Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:

 - a few misc things

 - most of MM

 - KASAN updates

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (102 commits)
  kasan: separate report parts by empty lines
  kasan: improve double-free report format
  kasan: print page description after stacks
  kasan: improve slab object description
  kasan: change report header
  kasan: simplify address description logic
  kasan: change allocation and freeing stack traces headers
  kasan: unify report headers
  kasan: introduce helper functions for determining bug type
  mm: hwpoison: call shake_page() after try_to_unmap() for mlocked page
  mm: hwpoison: call shake_page() unconditionally
  mm/swapfile.c: fix swap space leak in error path of swap_free_entries()
  mm/gup.c: fix access_ok() argument type
  mm/truncate: avoid pointless cleancache_invalidate_inode() calls.
  mm/truncate: bail out early from invalidate_inode_pages2_range() if mapping is empty
  fs/block_dev: always invalidate cleancache in invalidate_bdev()
  fs: fix data invalidation in the cleancache during direct IO
  zram: reduce load operation in page_same_filled
  zram: use zram_free_page instead of open-coded
  zram: introduce zram data accessor
  ...

Documentation/cgroup-v2.txt

@@ -871,6 +871,11 @@ PAGE_SIZE multiple when read back.
 
 		Amount of memory used in network transmission buffers
 
+	  shmem
+
+		Amount of cached filesystem data that is swap-backed,
+		such as tmpfs, shm segments, shared anonymous mmap()s
+
 	  file_mapped
 
 		Amount of cached filesystem data mapped with mmap()

Documentation/filesystems/proc.txt

@@ -413,6 +413,7 @@ Private_Clean:         0 kB
 Private_Dirty:         0 kB
 Referenced:          892 kB
 Anonymous:             0 kB
+LazyFree:              0 kB
 AnonHugePages:         0 kB
 ShmemPmdMapped:        0 kB
 Shared_Hugetlb:        0 kB
@@ -442,6 +443,11 @@ accessed.
 "Anonymous" shows the amount of memory that does not belong to any file.  Even
 a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE
 and a page is modified, the file page is replaced by a private anonymous copy.
+"LazyFree" shows the amount of memory which is marked by madvise(MADV_FREE).
+The memory isn't freed immediately with madvise(). It's freed in memory
+pressure if the memory is clean. Please note that the printed value might
+be lower than the real value due to optimizations used in the current
+implementation. If this is not desirable please file a bug report.
 "AnonHugePages" shows the ammount of memory backed by transparent hugepage.
 "ShmemPmdMapped" shows the ammount of shared (shmem/tmpfs) memory backed by
 huge pages.

Documentation/vm/00-INDEX

@@ -12,6 +12,8 @@ highmem.txt
 	- Outline of highmem and common issues.
 hugetlbpage.txt
 	- a brief summary of hugetlbpage support in the Linux kernel.
+hugetlbfs_reserv.txt
+	- A brief overview of hugetlbfs reservation design/implementation.
 hwpoison.txt
 	- explains what hwpoison is
 idle_page_tracking.txt

arch/blackfin/mach-bf609/clock.c

@@ -97,6 +97,9 @@ EXPORT_SYMBOL(clk_enable);
 
 void clk_disable(struct clk *clk)
 {
+	if (!clk)
+		return;
+
 	if (clk->ops && clk->ops->disable)
 		clk->ops->disable(clk);
 }

drivers/block/zram/zram_drv.h

@@ -92,13 +92,9 @@ struct zram_stats {
 	atomic64_t writestall;		/* no. of write slow paths */
 };
 
-struct zram_meta {
+struct zram {
 	struct zram_table_entry *table;
 	struct zs_pool *mem_pool;
-};
-
-struct zram {
-	struct zram_meta *meta;
 	struct zcomp *comp;
 	struct gendisk *disk;
 	/* Prevent concurrent execution of device init */

drivers/tty/sysrq.c

@@ -372,7 +372,7 @@ static void moom_callback(struct work_struct *ignored)
 
 	mutex_lock(&oom_lock);
 	if (!out_of_memory(&oc))
-		pr_info("OOM request ignored because killer is disabled\n");
+		pr_info("OOM request ignored. No task eligible\n");
 	mutex_unlock(&oom_lock);
 }
 

fs/block_dev.c

@@ -103,12 +103,11 @@ void invalidate_bdev(struct block_device *bdev)
 {
 	struct address_space *mapping = bdev->bd_inode->i_mapping;
 
-	if (mapping->nrpages == 0)
+	if (mapping->nrpages) {
-		return;
+		invalidate_bh_lrus();
-
+		lru_add_drain_all();	/* make sure all lru add caches are flushed */
-	invalidate_bh_lrus();
+		invalidate_mapping_pages(mapping, 0, -1);
-	lru_add_drain_all();	/* make sure all lru add caches are flushed */
+	}
-	invalidate_mapping_pages(mapping, 0, -1);
 	/* 99% of the time, we don't need to flush the cleancache on the bdev.
 	 * But, for the strange corners, lets be cautious
 	 */

fs/iomap.c

@@ -887,16 +887,14 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		flags |= IOMAP_WRITE;
 	}
 
-	if (mapping->nrpages) {
+	ret = filemap_write_and_wait_range(mapping, start, end);
-		ret = filemap_write_and_wait_range(mapping, start, end);
+	if (ret)
-		if (ret)
+		goto out_free_dio;
-			goto out_free_dio;
 
-		ret = invalidate_inode_pages2_range(mapping,
+	ret = invalidate_inode_pages2_range(mapping,
-				start >> PAGE_SHIFT, end >> PAGE_SHIFT);
+			start >> PAGE_SHIFT, end >> PAGE_SHIFT);
-		WARN_ON_ONCE(ret);
+	WARN_ON_ONCE(ret);
-		ret = 0;
+	ret = 0;
-	}
 
 	inode_dio_begin(inode);
 
@@ -951,7 +949,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	 * one is a pretty crazy thing to do, so we don't support it 100%.  If
 	 * this invalidation fails, tough, the write still worked...
 	 */
-	if (iov_iter_rw(iter) == WRITE && mapping->nrpages) {
+	if (iov_iter_rw(iter) == WRITE) {
 		int err = invalidate_inode_pages2_range(mapping,
 				start >> PAGE_SHIFT, end >> PAGE_SHIFT);
 		WARN_ON_ONCE(err);

fs/jbd2/journal.c

@@ -43,6 +43,7 @@
 #include <linux/backing-dev.h>
 #include <linux/bitops.h>
 #include <linux/ratelimit.h>
+#include <linux/sched/mm.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/jbd2.h>
@@ -205,6 +206,14 @@ static int kjournald2(void *arg)
 	journal->j_task = current;
 	wake_up(&journal->j_wait_done_commit);
 
+	/*
+	 * Make sure that no allocations from this kernel thread will ever
+	 * recurse to the fs layer because we are responsible for the
+	 * transaction commit and any fs involvement might get stuck waiting for
+	 * the trasn. commit.
+	 */
+	memalloc_nofs_save();
+
 	/*
 	 * And now, wait forever for commit wakeup events.
 	 */

fs/jbd2/transaction.c

@@ -29,6 +29,7 @@
 #include <linux/backing-dev.h>
 #include <linux/bug.h>
 #include <linux/module.h>
+#include <linux/sched/mm.h>
 
 #include <trace/events/jbd2.h>
 
@@ -388,6 +389,11 @@ repeat:
 
 	rwsem_acquire_read(&journal->j_trans_commit_map, 0, 0, _THIS_IP_);
 	jbd2_journal_free_transaction(new_transaction);
+	/*
+	 * Ensure that no allocations done while the transaction is open are
+	 * going to recurse back to the fs layer.
+	 */
+	handle->saved_alloc_context = memalloc_nofs_save();
 	return 0;
 }
 
@@ -466,6 +472,7 @@ handle_t *jbd2__journal_start(journal_t *journal, int nblocks, int rsv_blocks,
 	trace_jbd2_handle_start(journal->j_fs_dev->bd_dev,
 				handle->h_transaction->t_tid, type,
 				line_no, nblocks);
+
 	return handle;
 }
 EXPORT_SYMBOL(jbd2__journal_start);
@@ -1760,6 +1767,11 @@ int jbd2_journal_stop(handle_t *handle)
 	if (handle->h_rsv_handle)
 		jbd2_journal_free_reserved(handle->h_rsv_handle);
 free_and_exit:
+	/*
+	 * Scope of the GFP_NOFS context is over here and so we can restore the
+	 * original alloc context.
+	 */
+	memalloc_nofs_restore(handle->saved_alloc_context);
 	jbd2_free_handle(handle);
 	return err;
 }

fs/ocfs2/cluster/heartbeat.c

@@ -2242,13 +2242,13 @@ unlock:
 	spin_unlock(&o2hb_live_lock);
 }
 
-static ssize_t o2hb_heartbeat_group_threshold_show(struct config_item *item,
+static ssize_t o2hb_heartbeat_group_dead_threshold_show(struct config_item *item,
 		char *page)
 {
 	return sprintf(page, "%u\n", o2hb_dead_threshold);
 }
 
-static ssize_t o2hb_heartbeat_group_threshold_store(struct config_item *item,
+static ssize_t o2hb_heartbeat_group_dead_threshold_store(struct config_item *item,
 		const char *page, size_t count)
 {
 	unsigned long tmp;
@@ -2297,11 +2297,11 @@ static ssize_t o2hb_heartbeat_group_mode_store(struct config_item *item,
 
 }
 
-CONFIGFS_ATTR(o2hb_heartbeat_group_, threshold);
+CONFIGFS_ATTR(o2hb_heartbeat_group_, dead_threshold);
 CONFIGFS_ATTR(o2hb_heartbeat_group_, mode);
 
 static struct configfs_attribute *o2hb_heartbeat_group_attrs[] = {
-	&o2hb_heartbeat_group_attr_threshold,
+	&o2hb_heartbeat_group_attr_dead_threshold,
 	&o2hb_heartbeat_group_attr_mode,
 	NULL,
 };

fs/ocfs2/cluster/tcp.c

@@ -450,9 +450,8 @@ static struct o2net_sock_container *sc_alloc(struct o2nm_node *node)
 	INIT_WORK(&sc->sc_shutdown_work, o2net_shutdown_sc);
 	INIT_DELAYED_WORK(&sc->sc_keepalive_work, o2net_sc_send_keep_req);
 
-	init_timer(&sc->sc_idle_timeout);
+	setup_timer(&sc->sc_idle_timeout, o2net_idle_timer,
-	sc->sc_idle_timeout.function = o2net_idle_timer;
+		    (unsigned long)sc);
-	sc->sc_idle_timeout.data = (unsigned long)sc;
 
 	sclog(sc, "alloced\n");
 
@@ -956,7 +955,7 @@ static void o2net_sendpage(struct o2net_sock_container *sc,
 		mutex_lock(&sc->sc_send_lock);
 		ret = sc->sc_sock->ops->sendpage(sc->sc_sock,
 						 virt_to_page(kmalloced_virt),
-						 (long)kmalloced_virt & ~PAGE_MASK,
+						 offset_in_page(kmalloced_virt),
 						 size, MSG_DONTWAIT);
 		mutex_unlock(&sc->sc_send_lock);
 		if (ret == size)

fs/proc/task_mmu.c

@@ -441,6 +441,7 @@ struct mem_size_stats {
 	unsigned long private_dirty;
 	unsigned long referenced;
 	unsigned long anonymous;
+	unsigned long lazyfree;
 	unsigned long anonymous_thp;
 	unsigned long shmem_thp;
 	unsigned long swap;
@@ -457,8 +458,11 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page,
 	int i, nr = compound ? 1 << compound_order(page) : 1;
 	unsigned long size = nr * PAGE_SIZE;
 
-	if (PageAnon(page))
+	if (PageAnon(page)) {
 		mss->anonymous += size;
+		if (!PageSwapBacked(page) && !dirty && !PageDirty(page))
+			mss->lazyfree += size;
+	}
 
 	mss->resident += size;
 	/* Accumulate the size in pages that have been accessed. */
@@ -771,6 +775,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 		   "Private_Dirty:  %8lu kB\n"
 		   "Referenced:     %8lu kB\n"
 		   "Anonymous:      %8lu kB\n"
+		   "LazyFree:       %8lu kB\n"
 		   "AnonHugePages:  %8lu kB\n"
 		   "ShmemPmdMapped: %8lu kB\n"
 		   "Shared_Hugetlb: %8lu kB\n"
@@ -789,6 +794,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 		   mss.private_dirty >> 10,
 		   mss.referenced >> 10,
 		   mss.anonymous >> 10,
+		   mss.lazyfree >> 10,
 		   mss.anonymous_thp >> 10,
 		   mss.shmem_thp >> 10,
 		   mss.shared_hugetlb >> 10,

fs/xfs/kmem.c

@@ -48,7 +48,7 @@ kmem_alloc(size_t size, xfs_km_flags_t flags)
 void *
 kmem_zalloc_large(size_t size, xfs_km_flags_t flags)
 {
-	unsigned noio_flag = 0;
+	unsigned nofs_flag = 0;
 	void	*ptr;
 	gfp_t	lflags;
 
@@ -60,17 +60,17 @@ kmem_zalloc_large(size_t size, xfs_km_flags_t flags)
 	 * __vmalloc() will allocate data pages and auxillary structures (e.g.
 	 * pagetables) with GFP_KERNEL, yet we may be under GFP_NOFS context
 	 * here. Hence we need to tell memory reclaim that we are in such a
-	 * context via PF_MEMALLOC_NOIO to prevent memory reclaim re-entering
+	 * context via PF_MEMALLOC_NOFS to prevent memory reclaim re-entering
 	 * the filesystem here and potentially deadlocking.
 	 */
-	if ((current->flags & PF_FSTRANS) || (flags & KM_NOFS))
+	if (flags & KM_NOFS)
-		noio_flag = memalloc_noio_save();
+		nofs_flag = memalloc_nofs_save();
 
 	lflags = kmem_flags_convert(flags);
 	ptr = __vmalloc(size, lflags | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL);
 
-	if ((current->flags & PF_FSTRANS) || (flags & KM_NOFS))
+	if (flags & KM_NOFS)
-		memalloc_noio_restore(noio_flag);
+		memalloc_nofs_restore(nofs_flag);
 
 	return ptr;
 }

fs/xfs/kmem.h

@@ -50,7 +50,7 @@ kmem_flags_convert(xfs_km_flags_t flags)
 		lflags = GFP_ATOMIC | __GFP_NOWARN;
 	} else {
 		lflags = GFP_KERNEL | __GFP_NOWARN;
-		if ((current->flags & PF_FSTRANS) || (flags & KM_NOFS))
+		if (flags & KM_NOFS)
 			lflags &= ~__GFP_FS;
 	}
 

fs/xfs/libxfs/xfs_btree.c

@@ -2886,7 +2886,7 @@ xfs_btree_split_worker(
 	struct xfs_btree_split_args	*args = container_of(work,
 						struct xfs_btree_split_args, work);
 	unsigned long		pflags;
-	unsigned long		new_pflags = PF_FSTRANS;
+	unsigned long		new_pflags = PF_MEMALLOC_NOFS;
 
 	/*
 	 * we are in a transaction context here, but may also be doing work

fs/xfs/xfs_aops.c

@@ -189,7 +189,7 @@ xfs_setfilesize_trans_alloc(
 	 * We hand off the transaction to the completion thread now, so
 	 * clear the flag here.
 	 */
-	current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS);
+	current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
 	return 0;
 }
 
@@ -252,7 +252,7 @@ xfs_setfilesize_ioend(
 	 * thus we need to mark ourselves as being in a transaction manually.
 	 * Similarly for freeze protection.
 	 */
-	current_set_flags_nested(&tp->t_pflags, PF_FSTRANS);
+	current_set_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
 	__sb_writers_acquired(VFS_I(ip)->i_sb, SB_FREEZE_FS);
 
 	/* we abort the update if there was an IO error */
@@ -1016,7 +1016,7 @@ xfs_do_writepage(
 	 * Given that we do not allow direct reclaim to call us, we should
 	 * never be called while in a filesystem transaction.
 	 */
-	if (WARN_ON_ONCE(current->flags & PF_FSTRANS))
+	if (WARN_ON_ONCE(current->flags & PF_MEMALLOC_NOFS))
 		goto redirty;
 
 	/*

fs/xfs/xfs_buf.c

@@ -443,17 +443,17 @@ _xfs_buf_map_pages(
 		bp->b_addr = NULL;
 	} else {
 		int retried = 0;
-		unsigned noio_flag;
+		unsigned nofs_flag;
 
 		/*
 		 * vm_map_ram() will allocate auxillary structures (e.g.
 		 * pagetables) with GFP_KERNEL, yet we are likely to be under
 		 * GFP_NOFS context here. Hence we need to tell memory reclaim
-		 * that we are in such a context via PF_MEMALLOC_NOIO to prevent
+		 * that we are in such a context via PF_MEMALLOC_NOFS to prevent
 		 * memory reclaim re-entering the filesystem here and
 		 * potentially deadlocking.
 		 */
-		noio_flag = memalloc_noio_save();
+		nofs_flag = memalloc_nofs_save();
 		do {
 			bp->b_addr = vm_map_ram(bp->b_pages, bp->b_page_count,
 						-1, PAGE_KERNEL);
@@ -461,7 +461,7 @@ _xfs_buf_map_pages(
 				break;
 			vm_unmap_aliases();
 		} while (retried++ <= 1);
-		memalloc_noio_restore(noio_flag);
+		memalloc_nofs_restore(nofs_flag);
 
 		if (!bp->b_addr)
 			return -ENOMEM;