Commit 0abcfd89 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge tag 'for-6.19/io_uring-20251201' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux 

Pull io_uring updates from Jens Axboe:

 - Unify how task_work cancelations are detected, placing it in the
   task_work running state rather than needing to check the task state

 - Series cleaning up and moving the cancelation code to where it
   belongs, in cancel.c

 - Cleanup of waitid and futex argument handling

 - Add support for mixed sized SQEs. 6.18 added support for mixed sized
   CQEs, improving flexibility and efficiency of workloads that need big
   CQEs. This adds similar support for SQEs, where the occasional need
   for a 128b SQE doesn't necessitate having all SQEs be 128b in size

 - Introduce zcrx and SQ/CQ layout queries. The former returns what zcrx
   features are available. And both return the ring size information to
   help with allocation size calculation for user provided rings like
   IORING_SETUP_NO_MMAP and IORING_MEM_REGION_TYPE_USER

 - Zcrx updates for 6.19. It includes a bunch of small patches,
   IORING_REGISTER_ZCRX_CTRL and RQ flushing and David's work on sharing
   zcrx b/w multiple io_uring instances

 - Series cleaning up ring initializations, notable deduplicating ring
   size and offset calculations. It also moves most of the checking
   before doing any allocations, making the code simpler

 - Add support for getsockname and getpeername, which is mostly a
   trivial hookup after a bit of refactoring on the networking side

 - Various fixes and cleanups

* tag 'for-6.19/io_uring-20251201' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux: (68 commits)
  io_uring: Introduce getsockname io_uring cmd
  socket: Split out a getsockname helper for io_uring
  socket: Unify getsockname and getpeername implementation
  io_uring/query: drop unused io_handle_query_entry() ctx arg
  io_uring/kbuf: remove obsolete buf_nr_pages and update comments
  io_uring/register: use correct location for io_rings_layout
  io_uring/zcrx: share an ifq between rings
  io_uring/zcrx: add io_fill_zcrx_offsets()
  io_uring/zcrx: export zcrx via a file
  io_uring/zcrx: move io_zcrx_scrub() and dependencies up
  io_uring/zcrx: count zcrx users
  io_uring/zcrx: add sync refill queue flushing
  io_uring/zcrx: introduce IORING_REGISTER_ZCRX_CTRL
  io_uring/zcrx: elide passing msg flags
  io_uring/zcrx: use folio_nr_pages() instead of shift operation
  io_uring/zcrx: convert to use netmem_desc
  io_uring/query: introduce rings info query
  io_uring/query: introduce zcrx query
  io_uring: move cq/sq user offset init around
  io_uring: pre-calculate scq layout
  ...
parents 8f7aa3d3 5d24321e

block/ioctl.c

+4 −2
Original line number Diff line number Diff line
@@ -769,14 +769,16 @@ struct blk_iou_cmd { 
	bool nowait;

};



static void blk_cmd_complete(struct io_uring_cmd *cmd, unsigned int issue_flags)

static void blk_cmd_complete(struct io_tw_req tw_req, io_tw_token_t tw)

{

	struct io_uring_cmd *cmd = io_uring_cmd_from_tw(tw_req);

	struct blk_iou_cmd *bic = io_uring_cmd_to_pdu(cmd, struct blk_iou_cmd);



	if (bic->res == -EAGAIN && bic->nowait)

		io_uring_cmd_issue_blocking(cmd);

	else

		io_uring_cmd_done(cmd, bic->res, issue_flags);

		io_uring_cmd_done(cmd, bic->res,

				  IO_URING_CMD_TASK_WORK_ISSUE_FLAGS);

}



static void bio_cmd_bio_end_io(struct bio *bio)

drivers/block/ublk_drv.c

+11 −11
Original line number Diff line number Diff line
@@ -1302,10 +1302,9 @@ static bool ublk_start_io(const struct ublk_queue *ubq, struct request *req, 
	return true;

}



static void ublk_dispatch_req(struct ublk_queue *ubq,

			      struct request *req,

			      unsigned int issue_flags)

static void ublk_dispatch_req(struct ublk_queue *ubq, struct request *req)

{

	unsigned int issue_flags = IO_URING_CMD_TASK_WORK_ISSUE_FLAGS;

	int tag = req->tag;

	struct ublk_io *io = &ubq->ios[tag];
@@ -1348,13 +1347,13 @@ static void ublk_dispatch_req(struct ublk_queue *ubq, 
		ublk_complete_io_cmd(io, req, UBLK_IO_RES_OK, issue_flags);

}



static void ublk_cmd_tw_cb(struct io_uring_cmd *cmd,

			   unsigned int issue_flags)

static void ublk_cmd_tw_cb(struct io_tw_req tw_req, io_tw_token_t tw)

{

	struct io_uring_cmd *cmd = io_uring_cmd_from_tw(tw_req);

	struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd);

	struct ublk_queue *ubq = pdu->ubq;



	ublk_dispatch_req(ubq, pdu->req, issue_flags);

	ublk_dispatch_req(ubq, pdu->req);

}



static void ublk_queue_cmd(struct ublk_queue *ubq, struct request *rq)
@@ -1366,9 +1365,9 @@ static void ublk_queue_cmd(struct ublk_queue *ubq, struct request *rq) 
	io_uring_cmd_complete_in_task(cmd, ublk_cmd_tw_cb);

}



static void ublk_cmd_list_tw_cb(struct io_uring_cmd *cmd,

		unsigned int issue_flags)

static void ublk_cmd_list_tw_cb(struct io_tw_req tw_req, io_tw_token_t tw)

{

	struct io_uring_cmd *cmd = io_uring_cmd_from_tw(tw_req);

	struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd);

	struct request *rq = pdu->req_list;

	struct request *next;
@@ -1376,7 +1375,7 @@ static void ublk_cmd_list_tw_cb(struct io_uring_cmd *cmd, 
	do {

		next = rq->rq_next;

		rq->rq_next = NULL;

		ublk_dispatch_req(rq->mq_hctx->driver_data, rq, issue_flags);

		ublk_dispatch_req(rq->mq_hctx->driver_data, rq);

		rq = next;

	} while (rq);

}
@@ -2523,9 +2522,10 @@ static inline struct request *__ublk_check_and_get_req(struct ublk_device *ub, 
	return NULL;

}



static void ublk_ch_uring_cmd_cb(struct io_uring_cmd *cmd,

		unsigned int issue_flags)

static void ublk_ch_uring_cmd_cb(struct io_tw_req tw_req, io_tw_token_t tw)

{

	unsigned int issue_flags = IO_URING_CMD_TASK_WORK_ISSUE_FLAGS;

	struct io_uring_cmd *cmd = io_uring_cmd_from_tw(tw_req);

	int ret = ublk_ch_uring_cmd_local(cmd, issue_flags);



	if (ret != -EIOCBQUEUED)

drivers/nvme/host/ioctl.c

+4 −3
Original line number Diff line number Diff line
@@ -398,14 +398,15 @@ static inline struct nvme_uring_cmd_pdu *nvme_uring_cmd_pdu( 
	return io_uring_cmd_to_pdu(ioucmd, struct nvme_uring_cmd_pdu);

}



static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd,

			       unsigned issue_flags)

static void nvme_uring_task_cb(struct io_tw_req tw_req, io_tw_token_t tw)

{

	struct io_uring_cmd *ioucmd = io_uring_cmd_from_tw(tw_req);

	struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd);



	if (pdu->bio)

		blk_rq_unmap_user(pdu->bio);

	io_uring_cmd_done32(ioucmd, pdu->status, pdu->result, issue_flags);

	io_uring_cmd_done32(ioucmd, pdu->status, pdu->result,

			    IO_URING_CMD_TASK_WORK_ISSUE_FLAGS);

}



static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req,

fs/btrfs/ioctl.c

+3 −2
Original line number Diff line number Diff line
@@ -4632,8 +4632,9 @@ struct io_btrfs_cmd { 
	struct btrfs_uring_priv *priv;

};



static void btrfs_uring_read_finished(struct io_uring_cmd *cmd, unsigned int issue_flags)

static void btrfs_uring_read_finished(struct io_tw_req tw_req, io_tw_token_t tw)

{

	struct io_uring_cmd *cmd = io_uring_cmd_from_tw(tw_req);

	struct io_btrfs_cmd *bc = io_uring_cmd_to_pdu(cmd, struct io_btrfs_cmd);

	struct btrfs_uring_priv *priv = bc->priv;

	struct btrfs_inode *inode = BTRFS_I(file_inode(priv->iocb.ki_filp));
@@ -4678,7 +4679,7 @@ static void btrfs_uring_read_finished(struct io_uring_cmd *cmd, unsigned int iss 
	btrfs_unlock_extent(io_tree, priv->start, priv->lockend, &priv->cached_state);

	btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED);



	io_uring_cmd_done(cmd, ret, issue_flags);

	io_uring_cmd_done(cmd, ret, IO_URING_CMD_TASK_WORK_ISSUE_FLAGS);

	add_rchar(current, ret);



	for (index = 0; index < priv->nr_pages; index++)

fs/fuse/dev_uring.c

+4 −3
Original line number Diff line number Diff line
@@ -1209,14 +1209,15 @@ static void fuse_uring_send(struct fuse_ring_ent *ent, struct io_uring_cmd *cmd, 
 * User buffers are not mapped yet - the application does not have permission

 * to write to it - this has to be executed in ring task context.

 */

static void fuse_uring_send_in_task(struct io_uring_cmd *cmd,

				    unsigned int issue_flags)

static void fuse_uring_send_in_task(struct io_tw_req tw_req, io_tw_token_t tw)

{

	unsigned int issue_flags = IO_URING_CMD_TASK_WORK_ISSUE_FLAGS;

	struct io_uring_cmd *cmd = io_uring_cmd_from_tw(tw_req);

	struct fuse_ring_ent *ent = uring_cmd_to_ring_ent(cmd);

	struct fuse_ring_queue *queue = ent->queue;

	int err;



	if (!(issue_flags & IO_URING_F_TASK_DEAD)) {

	if (!tw.cancel) {

		err = fuse_uring_prepare_send(ent, ent->fuse_req);

		if (err) {

			fuse_uring_next_fuse_req(ent, queue, issue_flags);