Merge tag 'for-6.16/block-20250523' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - ublk updates:
      - Add support for updating the size of a ublk instance
      - Zero-copy improvements
      - Auto-registering of buffers for zero-copy
      - Series simplifying and improving GET_DATA and request lookup
      - Series adding quiesce support
      - Lots of selftests additions
      - Various cleanups

 - NVMe updates via Christoph:
      - add per-node DMA pools and use them for PRP/SGL allocations
        (Caleb Sander Mateos, Keith Busch)
      - nvme-fcloop refcounting fixes (Daniel Wagner)
      - support delayed removal of the multipath node and optionally
        support the multipath node for private namespaces (Nilay Shroff)
      - support shared CQs in the PCI endpoint target code (Wilfred
        Mallawa)
      - support admin-queue only authentication (Hannes Reinecke)
      - use the crc32c library instead of the crypto API (Eric Biggers)
      - misc cleanups (Christoph Hellwig, Marcelo Moreira, Hannes
        Reinecke, Leon Romanovsky, Gustavo A. R. Silva)

 - MD updates via Yu:
      - Fix that normal IO can be starved by sync IO, found by mkfs on
        newly created large raid5, with some clean up patches for bdev
        inflight counters

 - Clean up brd, getting rid of atomic kmaps and bvec poking

 - Add loop driver specifically for zoned IO testing

 - Eliminate blk-rq-qos calls with a static key, if not enabled

 - Improve hctx locking for when a plug has IO for multiple queues
   pending

 - Remove block layer bouncing support, which in turn means we can
   remove the per-node bounce stat as well

 - Improve blk-throttle support

 - Improve delay support for blk-throttle

 - Improve brd discard support

 - Unify IO scheduler switching. This should also fix a bunch of lockdep
   warnings we've been seeing, after enabling lockdep support for queue
   freezing/unfreezeing

 - Add support for block write streams via FDP (flexible data placement)
   on NVMe

 - Add a bunch of block helpers, facilitating the removal of a bunch of
   duplicated boilerplate code

 - Remove obsolete BLK_MQ pci and virtio Kconfig options

 - Add atomic/untorn write support to blktrace

 - Various little cleanups and fixes

* tag 'for-6.16/block-20250523' of git://git.kernel.dk/linux: (186 commits)
  selftests: ublk: add test for UBLK_F_QUIESCE
  ublk: add feature UBLK_F_QUIESCE
  selftests: ublk: add test case for UBLK_U_CMD_UPDATE_SIZE
  traceevent/block: Add REQ_ATOMIC flag to block trace events
  ublk: run auto buf unregisgering in same io_ring_ctx with registering
  io_uring: add helper io_uring_cmd_ctx_handle()
  ublk: remove io argument from ublk_auto_buf_reg_fallback()
  ublk: handle ublk_set_auto_buf_reg() failure correctly in ublk_fetch()
  selftests: ublk: add test for covering UBLK_AUTO_BUF_REG_FALLBACK
  selftests: ublk: support UBLK_F_AUTO_BUF_REG
  ublk: support UBLK_AUTO_BUF_REG_FALLBACK
  ublk: register buffer to local io_uring with provided buf index via UBLK_F_AUTO_BUF_REG
  ublk: prepare for supporting to register request buffer automatically
  ublk: convert to refcount_t
  selftests: ublk: make IO & device removal test more stressful
  nvme: rename nvme_mpath_shutdown_disk to nvme_mpath_remove_disk
  nvme: introduce multipath_always_on module param
  nvme-multipath: introduce delayed removal of the multipath head node
  nvme-pci: derive and better document max segments limits
  nvme-pci: use struct_size for allocation struct nvme_dev
  ...

3 files changed, 133 insertions, 1 deletions

diff --git a/include/uapi/linux/blktrace_api.h b/include/uapi/linux/blktrace_api.h
index 690621b610e5..1bfb635e309b 100644
--- a/include/uapi/linux/blktrace_api.h
+++ b/include/uapi/linux/blktrace_api.h
@@ -49,7 +49,7 @@ enum blktrace_act {
 	__BLK_TA_UNPLUG_TIMER,		/* queue was unplugged by timer */
 	__BLK_TA_INSERT,		/* insert request */
 	__BLK_TA_SPLIT,			/* bio was split */
-	__BLK_TA_BOUNCE,		/* bio was bounced */
+	__BLK_TA_BOUNCE,		/* unused, was: bio was bounced */
 	__BLK_TA_REMAP,			/* bio was remapped */
 	__BLK_TA_ABORT,			/* request aborted */
 	__BLK_TA_DRV_DATA,		/* driver-specific binary data */
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 8f1fc12bac46..50e372ea97c5 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -93,6 +93,10 @@ struct io_uring_sqe {
 			__u16	addr_len;
 			__u16	__pad3[1];
 		};
+		struct {
+			__u8	write_stream;
+			__u8	__pad4[3];
+		};
 	};
 	union {
 		struct {
diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h
index 583b86681c93..56c7e3fc666f 100644
--- a/include/uapi/linux/ublk_cmd.h
+++ b/include/uapi/linux/ublk_cmd.h
@@ -51,6 +51,10 @@
 	_IOR('u', 0x13, struct ublksrv_ctrl_cmd)
 #define UBLK_U_CMD_DEL_DEV_ASYNC	\
 	_IOR('u', 0x14, struct ublksrv_ctrl_cmd)
+#define UBLK_U_CMD_UPDATE_SIZE		\
+	_IOWR('u', 0x15, struct ublksrv_ctrl_cmd)
+#define UBLK_U_CMD_QUIESCE_DEV		\
+	_IOWR('u', 0x16, struct ublksrv_ctrl_cmd)
 
 /*
  * 64bits are enough now, and it should be easy to extend in case of
@@ -211,6 +215,63 @@
  */
 #define UBLK_F_USER_RECOVERY_FAIL_IO (1ULL << 9)
 
+/*
+ * Resizing a block device is possible with UBLK_U_CMD_UPDATE_SIZE
+ * New size is passed in cmd->data[0] and is in units of sectors
+ */
+#define UBLK_F_UPDATE_SIZE		 (1ULL << 10)
+
+/*
+ * request buffer is registered automatically to uring_cmd's io_uring
+ * context before delivering this io command to ublk server, meantime
+ * it is un-registered automatically when completing this io command.
+ *
+ * For using this feature:
+ *
+ * - ublk server has to create sparse buffer table on the same `io_ring_ctx`
+ *   for issuing `UBLK_IO_FETCH_REQ` and `UBLK_IO_COMMIT_AND_FETCH_REQ`.
+ *   If uring_cmd isn't issued on same `io_ring_ctx`, it is ublk server's
+ *   responsibility to unregister the buffer by issuing `IO_UNREGISTER_IO_BUF`
+ *   manually, otherwise this ublk request won't complete.
+ *
+ * - ublk server passes auto buf register data via uring_cmd's sqe->addr,
+ *   `struct ublk_auto_buf_reg` is populated from sqe->addr, please see
+ *   the definition of ublk_sqe_addr_to_auto_buf_reg()
+ *
+ * - pass buffer index from `ublk_auto_buf_reg.index`
+ *
+ * - all reserved fields in `ublk_auto_buf_reg` need to be zeroed
+ *
+ * - pass flags from `ublk_auto_buf_reg.flags` if needed
+ *
+ * This way avoids extra cost from two uring_cmd, but also simplifies backend
+ * implementation, such as, the dependency on IO_REGISTER_IO_BUF and
+ * IO_UNREGISTER_IO_BUF becomes not necessary.
+ *
+ * If wrong data or flags are provided, both IO_FETCH_REQ and
+ * IO_COMMIT_AND_FETCH_REQ are failed, for the latter, the ublk IO request
+ * won't be completed until new IO_COMMIT_AND_FETCH_REQ command is issued
+ * successfully
+ */
+#define UBLK_F_AUTO_BUF_REG 	(1ULL << 11)
+
+/*
+ * Control command `UBLK_U_CMD_QUIESCE_DEV` is added for quiescing device,
+ * which state can be transitioned to `UBLK_S_DEV_QUIESCED` or
+ * `UBLK_S_DEV_FAIL_IO` finally, and it needs ublk server cooperation for
+ * handling `UBLK_IO_RES_ABORT` correctly.
+ *
+ * Typical use case is for supporting to upgrade ublk server application,
+ * meantime keep ublk block device persistent during the period.
+ *
+ * This feature is only available when UBLK_F_USER_RECOVERY is enabled.
+ *
+ * Note, this command returns -EBUSY in case that all IO commands are being
+ * handled by ublk server and not completed in specified time period which
+ * is passed from the control command parameter.
+ */
+#define UBLK_F_QUIESCE		(1ULL << 12)
+
 /* device state */
 #define UBLK_S_DEV_DEAD	0
 #define UBLK_S_DEV_LIVE	1
@@ -297,6 +358,17 @@ struct ublksrv_ctrl_dev_info {
 #define		UBLK_IO_F_FUA			(1U << 13)
 #define		UBLK_IO_F_NOUNMAP		(1U << 15)
 #define		UBLK_IO_F_SWAP			(1U << 16)
+/*
+ * For UBLK_F_AUTO_BUF_REG & UBLK_AUTO_BUF_REG_FALLBACK only.
+ *
+ * This flag is set if auto buffer register is failed & ublk server passes
+ * UBLK_AUTO_BUF_REG_FALLBACK, and ublk server need to register buffer
+ * manually for handling the delivered IO command if this flag is observed
+ *
+ * ublk server has to check this flag if UBLK_AUTO_BUF_REG_FALLBACK is
+ * passed in.
+ */
+#define		UBLK_IO_F_NEED_REG_BUF		(1U << 17)
 
 /*
  * io cmd is described by this structure, and stored in share memory, indexed
@@ -331,6 +403,62 @@ static inline __u32 ublksrv_get_flags(const struct ublksrv_io_desc *iod)
 	return iod->op_flags >> 8;
 }
 
+/*
+ * If this flag is set, fallback by completing the uring_cmd and setting
+ * `UBLK_IO_F_NEED_REG_BUF` in case of auto-buf-register failure;
+ * otherwise the client ublk request is failed silently
+ *
+ * If ublk server passes this flag, it has to check if UBLK_IO_F_NEED_REG_BUF
+ * is set in `ublksrv_io_desc.op_flags`. If UBLK_IO_F_NEED_REG_BUF is set,
+ * ublk server needs to register io buffer manually for handling IO command.
+ */
+#define UBLK_AUTO_BUF_REG_FALLBACK 	(1 << 0)
+#define UBLK_AUTO_BUF_REG_F_MASK 	UBLK_AUTO_BUF_REG_FALLBACK
+
+struct ublk_auto_buf_reg {
+	/* index for registering the delivered request buffer */
+	__u16  index;
+	__u8   flags;
+	__u8   reserved0;
+
+	/*
+	 * io_ring FD can be passed via the reserve field in future for
+	 * supporting to register io buffer to external io_uring
+	 */
+	__u32  reserved1;
+};
+
+/*
+ * For UBLK_F_AUTO_BUF_REG, auto buffer register data is carried via
+ * uring_cmd's sqe->addr:
+ *
+ * 	- bit0 ~ bit15: buffer index
+ * 	- bit16 ~ bit23: flags
+ * 	- bit24 ~ bit31: reserved0
+ * 	- bit32 ~ bit63: reserved1
+ */
+static inline struct ublk_auto_buf_reg ublk_sqe_addr_to_auto_buf_reg(
+		__u64 sqe_addr)
+{
+	struct ublk_auto_buf_reg reg = {
+		.index = sqe_addr & 0xffff,
+		.flags = (sqe_addr >> 16) & 0xff,
+		.reserved0 = (sqe_addr >> 24) & 0xff,
+		.reserved1 = sqe_addr >> 32,
+	};
+
+	return reg;
+}
+
+static inline __u64
+ublk_auto_buf_reg_to_sqe_addr(const struct ublk_auto_buf_reg *buf)
+{
+	__u64 addr = buf->index | (__u64)buf->flags << 16 | (__u64)buf->reserved0 << 24 |
+		(__u64)buf->reserved1 << 32;
+
+	return addr;
+}
+
 /* issued to ublk driver via /dev/ublkcN */
 struct ublksrv_io_cmd {
 	__u16	q_id;