Merge tag 'v3.14.10' into v3.14-rt

This is the 3.14.10 stable release

Signed-off-by: Anders Roxell <anders.roxell@linaro.org>

Conflicts:
	include/linux/irqdesc.h
	include/linux/thread_info.h
	kernel/irq/manage.c
	kernel/locking/rtmutex.c

13 files changed, 195 insertions, 82 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 64007ac64526..fc9125819598 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -263,6 +263,9 @@ config MIGRATION
 	  pages as migration can relocate pages to satisfy a huge page
 	  allocation instead of reclaiming.
 
+config ARCH_ENABLE_HUGEPAGE_MIGRATION
+	boolean
+
 config PHYS_ADDR_T_64BIT
 	def_bool 64BIT || ARCH_PHYS_ADDR_T_64BIT
 
diff --git a/mm/compaction.c b/mm/compaction.c
index 918577595ea8..5f702ef0a65f 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -666,16 +666,20 @@ static void isolate_freepages(struct zone *zone,
 				struct compact_control *cc)
 {
 	struct page *page;
-	unsigned long high_pfn, low_pfn, pfn, z_end_pfn, end_pfn;
+	unsigned long high_pfn, low_pfn, pfn, z_end_pfn;
 	int nr_freepages = cc->nr_freepages;
 	struct list_head *freelist = &cc->freepages;
 
 	/*
 	 * Initialise the free scanner. The starting point is where we last
-	 * scanned from (or the end of the zone if starting). The low point
-	 * is the end of the pageblock the migration scanner is using.
+	 * successfully isolated from, zone-cached value, or the end of the
+	 * zone when isolating for the first time. We need this aligned to
+	 * the pageblock boundary, because we do pfn -= pageblock_nr_pages
+	 * in the for loop.
+	 * The low boundary is the end of the pageblock the migration scanner
+	 * is using.
 	 */
-	pfn = cc->free_pfn;
+	pfn = cc->free_pfn & ~(pageblock_nr_pages-1);
 	low_pfn = ALIGN(cc->migrate_pfn + 1, pageblock_nr_pages);
 
 	/*
@@ -695,6 +699,7 @@ static void isolate_freepages(struct zone *zone,
 	for (; pfn >= low_pfn && cc->nr_migratepages > nr_freepages;
 					pfn -= pageblock_nr_pages) {
 		unsigned long isolated;
+		unsigned long end_pfn;
 
 		/*
 		 * This can iterate a massively long zone without finding any
@@ -729,13 +734,10 @@ static void isolate_freepages(struct zone *zone,
 		isolated = 0;
 
 		/*
-		 * As pfn may not start aligned, pfn+pageblock_nr_page
-		 * may cross a MAX_ORDER_NR_PAGES boundary and miss
-		 * a pfn_valid check. Ensure isolate_freepages_block()
-		 * only scans within a pageblock
+		 * Take care when isolating in last pageblock of a zone which
+		 * ends in the middle of a pageblock.
 		 */
-		end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
-		end_pfn = min(end_pfn, z_end_pfn);
+		end_pfn = min(pfn + pageblock_nr_pages, z_end_pfn);
 		isolated = isolate_freepages_block(cc, pfn, end_pfn,
 						   freelist, false);
 		nr_freepages += isolated;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 1546655a2d78..1c42d0c36d0b 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1611,16 +1611,23 @@ pmd_t *page_check_address_pmd(struct page *page,
 			      enum page_check_address_pmd_flag flag,
 			      spinlock_t **ptl)
 {
+	pgd_t *pgd;
+	pud_t *pud;
 	pmd_t *pmd;
 
 	if (address & ~HPAGE_PMD_MASK)
 		return NULL;
 
-	pmd = mm_find_pmd(mm, address);
-	if (!pmd)
+	pgd = pgd_offset(mm, address);
+	if (!pgd_present(*pgd))
 		return NULL;
+	pud = pud_offset(pgd, address);
+	if (!pud_present(*pud))
+		return NULL;
+	pmd = pmd_offset(pud, address);
+
 	*ptl = pmd_lock(mm, pmd);
-	if (pmd_none(*pmd))
+	if (!pmd_present(*pmd))
 		goto unlock;
 	if (pmd_page(*pmd) != page)
 		goto unlock;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 2de3c845f03a..06a9bc0a3120 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1134,6 +1134,7 @@ static void return_unused_surplus_pages(struct hstate *h,
 	while (nr_pages--) {
 		if (!free_pool_huge_page(h, &node_states[N_MEMORY], 1))
 			break;
+		cond_resched_lock(&hugetlb_lock);
 	}
 }
 
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 90002ea43638..33365e9ce6a7 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -208,9 +208,9 @@ static int kill_proc(struct task_struct *t, unsigned long addr, int trapno,
 #endif
 	si.si_addr_lsb = compound_order(compound_head(page)) + PAGE_SHIFT;
 
-	if ((flags & MF_ACTION_REQUIRED) && t == current) {
+	if ((flags & MF_ACTION_REQUIRED) && t->mm == current->mm) {
 		si.si_code = BUS_MCEERR_AR;
-		ret = force_sig_info(SIGBUS, &si, t);
+		ret = force_sig_info(SIGBUS, &si, current);
 	} else {
 		/*
 		 * Don't use force here, it's convenient if the signal
@@ -384,20 +384,51 @@ static void kill_procs(struct list_head *to_kill, int forcekill, int trapno,
 	}
 }
 
-static int task_early_kill(struct task_struct *tsk)
+/*
+ * Find a dedicated thread which is supposed to handle SIGBUS(BUS_MCEERR_AO)
+ * on behalf of the thread group. Return task_struct of the (first found)
+ * dedicated thread if found, and return NULL otherwise.
+ *
+ * We already hold read_lock(&tasklist_lock) in the caller, so we don't
+ * have to call rcu_read_lock/unlock() in this function.
+ */
+static struct task_struct *find_early_kill_thread(struct task_struct *tsk)
 {
+	struct task_struct *t;
+
+	for_each_thread(tsk, t)
+		if ((t->flags & PF_MCE_PROCESS) && (t->flags & PF_MCE_EARLY))
+			return t;
+	return NULL;
+}
+
+/*
+ * Determine whether a given process is "early kill" process which expects
+ * to be signaled when some page under the process is hwpoisoned.
+ * Return task_struct of the dedicated thread (main thread unless explicitly
+ * specified) if the process is "early kill," and otherwise returns NULL.
+ */
+static struct task_struct *task_early_kill(struct task_struct *tsk,
+					   int force_early)
+{
+	struct task_struct *t;
 	if (!tsk->mm)
-		return 0;
-	if (tsk->flags & PF_MCE_PROCESS)
-		return !!(tsk->flags & PF_MCE_EARLY);
-	return sysctl_memory_failure_early_kill;
+		return NULL;
+	if (force_early)
+		return tsk;
+	t = find_early_kill_thread(tsk);
+	if (t)
+		return t;
+	if (sysctl_memory_failure_early_kill)
+		return tsk;
+	return NULL;
 }
 
 /*
  * Collect processes when the error hit an anonymous page.
  */
 static void collect_procs_anon(struct page *page, struct list_head *to_kill,
-			      struct to_kill **tkc)
+			      struct to_kill **tkc, int force_early)
 {
 	struct vm_area_struct *vma;
 	struct task_struct *tsk;
@@ -412,16 +443,17 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
 	read_lock(&tasklist_lock);
 	for_each_process (tsk) {
 		struct anon_vma_chain *vmac;
+		struct task_struct *t = task_early_kill(tsk, force_early);
 
-		if (!task_early_kill(tsk))
+		if (!t)
 			continue;
 		anon_vma_interval_tree_foreach(vmac, &av->rb_root,
 					       pgoff, pgoff) {
 			vma = vmac->vma;
 			if (!page_mapped_in_vma(page, vma))
 				continue;
-			if (vma->vm_mm == tsk->mm)
-				add_to_kill(tsk, page, vma, to_kill, tkc);
+			if (vma->vm_mm == t->mm)
+				add_to_kill(t, page, vma, to_kill, tkc);
 		}
 	}
 	read_unlock(&tasklist_lock);
@@ -432,7 +464,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
  * Collect processes when the error hit a file mapped page.
  */
 static void collect_procs_file(struct page *page, struct list_head *to_kill,
-			      struct to_kill **tkc)
+			      struct to_kill **tkc, int force_early)
 {
 	struct vm_area_struct *vma;
 	struct task_struct *tsk;
@@ -442,10 +474,10 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 	read_lock(&tasklist_lock);
 	for_each_process(tsk) {
 		pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+		struct task_struct *t = task_early_kill(tsk, force_early);
 
-		if (!task_early_kill(tsk))
+		if (!t)
 			continue;
-
 		vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff,
 				      pgoff) {
 			/*
@@ -455,8 +487,8 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 			 * Assume applications who requested early kill want
 			 * to be informed of all such data corruptions.
 			 */
-			if (vma->vm_mm == tsk->mm)
-				add_to_kill(tsk, page, vma, to_kill, tkc);
+			if (vma->vm_mm == t->mm)
+				add_to_kill(t, page, vma, to_kill, tkc);
 		}
 	}
 	read_unlock(&tasklist_lock);
@@ -469,7 +501,8 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
  * First preallocate one tokill structure outside the spin locks,
  * so that we can kill at least one process reasonably reliable.
  */
-static void collect_procs(struct page *page, struct list_head *tokill)
+static void collect_procs(struct page *page, struct list_head *tokill,
+				int force_early)
 {
 	struct to_kill *tk;
 
@@ -480,9 +513,9 @@ static void collect_procs(struct page *page, struct list_head *tokill)
 	if (!tk)
 		return;
 	if (PageAnon(page))
-		collect_procs_anon(page, tokill, &tk);
+		collect_procs_anon(page, tokill, &tk, force_early);
 	else
-		collect_procs_file(page, tokill, &tk);
+		collect_procs_file(page, tokill, &tk, force_early);
 	kfree(tk);
 }
 
@@ -967,7 +1000,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	 * there's nothing that can be done.
 	 */
 	if (kill)
-		collect_procs(ppage, &tokill);
+		collect_procs(ppage, &tokill, flags & MF_ACTION_REQUIRED);
 
 	ret = try_to_unmap(ppage, ttu);
 	if (ret != SWAP_SUCCESS)
@@ -1085,15 +1118,16 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 			return 0;
 		} else if (PageHuge(hpage)) {
 			/*
-			 * Check "just unpoisoned", "filter hit", and
-			 * "race with other subpage."
+			 * Check "filter hit" and "race with other subpage."
 			 */
 			lock_page(hpage);
-			if (!PageHWPoison(hpage)
-			    || (hwpoison_filter(p) && TestClearPageHWPoison(p))
-			    || (p != hpage && TestSetPageHWPoison(hpage))) {
-				atomic_long_sub(nr_pages, &num_poisoned_pages);
-				return 0;
+			if (PageHWPoison(hpage)) {
+				if ((hwpoison_filter(p) && TestClearPageHWPoison(p))
+				    || (p != hpage && TestSetPageHWPoison(hpage))) {
+					atomic_long_sub(nr_pages, &num_poisoned_pages);
+					unlock_page(hpage);
+					return 0;
+				}
 			}
 			set_page_hwpoison_huge_page(hpage);
 			res = dequeue_hwpoisoned_huge_page(hpage);
@@ -1156,6 +1190,8 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	 */
 	if (!PageHWPoison(p)) {
 		printk(KERN_ERR "MCE %#lx: just unpoisoned\n", pfn);
+		atomic_long_sub(nr_pages, &num_poisoned_pages);
+		put_page(hpage);
 		res = 0;
 		goto out;
 	}
diff --git a/mm/memory.c b/mm/memory.c
index eef1e5cfe8de..8c595234528a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1929,12 +1929,17 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
 		     unsigned long address, unsigned int fault_flags)
 {
 	struct vm_area_struct *vma;
+	vm_flags_t vm_flags;
 	int ret;
 
 	vma = find_extend_vma(mm, address);
 	if (!vma || address < vma->vm_start)
 		return -EFAULT;
 
+	vm_flags = (fault_flags & FAULT_FLAG_WRITE) ? VM_WRITE : VM_READ;
+	if (!(vm_flags & vma->vm_flags))
+		return -EFAULT;
+
 	ret = handle_mm_fault(mm, vma, address, fault_flags);
 	if (ret & VM_FAULT_ERROR) {
 		if (ret & VM_FAULT_OOM)
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index ae3c8f3595d4..56224d998c39 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -526,9 +526,13 @@ static void queue_pages_hugetlb_pmd_range(struct vm_area_struct *vma,
 	int nid;
 	struct page *page;
 	spinlock_t *ptl;
+	pte_t entry;
 
 	ptl = huge_pte_lock(hstate_vma(vma), vma->vm_mm, (pte_t *)pmd);
-	page = pte_page(huge_ptep_get((pte_t *)pmd));
+	entry = huge_ptep_get((pte_t *)pmd);
+	if (!pte_present(entry))
+		goto unlock;
+	page = pte_page(entry);
 	nid = page_to_nid(page);
 	if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT))
 		goto unlock;
diff --git a/mm/mremap.c b/mm/mremap.c
index 0843feb66f3d..05f1180e9f21 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -194,10 +194,17 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 			break;
 		if (pmd_trans_huge(*old_pmd)) {
 			int err = 0;
-			if (extent == HPAGE_PMD_SIZE)
+			if (extent == HPAGE_PMD_SIZE) {
+				VM_BUG_ON(vma->vm_file || !vma->anon_vma);
+				/* See comment in move_ptes() */
+				if (need_rmap_locks)
+					anon_vma_lock_write(vma->anon_vma);
 				err = move_huge_pmd(vma, new_vma, old_addr,
 						    new_addr, old_end,
 						    old_pmd, new_pmd);
+				if (need_rmap_locks)
+					anon_vma_unlock_write(vma->anon_vma);
+			}
 			if (err > 0) {
 				need_flush = true;
 				continue;
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 7106cb1aca8e..d013dba21429 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -593,14 +593,14 @@ unsigned long bdi_dirty_limit(struct backing_dev_info *bdi, unsigned long dirty)
  * (5) the closer to setpoint, the smaller |df/dx| (and the reverse)
  *     => fast response on large errors; small oscillation near setpoint
  */
-static inline long long pos_ratio_polynom(unsigned long setpoint,
+static long long pos_ratio_polynom(unsigned long setpoint,
 					  unsigned long dirty,
 					  unsigned long limit)
 {
 	long long pos_ratio;
 	long x;
 
-	x = div_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT,
+	x = div64_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT,
 		    limit - setpoint + 1);
 	pos_ratio = x;
 	pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT;
@@ -842,7 +842,7 @@ static unsigned long bdi_position_ratio(struct backing_dev_info *bdi,
 	x_intercept = bdi_setpoint + span;
 
 	if (bdi_dirty < x_intercept - span / 4) {
-		pos_ratio = div_u64(pos_ratio * (x_intercept - bdi_dirty),
+		pos_ratio = div64_u64(pos_ratio * (x_intercept - bdi_dirty),
 				    x_intercept - bdi_setpoint + 1);
 	} else
 		pos_ratio /= 4;
@@ -2398,7 +2398,7 @@ int test_clear_page_writeback(struct page *page)
 	return ret;
 }
 
-int test_set_page_writeback(struct page *page)
+int __test_set_page_writeback(struct page *page, bool keep_write)
 {
 	struct address_space *mapping = page_mapping(page);
 	int ret;
@@ -2423,9 +2423,10 @@ int test_set_page_writeback(struct page *page)
 			radix_tree_tag_clear(&mapping->page_tree,
 						page_index(page),
 						PAGECACHE_TAG_DIRTY);
-		radix_tree_tag_clear(&mapping->page_tree,
-				     page_index(page),
-				     PAGECACHE_TAG_TOWRITE);
+		if (!keep_write)
+			radix_tree_tag_clear(&mapping->page_tree,
+						page_index(page),
+						PAGECACHE_TAG_TOWRITE);
 		spin_unlock_irqrestore(&mapping->tree_lock, flags);
 	} else {
 		ret = TestSetPageWriteback(page);
@@ -2436,7 +2437,7 @@ int test_set_page_writeback(struct page *page)
 	return ret;
 
 }
-EXPORT_SYMBOL(test_set_page_writeback);
+EXPORT_SYMBOL(__test_set_page_writeback);
 
 /*
  * Return true if any of the pages in the mapping are marked with the
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 563d41c4935b..672afc4c4157 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6064,53 +6064,65 @@ static inline int pfn_to_bitidx(struct zone *zone, unsigned long pfn)
  * @end_bitidx: The last bit of interest
  * returns pageblock_bits flags
  */
-unsigned long get_pageblock_flags_group(struct page *page,
-					int start_bitidx, int end_bitidx)
+unsigned long get_pageblock_flags_mask(struct page *page,
+					unsigned long end_bitidx,
+					unsigned long mask)
 {
 	struct zone *zone;
 	unsigned long *bitmap;
-	unsigned long pfn, bitidx;
-	unsigned long flags = 0;
-	unsigned long value = 1;
+	unsigned long pfn, bitidx, word_bitidx;
+	unsigned long word;
 
 	zone = page_zone(page);
 	pfn = page_to_pfn(page);
 	bitmap = get_pageblock_bitmap(zone, pfn);
 	bitidx = pfn_to_bitidx(zone, pfn);
+	word_bitidx = bitidx / BITS_PER_LONG;
+	bitidx &= (BITS_PER_LONG-1);
 
-	for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1)
-		if (test_bit(bitidx + start_bitidx, bitmap))
-			flags |= value;
-
-	return flags;
+	word = bitmap[word_bitidx];
+	bitidx += end_bitidx;
+	return (word >> (BITS_PER_LONG - bitidx - 1)) & mask;
 }
 
 /**
- * set_pageblock_flags_group - Set the requested group of flags for a pageblock_nr_pages block of pages
+ * set_pageblock_flags_mask - Set the requested group of flags for a pageblock_nr_pages block of pages
  * @page: The page within the block of interest
  * @start_bitidx: The first bit of interest
  * @end_bitidx: The last bit of interest
  * @flags: The flags to set
  */
-void set_pageblock_flags_group(struct page *page, unsigned long flags,
-					int start_bitidx, int end_bitidx)
+void set_pageblock_flags_mask(struct page *page, unsigned long flags,
+					unsigned long end_bitidx,
+					unsigned long mask)
 {
 	struct zone *zone;
 	unsigned long *bitmap;
-	unsigned long pfn, bitidx;
-	unsigned long value = 1;
+	unsigned long pfn, bitidx, word_bitidx;
+	unsigned long old_word, word;
+
+	BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4);
 
 	zone = page_zone(page);
 	pfn = page_to_pfn(page);
 	bitmap = get_pageblock_bitmap(zone, pfn);
 	bitidx = pfn_to_bitidx(zone, pfn);
+	word_bitidx = bitidx / BITS_PER_LONG;
+	bitidx &= (BITS_PER_LONG-1);
+
 	VM_BUG_ON_PAGE(!zone_spans_pfn(zone, pfn), page);
 
-	for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1)
-		if (flags & value)
-			__set_bit(bitidx + start_bitidx, bitmap);
-		else
-			__clear_bit(bitidx + start_bitidx, bitmap);
+	bitidx += end_bitidx;
+	mask <<= (BITS_PER_LONG - bitidx - 1);
+	flags <<= (BITS_PER_LONG - bitidx - 1);
+
+	word = ACCESS_ONCE(bitmap[word_bitidx]);
+	for (;;) {
+		old_word = cmpxchg(&bitmap[word_bitidx], word, (word & ~mask) | flags);
+		if (word == old_word)
+			break;
+		word = old_word;
+	}
 }
 
 /*
diff --git a/mm/percpu.c b/mm/percpu.c
index 036cfe07050f..a2a54a85f691 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -612,7 +612,7 @@ static struct pcpu_chunk *pcpu_alloc_chunk(void)
 	chunk->map = pcpu_mem_zalloc(PCPU_DFL_MAP_ALLOC *
 						sizeof(chunk->map[0]));
 	if (!chunk->map) {
-		kfree(chunk);
+		pcpu_mem_free(chunk, pcpu_chunk_struct_size);
 		return NULL;
 	}
 
diff --git a/mm/rmap.c b/mm/rmap.c
index d3cbac508c2f..cdbd31285cf6 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -103,6 +103,7 @@ static inline void anon_vma_free(struct anon_vma *anon_vma)
 	 * LOCK should suffice since the actual taking of the lock must
 	 * happen _before_ what follows.
 	 */
+	might_sleep();
 	if (rwsem_is_locked(&anon_vma->root->rwsem)) {
 		anon_vma_lock_write(anon_vma);
 		anon_vma_unlock_write(anon_vma);
@@ -426,8 +427,9 @@ struct anon_vma *page_get_anon_vma(struct page *page)
 	 * above cannot corrupt).
 	 */
 	if (!page_mapped(page)) {
+		rcu_read_unlock();
 		put_anon_vma(anon_vma);
-		anon_vma = NULL;
+		return NULL;
 	}
 out:
 	rcu_read_unlock();
@@ -477,9 +479,9 @@ struct anon_vma *page_lock_anon_vma_read(struct page *page)
 	}
 
 	if (!page_mapped(page)) {
+		rcu_read_unlock();
 		put_anon_vma(anon_vma);
-		anon_vma = NULL;
-		goto out;
+		return NULL;
 	}
 
 	/* we pinned the anon_vma, its safe to sleep */
@@ -1554,10 +1556,9 @@ void __put_anon_vma(struct anon_vma *anon_vma)
 {
 	struct anon_vma *root = anon_vma->root;
 
+	anon_vma_free(anon_vma);
 	if (root != anon_vma && atomic_dec_and_test(&root->refcount))
 		anon_vma_free(root);
-
-	anon_vma_free(anon_vma);
 }
 
 static struct anon_vma *rmap_walk_anon_lock(struct page *page,
diff --git a/mm/vmscan.c b/mm/vmscan.c
index a9c74b409681..6ef876cae8f1 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2502,10 +2502,17 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
 
 	for (i = 0; i <= ZONE_NORMAL; i++) {
 		zone = &pgdat->node_zones[i];
+		if (!populated_zone(zone))
+			continue;
+
 		pfmemalloc_reserve += min_wmark_pages(zone);
 		free_pages += zone_page_state(zone, NR_FREE_PAGES);
 	}
 
+	/* If there are no reserves (unexpected config) then do not throttle */
+	if (!pfmemalloc_reserve)
+		return true;
+
 	wmark_ok = free_pages > pfmemalloc_reserve / 2;
 
 	/* kswapd must be awake if processes are being throttled */
@@ -2530,9 +2537,9 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
 static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
 					nodemask_t *nodemask)
 {
+	struct zoneref *z;
 	struct zone *zone;
-	int high_zoneidx = gfp_zone(gfp_mask);
-	pg_data_t *pgdat;
+	pg_data_t *pgdat = NULL;
 
 	/*
 	 * Kernel threads should not be throttled as they may be indirectly
@@ -2551,10 +2558,34 @@ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
 	if (fatal_signal_pending(current))
 		goto out;
 
-	/* Check if the pfmemalloc reserves are ok */
-	first_zones_zonelist(zonelist, high_zoneidx, NULL, &zone);
-	pgdat = zone->zone_pgdat;
-	if (pfmemalloc_watermark_ok(pgdat))
+	/*
+	 * Check if the pfmemalloc reserves are ok by finding the first node
+	 * with a usable ZONE_NORMAL or lower zone. The expectation is that
+	 * GFP_KERNEL will be required for allocating network buffers when
+	 * swapping over the network so ZONE_HIGHMEM is unusable.
+	 *
+	 * Throttling is based on the first usable node and throttled processes
+	 * wait on a queue until kswapd makes progress and wakes them. There
+	 * is an affinity then between processes waking up and where reclaim
+	 * progress has been made assuming the process wakes on the same node.
+	 * More importantly, processes running on remote nodes will not compete
+	 * for remote pfmemalloc reserves and processes on different nodes
+	 * should make reasonable progress.
+	 */
+	for_each_zone_zonelist_nodemask(zone, z, zonelist,
+					gfp_mask, nodemask) {
+		if (zone_idx(zone) > ZONE_NORMAL)
+			continue;
+
+		/* Throttle based on the first usable node */
+		pgdat = zone->zone_pgdat;
+		if (pfmemalloc_watermark_ok(pgdat))
+			goto out;
+		break;
+	}
+
+	/* If no zone was usable by the allocation flags then do not throttle */
+	if (!pgdat)
 		goto out;
 
 	/* Account for the throttling */
@@ -3285,7 +3316,10 @@ static int kswapd(void *p)
 		}
 	}
 
+	tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD);
 	current->reclaim_state = NULL;
+	lockdep_clear_current_reclaim_state();
+
 	return 0;
 }