[SCSI] scsi_debug: fix logical block provisioning support

provisioning map (map_storep) is a bitmap accessed by bitops.

So the allocation size should be a multiple of sizeof(unsigned long) and
also the bitmap should be cleared by using bitmap_clear() instead of
memset().

Otherwise it will cause problem on big-endian architecture if the number of
bits is not a multiple of BITS_PER_LONG.

I tried testing the logical block provisioning support in scsi_debug,
but it didn't work as I expected.

For example, load scsi_debug module with UNMAP command supported
and fill the storage with random data.

        # modprobe scsi_debug lbpu=1
        # dd if=/dev/urandom of=/dev/sdb

Then, try to unmap LBA 0, but Get LBA status reports:

        # sg_unmap --lba=0 --num=1 /dev/sdb
        # sg_get_lba_status --lba=0 /dev/sdb
        descriptor LBA: 0x0000000000000000  blocks: 16384  mapped

This is unexpected result.  Because UNMAP command to LBA 0 finished
without any errors, but Get LBA status shows that LBA 0 is still mapped.

This problem is due to the wrong translation between LBA and index of
provisioning map.  Fix it by using correct translation functions.

Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Acked-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 4b5d388..154d987 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -1997,24 +1997,39 @@
 	return ret;
 }
 
+static unsigned long lba_to_map_index(sector_t lba)
+{
+	if (scsi_debug_unmap_alignment) {
+		lba += scsi_debug_unmap_granularity -
+			scsi_debug_unmap_alignment;
+	}
+	do_div(lba, scsi_debug_unmap_granularity);
+
+	return lba;
+}
+
+static sector_t map_index_to_lba(unsigned long index)
+{
+	return index * scsi_debug_unmap_granularity -
+		scsi_debug_unmap_alignment;
+}
+
 static unsigned int map_state(sector_t lba, unsigned int *num)
 {
-	unsigned int granularity, alignment, mapped;
-	sector_t block, next, end;
+	sector_t end;
+	unsigned int mapped;
+	unsigned long index;
+	unsigned long next;
 
-	granularity = scsi_debug_unmap_granularity;
-	alignment = granularity - scsi_debug_unmap_alignment;
-	block = lba + alignment;
-	do_div(block, granularity);
-
-	mapped = test_bit(block, map_storep);
+	index = lba_to_map_index(lba);
+	mapped = test_bit(index, map_storep);
 
 	if (mapped)
-		next = find_next_zero_bit(map_storep, map_size, block);
+		next = find_next_zero_bit(map_storep, map_size, index);
 	else
-		next = find_next_bit(map_storep, map_size, block);
+		next = find_next_bit(map_storep, map_size, index);
 
-	end = next * granularity - scsi_debug_unmap_alignment;
+	end = min_t(sector_t, sdebug_store_sectors,  map_index_to_lba(next));
 	*num = end - lba;
 
 	return mapped;
@@ -2022,48 +2037,37 @@
 
 static void map_region(sector_t lba, unsigned int len)
 {
-	unsigned int granularity, alignment;
 	sector_t end = lba + len;
 
-	granularity = scsi_debug_unmap_granularity;
-	alignment = granularity - scsi_debug_unmap_alignment;
-
 	while (lba < end) {
-		sector_t block, rem;
+		unsigned long index = lba_to_map_index(lba);
 
-		block = lba + alignment;
-		rem = do_div(block, granularity);
+		if (index < map_size)
+			set_bit(index, map_storep);
 
-		if (block < map_size)
-			set_bit(block, map_storep);
-
-		lba += granularity - rem;
+		lba = map_index_to_lba(index + 1);
 	}
 }
 
 static void unmap_region(sector_t lba, unsigned int len)
 {
-	unsigned int granularity, alignment;
 	sector_t end = lba + len;
 
-	granularity = scsi_debug_unmap_granularity;
-	alignment = granularity - scsi_debug_unmap_alignment;
-
 	while (lba < end) {
-		sector_t block, rem;
+		unsigned long index = lba_to_map_index(lba);
 
-		block = lba + alignment;
-		rem = do_div(block, granularity);
-
-		if (rem == 0 && lba + granularity < end && block < map_size) {
-			clear_bit(block, map_storep);
-			if (scsi_debug_lbprz)
+		if (lba == map_index_to_lba(index) &&
+		    lba + scsi_debug_unmap_granularity <= end &&
+		    index < map_size) {
+			clear_bit(index, map_storep);
+			if (scsi_debug_lbprz) {
 				memset(fake_storep +
 				       lba * scsi_debug_sector_size, 0,
 				       scsi_debug_sector_size *
 				       scsi_debug_unmap_granularity);
+			}
 		}
-		lba += granularity - rem;
+		lba = map_index_to_lba(index + 1);
 	}
 }
 
@@ -3402,8 +3406,6 @@
 
 	/* Logical Block Provisioning */
 	if (scsi_debug_lbp()) {
-		unsigned int map_bytes;
-
 		scsi_debug_unmap_max_blocks =
 			clamp(scsi_debug_unmap_max_blocks, 0U, 0xffffffffU);
 
@@ -3422,9 +3424,8 @@
 			return -EINVAL;
 		}
 
-		map_size = (sdebug_store_sectors / scsi_debug_unmap_granularity);
-		map_bytes = map_size >> 3;
-		map_storep = vmalloc(map_bytes);
+		map_size = lba_to_map_index(sdebug_store_sectors - 1) + 1;
+		map_storep = vmalloc(BITS_TO_LONGS(map_size) * sizeof(long));
 
 		printk(KERN_INFO "scsi_debug_init: %lu provisioning blocks\n",
 		       map_size);
@@ -3435,7 +3436,7 @@
 			goto free_vm;
 		}
 
-		memset(map_storep, 0x0, map_bytes);
+		bitmap_zero(map_storep, map_size);
 
 		/* Map first 1KB for partition table */
 		if (scsi_debug_num_parts)