1 files changed, 188 insertions, 172 deletions

diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index ccd0dd0c6b83..04fc6b552c04 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -152,6 +152,10 @@ static unsigned int xen_blkif_max_ring_order;
 module_param_named(max_ring_page_order, xen_blkif_max_ring_order, int, 0444);
 MODULE_PARM_DESC(max_ring_page_order, "Maximum order of pages to be used for the shared ring");
 
+static bool __read_mostly xen_blkif_trusted = true;
+module_param_named(trusted, xen_blkif_trusted, bool, 0644);
+MODULE_PARM_DESC(trusted, "Is the backend trusted");
+
 #define BLK_RING_SIZE(info)	\
 	__CONST_RING_SIZE(blkif, XEN_PAGE_SIZE * (info)->nr_ring_pages)
 
@@ -209,7 +213,11 @@ struct blkfront_info
 	unsigned int feature_fua:1;
 	unsigned int feature_discard:1;
 	unsigned int feature_secdiscard:1;
+	/* Connect-time cached feature_persistent parameter */
+	unsigned int feature_persistent_parm:1;
+	/* Persistent grants feature negotiation result */
 	unsigned int feature_persistent:1;
+	unsigned int bounce:1;
 	unsigned int discard_granularity;
 	unsigned int discard_alignment;
 	/* Number of 4KB segments handled */
@@ -229,8 +237,6 @@ static unsigned int nr_minors;
 static unsigned long *minors;
 static DEFINE_SPINLOCK(minor_lock);
 
-#define GRANT_INVALID_REF	0
-
 #define PARTS_PER_DISK		16
 #define PARTS_PER_EXT_DISK      256
 
@@ -312,8 +318,8 @@ static int fill_grant_buffer(struct blkfront_ring_info *rinfo, int num)
 		if (!gnt_list_entry)
 			goto out_of_memory;
 
-		if (info->feature_persistent) {
-			granted_page = alloc_page(GFP_NOIO);
+		if (info->bounce) {
+			granted_page = alloc_page(GFP_NOIO | __GFP_ZERO);
 			if (!granted_page) {
 				kfree(gnt_list_entry);
 				goto out_of_memory;
@@ -321,7 +327,7 @@ static int fill_grant_buffer(struct blkfront_ring_info *rinfo, int num)
 			gnt_list_entry->page = granted_page;
 		}
 
-		gnt_list_entry->gref = GRANT_INVALID_REF;
+		gnt_list_entry->gref = INVALID_GRANT_REF;
 		list_add(&gnt_list_entry->node, &rinfo->grants);
 		i++;
 	}
@@ -332,7 +338,7 @@ out_of_memory:
 	list_for_each_entry_safe(gnt_list_entry, n,
 	                         &rinfo->grants, node) {
 		list_del(&gnt_list_entry->node);
-		if (info->feature_persistent)
+		if (info->bounce)
 			__free_page(gnt_list_entry->page);
 		kfree(gnt_list_entry);
 		i--;
@@ -350,7 +356,7 @@ static struct grant *get_free_grant(struct blkfront_ring_info *rinfo)
 					  node);
 	list_del(&gnt_list_entry->node);
 
-	if (gnt_list_entry->gref != GRANT_INVALID_REF)
+	if (gnt_list_entry->gref != INVALID_GRANT_REF)
 		rinfo->persistent_gnts_c--;
 
 	return gnt_list_entry;
@@ -372,13 +378,13 @@ static struct grant *get_grant(grant_ref_t *gref_head,
 	struct grant *gnt_list_entry = get_free_grant(rinfo);
 	struct blkfront_info *info = rinfo->dev_info;
 
-	if (gnt_list_entry->gref != GRANT_INVALID_REF)
+	if (gnt_list_entry->gref != INVALID_GRANT_REF)
 		return gnt_list_entry;
 
 	/* Assign a gref to this page */
 	gnt_list_entry->gref = gnttab_claim_grant_reference(gref_head);
 	BUG_ON(gnt_list_entry->gref == -ENOSPC);
-	if (info->feature_persistent)
+	if (info->bounce)
 		grant_foreign_access(gnt_list_entry, info);
 	else {
 		/* Grant access to the GFN passed by the caller */
@@ -396,13 +402,13 @@ static struct grant *get_indirect_grant(grant_ref_t *gref_head,
 	struct grant *gnt_list_entry = get_free_grant(rinfo);
 	struct blkfront_info *info = rinfo->dev_info;
 
-	if (gnt_list_entry->gref != GRANT_INVALID_REF)
+	if (gnt_list_entry->gref != INVALID_GRANT_REF)
 		return gnt_list_entry;
 
 	/* Assign a gref to this page */
 	gnt_list_entry->gref = gnttab_claim_grant_reference(gref_head);
 	BUG_ON(gnt_list_entry->gref == -ENOSPC);
-	if (!info->feature_persistent) {
+	if (!info->bounce) {
 		struct page *indirect_page;
 
 		/* Fetch a pre-allocated page to use for indirect grefs */
@@ -487,11 +493,11 @@ static void blkif_restart_queue_callback(void *arg)
 	schedule_work(&rinfo->work);
 }
 
-static int blkif_getgeo(struct block_device *bd, struct hd_geometry *hg)
+static int blkif_getgeo(struct gendisk *disk, struct hd_geometry *hg)
 {
 	/* We don't have real geometry info, but let's at least return
 	   values consistent with the size of the device */
-	sector_t nsect = get_capacity(bd->bd_disk);
+	sector_t nsect = get_capacity(disk);
 	sector_t cylinders = nsect;
 
 	hg->heads = 0xff;
@@ -503,7 +509,7 @@ static int blkif_getgeo(struct block_device *bd, struct hd_geometry *hg)
 	return 0;
 }
 
-static int blkif_ioctl(struct block_device *bdev, fmode_t mode,
+static int blkif_ioctl(struct block_device *bdev, blk_mode_t mode,
 		       unsigned command, unsigned long argument)
 {
 	struct blkfront_info *info = bdev->bd_disk->private_data;
@@ -576,7 +582,7 @@ struct setup_rw_req {
 	struct blkif_request *ring_req;
 	grant_ref_t gref_head;
 	unsigned int id;
-	/* Only used when persistent grant is used and it's a read request */
+	/* Only used when persistent grant is used and it's a write request */
 	bool need_copy;
 	unsigned int bvec_off;
 	char *bvec_data;
@@ -705,7 +711,7 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri
 		.grant_idx = 0,
 		.segments = NULL,
 		.rinfo = rinfo,
-		.need_copy = rq_data_dir(req) && info->feature_persistent,
+		.need_copy = rq_data_dir(req) && info->bounce,
 	};
 
 	/*
@@ -745,7 +751,7 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri
 	id = blkif_ring_get_request(rinfo, req, &final_ring_req);
 	ring_req = &rinfo->shadow[id].req;
 
-	num_sg = blk_rq_map_sg(req->q, req, rinfo->shadow[id].sg);
+	num_sg = blk_rq_map_sg(req, rinfo->shadow[id].sg);
 	num_grant = 0;
 	/* Calculate the number of grant used */
 	for_each_sg(rinfo->shadow[id].sg, sg, num_sg, i)
@@ -774,13 +780,19 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri
 		ring_req->u.rw.handle = info->handle;
 		ring_req->operation = rq_data_dir(req) ?
 			BLKIF_OP_WRITE : BLKIF_OP_READ;
-		if (req_op(req) == REQ_OP_FLUSH || req->cmd_flags & REQ_FUA) {
+		if (req_op(req) == REQ_OP_FLUSH ||
+		    (req_op(req) == REQ_OP_WRITE && (req->cmd_flags & REQ_FUA))) {
 			/*
 			 * Ideally we can do an unordered flush-to-disk.
 			 * In case the backend onlysupports barriers, use that.
 			 * A barrier request a superset of FUA, so we can
 			 * implement it the same way.  (It's also a FLUSH+FUA,
 			 * since it is guaranteed ordered WRT previous writes.)
+			 *
+			 * Note that can end up here with a FUA write and the
+			 * flags cleared.  This happens when the flag was
+			 * run-time disabled after a failing I/O, and we'll
+			 * simplify submit it as a normal write.
 			 */
 			if (info->feature_flush && info->feature_fua)
 				ring_req->operation =
@@ -788,8 +800,6 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri
 			else if (info->feature_flush)
 				ring_req->operation =
 					BLKIF_OP_FLUSH_DISKCACHE;
-			else
-				ring_req->operation = 0;
 		}
 		ring_req->u.rw.nr_segments = num_grant;
 		if (unlikely(require_extra_req)) {
@@ -880,16 +890,6 @@ static inline void flush_requests(struct blkfront_ring_info *rinfo)
 		notify_remote_via_irq(rinfo->irq);
 }
 
-static inline bool blkif_request_flush_invalid(struct request *req,
-					       struct blkfront_info *info)
-{
-	return (blk_rq_is_passthrough(req) ||
-		((req_op(req) == REQ_OP_FLUSH) &&
-		 !info->feature_flush) ||
-		((req->cmd_flags & REQ_FUA) &&
-		 !info->feature_fua));
-}
-
 static blk_status_t blkif_queue_rq(struct blk_mq_hw_ctx *hctx,
 			  const struct blk_mq_queue_data *qd)
 {
@@ -901,12 +901,22 @@ static blk_status_t blkif_queue_rq(struct blk_mq_hw_ctx *hctx,
 	rinfo = get_rinfo(info, qid);
 	blk_mq_start_request(qd->rq);
 	spin_lock_irqsave(&rinfo->ring_lock, flags);
-	if (RING_FULL(&rinfo->ring))
-		goto out_busy;
 
-	if (blkif_request_flush_invalid(qd->rq, rinfo->dev_info))
-		goto out_err;
+	/*
+	 * Check if the backend actually supports flushes.
+	 *
+	 * While the block layer won't send us flushes if we don't claim to
+	 * support them, the Xen protocol allows the backend to revoke support
+	 * at any time.  That is of course a really bad idea and dangerous, but
+	 * has been allowed for 10+ years.  In that case we simply clear the
+	 * flags, and directly return here for an empty flush and ignore the
+	 * FUA flag later on.
+	 */
+	if (unlikely(req_op(qd->rq) == REQ_OP_FLUSH && !info->feature_flush))
+		goto complete;
 
+	if (RING_FULL(&rinfo->ring))
+		goto out_busy;
 	if (blkif_queue_request(qd->rq, rinfo))
 		goto out_busy;
 
@@ -914,14 +924,14 @@ static blk_status_t blkif_queue_rq(struct blk_mq_hw_ctx *hctx,
 	spin_unlock_irqrestore(&rinfo->ring_lock, flags);
 	return BLK_STS_OK;
 
-out_err:
-	spin_unlock_irqrestore(&rinfo->ring_lock, flags);
-	return BLK_STS_IOERR;
-
 out_busy:
 	blk_mq_stop_hw_queue(hctx);
 	spin_unlock_irqrestore(&rinfo->ring_lock, flags);
 	return BLK_STS_DEV_RESOURCE;
+complete:
+	spin_unlock_irqrestore(&rinfo->ring_lock, flags);
+	blk_mq_end_request(qd->rq, BLK_STS_OK);
+	return BLK_STS_OK;
 }
 
 static void blkif_complete_rq(struct request *rq)
@@ -934,39 +944,41 @@ static const struct blk_mq_ops blkfront_mq_ops = {
 	.complete = blkif_complete_rq,
 };
 
-static void blkif_set_queue_limits(struct blkfront_info *info)
+static void blkif_set_queue_limits(const struct blkfront_info *info,
+		struct queue_limits *lim)
 {
-	struct request_queue *rq = info->rq;
-	struct gendisk *gd = info->gd;
 	unsigned int segments = info->max_indirect_segments ? :
 				BLKIF_MAX_SEGMENTS_PER_REQUEST;
 
-	blk_queue_flag_set(QUEUE_FLAG_VIRT, rq);
-
 	if (info->feature_discard) {
-		blk_queue_flag_set(QUEUE_FLAG_DISCARD, rq);
-		blk_queue_max_discard_sectors(rq, get_capacity(gd));
-		rq->limits.discard_granularity = info->discard_granularity ?:
-						 info->physical_sector_size;
-		rq->limits.discard_alignment = info->discard_alignment;
+		lim->max_hw_discard_sectors = UINT_MAX;
+		if (info->discard_granularity)
+			lim->discard_granularity = info->discard_granularity;
+		lim->discard_alignment = info->discard_alignment;
 		if (info->feature_secdiscard)
-			blk_queue_flag_set(QUEUE_FLAG_SECERASE, rq);
+			lim->max_secure_erase_sectors = UINT_MAX;
+	}
+
+	if (info->feature_flush) {
+		lim->features |= BLK_FEAT_WRITE_CACHE;
+		if (info->feature_fua)
+			lim->features |= BLK_FEAT_FUA;
 	}
 
 	/* Hard sector size and max sectors impersonate the equiv. hardware. */
-	blk_queue_logical_block_size(rq, info->sector_size);
-	blk_queue_physical_block_size(rq, info->physical_sector_size);
-	blk_queue_max_hw_sectors(rq, (segments * XEN_PAGE_SIZE) / 512);
+	lim->logical_block_size = info->sector_size;
+	lim->physical_block_size = info->physical_sector_size;
+	lim->max_hw_sectors = (segments * XEN_PAGE_SIZE) / 512;
 
 	/* Each segment in a request is up to an aligned page in size. */
-	blk_queue_segment_boundary(rq, PAGE_SIZE - 1);
-	blk_queue_max_segment_size(rq, PAGE_SIZE);
+	lim->seg_boundary_mask = PAGE_SIZE - 1;
+	lim->max_segment_size = PAGE_SIZE;
 
 	/* Ensure a merged request will fit in a single I/O ring slot. */
-	blk_queue_max_segments(rq, segments / GRANTS_PER_PSEG);
+	lim->max_segments = segments / GRANTS_PER_PSEG;
 
 	/* Make sure buffer addresses are sector-aligned. */
-	blk_queue_dma_alignment(rq, 511);
+	lim->dma_alignment = 511;
 }
 
 static const char *flush_info(struct blkfront_info *info)
@@ -981,13 +993,12 @@ static const char *flush_info(struct blkfront_info *info)
 
 static void xlvbd_flush(struct blkfront_info *info)
 {
-	blk_queue_write_cache(info->rq, info->feature_flush ? true : false,
-			      info->feature_fua ? true : false);
-	pr_info("blkfront: %s: %s %s %s %s %s\n",
+	pr_info("blkfront: %s: %s %s %s %s %s %s %s\n",
 		info->gd->disk_name, flush_info(info),
 		"persistent grants:", info->feature_persistent ?
 		"enabled;" : "disabled;", "indirect descriptors:",
-		info->max_indirect_segments ? "enabled;" : "disabled;");
+		info->max_indirect_segments ? "enabled;" : "disabled;",
+		"bounce buffer:", info->bounce ? "enabled" : "disabled;");
 }
 
 static int xen_translate_vdev(int vdevice, int *minor, unsigned int *offset)
@@ -1059,9 +1070,9 @@ static char *encode_disk_name(char *ptr, unsigned int n)
 }
 
 static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
-		struct blkfront_info *info, u16 sector_size,
-		unsigned int physical_sector_size)
+		struct blkfront_info *info)
 {
+	struct queue_limits lim = {};
 	struct gendisk *gd;
 	int nr_minors = 1;
 	int err;
@@ -1120,7 +1131,6 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 	} else
 		info->tag_set.queue_depth = BLK_RING_SIZE(info);
 	info->tag_set.numa_node = NUMA_NO_NODE;
-	info->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
 	info->tag_set.cmd_size = sizeof(struct blkif_req);
 	info->tag_set.driver_data = info;
 
@@ -1128,7 +1138,8 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 	if (err)
 		goto out_release_minors;
 
-	gd = blk_mq_alloc_disk(&info->tag_set, info);
+	blkif_set_queue_limits(info, &lim);
+	gd = blk_mq_alloc_disk(&info->tag_set, &lim, info);
 	if (IS_ERR(gd)) {
 		err = PTR_ERR(gd);
 		goto out_free_tag_set;
@@ -1152,9 +1163,6 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 
 	info->rq = gd->queue;
 	info->gd = gd;
-	info->sector_size = sector_size;
-	info->physical_sector_size = physical_sector_size;
-	blkif_set_queue_limits(info);
 
 	xlvbd_flush(info);
 
@@ -1209,7 +1217,7 @@ static void blkif_free_ring(struct blkfront_ring_info *rinfo)
 	if (!list_empty(&rinfo->indirect_pages)) {
 		struct page *indirect_page, *n;
 
-		BUG_ON(info->feature_persistent);
+		BUG_ON(info->bounce);
 		list_for_each_entry_safe(indirect_page, n, &rinfo->indirect_pages, lru) {
 			list_del(&indirect_page->lru);
 			__free_page(indirect_page);
@@ -1221,12 +1229,12 @@ static void blkif_free_ring(struct blkfront_ring_info *rinfo)
 		list_for_each_entry_safe(persistent_gnt, n,
 					 &rinfo->grants, node) {
 			list_del(&persistent_gnt->node);
-			if (persistent_gnt->gref != GRANT_INVALID_REF) {
+			if (persistent_gnt->gref != INVALID_GRANT_REF) {
 				gnttab_end_foreign_access(persistent_gnt->gref,
-							  0, 0UL);
+							  NULL);
 				rinfo->persistent_gnts_c--;
 			}
-			if (info->feature_persistent)
+			if (info->bounce)
 				__free_page(persistent_gnt->page);
 			kfree(persistent_gnt);
 		}
@@ -1246,8 +1254,8 @@ static void blkif_free_ring(struct blkfront_ring_info *rinfo)
 		       rinfo->shadow[i].req.u.rw.nr_segments;
 		for (j = 0; j < segs; j++) {
 			persistent_gnt = rinfo->shadow[i].grants_used[j];
-			gnttab_end_foreign_access(persistent_gnt->gref, 0, 0UL);
-			if (info->feature_persistent)
+			gnttab_end_foreign_access(persistent_gnt->gref, NULL);
+			if (info->bounce)
 				__free_page(persistent_gnt->page);
 			kfree(persistent_gnt);
 		}
@@ -1261,7 +1269,7 @@ static void blkif_free_ring(struct blkfront_ring_info *rinfo)
 
 		for (j = 0; j < INDIRECT_GREFS(segs); j++) {
 			persistent_gnt = rinfo->shadow[i].indirect_grants[j];
-			gnttab_end_foreign_access(persistent_gnt->gref, 0, 0UL);
+			gnttab_end_foreign_access(persistent_gnt->gref, NULL);
 			__free_page(persistent_gnt->page);
 			kfree(persistent_gnt);
 		}
@@ -1282,14 +1290,8 @@ free_shadow:
 	flush_work(&rinfo->work);
 
 	/* Free resources associated with old device channel. */
-	for (i = 0; i < info->nr_ring_pages; i++) {
-		if (rinfo->ring_ref[i] != GRANT_INVALID_REF) {
-			gnttab_end_foreign_access(rinfo->ring_ref[i], 0, 0);
-			rinfo->ring_ref[i] = GRANT_INVALID_REF;
-		}
-	}
-	free_pages((unsigned long)rinfo->ring.sring, get_order(info->nr_ring_pages * XEN_PAGE_SIZE));
-	rinfo->ring.sring = NULL;
+	xenbus_teardown_ring((void **)&rinfo->ring.sring, info->nr_ring_pages,
+			     rinfo->ring_ref);
 
 	if (rinfo->irq)
 		unbind_from_irqhandler(rinfo->irq, rinfo);
@@ -1372,9 +1374,15 @@ static int blkif_get_final_status(enum blk_req_status s1,
 	return BLKIF_RSP_OKAY;
 }
 
-static bool blkif_completion(unsigned long *id,
-			     struct blkfront_ring_info *rinfo,
-			     struct blkif_response *bret)
+/*
+ * Return values:
+ *  1 response processed.
+ *  0 missing further responses.
+ * -1 error while processing.
+ */
+static int blkif_completion(unsigned long *id,
+			    struct blkfront_ring_info *rinfo,
+			    struct blkif_response *bret)
 {
 	int i = 0;
 	struct scatterlist *sg;
@@ -1397,7 +1405,7 @@ static bool blkif_completion(unsigned long *id,
 
 		/* Wait the second response if not yet here. */
 		if (s2->status < REQ_DONE)
-			return false;
+			return 0;
 
 		bret->status = blkif_get_final_status(s->status,
 						      s2->status);
@@ -1430,7 +1438,7 @@ static bool blkif_completion(unsigned long *id,
 	data.s = s;
 	num_sg = s->num_sg;
 
-	if (bret->operation == BLKIF_OP_READ && info->feature_persistent) {
+	if (bret->operation == BLKIF_OP_READ && info->bounce) {
 		for_each_sg(s->sg, sg, num_sg, i) {
 			BUG_ON(sg->offset + sg->length > PAGE_SIZE);
 
@@ -1448,57 +1456,58 @@ static bool blkif_completion(unsigned long *id,
 	}
 	/* Add the persistent grant into the list of free grants */
 	for (i = 0; i < num_grant; i++) {
-		if (gnttab_query_foreign_access(s->grants_used[i]->gref)) {
+		if (!gnttab_try_end_foreign_access(s->grants_used[i]->gref)) {
 			/*
 			 * If the grant is still mapped by the backend (the
 			 * backend has chosen to make this grant persistent)
 			 * we add it at the head of the list, so it will be
 			 * reused first.
 			 */
-			if (!info->feature_persistent)
-				pr_alert_ratelimited("backed has not unmapped grant: %u\n",
-						     s->grants_used[i]->gref);
+			if (!info->feature_persistent) {
+				pr_alert("backed has not unmapped grant: %u\n",
+					 s->grants_used[i]->gref);
+				return -1;
+			}
 			list_add(&s->grants_used[i]->node, &rinfo->grants);
 			rinfo->persistent_gnts_c++;
 		} else {
 			/*
-			 * If the grant is not mapped by the backend we end the
-			 * foreign access and add it to the tail of the list,
-			 * so it will not be picked again unless we run out of
-			 * persistent grants.
+			 * If the grant is not mapped by the backend we add it
+			 * to the tail of the list, so it will not be picked
+			 * again unless we run out of persistent grants.
 			 */
-			gnttab_end_foreign_access(s->grants_used[i]->gref, 0, 0UL);
-			s->grants_used[i]->gref = GRANT_INVALID_REF;
+			s->grants_used[i]->gref = INVALID_GRANT_REF;
 			list_add_tail(&s->grants_used[i]->node, &rinfo->grants);
 		}
 	}
 	if (s->req.operation == BLKIF_OP_INDIRECT) {
 		for (i = 0; i < INDIRECT_GREFS(num_grant); i++) {
-			if (gnttab_query_foreign_access(s->indirect_grants[i]->gref)) {
-				if (!info->feature_persistent)
-					pr_alert_ratelimited("backed has not unmapped grant: %u\n",
-							     s->indirect_grants[i]->gref);
+			if (!gnttab_try_end_foreign_access(s->indirect_grants[i]->gref)) {
+				if (!info->feature_persistent) {
+					pr_alert("backed has not unmapped grant: %u\n",
+						 s->indirect_grants[i]->gref);
+					return -1;
+				}
 				list_add(&s->indirect_grants[i]->node, &rinfo->grants);
 				rinfo->persistent_gnts_c++;
 			} else {
 				struct page *indirect_page;
 
-				gnttab_end_foreign_access(s->indirect_grants[i]->gref, 0, 0UL);
 				/*
 				 * Add the used indirect page back to the list of
 				 * available pages for indirect grefs.
 				 */
-				if (!info->feature_persistent) {
+				if (!info->bounce) {
 					indirect_page = s->indirect_grants[i]->page;
 					list_add(&indirect_page->lru, &rinfo->indirect_pages);
 				}
-				s->indirect_grants[i]->gref = GRANT_INVALID_REF;
+				s->indirect_grants[i]->gref = INVALID_GRANT_REF;
 				list_add_tail(&s->indirect_grants[i]->node, &rinfo->grants);
 			}
 		}
 	}
 
-	return true;
+	return 1;
 }
 
 static irqreturn_t blkif_interrupt(int irq, void *dev_id)
@@ -1564,12 +1573,17 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 		}
 
 		if (bret.operation != BLKIF_OP_DISCARD) {
+			int ret;
+
 			/*
 			 * We may need to wait for an extra response if the
 			 * I/O request is split in 2
 			 */
-			if (!blkif_completion(&id, rinfo, &bret))
+			ret = blkif_completion(&id, rinfo, &bret);
+			if (!ret)
 				continue;
+			if (unlikely(ret < 0))
+				goto err;
 		}
 
 		if (add_id_to_freelist(rinfo, id)) {
@@ -1593,8 +1607,8 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 				blkif_req(req)->error = BLK_STS_NOTSUPP;
 				info->feature_discard = 0;
 				info->feature_secdiscard = 0;
-				blk_queue_flag_clear(QUEUE_FLAG_DISCARD, rq);
-				blk_queue_flag_clear(QUEUE_FLAG_SECERASE, rq);
+				blk_queue_disable_discard(rq);
+				blk_queue_disable_secure_erase(rq);
 			}
 			break;
 		case BLKIF_OP_FLUSH_DISKCACHE:
@@ -1615,7 +1629,6 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 					blkif_req(req)->error = BLK_STS_OK;
 				info->feature_fua = 0;
 				info->feature_flush = 0;
-				xlvbd_flush(info);
 			}
 			fallthrough;
 		case BLKIF_OP_READ:
@@ -1668,31 +1681,16 @@ static int setup_blkring(struct xenbus_device *dev,
 			 struct blkfront_ring_info *rinfo)
 {
 	struct blkif_sring *sring;
-	int err, i;
+	int err;
 	struct blkfront_info *info = rinfo->dev_info;
 	unsigned long ring_size = info->nr_ring_pages * XEN_PAGE_SIZE;
-	grant_ref_t gref[XENBUS_MAX_RING_GRANTS];
-
-	for (i = 0; i < info->nr_ring_pages; i++)
-		rinfo->ring_ref[i] = GRANT_INVALID_REF;
 
-	sring = (struct blkif_sring *)__get_free_pages(GFP_NOIO | __GFP_HIGH,
-						       get_order(ring_size));
-	if (!sring) {
-		xenbus_dev_fatal(dev, -ENOMEM, "allocating shared ring");
-		return -ENOMEM;
-	}
-	SHARED_RING_INIT(sring);
-	FRONT_RING_INIT(&rinfo->ring, sring, ring_size);
-
-	err = xenbus_grant_ring(dev, rinfo->ring.sring, info->nr_ring_pages, gref);
-	if (err < 0) {
-		free_pages((unsigned long)sring, get_order(ring_size));
-		rinfo->ring.sring = NULL;
+	err = xenbus_setup_ring(dev, GFP_NOIO, (void **)&sring,
+				info->nr_ring_pages, rinfo->ring_ref);
+	if (err)
 		goto fail;
-	}
-	for (i = 0; i < info->nr_ring_pages; i++)
-		rinfo->ring_ref[i] = gref[i];
+
+	XEN_FRONT_RING_INIT(&rinfo->ring, sring, ring_size);
 
 	err = xenbus_alloc_evtchn(dev, &rinfo->evtchn);
 	if (err)
@@ -1761,6 +1759,12 @@ abort_transaction:
 	return err;
 }
 
+/* Enable the persistent grants feature. */
+static bool feature_persistent = true;
+module_param(feature_persistent, bool, 0644);
+MODULE_PARM_DESC(feature_persistent,
+		"Enables the persistent grants feature");
+
 /* Common code used when first setting up, and when resuming. */
 static int talk_to_blkback(struct xenbus_device *dev,
 			   struct blkfront_info *info)
@@ -1775,6 +1779,10 @@ static int talk_to_blkback(struct xenbus_device *dev,
 	if (!info)
 		return -ENODEV;
 
+	/* Check if backend is trusted. */
+	info->bounce = !xen_blkif_trusted ||
+		       !xenbus_read_unsigned(dev->nodename, "trusted", 1);
+
 	max_page_order = xenbus_read_unsigned(info->xbdev->otherend,
 					      "max-ring-page-order", 0);
 	ring_page_order = min(xen_blkif_max_ring_order, max_page_order);
@@ -1848,8 +1856,9 @@ again:
 		message = "writing protocol";
 		goto abort_transaction;
 	}
+	info->feature_persistent_parm = feature_persistent;
 	err = xenbus_printf(xbt, dev->nodename, "feature-persistent", "%u",
-			info->feature_persistent);
+			info->feature_persistent_parm);
 	if (err)
 		dev_warn(&dev->dev,
 			 "writing persistent grants feature to xenbus");
@@ -1917,12 +1926,6 @@ static int negotiate_mq(struct blkfront_info *info)
 	return 0;
 }
 
-/* Enable the persistent grants feature. */
-static bool feature_persistent = true;
-module_param(feature_persistent, bool, 0644);
-MODULE_PARM_DESC(feature_persistent,
-		"Enables the persistent grants feature");
-
 /*
  * Entry point to this code when a new device is created.  Allocate the basic
  * structures and the ring buffer for communication with the backend, and
@@ -1989,8 +1992,6 @@ static int blkfront_probe(struct xenbus_device *dev,
 	info->vdevice = vdevice;
 	info->connected = BLKIF_STATE_DISCONNECTED;
 
-	info->feature_persistent = feature_persistent;
-
 	/* Front end dir is a number, which is used as the id. */
 	info->handle = simple_strtoul(strrchr(dev->nodename, '/')+1, NULL, 0);
 	dev_set_drvdata(&dev->dev, info);
@@ -2004,18 +2005,19 @@ static int blkfront_probe(struct xenbus_device *dev,
 
 static int blkif_recover(struct blkfront_info *info)
 {
+	struct queue_limits lim;
 	unsigned int r_index;
 	struct request *req, *n;
 	int rc;
 	struct bio *bio;
-	unsigned int segs;
 	struct blkfront_ring_info *rinfo;
 
+	lim = queue_limits_start_update(info->rq);
 	blkfront_gather_backend_features(info);
-	/* Reset limits changed by blk_mq_update_nr_hw_queues(). */
-	blkif_set_queue_limits(info);
-	segs = info->max_indirect_segments ? : BLKIF_MAX_SEGMENTS_PER_REQUEST;
-	blk_queue_max_segments(info->rq, segs / GRANTS_PER_PSEG);
+	blkif_set_queue_limits(info, &lim);
+	rc = queue_limits_commit_update(info->rq, &lim);
+	if (rc)
+		return rc;
 
 	for_each_rinfo(info, rinfo, r_index) {
 		rc = blkfront_setup_indirect(rinfo);
@@ -2035,7 +2037,9 @@ static int blkif_recover(struct blkfront_info *info)
 	list_for_each_entry_safe(req, n, &info->requests, queuelist) {
 		/* Requeue pending requests (flush or discard) */
 		list_del_init(&req->queuelist);
-		BUG_ON(req->nr_phys_segments > segs);
+		BUG_ON(req->nr_phys_segments >
+		       (info->max_indirect_segments ? :
+			BLKIF_MAX_SEGMENTS_PER_REQUEST));
 		blk_mq_requeue_request(req, false);
 	}
 	blk_mq_start_stopped_hw_queues(info->rq, true);
@@ -2125,9 +2129,10 @@ static void blkfront_closing(struct blkfront_info *info)
 		return;
 
 	/* No more blkif_request(). */
-	blk_mq_stop_hw_queues(info->rq);
-	blk_set_queue_dying(info->rq);
-	set_capacity(info->gd, 0);
+	if (info->rq && info->gd) {
+		blk_mq_stop_hw_queues(info->rq);
+		blk_mark_disk_dead(info->gd);
+	}
 
 	for_each_rinfo(info, rinfo, i) {
 		/* No more gnttab callback work. */
@@ -2182,17 +2187,18 @@ static int blkfront_setup_indirect(struct blkfront_ring_info *rinfo)
 	if (err)
 		goto out_of_memory;
 
-	if (!info->feature_persistent && info->max_indirect_segments) {
+	if (!info->bounce && info->max_indirect_segments) {
 		/*
-		 * We are using indirect descriptors but not persistent
-		 * grants, we need to allocate a set of pages that can be
+		 * We are using indirect descriptors but don't have a bounce
+		 * buffer, we need to allocate a set of pages that can be
 		 * used for mapping indirect grefs
 		 */
 		int num = INDIRECT_GREFS(grants) * BLK_RING_SIZE(info);
 
 		BUG_ON(!list_empty(&rinfo->indirect_pages));
 		for (i = 0; i < num; i++) {
-			struct page *indirect_page = alloc_page(GFP_KERNEL);
+			struct page *indirect_page = alloc_page(GFP_KERNEL |
+								__GFP_ZERO);
 			if (!indirect_page)
 				goto out_of_memory;
 			list_add(&indirect_page->lru, &rinfo->indirect_pages);
@@ -2281,10 +2287,12 @@ static void blkfront_gather_backend_features(struct blkfront_info *info)
 	if (xenbus_read_unsigned(info->xbdev->otherend, "feature-discard", 0))
 		blkfront_setup_discard(info);
 
-	if (info->feature_persistent)
+	if (info->feature_persistent_parm)
 		info->feature_persistent =
 			!!xenbus_read_unsigned(info->xbdev->otherend,
 					       "feature-persistent", 0);
+	if (info->feature_persistent)
+		info->bounce = true;
 
 	indirect_segments = xenbus_read_unsigned(info->xbdev->otherend,
 					"feature-max-indirect-segments", 0);
@@ -2308,8 +2316,6 @@ static void blkfront_gather_backend_features(struct blkfront_info *info)
 static void blkfront_connect(struct blkfront_info *info)
 {
 	unsigned long long sectors;
-	unsigned long sector_size;
-	unsigned int physical_sector_size;
 	int err, i;
 	struct blkfront_ring_info *rinfo;
 
@@ -2348,7 +2354,7 @@ static void blkfront_connect(struct blkfront_info *info)
 	err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
 			    "sectors", "%llu", &sectors,
 			    "info", "%u", &info->vdisk_info,
-			    "sector-size", "%lu", &sector_size,
+			    "sector-size", "%lu", &info->sector_size,
 			    NULL);
 	if (err) {
 		xenbus_dev_fatal(info->xbdev, err,
@@ -2362,9 +2368,9 @@ static void blkfront_connect(struct blkfront_info *info)
 	 * provide this. Assume physical sector size to be the same as
 	 * sector_size in that case.
 	 */
-	physical_sector_size = xenbus_read_unsigned(info->xbdev->otherend,
+	info->physical_sector_size = xenbus_read_unsigned(info->xbdev->otherend,
 						    "physical-sector-size",
-						    sector_size);
+						    info->sector_size);
 	blkfront_gather_backend_features(info);
 	for_each_rinfo(info, rinfo, i) {
 		err = blkfront_setup_indirect(rinfo);
@@ -2376,8 +2382,7 @@ static void blkfront_connect(struct blkfront_info *info)
 		}
 	}
 
-	err = xlvbd_alloc_gendisk(sectors, info, sector_size,
-				  physical_sector_size);
+	err = xlvbd_alloc_gendisk(sectors, info);
 	if (err) {
 		xenbus_dev_fatal(info->xbdev, err, "xlvbd_add at %s",
 				 info->xbdev->otherend);
@@ -2393,7 +2398,7 @@ static void blkfront_connect(struct blkfront_info *info)
 
 	err = device_add_disk(&info->xbdev->dev, info->gd, NULL);
 	if (err) {
-		blk_cleanup_disk(info->gd);
+		put_disk(info->gd);
 		blk_mq_free_tag_set(&info->tag_set);
 		info->rq = NULL;
 		goto fail;
@@ -2462,25 +2467,27 @@ static void blkback_changed(struct xenbus_device *dev,
 	}
 }
 
-static int blkfront_remove(struct xenbus_device *xbdev)
+static void blkfront_remove(struct xenbus_device *xbdev)
 {
 	struct blkfront_info *info = dev_get_drvdata(&xbdev->dev);
 
 	dev_dbg(&xbdev->dev, "%s removed", xbdev->nodename);
 
-	del_gendisk(info->gd);
+	if (info->gd)
+		del_gendisk(info->gd);
 
 	mutex_lock(&blkfront_mutex);
 	list_del(&info->info_list);
 	mutex_unlock(&blkfront_mutex);
 
 	blkif_free(info, 0);
-	xlbd_release_minors(info->gd->first_minor, info->gd->minors);
-	blk_cleanup_disk(info->gd);
-	blk_mq_free_tag_set(&info->tag_set);
+	if (info->gd) {
+		xlbd_release_minors(info->gd->first_minor, info->gd->minors);
+		put_disk(info->gd);
+		blk_mq_free_tag_set(&info->tag_set);
+	}
 
 	kfree(info);
-	return 0;
 }
 
 static int blkfront_is_ready(struct xenbus_device *dev)
@@ -2521,6 +2528,7 @@ static void purge_persistent_grants(struct blkfront_info *info)
 
 	for_each_rinfo(info, rinfo, i) {
 		struct grant *gnt_list_entry, *tmp;
+		LIST_HEAD(grants);
 
 		spin_lock_irqsave(&rinfo->ring_lock, flags);
 
@@ -2531,17 +2539,18 @@ static void purge_persistent_grants(struct blkfront_info *info)
 
 		list_for_each_entry_safe(gnt_list_entry, tmp, &rinfo->grants,
 					 node) {
-			if (gnt_list_entry->gref == GRANT_INVALID_REF ||
-			    gnttab_query_foreign_access(gnt_list_entry->gref))
+			if (gnt_list_entry->gref == INVALID_GRANT_REF ||
+			    !gnttab_try_end_foreign_access(gnt_list_entry->gref))
 				continue;
 
 			list_del(&gnt_list_entry->node);
-			gnttab_end_foreign_access(gnt_list_entry->gref, 0, 0UL);
 			rinfo->persistent_gnts_c--;
-			gnt_list_entry->gref = GRANT_INVALID_REF;
-			list_add_tail(&gnt_list_entry->node, &rinfo->grants);
+			gnt_list_entry->gref = INVALID_GRANT_REF;
+			list_add_tail(&gnt_list_entry->node, &grants);
 		}
 
+		list_splice_tail(&grants, &rinfo->grants);
+
 		spin_unlock_irqrestore(&rinfo->ring_lock, flags);
 	}
 }
@@ -2551,6 +2560,13 @@ static void blkfront_delay_work(struct work_struct *work)
 	struct blkfront_info *info;
 	bool need_schedule_work = false;
 
+	/*
+	 * Note that when using bounce buffers but not persistent grants
+	 * there's no need to run blkfront_delay_work because grants are
+	 * revoked in blkif_completion or else an error is reported and the
+	 * connection is closed.
+	 */
+
 	mutex_lock(&blkfront_mutex);
 
 	list_for_each_entry(info, &info_list, info_list) {