Merge tag 'v4.1.42' into 4.1-2.0.x-imx

Linux 4.1.42

* tag 'v4.1.42': (146 commits)
  Linux 4.1.42
  mm: fix new crash in unmapped_area_topdown()
  mm: larger stack guard gap, between vmas
  alarmtimer: Rate limit periodic intervals
  MIPS: Fix bnezc/jialc return address calculation
  usb: dwc3: exynos fix axius clock error path to do cleanup
  genirq: Release resources in __setup_irq() error path
  swap: cond_resched in swap_cgroup_prepare()
  mm/memory-failure.c: use compound_head() flags for huge pages
  USB: gadgetfs, dummy-hcd, net2280: fix locking for callbacks
  usb: xhci: ASMedia ASM1042A chipset need shorts TX quirk
  drivers/misc/c2port/c2port-duramar2150.c: checking for NULL instead of IS_ERR()
  usb: r8a66597-hcd: decrease timeout
  usb: r8a66597-hcd: select a different endpoint on timeout
  USB: gadget: dummy_hcd: fix hub-descriptor removable fields
  [media] pvrusb2: reduce stack usage pvr2_eeprom_analyze()
  usb: core: fix potential memory leak in error path during hcd creation
  USB: hub: fix SS max number of ports
  iio: proximity: as3935: recalibrate RCO after resume
  staging: rtl8188eu: prevent an underflow in rtw_check_beacon_data()
  ...

30 files changed, 209 insertions, 91 deletions

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 2771bc32dbd9..1d8b3f8c3654 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3732,6 +3732,7 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
 				    info->space_info_kobj, "%s",
 				    alloc_name(found->flags));
 	if (ret) {
+		percpu_counter_destroy(&found->total_bytes_pinned);
 		kfree(found);
 		return ret;
 	}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 757a34bdd2b9..04997ac958c4 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7251,8 +7251,8 @@ bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end)
 	int found = false;
 	void **pagep = NULL;
 	struct page *page = NULL;
-	int start_idx;
-	int end_idx;
+	unsigned long start_idx;
+	unsigned long end_idx;
 
 	start_idx = start >> PAGE_CACHE_SHIFT;
 
diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c
index cc9f2546ea4a..52fc4e25a7cb 100644
--- a/fs/configfs/symlink.c
+++ b/fs/configfs/symlink.c
@@ -83,14 +83,13 @@ static int create_link(struct config_item *parent_item,
 	ret = -ENOMEM;
 	sl = kmalloc(sizeof(struct configfs_symlink), GFP_KERNEL);
 	if (sl) {
-		sl->sl_target = config_item_get(item);
 		spin_lock(&configfs_dirent_lock);
 		if (target_sd->s_type & CONFIGFS_USET_DROPPING) {
 			spin_unlock(&configfs_dirent_lock);
-			config_item_put(item);
 			kfree(sl);
 			return -ENOENT;
 		}
+		sl->sl_target = config_item_get(item);
 		list_add(&sl->sl_list, &target_sd->s_links);
 		spin_unlock(&configfs_dirent_lock);
 		ret = configfs_create_link(sl, parent_item->ci_dentry,
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 0d062ffacb24..ece4982ee593 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -354,47 +354,27 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
 		num = min_t(pgoff_t, end - index, PAGEVEC_SIZE);
 		nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index,
 					  (pgoff_t)num);
-		if (nr_pages == 0) {
-			if (whence == SEEK_DATA)
-				break;
-
-			BUG_ON(whence != SEEK_HOLE);
-			/*
-			 * If this is the first time to go into the loop and
-			 * offset is not beyond the end offset, it will be a
-			 * hole at this offset
-			 */
-			if (lastoff == startoff || lastoff < endoff)
-				found = 1;
+		if (nr_pages == 0)
 			break;
-		}
-
-		/*
-		 * If this is the first time to go into the loop and
-		 * offset is smaller than the first page offset, it will be a
-		 * hole at this offset.
-		 */
-		if (lastoff == startoff && whence == SEEK_HOLE &&
-		    lastoff < page_offset(pvec.pages[0])) {
-			found = 1;
-			break;
-		}
 
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 			struct buffer_head *bh, *head;
 
 			/*
-			 * If the current offset is not beyond the end of given
-			 * range, it will be a hole.
+			 * If current offset is smaller than the page offset,
+			 * there is a hole at this offset.
 			 */
-			if (lastoff < endoff && whence == SEEK_HOLE &&
-			    page->index > end) {
+			if (whence == SEEK_HOLE && lastoff < endoff &&
+			    lastoff < page_offset(pvec.pages[i])) {
 				found = 1;
 				*offset = lastoff;
 				goto out;
 			}
 
+			if (page->index > end)
+				goto out;
+
 			lock_page(page);
 
 			if (unlikely(page->mapping != inode->i_mapping)) {
@@ -434,20 +414,18 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
 			unlock_page(page);
 		}
 
-		/*
-		 * The no. of pages is less than our desired, that would be a
-		 * hole in there.
-		 */
-		if (nr_pages < num && whence == SEEK_HOLE) {
-			found = 1;
-			*offset = lastoff;
+		/* The no. of pages is less than our desired, we are done. */
+		if (nr_pages < num)
 			break;
-		}
 
 		index = pvec.pages[i - 1]->index + 1;
 		pagevec_release(&pvec);
 	} while (index <= end);
 
+	if (whence == SEEK_HOLE && lastoff < endoff) {
+		found = 1;
+		*offset = lastoff;
+	}
 out:
 	pagevec_release(&pvec);
 	return found;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 66e147b446c8..2ab9fd88a7c3 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5083,8 +5083,9 @@ static int ext4_expand_extra_isize(struct inode *inode,
 	/* No extended attributes present */
 	if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR) ||
 	    header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)) {
-		memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE, 0,
-			new_extra_isize);
+		memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE +
+		       EXT4_I(inode)->i_extra_isize, 0,
+		       new_extra_isize - EXT4_I(inode)->i_extra_isize);
 		EXT4_I(inode)->i_extra_isize = new_extra_isize;
 		return 0;
 	}
diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c
index 89acec742e0b..169685fa374d 100644
--- a/fs/fscache/cookie.c
+++ b/fs/fscache/cookie.c
@@ -541,6 +541,7 @@ void __fscache_disable_cookie(struct fscache_cookie *cookie, bool invalidate)
 		hlist_for_each_entry(object, &cookie->backing_objects, cookie_link) {
 			if (invalidate)
 				set_bit(FSCACHE_OBJECT_RETIRED, &object->flags);
+			clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
 			fscache_raise_event(object, FSCACHE_OBJECT_EV_KILL);
 		}
 	} else {
@@ -559,6 +560,10 @@ void __fscache_disable_cookie(struct fscache_cookie *cookie, bool invalidate)
 		wait_on_atomic_t(&cookie->n_active, fscache_wait_atomic_t,
 				 TASK_UNINTERRUPTIBLE);
 
+	/* Make sure any pending writes are cancelled. */
+	if (cookie->def->type != FSCACHE_COOKIE_TYPE_INDEX)
+		fscache_invalidate_writes(cookie);
+
 	/* Reset the cookie state if it wasn't relinquished */
 	if (!test_bit(FSCACHE_COOKIE_RELINQUISHED, &cookie->flags)) {
 		atomic_inc(&cookie->n_active);
diff --git a/fs/fscache/object.c b/fs/fscache/object.c
index da032daf0e0d..4231621225c3 100644
--- a/fs/fscache/object.c
+++ b/fs/fscache/object.c
@@ -632,6 +632,12 @@ static const struct fscache_state *fscache_kill_object(struct fscache_object *ob
 	clear_bit(FSCACHE_OBJECT_IS_LIVE, &object->flags);
 	object->oob_event_mask = 0;
 
+	if (test_bit(FSCACHE_OBJECT_RETIRED, &object->flags)) {
+		/* Reject any new read/write ops and abort any that are pending. */
+		clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
+		fscache_cancel_all_ops(object);
+	}
+
 	if (list_empty(&object->dependents) &&
 	    object->n_ops == 0 &&
 	    object->n_children == 0)
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index a533d8c66489..320150137f99 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -168,7 +168,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 		addr = ALIGN(addr, huge_page_size(h));
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 2b50bc0c545e..1e58fa0a28a3 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1701,6 +1701,12 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
 			opdesc->op_get_currentstateid(cstate, &op->u);
 		op->status = opdesc->op_func(rqstp, cstate, &op->u);
 
+		/* Only from SEQUENCE */
+		if (cstate->status == nfserr_replay_cache) {
+			dprintk("%s NFS4.1 replay from cache\n", __func__);
+			status = op->status;
+			goto out;
+		}
 		if (!op->status) {
 			if (opdesc->op_set_currentstateid)
 				opdesc->op_set_currentstateid(cstate, &op->u);
@@ -1711,14 +1717,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
 			if (need_wrongsec_check(rqstp))
 				op->status = check_nfsd_access(current_fh->fh_export, rqstp);
 		}
-
 encode_op:
-		/* Only from SEQUENCE */
-		if (cstate->status == nfserr_replay_cache) {
-			dprintk("%s NFS4.1 replay from cache\n", __func__);
-			status = op->status;
-			goto out;
-		}
 		if (op->status == nfserr_replay_me) {
 			op->replay = &cstate->replay_owner->so_replay;
 			nfsd4_encode_replay(&resp->xdr, op);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index fab32ad5d96d..d5665490563b 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2880,6 +2880,8 @@ int proc_pid_readdir(struct file *file, struct dir_context *ctx)
 	     iter.tgid += 1, iter = next_tgid(ns, iter)) {
 		char name[PROC_NUMBUF];
 		int len;
+
+		cond_resched();
 		if (!has_pid_permissions(ns, iter.task, 2))
 			continue;
 
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 32287fb146db..72c60f0b4b28 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -287,11 +287,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 
 	/* We don't show the stack guard page in /proc/maps */
 	start = vma->vm_start;
-	if (stack_guard_page_start(vma, start))
-		start += PAGE_SIZE;
 	end = vma->vm_end;
-	if (stack_guard_page_end(vma, end))
-		end -= PAGE_SIZE;
 
 	seq_setwidth(m, 25 + sizeof(void *) * 6 - 1);
 	seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ",
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index 268733cda397..5f4f1882dc7d 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -74,6 +74,7 @@
 #include <linux/highmem.h>
 #include <linux/pagemap.h>
 #include <linux/uaccess.h>
+#include <linux/major.h>
 #include "internal.h"
 
 static struct kmem_cache *romfs_inode_cachep;
@@ -415,7 +416,22 @@ static void romfs_destroy_inode(struct inode *inode)
 static int romfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct super_block *sb = dentry->d_sb;
-	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
+	u64 id = 0;
+
+	/* When calling huge_encode_dev(),
+	 * use sb->s_bdev->bd_dev when,
+	 *   - CONFIG_ROMFS_ON_BLOCK defined
+	 * use sb->s_dev when,
+	 *   - CONFIG_ROMFS_ON_BLOCK undefined and
+	 *   - CONFIG_ROMFS_ON_MTD defined
+	 * leave id as 0 when,
+	 *   - CONFIG_ROMFS_ON_BLOCK undefined and
+	 *   - CONFIG_ROMFS_ON_MTD undefined
+	 */
+	if (sb->s_bdev)
+		id = huge_encode_dev(sb->s_bdev->bd_dev);
+	else if (sb->s_dev)
+		id = huge_encode_dev(sb->s_dev);
 
 	buf->f_type = ROMFS_MAGIC;
 	buf->f_namelen = ROMFS_MAXFN;
@@ -488,6 +504,11 @@ static int romfs_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_flags |= MS_RDONLY | MS_NOATIME;
 	sb->s_op = &romfs_super_ops;
 
+#ifdef CONFIG_ROMFS_ON_MTD
+	/* Use same dev ID from the underlying mtdblock device */
+	if (sb->s_mtd)
+		sb->s_dev = MKDEV(MTD_BLOCK_MAJOR, sb->s_mtd->index);
+#endif
 	/* read the image superblock and check it */
 	rsb = kmalloc(512, GFP_KERNEL);
 	if (!rsb)
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index dc33f9416340..e295994fbbf0 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -764,6 +764,23 @@ static void ufs_put_super(struct super_block *sb)
 	return;
 }
 
+static u64 ufs_max_bytes(struct super_block *sb)
+{
+	struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi;
+	int bits = uspi->s_apbshift;
+	u64 res;
+
+	if (bits > 21)
+		res = ~0ULL;
+	else
+		res = UFS_NDADDR + (1LL << bits) + (1LL << (2*bits)) +
+			(1LL << (3*bits));
+
+	if (res >= (MAX_LFS_FILESIZE >> uspi->s_bshift))
+		return MAX_LFS_FILESIZE;
+	return res << uspi->s_bshift;
+}
+
 static int ufs_fill_super(struct super_block *sb, void *data, int silent)
 {
 	struct ufs_sb_info * sbi;
@@ -831,9 +848,8 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent)
 	uspi->s_dirblksize = UFS_SECTOR_SIZE;
 	super_block_offset=UFS_SBLOCK;
 
-	/* Keep 2Gig file limit. Some UFS variants need to override 
-	   this but as I don't know which I'll let those in the know loosen
-	   the rules */
+	sb->s_maxbytes = MAX_LFS_FILESIZE;
+
 	switch (sbi->s_mount_opt & UFS_MOUNT_UFSTYPE) {
 	case UFS_MOUNT_UFSTYPE_44BSD:
 		UFSD("ufstype=44bsd\n");
@@ -1231,6 +1247,7 @@ magic_found:
 			    "fast symlink size (%u)\n", uspi->s_maxsymlinklen);
 		uspi->s_maxsymlinklen = maxsymlen;
 	}
+	sb->s_maxbytes = ufs_max_bytes(sb);
 	sb->s_max_links = UFS_LINK_MAX;
 
 	inode = ufs_iget(sb, UFS_ROOTINO);
diff --git a/fs/ufs/util.h b/fs/ufs/util.h
index 954175928240..3f9463f8cf2f 100644
--- a/fs/ufs/util.h
+++ b/fs/ufs/util.h
@@ -473,15 +473,19 @@ static inline unsigned _ubh_find_last_zero_bit_(
 static inline int _ubh_isblockset_(struct ufs_sb_private_info * uspi,
 	struct ufs_buffer_head * ubh, unsigned begin, unsigned block)
 {
+	u8 mask;
 	switch (uspi->s_fpb) {
 	case 8:
 	    	return (*ubh_get_addr (ubh, begin + block) == 0xff);
 	case 4:
-		return (*ubh_get_addr (ubh, begin + (block >> 1)) == (0x0f << ((block & 0x01) << 2)));
+		mask = 0x0f << ((block & 0x01) << 2);
+		return (*ubh_get_addr (ubh, begin + (block >> 1)) & mask) == mask;
 	case 2:
-		return (*ubh_get_addr (ubh, begin + (block >> 2)) == (0x03 << ((block & 0x03) << 1)));
+		mask = 0x03 << ((block & 0x03) << 1);
+		return (*ubh_get_addr (ubh, begin + (block >> 2)) & mask) == mask;
 	case 1:
-		return (*ubh_get_addr (ubh, begin + (block >> 3)) == (0x01 << (block & 0x07)));
+		mask = 0x01 << (block & 0x07);
+		return (*ubh_get_addr (ubh, begin + (block >> 3)) & mask) == mask;
 	}
 	return 0;	
 }
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index f1026e86dabc..51c85b6a0c34 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -2180,8 +2180,10 @@ xfs_bmap_add_extent_delay_real(
 		}
 		temp = xfs_bmap_worst_indlen(bma->ip, temp);
 		temp2 = xfs_bmap_worst_indlen(bma->ip, temp2);
-		diff = (int)(temp + temp2 - startblockval(PREV.br_startblock) -
-			(bma->cur ? bma->cur->bc_private.b.allocated : 0));
+		diff = (int)(temp + temp2 -
+			     (startblockval(PREV.br_startblock) -
+			      (bma->cur ?
+			       bma->cur->bc_private.b.allocated : 0)));
 		if (diff > 0) {
 			error = xfs_mod_fdblocks(bma->ip->i_mount,
 						 -((int64_t)diff), false);
@@ -2233,7 +2235,6 @@ xfs_bmap_add_extent_delay_real(
 		temp = da_new;
 		if (bma->cur)
 			temp += bma->cur->bc_private.b.allocated;
-		ASSERT(temp <= da_old);
 		if (temp < da_old)
 			xfs_mod_fdblocks(bma->ip->i_mount,
 					(int64_t)(da_old - temp), false);
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index c72283dd8d44..1c677b7c274b 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -4049,7 +4049,7 @@ xfs_btree_change_owner(
 			xfs_btree_readahead_ptr(cur, ptr, 1);
 
 			/* save for the next iteration of the loop */
-			lptr = *ptr;
+			xfs_btree_copy_ptrs(cur, &lptr, ptr, 1);
 		}
 
 		/* for each buffer in the level */
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index a52bbd3abc7d..80b540c75512 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -656,7 +656,7 @@ xfs_getbmap(
 			 * extents.
 			 */
 			if (map[i].br_startblock == DELAYSTARTBLOCK &&
-			    map[i].br_startoff <= XFS_B_TO_FSB(mp, XFS_ISIZE(ip)))
+			    map[i].br_startoff < XFS_B_TO_FSB(mp, XFS_ISIZE(ip)))
 				ASSERT((iflags & BMV_IF_DELALLOC) != 0);
 
                         if (map[i].br_startblock == HOLESTARTBLOCK &&
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 6e2b892b58ee..fb0eb697a621 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -979,6 +979,8 @@ void
 xfs_buf_unlock(
 	struct xfs_buf		*bp)
 {
+	ASSERT(xfs_buf_islocked(bp));
+
 	XB_CLEAR_OWNER(bp);
 	up(&bp->b_sema);
 
@@ -1713,6 +1715,28 @@ error:
 }
 
 /*
+ * Cancel a delayed write list.
+ *
+ * Remove each buffer from the list, clear the delwri queue flag and drop the
+ * associated buffer reference.
+ */
+void
+xfs_buf_delwri_cancel(
+	struct list_head	*list)
+{
+	struct xfs_buf		*bp;
+
+	while (!list_empty(list)) {
+		bp = list_first_entry(list, struct xfs_buf, b_list);
+
+		xfs_buf_lock(bp);
+		bp->b_flags &= ~_XBF_DELWRI_Q;
+		list_del_init(&bp->b_list);
+		xfs_buf_relse(bp);
+	}
+}
+
+/*
  * Add a buffer to the delayed write list.
  *
  * This queues a buffer for writeout if it hasn't already been.  Note that
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 110cb85e04f3..102b77af00b6 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -303,6 +303,7 @@ extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, void *,
 extern xfs_caddr_t xfs_buf_offset(xfs_buf_t *, size_t);
 
 /* Delayed Write Buffer Routines */
+extern void xfs_buf_delwri_cancel(struct list_head *);
 extern bool xfs_buf_delwri_queue(struct xfs_buf *, struct list_head *);
 extern int xfs_buf_delwri_submit(struct list_head *);
 extern int xfs_buf_delwri_submit_nowait(struct list_head *);
diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c
index 098cd78fe708..21d43c33a2cc 100644
--- a/fs/xfs/xfs_dir2_readdir.c
+++ b/fs/xfs/xfs_dir2_readdir.c
@@ -403,6 +403,7 @@ xfs_dir2_leaf_readbuf(
 
 	/*
 	 * Do we need more readahead?
+	 * Each loop tries to process 1 full dir blk; last may be partial.
 	 */
 	blk_start_plug(&plug);
 	for (mip->ra_index = mip->ra_offset = i = 0;
@@ -413,7 +414,8 @@ xfs_dir2_leaf_readbuf(
 		 * Read-ahead a contiguous directory block.
 		 */
 		if (i > mip->ra_current &&
-		    map[mip->ra_index].br_blockcount >= geo->fsbcount) {
+		    (map[mip->ra_index].br_blockcount - mip->ra_offset) >=
+		    geo->fsbcount) {
 			xfs_dir3_data_readahead(dp,
 				map[mip->ra_index].br_startoff + mip->ra_offset,
 				XFS_FSB_TO_DADDR(dp->i_mount,
@@ -434,14 +436,19 @@ xfs_dir2_leaf_readbuf(
 		}
 
 		/*
-		 * Advance offset through the mapping table.
+		 * Advance offset through the mapping table, processing a full
+		 * dir block even if it is fragmented into several extents.
+		 * But stop if we have consumed all valid mappings, even if
+		 * it's not yet a full directory block.
 		 */
-		for (j = 0; j < geo->fsbcount; j += length ) {
+		for (j = 0;
+		     j < geo->fsbcount && mip->ra_index < mip->map_valid;
+		     j += length ) {
 			/*
 			 * The rest of this extent but not more than a dir
 			 * block.
 			 */
-			length = min_t(int, geo->fsbcount,
+			length = min_t(int, geo->fsbcount - j,
 					map[mip->ra_index].br_blockcount -
 							mip->ra_offset);
 			mip->ra_offset += length;
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 76a9f2783282..d5d5333afa81 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -210,14 +210,17 @@ xfs_iget_cache_hit(
 
 		error = inode_init_always(mp->m_super, inode);
 		if (error) {
+			bool wake;
 			/*
 			 * Re-initializing the inode failed, and we are in deep
 			 * trouble.  Try to re-add it to the reclaim list.
 			 */
 			rcu_read_lock();
 			spin_lock(&ip->i_flags_lock);
-
+			wake = !!__xfs_iflags_test(ip, XFS_INEW);
 			ip->i_flags &= ~(XFS_INEW | XFS_IRECLAIM);
+			if (wake)
+				wake_up_bit(&ip->i_flags, __XFS_INEW_BIT);
 			ASSERT(ip->i_flags & XFS_IRECLAIMABLE);
 			trace_xfs_iget_reclaim_fail(ip);
 			goto out_error;
@@ -363,6 +366,22 @@ out_destroy:
 	return error;
 }
 
+static void
+xfs_inew_wait(
+	struct xfs_inode	*ip)
+{
+	wait_queue_head_t *wq = bit_waitqueue(&ip->i_flags, __XFS_INEW_BIT);
+	DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_INEW_BIT);
+
+	do {
+		prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE);
+		if (!xfs_iflags_test(ip, XFS_INEW))
+			break;
+		schedule();
+	} while (true);
+	finish_wait(wq, &wait.wait);
+}
+
 /*
  * Look up an inode by number in the given file system.
  * The inode is looked up in the cache held in each AG.
@@ -465,9 +484,11 @@ out_error_or_again:
 
 STATIC int
 xfs_inode_ag_walk_grab(
-	struct xfs_inode	*ip)
+	struct xfs_inode	*ip,
+	int			flags)
 {
 	struct inode		*inode = VFS_I(ip);
+	bool			newinos = !!(flags & XFS_AGITER_INEW_WAIT);
 
 	ASSERT(rcu_read_lock_held());
 
@@ -485,7 +506,8 @@ xfs_inode_ag_walk_grab(
 		goto out_unlock_noent;
 
 	/* avoid new or reclaimable inodes. Leave for reclaim code to flush */
-	if (__xfs_iflags_test(ip, XFS_INEW | XFS_IRECLAIMABLE | XFS_IRECLAIM))
+	if ((!newinos && __xfs_iflags_test(ip, XFS_INEW)) ||
+	    __xfs_iflags_test(ip, XFS_IRECLAIMABLE | XFS_IRECLAIM))
 		goto out_unlock_noent;
 	spin_unlock(&ip->i_flags_lock);
 
@@ -513,7 +535,8 @@ xfs_inode_ag_walk(
 					   void *args),
 	int			flags,
 	void			*args,
-	int			tag)
+	int			tag,
+	int			iter_flags)
 {
 	uint32_t		first_index;
 	int			last_error = 0;
@@ -555,7 +578,7 @@ restart:
 		for (i = 0; i < nr_found; i++) {
 			struct xfs_inode *ip = batch[i];
 
-			if (done || xfs_inode_ag_walk_grab(ip))
+			if (done || xfs_inode_ag_walk_grab(ip, iter_flags))
 				batch[i] = NULL;
 
 			/*
@@ -583,6 +606,9 @@ restart:
 		for (i = 0; i < nr_found; i++) {
 			if (!batch[i])
 				continue;
+			if ((iter_flags & XFS_AGITER_INEW_WAIT) &&
+			    xfs_iflags_test(batch[i], XFS_INEW))
+				xfs_inew_wait(batch[i]);
 			error = execute(batch[i], flags, args);
 			IRELE(batch[i]);
 			if (error == -EAGAIN) {
@@ -635,12 +661,13 @@ xfs_eofblocks_worker(
 }
 
 int
-xfs_inode_ag_iterator(
+xfs_inode_ag_iterator_flags(
 	struct xfs_mount	*mp,
 	int			(*execute)(struct xfs_inode *ip, int flags,
 					   void *args),
 	int			flags,
-	void			*args)
+	void			*args,
+	int			iter_flags)
 {
 	struct xfs_perag	*pag;
 	int			error = 0;
@@ -650,7 +677,8 @@ xfs_inode_ag_iterator(
 	ag = 0;
 	while ((pag = xfs_perag_get(mp, ag))) {
 		ag = pag->pag_agno + 1;
-		error = xfs_inode_ag_walk(mp, pag, execute, flags, args, -1);
+		error = xfs_inode_ag_walk(mp, pag, execute, flags, args, -1,
+					  iter_flags);
 		xfs_perag_put(pag);
 		if (error) {
 			last_error = error;
@@ -662,6 +690,17 @@ xfs_inode_ag_iterator(
 }
 
 int
+xfs_inode_ag_iterator(
+	struct xfs_mount	*mp,
+	int			(*execute)(struct xfs_inode *ip, int flags,
+					   void *args),
+	int			flags,
+	void			*args)
+{
+	return xfs_inode_ag_iterator_flags(mp, execute, flags, args, 0);
+}
+
+int
 xfs_inode_ag_iterator_tag(
 	struct xfs_mount	*mp,
 	int			(*execute)(struct xfs_inode *ip, int flags,
@@ -678,7 +717,8 @@ xfs_inode_ag_iterator_tag(
 	ag = 0;
 	while ((pag = xfs_perag_get_tag(mp, ag, tag))) {
 		ag = pag->pag_agno + 1;
-		error = xfs_inode_ag_walk(mp, pag, execute, flags, args, tag);
+		error = xfs_inode_ag_walk(mp, pag, execute, flags, args, tag,
+					  0);
 		xfs_perag_put(pag);
 		if (error) {
 			last_error = error;
diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h
index 62f1f91c32cb..147a79212e63 100644
--- a/fs/xfs/xfs_icache.h
+++ b/fs/xfs/xfs_icache.h
@@ -48,6 +48,11 @@ struct xfs_eofblocks {
 #define XFS_IGET_UNTRUSTED	0x2
 #define XFS_IGET_DONTCACHE	0x4
 
+/*
+ * flags for AG inode iterator
+ */
+#define XFS_AGITER_INEW_WAIT	0x1	/* wait on new inodes */
+
 int xfs_iget(struct xfs_mount *mp, struct xfs_trans *tp, xfs_ino_t ino,
 	     uint flags, uint lock_flags, xfs_inode_t **ipp);
 
@@ -72,6 +77,9 @@ void xfs_eofblocks_worker(struct work_struct *);
 int xfs_inode_ag_iterator(struct xfs_mount *mp,
 	int (*execute)(struct xfs_inode *ip, int flags, void *args),
 	int flags, void *args);
+int xfs_inode_ag_iterator_flags(struct xfs_mount *mp,
+	int (*execute)(struct xfs_inode *ip, int flags, void *args),
+	int flags, void *args, int iter_flags);
 int xfs_inode_ag_iterator_tag(struct xfs_mount *mp,
 	int (*execute)(struct xfs_inode *ip, int flags, void *args),
 	int flags, void *args, int tag);
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 8f22d20368d8..bc719acd602b 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -208,7 +208,8 @@ xfs_get_initial_prid(struct xfs_inode *dp)
 #define XFS_IRECLAIM		(1 << 0) /* started reclaiming this inode */
 #define XFS_ISTALE		(1 << 1) /* inode has been staled */
 #define XFS_IRECLAIMABLE	(1 << 2) /* inode can be reclaimed */
-#define XFS_INEW		(1 << 3) /* inode has just been allocated */
+#define __XFS_INEW_BIT		3	 /* inode has just been allocated */
+#define XFS_INEW		(1 << __XFS_INEW_BIT)
 #define XFS_ITRUNCATED		(1 << 5) /* truncated down so flush-on-close */
 #define XFS_IDIRTY_RELEASE	(1 << 6) /* dirty release already seen */
 #define __XFS_IFLOCK_BIT	7	 /* inode is being flushed right now */
@@ -420,6 +421,7 @@ static inline void xfs_finish_inode_setup(struct xfs_inode *ip)
 	xfs_iflags_clear(ip, XFS_INEW);
 	barrier();
 	unlock_new_inode(VFS_I(ip));
+	wake_up_bit(&ip->i_flags, __XFS_INEW_BIT);
 }
 
 static inline void xfs_setup_existing_inode(struct xfs_inode *ip)
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 82e49109d0b6..e69a0899bc05 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -1368,10 +1368,11 @@ xfs_ioc_getbmap(
 	unsigned int		cmd,
 	void			__user *arg)
 {
-	struct getbmapx		bmx;
+	struct getbmapx		bmx = { 0 };
 	int			error;
 
-	if (copy_from_user(&bmx, arg, sizeof(struct getbmapx)))
+	/* struct getbmap is a strict subset of struct getbmapx. */
+	if (copy_from_user(&bmx, arg, offsetof(struct getbmapx, bmv_iflags)))
 		return -EFAULT;
 
 	if (bmx.bmv_count < 2)
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index 80429891dc9b..b5cab0d1831b 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -570,7 +570,7 @@ xfs_inumbers(
 		return error;
 
 	bcount = MIN(left, (int)(PAGE_SIZE / sizeof(*buffer)));
-	buffer = kmem_alloc(bcount * sizeof(*buffer), KM_SLEEP);
+	buffer = kmem_zalloc(bcount * sizeof(*buffer), KM_SLEEP);
 	do {
 		struct xfs_inobt_rec_incore	r;
 		int				stat;
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index bcc7cfabb787..7ee735c0f490 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1273,7 +1273,7 @@ void
 xfs_log_work_queue(
 	struct xfs_mount        *mp)
 {
-	queue_delayed_work(mp->m_log_workqueue, &mp->m_log->l_work,
+	queue_delayed_work(mp->m_sync_workqueue, &mp->m_log->l_work,
 				msecs_to_jiffies(xfs_syncd_centisecs * 10));
 }
 
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 8c995a2ccb6f..9cccfd6f18c7 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -133,6 +133,7 @@ typedef struct xfs_mount {
 	struct workqueue_struct	*m_reclaim_workqueue;
 	struct workqueue_struct	*m_log_workqueue;
 	struct workqueue_struct *m_eofblocks_workqueue;
+	struct workqueue_struct	*m_sync_workqueue;
 
 	/*
 	 * Generation of the filesysyem layout.  This is incremented by each
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 5538468c7f63..7d81032a645f 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -1356,12 +1356,7 @@ xfs_qm_quotacheck(
 	mp->m_qflags |= flags;
 
  error_return:
-	while (!list_empty(&buffer_list)) {
-		struct xfs_buf *bp =
-			list_first_entry(&buffer_list, struct xfs_buf, b_list);
-		list_del_init(&bp->b_list);
-		xfs_buf_relse(bp);
-	}
+	xfs_buf_delwri_cancel(&buffer_list);
 
 	if (error) {
 		xfs_warn(mp,
diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c
index 9a25c9275fb3..a3b3f5c689bb 100644
--- a/fs/xfs/xfs_qm_syscalls.c
+++ b/fs/xfs/xfs_qm_syscalls.c
@@ -766,5 +766,6 @@ xfs_qm_dqrele_all_inodes(
 	uint		 flags)
 {
 	ASSERT(mp->m_quotainfo);
-	xfs_inode_ag_iterator(mp, xfs_dqrele_inode, flags, NULL);
+	xfs_inode_ag_iterator_flags(mp, xfs_dqrele_inode, flags, NULL,
+				    XFS_AGITER_INEW_WAIT);
 }
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 2a517576f2bc..9ea51a71028e 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -853,8 +853,15 @@ xfs_init_mount_workqueues(
 	if (!mp->m_eofblocks_workqueue)
 		goto out_destroy_log;
 
+	mp->m_sync_workqueue = alloc_workqueue("xfs-sync/%s", WQ_FREEZABLE, 0,
+					       mp->m_fsname);
+	if (!mp->m_sync_workqueue)
+		goto out_destroy_eofb;
+
 	return 0;
 
+out_destroy_eofb:
+	destroy_workqueue(mp->m_eofblocks_workqueue);
 out_destroy_log:
 	destroy_workqueue(mp->m_log_workqueue);
 out_destroy_reclaim:
@@ -875,6 +882,7 @@ STATIC void
 xfs_destroy_mount_workqueues(
 	struct xfs_mount	*mp)
 {
+	destroy_workqueue(mp->m_sync_workqueue);
 	destroy_workqueue(mp->m_eofblocks_workqueue);
 	destroy_workqueue(mp->m_log_workqueue);
 	destroy_workqueue(mp->m_reclaim_workqueue);