Merge remote-tracking branch 'torvalds/master' into perf/core

To pick up fixes.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

16 files changed, 112 insertions, 181 deletions

diff --git a/mm/compaction.c b/mm/compaction.c
index 6e0ee5641788..13cb7a961b31 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -817,6 +817,10 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 	 * delay for some time until fewer pages are isolated
 	 */
 	while (unlikely(too_many_isolated(pgdat))) {
+		/* stop isolation if there are still pages not migrated */
+		if (cc->nr_migratepages)
+			return 0;
+
 		/* async migration should just abort */
 		if (cc->mode == MIGRATE_ASYNC)
 			return 0;
@@ -1012,8 +1016,8 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 
 isolate_success:
 		list_add(&page->lru, &cc->migratepages);
-		cc->nr_migratepages++;
-		nr_isolated++;
+		cc->nr_migratepages += compound_nr(page);
+		nr_isolated += compound_nr(page);
 
 		/*
 		 * Avoid isolating too much unless this block is being
@@ -1021,7 +1025,7 @@ isolate_success:
 		 * or a lock is contended. For contention, isolate quickly to
 		 * potentially remove one source of contention.
 		 */
-		if (cc->nr_migratepages == COMPACT_CLUSTER_MAX &&
+		if (cc->nr_migratepages >= COMPACT_CLUSTER_MAX &&
 		    !cc->rescan && !cc->contended) {
 			++low_pfn;
 			break;
@@ -1132,7 +1136,7 @@ isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn,
 		if (!pfn)
 			break;
 
-		if (cc->nr_migratepages == COMPACT_CLUSTER_MAX)
+		if (cc->nr_migratepages >= COMPACT_CLUSTER_MAX)
 			break;
 	}
 
diff --git a/mm/filemap.c b/mm/filemap.c
index d5e7c2029d16..0b2067b3c328 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1484,11 +1484,19 @@ void end_page_writeback(struct page *page)
 		rotate_reclaimable_page(page);
 	}
 
+	/*
+	 * Writeback does not hold a page reference of its own, relying
+	 * on truncation to wait for the clearing of PG_writeback.
+	 * But here we must make sure that the page is not freed and
+	 * reused before the wake_up_page().
+	 */
+	get_page(page);
 	if (!test_clear_page_writeback(page))
 		BUG();
 
 	smp_mb__after_atomic();
 	wake_up_page(page, PG_writeback);
+	put_page(page);
 }
 EXPORT_SYMBOL(end_page_writeback);
 
@@ -2347,10 +2355,15 @@ page_ok:
 
 page_not_up_to_date:
 		/* Get exclusive access to the page ... */
-		if (iocb->ki_flags & IOCB_WAITQ)
+		if (iocb->ki_flags & IOCB_WAITQ) {
+			if (written) {
+				put_page(page);
+				goto out;
+			}
 			error = lock_page_async(page, iocb->ki_waitq);
-		else
+		} else {
 			error = lock_page_killable(page);
+		}
 		if (unlikely(error))
 			goto readpage_error;
 
@@ -2393,10 +2406,15 @@ readpage:
 		}
 
 		if (!PageUptodate(page)) {
-			if (iocb->ki_flags & IOCB_WAITQ)
+			if (iocb->ki_flags & IOCB_WAITQ) {
+				if (written) {
+					put_page(page);
+					goto out;
+				}
 				error = lock_page_async(page, iocb->ki_waitq);
-			else
+			} else {
 				error = lock_page_killable(page);
+			}
 
 			if (unlikely(error))
 				goto readpage_error;
diff --git a/mm/gup.c b/mm/gup.c
index 102877ed77a4..98eb8e6d2609 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1647,8 +1647,11 @@ check_again:
 		/*
 		 * drop the above get_user_pages reference.
 		 */
-		for (i = 0; i < nr_pages; i++)
-			put_page(pages[i]);
+		if (gup_flags & FOLL_PIN)
+			unpin_user_pages(pages, nr_pages);
+		else
+			for (i = 0; i < nr_pages; i++)
+				put_page(pages[i]);
 
 		if (migrate_pages(&cma_page_list, alloc_migration_target, NULL,
 			(unsigned long)&mtc, MIGRATE_SYNC, MR_CONTIG_RANGE)) {
@@ -1728,8 +1731,11 @@ static long __gup_longterm_locked(struct mm_struct *mm,
 			goto out;
 
 		if (check_dax_vmas(vmas_tmp, rc)) {
-			for (i = 0; i < rc; i++)
-				put_page(pages[i]);
+			if (gup_flags & FOLL_PIN)
+				unpin_user_pages(pages, rc);
+			else
+				for (i = 0; i < rc; i++)
+					put_page(pages[i]);
 			rc = -EOPNOTSUPP;
 			goto out;
 		}
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 9474dbc150ed..ec2bb93f7431 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -710,7 +710,6 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
 			transparent_hugepage_use_zero_page()) {
 		pgtable_t pgtable;
 		struct page *zero_page;
-		bool set;
 		vm_fault_t ret;
 		pgtable = pte_alloc_one(vma->vm_mm);
 		if (unlikely(!pgtable))
@@ -723,25 +722,25 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
 		}
 		vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
 		ret = 0;
-		set = false;
 		if (pmd_none(*vmf->pmd)) {
 			ret = check_stable_address_space(vma->vm_mm);
 			if (ret) {
 				spin_unlock(vmf->ptl);
+				pte_free(vma->vm_mm, pgtable);
 			} else if (userfaultfd_missing(vma)) {
 				spin_unlock(vmf->ptl);
+				pte_free(vma->vm_mm, pgtable);
 				ret = handle_userfault(vmf, VM_UFFD_MISSING);
 				VM_BUG_ON(ret & VM_FAULT_FALLBACK);
 			} else {
 				set_huge_zero_page(pgtable, vma->vm_mm, vma,
 						   haddr, vmf->pmd, zero_page);
 				spin_unlock(vmf->ptl);
-				set = true;
 			}
-		} else
+		} else {
 			spin_unlock(vmf->ptl);
-		if (!set)
 			pte_free(vma->vm_mm, pgtable);
+		}
 		return ret;
 	}
 	gfp = alloc_hugepage_direct_gfpmask(vma);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 5a620f690911..37f15c3c24dc 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1568,103 +1568,23 @@ int PageHeadHuge(struct page *page_head)
 }
 
 /*
- * Find address_space associated with hugetlbfs page.
- * Upon entry page is locked and page 'was' mapped although mapped state
- * could change.  If necessary, use anon_vma to find vma and associated
- * address space.  The returned mapping may be stale, but it can not be
- * invalid as page lock (which is held) is required to destroy mapping.
- */
-static struct address_space *_get_hugetlb_page_mapping(struct page *hpage)
-{
-	struct anon_vma *anon_vma;
-	pgoff_t pgoff_start, pgoff_end;
-	struct anon_vma_chain *avc;
-	struct address_space *mapping = page_mapping(hpage);
-
-	/* Simple file based mapping */
-	if (mapping)
-		return mapping;
-
-	/*
-	 * Even anonymous hugetlbfs mappings are associated with an
-	 * underlying hugetlbfs file (see hugetlb_file_setup in mmap
-	 * code).  Find a vma associated with the anonymous vma, and
-	 * use the file pointer to get address_space.
-	 */
-	anon_vma = page_lock_anon_vma_read(hpage);
-	if (!anon_vma)
-		return mapping;  /* NULL */
-
-	/* Use first found vma */
-	pgoff_start = page_to_pgoff(hpage);
-	pgoff_end = pgoff_start + pages_per_huge_page(page_hstate(hpage)) - 1;
-	anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root,
-					pgoff_start, pgoff_end) {
-		struct vm_area_struct *vma = avc->vma;
-
-		mapping = vma->vm_file->f_mapping;
-		break;
-	}
-
-	anon_vma_unlock_read(anon_vma);
-	return mapping;
-}
-
-/*
  * Find and lock address space (mapping) in write mode.
  *
- * Upon entry, the page is locked which allows us to find the mapping
- * even in the case of an anon page.  However, locking order dictates
- * the i_mmap_rwsem be acquired BEFORE the page lock.  This is hugetlbfs
- * specific.  So, we first try to lock the sema while still holding the
- * page lock.  If this works, great!  If not, then we need to drop the
- * page lock and then acquire i_mmap_rwsem and reacquire page lock.  Of
- * course, need to revalidate state along the way.
+ * Upon entry, the page is locked which means that page_mapping() is
+ * stable.  Due to locking order, we can only trylock_write.  If we can
+ * not get the lock, simply return NULL to caller.
  */
 struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage)
 {
-	struct address_space *mapping, *mapping2;
+	struct address_space *mapping = page_mapping(hpage);
 
-	mapping = _get_hugetlb_page_mapping(hpage);
-retry:
 	if (!mapping)
 		return mapping;
 
-	/*
-	 * If no contention, take lock and return
-	 */
 	if (i_mmap_trylock_write(mapping))
 		return mapping;
 
-	/*
-	 * Must drop page lock and wait on mapping sema.
-	 * Note:  Once page lock is dropped, mapping could become invalid.
-	 * As a hack, increase map count until we lock page again.
-	 */
-	atomic_inc(&hpage->_mapcount);
-	unlock_page(hpage);
-	i_mmap_lock_write(mapping);
-	lock_page(hpage);
-	atomic_add_negative(-1, &hpage->_mapcount);
-
-	/* verify page is still mapped */
-	if (!page_mapped(hpage)) {
-		i_mmap_unlock_write(mapping);
-		return NULL;
-	}
-
-	/*
-	 * Get address space again and verify it is the same one
-	 * we locked.  If not, drop lock and retry.
-	 */
-	mapping2 = _get_hugetlb_page_mapping(hpage);
-	if (mapping2 != mapping) {
-		i_mmap_unlock_write(mapping);
-		mapping = mapping2;
-		goto retry;
-	}
-
-	return mapping;
+	return NULL;
 }
 
 pgoff_t __basepage_index(struct page *page)
diff --git a/mm/madvise.c b/mm/madvise.c
index 416a56b8e757..a8d8d48a57fe 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -226,7 +226,7 @@ static void force_shm_swapin_readahead(struct vm_area_struct *vma,
 		struct address_space *mapping)
 {
 	XA_STATE(xas, &mapping->i_pages, linear_page_index(vma, start));
-	pgoff_t end_index = end / PAGE_SIZE;
+	pgoff_t end_index = linear_page_index(vma, end + PAGE_SIZE - 1);
 	struct page *page;
 
 	rcu_read_lock();
@@ -1231,8 +1231,6 @@ SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec,
 		ret = total_len - iov_iter_count(&iter);
 
 	mmput(mm);
-	return ret;
-
 release_task:
 	put_task_struct(task);
 put_pid:
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 3dcbf24d2227..29459a6ce1c7 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -867,8 +867,13 @@ void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val)
 	rcu_read_lock();
 	memcg = mem_cgroup_from_obj(p);
 
-	/* Untracked pages have no memcg, no lruvec. Update only the node */
-	if (!memcg || memcg == root_mem_cgroup) {
+	/*
+	 * Untracked pages have no memcg, no lruvec. Update only the
+	 * node. If we reparent the slab objects to the root memcg,
+	 * when we free the slab object, we need to update the per-memcg
+	 * vmstats to keep it correct for the root memcg.
+	 */
+	if (!memcg) {
 		__mod_node_page_state(pgdat, idx, val);
 	} else {
 		lruvec = mem_cgroup_lruvec(memcg, pgdat);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index c0bb186bba62..5d880d4eb9a2 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1057,27 +1057,25 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	if (!PageHuge(hpage)) {
 		unmap_success = try_to_unmap(hpage, ttu);
 	} else {
-		/*
-		 * For hugetlb pages, try_to_unmap could potentially call
-		 * huge_pmd_unshare.  Because of this, take semaphore in
-		 * write mode here and set TTU_RMAP_LOCKED to indicate we
-		 * have taken the lock at this higer level.
-		 *
-		 * Note that the call to hugetlb_page_mapping_lock_write
-		 * is necessary even if mapping is already set.  It handles
-		 * ugliness of potentially having to drop page lock to obtain
-		 * i_mmap_rwsem.
-		 */
-		mapping = hugetlb_page_mapping_lock_write(hpage);
-
-		if (mapping) {
-			unmap_success = try_to_unmap(hpage,
+		if (!PageAnon(hpage)) {
+			/*
+			 * For hugetlb pages in shared mappings, try_to_unmap
+			 * could potentially call huge_pmd_unshare.  Because of
+			 * this, take semaphore in write mode here and set
+			 * TTU_RMAP_LOCKED to indicate we have taken the lock
+			 * at this higer level.
+			 */
+			mapping = hugetlb_page_mapping_lock_write(hpage);
+			if (mapping) {
+				unmap_success = try_to_unmap(hpage,
 						     ttu|TTU_RMAP_LOCKED);
-			i_mmap_unlock_write(mapping);
+				i_mmap_unlock_write(mapping);
+			} else {
+				pr_info("Memory failure: %#lx: could not lock mapping for mapped huge page\n", pfn);
+				unmap_success = false;
+			}
 		} else {
-			pr_info("Memory failure: %#lx: could not find mapping for mapped huge page\n",
-				pfn);
-			unmap_success = false;
+			unmap_success = try_to_unmap(hpage, ttu);
 		}
 	}
 	if (!unmap_success)
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index b44d4c7ba73b..63b2e46b6555 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -350,24 +350,6 @@ int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages,
 	return err;
 }
 
-#ifdef CONFIG_NUMA
-int __weak memory_add_physaddr_to_nid(u64 start)
-{
-	pr_info_once("Unknown online node for memory at 0x%llx, assuming node 0\n",
-			start);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
-
-int __weak phys_to_target_node(u64 start)
-{
-	pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n",
-			start);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(phys_to_target_node);
-#endif
-
 /* find the smallest valid pfn in the range [start_pfn, end_pfn) */
 static unsigned long find_smallest_section_pfn(int nid, struct zone *zone,
 				     unsigned long start_pfn,
diff --git a/mm/migrate.c b/mm/migrate.c
index 5ca5842df5db..5795cb82e27c 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1328,34 +1328,38 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
 		goto put_anon;
 
 	if (page_mapped(hpage)) {
-		/*
-		 * try_to_unmap could potentially call huge_pmd_unshare.
-		 * Because of this, take semaphore in write mode here and
-		 * set TTU_RMAP_LOCKED to let lower levels know we have
-		 * taken the lock.
-		 */
-		mapping = hugetlb_page_mapping_lock_write(hpage);
-		if (unlikely(!mapping))
-			goto unlock_put_anon;
+		bool mapping_locked = false;
+		enum ttu_flags ttu = TTU_MIGRATION|TTU_IGNORE_MLOCK|
+					TTU_IGNORE_ACCESS;
+
+		if (!PageAnon(hpage)) {
+			/*
+			 * In shared mappings, try_to_unmap could potentially
+			 * call huge_pmd_unshare.  Because of this, take
+			 * semaphore in write mode here and set TTU_RMAP_LOCKED
+			 * to let lower levels know we have taken the lock.
+			 */
+			mapping = hugetlb_page_mapping_lock_write(hpage);
+			if (unlikely(!mapping))
+				goto unlock_put_anon;
+
+			mapping_locked = true;
+			ttu |= TTU_RMAP_LOCKED;
+		}
 
-		try_to_unmap(hpage,
-			TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS|
-			TTU_RMAP_LOCKED);
+		try_to_unmap(hpage, ttu);
 		page_was_mapped = 1;
-		/*
-		 * Leave mapping locked until after subsequent call to
-		 * remove_migration_ptes()
-		 */
+
+		if (mapping_locked)
+			i_mmap_unlock_write(mapping);
 	}
 
 	if (!page_mapped(hpage))
 		rc = move_to_new_page(new_hpage, hpage, mode);
 
-	if (page_was_mapped) {
+	if (page_was_mapped)
 		remove_migration_ptes(hpage,
-			rc == MIGRATEPAGE_SUCCESS ? new_hpage : hpage, true);
-		i_mmap_unlock_write(mapping);
-	}
+			rc == MIGRATEPAGE_SUCCESS ? new_hpage : hpage, false);
 
 unlock_put_anon:
 	unlock_page(new_hpage);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 7709f0e223f5..586042472ac9 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2754,12 +2754,6 @@ int test_clear_page_writeback(struct page *page)
 	} else {
 		ret = TestClearPageWriteback(page);
 	}
-	/*
-	 * NOTE: Page might be free now! Writeback doesn't hold a page
-	 * reference on its own, it relies on truncation to wait for
-	 * the clearing of PG_writeback. The below can only access
-	 * page state that is static across allocation cycles.
-	 */
 	if (ret) {
 		dec_lruvec_state(lruvec, NR_WRITEBACK);
 		dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 23f5066bd4a5..eaa227a479e4 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5103,6 +5103,11 @@ refill:
 		if (!page_ref_sub_and_test(page, nc->pagecnt_bias))
 			goto refill;
 
+		if (unlikely(nc->pfmemalloc)) {
+			free_the_page(page, compound_order(page));
+			goto refill;
+		}
+
 #if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
 		/* if size can vary use size else just use PAGE_SIZE */
 		size = nc->size;
diff --git a/mm/percpu.c b/mm/percpu.c
index 66a93f096394..ad7a37ee74ef 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1315,8 +1315,8 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr,
 	region_size = ALIGN(start_offset + map_size, lcm_align);
 
 	/* allocate chunk */
-	alloc_size = sizeof(struct pcpu_chunk) +
-		BITS_TO_LONGS(region_size >> PAGE_SHIFT) * sizeof(unsigned long);
+	alloc_size = struct_size(chunk, populated,
+				 BITS_TO_LONGS(region_size >> PAGE_SHIFT));
 	chunk = memblock_alloc(alloc_size, SMP_CACHE_BYTES);
 	if (!chunk)
 		panic("%s: Failed to allocate %zu bytes\n", __func__,
@@ -2521,8 +2521,8 @@ void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 	pcpu_unit_pages = ai->unit_size >> PAGE_SHIFT;
 	pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT;
 	pcpu_atom_size = ai->atom_size;
-	pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) +
-		BITS_TO_LONGS(pcpu_unit_pages) * sizeof(unsigned long);
+	pcpu_chunk_struct_size = struct_size(chunk, populated,
+					     BITS_TO_LONGS(pcpu_unit_pages));
 
 	pcpu_stats_save_ai(ai);
 
diff --git a/mm/rmap.c b/mm/rmap.c
index 1b84945d655c..31b29321adfe 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1413,9 +1413,6 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 		/*
 		 * If sharing is possible, start and end will be adjusted
 		 * accordingly.
-		 *
-		 * If called for a huge page, caller must hold i_mmap_rwsem
-		 * in write mode as it is possible to call huge_pmd_unshare.
 		 */
 		adjust_range_if_pmd_sharing_possible(vma, &range.start,
 						     &range.end);
@@ -1462,7 +1459,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 		subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte);
 		address = pvmw.address;
 
-		if (PageHuge(page)) {
+		if (PageHuge(page) && !PageAnon(page)) {
 			/*
 			 * To call huge_pmd_unshare, i_mmap_rwsem must be
 			 * held in write mode.  Caller needs to explicitly
diff --git a/mm/slub.c b/mm/slub.c
index b30be2385d1c..34dcc09e2ec9 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2852,7 +2852,7 @@ redo:
 
 	object = c->freelist;
 	page = c->page;
-	if (unlikely(!object || !node_match(page, node))) {
+	if (unlikely(!object || !page || !node_match(page, node))) {
 		object = __slab_alloc(s, gfpflags, node, addr, c);
 	} else {
 		void *next_object = get_freepointer_safe(s, object);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 1b8f0e059767..7b4e31eac2cf 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1516,7 +1516,8 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
 	nr_reclaimed = shrink_page_list(&clean_pages, zone->zone_pgdat, &sc,
 			TTU_IGNORE_ACCESS, &stat, true);
 	list_splice(&clean_pages, page_list);
-	mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -nr_reclaimed);
+	mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE,
+			    -(long)nr_reclaimed);
 	/*
 	 * Since lazyfree pages are isolated from file LRU from the beginning,
 	 * they will rotate back to anonymous LRU in the end if it failed to
@@ -1526,7 +1527,7 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
 	mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON,
 			    stat.nr_lazyfree_fail);
 	mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE,
-			    -stat.nr_lazyfree_fail);
+			    -(long)stat.nr_lazyfree_fail);
 	return nr_reclaimed;
 }