[PATCH v8 06/10] io_uring/rw: add support to send metadata along with read/write

[Anuj Gupta <anuj20.g@samsung.com>]

This patch adds the capability of passing integrity metadata along with
read/write. A new ext_cap (extended_capability) field is introduced in SQE
which indicates the type of extra information being sent. A new
'struct io_uring_sqe_ext' represents the secondary SQE space for
read/write. In future if another extension needs to be added, then one
needs to:
1. Add extra fields in the sqe/secondary-sqe
2. Introduce a ext_cap flag indicating additional values that have been
passed

The last 32 bytes of secondary SQE is used to pass following PI related
information:

- flags: integrity check flags namely
IO_INTEGRITY_CHK_{GUARD/APPTAG/REFTAG}
- len: length of the pi/metadata buffer
- buf: address of the metadata buffer
- seed: seed value for reftag remapping
- app_tag: application defined 16b value

Application sets up a SQE128 ring, prepares PI information within the
second SQE and sets the ext_cap field to EXT_CAP_PI.  The patch processes
this information to prepare uio_meta descriptor and passes it down using
kiocb->private.

Meta exchange is supported only for direct IO.
Also vectored read/write operations with meta are not supported
currently.

Signed-off-by: Anuj Gupta <anuj20.g@samsung.com>
Signed-off-by: Kanchan Joshi <joshi.k@samsung.com>
---
 include/uapi/linux/io_uring.h | 34 ++++++++++++++
 io_uring/io_uring.c           |  8 ++++
 io_uring/rw.c                 | 88 ++++++++++++++++++++++++++++++++++-
 io_uring/rw.h                 | 14 +++++-
 4 files changed, 141 insertions(+), 3 deletions(-)

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 56cf30b49ef5..449e7627b1b5 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -92,6 +92,11 @@ struct io_uring_sqe {
 			__u16	addr_len;
 			__u16	__pad3[1];
 		};
+		struct {
+			/* flags indicating additional information being passed */
+			__u16	ext_cap;
+			__u16	__pad4[1];
+		};
 	};
 	union {
 		struct {
@@ -107,6 +112,35 @@ struct io_uring_sqe {
 	};
 };
 
+enum io_uring_sqe_ext_cap_bits {
+	EXT_CAP_PI_BIT,
+	/*
+	 * not a real extended capability; just to make sure that we don't
+	 * overflow
+	 */
+	EXT_CAP_LAST_BIT,
+};
+
+/* extended capability flags */
+#define EXT_CAP_PI	(1U << EXT_CAP_PI_BIT)
+
+/* Second half of SQE128 for IORING_OP_READ/WRITE */
+struct io_uring_sqe_ext {
+	__u64	rsvd0[4];
+	/* if sqe->ext_cap is EXT_CAP_PI, last 32 bytes are for PI */
+	union {
+		__u64	rsvd1[4];
+		struct {
+			__u16	flags;
+			__u16	app_tag;
+			__u32	len;
+			__u64	addr;
+			__u64	seed;
+			__u64	rsvd;
+		} rw_pi;
+	};
+};
+
 /*
  * If sqe->file_index is set to this for opcodes that instantiate a new
  * direct descriptor (like openat/openat2/accept), then io_uring will allocate
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index b590e50f09e7..6e582fe93bc4 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -4165,7 +4165,9 @@ static int __init io_uring_init(void)
 	BUILD_BUG_SQE_ELEM(44, __s32,  splice_fd_in);
 	BUILD_BUG_SQE_ELEM(44, __u32,  file_index);
 	BUILD_BUG_SQE_ELEM(44, __u16,  addr_len);
+	BUILD_BUG_SQE_ELEM(44, __u16,  ext_cap);
 	BUILD_BUG_SQE_ELEM(46, __u16,  __pad3[0]);
+	BUILD_BUG_SQE_ELEM(46, __u16,  __pad4[0]);
 	BUILD_BUG_SQE_ELEM(48, __u64,  addr3);
 	BUILD_BUG_SQE_ELEM_SIZE(48, 0, cmd);
 	BUILD_BUG_SQE_ELEM(56, __u64,  __pad2);
@@ -4192,6 +4194,12 @@ static int __init io_uring_init(void)
 	/* top 8bits are for internal use */
 	BUILD_BUG_ON((IORING_URING_CMD_MASK & 0xff000000) != 0);
 
+	BUILD_BUG_ON(sizeof(struct io_uring_sqe_ext) !=
+		     sizeof(struct io_uring_sqe));
+
+	BUILD_BUG_ON(EXT_CAP_LAST_BIT >
+		     8 * sizeof_field(struct io_uring_sqe, ext_cap));
+
 	io_uring_optable_init();
 
 	/*
diff --git a/io_uring/rw.c b/io_uring/rw.c
index 768a908ca2a8..e60bf0ed4c4f 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -257,11 +257,64 @@ static int io_prep_rw_setup(struct io_kiocb *req, int ddir, bool do_import)
 	return 0;
 }
 
+static inline void io_meta_save_state(struct io_async_rw *io)
+{
+	io->meta_state.seed = io->meta.seed;
+	iov_iter_save_state(&io->meta.iter, &io->meta_state.iter_meta);
+}
+
+static inline void io_meta_restore(struct io_async_rw *io)
+{
+	io->meta.seed = io->meta_state.seed;
+	iov_iter_restore(&io->meta.iter, &io->meta_state.iter_meta);
+}
+
+static inline const void *io_uring_sqe_ext(const struct io_uring_sqe *sqe)
+{
+	return (sqe + 1);
+}
+
+static int io_prep_rw_pi(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+			   struct io_rw *rw, int ddir)
+{
+	const struct io_uring_sqe_ext *sqe_ext;
+	const struct io_issue_def *def;
+	struct io_async_rw *io;
+	int ret;
+
+	if (!(req->ctx->flags & IORING_SETUP_SQE128))
+		return -EINVAL;
+
+	sqe_ext = io_uring_sqe_ext(sqe);
+	if (READ_ONCE(sqe_ext->rsvd0[0]) || READ_ONCE(sqe_ext->rsvd0[1])
+	    || READ_ONCE(sqe_ext->rsvd0[2]) || READ_ONCE(sqe_ext->rsvd0[3]))
+		return -EINVAL;
+	if (READ_ONCE(sqe_ext->rw_pi.rsvd))
+		return -EINVAL;
+
+	def = &io_issue_defs[req->opcode];
+	if (def->vectored)
+		return -EOPNOTSUPP;
+
+	io = req->async_data;
+	io->meta.flags = READ_ONCE(sqe_ext->rw_pi.flags);
+	io->meta.app_tag = READ_ONCE(sqe_ext->rw_pi.app_tag);
+	io->meta.seed = READ_ONCE(sqe_ext->rw_pi.seed);
+	ret = import_ubuf(ddir, u64_to_user_ptr(READ_ONCE(sqe_ext->rw_pi.addr)),
+			  READ_ONCE(sqe_ext->rw_pi.len), &io->meta.iter);
+	if (unlikely(ret < 0))
+		return ret;
+	rw->kiocb.ki_flags |= IOCB_HAS_METADATA;
+	io_meta_save_state(io);
+	return ret;
+}
+
 static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 		      int ddir, bool do_import)
 {
 	struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
 	unsigned ioprio;
+	u16 ext_cap;
 	int ret;
 
 	rw->kiocb.ki_pos = READ_ONCE(sqe->off);
@@ -279,11 +332,23 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 		rw->kiocb.ki_ioprio = get_current_ioprio();
 	}
 	rw->kiocb.dio_complete = NULL;
+	rw->kiocb.ki_flags = 0;
 
 	rw->addr = READ_ONCE(sqe->addr);
 	rw->len = READ_ONCE(sqe->len);
 	rw->flags = READ_ONCE(sqe->rw_flags);
-	return io_prep_rw_setup(req, ddir, do_import);
+	ret = io_prep_rw_setup(req, ddir, do_import);
+
+	if (unlikely(ret))
+		return ret;
+
+	ext_cap = READ_ONCE(sqe->ext_cap);
+	if (ext_cap) {
+		if (READ_ONCE(sqe->__pad4[0]) || !(ext_cap & EXT_CAP_PI))
+			return -EINVAL;
+		ret = io_prep_rw_pi(req, sqe, rw, ddir);
+	}
+	return ret;
 }
 
 int io_prep_read(struct io_kiocb *req, const struct io_uring_sqe *sqe)
@@ -410,7 +475,10 @@ static inline loff_t *io_kiocb_update_pos(struct io_kiocb *req)
 static void io_resubmit_prep(struct io_kiocb *req)
 {
 	struct io_async_rw *io = req->async_data;
+	struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
 
+	if (rw->kiocb.ki_flags & IOCB_HAS_METADATA)
+		io_meta_restore(io);
 	iov_iter_restore(&io->iter, &io->iter_state);
 }
 
@@ -795,7 +863,7 @@ static int io_rw_init_file(struct io_kiocb *req, fmode_t mode, int rw_type)
 	if (!(req->flags & REQ_F_FIXED_FILE))
 		req->flags |= io_file_get_flags(file);
 
-	kiocb->ki_flags = file->f_iocb_flags;
+	kiocb->ki_flags |= file->f_iocb_flags;
 	ret = kiocb_set_rw_flags(kiocb, rw->flags, rw_type);
 	if (unlikely(ret))
 		return ret;
@@ -829,6 +897,18 @@ static int io_rw_init_file(struct io_kiocb *req, fmode_t mode, int rw_type)
 		kiocb->ki_complete = io_complete_rw;
 	}
 
+	if (kiocb->ki_flags & IOCB_HAS_METADATA) {
+		struct io_async_rw *io = req->async_data;
+
+		/*
+		 * We have a union of meta fields with wpq used for buffered-io
+		 * in io_async_rw, so fail it here.
+		 */
+		if (!(req->file->f_flags & O_DIRECT))
+			return -EOPNOTSUPP;
+		kiocb->private = &io->meta;
+	}
+
 	return 0;
 }
 
@@ -903,6 +983,8 @@ static int __io_read(struct io_kiocb *req, unsigned int issue_flags)
 	 * manually if we need to.
 	 */
 	iov_iter_restore(&io->iter, &io->iter_state);
+	if (kiocb->ki_flags & IOCB_HAS_METADATA)
+		io_meta_restore(io);
 
 	do {
 		/*
@@ -1126,6 +1208,8 @@ int io_write(struct io_kiocb *req, unsigned int issue_flags)
 	} else {
 ret_eagain:
 		iov_iter_restore(&io->iter, &io->iter_state);
+		if (kiocb->ki_flags & IOCB_HAS_METADATA)
+			io_meta_restore(io);
 		if (kiocb->ki_flags & IOCB_WRITE)
 			io_req_end_write(req);
 		return -EAGAIN;
diff --git a/io_uring/rw.h b/io_uring/rw.h
index 3f432dc75441..2d7656bd268d 100644
--- a/io_uring/rw.h
+++ b/io_uring/rw.h
@@ -2,6 +2,11 @@
 
 #include <linux/pagemap.h>
 
+struct io_meta_state {
+	u32			seed;
+	struct iov_iter_state	iter_meta;
+};
+
 struct io_async_rw {
 	size_t				bytes_done;
 	struct iov_iter			iter;
@@ -9,7 +14,14 @@ struct io_async_rw {
 	struct iovec			fast_iov;
 	struct iovec			*free_iovec;
 	int				free_iov_nr;
-	struct wait_page_queue		wpq;
+	/* wpq is for buffered io, while meta fields are used with direct io */
+	union {
+		struct wait_page_queue		wpq;
+		struct {
+			struct uio_meta			meta;
+			struct io_meta_state		meta_state;
+		};
+	};
 };
 
 int io_prep_read_fixed(struct io_kiocb *req, const struct io_uring_sqe *sqe);
-- 
2.25.1