Merge tag 'for-5.19/io_uring-passthrough-2022-05-22' of git://git.kernel.dk/linux-block

Pull io_uring NVMe command passthrough from Jens Axboe:
 "On top of everything else, this adds support for passthrough for
  io_uring.

  The initial feature for this is NVMe passthrough support, which allows
  non-filesystem based IO commands and admin commands.

  To support this, io_uring grows support for SQE and CQE members that
  are twice as big, allowing to pass in a full NVMe command without
  having to copy data around. And to complete with more than just a
  single 32-bit value as the output"

* tag 'for-5.19/io_uring-passthrough-2022-05-22' of git://git.kernel.dk/linux-block: (22 commits)
  io_uring: cleanup handling of the two task_work lists
  nvme: enable uring-passthrough for admin commands
  nvme: helper for uring-passthrough checks
  blk-mq: fix passthrough plugging
  nvme: add vectored-io support for uring-cmd
  nvme: wire-up uring-cmd support for io-passthru on char-device.
  nvme: refactor nvme_submit_user_cmd()
  block: wire-up support for passthrough plugging
  fs,io_uring: add infrastructure for uring-cmd
  io_uring: support CQE32 for nop operation
  io_uring: enable CQE32
  io_uring: support CQE32 in /proc info
  io_uring: add tracing for additional CQE32 fields
  io_uring: overflow processing for CQE32
  io_uring: flush completions for CQE32
  io_uring: modify io_get_cqe for CQE32
  io_uring: add CQE32 completion processing
  io_uring: add CQE32 setup processing
  io_uring: change ring size calculation for CQE32
  io_uring: store add. return values for CQE32
  ...

5 files changed, 99 insertions, 6 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index bbde95387a23..87b5af1d9fbe 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1953,6 +1953,7 @@ struct dir_context {
 #define REMAP_FILE_ADVISORY		(REMAP_FILE_CAN_SHORTEN)
 
 struct iov_iter;
+struct io_uring_cmd;
 
 struct file_operations {
 	struct module *owner;
@@ -1995,6 +1996,7 @@ struct file_operations {
 				   struct file *file_out, loff_t pos_out,
 				   loff_t len, unsigned int remap_flags);
 	int (*fadvise)(struct file *, loff_t, loff_t, int);
+	int (*uring_cmd)(struct io_uring_cmd *ioucmd, unsigned int issue_flags);
 } __randomize_layout;
 
 struct inode_operations {
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index 24651c229ed2..4a2f6cc5a492 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -5,7 +5,32 @@
 #include <linux/sched.h>
 #include <linux/xarray.h>
 
+enum io_uring_cmd_flags {
+	IO_URING_F_COMPLETE_DEFER	= 1,
+	IO_URING_F_UNLOCKED		= 2,
+	/* int's last bit, sign checks are usually faster than a bit test */
+	IO_URING_F_NONBLOCK		= INT_MIN,
+
+	/* ctx state flags, for URING_CMD */
+	IO_URING_F_SQE128		= 4,
+	IO_URING_F_CQE32		= 8,
+	IO_URING_F_IOPOLL		= 16,
+};
+
+struct io_uring_cmd {
+	struct file	*file;
+	const void	*cmd;
+	/* callback to defer completions to task context */
+	void (*task_work_cb)(struct io_uring_cmd *cmd);
+	u32		cmd_op;
+	u32		pad;
+	u8		pdu[32]; /* available inline for free use */
+};
+
 #if defined(CONFIG_IO_URING)
+void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2);
+void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
+			void (*task_work_cb)(struct io_uring_cmd *));
 struct sock *io_uring_get_socket(struct file *file);
 void __io_uring_cancel(bool cancel_all);
 void __io_uring_free(struct task_struct *tsk);
@@ -30,6 +55,14 @@ static inline void io_uring_free(struct task_struct *tsk)
 		__io_uring_free(tsk);
 }
 #else
+static inline void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret,
+		ssize_t ret2)
+{
+}
+static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
+			void (*task_work_cb)(struct io_uring_cmd *))
+{
+}
 static inline struct sock *io_uring_get_socket(struct file *file)
 {
 	return NULL;
diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h
index 610e493234db..66fcc5a1a5b1 100644
--- a/include/trace/events/io_uring.h
+++ b/include/trace/events/io_uring.h
@@ -321,13 +321,16 @@ TRACE_EVENT(io_uring_fail_link,
  * @user_data:		user data associated with the request
  * @res:		result of the request
  * @cflags:		completion flags
+ * @extra1:		extra 64-bit data for CQE32
+ * @extra2:		extra 64-bit data for CQE32
  *
  */
 TRACE_EVENT(io_uring_complete,
 
-	TP_PROTO(void *ctx, void *req, u64 user_data, int res, unsigned cflags),
+	TP_PROTO(void *ctx, void *req, u64 user_data, int res, unsigned cflags,
+		 u64 extra1, u64 extra2),
 
-	TP_ARGS(ctx, req, user_data, res, cflags),
+	TP_ARGS(ctx, req, user_data, res, cflags, extra1, extra2),
 
 	TP_STRUCT__entry (
 		__field(  void *,	ctx		)
@@ -335,6 +338,8 @@ TRACE_EVENT(io_uring_complete,
 		__field(  u64,		user_data	)
 		__field(  int,		res		)
 		__field(  unsigned,	cflags		)
+		__field(  u64,		extra1		)
+		__field(  u64,		extra2		)
 	),
 
 	TP_fast_assign(
@@ -343,12 +348,17 @@ TRACE_EVENT(io_uring_complete,
 		__entry->user_data	= user_data;
 		__entry->res		= res;
 		__entry->cflags		= cflags;
+		__entry->extra1		= extra1;
+		__entry->extra2		= extra2;
 	),
 
-	TP_printk("ring %p, req %p, user_data 0x%llx, result %d, cflags 0x%x",
+	TP_printk("ring %p, req %p, user_data 0x%llx, result %d, cflags 0x%x "
+		  "extra1 %llu extra2 %llu ",
 		__entry->ctx, __entry->req,
 		__entry->user_data,
-		__entry->res, __entry->cflags)
+		__entry->res, __entry->cflags,
+		(unsigned long long) __entry->extra1,
+		(unsigned long long) __entry->extra2)
 );
 
 /**
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index cc9544629eee..53e7dae92e42 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -22,6 +22,7 @@ struct io_uring_sqe {
 	union {
 		__u64	off;	/* offset into file */
 		__u64	addr2;
+		__u32	cmd_op;
 	};
 	union {
 		__u64	addr;	/* pointer to buffer or iovecs */
@@ -61,8 +62,17 @@ struct io_uring_sqe {
 		__s32	splice_fd_in;
 		__u32	file_index;
 	};
-	__u64	addr3;
-	__u64	__pad2[1];
+	union {
+		struct {
+			__u64	addr3;
+			__u64	__pad2[1];
+		};
+		/*
+		 * If the ring is initialized with IORING_SETUP_SQE128, then
+		 * this field is used for 80 bytes of arbitrary command data
+		 */
+		__u8	cmd[0];
+	};
 };
 
 /*
@@ -128,6 +138,9 @@ enum {
  */
 #define IORING_SETUP_TASKRUN_FLAG	(1U << 9)
 
+#define IORING_SETUP_SQE128		(1U << 10) /* SQEs are 128 byte */
+#define IORING_SETUP_CQE32		(1U << 11) /* CQEs are 32 byte */
+
 enum io_uring_op {
 	IORING_OP_NOP,
 	IORING_OP_READV,
@@ -175,6 +188,7 @@ enum io_uring_op {
 	IORING_OP_FGETXATTR,
 	IORING_OP_GETXATTR,
 	IORING_OP_SOCKET,
+	IORING_OP_URING_CMD,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
@@ -251,6 +265,12 @@ struct io_uring_cqe {
 	__u64	user_data;	/* sqe->data submission passed back */
 	__s32	res;		/* result code for this event */
 	__u32	flags;
+
+	/*
+	 * If the ring is initialized with IORING_SETUP_CQE32, then this field
+	 * contains 16-bytes of padding, doubling the size of the CQE.
+	 */
+	__u64 big_cqe[];
 };
 
 /*
diff --git a/include/uapi/linux/nvme_ioctl.h b/include/uapi/linux/nvme_ioctl.h
index b2e43185e3b5..2f76cba67166 100644
--- a/include/uapi/linux/nvme_ioctl.h
+++ b/include/uapi/linux/nvme_ioctl.h
@@ -70,6 +70,28 @@ struct nvme_passthru_cmd64 {
 	__u64	result;
 };
 
+/* same as struct nvme_passthru_cmd64, minus the 8b result field */
+struct nvme_uring_cmd {
+	__u8	opcode;
+	__u8	flags;
+	__u16	rsvd1;
+	__u32	nsid;
+	__u32	cdw2;
+	__u32	cdw3;
+	__u64	metadata;
+	__u64	addr;
+	__u32	metadata_len;
+	__u32	data_len;
+	__u32	cdw10;
+	__u32	cdw11;
+	__u32	cdw12;
+	__u32	cdw13;
+	__u32	cdw14;
+	__u32	cdw15;
+	__u32	timeout_ms;
+	__u32   rsvd2;
+};
+
 #define nvme_admin_cmd nvme_passthru_cmd
 
 #define NVME_IOCTL_ID		_IO('N', 0x40)
@@ -83,4 +105,10 @@ struct nvme_passthru_cmd64 {
 #define NVME_IOCTL_IO64_CMD	_IOWR('N', 0x48, struct nvme_passthru_cmd64)
 #define NVME_IOCTL_IO64_CMD_VEC	_IOWR('N', 0x49, struct nvme_passthru_cmd64)
 
+/* io_uring async commands: */
+#define NVME_URING_CMD_IO	_IOWR('N', 0x80, struct nvme_uring_cmd)
+#define NVME_URING_CMD_IO_VEC	_IOWR('N', 0x81, struct nvme_uring_cmd)
+#define NVME_URING_CMD_ADMIN	_IOWR('N', 0x82, struct nvme_uring_cmd)
+#define NVME_URING_CMD_ADMIN_VEC _IOWR('N', 0x83, struct nvme_uring_cmd)
+
 #endif /* _UAPI_LINUX_NVME_IOCTL_H */