Merge branch 'for-6.11/block-limits' into for-6.11/block

Merge in last round of queue limits changes from Christoph.

* for-6.11/block-limits: (26 commits)
  block: move the bounce flag into the features field
  block: move the skip_tagset_quiesce flag to queue_limits
  block: move the pci_p2pdma flag to queue_limits
  block: move the zone_resetall flag to queue_limits
  block: move the zoned flag into the features field
  block: move the poll flag to queue_limits
  block: move the dax flag to queue_limits
  block: move the nowait flag to queue_limits
  block: move the synchronous flag to queue_limits
  block: move the stable_writes flag to queue_limits
  block: move the io_stat flag setting to queue_limits
  block: move the add_random flag to queue_limits
  block: move the nonrot flag to queue_limits
  block: move cache control settings out of queue->flags
  block: remove blk_flush_policy
  block: freeze the queue in queue_attr_store
  nbd: move setting the cache control flags to __nbd_set_size
  virtio_blk: remove virtblk_update_cache_mode
  loop: fold loop_update_rotational into loop_reconfigure_limits
  loop: also use the default block size from an underlying block device
  ...

Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 83 insertions, 36 deletions

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 83af6ac5aa48..bc8d17b7f29d 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -282,6 +282,67 @@ static inline bool blk_op_is_passthrough(blk_opf_t op)
 	return op == REQ_OP_DRV_IN || op == REQ_OP_DRV_OUT;
 }
 
+/* flags set by the driver in queue_limits.features */
+enum {
+	/* supports a volatile write cache */
+	BLK_FEAT_WRITE_CACHE			= (1u << 0),
+
+	/* supports passing on the FUA bit */
+	BLK_FEAT_FUA				= (1u << 1),
+
+	/* rotational device (hard drive or floppy) */
+	BLK_FEAT_ROTATIONAL			= (1u << 2),
+
+	/* contributes to the random number pool */
+	BLK_FEAT_ADD_RANDOM			= (1u << 3),
+
+	/* do disk/partitions IO accounting */
+	BLK_FEAT_IO_STAT			= (1u << 4),
+
+	/* don't modify data until writeback is done */
+	BLK_FEAT_STABLE_WRITES			= (1u << 5),
+
+	/* always completes in submit context */
+	BLK_FEAT_SYNCHRONOUS			= (1u << 6),
+
+	/* supports REQ_NOWAIT */
+	BLK_FEAT_NOWAIT				= (1u << 7),
+
+	/* supports DAX */
+	BLK_FEAT_DAX				= (1u << 8),
+
+	/* supports I/O polling */
+	BLK_FEAT_POLL				= (1u << 9),
+
+	/* is a zoned device */
+	BLK_FEAT_ZONED				= (1u << 10),
+
+	/* supports Zone Reset All */
+	BLK_FEAT_ZONE_RESETALL			= (1u << 11),
+
+	/* supports PCI(e) p2p requests */
+	BLK_FEAT_PCI_P2PDMA			= (1u << 12),
+
+	/* skip this queue in blk_mq_(un)quiesce_tagset */
+	BLK_FEAT_SKIP_TAGSET_QUIESCE		= (1u << 13),
+
+	/* bounce all highmem pages */
+	BLK_FEAT_BOUNCE_HIGH			= (1u << 14),
+};
+
+/*
+ * Flags automatically inherited when stacking limits.
+ */
+#define BLK_FEAT_INHERIT_MASK \
+	(BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA | BLK_FEAT_ROTATIONAL | \
+	 BLK_FEAT_STABLE_WRITES | BLK_FEAT_ZONED | BLK_FEAT_BOUNCE_HIGH)
+
+/* internal flags in queue_limits.flags */
+enum {
+	/* do not send FLUSH or FUA command despite advertised write cache */
+	BLK_FLAGS_WRITE_CACHE_DISABLED		= (1u << 31),
+};
+
 /*
  * BLK_BOUNCE_NONE:	never bounce (default)
  * BLK_BOUNCE_HIGH:	bounce all highmem pages
@@ -292,7 +353,8 @@ enum blk_bounce {
 };
 
 struct queue_limits {
-	enum blk_bounce		bounce;
+	unsigned int		features;
+	unsigned int		flags;
 	unsigned long		seg_boundary_mask;
 	unsigned long		virt_boundary_mask;
 
@@ -324,7 +386,6 @@ struct queue_limits {
 	unsigned char		misaligned;
 	unsigned char		discard_misaligned;
 	unsigned char		raid_partial_stripes_expensive;
-	bool			zoned;
 	unsigned int		max_open_zones;
 	unsigned int		max_active_zones;
 
@@ -529,34 +590,17 @@ struct request_queue {
 #define QUEUE_FLAG_NOMERGES     3	/* disable merge attempts */
 #define QUEUE_FLAG_SAME_COMP	4	/* complete on same CPU-group */
 #define QUEUE_FLAG_FAIL_IO	5	/* fake timeout */
-#define QUEUE_FLAG_NONROT	6	/* non-rotational device (SSD) */
-#define QUEUE_FLAG_VIRT		QUEUE_FLAG_NONROT /* paravirt device */
-#define QUEUE_FLAG_IO_STAT	7	/* do disk/partitions IO accounting */
 #define QUEUE_FLAG_NOXMERGES	9	/* No extended merges */
-#define QUEUE_FLAG_ADD_RANDOM	10	/* Contributes to random pool */
-#define QUEUE_FLAG_SYNCHRONOUS	11	/* always completes in submit context */
 #define QUEUE_FLAG_SAME_FORCE	12	/* force complete on same CPU */
-#define QUEUE_FLAG_HW_WC	13	/* Write back caching supported */
 #define QUEUE_FLAG_INIT_DONE	14	/* queue is initialized */
-#define QUEUE_FLAG_STABLE_WRITES 15	/* don't modify blks until WB is done */
-#define QUEUE_FLAG_POLL		16	/* IO polling enabled if set */
-#define QUEUE_FLAG_WC		17	/* Write back caching */
-#define QUEUE_FLAG_FUA		18	/* device supports FUA writes */
-#define QUEUE_FLAG_DAX		19	/* device supports DAX */
 #define QUEUE_FLAG_STATS	20	/* track IO start and completion times */
 #define QUEUE_FLAG_REGISTERED	22	/* queue has been registered to a disk */
 #define QUEUE_FLAG_QUIESCED	24	/* queue has been quiesced */
-#define QUEUE_FLAG_PCI_P2PDMA	25	/* device supports PCI p2p requests */
-#define QUEUE_FLAG_ZONE_RESETALL 26	/* supports Zone Reset All */
 #define QUEUE_FLAG_RQ_ALLOC_TIME 27	/* record rq->alloc_time_ns */
 #define QUEUE_FLAG_HCTX_ACTIVE	28	/* at least one blk-mq hctx is active */
-#define QUEUE_FLAG_NOWAIT       29	/* device supports NOWAIT */
 #define QUEUE_FLAG_SQ_SCHED     30	/* single queue style io dispatch */
-#define QUEUE_FLAG_SKIP_TAGSET_QUIESCE	31 /* quiesce_tagset skip the queue*/
 
-#define QUEUE_FLAG_MQ_DEFAULT	((1UL << QUEUE_FLAG_IO_STAT) |		\
-				 (1UL << QUEUE_FLAG_SAME_COMP) |	\
-				 (1UL << QUEUE_FLAG_NOWAIT))
+#define QUEUE_FLAG_MQ_DEFAULT	(1UL << QUEUE_FLAG_SAME_COMP)
 
 void blk_queue_flag_set(unsigned int flag, struct request_queue *q);
 void blk_queue_flag_clear(unsigned int flag, struct request_queue *q);
@@ -568,14 +612,12 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
 #define blk_queue_nomerges(q)	test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags)
 #define blk_queue_noxmerges(q)	\
 	test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags)
-#define blk_queue_nonrot(q)	test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags)
-#define blk_queue_io_stat(q)	test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags)
-#define blk_queue_add_random(q)	test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags)
+#define blk_queue_nonrot(q)	((q)->limits.features & BLK_FEAT_ROTATIONAL)
+#define blk_queue_io_stat(q)	((q)->limits.features & BLK_FEAT_IO_STAT)
 #define blk_queue_zone_resetall(q)	\
-	test_bit(QUEUE_FLAG_ZONE_RESETALL, &(q)->queue_flags)
-#define blk_queue_dax(q)	test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags)
-#define blk_queue_pci_p2pdma(q)	\
-	test_bit(QUEUE_FLAG_PCI_P2PDMA, &(q)->queue_flags)
+	((q)->limits.features & BLK_FEAT_ZONE_RESETALL)
+#define blk_queue_dax(q)	((q)->limits.features & BLK_FEAT_DAX)
+#define blk_queue_pci_p2pdma(q)	((q)->limits.features & BLK_FEAT_PCI_P2PDMA)
 #ifdef CONFIG_BLK_RQ_ALLOC_TIME
 #define blk_queue_rq_alloc_time(q)	\
 	test_bit(QUEUE_FLAG_RQ_ALLOC_TIME, &(q)->queue_flags)
@@ -591,7 +633,7 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
 #define blk_queue_registered(q)	test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags)
 #define blk_queue_sq_sched(q)	test_bit(QUEUE_FLAG_SQ_SCHED, &(q)->queue_flags)
 #define blk_queue_skip_tagset_quiesce(q) \
-	test_bit(QUEUE_FLAG_SKIP_TAGSET_QUIESCE, &(q)->queue_flags)
+	((q)->limits.features & BLK_FEAT_SKIP_TAGSET_QUIESCE)
 
 extern void blk_set_pm_only(struct request_queue *q);
 extern void blk_clear_pm_only(struct request_queue *q);
@@ -621,7 +663,8 @@ static inline enum rpm_status queue_rpm_status(struct request_queue *q)
 
 static inline bool blk_queue_is_zoned(struct request_queue *q)
 {
-	return IS_ENABLED(CONFIG_BLK_DEV_ZONED) && q->limits.zoned;
+	return IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
+		(q->limits.features & BLK_FEAT_ZONED);
 }
 
 #ifdef CONFIG_BLK_DEV_ZONED
@@ -950,7 +993,6 @@ void queue_limits_stack_bdev(struct queue_limits *t, struct block_device *bdev,
 		sector_t offset, const char *pfx);
 extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int);
 extern void blk_queue_rq_timeout(struct request_queue *, unsigned int);
-extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua);
 
 struct blk_independent_access_ranges *
 disk_alloc_independent_access_ranges(struct gendisk *disk, int nr_ia_ranges);
@@ -1289,8 +1331,7 @@ static inline bool bdev_nonrot(struct block_device *bdev)
 
 static inline bool bdev_synchronous(struct block_device *bdev)
 {
-	return test_bit(QUEUE_FLAG_SYNCHRONOUS,
-			&bdev_get_queue(bdev)->queue_flags);
+	return bdev->bd_disk->queue->limits.features & BLK_FEAT_SYNCHRONOUS;
 }
 
 static inline bool bdev_stable_writes(struct block_device *bdev)
@@ -1300,22 +1341,28 @@ static inline bool bdev_stable_writes(struct block_device *bdev)
 	if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) &&
 	    q->limits.integrity.csum_type != BLK_INTEGRITY_CSUM_NONE)
 		return true;
-	return test_bit(QUEUE_FLAG_STABLE_WRITES, &q->queue_flags);
+	return q->limits.features & BLK_FEAT_STABLE_WRITES;
+}
+
+static inline bool blk_queue_write_cache(struct request_queue *q)
+{
+	return (q->limits.features & BLK_FEAT_WRITE_CACHE) &&
+		!(q->limits.flags & BLK_FLAGS_WRITE_CACHE_DISABLED);
 }
 
 static inline bool bdev_write_cache(struct block_device *bdev)
 {
-	return test_bit(QUEUE_FLAG_WC, &bdev_get_queue(bdev)->queue_flags);
+	return blk_queue_write_cache(bdev_get_queue(bdev));
 }
 
 static inline bool bdev_fua(struct block_device *bdev)
 {
-	return test_bit(QUEUE_FLAG_FUA, &bdev_get_queue(bdev)->queue_flags);
+	return bdev_get_queue(bdev)->limits.features & BLK_FEAT_FUA;
 }
 
 static inline bool bdev_nowait(struct block_device *bdev)
 {
-	return test_bit(QUEUE_FLAG_NOWAIT, &bdev_get_queue(bdev)->queue_flags);
+	return bdev->bd_disk->queue->limits.features & BLK_FEAT_NOWAIT;
 }
 
 static inline bool bdev_is_zoned(struct block_device *bdev)