[dm-devel] [PATCH V6 4/4] block: Limit zone array allocation size

[Damien Le Moal]

Limit the size of the struct blk_zone array used in
blk_revalidate_disk_zones() to avoid memory allocation failures leading
to disk revalidation failure. Also further reduce the likelyhood of
such failures by using kvcalloc() (that is vmalloc()) instead of
allocating contiguous pages with alloc_pages().

Fixes: 515ce6061312 ("scsi: sd_zbc: Fix sd_zbc_report_zones() buffer allocation")
Fixes: e76239a3748c ("block: add a report_zones method")
Cc: stable at vger.kernel.org
Signed-off-by: Damien Le Moal <damien.lemoal at wdc.com>
---
 block/blk-zoned.c      | 36 ++++++++++++++++++++----------------
 include/linux/blkdev.h |  5 +++++
 2 files changed, 25 insertions(+), 16 deletions(-)

diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 60dfc3f22350..79ad269b545d 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -14,6 +14,8 @@
 #include <linux/rbtree.h>
 #include <linux/blkdev.h>
 #include <linux/blk-mq.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
 #include <linux/sched/mm.h>
 
 #include "blk.h"
@@ -371,22 +373,25 @@ static inline unsigned long *blk_alloc_zone_bitmap(int node,
  * Allocate an array of struct blk_zone to get nr_zones zone information.
  * The allocated array may be smaller than nr_zones.
  */
-static struct blk_zone *blk_alloc_zones(int node, unsigned int *nr_zones)
+static struct blk_zone *blk_alloc_zones(unsigned int *nr_zones)
 {
-	size_t size = *nr_zones * sizeof(struct blk_zone);
-	struct page *page;
-	int order;
-
-	for (order = get_order(size); order >= 0; order--) {
-		page = alloc_pages_node(node, GFP_NOIO | __GFP_ZERO, order);
-		if (page) {
-			*nr_zones = min_t(unsigned int, *nr_zones,
-				(PAGE_SIZE << order) / sizeof(struct blk_zone));
-			return page_address(page);
-		}
+	struct blk_zone *zones;
+	size_t nrz = min(*nr_zones, BLK_ZONED_REPORT_MAX_ZONES);
+
+	/*
+	 * GFP_KERNEL here is meaningless as the caller task context has
+	 * the PF_MEMALLOC_NOIO flag set in blk_revalidate_disk_zones()
+	 * with memalloc_noio_save().
+	 */
+	zones = kvcalloc(nrz, sizeof(struct blk_zone), GFP_KERNEL);
+	if (!zones) {
+		*nr_zones = 0;
+		return NULL;
 	}
 
-	return NULL;
+	*nr_zones = nrz;
+
+	return zones;
 }
 
 void blk_queue_free_zone_bitmaps(struct request_queue *q)
@@ -448,7 +453,7 @@ int blk_revalidate_disk_zones(struct gendisk *disk)
 
 	/* Get zone information and initialize seq_zones_bitmap */
 	rep_nr_zones = nr_zones;
-	zones = blk_alloc_zones(q->node, &rep_nr_zones);
+	zones = blk_alloc_zones(&rep_nr_zones);
 	if (!zones)
 		goto out;
 
@@ -487,8 +492,7 @@ int blk_revalidate_disk_zones(struct gendisk *disk)
 out:
 	memalloc_noio_restore(noio_flag);
 
-	free_pages((unsigned long)zones,
-		   get_order(rep_nr_zones * sizeof(struct blk_zone)));
+	kvfree(zones);
 	kfree(seq_zones_wlock);
 	kfree(seq_zones_bitmap);
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 472ba74ca968..5ace0bb77213 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -344,6 +344,11 @@ struct queue_limits {
 
 #ifdef CONFIG_BLK_DEV_ZONED
 
+/*
+ * Maximum number of zones to report with a single report zones command.
+ */
+#define BLK_ZONED_REPORT_MAX_ZONES	8192U
+
 extern unsigned int blkdev_nr_zones(struct block_device *bdev);
 extern int blkdev_report_zones(struct block_device *bdev,
 			       sector_t sector, struct blk_zone *zones,
-- 
2.21.0