/* Try to sleep for a short interval */
 	if (prepare_kswapd_sleep(pgdat, order, remaining,
 						balanced_classzone_idx)) {
+		/*
+		 * Compaction records what page blocks it recently failed to
+		 * isolate pages from and skips them in the future scanning.
+		 * When kswapd is going to sleep, it is reasonable to assume
+		 * that pages and compaction may succeed so reset the cache.
+		 */
+		reset_isolation_suitable(pgdat);
+
+		/*
+		 * We have freed the memory, now we should compact it to make
+		 * allocation of the requested order possible.
+		 */
+		wakeup_kcompactd(pgdat, order, classzone_idx);
+
 		remaining = schedule_timeout(HZ/10);
 		finish_wait(&pgdat->kswapd_wait, &wait);
 		prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
@@ -3341,20 +3355,6 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
 		 */
 		set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold);
 
-		/*
-		 * Compaction records what page blocks it recently failed to
-		 * isolate pages from and skips them in the future scanning.
-		 * When kswapd is going to sleep, it is reasonable to assume
-		 * that pages and compaction may succeed so reset the cache.
-		 */
-		reset_isolation_suitable(pgdat);
-
-		/*
-		 * We have freed the memory, now we should compact it to make
-		 * allocation of the requested order possible.
-		 */
-		wakeup_kcompactd(pgdat, order, classzone_idx);
-
 		if (!kthread_should_stop())
 			schedule();