Merge branch 'for-6.7/io_uring' into for-6.7/block

Merge in io_uring fixes, as the ublk simplifying cancelations and
aborts depend on the two patches from Ming adding cancelation support
for uring_cmd.

* for-6.7/io_uring:
  io_uring/kbuf: Use slab for struct io_buffer objects
  io_uring/kbuf: Allow the full buffer id space for provided buffers
  io_uring/kbuf: Fix check of BID wrapping in provided buffers
  io_uring/rsrc: cleanup io_pin_pages()
  io_uring: cancelable uring_cmd
  io_uring: retain top 8bits of uring_cmd flags for kernel internal use
  io_uring: add IORING_OP_WAITID support
  exit: add internal include file with helpers
  exit: add kernel_waitid_prepare() helper
  exit: move core of do_wait() into helper
  exit: abstract out should_wake helper for child_wait_callback()
  io_uring/rw: add support for IORING_OP_READ_MULTISHOT
  io_uring/rw: mark readv/writev as vectored in the opcode definition
  io_uring/rw: split io_read() into a helper

3 files changed, 31 insertions, 5 deletions

diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index 106cdc55ff3b..b4391e0a9bc8 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -20,8 +20,15 @@ enum io_uring_cmd_flags {
 	IO_URING_F_SQE128		= (1 << 8),
 	IO_URING_F_CQE32		= (1 << 9),
 	IO_URING_F_IOPOLL		= (1 << 10),
+
+	/* set when uring wants to cancel a previously issued command */
+	IO_URING_F_CANCEL		= (1 << 11),
 };
 
+/* only top 8 bits of sqe->uring_cmd_flags for kernel internal use */
+#define IORING_URING_CMD_CANCELABLE	(1U << 30)
+#define IORING_URING_CMD_POLLED		(1U << 31)
+
 struct io_uring_cmd {
 	struct file	*file;
 	const struct io_uring_sqe *sqe;
@@ -82,6 +89,9 @@ static inline void io_uring_free(struct task_struct *tsk)
 		__io_uring_free(tsk);
 }
 int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags);
+void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd,
+		unsigned int issue_flags);
+struct task_struct *io_uring_cmd_get_task(struct io_uring_cmd *cmd);
 #else
 static inline int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
 			      struct iov_iter *iter, void *ioucmd)
@@ -122,6 +132,14 @@ static inline int io_uring_cmd_sock(struct io_uring_cmd *cmd,
 {
 	return -EOPNOTSUPP;
 }
+static inline void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd,
+		unsigned int issue_flags)
+{
+}
+static inline struct task_struct *io_uring_cmd_get_task(struct io_uring_cmd *cmd)
+{
+	return NULL;
+}
 #endif
 
 #endif
diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 13d19b9be9f4..e4e67899b134 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -265,6 +265,12 @@ struct io_ring_ctx {
 		 */
 		struct io_wq_work_list	iopoll_list;
 		bool			poll_multi_queue;
+
+		/*
+		 * Any cancelable uring_cmd is added to this list in
+		 * ->uring_cmd() by io_uring_cmd_insert_cancelable()
+		 */
+		struct hlist_head	cancelable_uring_cmd;
 	} ____cacheline_aligned_in_smp;
 
 	struct {
@@ -313,6 +319,8 @@ struct io_ring_ctx {
 	struct list_head	cq_overflow_list;
 	struct io_hash_table	cancel_table;
 
+	struct hlist_head	waitid_list;
+
 	const struct cred	*sq_creds;	/* cred used for __io_sq_thread() */
 	struct io_sq_data	*sq_data;	/* if using sq thread polling */
 
@@ -342,8 +350,6 @@ struct io_ring_ctx {
 	struct wait_queue_head		rsrc_quiesce_wq;
 	unsigned			rsrc_quiesce;
 
-	struct list_head		io_buffers_pages;
-
 	#if defined(CONFIG_UNIX)
 		struct socket		*ring_sock;
 	#endif
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 8e61f8b7c2ce..425f64eee44e 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -65,6 +65,7 @@ struct io_uring_sqe {
 		__u32		xattr_flags;
 		__u32		msg_ring_flags;
 		__u32		uring_cmd_flags;
+		__u32		waitid_flags;
 	};
 	__u64	user_data;	/* data to be passed back at completion time */
 	/* pack this to avoid bogus arm OABI complaints */
@@ -240,19 +241,20 @@ enum io_uring_op {
 	IORING_OP_URING_CMD,
 	IORING_OP_SEND_ZC,
 	IORING_OP_SENDMSG_ZC,
+	IORING_OP_READ_MULTISHOT,
+	IORING_OP_WAITID,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
 };
 
 /*
- * sqe->uring_cmd_flags
+ * sqe->uring_cmd_flags		top 8bits aren't available for userspace
  * IORING_URING_CMD_FIXED	use registered buffer; pass this flag
  *				along with setting sqe->buf_index.
- * IORING_URING_CMD_POLLED	driver use only
  */
 #define IORING_URING_CMD_FIXED	(1U << 0)
-#define IORING_URING_CMD_POLLED	(1U << 31)
+#define IORING_URING_CMD_MASK	IORING_URING_CMD_FIXED
 
 
 /*