Merge branch 'akpm' (patches from Andrew)

Merge more fixes from Andrew Morton:
 "The usual shower of hotfixes and some followups to the recently merged
  page_owner enhancements"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  mm/memory-failure: poison read receives SIGKILL instead of SIGBUS if mmaped more than once
  mm/slab.c: fix kernel-doc warning for __ksize()
  xarray.h: fix kernel-doc warning
  bitmap.h: fix kernel-doc warning and typo
  fs/fs-writeback.c: fix kernel-doc warning
  fs/libfs.c: fix kernel-doc warning
  fs/direct-io.c: fix kernel-doc warning
  mm, compaction: fix wrong pfn handling in __reset_isolation_pfn()
  mm, hugetlb: allow hugepage allocations to reclaim as needed
  lib/test_meminit: add a kmem_cache_alloc_bulk() test
  mm/slub.c: init_on_free=1 should wipe freelist ptr for bulk allocations
  lib/generic-radix-tree.c: add kmemleak annotations
  mm/slub: fix a deadlock in show_slab_objects()
  mm, page_owner: rename flag indicating that page is allocated
  mm, page_owner: decouple freeing stack trace from debug_pagealloc
  mm, page_owner: fix off-by-one error in __set_page_owner_handle()

Documentation/dev-tools/kasan.rst

@@ -41,6 +41,9 @@ smaller binary while the latter is 1.1 - 2 times faster.
 Both KASAN modes work with both SLUB and SLAB memory allocators.
 For better bug detection and nicer reporting, enable CONFIG_STACKTRACE.
 
+To augment reports with last allocation and freeing stack of the physical page,
+it is recommended to enable also CONFIG_PAGE_OWNER and boot with page_owner=on.
+
 To disable instrumentation for specific files or directories, add a line
 similar to the following to the respective kernel Makefile:
 

fs/direct-io.c

@@ -241,9 +241,8 @@ void dio_warn_stale_pagecache(struct file *filp)
 	}
 }
 
-/**
+/*
  * dio_complete() - called when all DIO BIO I/O has been completed
- * @offset: the byte offset in the file of the completed operation
  *
  * This drops i_dio_count, lets interested parties know that a DIO operation
  * has completed, and calculates the resulting return code for the operation.

fs/fs-writeback.c

@@ -905,7 +905,7 @@ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi,
  * cgroup_writeback_by_id - initiate cgroup writeback from bdi and memcg IDs
  * @bdi_id: target bdi id
  * @memcg_id: target memcg css id
- * @nr_pages: number of pages to write, 0 for best-effort dirty flushing
+ * @nr: number of pages to write, 0 for best-effort dirty flushing
  * @reason: reason why some writeback work initiated
  * @done: target wb_completion
  *

fs/libfs.c

@@ -473,8 +473,7 @@ EXPORT_SYMBOL(simple_write_begin);
 
 /**
  * simple_write_end - .write_end helper for non-block-device FSes
- * @available: See .write_end of address_space_operations
- * @file: 		"
+ * @file: See .write_end of address_space_operations
  * @mapping: 		"
  * @pos: 		"
  * @len: 		"

include/linux/bitmap.h

@@ -326,10 +326,11 @@ static inline int bitmap_equal(const unsigned long *src1,
 }
 
 /**
- * bitmap_or_equal - Check whether the or of two bitnaps is equal to a third
+ * bitmap_or_equal - Check whether the or of two bitmaps is equal to a third
  * @src1:	Pointer to bitmap 1
  * @src2:	Pointer to bitmap 2 will be or'ed with bitmap 1
  * @src3:	Pointer to bitmap 3. Compare to the result of *@src1 | *@src2
+ * @nbits:	number of bits in each of these bitmaps
  *
  * Returns: True if (*@src1 | *@src2) == *@src3, false otherwise
  */

include/linux/page_ext.h

@@ -18,7 +18,7 @@ struct page_ext_operations {
 
 enum page_ext_flags {
 	PAGE_EXT_OWNER,
-	PAGE_EXT_OWNER_ACTIVE,
+	PAGE_EXT_OWNER_ALLOCATED,
 #if defined(CONFIG_IDLE_PAGE_TRACKING) && !defined(CONFIG_64BIT)
 	PAGE_EXT_YOUNG,
 	PAGE_EXT_IDLE,
@@ -36,6 +36,7 @@ struct page_ext {
 	unsigned long flags;
 };
 
+extern unsigned long page_ext_size;
 extern void pgdat_page_ext_init(struct pglist_data *pgdat);
 
 #ifdef CONFIG_SPARSEMEM
@@ -52,6 +53,13 @@ static inline void page_ext_init(void)
 
 struct page_ext *lookup_page_ext(const struct page *page);
 
+static inline struct page_ext *page_ext_next(struct page_ext *curr)
+{
+	void *next = curr;
+	next += page_ext_size;
+	return next;
+}
+
 #else /* !CONFIG_PAGE_EXTENSION */
 struct page_ext;
 

include/linux/xarray.h

@@ -230,8 +230,8 @@ static inline int xa_err(void *entry)
  * This structure is used either directly or via the XA_LIMIT() macro
  * to communicate the range of IDs that are valid for allocation.
  * Two common ranges are predefined for you:
- *  * xa_limit_32b	- [0 - UINT_MAX]
- *  * xa_limit_31b	- [0 - INT_MAX]
+ * * xa_limit_32b	- [0 - UINT_MAX]
+ * * xa_limit_31b	- [0 - INT_MAX]
  */
 struct xa_limit {
 	u32 max;

lib/generic-radix-tree.c

@@ -2,6 +2,7 @@
 #include <linux/export.h>
 #include <linux/generic-radix-tree.h>
 #include <linux/gfp.h>
+#include <linux/kmemleak.h>
 
 #define GENRADIX_ARY		(PAGE_SIZE / sizeof(struct genradix_node *))
 #define GENRADIX_ARY_SHIFT	ilog2(GENRADIX_ARY)
@@ -75,6 +76,27 @@ void *__genradix_ptr(struct __genradix *radix, size_t offset)
 }
 EXPORT_SYMBOL(__genradix_ptr);
 
+static inline struct genradix_node *genradix_alloc_node(gfp_t gfp_mask)
+{
+	struct genradix_node *node;
+
+	node = (struct genradix_node *)__get_free_page(gfp_mask|__GFP_ZERO);
+
+	/*
+	 * We're using pages (not slab allocations) directly for kernel data
+	 * structures, so we need to explicitly inform kmemleak of them in order
+	 * to avoid false positive memory leak reports.
+	 */
+	kmemleak_alloc(node, PAGE_SIZE, 1, gfp_mask);
+	return node;
+}
+
+static inline void genradix_free_node(struct genradix_node *node)
+{
+	kmemleak_free(node);
+	free_page((unsigned long)node);
+}
+
 /*
  * Returns pointer to the specified byte @offset within @radix, allocating it if
  * necessary - newly allocated slots are always zeroed out:
@@ -97,8 +119,7 @@ void *__genradix_ptr_alloc(struct __genradix *radix, size_t offset,
 			break;
 
 		if (!new_node) {
-			new_node = (void *)
-				__get_free_page(gfp_mask|__GFP_ZERO);
+			new_node = genradix_alloc_node(gfp_mask);
 			if (!new_node)
 				return NULL;
 		}
@@ -121,8 +142,7 @@ void *__genradix_ptr_alloc(struct __genradix *radix, size_t offset,
 		n = READ_ONCE(*p);
 		if (!n) {
 			if (!new_node) {
-				new_node = (void *)
-					__get_free_page(gfp_mask|__GFP_ZERO);
+				new_node = genradix_alloc_node(gfp_mask);
 				if (!new_node)
 					return NULL;
 			}
@@ -133,7 +153,7 @@ void *__genradix_ptr_alloc(struct __genradix *radix, size_t offset,
 	}
 
 	if (new_node)
-		free_page((unsigned long) new_node);
+		genradix_free_node(new_node);
 
 	return &n->data[offset];
 }
@@ -191,7 +211,7 @@ static void genradix_free_recurse(struct genradix_node *n, unsigned level)
 				genradix_free_recurse(n->children[i], level - 1);
 	}
 
-	free_page((unsigned long) n);
+	genradix_free_node(n);
 }
 
 int __genradix_prealloc(struct __genradix *radix, size_t size,

lib/test_meminit.c

@@ -297,6 +297,32 @@ static int __init do_kmem_cache_rcu_persistent(int size, int *total_failures)
 	return 1;
 }
 
+static int __init do_kmem_cache_size_bulk(int size, int *total_failures)
+{
+	struct kmem_cache *c;
+	int i, iter, maxiter = 1024;
+	int num, bytes;
+	bool fail = false;
+	void *objects[10];
+
+	c = kmem_cache_create("test_cache", size, size, 0, NULL);
+	for (iter = 0; (iter < maxiter) && !fail; iter++) {
+		num = kmem_cache_alloc_bulk(c, GFP_KERNEL, ARRAY_SIZE(objects),
+					    objects);
+		for (i = 0; i < num; i++) {
+			bytes = count_nonzero_bytes(objects[i], size);
+			if (bytes)
+				fail = true;
+			fill_with_garbage(objects[i], size);
+		}
+
+		if (num)
+			kmem_cache_free_bulk(c, num, objects);
+	}
+	*total_failures += fail;
+	return 1;
+}
+
 /*
  * Test kmem_cache allocation by creating caches of different sizes, with and
  * without constructors, with and without SLAB_TYPESAFE_BY_RCU.
@@ -318,6 +344,7 @@ static int __init test_kmemcache(int *total_failures)
 			num_tests += do_kmem_cache_size(size, ctor, rcu, zero,
 							&failures);
 		}
+		num_tests += do_kmem_cache_size_bulk(size, &failures);
 	}
 	REPORT_FAILURES_IN_FN();
 	*total_failures += failures;

mm/compaction.c

@@ -270,14 +270,15 @@ __reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source,
 
 	/* Ensure the start of the pageblock or zone is online and valid */
 	block_pfn = pageblock_start_pfn(pfn);
-	block_page = pfn_to_online_page(max(block_pfn, zone->zone_start_pfn));
+	block_pfn = max(block_pfn, zone->zone_start_pfn);
+	block_page = pfn_to_online_page(block_pfn);
 	if (block_page) {
 		page = block_page;
 		pfn = block_pfn;
 	}
 
 	/* Ensure the end of the pageblock or zone is online and valid */
-	block_pfn += pageblock_nr_pages;
+	block_pfn = pageblock_end_pfn(pfn) - 1;
 	block_pfn = min(block_pfn, zone_end_pfn(zone) - 1);
 	end_page = pfn_to_online_page(block_pfn);
 	if (!end_page)
@@ -303,7 +304,7 @@ __reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source,
 
 		page += (1 << PAGE_ALLOC_COSTLY_ORDER);
 		pfn += (1 << PAGE_ALLOC_COSTLY_ORDER);
-	} while (page < end_page);
+	} while (page <= end_page);
 
 	return false;
 }

mm/memory-failure.c

@@ -199,7 +199,6 @@ struct to_kill {
 	struct task_struct *tsk;
 	unsigned long addr;
 	short size_shift;
-	char addr_valid;
 };
 
 /*
@@ -324,22 +323,27 @@ static void add_to_kill(struct task_struct *tsk, struct page *p,
 		}
 	}
 	tk->addr = page_address_in_vma(p, vma);
-	tk->addr_valid = 1;
 	if (is_zone_device_page(p))
 		tk->size_shift = dev_pagemap_mapping_shift(p, vma);
 	else
 		tk->size_shift = compound_order(compound_head(p)) + PAGE_SHIFT;
 
 	/*
-	 * In theory we don't have to kill when the page was
-	 * munmaped. But it could be also a mremap. Since that's
-	 * likely very rare kill anyways just out of paranoia, but use
-	 * a SIGKILL because the error is not contained anymore.
+	 * Send SIGKILL if "tk->addr == -EFAULT". Also, as
+	 * "tk->size_shift" is always non-zero for !is_zone_device_page(),
+	 * so "tk->size_shift == 0" effectively checks no mapping on
+	 * ZONE_DEVICE. Indeed, when a devdax page is mmapped N times
+	 * to a process' address space, it's possible not all N VMAs
+	 * contain mappings for the page, but at least one VMA does.
+	 * Only deliver SIGBUS with payload derived from the VMA that
+	 * has a mapping for the page.
 	 */
-	if (tk->addr == -EFAULT || tk->size_shift == 0) {
+	if (tk->addr == -EFAULT) {
 		pr_info("Memory failure: Unable to find user space address %lx in %s\n",
 			page_to_pfn(p), tsk->comm);
-		tk->addr_valid = 0;
+	} else if (tk->size_shift == 0) {
+		kfree(tk);
+		return;
 	}
 	get_task_struct(tsk);
 	tk->tsk = tsk;
@@ -366,7 +370,7 @@ static void kill_procs(struct list_head *to_kill, int forcekill, bool fail,
 			 * make sure the process doesn't catch the
 			 * signal and then access the memory. Just kill it.
 			 */
-			if (fail || tk->addr_valid == 0) {
+			if (fail || tk->addr == -EFAULT) {
 				pr_err("Memory failure: %#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n",
 				       pfn, tk->tsk->comm, tk->tsk->pid);
 				do_send_sig_info(SIGKILL, SEND_SIG_PRIV,

mm/page_alloc.c

@@ -4473,12 +4473,14 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 		if (page)
 			goto got_pg;
 
-		 if (order >= pageblock_order && (gfp_mask & __GFP_IO)) {
+		 if (order >= pageblock_order && (gfp_mask & __GFP_IO) &&
+		     !(gfp_mask & __GFP_RETRY_MAYFAIL)) {
 			/*
 			 * If allocating entire pageblock(s) and compaction
 			 * failed because all zones are below low watermarks
 			 * or is prohibited because it recently failed at this
-			 * order, fail immediately.
+			 * order, fail immediately unless the allocator has
+			 * requested compaction and reclaim retry.
 			 *
 			 * Reclaim is
 			 *  - potentially very expensive because zones are far

mm/page_ext.c

@@ -67,8 +67,9 @@ static struct page_ext_operations *page_ext_ops[] = {
 #endif
 };
 
+unsigned long page_ext_size = sizeof(struct page_ext);
+
 static unsigned long total_usage;
-static unsigned long extra_mem;
 
 static bool __init invoke_need_callbacks(void)
 {
@@ -78,9 +79,8 @@ static bool __init invoke_need_callbacks(void)
 
 	for (i = 0; i < entries; i++) {
 		if (page_ext_ops[i]->need && page_ext_ops[i]->need()) {
-			page_ext_ops[i]->offset = sizeof(struct page_ext) +
-						extra_mem;
-			extra_mem += page_ext_ops[i]->size;
+			page_ext_ops[i]->offset = page_ext_size;
+			page_ext_size += page_ext_ops[i]->size;
 			need = true;
 		}
 	}
@@ -99,14 +99,9 @@ static void __init invoke_init_callbacks(void)
 	}
 }
 
-static unsigned long get_entry_size(void)
-{
-	return sizeof(struct page_ext) + extra_mem;
-}
-
 static inline struct page_ext *get_entry(void *base, unsigned long index)
 {
-	return base + get_entry_size() * index;
+	return base + page_ext_size * index;
 }
 
 #if !defined(CONFIG_SPARSEMEM)
@@ -156,7 +151,7 @@ static int __init alloc_node_page_ext(int nid)
 		!IS_ALIGNED(node_end_pfn(nid), MAX_ORDER_NR_PAGES))
 		nr_pages += MAX_ORDER_NR_PAGES;
 
-	table_size = get_entry_size() * nr_pages;
+	table_size = page_ext_size * nr_pages;
 
 	base = memblock_alloc_try_nid(
 			table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS),
@@ -234,7 +229,7 @@ static int __meminit init_section_page_ext(unsigned long pfn, int nid)
 	if (section->page_ext)
 		return 0;
 
-	table_size = get_entry_size() * PAGES_PER_SECTION;
+	table_size = page_ext_size * PAGES_PER_SECTION;
 	base = alloc_page_ext(table_size, nid);
 
 	/*
@@ -254,7 +249,7 @@ static int __meminit init_section_page_ext(unsigned long pfn, int nid)
 	 * we need to apply a mask.
 	 */
 	pfn &= PAGE_SECTION_MASK;
-	section->page_ext = (void *)base - get_entry_size() * pfn;
+	section->page_ext = (void *)base - page_ext_size * pfn;
 	total_usage += table_size;
 	return 0;
 }
@@ -267,7 +262,7 @@ static void free_page_ext(void *addr)
 		struct page *page = virt_to_page(addr);
 		size_t table_size;
 
-		table_size = get_entry_size() * PAGES_PER_SECTION;
+		table_size = page_ext_size * PAGES_PER_SECTION;
 
 		BUG_ON(PageReserved(page));
 		kmemleak_free(addr);