Merge tag 'for-6.12/block-20240913' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - MD changes via Song:
      - md-bitmap refactoring (Yu Kuai)
      - raid5 performance optimization (Artur Paszkiewicz)
      - Other small fixes (Yu Kuai, Chen Ni)
      - Add a sysfs entry 'new_level' (Xiao Ni)
      - Improve information reported in /proc/mdstat (Mateusz Kusiak)

 - NVMe changes via Keith:
      - Asynchronous namespace scanning (Stuart)
      - TCP TLS updates (Hannes)
      - RDMA queue controller validation (Niklas)
      - Align field names to the spec (Anuj)
      - Metadata support validation (Puranjay)
      - A syntax cleanup (Shen)
      - Fix a Kconfig linking error (Arnd)
      - New queue-depth quirk (Keith)

 - Add missing unplug trace event (Keith)

 - blk-iocost fixes (Colin, Konstantin)

 - t10-pi modular removal and fixes (Alexey)

 - Fix for potential BLKSECDISCARD overflow (Alexey)

 - bio splitting cleanups and fixes (Christoph)

 - Deal with folios rather than rather than pages, speeding up how the
   block layer handles bigger IOs (Kundan)

 - Use spinlocks rather than bit spinlocks in zram (Sebastian, Mike)

 - Reduce zoned device overhead in ublk (Ming)

 - Add and use sendpages_ok() for drbd and nvme-tcp (Ofir)

 - Fix regression in partition error pointer checking (Riyan)

 - Add support for write zeroes and rotational status in nbd (Wouter)

 - Add Yu Kuai as new BFQ maintainer. The scheduler has been
   unmaintained for quite a while.

 - Various sets of fixes for BFQ (Yu Kuai)

 - Misc fixes and cleanups (Alvaro, Christophe, Li, Md Haris, Mikhail,
   Yang)

* tag 'for-6.12/block-20240913' of git://git.kernel.dk/linux: (120 commits)
  nvme-pci: qdepth 1 quirk
  block: fix potential invalid pointer dereference in blk_add_partition
  blk_iocost: make read-only static array vrate_adj_pct const
  block: unpin user pages belonging to a folio at once
  mm: release number of pages of a folio
  block: introduce folio awareness and add a bigger size from folio
  block: Added folio-ized version of bio_add_hw_page()
  block, bfq: factor out a helper to split bfqq in bfq_init_rq()
  block, bfq: remove local variable 'bfqq_already_existing' in bfq_init_rq()
  block, bfq: remove local variable 'split' in bfq_init_rq()
  block, bfq: remove bfq_log_bfqg()
  block, bfq: merge bfq_release_process_ref() into bfq_put_cooperator()
  block, bfq: fix procress reference leakage for bfqq in merge chain
  block, bfq: fix uaf for accessing waker_bfqq after splitting
  blk-throttle: support prioritized processing of metadata
  blk-throttle: remove last_low_overflow_time
  drbd: Add NULL check for net_conf to prevent dereference in state validation
  nvme-tcp: fix link failure for TCP auth
  blk-mq: add missing unplug trace event
  mtip32xx: Remove redundant null pointer checks in mtip_hw_debugfs_init()
  ...

8 files changed, 44 insertions, 11 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index a46e2047bea4..faceadb040f9 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -324,8 +324,8 @@ static inline void bio_next_folio(struct folio_iter *fi, struct bio *bio)
 void bio_trim(struct bio *bio, sector_t offset, sector_t size);
 extern struct bio *bio_split(struct bio *bio, int sectors,
 			     gfp_t gfp, struct bio_set *bs);
-struct bio *bio_split_rw(struct bio *bio, const struct queue_limits *lim,
-		unsigned *segs, struct bio_set *bs, unsigned max_bytes);
+int bio_split_rw_at(struct bio *bio, const struct queue_limits *lim,
+		unsigned *segs, unsigned max_bytes);
 
 /**
  * bio_next_split - get next @sectors from a bio, splitting if necessary
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index b7664d593486..643c9020a35a 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1187,7 +1187,8 @@ static inline unsigned int queue_max_segment_size(const struct request_queue *q)
 	return q->limits.max_segment_size;
 }
 
-static inline unsigned int queue_limits_max_zone_append_sectors(struct queue_limits *l)
+static inline unsigned int
+queue_limits_max_zone_append_sectors(const struct queue_limits *l)
 {
 	unsigned int max_sectors = min(l->chunk_sectors, l->max_hw_sectors);
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 3065972c94ba..3066af38e94e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1605,6 +1605,7 @@ void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages,
 void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages,
 				      bool make_dirty);
 void unpin_user_pages(struct page **pages, unsigned long npages);
+void unpin_user_folio(struct folio *folio, unsigned long npages);
 void unpin_folios(struct folio **folios, unsigned long nfolios);
 
 static inline bool is_cow_mapping(vm_flags_t flags)
diff --git a/include/linux/net.h b/include/linux/net.h
index 688320b79fcc..b75bc534c1b3 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -322,6 +322,25 @@ static inline bool sendpage_ok(struct page *page)
 	return !PageSlab(page) && page_count(page) >= 1;
 }
 
+/*
+ * Check sendpage_ok on contiguous pages.
+ */
+static inline bool sendpages_ok(struct page *page, size_t len, size_t offset)
+{
+	struct page *p = page + (offset >> PAGE_SHIFT);
+	size_t count = 0;
+
+	while (count < len) {
+		if (!sendpage_ok(p))
+			return false;
+
+		p++;
+		count += PAGE_SIZE;
+	}
+
+	return true;
+}
+
 int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec,
 		   size_t num, size_t len);
 int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg,
diff --git a/include/linux/nvme-keyring.h b/include/linux/nvme-keyring.h
index e10333d78dbb..19d2b256180f 100644
--- a/include/linux/nvme-keyring.h
+++ b/include/linux/nvme-keyring.h
@@ -12,7 +12,7 @@ key_serial_t nvme_tls_psk_default(struct key *keyring,
 		const char *hostnqn, const char *subnqn);
 
 key_serial_t nvme_keyring_id(void);
-
+struct key *nvme_tls_key_lookup(key_serial_t key_id);
 #else
 
 static inline key_serial_t nvme_tls_psk_default(struct key *keyring,
@@ -24,5 +24,9 @@ static inline key_serial_t nvme_keyring_id(void)
 {
 	return 0;
 }
+static inline struct key *nvme_tls_key_lookup(key_serial_t key_id)
+{
+	return ERR_PTR(-ENOTSUPP);
+}
 #endif /* !CONFIG_NVME_KEYRING */
 #endif /* _NVME_KEYRING_H */
diff --git a/include/linux/nvme-rdma.h b/include/linux/nvme-rdma.h
index eb2f04d636c8..97c5f00b9aa3 100644
--- a/include/linux/nvme-rdma.h
+++ b/include/linux/nvme-rdma.h
@@ -25,6 +25,7 @@ enum nvme_rdma_cm_status {
 	NVME_RDMA_CM_NO_RSC		= 0x06,
 	NVME_RDMA_CM_INVALID_IRD	= 0x07,
 	NVME_RDMA_CM_INVALID_ORD	= 0x08,
+	NVME_RDMA_CM_INVALID_CNTLID	= 0x09,
 };
 
 static inline const char *nvme_rdma_cm_msg(enum nvme_rdma_cm_status status)
@@ -46,6 +47,8 @@ static inline const char *nvme_rdma_cm_msg(enum nvme_rdma_cm_status status)
 		return "invalid IRD";
 	case NVME_RDMA_CM_INVALID_ORD:
 		return "Invalid ORD";
+	case NVME_RDMA_CM_INVALID_CNTLID:
+		return "invalid controller ID";
 	default:
 		return "unrecognized reason";
 	}
@@ -64,7 +67,8 @@ struct nvme_rdma_cm_req {
 	__le16		qid;
 	__le16		hrqsize;
 	__le16		hsqsize;
-	u8		rsvd[24];
+	__le16		cntlid;
+	u8		rsvd[22];
 };
 
 /**
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 7b2ae2e43544..b58d9405d65e 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -987,8 +987,8 @@ struct nvme_rw_command {
 	__le16			control;
 	__le32			dsmgmt;
 	__le32			reftag;
-	__le16			apptag;
-	__le16			appmask;
+	__le16			lbat;
+	__le16			lbatm;
 };
 
 enum {
@@ -1057,8 +1057,8 @@ struct nvme_write_zeroes_cmd {
 	__le16			control;
 	__le32			dsmgmt;
 	__le32			reftag;
-	__le16			apptag;
-	__le16			appmask;
+	__le16			lbat;
+	__le16			lbatm;
 };
 
 enum nvme_zone_mgmt_action {
diff --git a/include/uapi/linux/nbd.h b/include/uapi/linux/nbd.h
index 80ce0ef43afd..f1d468acfb25 100644
--- a/include/uapi/linux/nbd.h
+++ b/include/uapi/linux/nbd.h
@@ -42,8 +42,9 @@ enum {
 	NBD_CMD_WRITE = 1,
 	NBD_CMD_DISC = 2,
 	NBD_CMD_FLUSH = 3,
-	NBD_CMD_TRIM = 4
+	NBD_CMD_TRIM = 4,
 	/* userspace defines additional extension commands */
+	NBD_CMD_WRITE_ZEROES = 6,
 };
 
 /* values for flags field, these are server interaction specific. */
@@ -51,12 +52,15 @@ enum {
 #define NBD_FLAG_READ_ONLY	(1 << 1) /* device is read-only */
 #define NBD_FLAG_SEND_FLUSH	(1 << 2) /* can flush writeback cache */
 #define NBD_FLAG_SEND_FUA	(1 << 3) /* send FUA (forced unit access) */
-/* there is a gap here to match userspace */
+#define NBD_FLAG_ROTATIONAL	(1 << 4) /* device is rotational */
 #define NBD_FLAG_SEND_TRIM	(1 << 5) /* send trim/discard */
+#define NBD_FLAG_SEND_WRITE_ZEROES (1 << 6) /* supports WRITE_ZEROES */
+/* there is a gap here to match userspace */
 #define NBD_FLAG_CAN_MULTI_CONN	(1 << 8)	/* Server supports multiple connections per export. */
 
 /* values for cmd flags in the upper 16 bits of request type */
 #define NBD_CMD_FLAG_FUA	(1 << 16) /* FUA (forced unit access) op */
+#define NBD_CMD_FLAG_NO_HOLE	(1 << 17) /* Do not punch a hole for WRITE_ZEROES */
 
 /* These are client behavior specific flags. */
 #define NBD_CFLAG_DESTROY_ON_DISCONNECT	(1 << 0) /* delete the nbd device on