1 files changed, 40 insertions, 29 deletions

diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index ae7e91bd0618..6c503824ba3f 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -14,6 +14,9 @@
 #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"
 
@@ -70,7 +73,7 @@ EXPORT_SYMBOL_GPL(__blk_req_zone_write_unlock);
 static inline unsigned int __blkdev_nr_zones(struct request_queue *q,
 					     sector_t nr_sectors)
 {
-	unsigned long zone_sectors = blk_queue_zone_sectors(q);
+	sector_t zone_sectors = blk_queue_zone_sectors(q);
 
 	return (nr_sectors + zone_sectors - 1) >> ilog2(zone_sectors);
 }
@@ -117,8 +120,7 @@ static bool blkdev_report_zone(struct block_device *bdev, struct blk_zone *rep)
 }
 
 static int blk_report_zones(struct gendisk *disk, sector_t sector,
-			    struct blk_zone *zones, unsigned int *nr_zones,
-			    gfp_t gfp_mask)
+			    struct blk_zone *zones, unsigned int *nr_zones)
 {
 	struct request_queue *q = disk->queue;
 	unsigned int z = 0, n, nrz = *nr_zones;
@@ -127,8 +129,7 @@ static int blk_report_zones(struct gendisk *disk, sector_t sector,
 
 	while (z < nrz && sector < capacity) {
 		n = nrz - z;
-		ret = disk->fops->report_zones(disk, sector, &zones[z], &n,
-					       gfp_mask);
+		ret = disk->fops->report_zones(disk, sector, &zones[z], &n);
 		if (ret)
 			return ret;
 		if (!n)
@@ -149,17 +150,18 @@ static int blk_report_zones(struct gendisk *disk, sector_t sector,
  * @sector:	Sector from which to report zones
  * @zones:	Array of zone structures where to return the zones information
  * @nr_zones:	Number of zone structures in the zone array
- * @gfp_mask:	Memory allocation flags (for bio_alloc)
  *
  * Description:
  *    Get zone information starting from the zone containing @sector.
  *    The number of zone information reported may be less than the number
  *    requested by @nr_zones. The number of zones actually reported is
  *    returned in @nr_zones.
+ *    The caller must use memalloc_noXX_save/restore() calls to control
+ *    memory allocations done within this function (zone array and command
+ *    buffer allocation by the device driver).
  */
 int blkdev_report_zones(struct block_device *bdev, sector_t sector,
-			struct blk_zone *zones, unsigned int *nr_zones,
-			gfp_t gfp_mask)
+			struct blk_zone *zones, unsigned int *nr_zones)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
 	unsigned int i, nrz;
@@ -184,7 +186,7 @@ int blkdev_report_zones(struct block_device *bdev, sector_t sector,
 	nrz = min(*nr_zones,
 		  __blkdev_nr_zones(q, bdev->bd_part->nr_sects - sector));
 	ret = blk_report_zones(bdev->bd_disk, get_start_sect(bdev) + sector,
-			       zones, &nrz, gfp_mask);
+			       zones, &nrz);
 	if (ret)
 		return ret;
 
@@ -305,9 +307,7 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
 	if (!zones)
 		return -ENOMEM;
 
-	ret = blkdev_report_zones(bdev, rep.sector,
-				  zones, &rep.nr_zones,
-				  GFP_KERNEL);
+	ret = blkdev_report_zones(bdev, rep.sector, zones, &rep.nr_zones);
 	if (ret)
 		goto out;
 
@@ -373,22 +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)
@@ -415,6 +418,7 @@ int blk_revalidate_disk_zones(struct gendisk *disk)
 	unsigned long *seq_zones_wlock = NULL, *seq_zones_bitmap = NULL;
 	unsigned int i, rep_nr_zones = 0, z = 0, nrz;
 	struct blk_zone *zones = NULL;
+	unsigned int noio_flag;
 	sector_t sector = 0;
 	int ret = 0;
 
@@ -427,6 +431,12 @@ int blk_revalidate_disk_zones(struct gendisk *disk)
 		return 0;
 	}
 
+	/*
+	 * Ensure that all memory allocations in this context are done as
+	 * if GFP_NOIO was specified.
+	 */
+	noio_flag = memalloc_noio_save();
+
 	if (!blk_queue_is_zoned(q) || !nr_zones) {
 		nr_zones = 0;
 		goto update;
@@ -443,13 +453,13 @@ 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;
 
 	while (z < nr_zones) {
 		nrz = min(nr_zones - z, rep_nr_zones);
-		ret = blk_report_zones(disk, sector, zones, &nrz, GFP_NOIO);
+		ret = blk_report_zones(disk, sector, zones, &nrz);
 		if (ret)
 			goto out;
 		if (!nrz)
@@ -480,8 +490,9 @@ update:
 	blk_mq_unfreeze_queue(q);
 
 out:
-	free_pages((unsigned long)zones,
-		   get_order(rep_nr_zones * sizeof(struct blk_zone)));
+	memalloc_noio_restore(noio_flag);
+
+	kvfree(zones);
 	kfree(seq_zones_wlock);
 	kfree(seq_zones_bitmap);