Merge branch 'akpm' (patches from Andrew)

Merge misc fixes from Andrew Morton:
 "13 fixes"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  memcg: disable hierarchy support if bound to the legacy cgroup hierarchy
  mm: reorder can_do_mlock to fix audit denial
  kasan, module: move MODULE_ALIGN macro into <linux/moduleloader.h>
  kasan, module, vmalloc: rework shadow allocation for modules
  fanotify: fix event filtering with FAN_ONDIR set
  mm/nommu.c: export symbol max_mapnr
  arch/c6x/include/asm/pgtable.h: define dummy pgprot_writecombine for !MMU
  nilfs2: fix deadlock of segment constructor during recovery
  mm: cma: fix CMA aligned offset calculation
  mm, hugetlb: close race when setting PageTail for gigantic pages
  mm, oom: do not fail __GFP_NOFAIL allocation if oom killer is disabled
  drivers/rtc/rtc-s3c.c: add .needs_src_clk to s3c6410 RTC data
  ocfs2: make append_dio an incompat feature

arch/c6x/include/asm/pgtable.h

@@ -67,6 +67,11 @@ extern unsigned long empty_zero_page;
  */
 #define pgtable_cache_init()   do { } while (0)
 
+/*
+ * c6x is !MMU, so define the simpliest implementation
+ */
+#define pgprot_writecombine pgprot_noncached
+
 #include <asm-generic/pgtable.h>
 
 #endif /* _ASM_C6X_PGTABLE_H */

drivers/rtc/rtc-s3c.c

@@ -849,6 +849,7 @@ static struct s3c_rtc_data const s3c2443_rtc_data = {
 
 static struct s3c_rtc_data const s3c6410_rtc_data = {
 	.max_user_freq		= 32768,
+	.needs_src_clk		= true,
 	.irq_handler		= s3c6410_rtc_irq,
 	.set_freq		= s3c6410_rtc_setfreq,
 	.enable_tick		= s3c6410_rtc_enable_tick,

fs/nilfs2/segment.c

@@ -1907,6 +1907,7 @@ static void nilfs_segctor_drop_written_files(struct nilfs_sc_info *sci,
 					     struct the_nilfs *nilfs)
 {
 	struct nilfs_inode_info *ii, *n;
+	int during_mount = !(sci->sc_super->s_flags & MS_ACTIVE);
 	int defer_iput = false;
 
 	spin_lock(&nilfs->ns_inode_lock);
@@ -1919,10 +1920,10 @@ static void nilfs_segctor_drop_written_files(struct nilfs_sc_info *sci,
 		brelse(ii->i_bh);
 		ii->i_bh = NULL;
 		list_del_init(&ii->i_dirty);
-		if (!ii->vfs_inode.i_nlink) {
+		if (!ii->vfs_inode.i_nlink || during_mount) {
 			/*
-			 * Defer calling iput() to avoid a deadlock
+			 * Defer calling iput() to avoid deadlocks if
-			 * over I_SYNC flag for inodes with i_nlink == 0
+			 * i_nlink == 0 or mount is not yet finished.
 			 */
 			list_add_tail(&ii->i_dirty, &sci->sc_iput_queue);
 			defer_iput = true;

fs/notify/fanotify/fanotify.c

@@ -143,7 +143,8 @@ static bool fanotify_should_send_event(struct fsnotify_mark *inode_mark,
 	    !(marks_mask & FS_ISDIR & ~marks_ignored_mask))
 		return false;
 
-	if (event_mask & marks_mask & ~marks_ignored_mask)
+	if (event_mask & FAN_ALL_OUTGOING_EVENTS & marks_mask &
+				 ~marks_ignored_mask)
 		return true;
 
 	return false;

fs/ocfs2/ocfs2.h

@@ -502,7 +502,7 @@ static inline int ocfs2_writes_unwritten_extents(struct ocfs2_super *osb)
 
 static inline int ocfs2_supports_append_dio(struct ocfs2_super *osb)
 {
-	if (osb->s_feature_ro_compat & OCFS2_FEATURE_RO_COMPAT_APPEND_DIO)
+	if (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_APPEND_DIO)
 		return 1;
 	return 0;
 }

fs/ocfs2/ocfs2_fs.h

@@ -102,11 +102,11 @@
 					 | OCFS2_FEATURE_INCOMPAT_INDEXED_DIRS \
 					 | OCFS2_FEATURE_INCOMPAT_REFCOUNT_TREE \
 					 | OCFS2_FEATURE_INCOMPAT_DISCONTIG_BG	\
-					 | OCFS2_FEATURE_INCOMPAT_CLUSTERINFO)
+					 | OCFS2_FEATURE_INCOMPAT_CLUSTERINFO \
+					 | OCFS2_FEATURE_INCOMPAT_APPEND_DIO)
 #define OCFS2_FEATURE_RO_COMPAT_SUPP	(OCFS2_FEATURE_RO_COMPAT_UNWRITTEN \
 					 | OCFS2_FEATURE_RO_COMPAT_USRQUOTA \
-					 | OCFS2_FEATURE_RO_COMPAT_GRPQUOTA \
+					 | OCFS2_FEATURE_RO_COMPAT_GRPQUOTA)
-					 | OCFS2_FEATURE_RO_COMPAT_APPEND_DIO)
 
 /*
  * Heartbeat-only devices are missing journals and other files.  The
@@ -178,6 +178,11 @@
  */
 #define OCFS2_FEATURE_INCOMPAT_CLUSTERINFO	0x4000
 
+/*
+ * Append Direct IO support
+ */
+#define OCFS2_FEATURE_INCOMPAT_APPEND_DIO	0x8000
+
 /*
  * backup superblock flag is used to indicate that this volume
  * has backup superblocks.
@@ -200,10 +205,6 @@
 #define OCFS2_FEATURE_RO_COMPAT_USRQUOTA	0x0002
 #define OCFS2_FEATURE_RO_COMPAT_GRPQUOTA	0x0004
 
-/*
- * Append Direct IO support
- */
-#define OCFS2_FEATURE_RO_COMPAT_APPEND_DIO	0x0008
 
 /* The byte offset of the first backup block will be 1G.
  * The following will be 4G, 16G, 64G, 256G and 1T.

include/linux/kasan.h

@@ -5,6 +5,7 @@
 
 struct kmem_cache;
 struct page;
+struct vm_struct;
 
 #ifdef CONFIG_KASAN
 
@@ -49,15 +50,11 @@ void kasan_krealloc(const void *object, size_t new_size);
 void kasan_slab_alloc(struct kmem_cache *s, void *object);
 void kasan_slab_free(struct kmem_cache *s, void *object);
 
-#define MODULE_ALIGN (PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT)
-
 int kasan_module_alloc(void *addr, size_t size);
-void kasan_module_free(void *addr);
+void kasan_free_shadow(const struct vm_struct *vm);
 
 #else /* CONFIG_KASAN */
 
-#define MODULE_ALIGN 1
-
 static inline void kasan_unpoison_shadow(const void *address, size_t size) {}
 
 static inline void kasan_enable_current(void) {}
@@ -82,7 +79,7 @@ static inline void kasan_slab_alloc(struct kmem_cache *s, void *object) {}
 static inline void kasan_slab_free(struct kmem_cache *s, void *object) {}
 
 static inline int kasan_module_alloc(void *addr, size_t size) { return 0; }
-static inline void kasan_module_free(void *addr) {}
+static inline void kasan_free_shadow(const struct vm_struct *vm) {}
 
 #endif /* CONFIG_KASAN */
 

include/linux/moduleloader.h

@@ -84,4 +84,12 @@ void module_arch_cleanup(struct module *mod);
 
 /* Any cleanup before freeing mod->module_init */
 void module_arch_freeing_init(struct module *mod);
+
+#ifdef CONFIG_KASAN
+#include <linux/kasan.h>
+#define MODULE_ALIGN (PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT)
+#else
+#define MODULE_ALIGN PAGE_SIZE
+#endif
+
 #endif

include/linux/vmalloc.h

@@ -17,6 +17,7 @@ struct vm_area_struct;		/* vma defining user mapping in mm_types.h */
 #define VM_VPAGES		0x00000010	/* buffer for pages was vmalloc'ed */
 #define VM_UNINITIALIZED	0x00000020	/* vm_struct is not fully initialized */
 #define VM_NO_GUARD		0x00000040      /* don't add guard page */
+#define VM_KASAN		0x00000080      /* has allocated kasan shadow memory */
 /* bits [20..32] reserved for arch specific ioremap internals */
 
 /*

kernel/module.c

@@ -56,7 +56,6 @@
 #include <linux/async.h>
 #include <linux/percpu.h>
 #include <linux/kmemleak.h>
-#include <linux/kasan.h>
 #include <linux/jump_label.h>
 #include <linux/pfn.h>
 #include <linux/bsearch.h>
@@ -1814,7 +1813,6 @@ static void unset_module_init_ro_nx(struct module *mod) { }
 void __weak module_memfree(void *module_region)
 {
 	vfree(module_region);
-	kasan_module_free(module_region);
 }
 
 void __weak module_arch_cleanup(struct module *mod)

mm/cma.c

@@ -64,15 +64,17 @@ static unsigned long cma_bitmap_aligned_mask(struct cma *cma, int align_order)
 	return (1UL << (align_order - cma->order_per_bit)) - 1;
 }
 
+/*
+ * Find a PFN aligned to the specified order and return an offset represented in
+ * order_per_bits.
+ */
 static unsigned long cma_bitmap_aligned_offset(struct cma *cma, int align_order)
 {
-	unsigned int alignment;
-
 	if (align_order <= cma->order_per_bit)
 		return 0;
-	alignment = 1UL << (align_order - cma->order_per_bit);
+
-	return ALIGN(cma->base_pfn, alignment) -
+	return (ALIGN(cma->base_pfn, (1UL << align_order))
-		(cma->base_pfn >> cma->order_per_bit);
+		- cma->base_pfn) >> cma->order_per_bit;
 }
 
 static unsigned long cma_bitmap_maxno(struct cma *cma)

mm/hugetlb.c

@@ -917,7 +917,6 @@ static void prep_compound_gigantic_page(struct page *page, unsigned long order)
 	__SetPageHead(page);
 	__ClearPageReserved(page);
 	for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
-		__SetPageTail(p);
 		/*
 		 * For gigantic hugepages allocated through bootmem at
 		 * boot, it's safer to be consistent with the not-gigantic
@@ -933,6 +932,9 @@ static void prep_compound_gigantic_page(struct page *page, unsigned long order)
 		__ClearPageReserved(p);
 		set_page_count(p, 0);
 		p->first_page = page;
+		/* Make sure p->first_page is always valid for PageTail() */
+		smp_wmb();
+		__SetPageTail(p);
 	}
 }
 

mm/kasan/kasan.c

@@ -29,6 +29,7 @@
 #include <linux/stacktrace.h>
 #include <linux/string.h>
 #include <linux/types.h>
+#include <linux/vmalloc.h>
 #include <linux/kasan.h>
 
 #include "kasan.h"
@@ -414,12 +415,19 @@ int kasan_module_alloc(void *addr, size_t size)
 			GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO,
 			PAGE_KERNEL, VM_NO_GUARD, NUMA_NO_NODE,
 			__builtin_return_address(0));
-	return ret ? 0 : -ENOMEM;
+
+	if (ret) {
+		find_vm_area(addr)->flags |= VM_KASAN;
+		return 0;
+	}
+
+	return -ENOMEM;
 }
 
-void kasan_module_free(void *addr)
+void kasan_free_shadow(const struct vm_struct *vm)
 {
-	vfree(kasan_mem_to_shadow(addr));
+	if (vm->flags & VM_KASAN)
+		vfree(kasan_mem_to_shadow(vm->addr));
 }
 
 static void register_global(struct kasan_global *global)

mm/memcontrol.c

@@ -5232,7 +5232,9 @@ static void mem_cgroup_bind(struct cgroup_subsys_state *root_css)
 	 * on for the root memcg is enough.
 	 */
 	if (cgroup_on_dfl(root_css->cgroup))
-		mem_cgroup_from_css(root_css)->use_hierarchy = true;
+		root_mem_cgroup->use_hierarchy = true;
+	else
+		root_mem_cgroup->use_hierarchy = false;
 }
 
 static u64 memory_current_read(struct cgroup_subsys_state *css,

mm/mlock.c

@@ -26,10 +26,10 @@
 
 int can_do_mlock(void)
 {
-	if (capable(CAP_IPC_LOCK))
-		return 1;
 	if (rlimit(RLIMIT_MEMLOCK) != 0)
 		return 1;
+	if (capable(CAP_IPC_LOCK))
+		return 1;
 	return 0;
 }
 EXPORT_SYMBOL(can_do_mlock);

mm/nommu.c

@@ -62,6 +62,7 @@ void *high_memory;
 EXPORT_SYMBOL(high_memory);
 struct page *mem_map;
 unsigned long max_mapnr;
+EXPORT_SYMBOL(max_mapnr);
 unsigned long highest_memmap_pfn;
 struct percpu_counter vm_committed_as;
 int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */

mm/page_alloc.c

@@ -2373,7 +2373,8 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 			goto out;
 	}
 	/* Exhausted what can be done so it's blamo time */
-	if (out_of_memory(ac->zonelist, gfp_mask, order, ac->nodemask, false))
+	if (out_of_memory(ac->zonelist, gfp_mask, order, ac->nodemask, false)
+			|| WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL))
 		*did_some_progress = 1;
 out:
 	oom_zonelist_unlock(ac->zonelist, gfp_mask);

mm/vmalloc.c

@@ -1418,6 +1418,7 @@ struct vm_struct *remove_vm_area(const void *addr)
 		spin_unlock(&vmap_area_lock);
 
 		vmap_debug_free_range(va->va_start, va->va_end);
+		kasan_free_shadow(vm);
 		free_unmap_vmap_area(va);
 		vm->size -= PAGE_SIZE;