Merge branch 'libnvdimm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull libnvdimm fixes from Dan Williams:

 - A collection of crash and deadlock fixes for DAX that are also tagged
   for -stable.  We will look to re-enable DAX pmd mappings in 4.5, but
   for now 4.4 and -stable should disable it by default.

 - A fixup to ext2 and ext4 to mirror the same warning emitted by XFS
   when mounting with "-o dax"

* 'libnvdimm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm:
  block: protect rw_page against device teardown
  mm, dax: fix DAX deadlocks (COW fault)
  dax: disable pmd mappings
  ext2, ext4: warn when mounting with dax enabled

block/blk.h

@@ -72,8 +72,6 @@ void blk_dequeue_request(struct request *rq);
 void __blk_queue_free_tags(struct request_queue *q);
 bool __blk_end_bidi_request(struct request *rq, int error,
 			    unsigned int nr_bytes, unsigned int bidi_bytes);
-int blk_queue_enter(struct request_queue *q, gfp_t gfp);
-void blk_queue_exit(struct request_queue *q);
 void blk_freeze_queue(struct request_queue *q);
 
 static inline void blk_queue_enter_live(struct request_queue *q)

fs/Kconfig

@@ -46,6 +46,12 @@ config FS_DAX
 	  or if unsure, say N.  Saying Y will increase the size of the kernel
 	  by about 5kB.
 
+config FS_DAX_PMD
+	bool
+	default FS_DAX
+	depends on FS_DAX
+	depends on BROKEN
+
 endif # BLOCK
 
 # Posix ACL utility routines

fs/block_dev.c

@@ -390,9 +390,17 @@ int bdev_read_page(struct block_device *bdev, sector_t sector,
 			struct page *page)
 {
 	const struct block_device_operations *ops = bdev->bd_disk->fops;
+	int result = -EOPNOTSUPP;
+
 	if (!ops->rw_page || bdev_get_integrity(bdev))
-		return -EOPNOTSUPP;
-	return ops->rw_page(bdev, sector + get_start_sect(bdev), page, READ);
+		return result;
+
+	result = blk_queue_enter(bdev->bd_queue, GFP_KERNEL);
+	if (result)
+		return result;
+	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, READ);
+	blk_queue_exit(bdev->bd_queue);
+	return result;
 }
 EXPORT_SYMBOL_GPL(bdev_read_page);
 
@@ -421,14 +429,20 @@ int bdev_write_page(struct block_device *bdev, sector_t sector,
 	int result;
 	int rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE;
 	const struct block_device_operations *ops = bdev->bd_disk->fops;
+
 	if (!ops->rw_page || bdev_get_integrity(bdev))
 		return -EOPNOTSUPP;
+	result = blk_queue_enter(bdev->bd_queue, GFP_KERNEL);
+	if (result)
+		return result;
+
 	set_page_writeback(page);
 	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, rw);
 	if (result)
 		end_page_writeback(page);
 	else
 		unlock_page(page);
+	blk_queue_exit(bdev->bd_queue);
 	return result;
 }
 EXPORT_SYMBOL_GPL(bdev_write_page);

fs/dax.c

@@ -541,6 +541,10 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	unsigned long pfn;
 	int result = 0;
 
+	/* dax pmd mappings are broken wrt gup and fork */
+	if (!IS_ENABLED(CONFIG_FS_DAX_PMD))
+		return VM_FAULT_FALLBACK;
+
 	/* Fall back to PTEs if we're going to COW */
 	if (write && !(vma->vm_flags & VM_SHARED))
 		return VM_FAULT_FALLBACK;

fs/ext2/super.c

@@ -569,6 +569,8 @@ static int parse_options(char *options, struct super_block *sb)
 			/* Fall through */
 		case Opt_dax:
 #ifdef CONFIG_FS_DAX
+			ext2_msg(sb, KERN_WARNING,
+		"DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
 			set_opt(sbi->s_mount_opt, DAX);
 #else
 			ext2_msg(sb, KERN_INFO, "dax option not supported");

fs/ext4/super.c

@@ -1664,8 +1664,12 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 		}
 		sbi->s_jquota_fmt = m->mount_opt;
 #endif
-#ifndef CONFIG_FS_DAX
 	} else if (token == Opt_dax) {
+#ifdef CONFIG_FS_DAX
+		ext4_msg(sb, KERN_WARNING,
+		"DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
+			sbi->s_mount_opt |= m->mount_opt;
+#else
 		ext4_msg(sb, KERN_INFO, "dax option not supported");
 		return -1;
 #endif

include/linux/blkdev.h

@@ -794,6 +794,8 @@ extern int scsi_cmd_ioctl(struct request_queue *, struct gendisk *, fmode_t,
 extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t,
 			 struct scsi_ioctl_command __user *);
 
+extern int blk_queue_enter(struct request_queue *q, gfp_t gfp);
+extern void blk_queue_exit(struct request_queue *q);
 extern void blk_start_queue(struct request_queue *q);
 extern void blk_stop_queue(struct request_queue *q);
 extern void blk_sync_queue(struct request_queue *q);

mm/memory.c

@@ -3015,9 +3015,9 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		} else {
 			/*
 			 * The fault handler has no page to lock, so it holds
-			 * i_mmap_lock for write to protect against truncate.
+			 * i_mmap_lock for read to protect against truncate.
 			 */
-			i_mmap_unlock_write(vma->vm_file->f_mapping);
+			i_mmap_unlock_read(vma->vm_file->f_mapping);
 		}
 		goto uncharge_out;
 	}
@@ -3031,9 +3031,9 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	} else {
 		/*
 		 * The fault handler has no page to lock, so it holds
-		 * i_mmap_lock for write to protect against truncate.
+		 * i_mmap_lock for read to protect against truncate.
 		 */
-		i_mmap_unlock_write(vma->vm_file->f_mapping);
+		i_mmap_unlock_read(vma->vm_file->f_mapping);
 	}
 	return ret;
 uncharge_out: