block: make dma_alignment a stacking queue_limit

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.

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>

diff --git a/block/blk-core.c b/block/blk-core.c
index 17667159482e0309d37c6784b7f3f8b4aac1a63c..5487912befe891610cbf2ac052260a05870310ce 100644 (file)
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -425,7 +425,6 @@ struct request_queue *blk_alloc_queue(int node_id, bool alloc_srcu)
                                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;
 

diff --git a/block/blk-settings.c b/block/blk-settings.c
index 8bb9eef5310eb040780ca42db0feb1655dc2db68..4949ed3ce7c9543f76dd93c5f049b15e96c7e3fd 100644 (file)
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -57,6 +57,7 @@ void blk_set_default_limits(struct queue_limits *lim)
        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, struct queue_limits *b,
 
        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(struct request_queue *q, int mask)
 {
        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);
 

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 50e358a19d98643b2bc927372cb2c46b6d4ca52c..9898e34b2c2d9022e6754f373b960d5feac48e8a 100644 (file)
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -311,6 +311,13 @@ 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,
@@ -456,12 +463,6 @@ struct request_queue {
        unsigned long           nr_requests;    /* Max # of requests */
 
        unsigned int            dma_pad_mask;
-       /*
-        * 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;
 
 #ifdef CONFIG_BLK_INLINE_ENCRYPTION
        struct blk_crypto_profile *crypto_profile;
@@ -1324,7 +1325,7 @@ static inline sector_t bdev_zone_sectors(struct block_device *bdev)
 
 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 unsigned int bdev_dma_alignment(struct block_device *bdev)