From c964d62f5cab7b43dd0534f22a96eab386c6ec5d Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Thu, 10 Nov 2022 10:44:57 -0800
Subject: [PATCH 3/5] block: make dma_alignment a stacking queue_limit
Git-commit: c964d62f5cab7b43dd0534f22a96eab386c6ec5d
Patch-mainline: v6.1-rc6
References: jsc#PED-2765

Device mappers had always been getting the default 511 dma mask, but
the underlying device might have a larger alignment requirement. Since
this value is used to determine alloweable direct-io alignment, this
needs to be a stackable limit.

(Coly Li: rebased for Linux v5.14 based SUSE kernel)

Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20221110184501.2451620-2-kbusch@meta.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Coly Li <colyli@suse.de>
---
 block/blk-core.c       |    1 -
 block/blk-settings.c   |    8 +++++---
 include/linux/blkdev.h |   10 ++++++++--
 3 files changed, 13 insertions(+), 6 deletions(-)

--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -487,7 +487,6 @@ struct request_queue *blk_alloc_queue(in
 				PERCPU_REF_INIT_ATOMIC, GFP_KERNEL))
 		goto fail_stats;
 
-	blk_queue_dma_alignment(q, 511);
 	blk_set_default_limits(&q->limits);
 	q->nr_requests = BLKDEV_DEFAULT_RQ;
 
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -57,6 +57,7 @@ void blk_set_default_limits(struct queue
 	lim->misaligned = 0;
 	lim->zoned = BLK_ZONED_NONE;
 	lim->zone_write_granularity = 0;
+	lim->dma_alignment = 511;
 }
 EXPORT_SYMBOL(blk_set_default_limits);
 
@@ -600,6 +601,7 @@ int blk_stack_limits(struct queue_limits
 
 	t->io_min = max(t->io_min, b->io_min);
 	t->io_opt = lcm_not_zero(t->io_opt, b->io_opt);
+	t->dma_alignment = max(t->dma_alignment, b->dma_alignment);
 
 	/* Set non-power-of-2 compatible chunk_sectors boundary */
 	if (b->chunk_sectors)
@@ -773,7 +775,7 @@ EXPORT_SYMBOL(blk_queue_virt_boundary);
  **/
 void blk_queue_dma_alignment(struct request_queue *q, int mask)
 {
-	q->dma_alignment = mask;
+	q->limits.dma_alignment = mask;
 }
 EXPORT_SYMBOL(blk_queue_dma_alignment);
 
@@ -795,8 +797,8 @@ void blk_queue_update_dma_alignment(stru
 {
 	BUG_ON(mask > PAGE_SIZE);
 
-	if (mask > q->dma_alignment)
-		q->dma_alignment = mask;
+	if (mask > q->limits.dma_alignment)
+		q->limits.dma_alignment = mask;
 }
 EXPORT_SYMBOL(blk_queue_update_dma_alignment);
 
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -278,6 +278,13 @@ struct queue_limits {
 	unsigned char		discard_misaligned;
 	unsigned char		raid_partial_stripes_expensive;
 	enum blk_zoned_model	zoned;
+
+	/*
+	 * Drivers that set dma_alignment to less than 511 must be prepared to
+	 * handle individual bvec's that are not a multiple of a SECTOR_SIZE
+	 * due to possible offsets.
+	 */
+	unsigned int		dma_alignment;
 };
 
 typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx,
@@ -424,7 +431,6 @@ struct request_queue {
 	unsigned long		nr_requests;	/* Max # of requests */
 
 	unsigned int		dma_pad_mask;
-	unsigned int		dma_alignment;
 
 #ifdef CONFIG_BLK_INLINE_ENCRYPTION
 	struct blk_crypto_profile *crypto_profile;
@@ -1369,7 +1375,7 @@ static inline unsigned int bdev_max_acti
 
 static inline int queue_dma_alignment(const struct request_queue *q)
 {
-	return q ? q->dma_alignment : 511;
+	return q ? q->limits.dma_alignment : 511;
 }
 
 static inline int blk_rq_aligned(struct request_queue *q, unsigned long addr,