1 files changed, 280 insertions, 241 deletions

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 4720c7ade0a..6cb1beb47c2 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -63,19 +63,20 @@
 #include <linux/init.h>
 #include <linux/swap.h>
 #include <linux/slab.h>
-#include <linux/loop.h>
 #include <linux/compat.h>
 #include <linux/suspend.h>
 #include <linux/freezer.h>
 #include <linux/mutex.h>
 #include <linux/writeback.h>
-#include <linux/buffer_head.h>		/* for invalidate_bdev() */
 #include <linux/completion.h>
 #include <linux/highmem.h>
 #include <linux/kthread.h>
 #include <linux/splice.h>
 #include <linux/sysfs.h>
 #include <linux/miscdevice.h>
+#include <linux/falloc.h>
+#include "loop.h"
+
 #include <asm/uaccess.h>
 
 static DEFINE_IDR(loop_index_idr);
@@ -92,16 +93,16 @@ static int transfer_none(struct loop_device *lo, int cmd,
 			 struct page *loop_page, unsigned loop_off,
 			 int size, sector_t real_block)
 {
-	char *raw_buf = kmap_atomic(raw_page, KM_USER0) + raw_off;
-	char *loop_buf = kmap_atomic(loop_page, KM_USER1) + loop_off;
+	char *raw_buf = kmap_atomic(raw_page) + raw_off;
+	char *loop_buf = kmap_atomic(loop_page) + loop_off;
 
 	if (cmd == READ)
 		memcpy(loop_buf, raw_buf, size);
 	else
 		memcpy(raw_buf, loop_buf, size);
 
-	kunmap_atomic(loop_buf, KM_USER1);
-	kunmap_atomic(raw_buf, KM_USER0);
+	kunmap_atomic(loop_buf);
+	kunmap_atomic(raw_buf);
 	cond_resched();
 	return 0;
 }
@@ -111,8 +112,8 @@ static int transfer_xor(struct loop_device *lo, int cmd,
 			struct page *loop_page, unsigned loop_off,
 			int size, sector_t real_block)
 {
-	char *raw_buf = kmap_atomic(raw_page, KM_USER0) + raw_off;
-	char *loop_buf = kmap_atomic(loop_page, KM_USER1) + loop_off;
+	char *raw_buf = kmap_atomic(raw_page) + raw_off;
+	char *loop_buf = kmap_atomic(loop_page) + loop_off;
 	char *in, *out, *key;
 	int i, keysize;
 
@@ -129,8 +130,8 @@ static int transfer_xor(struct loop_device *lo, int cmd,
 	for (i = 0; i < size; i++)
 		*out++ = *in++ ^ key[(i & 511) % keysize];
 
-	kunmap_atomic(loop_buf, KM_USER1);
-	kunmap_atomic(raw_buf, KM_USER0);
+	kunmap_atomic(loop_buf);
+	kunmap_atomic(raw_buf);
 	cond_resched();
 	return 0;
 }
@@ -159,17 +160,20 @@ static struct loop_func_table *xfer_funcs[MAX_LO_CRYPT] = {
 	&xor_funcs
 };
 
-static loff_t get_loop_size(struct loop_device *lo, struct file *file)
+static loff_t get_size(loff_t offset, loff_t sizelimit, struct file *file)
 {
-	loff_t size, offset, loopsize;
+	loff_t loopsize;
 
 	/* Compute loopsize in bytes */
-	size = i_size_read(file->f_mapping->host);
-	offset = lo->lo_offset;
-	loopsize = size - offset;
-	if (lo->lo_sizelimit > 0 && lo->lo_sizelimit < loopsize)
-		loopsize = lo->lo_sizelimit;
+	loopsize = i_size_read(file->f_mapping->host);
+	if (offset > 0)
+		loopsize -= offset;
+	/* offset is beyond i_size, weird but possible */
+	if (loopsize < 0)
+		return 0;
 
+	if (sizelimit > 0 && sizelimit < loopsize)
+		loopsize = sizelimit;
 	/*
 	 * Unfortunately, if we want to do I/O on the device,
 	 * the number of 512-byte sectors has to fit into a sector_t.
@@ -177,17 +181,29 @@ static loff_t get_loop_size(struct loop_device *lo, struct file *file)
 	return loopsize >> 9;
 }
 
+static loff_t get_loop_size(struct loop_device *lo, struct file *file)
+{
+	return get_size(lo->lo_offset, lo->lo_sizelimit, file);
+}
+
 static int
-figure_loop_size(struct loop_device *lo)
+figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit)
 {
-	loff_t size = get_loop_size(lo, lo->lo_backing_file);
+	loff_t size = get_size(offset, sizelimit, lo->lo_backing_file);
 	sector_t x = (sector_t)size;
+	struct block_device *bdev = lo->lo_device;
 
 	if (unlikely((loff_t)x != size))
 		return -EFBIG;
-
+	if (lo->lo_offset != offset)
+		lo->lo_offset = offset;
+	if (lo->lo_sizelimit != sizelimit)
+		lo->lo_sizelimit = sizelimit;
 	set_capacity(lo->lo_disk, x);
-	return 0;					
+	bd_set_size(bdev, (loff_t)get_capacity(bdev->bd_disk) << 9);
+	/* let user-space know about the new size */
+	kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE);
+	return 0;
 }
 
 static inline int
@@ -203,74 +219,6 @@ lo_do_transfer(struct loop_device *lo, int cmd,
 }
 
 /**
- * do_lo_send_aops - helper for writing data to a loop device
- *
- * This is the fast version for backing filesystems which implement the address
- * space operations write_begin and write_end.
- */
-static int do_lo_send_aops(struct loop_device *lo, struct bio_vec *bvec,
-		loff_t pos, struct page *unused)
-{
-	struct file *file = lo->lo_backing_file; /* kudos to NFsckingS */
-	struct address_space *mapping = file->f_mapping;
-	pgoff_t index;
-	unsigned offset, bv_offs;
-	int len, ret;
-
-	mutex_lock(&mapping->host->i_mutex);
-	index = pos >> PAGE_CACHE_SHIFT;
-	offset = pos & ((pgoff_t)PAGE_CACHE_SIZE - 1);
-	bv_offs = bvec->bv_offset;
-	len = bvec->bv_len;
-	while (len > 0) {
-		sector_t IV;
-		unsigned size, copied;
-		int transfer_result;
-		struct page *page;
-		void *fsdata;
-
-		IV = ((sector_t)index << (PAGE_CACHE_SHIFT - 9))+(offset >> 9);
-		size = PAGE_CACHE_SIZE - offset;
-		if (size > len)
-			size = len;
-
-		ret = pagecache_write_begin(file, mapping, pos, size, 0,
-							&page, &fsdata);
-		if (ret)
-			goto fail;
-
-		file_update_time(file);
-
-		transfer_result = lo_do_transfer(lo, WRITE, page, offset,
-				bvec->bv_page, bv_offs, size, IV);
-		copied = size;
-		if (unlikely(transfer_result))
-			copied = 0;
-
-		ret = pagecache_write_end(file, mapping, pos, size, copied,
-							page, fsdata);
-		if (ret < 0 || ret != copied)
-			goto fail;
-
-		if (unlikely(transfer_result))
-			goto fail;
-
-		bv_offs += copied;
-		len -= copied;
-		offset = 0;
-		index++;
-		pos += copied;
-	}
-	ret = 0;
-out:
-	mutex_unlock(&mapping->host->i_mutex);
-	return ret;
-fail:
-	ret = -1;
-	goto out;
-}
-
-/**
  * __do_lo_send_write - helper for writing data to a loop device
  *
  * This helper just factors out common code between do_lo_send_direct_write()
@@ -282,12 +230,14 @@ static int __do_lo_send_write(struct file *file,
 	ssize_t bw;
 	mm_segment_t old_fs = get_fs();
 
+	file_start_write(file);
 	set_fs(get_ds());
 	bw = file->f_op->write(file, buf, len, &pos);
 	set_fs(old_fs);
+	file_end_write(file);
 	if (likely(bw == len))
 		return 0;
-	printk(KERN_ERR "loop: Write error at byte offset %llu, length %i.\n",
+	printk_ratelimited(KERN_ERR "loop: Write error at byte offset %llu, length %i.\n",
 			(unsigned long long)pos, len);
 	if (bw >= 0)
 		bw = -EIO;
@@ -297,10 +247,8 @@ static int __do_lo_send_write(struct file *file,
 /**
  * do_lo_send_direct_write - helper for writing data to a loop device
  *
- * This is the fast, non-transforming version for backing filesystems which do
- * not implement the address space operations write_begin and write_end.
- * It uses the write file operation which should be present on all writeable
- * filesystems.
+ * This is the fast, non-transforming version that does not need double
+ * buffering.
  */
 static int do_lo_send_direct_write(struct loop_device *lo,
 		struct bio_vec *bvec, loff_t pos, struct page *page)
@@ -316,15 +264,9 @@ static int do_lo_send_direct_write(struct loop_device *lo,
 /**
  * do_lo_send_write - helper for writing data to a loop device
  *
- * This is the slow, transforming version for filesystems which do not
- * implement the address space operations write_begin and write_end.  It
- * uses the write file operation which should be present on all writeable
- * filesystems.
- *
- * Using fops->write is slower than using aops->{prepare,commit}_write in the
- * transforming case because we need to double buffer the data as we cannot do
- * the transformations in place as we do not have direct access to the
- * destination pages of the backing file.
+ * This is the slow, transforming version that needs to double buffer the
+ * data as it cannot do the transformations in place without having direct
+ * access to the destination pages of the backing file.
  */
 static int do_lo_send_write(struct loop_device *lo, struct bio_vec *bvec,
 		loff_t pos, struct page *page)
@@ -335,7 +277,7 @@ static int do_lo_send_write(struct loop_device *lo, struct bio_vec *bvec,
 		return __do_lo_send_write(lo->lo_backing_file,
 				page_address(page), bvec->bv_len,
 				pos);
-	printk(KERN_ERR "loop: Transfer error at byte offset %llu, "
+	printk_ratelimited(KERN_ERR "loop: Transfer error at byte offset %llu, "
 			"length %i.\n", (unsigned long long)pos, bvec->bv_len);
 	if (ret > 0)
 		ret = -EIO;
@@ -346,26 +288,26 @@ static int lo_send(struct loop_device *lo, struct bio *bio, loff_t pos)
 {
 	int (*do_lo_send)(struct loop_device *, struct bio_vec *, loff_t,
 			struct page *page);
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
 	struct page *page = NULL;
-	int i, ret = 0;
+	int ret = 0;
 
-	do_lo_send = do_lo_send_aops;
-	if (!(lo->lo_flags & LO_FLAGS_USE_AOPS)) {
+	if (lo->transfer != transfer_none) {
+		page = alloc_page(GFP_NOIO | __GFP_HIGHMEM);
+		if (unlikely(!page))
+			goto fail;
+		kmap(page);
+		do_lo_send = do_lo_send_write;
+	} else {
 		do_lo_send = do_lo_send_direct_write;
-		if (lo->transfer != transfer_none) {
-			page = alloc_page(GFP_NOIO | __GFP_HIGHMEM);
-			if (unlikely(!page))
-				goto fail;
-			kmap(page);
-			do_lo_send = do_lo_send_write;
-		}
 	}
-	bio_for_each_segment(bvec, bio, i) {
-		ret = do_lo_send(lo, bvec, pos, page);
+
+	bio_for_each_segment(bvec, bio, iter) {
+		ret = do_lo_send(lo, &bvec, pos, page);
 		if (ret < 0)
 			break;
-		pos += bvec->bv_len;
+		pos += bvec.bv_len;
 	}
 	if (page) {
 		kunmap(page);
@@ -374,7 +316,7 @@ static int lo_send(struct loop_device *lo, struct bio *bio, loff_t pos)
 out:
 	return ret;
 fail:
-	printk(KERN_ERR "loop: Failed to allocate temporary page for write.\n");
+	printk_ratelimited(KERN_ERR "loop: Failed to allocate temporary page for write.\n");
 	ret = -ENOMEM;
 	goto out;
 }
@@ -403,7 +345,7 @@ lo_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
 		size = p->bsize;
 
 	if (lo_do_transfer(lo, READ, page, buf->offset, p->page, p->offset, size, IV)) {
-		printk(KERN_ERR "loop: transfer error block %ld\n",
+		printk_ratelimited(KERN_ERR "loop: transfer error block %ld\n",
 		       page->index);
 		size = -EINVAL;
 	}
@@ -422,14 +364,14 @@ lo_direct_splice_actor(struct pipe_inode_info *pipe, struct splice_desc *sd)
 	return __splice_from_pipe(pipe, sd, lo_splice_actor);
 }
 
-static int
+static ssize_t
 do_lo_receive(struct loop_device *lo,
 	      struct bio_vec *bvec, int bsize, loff_t pos)
 {
 	struct lo_read_data cookie;
 	struct splice_desc sd;
 	struct file *file;
-	long retval;
+	ssize_t retval;
 
 	cookie.lo = lo;
 	cookie.page = bvec->bv_page;
@@ -445,25 +387,28 @@ do_lo_receive(struct loop_device *lo,
 	file = lo->lo_backing_file;
 	retval = splice_direct_to_actor(file, &sd, lo_direct_splice_actor);
 
-	if (retval < 0)
-		return retval;
-
-	return 0;
+	return retval;
 }
 
 static int
 lo_receive(struct loop_device *lo, struct bio *bio, int bsize, loff_t pos)
 {
-	struct bio_vec *bvec;
-	int i, ret = 0;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
+	ssize_t s;
 
-	bio_for_each_segment(bvec, bio, i) {
-		ret = do_lo_receive(lo, bvec, bsize, pos);
-		if (ret < 0)
+	bio_for_each_segment(bvec, bio, iter) {
+		s = do_lo_receive(lo, &bvec, bsize, pos);
+		if (s < 0)
+			return s;
+
+		if (s != bvec.bv_len) {
+			zero_fill_bio(bio);
 			break;
-		pos += bvec->bv_len;
+		}
+		pos += bvec.bv_len;
 	}
-	return ret;
+	return 0;
 }
 
 static int do_bio_filebacked(struct loop_device *lo, struct bio *bio)
@@ -471,7 +416,7 @@ static int do_bio_filebacked(struct loop_device *lo, struct bio *bio)
 	loff_t pos;
 	int ret;
 
-	pos = ((loff_t) bio->bi_sector << 9) + lo->lo_offset;
+	pos = ((loff_t) bio->bi_iter.bi_sector << 9) + lo->lo_offset;
 
 	if (bio_rw(bio) == WRITE) {
 		struct file *file = lo->lo_backing_file;
@@ -484,6 +429,29 @@ static int do_bio_filebacked(struct loop_device *lo, struct bio *bio)
 			}
 		}
 
+		/*
+		 * We use punch hole to reclaim the free space used by the
+		 * image a.k.a. discard. However we do not support discard if
+		 * encryption is enabled, because it may give an attacker
+		 * useful information.
+		 */
+		if (bio->bi_rw & REQ_DISCARD) {
+			struct file *file = lo->lo_backing_file;
+			int mode = FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE;
+
+			if ((!file->f_op->fallocate) ||
+			    lo->lo_encrypt_key_size) {
+				ret = -EOPNOTSUPP;
+				goto out;
+			}
+			ret = file->f_op->fallocate(file, mode, pos,
+						    bio->bi_iter.bi_size);
+			if (unlikely(ret && ret != -EINVAL &&
+				     ret != -EOPNOTSUPP))
+				ret = -EIO;
+			goto out;
+		}
+
 		ret = lo_send(lo, bio, pos);
 
 		if ((bio->bi_rw & REQ_FUA) && !ret) {
@@ -503,6 +471,7 @@ out:
  */
 static void loop_add_bio(struct loop_device *lo, struct bio *bio)
 {
+	lo->lo_bio_count++;
 	bio_list_add(&lo->lo_bio_list, bio);
 }
 
@@ -511,10 +480,11 @@ static void loop_add_bio(struct loop_device *lo, struct bio *bio)
  */
 static struct bio *loop_get_bio(struct loop_device *lo)
 {
+	lo->lo_bio_count--;
 	return bio_list_pop(&lo->lo_bio_list);
 }
 
-static int loop_make_request(struct request_queue *q, struct bio *old_bio)
+static void loop_make_request(struct request_queue *q, struct bio *old_bio)
 {
 	struct loop_device *lo = q->queuedata;
 	int rw = bio_rw(old_bio);
@@ -529,15 +499,18 @@ static int loop_make_request(struct request_queue *q, struct bio *old_bio)
 		goto out;
 	if (unlikely(rw == WRITE && (lo->lo_flags & LO_FLAGS_READ_ONLY)))
 		goto out;
+	if (lo->lo_bio_count >= q->nr_congestion_on)
+		wait_event_lock_irq(lo->lo_req_wait,
+				    lo->lo_bio_count < q->nr_congestion_off,
+				    lo->lo_lock);
 	loop_add_bio(lo, old_bio);
 	wake_up(&lo->lo_event);
 	spin_unlock_irq(&lo->lo_lock);
-	return 0;
+	return;
 
 out:
 	spin_unlock_irq(&lo->lo_lock);
 	bio_io_error(old_bio);
-	return 0;
 }
 
 struct switch_request {
@@ -575,7 +548,7 @@ static int loop_thread(void *data)
 	struct loop_device *lo = data;
 	struct bio *bio;
 
-	set_user_nice(current, -20);
+	set_user_nice(current, MIN_NICE);
 
 	while (!kthread_should_stop() || !bio_list_empty(&lo->lo_bio_list)) {
 
@@ -587,6 +560,8 @@ static int loop_thread(void *data)
 			continue;
 		spin_lock_irq(&lo->lo_lock);
 		bio = loop_get_bio(lo);
+		if (lo->lo_bio_count < lo->lo_queue->nr_congestion_off)
+			wake_up(&lo->lo_req_wait);
 		spin_unlock_irq(&lo->lo_lock);
 
 		BUG_ON(!bio);
@@ -700,7 +675,7 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 		goto out_putf;
 
 	fput(old_file);
-	if (max_part > 0)
+	if (lo->lo_flags & LO_FLAGS_PARTSCAN)
 		ioctl_by_bdev(bdev, BLKRRPART, 0);
 	return 0;
 
@@ -777,16 +752,25 @@ static ssize_t loop_attr_autoclear_show(struct loop_device *lo, char *buf)
 	return sprintf(buf, "%s\n", autoclear ? "1" : "0");
 }
 
+static ssize_t loop_attr_partscan_show(struct loop_device *lo, char *buf)
+{
+	int partscan = (lo->lo_flags & LO_FLAGS_PARTSCAN);
+
+	return sprintf(buf, "%s\n", partscan ? "1" : "0");
+}
+
 LOOP_ATTR_RO(backing_file);
 LOOP_ATTR_RO(offset);
 LOOP_ATTR_RO(sizelimit);
 LOOP_ATTR_RO(autoclear);
+LOOP_ATTR_RO(partscan);
 
 static struct attribute *loop_attrs[] = {
 	&loop_attr_backing_file.attr,
 	&loop_attr_offset.attr,
 	&loop_attr_sizelimit.attr,
 	&loop_attr_autoclear.attr,
+	&loop_attr_partscan.attr,
 	NULL,
 };
 
@@ -807,6 +791,35 @@ static void loop_sysfs_exit(struct loop_device *lo)
 			   &loop_attribute_group);
 }
 
+static void loop_config_discard(struct loop_device *lo)
+{
+	struct file *file = lo->lo_backing_file;
+	struct inode *inode = file->f_mapping->host;
+	struct request_queue *q = lo->lo_queue;
+
+	/*
+	 * We use punch hole to reclaim the free space used by the
+	 * image a.k.a. discard. However we do not support discard if
+	 * encryption is enabled, because it may give an attacker
+	 * useful information.
+	 */
+	if ((!file->f_op->fallocate) ||
+	    lo->lo_encrypt_key_size) {
+		q->limits.discard_granularity = 0;
+		q->limits.discard_alignment = 0;
+		q->limits.max_discard_sectors = 0;
+		q->limits.discard_zeroes_data = 0;
+		queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q);
+		return;
+	}
+
+	q->limits.discard_granularity = inode->i_sb->s_blocksize;
+	q->limits.discard_alignment = 0;
+	q->limits.max_discard_sectors = UINT_MAX >> 9;
+	q->limits.discard_zeroes_data = 1;
+	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
+}
+
 static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 		       struct block_device *bdev, unsigned int arg)
 {
@@ -849,35 +862,23 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	mapping = file->f_mapping;
 	inode = mapping->host;
 
-	if (!(file->f_mode & FMODE_WRITE))
-		lo_flags |= LO_FLAGS_READ_ONLY;
-
 	error = -EINVAL;
-	if (S_ISREG(inode->i_mode) || S_ISBLK(inode->i_mode)) {
-		const struct address_space_operations *aops = mapping->a_ops;
-
-		if (aops->write_begin)
-			lo_flags |= LO_FLAGS_USE_AOPS;
-		if (!(lo_flags & LO_FLAGS_USE_AOPS) && !file->f_op->write)
-			lo_flags |= LO_FLAGS_READ_ONLY;
+	if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))
+		goto out_putf;
 
-		lo_blocksize = S_ISBLK(inode->i_mode) ?
-			inode->i_bdev->bd_block_size : PAGE_SIZE;
+	if (!(file->f_mode & FMODE_WRITE) || !(mode & FMODE_WRITE) ||
+	    !file->f_op->write)
+		lo_flags |= LO_FLAGS_READ_ONLY;
 
-		error = 0;
-	} else {
-		goto out_putf;
-	}
+	lo_blocksize = S_ISBLK(inode->i_mode) ?
+		inode->i_bdev->bd_block_size : PAGE_SIZE;
 
+	error = -EFBIG;
 	size = get_loop_size(lo, file);
-
-	if ((loff_t)(sector_t)size != size) {
-		error = -EFBIG;
+	if ((loff_t)(sector_t)size != size)
 		goto out_putf;
-	}
 
-	if (!(mode & FMODE_WRITE))
-		lo_flags |= LO_FLAGS_READ_ONLY;
+	error = 0;
 
 	set_device_ro(bdev, (lo_flags & LO_FLAGS_READ_ONLY) != 0);
 
@@ -888,18 +889,12 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	lo->transfer = transfer_none;
 	lo->ioctl = NULL;
 	lo->lo_sizelimit = 0;
+	lo->lo_bio_count = 0;
 	lo->old_gfp_mask = mapping_gfp_mask(mapping);
 	mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
 
 	bio_list_init(&lo->lo_bio_list);
 
-	/*
-	 * set queue make_request_fn, and add limits based on lower level
-	 * device
-	 */
-	blk_queue_make_request(lo->lo_queue, loop_make_request);
-	lo->lo_queue->queuedata = lo;
-
 	if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
 		blk_queue_flush(lo->lo_queue, REQ_FLUSH);
 
@@ -919,8 +914,15 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	}
 	lo->lo_state = Lo_bound;
 	wake_up_process(lo->lo_thread);
-	if (max_part > 0)
+	if (part_shift)
+		lo->lo_flags |= LO_FLAGS_PARTSCAN;
+	if (lo->lo_flags & LO_FLAGS_PARTSCAN)
 		ioctl_by_bdev(bdev, BLKRRPART, 0);
+
+	/* Grab the block_device to prevent its destruction after we
+	 * put /dev/loopXX inode. Later in loop_clr_fd() we bdput(bdev).
+	 */
+	bdgrab(bdev);
 	return 0;
 
 out_clr:
@@ -980,16 +982,30 @@ loop_init_xfer(struct loop_device *lo, struct loop_func_table *xfer,
 	return err;
 }
 
-static int loop_clr_fd(struct loop_device *lo, struct block_device *bdev)
+static int loop_clr_fd(struct loop_device *lo)
 {
 	struct file *filp = lo->lo_backing_file;
 	gfp_t gfp = lo->old_gfp_mask;
+	struct block_device *bdev = lo->lo_device;
 
 	if (lo->lo_state != Lo_bound)
 		return -ENXIO;
 
-	if (lo->lo_refcnt > 1)	/* we needed one fd for the ioctl */
-		return -EBUSY;
+	/*
+	 * If we've explicitly asked to tear down the loop device,
+	 * and it has an elevated reference count, set it for auto-teardown when
+	 * the last reference goes away. This stops $!~#$@ udev from
+	 * preventing teardown because it decided that it needs to run blkid on
+	 * the loopback device whenever they appear. xfstests is notorious for
+	 * failing tests because blkid via udev races with a losetup
+	 * <dev>/do something like mkfs/losetup -d <dev> causing the losetup -d
+	 * command to fail with EBUSY.
+	 */
+	if (lo->lo_refcnt > 1) {
+		lo->lo_flags |= LO_FLAGS_AUTOCLEAR;
+		mutex_unlock(&lo->lo_ctl_mutex);
+		return 0;
+	}
 
 	if (filp == NULL)
 		return -EINVAL;
@@ -1012,13 +1028,14 @@ static int loop_clr_fd(struct loop_device *lo, struct block_device *bdev)
 	lo->lo_offset = 0;
 	lo->lo_sizelimit = 0;
 	lo->lo_encrypt_key_size = 0;
-	lo->lo_flags = 0;
 	lo->lo_thread = NULL;
 	memset(lo->lo_encrypt_key, 0, LO_KEY_SIZE);
 	memset(lo->lo_crypt_name, 0, LO_NAME_SIZE);
 	memset(lo->lo_file_name, 0, LO_NAME_SIZE);
-	if (bdev)
+	if (bdev) {
+		bdput(bdev);
 		invalidate_bdev(bdev);
+	}
 	set_capacity(lo->lo_disk, 0);
 	loop_sysfs_exit(lo);
 	if (bdev) {
@@ -1030,8 +1047,11 @@ static int loop_clr_fd(struct loop_device *lo, struct block_device *bdev)
 	lo->lo_state = Lo_unbound;
 	/* This is safe: open() is still holding a reference. */
 	module_put(THIS_MODULE);
-	if (max_part > 0 && bdev)
+	if (lo->lo_flags & LO_FLAGS_PARTSCAN && bdev)
 		ioctl_by_bdev(bdev, BLKRRPART, 0);
+	lo->lo_flags = 0;
+	if (!part_shift)
+		lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN;
 	mutex_unlock(&lo->lo_ctl_mutex);
 	/*
 	 * Need not hold lo_ctl_mutex to fput backing file.
@@ -1048,10 +1068,10 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 {
 	int err;
 	struct loop_func_table *xfer;
-	uid_t uid = current_uid();
+	kuid_t uid = current_uid();
 
 	if (lo->lo_encrypt_key_size &&
-	    lo->lo_key_owner != uid &&
+	    !uid_eq(lo->lo_key_owner, uid) &&
 	    !capable(CAP_SYS_ADMIN))
 		return -EPERM;
 	if (lo->lo_state != Lo_bound)
@@ -1079,12 +1099,11 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 		return err;
 
 	if (lo->lo_offset != info->lo_offset ||
-	    lo->lo_sizelimit != info->lo_sizelimit) {
-		lo->lo_offset = info->lo_offset;
-		lo->lo_sizelimit = info->lo_sizelimit;
-		if (figure_loop_size(lo))
+	    lo->lo_sizelimit != info->lo_sizelimit)
+		if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit))
 			return -EFBIG;
-	}
+
+	loop_config_discard(lo);
 
 	memcpy(lo->lo_file_name, info->lo_file_name, LO_NAME_SIZE);
 	memcpy(lo->lo_crypt_name, info->lo_crypt_name, LO_NAME_SIZE);
@@ -1100,6 +1119,13 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	     (info->lo_flags & LO_FLAGS_AUTOCLEAR))
 		lo->lo_flags ^= LO_FLAGS_AUTOCLEAR;
 
+	if ((info->lo_flags & LO_FLAGS_PARTSCAN) &&
+	     !(lo->lo_flags & LO_FLAGS_PARTSCAN)) {
+		lo->lo_flags |= LO_FLAGS_PARTSCAN;
+		lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN;
+		ioctl_by_bdev(lo->lo_device, BLKRRPART, 0);
+	}
+
 	lo->lo_encrypt_key_size = info->lo_encrypt_key_size;
 	lo->lo_init[0] = info->lo_init[0];
 	lo->lo_init[1] = info->lo_init[1];
@@ -1121,7 +1147,7 @@ loop_get_status(struct loop_device *lo, struct loop_info64 *info)
 
 	if (lo->lo_state != Lo_bound)
 		return -ENXIO;
-	error = vfs_getattr(file->f_path.mnt, file->f_path.dentry, &stat);
+	error = vfs_getattr(&file->f_path, &stat);
 	if (error)
 		return error;
 	memset(info, 0, sizeof(*info));
@@ -1253,28 +1279,10 @@ loop_get_status64(struct loop_device *lo, struct loop_info64 __user *arg) {
 
 static int loop_set_capacity(struct loop_device *lo, struct block_device *bdev)
 {
-	int err;
-	sector_t sec;
-	loff_t sz;
-
-	err = -ENXIO;
 	if (unlikely(lo->lo_state != Lo_bound))
-		goto out;
-	err = figure_loop_size(lo);
-	if (unlikely(err))
-		goto out;
-	sec = get_capacity(lo->lo_disk);
-	/* the width of sector_t may be narrow for bit-shift */
-	sz = sec;
-	sz <<= 9;
-	mutex_lock(&bdev->bd_mutex);
-	bd_set_size(bdev, sz);
-	/* let user-space know about the new size */
-	kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE);
-	mutex_unlock(&bdev->bd_mutex);
+		return -ENXIO;
 
- out:
-	return err;
+	return figure_loop_size(lo, lo->lo_offset, lo->lo_sizelimit);
 }
 
 static int lo_ioctl(struct block_device *bdev, fmode_t mode,
@@ -1293,18 +1301,24 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode,
 		break;
 	case LOOP_CLR_FD:
 		/* loop_clr_fd would have unlocked lo_ctl_mutex on success */
-		err = loop_clr_fd(lo, bdev);
+		err = loop_clr_fd(lo);
 		if (!err)
 			goto out_unlocked;
 		break;
 	case LOOP_SET_STATUS:
-		err = loop_set_status_old(lo, (struct loop_info __user *) arg);
+		err = -EPERM;
+		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
+			err = loop_set_status_old(lo,
+					(struct loop_info __user *)arg);
 		break;
 	case LOOP_GET_STATUS:
 		err = loop_get_status_old(lo, (struct loop_info __user *) arg);
 		break;
 	case LOOP_SET_STATUS64:
-		err = loop_set_status64(lo, (struct loop_info64 __user *) arg);
+		err = -EPERM;
+		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
+			err = loop_set_status64(lo,
+					(struct loop_info64 __user *) arg);
 		break;
 	case LOOP_GET_STATUS64:
 		err = loop_get_status64(lo, (struct loop_info64 __user *) arg);
@@ -1498,7 +1512,7 @@ out:
 	return err;
 }
 
-static int lo_release(struct gendisk *disk, fmode_t mode)
+static void lo_release(struct gendisk *disk, fmode_t mode)
 {
 	struct loop_device *lo = disk->private_data;
 	int err;
@@ -1513,9 +1527,9 @@ static int lo_release(struct gendisk *disk, fmode_t mode)
 		 * In autoclear mode, stop the loop thread
 		 * and remove configuration after last close.
 		 */
-		err = loop_clr_fd(lo, NULL);
+		err = loop_clr_fd(lo);
 		if (!err)
-			goto out_unlocked;
+			return;
 	} else {
 		/*
 		 * Otherwise keep thread (if running) and config,
@@ -1526,8 +1540,6 @@ static int lo_release(struct gendisk *disk, fmode_t mode)
 
 out:
 	mutex_unlock(&lo->lo_ctl_mutex);
-out_unlocked:
-	return 0;
 }
 
 static const struct block_device_operations lo_fops = {
@@ -1595,50 +1607,66 @@ static int loop_add(struct loop_device **l, int i)
 	struct gendisk *disk;
 	int err;
 
+	err = -ENOMEM;
 	lo = kzalloc(sizeof(*lo), GFP_KERNEL);
-	if (!lo) {
-		err = -ENOMEM;
+	if (!lo)
 		goto out;
-	}
 
-	err = idr_pre_get(&loop_index_idr, GFP_KERNEL);
-	if (err < 0)
-		goto out_free_dev;
+	lo->lo_state = Lo_unbound;
 
+	/* allocate id, if @id >= 0, we're requesting that specific id */
 	if (i >= 0) {
-		int m;
-
-		/* create specific i in the index */
-		err = idr_get_new_above(&loop_index_idr, lo, i, &m);
-		if (err >= 0 && i != m) {
-			idr_remove(&loop_index_idr, m);
+		err = idr_alloc(&loop_index_idr, lo, i, i + 1, GFP_KERNEL);
+		if (err == -ENOSPC)
 			err = -EEXIST;
-		}
-	} else if (i == -1) {
-		int m;
-
-		/* get next free nr */
-		err = idr_get_new(&loop_index_idr, lo, &m);
-		if (err >= 0)
-			i = m;
 	} else {
-		err = -EINVAL;
+		err = idr_alloc(&loop_index_idr, lo, 0, 0, GFP_KERNEL);
 	}
 	if (err < 0)
 		goto out_free_dev;
+	i = err;
 
+	err = -ENOMEM;
 	lo->lo_queue = blk_alloc_queue(GFP_KERNEL);
 	if (!lo->lo_queue)
-		goto out_free_dev;
+		goto out_free_idr;
+
+	/*
+	 * set queue make_request_fn
+	 */
+	blk_queue_make_request(lo->lo_queue, loop_make_request);
+	lo->lo_queue->queuedata = lo;
 
 	disk = lo->lo_disk = alloc_disk(1 << part_shift);
 	if (!disk)
 		goto out_free_queue;
 
+	/*
+	 * Disable partition scanning by default. The in-kernel partition
+	 * scanning can be requested individually per-device during its
+	 * setup. Userspace can always add and remove partitions from all
+	 * devices. The needed partition minors are allocated from the
+	 * extended minor space, the main loop device numbers will continue
+	 * to match the loop minors, regardless of the number of partitions
+	 * used.
+	 *
+	 * If max_part is given, partition scanning is globally enabled for
+	 * all loop devices. The minors for the main loop devices will be
+	 * multiples of max_part.
+	 *
+	 * Note: Global-for-all-devices, set-only-at-init, read-only module
+	 * parameteters like 'max_loop' and 'max_part' make things needlessly
+	 * complicated, are too static, inflexible and may surprise
+	 * userspace tools. Parameters like this in general should be avoided.
+	 */
+	if (!part_shift)
+		disk->flags |= GENHD_FL_NO_PART_SCAN;
+	disk->flags |= GENHD_FL_EXT_DEVT;
 	mutex_init(&lo->lo_ctl_mutex);
 	lo->lo_number		= i;
 	lo->lo_thread		= NULL;
 	init_waitqueue_head(&lo->lo_event);
+	init_waitqueue_head(&lo->lo_req_wait);
 	spin_lock_init(&lo->lo_lock);
 	disk->major		= LOOP_MAJOR;
 	disk->first_minor	= i << part_shift;
@@ -1652,6 +1680,8 @@ static int loop_add(struct loop_device **l, int i)
 
 out_free_queue:
 	blk_cleanup_queue(lo->lo_queue);
+out_free_idr:
+	idr_remove(&loop_index_idr, i);
 out_free_dev:
 	kfree(lo);
 out:
@@ -1715,7 +1745,7 @@ static struct kobject *loop_probe(dev_t dev, int *part, void *data)
 	if (err < 0)
 		err = loop_add(&lo, MINOR(dev) >> part_shift);
 	if (err < 0)
-		kobj = ERR_PTR(err);
+		kobj = NULL;
 	else
 		kobj = get_disk(lo->lo_disk);
 	mutex_unlock(&loop_index_mutex);
@@ -1814,11 +1844,15 @@ static int __init loop_init(void)
 		max_part = (1UL << part_shift) - 1;
 	}
 
-	if ((1UL << part_shift) > DISK_MAX_PARTS)
-		return -EINVAL;
+	if ((1UL << part_shift) > DISK_MAX_PARTS) {
+		err = -EINVAL;
+		goto misc_out;
+	}
 
-	if (max_loop > 1UL << (MINORBITS - part_shift))
-		return -EINVAL;
+	if (max_loop > 1UL << (MINORBITS - part_shift)) {
+		err = -EINVAL;
+		goto misc_out;
+	}
 
 	/*
 	 * If max_loop is specified, create that many devices upfront.
@@ -1836,8 +1870,10 @@ static int __init loop_init(void)
 		range = 1UL << MINORBITS;
 	}
 
-	if (register_blkdev(LOOP_MAJOR, "loop"))
-		return -EIO;
+	if (register_blkdev(LOOP_MAJOR, "loop")) {
+		err = -EIO;
+		goto misc_out;
+	}
 
 	blk_register_region(MKDEV(LOOP_MAJOR, 0), range,
 				  THIS_MODULE, loop_probe, NULL, NULL);
@@ -1850,6 +1886,10 @@ static int __init loop_init(void)
 
 	printk(KERN_INFO "loop: module loaded\n");
 	return 0;
+
+misc_out:
+	misc_deregister(&loop_misc);
+	return err;
 }
 
 static int loop_exit_cb(int id, void *ptr, void *data)
@@ -1867,7 +1907,6 @@ static void __exit loop_exit(void)
 	range = max_loop ? max_loop << part_shift : 1UL << MINORBITS;
 
 	idr_for_each(&loop_index_idr, &loop_exit_cb, NULL);
-	idr_remove_all(&loop_index_idr);
 	idr_destroy(&loop_index_idr);
 
 	blk_unregister_region(MKDEV(LOOP_MAJOR, 0), range);