Merge tag 'for-7.2/block-20260615' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux

Pull block updates from Jens Axboe:

 - NVMe pull request via Keith:
     - Per-controller admin and IO timeout sysfs attributes, and
       letting the block layer set request timeouts (Maurizio,
       Maximilian)
     - Multipath passthrough iostats, and PCI P2PDMA enablement for
       multipath devices (Keith, Kiran)
     - A new diag sysfs attribute group exporting per-controller
       counters (retries, multipath failover, error counters, requeue
       and failure counts, reset and reconnect events) (Nilay)
     - FDP configuration validation and bounds check fixes (liuxixin)
     - Various nvmet fixes, including a pre-auth out-of-bounds read in
       the Discovery Get Log Page handler, auth payload bounds
       validation, and tcp error-path leak fixes (Bryam, Tianchu,
       Geliang)
     - nvme-tcp lockdep and workqueue fixes (Shin'ichiro, Kuniyuki,
       Eric)
     - Assorted other fixes and cleanups (John, Yao, Chao, Mateusz,
       Achkinazi, Wentao)

 - MD pull request via Yu Kuai:
     - raid1/raid10 fixes for a deadlock in the read error recovery
       path, error-path detection and bio accounting with cloned bios,
       and an nr_pending leak in the REQ_ATOMIC bad-block error path
       (Abd-Alrhman)
     - PCI P2PDMA propagation from member devices to the RAID device
       (Kiran)
     - dm-raid bio requeue fix, and various smaller fixes and cleanups
       (Benjamin, Chen, Li, Thorsten)

 - Enable Clang lock context analysis for the block layer, with the
   accompanying annotations across queue limits, the blk_holder_ops
   callbacks, crypto, cgroup, iocost, kyber and mq-deadline (Bart)

 - Block status code infrastructure work: a tagged status table, a
   str_to_blk_op() helper, a bio_endio_status() helper, and on top of
   that a new configurable block-layer error injection facility
   (Christoph)

 - DRBD netlink rework, replacing the genl_magic machinery with explicit
   netlink serialization and moving the DRBD UAPI headers to
   include/uapi/linux/ (Christoph Böhmwalder)

 - bvec improvements: a bvec_folio() helper and making the bvec_iter
   helpers proper inline functions (Willy, Christoph)

 - ublk cleanups and a canceling-flag fix for the disk-not-allocated
   case (Caleb, Ming)

 - Partition handling fixes: bound the AIX pp_count scan, fix an of_node
   refcount leak, and replace __get_free_page() with kmalloc() (Bryam,
   Wentao, Mike)

 - Convert numa_node to int in blk_mq_hw_ctx and ->init_request, and add
   WQ_PERCPU to the block workqueue users (Mateusz, Marco)

 - Block statistics and tracing: propagate in-flight to the whole disk
   on partition IO, export passthrough stats, and a new
   block_rq_tag_wait tracepoint (Tang, Keith, Aaron)

 - A round of removals, unexports and cleanups across bio, direct-io and
   the bvec helpers (Christoph)

 - Various driver fixes (mtip32xx use-after-free, rbd snap_count
   validation and strscpy conversion, nbd socket lockdep reclassify,
   virtio-blk zone report clamp, floppy) and a batch of MAINTAINERS
   email/list updates (Coly, Li, Yu, Christoph Böhmwalder)

 - Other little fixes and cleanups all over

* tag 'for-7.2/block-20260615' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux: (117 commits)
  MAINTAINERS: Update Coly Li's email address
  block: check bio split for unaligned bvec
  nbd: Reclassify sockets to avoid lockdep circular dependency
  block: add configurable error injection
  block: add a str_to_blk_op helper
  block: add a "tag" for block status codes
  block: add a macro to initialize the status table
  floppy: Drop unused pnp driver data
  block: propagate in_flight to whole disk on partition I/O
  virtio-blk: clamp zone report to the report buffer capacity
  block: optimize I/O merge hot path with unlikely() hints
  drivers/block/rbd: Use strscpy() to copy strings into arrays
  partitions: aix: bound the pp_count scan to the ppe array
  block: Enable lock context analysis
  block/mq-deadline: Make the lock context annotations compatible with Clang
  block/Kyber: Make the lock context annotations compatible with Clang
  block/blk-mq-debugfs: Improve lock context annotations
  block/blk-iocost: Inline iocg_lock() and iocg_unlock()
  block/blk-iocost: Split ioc_rqos_throttle()
  block/crypto: Annotate the crypto functions
  ...

13 files changed, 636 insertions, 1383 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index 8300d5565e36..8f33f717b14f 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -283,7 +283,7 @@ static inline void bio_first_folio(struct folio_iter *fi, struct bio *bio,
 		return;
 	}
 
-	fi->folio = page_folio(bvec->bv_page);
+	fi->folio = bvec_folio(bvec);
 	fi->offset = bvec->bv_offset +
 			PAGE_SIZE * folio_page_idx(fi->folio, bvec->bv_page);
 	fi->_seg_count = bvec->bv_len;
@@ -347,7 +347,6 @@ enum {
 };
 extern int bioset_init(struct bio_set *, unsigned int, unsigned int, int flags);
 extern void bioset_exit(struct bio_set *);
-extern int biovec_init_pool(mempool_t *pool, int pool_entries);
 
 struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs,
 			     blk_opf_t opf, gfp_t gfp, struct bio_set *bs);
@@ -371,17 +370,27 @@ void submit_bio(struct bio *bio);
 
 extern void bio_endio(struct bio *);
 
-static inline void bio_io_error(struct bio *bio)
+/**
+ * bio_endio_status - end I/O on a bio with a specific status
+ * @bio:	bio
+ * @status:	status to set
+ *
+ * Set @bio->bi_status to @status and call bio_endio().
+ **/
+static inline void bio_endio_status(struct bio *bio, blk_status_t status)
 {
-	bio->bi_status = BLK_STS_IOERR;
+	bio->bi_status = status;
 	bio_endio(bio);
 }
 
+static inline void bio_io_error(struct bio *bio)
+{
+	bio_endio_status(bio, BLK_STS_IOERR);
+}
+
 static inline void bio_wouldblock_error(struct bio *bio)
 {
-	bio_set_flag(bio, BIO_QUIET);
-	bio->bi_status = BLK_STS_AGAIN;
-	bio_endio(bio);
+	bio_endio_status(bio, BLK_STS_AGAIN);
 }
 
 /*
@@ -479,17 +488,10 @@ int bio_iov_iter_bounce(struct bio *bio, struct iov_iter *iter, size_t maxlen,
 		size_t minsize);
 void bio_iov_iter_unbounce(struct bio *bio, bool is_error, bool mark_dirty);
 
-extern void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter,
-			       struct bio *src, struct bvec_iter *src_iter);
 extern void bio_copy_data(struct bio *dst, struct bio *src);
 extern void bio_free_pages(struct bio *bio);
+void zero_fill_bio(struct bio *bio);
 void guard_bio_eod(struct bio *bio);
-void zero_fill_bio_iter(struct bio *bio, struct bvec_iter iter);
-
-static inline void zero_fill_bio(struct bio *bio)
-{
-	zero_fill_bio_iter(bio, bio->bi_iter);
-}
 
 static inline void bio_release_pages(struct bio *bio, bool mark_dirty)
 {
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 18a2388ba581..af878597afb8 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -428,7 +428,7 @@ struct blk_mq_hw_ctx {
 	struct blk_mq_tags	*sched_tags;
 
 	/** @numa_node: NUMA node the storage adapter has been connected to. */
-	unsigned int		numa_node;
+	int			numa_node;
 	/** @queue_num: Index of this hardware queue. */
 	unsigned int		queue_num;
 
@@ -653,7 +653,7 @@ struct blk_mq_ops {
 	 * flush request.
 	 */
 	int (*init_request)(struct blk_mq_tag_set *set, struct request *,
-			    unsigned int, unsigned int);
+			    unsigned int, int);
 	/**
 	 * @exit_request: Ditto for exit/teardown.
 	 */
@@ -1104,6 +1104,7 @@ struct req_iterator {
 /*
  * blk_rq_pos()			: the current sector
  * blk_rq_bytes()		: bytes left in the entire request
+ * blk_rq_has_data()		: whether the request carries data
  * blk_rq_cur_bytes()		: bytes left in the current segment
  * blk_rq_sectors()		: sectors left in the entire request
  * blk_rq_cur_sectors()		: sectors left in the current segment
@@ -1119,6 +1120,14 @@ static inline unsigned int blk_rq_bytes(const struct request *rq)
 	return rq->__data_len;
 }
 
+static inline bool blk_rq_has_data(const struct request *rq)
+{
+	return blk_rq_bytes(rq) &&
+	       req_op(rq) != REQ_OP_DISCARD &&
+	       req_op(rq) != REQ_OP_SECURE_ERASE &&
+	       req_op(rq) != REQ_OP_WRITE_ZEROES;
+}
+
 static inline int blk_rq_cur_bytes(const struct request *rq)
 {
 	if (!rq->bio)
@@ -1243,4 +1252,44 @@ static inline int blk_rq_map_sg(struct request *rq, struct scatterlist *sglist)
 }
 void blk_dump_rq_flags(struct request *, char *);
 
+/**
+ * blk_rq_passthrough_stats - check if this request should account stats
+ * @rq: request to check
+ * @q: the queue accumulating the stats
+ *
+ * Note, @q does not necessarily need to be the request_queue that provides
+ * @rq.
+ *
+ * Return: true if stats should be accounted.
+ */
+static inline bool blk_rq_passthrough_stats(struct request *rq,
+					    struct request_queue *q)
+{
+	struct bio *bio = rq->bio;
+
+	if (!blk_queue_passthrough_stat(q))
+		return false;
+
+	/* Requests without a bio do not transfer data. */
+	if (!bio)
+		return false;
+
+	/*
+	 * Stats are accumulated in the bdev, so must have one attached to a
+	 * bio to track stats. Most drivers do not set the bdev for passthrough
+	 * requests, but nvme is one that will set it.
+	 */
+	if (!bio->bi_bdev)
+		return false;
+
+	/*
+	 * We don't know what a passthrough command does, but we know the
+	 * payload size and data direction. Ensuring the size is aligned to the
+	 * block size filters out most commands with payloads that don't
+	 * represent sector access.
+	 */
+	if (blk_rq_bytes(rq) & (bdev_logical_block_size(bio->bi_bdev) - 1))
+		return false;
+	return true;
+}
 #endif /* BLK_MQ_H */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 890128cdea1c..5070851cf924 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -176,6 +176,7 @@ struct gendisk {
 #define GD_SUPPRESS_PART_SCAN		5
 #define GD_OWNS_QUEUE			6
 #define GD_ZONE_APPEND_USED		7
+#define GD_ERROR_INJECT			8
 
 	struct mutex open_mutex;	/* open/close mutex */
 	unsigned open_partitions;	/* number of open partitions */
@@ -227,6 +228,11 @@ struct gendisk {
 	 */
 	struct blk_independent_access_ranges *ia_ranges;
 
+#ifdef CONFIG_BLK_ERROR_INJECTION
+	struct mutex		error_injection_lock;
+	struct list_head	error_injection_list;
+#endif
+
 	struct mutex rqos_state_mutex;	/* rqos state change mutex */
 };
 
@@ -1040,7 +1046,6 @@ extern const char *blk_op_str(enum req_op op);
 
 int blk_status_to_errno(blk_status_t status);
 blk_status_t errno_to_blk_status(int errno);
-const char *blk_status_to_str(blk_status_t status);
 
 /* only poll the hardware once, don't continue until a completion was found */
 #define BLK_POLL_ONESHOT		(1 << 0)
@@ -1093,15 +1098,17 @@ static inline unsigned int blk_boundary_sectors_left(sector_t offset,
  */
 static inline struct queue_limits
 queue_limits_start_update(struct request_queue *q)
+	__acquires(&q->limits_lock)
 {
 	mutex_lock(&q->limits_lock);
 	return q->limits;
 }
 int queue_limits_commit_update_frozen(struct request_queue *q,
-		struct queue_limits *lim);
+		struct queue_limits *lim) __releases(&q->limits_lock);
 int queue_limits_commit_update(struct request_queue *q,
-		struct queue_limits *lim);
-int queue_limits_set(struct request_queue *q, struct queue_limits *lim);
+		struct queue_limits *lim) __releases(&q->limits_lock);
+int queue_limits_set(struct request_queue *q, struct queue_limits *lim)
+	__must_not_hold(&q->limits_lock);
 int blk_validate_limits(struct queue_limits *lim);
 
 /**
@@ -1113,6 +1120,7 @@ int blk_validate_limits(struct queue_limits *lim);
  * starting update.
  */
 static inline void queue_limits_cancel_update(struct request_queue *q)
+	__releases(&q->limits_lock)
 {
 	mutex_unlock(&q->limits_lock);
 }
@@ -1744,22 +1752,26 @@ void blkdev_show(struct seq_file *seqf, off_t offset);
 #endif
 
 struct blk_holder_ops {
-	void (*mark_dead)(struct block_device *bdev, bool surprise);
+	void (*mark_dead)(struct block_device *bdev, bool surprise)
+		__releases(&bdev->bd_holder_lock);
 
 	/*
 	 * Sync the file system mounted on the block device.
 	 */
-	void (*sync)(struct block_device *bdev);
+	void (*sync)(struct block_device *bdev)
+		__releases(&bdev->bd_holder_lock);
 
 	/*
 	 * Freeze the file system mounted on the block device.
 	 */
-	int (*freeze)(struct block_device *bdev);
+	int (*freeze)(struct block_device *bdev)
+		__releases(&bdev->bd_holder_lock);
 
 	/*
 	 * Thaw the file system mounted on the block device.
 	 */
-	int (*thaw)(struct block_device *bdev);
+	int (*thaw)(struct block_device *bdev)
+		__releases(&bdev->bd_holder_lock);
 };
 
 /*
diff --git a/include/linux/bvec.h b/include/linux/bvec.h
index d36dd476feda..92837e2743f1 100644
--- a/include/linux/bvec.h
+++ b/include/linux/bvec.h
@@ -74,6 +74,21 @@ static inline void bvec_set_virt(struct bio_vec *bv, void *vaddr,
 	bvec_set_page(bv, virt_to_page(vaddr), len, offset_in_page(vaddr));
 }
 
+/**
+ * bvec_folio - Return the first folio referenced by this bvec
+ * @bv: bvec to access
+ *
+ * A bvec can contain non-folio memory, so this should only be called by
+ * the creator of the bvec; drivers have no business looking at the owner
+ * of the memory.  It may not even be the right interface for the caller
+ * to use as a bvec can span multiple folios.  You may be better off using
+ * something like bio_for_each_folio_all() which iterates over all folios.
+ */
+static inline struct folio *bvec_folio(const struct bio_vec *bv)
+{
+	return page_folio(bv->bv_page);
+}
+
 struct bvec_iter {
 	/*
 	 * Current device address in 512 byte sectors. Only updated by the bio
@@ -104,51 +119,78 @@ struct bvec_iter_all {
 	unsigned	done;
 };
 
-/*
- * various member access, note that bio_data should of course not be used
- * on highmem page vectors
- */
-#define __bvec_iter_bvec(bvec, iter)	(&(bvec)[(iter).bi_idx])
+static __always_inline const struct bio_vec *
+__bvec_iter_bvec(const struct bio_vec *bvecs, const struct bvec_iter iter)
+{
+	return bvecs + iter.bi_idx;
+}
 
 /* multi-page (mp_bvec) helpers */
-#define mp_bvec_iter_page(bvec, iter)				\
-	(__bvec_iter_bvec((bvec), (iter))->bv_page)
+static __always_inline struct page *
+mp_bvec_iter_page(const struct bio_vec *bvecs, const struct bvec_iter iter)
+{
+	return __bvec_iter_bvec(bvecs, iter)->bv_page;
+}
 
-#define mp_bvec_iter_len(bvec, iter)				\
-	min((iter).bi_size,					\
-	    __bvec_iter_bvec((bvec), (iter))->bv_len - (iter).bi_bvec_done)
+static __always_inline unsigned int
+mp_bvec_iter_len(const struct bio_vec *bvecs, const struct bvec_iter iter)
+{
+	return min(__bvec_iter_bvec(bvecs, iter)->bv_len - iter.bi_bvec_done,
+			iter.bi_size);
+}
 
-#define mp_bvec_iter_offset(bvec, iter)				\
-	(__bvec_iter_bvec((bvec), (iter))->bv_offset + (iter).bi_bvec_done)
+static __always_inline unsigned int
+mp_bvec_iter_offset(const struct bio_vec *bvecs, const struct bvec_iter iter)
+{
+	return __bvec_iter_bvec(bvecs, iter)->bv_offset + iter.bi_bvec_done;
+}
 
-#define mp_bvec_iter_page_idx(bvec, iter)			\
-	(mp_bvec_iter_offset((bvec), (iter)) / PAGE_SIZE)
+static __always_inline unsigned int
+mp_bvec_iter_page_idx(const struct bio_vec *bvecs, const struct bvec_iter iter)
+{
+	return mp_bvec_iter_offset(bvecs, iter) / PAGE_SIZE;
+}
 
-#define mp_bvec_iter_bvec(bvec, iter)				\
-((struct bio_vec) {						\
-	.bv_page	= mp_bvec_iter_page((bvec), (iter)),	\
-	.bv_len		= mp_bvec_iter_len((bvec), (iter)),	\
-	.bv_offset	= mp_bvec_iter_offset((bvec), (iter)),	\
-})
+static __always_inline struct bio_vec
+mp_bvec_iter_bvec(const struct bio_vec *bvecs, const struct bvec_iter iter)
+{
+	return (struct bio_vec) {
+		.bv_page	= mp_bvec_iter_page(bvecs, iter),
+		.bv_len		= mp_bvec_iter_len(bvecs, iter),
+		.bv_offset	= mp_bvec_iter_offset(bvecs, iter),
+	};
+}
 
 /* For building single-page bvec in flight */
- #define bvec_iter_offset(bvec, iter)				\
-	(mp_bvec_iter_offset((bvec), (iter)) % PAGE_SIZE)
+static __always_inline unsigned int
+bvec_iter_offset(const struct bio_vec *bvecs, const struct bvec_iter iter)
+{
+	return mp_bvec_iter_offset(bvecs, iter) % PAGE_SIZE;
+}
 
-#define bvec_iter_len(bvec, iter)				\
-	min_t(unsigned, mp_bvec_iter_len((bvec), (iter)),		\
-	      PAGE_SIZE - bvec_iter_offset((bvec), (iter)))
+static __always_inline unsigned int
+bvec_iter_len(const struct bio_vec *bvecs, const struct bvec_iter iter)
+{
+	return min(mp_bvec_iter_len(bvecs, iter),
+			PAGE_SIZE - bvec_iter_offset(bvecs, iter));
+}
 
-#define bvec_iter_page(bvec, iter)				\
-	(mp_bvec_iter_page((bvec), (iter)) +			\
-	 mp_bvec_iter_page_idx((bvec), (iter)))
+static __always_inline struct page *
+bvec_iter_page(const struct bio_vec *bvecs, const struct bvec_iter iter)
+{
+	return mp_bvec_iter_page(bvecs, iter) +
+		mp_bvec_iter_page_idx(bvecs, iter);
+}
 
-#define bvec_iter_bvec(bvec, iter)				\
-((struct bio_vec) {						\
-	.bv_page	= bvec_iter_page((bvec), (iter)),	\
-	.bv_len		= bvec_iter_len((bvec), (iter)),	\
-	.bv_offset	= bvec_iter_offset((bvec), (iter)),	\
-})
+static __always_inline struct bio_vec
+bvec_iter_bvec(const struct bio_vec *bvecs, const struct bvec_iter iter)
+{
+	return (struct bio_vec) {
+		.bv_page	= bvec_iter_page(bvecs, iter),
+		.bv_len		= bvec_iter_len(bvecs, iter),
+		.bv_offset	= bvec_iter_offset(bvecs, iter),
+	};
+}
 
 static inline bool bvec_iter_advance(const struct bio_vec *bv,
 		struct bvec_iter *iter, unsigned bytes)
@@ -247,6 +289,7 @@ static inline void *bvec_kmap_local(struct bio_vec *bvec)
 
 /**
  * memcpy_from_bvec - copy data from a bvec
+ * @to: Kernel virtual address to copy to.
  * @bvec: bvec to copy from
  *
  * Must be called on single-page bvecs only.
@@ -259,6 +302,7 @@ static inline void memcpy_from_bvec(char *to, struct bio_vec *bvec)
 /**
  * memcpy_to_bvec - copy data to a bvec
  * @bvec: bvec to copy to
+ * @from: Kernel virtual address to copy from.
  *
  * Must be called on single-page bvecs only.
  */
diff --git a/include/linux/drbd_config.h b/include/linux/drbd_config.h
deleted file mode 100644
index d215365c6bb1..000000000000
--- a/include/linux/drbd_config.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * drbd_config.h
- * DRBD's compile time configuration.
- */
-
-#ifndef DRBD_CONFIG_H
-#define DRBD_CONFIG_H
-
-extern const char *drbd_buildtag(void);
-
-#define REL_VERSION "8.4.11"
-#define PRO_VERSION_MIN 86
-#define PRO_VERSION_MAX 101
-
-#endif
diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
deleted file mode 100644
index f53c534aba0c..000000000000
--- a/include/linux/drbd_genl.h
+++ /dev/null
@@ -1,536 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * General overview:
- * full generic netlink message:
- * |nlmsghdr|genlmsghdr|<payload>
- *
- * payload:
- * |optional fixed size family header|<sequence of netlink attributes>
- *
- * sequence of netlink attributes:
- * I chose to have all "top level" attributes NLA_NESTED,
- * corresponding to some real struct.
- * So we have a sequence of |tla, len|<nested nla sequence>
- *
- * nested nla sequence:
- * may be empty, or contain a sequence of netlink attributes
- * representing the struct fields.
- *
- * The tag number of any field (regardless of containing struct)
- * will be available as T_ ## field_name,
- * so you cannot have the same field name in two differnt structs.
- *
- * The tag numbers themselves are per struct, though,
- * so should always begin at 1 (not 0, that is the special "NLA_UNSPEC" type,
- * which we won't use here).
- * The tag numbers are used as index in the respective nla_policy array.
- *
- * GENL_struct(tag_name, tag_number, struct name, struct fields) - struct and policy
- *	genl_magic_struct.h
- *		generates the struct declaration,
- *		generates an entry in the tla enum,
- *	genl_magic_func.h
- *		generates an entry in the static tla policy
- *		with .type = NLA_NESTED
- *		generates the static <struct_name>_nl_policy definition,
- *		and static conversion functions
- *
- *	genl_magic_func.h
- *
- * GENL_mc_group(group)
- *	genl_magic_struct.h
- *		does nothing
- *	genl_magic_func.h
- *		defines and registers the mcast group,
- *		and provides a send helper
- *
- * GENL_notification(op_name, op_num, mcast_group, tla list)
- *	These are notifications to userspace.
- *
- *	genl_magic_struct.h
- *		generates an entry in the genl_ops enum,
- *	genl_magic_func.h
- *		does nothing
- *
- *	mcast group: the name of the mcast group this notification should be
- *	expected on
- *	tla list: the list of expected top level attributes,
- *	for documentation and sanity checking.
- *
- * GENL_op(op_name, op_num, flags and handler, tla list) - "genl operations"
- *	These are requests from userspace.
- *
- *	_op and _notification share the same "number space",
- *	op_nr will be assigned to "genlmsghdr->cmd"
- *
- *	genl_magic_struct.h
- *		generates an entry in the genl_ops enum,
- *	genl_magic_func.h
- *		generates an entry in the static genl_ops array,
- *		and static register/unregister functions to
- *		genl_register_family().
- *
- *	flags and handler:
- *		GENL_op_init( .doit = x, .dumpit = y, .flags = something)
- *		GENL_doit(x) => .dumpit = NULL, .flags = GENL_ADMIN_PERM
- *	tla list: the list of expected top level attributes,
- *	for documentation and sanity checking.
- */
-
-/*
- * STRUCTS
- */
-
-/* this is sent kernel -> userland on various error conditions, and contains
- * informational textual info, which is supposedly human readable.
- * The computer relevant return code is in the drbd_genlmsghdr.
- */
-GENL_struct(DRBD_NLA_CFG_REPLY, 1, drbd_cfg_reply,
-		/* "arbitrary" size strings, nla_policy.len = 0 */
-	__str_field(1, 0,	info_text, 0)
-)
-
-/* Configuration requests typically need a context to operate on.
- * Possible keys are device minor (fits in the drbd_genlmsghdr),
- * the replication link (aka connection) name,
- * and/or the replication group (aka resource) name,
- * and the volume id within the resource. */
-GENL_struct(DRBD_NLA_CFG_CONTEXT, 2, drbd_cfg_context,
-	__u32_field(1, 0,	ctx_volume)
-	__str_field(2, 0,	ctx_resource_name, 128)
-	__bin_field(3, 0,	ctx_my_addr, 128)
-	__bin_field(4, 0,	ctx_peer_addr, 128)
-)
-
-GENL_struct(DRBD_NLA_DISK_CONF, 3, disk_conf,
-	__str_field(1, DRBD_F_REQUIRED | DRBD_F_INVARIANT,	backing_dev,	128)
-	__str_field(2, DRBD_F_REQUIRED | DRBD_F_INVARIANT,	meta_dev,	128)
-	__s32_field(3, DRBD_F_REQUIRED | DRBD_F_INVARIANT,	meta_dev_idx)
-
-	/* use the resize command to try and change the disk_size */
-	__u64_field(4, DRBD_F_INVARIANT,	disk_size)
-	/* we could change the max_bio_bvecs,
-	 * but it won't propagate through the stack */
-	__u32_field(5, DRBD_F_INVARIANT,	max_bio_bvecs)
-
-	__u32_field_def(6, 0,	on_io_error, DRBD_ON_IO_ERROR_DEF)
-	__u32_field_def(7, 0,	fencing, DRBD_FENCING_DEF)
-
-	__u32_field_def(8,	0,	resync_rate, DRBD_RESYNC_RATE_DEF)
-	__s32_field_def(9,	0,	resync_after, DRBD_MINOR_NUMBER_DEF)
-	__u32_field_def(10,	0,	al_extents, DRBD_AL_EXTENTS_DEF)
-	__u32_field_def(11,	0,	c_plan_ahead, DRBD_C_PLAN_AHEAD_DEF)
-	__u32_field_def(12,	0,	c_delay_target, DRBD_C_DELAY_TARGET_DEF)
-	__u32_field_def(13,	0,	c_fill_target, DRBD_C_FILL_TARGET_DEF)
-	__u32_field_def(14,	0,	c_max_rate, DRBD_C_MAX_RATE_DEF)
-	__u32_field_def(15,	0,	c_min_rate, DRBD_C_MIN_RATE_DEF)
-	__u32_field_def(20,     0, disk_timeout, DRBD_DISK_TIMEOUT_DEF)
-	__u32_field_def(21,     0 /* OPTIONAL */,       read_balancing, DRBD_READ_BALANCING_DEF)
-	__u32_field_def(25,     0 /* OPTIONAL */,       rs_discard_granularity, DRBD_RS_DISCARD_GRANULARITY_DEF)
-
-	__flg_field_def(16, 0,	disk_barrier, DRBD_DISK_BARRIER_DEF)
-	__flg_field_def(17, 0,	disk_flushes, DRBD_DISK_FLUSHES_DEF)
-	__flg_field_def(18, 0,	disk_drain, DRBD_DISK_DRAIN_DEF)
-	__flg_field_def(19, 0,	md_flushes, DRBD_MD_FLUSHES_DEF)
-	__flg_field_def(23,     0 /* OPTIONAL */,	al_updates, DRBD_AL_UPDATES_DEF)
-	__flg_field_def(24,     0 /* OPTIONAL */,	discard_zeroes_if_aligned, DRBD_DISCARD_ZEROES_IF_ALIGNED_DEF)
-	__flg_field_def(26,     0 /* OPTIONAL */,	disable_write_same, DRBD_DISABLE_WRITE_SAME_DEF)
-)
-
-GENL_struct(DRBD_NLA_RESOURCE_OPTS, 4, res_opts,
-	__str_field_def(1,	0,	cpu_mask,       DRBD_CPU_MASK_SIZE)
-	__u32_field_def(2,	0,	on_no_data, DRBD_ON_NO_DATA_DEF)
-)
-
-GENL_struct(DRBD_NLA_NET_CONF, 5, net_conf,
-	__str_field_def(1,	DRBD_F_SENSITIVE,
-						shared_secret,	SHARED_SECRET_MAX)
-	__str_field_def(2,	0,	cram_hmac_alg,	SHARED_SECRET_MAX)
-	__str_field_def(3,	0,	integrity_alg,	SHARED_SECRET_MAX)
-	__str_field_def(4,	0,	verify_alg,     SHARED_SECRET_MAX)
-	__str_field_def(5,	0,	csums_alg,	SHARED_SECRET_MAX)
-	__u32_field_def(6,	0,	wire_protocol, DRBD_PROTOCOL_DEF)
-	__u32_field_def(7,	0,	connect_int, DRBD_CONNECT_INT_DEF)
-	__u32_field_def(8,	0,	timeout, DRBD_TIMEOUT_DEF)
-	__u32_field_def(9,	0,	ping_int, DRBD_PING_INT_DEF)
-	__u32_field_def(10,	0,	ping_timeo, DRBD_PING_TIMEO_DEF)
-	__u32_field_def(11,	0,	sndbuf_size, DRBD_SNDBUF_SIZE_DEF)
-	__u32_field_def(12,	0,	rcvbuf_size, DRBD_RCVBUF_SIZE_DEF)
-	__u32_field_def(13,	0,	ko_count, DRBD_KO_COUNT_DEF)
-	__u32_field_def(14,	0,	max_buffers, DRBD_MAX_BUFFERS_DEF)
-	__u32_field_def(15,	0,	max_epoch_size, DRBD_MAX_EPOCH_SIZE_DEF)
-	__u32_field_def(16,	0,	unplug_watermark, DRBD_UNPLUG_WATERMARK_DEF)
-	__u32_field_def(17,	0,	after_sb_0p, DRBD_AFTER_SB_0P_DEF)
-	__u32_field_def(18,	0,	after_sb_1p, DRBD_AFTER_SB_1P_DEF)
-	__u32_field_def(19,	0,	after_sb_2p, DRBD_AFTER_SB_2P_DEF)
-	__u32_field_def(20,	0,	rr_conflict, DRBD_RR_CONFLICT_DEF)
-	__u32_field_def(21,	0,	on_congestion, DRBD_ON_CONGESTION_DEF)
-	__u32_field_def(22,	0,	cong_fill, DRBD_CONG_FILL_DEF)
-	__u32_field_def(23,	0,	cong_extents, DRBD_CONG_EXTENTS_DEF)
-	__flg_field_def(24, 0,	two_primaries, DRBD_ALLOW_TWO_PRIMARIES_DEF)
-	__flg_field(25, DRBD_F_INVARIANT,	discard_my_data)
-	__flg_field_def(26, 0,	tcp_cork, DRBD_TCP_CORK_DEF)
-	__flg_field_def(27, 0,	always_asbp, DRBD_ALWAYS_ASBP_DEF)
-	__flg_field(28, DRBD_F_INVARIANT,	tentative)
-	__flg_field_def(29,	0,	use_rle, DRBD_USE_RLE_DEF)
-	/* 9: __u32_field_def(30,	0,	fencing_policy, DRBD_FENCING_DEF) */
-	/* 9: __str_field_def(31,     0, name, SHARED_SECRET_MAX) */
-	/* 9: __u32_field(32,         DRBD_F_REQUIRED | DRBD_F_INVARIANT,     peer_node_id) */
-	__flg_field_def(33, 0 /* OPTIONAL */,	csums_after_crash_only, DRBD_CSUMS_AFTER_CRASH_ONLY_DEF)
-	__u32_field_def(34, 0 /* OPTIONAL */, sock_check_timeo, DRBD_SOCKET_CHECK_TIMEO_DEF)
-)
-
-GENL_struct(DRBD_NLA_SET_ROLE_PARMS, 6, set_role_parms,
-	__flg_field(1, 0,	assume_uptodate)
-)
-
-GENL_struct(DRBD_NLA_RESIZE_PARMS, 7, resize_parms,
-	__u64_field(1, 0,	resize_size)
-	__flg_field(2, 0,	resize_force)
-	__flg_field(3, 0,	no_resync)
-	__u32_field_def(4, 0 /* OPTIONAL */, al_stripes, DRBD_AL_STRIPES_DEF)
-	__u32_field_def(5, 0 /* OPTIONAL */, al_stripe_size, DRBD_AL_STRIPE_SIZE_DEF)
-)
-
-GENL_struct(DRBD_NLA_STATE_INFO, 8, state_info,
-	/* the reason of the broadcast,
-	 * if this is an event triggered broadcast. */
-	__u32_field(1, 0,	sib_reason)
-	__u32_field(2, DRBD_F_REQUIRED,	current_state)
-	__u64_field(3, 0,	capacity)
-	__u64_field(4, 0,	ed_uuid)
-
-	/* These are for broadcast from after state change work.
-	 * prev_state and new_state are from the moment the state change took
-	 * place, new_state is not neccessarily the same as current_state,
-	 * there may have been more state changes since.  Which will be
-	 * broadcasted soon, in their respective after state change work.  */
-	__u32_field(5, 0,	prev_state)
-	__u32_field(6, 0,	new_state)
-
-	/* if we have a local disk: */
-	__bin_field(7, 0,	uuids, (UI_SIZE*sizeof(__u64)))
-	__u32_field(8, 0,	disk_flags)
-	__u64_field(9, 0,	bits_total)
-	__u64_field(10, 0,	bits_oos)
-	/* and in case resync or online verify is active */
-	__u64_field(11, 0,	bits_rs_total)
-	__u64_field(12, 0,	bits_rs_failed)
-
-	/* for pre and post notifications of helper execution */
-	__str_field(13, 0,	helper, 32)
-	__u32_field(14, 0,	helper_exit_code)
-
-	__u64_field(15,                      0, send_cnt)
-	__u64_field(16,                      0, recv_cnt)
-	__u64_field(17,                      0, read_cnt)
-	__u64_field(18,                      0, writ_cnt)
-	__u64_field(19,                      0, al_writ_cnt)
-	__u64_field(20,                      0, bm_writ_cnt)
-	__u32_field(21,                      0, ap_bio_cnt)
-	__u32_field(22,                      0, ap_pending_cnt)
-	__u32_field(23,                      0, rs_pending_cnt)
-)
-
-GENL_struct(DRBD_NLA_START_OV_PARMS, 9, start_ov_parms,
-	__u64_field(1, 0,	ov_start_sector)
-	__u64_field(2, 0,	ov_stop_sector)
-)
-
-GENL_struct(DRBD_NLA_NEW_C_UUID_PARMS, 10, new_c_uuid_parms,
-	__flg_field(1, 0, clear_bm)
-)
-
-GENL_struct(DRBD_NLA_TIMEOUT_PARMS, 11, timeout_parms,
-	__u32_field(1,	DRBD_F_REQUIRED,	timeout_type)
-)
-
-GENL_struct(DRBD_NLA_DISCONNECT_PARMS, 12, disconnect_parms,
-	__flg_field(1, 0,	force_disconnect)
-)
-
-GENL_struct(DRBD_NLA_DETACH_PARMS, 13, detach_parms,
-	__flg_field(1, 0,	force_detach)
-)
-
-GENL_struct(DRBD_NLA_RESOURCE_INFO, 15, resource_info,
-	__u32_field(1, 0, res_role)
-	__flg_field(2, 0, res_susp)
-	__flg_field(3, 0, res_susp_nod)
-	__flg_field(4, 0, res_susp_fen)
-	/* __flg_field(5, 0, res_weak) */
-)
-
-GENL_struct(DRBD_NLA_DEVICE_INFO, 16, device_info,
-	__u32_field(1, 0, dev_disk_state)
-)
-
-GENL_struct(DRBD_NLA_CONNECTION_INFO, 17, connection_info,
-	__u32_field(1, 0, conn_connection_state)
-	__u32_field(2, 0, conn_role)
-)
-
-GENL_struct(DRBD_NLA_PEER_DEVICE_INFO, 18, peer_device_info,
-	__u32_field(1, 0, peer_repl_state)
-	__u32_field(2, 0, peer_disk_state)
-	__u32_field(3, 0, peer_resync_susp_user)
-	__u32_field(4, 0, peer_resync_susp_peer)
-	__u32_field(5, 0, peer_resync_susp_dependency)
-)
-
-GENL_struct(DRBD_NLA_RESOURCE_STATISTICS, 19, resource_statistics,
-	__u32_field(1, 0, res_stat_write_ordering)
-)
-
-GENL_struct(DRBD_NLA_DEVICE_STATISTICS, 20, device_statistics,
-	__u64_field(1, 0, dev_size)  /* (sectors) */
-	__u64_field(2, 0, dev_read)  /* (sectors) */
-	__u64_field(3, 0, dev_write)  /* (sectors) */
-	__u64_field(4, 0, dev_al_writes)  /* activity log writes (count) */
-	__u64_field(5, 0, dev_bm_writes)  /*  bitmap writes  (count) */
-	__u32_field(6, 0, dev_upper_pending)  /* application requests in progress */
-	__u32_field(7, 0, dev_lower_pending)  /* backing device requests in progress */
-	__flg_field(8, 0, dev_upper_blocked)
-	__flg_field(9, 0, dev_lower_blocked)
-	__flg_field(10, 0, dev_al_suspended)  /* activity log suspended */
-	__u64_field(11, 0, dev_exposed_data_uuid)
-	__u64_field(12, 0, dev_current_uuid)
-	__u32_field(13, 0, dev_disk_flags)
-	__bin_field(14, 0, history_uuids, HISTORY_UUIDS * sizeof(__u64))
-)
-
-GENL_struct(DRBD_NLA_CONNECTION_STATISTICS, 21, connection_statistics,
-	__flg_field(1, 0, conn_congested)
-)
-
-GENL_struct(DRBD_NLA_PEER_DEVICE_STATISTICS, 22, peer_device_statistics,
-	__u64_field(1, 0, peer_dev_received)  /* sectors */
-	__u64_field(2, 0, peer_dev_sent)  /* sectors */
-	__u32_field(3, 0, peer_dev_pending)  /* number of requests */
-	__u32_field(4, 0, peer_dev_unacked)  /* number of requests */
-	__u64_field(5, 0, peer_dev_out_of_sync)  /* sectors */
-	__u64_field(6, 0, peer_dev_resync_failed)  /* sectors */
-	__u64_field(7, 0, peer_dev_bitmap_uuid)
-	__u32_field(9, 0, peer_dev_flags)
-)
-
-GENL_struct(DRBD_NLA_NOTIFICATION_HEADER, 23, drbd_notification_header,
-	__u32_field(1, 0, nh_type)
-)
-
-GENL_struct(DRBD_NLA_HELPER, 24, drbd_helper_info,
-	__str_field(1, 0, helper_name, 32)
-	__u32_field(2, 0, helper_status)
-)
-
-/*
- * Notifications and commands (genlmsghdr->cmd)
- */
-GENL_mc_group(events)
-
-	/* kernel -> userspace announcement of changes */
-GENL_notification(
-	DRBD_EVENT, 1, events,
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)
-	GENL_tla_expected(DRBD_NLA_STATE_INFO, DRBD_F_REQUIRED)
-	GENL_tla_expected(DRBD_NLA_NET_CONF, 0)
-	GENL_tla_expected(DRBD_NLA_DISK_CONF, 0)
-	GENL_tla_expected(DRBD_NLA_SYNCER_CONF, 0)
-)
-
-	/* query kernel for specific or all info */
-GENL_op(
-	DRBD_ADM_GET_STATUS, 2,
-	GENL_op_init(
-		.doit = drbd_adm_get_status,
-		.dumpit = drbd_adm_get_status_all,
-		/* anyone may ask for the status,
-		 * it is broadcasted anyways */
-	),
-	/* To select the object .doit.
-	 * Or a subset of objects in .dumpit. */
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, 0)
-)
-
-	/* add DRBD minor devices as volumes to resources */
-GENL_op(DRBD_ADM_NEW_MINOR, 5, GENL_doit(drbd_adm_new_minor),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
-GENL_op(DRBD_ADM_DEL_MINOR, 6, GENL_doit(drbd_adm_del_minor),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
-
-	/* add or delete resources */
-GENL_op(DRBD_ADM_NEW_RESOURCE, 7, GENL_doit(drbd_adm_new_resource),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
-GENL_op(DRBD_ADM_DEL_RESOURCE, 8, GENL_doit(drbd_adm_del_resource),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
-
-GENL_op(DRBD_ADM_RESOURCE_OPTS, 9,
-	GENL_doit(drbd_adm_resource_opts),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)
-	GENL_tla_expected(DRBD_NLA_RESOURCE_OPTS, 0)
-)
-
-GENL_op(
-	DRBD_ADM_CONNECT, 10,
-	GENL_doit(drbd_adm_connect),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)
-	GENL_tla_expected(DRBD_NLA_NET_CONF, DRBD_F_REQUIRED)
-)
-
-GENL_op(
-	DRBD_ADM_CHG_NET_OPTS, 29,
-	GENL_doit(drbd_adm_net_opts),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)
-	GENL_tla_expected(DRBD_NLA_NET_CONF, DRBD_F_REQUIRED)
-)
-
-GENL_op(DRBD_ADM_DISCONNECT, 11, GENL_doit(drbd_adm_disconnect),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
-
-GENL_op(DRBD_ADM_ATTACH, 12,