Merge tag 'for-6.11/block-20240722' of git://git.kernel.dk/linux

Pull more block updates from Jens Axboe:

 - MD fixes via Song:
     - md-cluster fixes (Heming Zhao)
     - raid1 fix (Mateusz Jończyk)

 - s390/dasd module description (Jeff)

 - Series cleaning up and hardening the blk-mq debugfs flag handling
   (John, Christoph)

 - blk-cgroup cleanup (Xiu)

 - Error polled IO attempts if backend doesn't support it (hexue)

 - Fix for an sbitmap hang (Yang)

* tag 'for-6.11/block-20240722' of git://git.kernel.dk/linux: (23 commits)
  blk-cgroup: move congestion_count to struct blkcg
  sbitmap: fix io hung due to race on sbitmap_word::cleared
  block: avoid polling configuration errors
  block: Catch possible entries missing from rqf_name[]
  block: Simplify definition of RQF_NAME()
  block: Use enum to define RQF_x bit indexes
  block: Catch possible entries missing from cmd_flag_name[]
  block: Catch possible entries missing from alloc_policy_name[]
  block: Catch possible entries missing from hctx_flag_name[]
  block: Catch possible entries missing from hctx_state_name[]
  block: Catch possible entries missing from blk_queue_flag_name[]
  block: Make QUEUE_FLAG_x as an enum
  block: Relocate BLK_MQ_MAX_DEPTH
  block: Relocate BLK_MQ_CPU_WORK_BATCH
  block: remove QUEUE_FLAG_STOPPED
  block: Add missing entry to hctx_flag_name[]
  block: Add zone write plugging entry to rqf_name[]
  block: Add missing entries from cmd_flag_name[]
  s390/dasd: fix error checks in dasd_copy_pair_store()
  s390/dasd: add missing MODULE_DESCRIPTION() macros
  ...

5 files changed, 100 insertions, 67 deletions

diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 89ba6b16fe8b..8d304b1d16b1 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -27,38 +27,61 @@ typedef enum rq_end_io_ret (rq_end_io_fn)(struct request *, blk_status_t);
  * request flags */
 typedef __u32 __bitwise req_flags_t;
 
-/* drive already may have started this one */
-#define RQF_STARTED		((__force req_flags_t)(1 << 1))
-/* request for flush sequence */
-#define RQF_FLUSH_SEQ		((__force req_flags_t)(1 << 4))
-/* merge of different types, fail separately */
-#define RQF_MIXED_MERGE		((__force req_flags_t)(1 << 5))
-/* don't call prep for this one */
-#define RQF_DONTPREP		((__force req_flags_t)(1 << 7))
-/* use hctx->sched_tags */
-#define RQF_SCHED_TAGS		((__force req_flags_t)(1 << 8))
-/* use an I/O scheduler for this request */
-#define RQF_USE_SCHED		((__force req_flags_t)(1 << 9))
-/* vaguely specified driver internal error.  Ignored by the block layer */
-#define RQF_FAILED		((__force req_flags_t)(1 << 10))
-/* don't warn about errors */
-#define RQF_QUIET		((__force req_flags_t)(1 << 11))
-/* account into disk and partition IO statistics */
-#define RQF_IO_STAT		((__force req_flags_t)(1 << 13))
-/* runtime pm request */
-#define RQF_PM			((__force req_flags_t)(1 << 15))
-/* on IO scheduler merge hash */
-#define RQF_HASHED		((__force req_flags_t)(1 << 16))
-/* track IO completion time */
-#define RQF_STATS		((__force req_flags_t)(1 << 17))
-/* Look at ->special_vec for the actual data payload instead of the
-   bio chain. */
-#define RQF_SPECIAL_PAYLOAD	((__force req_flags_t)(1 << 18))
-/* The request completion needs to be signaled to zone write pluging. */
-#define RQF_ZONE_WRITE_PLUGGING	((__force req_flags_t)(1 << 20))
-/* ->timeout has been called, don't expire again */
-#define RQF_TIMED_OUT		((__force req_flags_t)(1 << 21))
-#define RQF_RESV		((__force req_flags_t)(1 << 23))
+/* Keep rqf_name[] in sync with the definitions below */
+enum {
+	/* drive already may have started this one */
+	__RQF_STARTED,
+	/* request for flush sequence */
+	__RQF_FLUSH_SEQ,
+	/* merge of different types, fail separately */
+	__RQF_MIXED_MERGE,
+	/* don't call prep for this one */
+	__RQF_DONTPREP,
+	/* use hctx->sched_tags */
+	__RQF_SCHED_TAGS,
+	/* use an I/O scheduler for this request */
+	__RQF_USE_SCHED,
+	/* vaguely specified driver internal error.  Ignored by block layer */
+	__RQF_FAILED,
+	/* don't warn about errors */
+	__RQF_QUIET,
+	/* account into disk and partition IO statistics */
+	__RQF_IO_STAT,
+	/* runtime pm request */
+	__RQF_PM,
+	/* on IO scheduler merge hash */
+	__RQF_HASHED,
+	/* track IO completion time */
+	__RQF_STATS,
+	/* Look at ->special_vec for the actual data payload instead of the
+	   bio chain. */
+	__RQF_SPECIAL_PAYLOAD,
+	/* request completion needs to be signaled to zone write plugging. */
+	__RQF_ZONE_WRITE_PLUGGING,
+	/* ->timeout has been called, don't expire again */
+	__RQF_TIMED_OUT,
+	__RQF_RESV,
+	__RQF_BITS
+};
+
+#define RQF_STARTED		((__force req_flags_t)(1 << __RQF_STARTED))
+#define RQF_FLUSH_SEQ		((__force req_flags_t)(1 << __RQF_FLUSH_SEQ))
+#define RQF_MIXED_MERGE		((__force req_flags_t)(1 << __RQF_MIXED_MERGE))
+#define RQF_DONTPREP		((__force req_flags_t)(1 << __RQF_DONTPREP))
+#define RQF_SCHED_TAGS		((__force req_flags_t)(1 << __RQF_SCHED_TAGS))
+#define RQF_USE_SCHED		((__force req_flags_t)(1 << __RQF_USE_SCHED))
+#define RQF_FAILED		((__force req_flags_t)(1 << __RQF_FAILED))
+#define RQF_QUIET		((__force req_flags_t)(1 << __RQF_QUIET))
+#define RQF_IO_STAT		((__force req_flags_t)(1 << __RQF_IO_STAT))
+#define RQF_PM			((__force req_flags_t)(1 << __RQF_PM))
+#define RQF_HASHED		((__force req_flags_t)(1 << __RQF_HASHED))
+#define RQF_STATS		((__force req_flags_t)(1 << __RQF_STATS))
+#define RQF_SPECIAL_PAYLOAD	\
+			((__force req_flags_t)(1 << __RQF_SPECIAL_PAYLOAD))
+#define RQF_ZONE_WRITE_PLUGGING	\
+			((__force req_flags_t)(1 << __RQF_ZONE_WRITE_PLUGGING))
+#define RQF_TIMED_OUT		((__force req_flags_t)(1 << __RQF_TIMED_OUT))
+#define RQF_RESV		((__force req_flags_t)(1 << __RQF_RESV))
 
 /* flags that prevent us from merging requests: */
 #define RQF_NOMERGE_FLAGS \
@@ -278,8 +301,12 @@ enum blk_eh_timer_return {
 	BLK_EH_RESET_TIMER,
 };
 
-#define BLK_TAG_ALLOC_FIFO 0 /* allocate starting from 0 */
-#define BLK_TAG_ALLOC_RR 1 /* allocate starting from last allocated tag */
+/* Keep alloc_policy_name[] in sync with the definitions below */
+enum {
+	BLK_TAG_ALLOC_FIFO,	/* allocate starting from 0 */
+	BLK_TAG_ALLOC_RR,	/* allocate starting from last allocated tag */
+	BLK_TAG_ALLOC_MAX
+};
 
 /**
  * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware
@@ -644,6 +671,7 @@ struct blk_mq_ops {
 #endif
 };
 
+/* Keep hctx_flag_name[] in sync with the definitions below */
 enum {
 	BLK_MQ_F_SHOULD_MERGE	= 1 << 0,
 	BLK_MQ_F_TAG_QUEUE_SHARED = 1 << 1,
@@ -653,27 +681,17 @@ enum {
 	 */
 	BLK_MQ_F_STACKING	= 1 << 2,
 	BLK_MQ_F_TAG_HCTX_SHARED = 1 << 3,
-	BLK_MQ_F_BLOCKING	= 1 << 5,
+	BLK_MQ_F_BLOCKING	= 1 << 4,
 	/* Do not allow an I/O scheduler to be configured. */
-	BLK_MQ_F_NO_SCHED	= 1 << 6,
+	BLK_MQ_F_NO_SCHED	= 1 << 5,
+
 	/*
 	 * Select 'none' during queue registration in case of a single hwq
 	 * or shared hwqs instead of 'mq-deadline'.
 	 */
-	BLK_MQ_F_NO_SCHED_BY_DEFAULT	= 1 << 7,
-	BLK_MQ_F_ALLOC_POLICY_START_BIT = 8,
+	BLK_MQ_F_NO_SCHED_BY_DEFAULT	= 1 << 6,
+	BLK_MQ_F_ALLOC_POLICY_START_BIT = 7,
 	BLK_MQ_F_ALLOC_POLICY_BITS = 1,
-
-	BLK_MQ_S_STOPPED	= 0,
-	BLK_MQ_S_TAG_ACTIVE	= 1,
-	BLK_MQ_S_SCHED_RESTART	= 2,
-
-	/* hw queue is inactive after all its CPUs become offline */
-	BLK_MQ_S_INACTIVE	= 3,
-
-	BLK_MQ_MAX_DEPTH	= 10240,
-
-	BLK_MQ_CPU_WORK_BATCH	= 8,
 };
 #define BLK_MQ_FLAG_TO_ALLOC_POLICY(flags) \
 	((flags >> BLK_MQ_F_ALLOC_POLICY_START_BIT) & \
@@ -682,8 +700,19 @@ enum {
 	((policy & ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) \
 		<< BLK_MQ_F_ALLOC_POLICY_START_BIT)
 
+#define BLK_MQ_MAX_DEPTH	(10240)
 #define BLK_MQ_NO_HCTX_IDX	(-1U)
 
+enum {
+	/* Keep hctx_state_name[] in sync with the definitions below */
+	BLK_MQ_S_STOPPED,
+	BLK_MQ_S_TAG_ACTIVE,
+	BLK_MQ_S_SCHED_RESTART,
+	/* hw queue is inactive after all its CPUs become offline */
+	BLK_MQ_S_INACTIVE,
+	BLK_MQ_S_MAX
+};
+
 struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set,
 		struct queue_limits *lim, void *queuedata,
 		struct lock_class_key *lkclass);
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 632edd71f8c6..36ed96133217 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -354,6 +354,7 @@ enum req_op {
 	REQ_OP_LAST		= (__force blk_opf_t)36,
 };
 
+/* Keep cmd_flag_name[] in sync with the definitions below */
 enum req_flag_bits {
 	__REQ_FAILFAST_DEV =	/* no driver retries of device errors */
 		REQ_OP_BITS,
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index b8196e219ac2..e85ec73a07d5 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -588,27 +588,28 @@ struct request_queue {
 };
 
 /* Keep blk_queue_flag_name[] in sync with the definitions below */
-#define QUEUE_FLAG_STOPPED	0	/* queue is stopped */
-#define QUEUE_FLAG_DYING	1	/* queue being torn down */
-#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_NOXMERGES	9	/* No extended merges */
-#define QUEUE_FLAG_SAME_FORCE	12	/* force complete on same CPU */
-#define QUEUE_FLAG_INIT_DONE	14	/* queue is initialized */
-#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_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_SQ_SCHED     30	/* single queue style io dispatch */
+enum {
+	QUEUE_FLAG_DYING,		/* queue being torn down */
+	QUEUE_FLAG_NOMERGES,		/* disable merge attempts */
+	QUEUE_FLAG_SAME_COMP,		/* complete on same CPU-group */
+	QUEUE_FLAG_FAIL_IO,		/* fake timeout */
+	QUEUE_FLAG_NOXMERGES,		/* No extended merges */
+	QUEUE_FLAG_SAME_FORCE,		/* force complete on same CPU */
+	QUEUE_FLAG_INIT_DONE,		/* queue is initialized */
+	QUEUE_FLAG_STATS,		/* track IO start and completion times */
+	QUEUE_FLAG_REGISTERED,		/* queue has been registered to a disk */
+	QUEUE_FLAG_QUIESCED,		/* queue has been quiesced */
+	QUEUE_FLAG_RQ_ALLOC_TIME,	/* record rq->alloc_time_ns */
+	QUEUE_FLAG_HCTX_ACTIVE,		/* at least one blk-mq hctx is active */
+	QUEUE_FLAG_SQ_SCHED,		/* single queue style io dispatch */
+	QUEUE_FLAG_MAX
+};
 
 #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);
 
-#define blk_queue_stopped(q)	test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
 #define blk_queue_dying(q)	test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags)
 #define blk_queue_init_done(q)	test_bit(QUEUE_FLAG_INIT_DONE, &(q)->queue_flags)
 #define blk_queue_nomerges(q)	test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags)
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 293af7f8a694..ae04035b6cbe 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -539,9 +539,6 @@ struct cgroup {
 	/* used to store eBPF programs */
 	struct cgroup_bpf bpf;
 
-	/* If there is block congestion on this cgroup. */
-	atomic_t congestion_count;
-
 	/* Used to store internal freezer state */
 	struct cgroup_freezer_state freezer;
 
diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h
index d662cf136021..c09cdcc99471 100644
--- a/include/linux/sbitmap.h
+++ b/include/linux/sbitmap.h
@@ -36,6 +36,11 @@ struct sbitmap_word {
 	 * @cleared: word holding cleared bits
 	 */
 	unsigned long cleared ____cacheline_aligned_in_smp;
+
+	/**
+	 * @swap_lock: serializes simultaneous updates of ->word and ->cleared
+	 */
+	spinlock_t swap_lock;
 } ____cacheline_aligned_in_smp;
 
 /**