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

Pull io_uring async discard support from Jens Axboe:
 "Sitting on top of both the 6.12 block and io_uring core branches,
  here's support for async discard through io_uring.

  This allows applications to issue async discards, rather than rely on
  the blocking sync ioctl discards we already have. The sync support is
  difficult to use outside of idle/cleanup periods.

  On a real (but slow) device, testing shows the following results when
  compared to sync discard:

	qd64 sync discard: 21K IOPS, lat avg 3 msec (max 21 msec)
	qd64 async discard: 76K IOPS, lat avg 845 usec (max 2.2 msec)

	qd64 sync discard: 14K IOPS, lat avg 5 msec (max 25 msec)
	qd64 async discard: 56K IOPS, lat avg 1153 usec (max 3.6 msec)

  and synthetic null_blk testing with the same queue depth and block
  size settings as above shows:

	Type    Trim size       IOPS    Lat avg (usec)  Lat Max (usec)
	==============================================================
	sync    4k               144K       444            20314
	async   4k              1353K        47              595
	sync    1M                56K      1136            21031
	async   1M                94K       680              760"

* tag 'for-6.12/io_uring-discard-20240913' of git://git.kernel.dk/linux:
  block: implement async io_uring discard cmd
  block: introduce blk_validate_byte_range()
  filemap: introduce filemap_invalidate_pages
  io_uring/cmd: give inline space in request to cmds
  io_uring/cmd: expose iowq to cmds

3 files changed, 19 insertions, 0 deletions

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 1aca501efaf6..86cf31902841 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -533,6 +533,17 @@ static void io_queue_iowq(struct io_kiocb *req)
 		io_queue_linked_timeout(link);
 }
 
+static void io_req_queue_iowq_tw(struct io_kiocb *req, struct io_tw_state *ts)
+{
+	io_queue_iowq(req);
+}
+
+void io_req_queue_iowq(struct io_kiocb *req)
+{
+	req->io_task_work.func = io_req_queue_iowq_tw;
+	io_req_task_work_add(req);
+}
+
 static __cold void io_queue_deferred(struct io_ring_ctx *ctx)
 {
 	while (!list_empty(&ctx->defer_list)) {
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index 65078e641390..9d70b2cf7b1e 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -94,6 +94,7 @@ int io_uring_alloc_task_context(struct task_struct *task,
 
 int io_ring_add_registered_file(struct io_uring_task *tctx, struct file *file,
 				     int start, int end);
+void io_req_queue_iowq(struct io_kiocb *req);
 
 int io_poll_issue(struct io_kiocb *req, struct io_tw_state *ts);
 int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr);
diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
index 8391c7c7c1ec..39c3c816ec78 100644
--- a/io_uring/uring_cmd.c
+++ b/io_uring/uring_cmd.c
@@ -277,6 +277,13 @@ int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
 }
 EXPORT_SYMBOL_GPL(io_uring_cmd_import_fixed);
 
+void io_uring_cmd_issue_blocking(struct io_uring_cmd *ioucmd)
+{
+	struct io_kiocb *req = cmd_to_io_kiocb(ioucmd);
+
+	io_req_queue_iowq(req);
+}
+
 static inline int io_uring_cmd_getsockopt(struct socket *sock,
 					  struct io_uring_cmd *cmd,
 					  unsigned int issue_flags)