Merge branch 'WIP.sched/core' into sched/core

 Conflicts:
	kernel/sched/Makefile

Pick up the waitqueue related renames - it didn't get much feedback,
so it appears to be uncontroversial. Famous last words? ;-)

Signed-off-by: Ingo Molnar <mingo@kernel.org>

18 files changed, 227 insertions, 171 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 6f1be573a5e6..926484561624 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -768,10 +768,10 @@ struct wait_page_key {
 struct wait_page_queue {
 	struct page *page;
 	int bit_nr;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 };
 
-static int wake_page_function(wait_queue_t *wait, unsigned mode, int sync, void *arg)
+static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg)
 {
 	struct wait_page_key *key = arg;
 	struct wait_page_queue *wait_page
@@ -834,7 +834,7 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q,
 		struct page *page, int bit_nr, int state, bool lock)
 {
 	struct wait_page_queue wait_page;
-	wait_queue_t *wait = &wait_page.wait;
+	wait_queue_entry_t *wait = &wait_page.wait;
 	int ret = 0;
 
 	init_wait(wait);
@@ -845,9 +845,9 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q,
 	for (;;) {
 		spin_lock_irq(&q->lock);
 
-		if (likely(list_empty(&wait->task_list))) {
+		if (likely(list_empty(&wait->entry))) {
 			if (lock)
-				__add_wait_queue_tail_exclusive(q, wait);
+				__add_wait_queue_entry_tail_exclusive(q, wait);
 			else
 				__add_wait_queue(q, wait);
 			SetPageWaiters(page);
@@ -907,7 +907,7 @@ int wait_on_page_bit_killable(struct page *page, int bit_nr)
  *
  * Add an arbitrary @waiter to the wait queue for the nominated @page.
  */
-void add_page_wait_queue(struct page *page, wait_queue_t *waiter)
+void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter)
 {
 	wait_queue_head_t *q = page_waitqueue(page);
 	unsigned long flags;
diff --git a/mm/gup.c b/mm/gup.c
index d9e6fddcc51f..576c4df58882 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -387,11 +387,6 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
 	/* mlock all present pages, but do not fault in new pages */
 	if ((*flags & (FOLL_POPULATE | FOLL_MLOCK)) == FOLL_MLOCK)
 		return -ENOENT;
-	/* For mm_populate(), just skip the stack guard page. */
-	if ((*flags & FOLL_POPULATE) &&
-			(stack_guard_page_start(vma, address) ||
-			 stack_guard_page_end(vma, address + PAGE_SIZE)))
-		return -ENOENT;
 	if (*flags & FOLL_WRITE)
 		fault_flags |= FAULT_FLAG_WRITE;
 	if (*flags & FOLL_REMOTE)
@@ -407,12 +402,10 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
 
 	ret = handle_mm_fault(vma, address, fault_flags);
 	if (ret & VM_FAULT_ERROR) {
-		if (ret & VM_FAULT_OOM)
-			return -ENOMEM;
-		if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE))
-			return *flags & FOLL_HWPOISON ? -EHWPOISON : -EFAULT;
-		if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV))
-			return -EFAULT;
+		int err = vm_fault_to_errno(ret, *flags);
+
+		if (err)
+			return err;
 		BUG();
 	}
 
@@ -723,12 +716,10 @@ retry:
 	ret = handle_mm_fault(vma, address, fault_flags);
 	major |= ret & VM_FAULT_MAJOR;
 	if (ret & VM_FAULT_ERROR) {
-		if (ret & VM_FAULT_OOM)
-			return -ENOMEM;
-		if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE))
-			return -EHWPOISON;
-		if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV))
-			return -EFAULT;
+		int err = vm_fault_to_errno(ret, 0);
+
+		if (err)
+			return err;
 		BUG();
 	}
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index a84909cf20d3..88c6167f194d 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1426,8 +1426,11 @@ int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd)
 	 */
 	if (unlikely(pmd_trans_migrating(*vmf->pmd))) {
 		page = pmd_page(*vmf->pmd);
+		if (!get_page_unless_zero(page))
+			goto out_unlock;
 		spin_unlock(vmf->ptl);
 		wait_on_page_locked(page);
+		put_page(page);
 		goto out;
 	}
 
@@ -1459,9 +1462,12 @@ int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd)
 
 	/* Migration could have started since the pmd_trans_migrating check */
 	if (!page_locked) {
+		page_nid = -1;
+		if (!get_page_unless_zero(page))
+			goto out_unlock;
 		spin_unlock(vmf->ptl);
 		wait_on_page_locked(page);
-		page_nid = -1;
+		put_page(page);
 		goto out;
 	}
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index e5828875f7bb..3eedb187e549 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4170,6 +4170,11 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			}
 			ret = hugetlb_fault(mm, vma, vaddr, fault_flags);
 			if (ret & VM_FAULT_ERROR) {
+				int err = vm_fault_to_errno(ret, flags);
+
+				if (err)
+					return err;
+
 				remainder = 0;
 				break;
 			}
diff --git a/mm/ksm.c b/mm/ksm.c
index d9fc0e456128..216184af0e19 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1028,8 +1028,7 @@ static int try_to_merge_one_page(struct vm_area_struct *vma,
 		goto out;
 
 	if (PageTransCompound(page)) {
-		err = split_huge_page(page);
-		if (err)
+		if (split_huge_page(page))
 			goto out_unlock;
 	}
 
diff --git a/mm/memblock.c b/mm/memblock.c
index b049c9b2dba8..7b8a5db76a2f 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1739,6 +1739,29 @@ static void __init_memblock memblock_dump(struct memblock_type *type)
 	}
 }
 
+extern unsigned long __init_memblock
+memblock_reserved_memory_within(phys_addr_t start_addr, phys_addr_t end_addr)
+{
+	struct memblock_region *rgn;
+	unsigned long size = 0;
+	int idx;
+
+	for_each_memblock_type((&memblock.reserved), rgn) {
+		phys_addr_t start, end;
+
+		if (rgn->base + rgn->size < start_addr)
+			continue;
+		if (rgn->base > end_addr)
+			continue;
+
+		start = rgn->base;
+		end = start + rgn->size;
+		size += end - start;
+	}
+
+	return size;
+}
+
 void __init_memblock __memblock_dump_all(void)
 {
 	pr_info("MEMBLOCK configuration:\n");
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 94172089f52f..d75b38b66ef6 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -170,7 +170,7 @@ struct mem_cgroup_event {
 	 */
 	poll_table pt;
 	wait_queue_head_t *wqh;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 	struct work_struct remove;
 };
 
@@ -1479,10 +1479,10 @@ static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq);
 
 struct oom_wait_info {
 	struct mem_cgroup *memcg;
-	wait_queue_t	wait;
+	wait_queue_entry_t	wait;
 };
 
-static int memcg_oom_wake_function(wait_queue_t *wait,
+static int memcg_oom_wake_function(wait_queue_entry_t *wait,
 	unsigned mode, int sync, void *arg)
 {
 	struct mem_cgroup *wake_memcg = (struct mem_cgroup *)arg;
@@ -1570,7 +1570,7 @@ bool mem_cgroup_oom_synchronize(bool handle)
 	owait.wait.flags = 0;
 	owait.wait.func = memcg_oom_wake_function;
 	owait.wait.private = current;
-	INIT_LIST_HEAD(&owait.wait.task_list);
+	INIT_LIST_HEAD(&owait.wait.entry);
 
 	prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE);
 	mem_cgroup_mark_under_oom(memcg);
@@ -3725,7 +3725,7 @@ static void memcg_event_remove(struct work_struct *work)
  *
  * Called with wqh->lock held and interrupts disabled.
  */
-static int memcg_event_wake(wait_queue_t *wait, unsigned mode,
+static int memcg_event_wake(wait_queue_entry_t *wait, unsigned mode,
 			    int sync, void *key)
 {
 	struct mem_cgroup_event *event =
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 2527dfeddb00..ecc183fd94f3 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1184,7 +1184,10 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	 * page_remove_rmap() in try_to_unmap_one(). So to determine page status
 	 * correctly, we save a copy of the page flags at this time.
 	 */
-	page_flags = p->flags;
+	if (PageHuge(p))
+		page_flags = hpage->flags;
+	else
+		page_flags = p->flags;
 
 	/*
 	 * unpoison always clear PG_hwpoison inside page lock
@@ -1595,12 +1598,8 @@ static int soft_offline_huge_page(struct page *page, int flags)
 	if (ret) {
 		pr_info("soft offline: %#lx: migration failed %d, type %lx (%pGp)\n",
 			pfn, ret, page->flags, &page->flags);
-		/*
-		 * We know that soft_offline_huge_page() tries to migrate
-		 * only one hugepage pointed to by hpage, so we need not
-		 * run through the pagelist here.
-		 */
-		putback_active_hugepage(hpage);
+		if (!list_empty(&pagelist))
+			putback_movable_pages(&pagelist);
 		if (ret > 0)
 			ret = -EIO;
 	} else {
diff --git a/mm/memory.c b/mm/memory.c
index 6ff5d729ded0..bb11c474857e 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2855,40 +2855,6 @@ out_release:
 }
 
 /*
- * This is like a special single-page "expand_{down|up}wards()",
- * except we must first make sure that 'address{-|+}PAGE_SIZE'
- * doesn't hit another vma.
- */
-static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned long address)
-{
-	address &= PAGE_MASK;
-	if ((vma->vm_flags & VM_GROWSDOWN) && address == vma->vm_start) {
-		struct vm_area_struct *prev = vma->vm_prev;
-
-		/*
-		 * Is there a mapping abutting this one below?
-		 *
-		 * That's only ok if it's the same stack mapping
-		 * that has gotten split..
-		 */
-		if (prev && prev->vm_end == address)
-			return prev->vm_flags & VM_GROWSDOWN ? 0 : -ENOMEM;
-
-		return expand_downwards(vma, address - PAGE_SIZE);
-	}
-	if ((vma->vm_flags & VM_GROWSUP) && address + PAGE_SIZE == vma->vm_end) {
-		struct vm_area_struct *next = vma->vm_next;
-
-		/* As VM_GROWSDOWN but s/below/above/ */
-		if (next && next->vm_start == address + PAGE_SIZE)
-			return next->vm_flags & VM_GROWSUP ? 0 : -ENOMEM;
-
-		return expand_upwards(vma, address + PAGE_SIZE);
-	}
-	return 0;
-}
-
-/*
  * We enter with non-exclusive mmap_sem (to exclude vma changes,
  * but allow concurrent faults), and pte mapped but not yet locked.
  * We return with mmap_sem still held, but pte unmapped and unlocked.
@@ -2904,10 +2870,6 @@ static int do_anonymous_page(struct vm_fault *vmf)
 	if (vma->vm_flags & VM_SHARED)
 		return VM_FAULT_SIGBUS;
 
-	/* Check if we need to add a guard page to the stack */
-	if (check_stack_guard_page(vma, vmf->address) < 0)
-		return VM_FAULT_SIGSEGV;
-
 	/*
 	 * Use pte_alloc() instead of pte_alloc_map().  We can't run
 	 * pte_offset_map() on pmds where a huge pmd might be created
@@ -3029,6 +2991,17 @@ static int __do_fault(struct vm_fault *vmf)
 	return ret;
 }
 
+/*
+ * The ordering of these checks is important for pmds with _PAGE_DEVMAP set.
+ * If we check pmd_trans_unstable() first we will trip the bad_pmd() check
+ * inside of pmd_none_or_trans_huge_or_clear_bad(). This will end up correctly
+ * returning 1 but not before it spams dmesg with the pmd_clear_bad() output.
+ */
+static int pmd_devmap_trans_unstable(pmd_t *pmd)
+{
+	return pmd_devmap(*pmd) || pmd_trans_unstable(pmd);
+}
+
 static int pte_alloc_one_map(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
@@ -3052,18 +3025,27 @@ static int pte_alloc_one_map(struct vm_fault *vmf)
 map_pte:
 	/*
 	 * If a huge pmd materialized under us just retry later.  Use
-	 * pmd_trans_unstable() instead of pmd_trans_huge() to ensure the pmd
-	 * didn't become pmd_trans_huge under us and then back to pmd_none, as
-	 * a result of MADV_DONTNEED running immediately after a huge pmd fault
-	 * in a different thread of this mm, in turn leading to a misleading
-	 * pmd_trans_huge() retval.  All we have to ensure is that it is a
-	 * regular pmd that we can walk with pte_offset_map() and we can do that
-	 * through an atomic read in C, which is what pmd_trans_unstable()
-	 * provides.
+	 * pmd_trans_unstable() via pmd_devmap_trans_unstable() instead of
+	 * pmd_trans_huge() to ensure the pmd didn't become pmd_trans_huge
+	 * under us and then back to pmd_none, as a result of MADV_DONTNEED
+	 * running immediately after a huge pmd fault in a different thread of
+	 * this mm, in turn leading to a misleading pmd_trans_huge() retval.
+	 * All we have to ensure is that it is a regular pmd that we can walk
+	 * with pte_offset_map() and we can do that through an atomic read in
+	 * C, which is what pmd_trans_unstable() provides.
 	 */
-	if (pmd_trans_unstable(vmf->pmd) || pmd_devmap(*vmf->pmd))
+	if (pmd_devmap_trans_unstable(vmf->pmd))
 		return VM_FAULT_NOPAGE;
 
+	/*
+	 * At this point we know that our vmf->pmd points to a page of ptes
+	 * and it cannot become pmd_none(), pmd_devmap() or pmd_trans_huge()
+	 * for the duration of the fault.  If a racing MADV_DONTNEED runs and
+	 * we zap the ptes pointed to by our vmf->pmd, the vmf->ptl will still
+	 * be valid and we will re-check to make sure the vmf->pte isn't
+	 * pte_none() under vmf->ptl protection when we return to
+	 * alloc_set_pte().
+	 */
 	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
 			&vmf->ptl);
 	return 0;
@@ -3690,7 +3672,7 @@ static int handle_pte_fault(struct vm_fault *vmf)
 		vmf->pte = NULL;
 	} else {
 		/* See comment in pte_alloc_one_map() */
-		if (pmd_trans_unstable(vmf->pmd) || pmd_devmap(*vmf->pmd))
+		if (pmd_devmap_trans_unstable(vmf->pmd))
 			return 0;
 		/*
 		 * A regular pmd is established and it can't morph into a huge
diff --git a/mm/mempool.c b/mm/mempool.c
index 47a659dedd44..1c0294858527 100644
--- a/mm/mempool.c
+++ b/mm/mempool.c
@@ -312,7 +312,7 @@ void *mempool_alloc(mempool_t *pool, gfp_t gfp_mask)
 {
 	void *element;
 	unsigned long flags;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 	gfp_t gfp_temp;
 
 	VM_WARN_ON_ONCE(gfp_mask & __GFP_ZERO);
diff --git a/mm/mlock.c b/mm/mlock.c
index c483c5c20b4b..b562b5523a65 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -284,7 +284,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 {
 	int i;
 	int nr = pagevec_count(pvec);
-	int delta_munlocked;
+	int delta_munlocked = -nr;
 	struct pagevec pvec_putback;
 	int pgrescued = 0;
 
@@ -304,6 +304,8 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 				continue;
 			else
 				__munlock_isolation_failed(page);
+		} else {
+			delta_munlocked++;
 		}
 
 		/*
@@ -315,7 +317,6 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 		pagevec_add(&pvec_putback, pvec->pages[i]);
 		pvec->pages[i] = NULL;
 	}
-	delta_munlocked = -nr + pagevec_count(&pvec_putback);
 	__mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
 	spin_unlock_irq(zone_lru_lock(zone));
 
diff --git a/mm/mmap.c b/mm/mmap.c
index f82741e199c0..8e07976d5e47 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -183,6 +183,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
 	unsigned long retval;
 	unsigned long newbrk, oldbrk;
 	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *next;
 	unsigned long min_brk;
 	bool populate;
 	LIST_HEAD(uf);
@@ -229,7 +230,8 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
 	}
 
 	/* Check against existing mmap mappings. */
-	if (find_vma_intersection(mm, oldbrk, newbrk+PAGE_SIZE))
+	next = find_vma(mm, oldbrk);
+	if (next && newbrk + PAGE_SIZE > vm_start_gap(next))
 		goto out;
 
 	/* Ok, looks good - let it rip. */
@@ -253,10 +255,22 @@ out:
 
 static long vma_compute_subtree_gap(struct vm_area_struct *vma)
 {
-	unsigned long max, subtree_gap;
-	max = vma->vm_start;
-	if (vma->vm_prev)
-		max -= vma->vm_prev->vm_end;
+	unsigned long max, prev_end, subtree_gap;
+
+	/*
+	 * Note: in the rare case of a VM_GROWSDOWN above a VM_GROWSUP, we
+	 * allow two stack_guard_gaps between them here, and when choosing
+	 * an unmapped area; whereas when expanding we only require one.
+	 * That's a little inconsistent, but keeps the code here simpler.
+	 */
+	max = vm_start_gap(vma);
+	if (vma->vm_prev) {
+		prev_end = vm_end_gap(vma->vm_prev);
+		if (max > prev_end)
+			max -= prev_end;
+		else
+			max = 0;
+	}
 	if (vma->vm_rb.rb_left) {
 		subtree_gap = rb_entry(vma->vm_rb.rb_left,
 				struct vm_area_struct, vm_rb)->rb_subtree_gap;
@@ -352,7 +366,7 @@ static void validate_mm(struct mm_struct *mm)
 			anon_vma_unlock_read(anon_vma);
 		}
 
-		highest_address = vma->vm_end;
+		highest_address = vm_end_gap(vma);
 		vma = vma->vm_next;
 		i++;
 	}
@@ -541,7 +555,7 @@ void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (vma->vm_next)
 		vma_gap_update(vma->vm_next);
 	else
-		mm->highest_vm_end = vma->vm_end;
+		mm->highest_vm_end = vm_end_gap(vma);
 
 	/*
 	 * vma->vm_prev wasn't known when we followed the rbtree to find the
@@ -856,7 +870,7 @@ again:
 			vma_gap_update(vma);
 		if (end_changed) {
 			if (!next)
-				mm->highest_vm_end = end;
+				mm->highest_vm_end = vm_end_gap(vma);
 			else if (!adjust_next)
 				vma_gap_update(next);
 		}
@@ -941,7 +955,7 @@ again:
 			 * mm->highest_vm_end doesn't need any update
 			 * in remove_next == 1 case.
 			 */
-			VM_WARN_ON(mm->highest_vm_end != end);
+			VM_WARN_ON(mm->highest_vm_end != vm_end_gap(vma));
 		}
 	}
 	if (insert && file)
@@ -1787,7 +1801,7 @@ unsigned long unmapped_area(struct vm_unmapped_area_info *info)
 
 	while (true) {
 		/* Visit left subtree if it looks promising */
-		gap_end = vma->vm_start;
+		gap_end = vm_start_gap(vma);
 		if (gap_end >= low_limit && vma->vm_rb.rb_left) {
 			struct vm_area_struct *left =
 				rb_entry(vma->vm_rb.rb_left,
@@ -1798,7 +1812,7 @@ unsigned long unmapped_area(struct vm_unmapped_area_info *info)
 			}
 		}
 
-		gap_start = vma->vm_prev ? vma->vm_prev->vm_end : 0;
+		gap_start = vma->vm_prev ? vm_end_gap(vma->vm_prev) : 0;
 check_current:
 		/* Check if current node has a suitable gap */
 		if (gap_start > high_limit)
@@ -1825,8 +1839,8 @@ check_current:
 			vma = rb_entry(rb_parent(prev),
 				       struct vm_area_struct, vm_rb);
 			if (prev == vma->vm_rb.rb_left) {
-				gap_start = vma->vm_prev->vm_end;
-				gap_end = vma->vm_start;
+				gap_start = vm_end_gap(vma->vm_prev);
+				gap_end = vm_start_gap(vma);
 				goto check_current;
 			}
 		}
@@ -1890,7 +1904,7 @@ unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info)
 
 	while (true) {
 		/* Visit right subtree if it looks promising */
-		gap_start = vma->vm_prev ? vma->vm_prev->vm_end : 0;
+		gap_start = vma->vm_prev ? vm_end_gap(vma->vm_prev) : 0;
 		if (gap_start <= high_limit && vma->vm_rb.rb_right) {
 			struct vm_area_struct *right =
 				rb_entry(vma->vm_rb.rb_right,
@@ -1903,7 +1917,7 @@ unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info)
 
 check_current:
 		/* Check if current node has a suitable gap */
-		gap_end = vma->vm_start;
+		gap_end = vm_start_gap(vma);
 		if (gap_end < low_limit)
 			return -ENOMEM;
 		if (gap_start <= high_limit && gap_end - gap_start >= length)
@@ -1929,7 +1943,7 @@ check_current:
 				       struct vm_area_struct, vm_rb);
 			if (prev == vma->vm_rb.rb_right) {
 				gap_start = vma->vm_prev ?
-					vma->vm_prev->vm_end : 0;
+					vm_end_gap(vma->vm_prev) : 0;
 				goto check_current;
 			}
 		}
@@ -1967,7 +1981,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 		unsigned long len, unsigned long pgoff, unsigned long flags)
 {
 	struct mm_struct *mm = current->mm;
-	struct vm_area_struct *vma;
+	struct vm_area_struct *vma, *prev;
 	struct vm_unmapped_area_info info;
 
 	if (len > TASK_SIZE - mmap_min_addr)
@@ -1978,9 +1992,10 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 
 	if (addr) {
 		addr = PAGE_ALIGN(addr);
-		vma = find_vma(mm, addr);
+		vma = find_vma_prev(mm, addr, &prev);
 		if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)) &&
+		    (!prev || addr >= vm_end_gap(prev)))
 			return addr;
 	}
 
@@ -2003,7 +2018,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 			  const unsigned long len, const unsigned long pgoff,
 			  const unsigned long flags)
 {
-	struct vm_area_struct *vma;
+	struct vm_area_struct *vma, *prev;
 	struct mm_struct *mm = current->mm;
 	unsigned long addr = addr0;
 	struct vm_unmapped_area_info info;
@@ -2018,9 +2033,10 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	/* requesting a specific address */
 	if (addr) {
 		addr = PAGE_ALIGN(addr);
-		vma = find_vma(mm, addr);
+		vma = find_vma_prev(mm, addr, &prev);
 		if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
-				(!vma || addr + len <= vma->vm_start))
+				(!vma || addr + len <= vm_start_gap(vma)) &&
+				(!prev || addr >= vm_end_gap(prev)))
 			return addr;
 	}
 
@@ -2155,21 +2171,19 @@ find_vma_prev(struct mm_struct *mm, unsigned long addr,
  * update accounting. This is shared with both the
  * grow-up and grow-down cases.
  */
-static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, unsigned long grow)
+static int acct_stack_growth(struct vm_area_struct *vma,
+			     unsigned long size, unsigned long grow)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	struct rlimit *rlim = current->signal->rlim;
-	unsigned long new_start, actual_size;
+	unsigned long new_start;
 
 	/* address space limit tests */
 	if (!may_expand_vm(mm, vma->vm_flags, grow))
 		return -ENOMEM;
 
 	/* Stack limit test */
-	actual_size = size;
-	if (size && (vma->vm_flags & (VM_GROWSUP | VM_GROWSDOWN)))
-		actual_size -= PAGE_SIZE;
-	if (actual_size > READ_ONCE(rlim[RLIMIT_STACK].rlim_cur))
+	if (size > READ_ONCE(rlim[RLIMIT_STACK].rlim_cur))
 		return -ENOMEM;
 
 	/* mlock limit tests */
@@ -2207,17 +2221,30 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns
 int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 {
 	struct mm_struct *mm = vma->vm_mm;
+	struct vm_area_struct *next;
+	unsigned long gap_addr;
 	int error = 0;
 
 	if (!(vma->vm_flags & VM_GROWSUP))
 		return -EFAULT;
 
 	/* Guard against wrapping around to address 0. */
-	if (address < PAGE_ALIGN(address+4))
-		address = PAGE_ALIGN(address+4);
-	else
+	address &= PAGE_MASK;
+	address += PAGE_SIZE;
+	if (!address)
 		return -ENOMEM;
 
+	/* Enforce stack_guard_gap */
+	gap_addr = address + stack_guard_gap;
+	if (gap_addr < address)
+		return -ENOMEM;
+	next = vma->vm_next;
+	if (next && next->vm_start < gap_addr) {
+		if (!(next->vm_flags & VM_GROWSUP))
+			return -ENOMEM;
+		/* Check that both stack segments have the same anon_vma? */
+	}
+
 	/* We must make sure the anon_vma is allocated. */
 	if (unlikely(anon_vma_prepare(vma)))
 		return -ENOMEM;
@@ -2261,7 +2288,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 				if (vma->vm_next)
 					vma_gap_update(vma->vm_next);
 				else
-					mm->highest_vm_end = address;
+					mm->highest_vm_end = vm_end_gap(vma);
 				spin_unlock(&mm->page_table_lock);
 
 				perf_event_mmap(vma);
@@ -2282,6 +2309,8 @@ int expand_downwards(struct vm_area_struct *vma,
 				   unsigned long address)
 {
 	struct mm_struct *mm = vma->vm_mm;
+	struct vm_area_struct *prev;
+	unsigned long gap_addr;
 	int error;
 
 	address &= PAGE_MASK;
@@ -2289,6 +2318,17 @@ int expand_downwards(struct vm_area_struct *vma,
 	if (error)
 		return error;
 
+	/* Enforce stack_guard_gap */
+	gap_addr = address - stack_guard_gap;
+	if (gap_addr > address)
+		return -ENOMEM;
+	prev = vma->vm_prev;
+	if (prev && prev->vm_end > gap_addr) {
+		if (!(prev->vm_flags & VM_GROWSDOWN))
+			return -ENOMEM;
+		/* Check that both stack segments have the same anon_vma? */
+	}
+
 	/* We must make sure the anon_vma is allocated. */
 	if (unlikely(anon_vma_prepare(vma)))
 		return -ENOMEM;
@@ -2343,28 +2383,25 @@ int expand_downwards(struct vm_area_struct *vma,
 	return error;
 }
 
-/*
- * Note how expand_stack() refuses to expand the stack all the way to
- * abut the next virtual mapping, *unless* that mapping itself is also
- * a stack mapping. We want to leave room for a guard page, after all
- * (the guard page itself is not added here, that is done by the
- * actual page faulting logic)
- *
- * This matches the behavior of the guard page logic (see mm/memory.c:
- * check_stack_guard_page()), which only allows the guard page to be
- * removed under these circumstances.
- */
+/* enforced gap between the expanding stack and other mappings. */
+unsigned long stack_guard_gap = 256UL<<PAGE_SHIFT;
+
+static int __init cmdline_parse_stack_guard_gap(char *p)
+{
+	unsigned long val;
+	char *endptr;
+
+	val = simple_strtoul(p, &endptr, 10);
+	if (!*endptr)
+		stack_guard_gap = val << PAGE_SHIFT;
+
+	return 0;
+}
+__setup("stack_guard_gap=", cmdline_parse_stack_guard_gap);
+
 #ifdef CONFIG_STACK_GROWSUP
 int expand_stack(struct vm_area_struct *vma, unsigned long address)
 {
-	struct vm_area_struct *next;
-
-	address &= PAGE_MASK;
-	next = vma->vm_next;
-	if (next && next->vm_start == address + PAGE_SIZE) {
-		if (!(next->vm_flags & VM_GROWSUP))
-			return -ENOMEM;
-	}
 	return expand_upwards(vma, address);
 }
 
@@ -2386,14 +2423,6 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr)
 #else
 int expand_stack(struct vm_area_struct *vma, unsigned long address)
 {
-	struct vm_area_struct *prev;
-
-	address &= PAGE_MASK;
-	prev = vma->vm_prev;
-	if (prev && prev->vm_end == address) {
-		if (!(prev->vm_flags & VM_GROWSDOWN))
-			return -ENOMEM;
-	}
 	return expand_downwards(vma, address);
 }
 
@@ -2491,7 +2520,7 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
 		vma->vm_prev = prev;
 		vma_gap_update(vma);
 	} else
-		mm->highest_vm_end = prev ? prev->vm_end : 0;
+		mm->highest_vm_end = prev ? vm_end_gap(prev) : 0;
 	tail_vma->vm_next = NULL;
 
 	/* Kill the cache */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index f9e450c6b6e4..2302f250d6b1 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -292,6 +292,26 @@ int page_group_by_mobility_disabled __read_mostly;
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
 static inline void reset_deferred_meminit(pg_data_t *pgdat)
 {
+	unsigned long max_initialise;
+	unsigned long reserved_lowmem;
+
+	/*
+	 * Initialise at least 2G of a node but also take into account that
+	 * two large system hashes that can take up 1GB for 0.25TB/node.
+	 */
+	max_initialise = max(2UL << (30 - PAGE_SHIFT),
+		(pgdat->node_spanned_pages >> 8));
+
+	/*
+	 * Compensate the all the memblock reservations (e.g. crash kernel)
+	 * from the initial estimation to make sure we will initialize enough
+	 * memory to boot.
+	 */
+	reserved_lowmem = memblock_reserved_memory_within(pgdat->node_start_pfn,
+			pgdat->node_start_pfn + max_initialise);
+	max_initialise += reserved_lowmem;
+
+	pgdat->static_init_size = min(max_initialise, pgdat->node_spanned_pages);
 	pgdat->first_deferred_pfn = ULONG_MAX;
 }
 
@@ -314,20 +334,11 @@ static inline bool update_defer_init(pg_data_t *pgdat,
 				unsigned long pfn, unsigned long zone_end,
 				unsigned long *nr_initialised)
 {
-	unsigned long max_initialise;
-
 	/* Always populate low zones for address-contrained allocations */
 	if (zone_end < pgdat_end_pfn(pgdat))
 		return true;
-	/*
-	 * Initialise at least 2G of a node but also take into account that
-	 * two large system hashes that can take up 1GB for 0.25TB/node.
-	 */
-	max_initialise = max(2UL << (30 - PAGE_SHIFT),
-		(pgdat->node_spanned_pages >> 8));
-
 	(*nr_initialised)++;
-	if ((*nr_initialised > max_initialise) &&
+	if ((*nr_initialised > pgdat->static_init_size) &&
 	    (pfn & (PAGES_PER_SECTION - 1)) == 0) {
 		pgdat->first_deferred_pfn = pfn;
 		return false;
@@ -3870,7 +3881,9 @@ retry:
 		goto got_pg;
 
 	/* Avoid allocations with no watermarks from looping endlessly */
-	if (test_thread_flag(TIF_MEMDIE))
+	if (test_thread_flag(TIF_MEMDIE) &&
+	    (alloc_flags == ALLOC_NO_WATERMARKS ||
+	     (gfp_mask & __GFP_NOMEMALLOC)))
 		goto nopage;
 
 	/* Retry as long as the OOM killer is making progress */
@@ -6136,7 +6149,6 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 	/* pg_data_t should be reset to zero when it's allocated */
 	WARN_ON(pgdat->nr_zones || pgdat->kswapd_classzone_idx);
 
-	reset_deferred_meminit(pgdat);
 	pgdat->node_id = nid;
 	pgdat->node_start_pfn = node_start_pfn;
 	pgdat->per_cpu_nodestats = NULL;
@@ -6158,6 +6170,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 		(unsigned long)pgdat->node_mem_map);
 #endif
 
+	reset_deferred_meminit(pgdat);
 	free_area_init_core(pgdat);
 }
 
diff --git a/mm/shmem.c b/mm/shmem.c
index e67d6ba4e98e..fdc413f82a99 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1902,10 +1902,10 @@ unlock:
  * entry unconditionally - even if something else had already woken the
  * target.
  */
-static int synchronous_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key)
+static int synchronous_wake_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
 {
 	int ret = default_wake_function(wait, mode, sync, key);
-	list_del_init(&wait->task_list);
+	list_del_init(&wait->entry);
 	return ret;
 }
 
@@ -2840,7 +2840,7 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 		spin_lock(&inode->i_lock);
 		inode->i_private = NULL;
 		wake_up_all(&shmem_falloc_waitq);
-		WARN_ON_ONCE(!list_empty(&shmem_falloc_waitq.task_list));
+		WARN_ON_ONCE(!list_empty(&shmem_falloc_waitq.head));
 		spin_unlock(&inode->i_lock);
 		error = 0;
 		goto out;
diff --git a/mm/slub.c b/mm/slub.c
index 57e5156f02be..7449593fca72 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -5512,6 +5512,7 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s)
 		char mbuf[64];
 		char *buf;
 		struct slab_attribute *attr = to_slab_attr(slab_attrs[i]);
+		ssize_t len;
 
 		if (!attr || !attr->store || !attr->show)
 			continue;
@@ -5536,8 +5537,9 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s)
 			buf = buffer;
 		}
 
-		attr->show(root_cache, buf);
-		attr->store(s, buf, strlen(buf));
+		len = attr->show(root_cache, buf);
+		if (len > 0)
+			attr->store(s, buf, len);
 	}
 
 	if (buffer)
diff --git a/mm/swap_cgroup.c b/mm/swap_cgroup.c
index ac6318a064d3..3405b4ee1757 100644
--- a/mm/swap_cgroup.c
+++ b/mm/swap_cgroup.c
@@ -48,6 +48,9 @@ static int swap_cgroup_prepare(int type)
 		if (!page)
 			goto not_enough_page;
 		ctrl->map[idx] = page;
+
+		if (!(idx % SWAP_CLUSTER_MAX))
+			cond_resched();
 	}
 	return 0;
 not_enough_page:
diff --git a/mm/util.c b/mm/util.c
index 464df3489903..26be6407abd7 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -357,8 +357,11 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node)
 	WARN_ON_ONCE((flags & GFP_KERNEL) != GFP_KERNEL);
 
 	/*
-	 * Make sure that larger requests are not too disruptive - no OOM
-	 * killer and no allocation failure warnings as we have a fallback
+	 * We want to attempt a large physically contiguous block first because
+	 * it is less likely to fragment multiple larger blocks and therefore
+	 * contribute to a long term fragmentation less than vmalloc fallback.
+	 * However make sure that larger requests are not too disruptive - no
+	 * OOM killer and no allocation failure warnings as we have a fallback.
 	 */
 	if (size > PAGE_SIZE) {
 		kmalloc_flags |= __GFP_NOWARN;
diff --git a/mm/vmpressure.c b/mm/vmpressure.c
index 6063581f705c..ce0618bfa8d0 100644
--- a/mm/vmpressure.c
+++ b/mm/vmpressure.c
@@ -115,9 +115,9 @@ static enum vmpressure_levels vmpressure_calc_level(unsigned long scanned,
 	unsigned long pressure = 0;
 
 	/*
-	 * reclaimed can be greater than scanned in cases
-	 * like THP, where the scanned is 1 and reclaimed
-	 * could be 512
+	 * reclaimed can be greater than scanned for things such as reclaimed
+	 * slab pages. shrink_node() just adds reclaimed pages without a
+	 * related increment to scanned pages.
 	 */
 	if (reclaimed >= scanned)
 		goto out;