1 files changed, 182 insertions, 47 deletions

diff --git a/io_uring/rw.c b/io_uring/rw.c
index 0a0c1c9db..c3c154790 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -10,7 +10,7 @@
 #include <linux/poll.h>
 #include <linux/nospec.h>
 #include <linux/compat.h>
-#include <linux/io_uring.h>
+#include <linux/io_uring/cmd.h>
 
 #include <uapi/linux/io_uring.h>
 
@@ -18,6 +18,7 @@
 #include "opdef.h"
 #include "kbuf.h"
 #include "rsrc.h"
+#include "poll.h"
 #include "rw.h"
 
 struct io_rw {
@@ -83,18 +84,6 @@ int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	/* used for fixed read/write too - just read unconditionally */
 	req->buf_index = READ_ONCE(sqe->buf_index);
 
-	if (req->opcode == IORING_OP_READ_FIXED ||
-	    req->opcode == IORING_OP_WRITE_FIXED) {
-		struct io_ring_ctx *ctx = req->ctx;
-		u16 index;
-
-		if (unlikely(req->buf_index >= ctx->nr_user_bufs))
-			return -EFAULT;
-		index = array_index_nospec(req->buf_index, ctx->nr_user_bufs);
-		req->imu = ctx->user_bufs[index];
-		io_req_set_rsrc_node(req, ctx, 0);
-	}
-
 	ioprio = READ_ONCE(sqe->ioprio);
 	if (ioprio) {
 		ret = ioprio_check_cap(ioprio);
@@ -110,45 +99,74 @@ int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	rw->addr = READ_ONCE(sqe->addr);
 	rw->len = READ_ONCE(sqe->len);
 	rw->flags = READ_ONCE(sqe->rw_flags);
+	return 0;
+}
+
+int io_prep_rwv(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	int ret;
+
+	ret = io_prep_rw(req, sqe);
+	if (unlikely(ret))
+		return ret;
 
-	/* Have to do this validation here, as this is in io_read() rw->len might
-	 * have chanaged due to buffer selection
+	/*
+	 * Have to do this validation here, as this is in io_read() rw->len
+	 * might have chanaged due to buffer selection
 	 */
-	if (req->opcode == IORING_OP_READV && req->flags & REQ_F_BUFFER_SELECT) {
-		ret = io_iov_buffer_select_prep(req);
-		if (ret)
-			return ret;
-	}
+	if (req->flags & REQ_F_BUFFER_SELECT)
+		return io_iov_buffer_select_prep(req);
 
 	return 0;
 }
 
-void io_readv_writev_cleanup(struct io_kiocb *req)
+int io_prep_rw_fixed(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
-	struct io_async_rw *io = req->async_data;
+	struct io_ring_ctx *ctx = req->ctx;
+	u16 index;
+	int ret;
 
-	kfree(io->free_iovec);
+	ret = io_prep_rw(req, sqe);
+	if (unlikely(ret))
+		return ret;
+
+	if (unlikely(req->buf_index >= ctx->nr_user_bufs))
+		return -EFAULT;
+	index = array_index_nospec(req->buf_index, ctx->nr_user_bufs);
+	req->imu = ctx->user_bufs[index];
+	io_req_set_rsrc_node(req, ctx, 0);
+	return 0;
 }
 
-static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret)
+/*
+ * Multishot read is prepared just like a normal read/write request, only
+ * difference is that we set the MULTISHOT flag.
+ */
+int io_read_mshot_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
-	switch (ret) {
-	case -EIOCBQUEUED:
-		break;
-	case -ERESTARTSYS:
-	case -ERESTARTNOINTR:
-	case -ERESTARTNOHAND:
-	case -ERESTART_RESTARTBLOCK:
-		/*
-		 * We can't just restart the syscall, since previously
-		 * submitted sqes may already be in progress. Just fail this
-		 * IO with EINTR.
-		 */
-		ret = -EINTR;
-		fallthrough;
-	default:
-		kiocb->ki_complete(kiocb, ret);
-	}
+	struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
+	int ret;
+
+	/* must be used with provided buffers */
+	if (!(req->flags & REQ_F_BUFFER_SELECT))
+		return -EINVAL;
+
+	ret = io_prep_rw(req, sqe);
+	if (unlikely(ret))
+		return ret;
+
+	if (rw->addr || rw->len)
+		return -EINVAL;
+
+	req->flags |= REQ_F_APOLL_MULTISHOT;
+	return 0;
+}
+
+void io_readv_writev_cleanup(struct io_kiocb *req)
+{
+	struct io_async_rw *io = req->async_data;
+
+	kfree(io->free_iovec);
 }
 
 static inline loff_t *io_kiocb_update_pos(struct io_kiocb *req)
@@ -333,6 +351,33 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res)
 	smp_store_release(&req->iopoll_completed, 1);
 }
 
+static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret)
+{
+	/* IO was queued async, completion will happen later */
+	if (ret == -EIOCBQUEUED)
+		return;
+
+	/* transform internal restart error codes */
+	if (unlikely(ret < 0)) {
+		switch (ret) {
+		case -ERESTARTSYS:
+		case -ERESTARTNOINTR:
+		case -ERESTARTNOHAND:
+		case -ERESTART_RESTARTBLOCK:
+			/*
+			 * We can't just restart the syscall, since previously
+			 * submitted sqes may already be in progress. Just fail
+			 * this IO with EINTR.
+			 */
+			ret = -EINTR;
+			break;
+		}
+	}
+
+	INDIRECT_CALL_2(kiocb->ki_complete, io_complete_rw_iopoll,
+			io_complete_rw, kiocb, ret);
+}
+
 static int kiocb_done(struct io_kiocb *req, ssize_t ret,
 		       unsigned int issue_flags)
 {
@@ -388,8 +433,7 @@ static struct iovec *__io_import_iovec(int ddir, struct io_kiocb *req,
 	buf = u64_to_user_ptr(rw->addr);
 	sqe_len = rw->len;
 
-	if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE ||
-	    (req->flags & REQ_F_BUFFER_SELECT)) {
+	if (!io_issue_defs[opcode].vectored || req->flags & REQ_F_BUFFER_SELECT) {
 		if (io_do_buffer_select(req)) {
 			buf = io_buffer_select(req, &sqe_len, issue_flags);
 			if (!buf)
@@ -527,6 +571,9 @@ static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec,
 {
 	if (!force && !io_cold_defs[req->opcode].prep_async)
 		return 0;
+	/* opcode type doesn't need async data */
+	if (!io_cold_defs[req->opcode].async_size)
+		return 0;
 	if (!req_has_async_data(req)) {
 		struct io_async_rw *iorw;
 
@@ -712,7 +759,7 @@ static int io_rw_init_file(struct io_kiocb *req, fmode_t mode)
 	return 0;
 }
 
-int io_read(struct io_kiocb *req, unsigned int issue_flags)
+static int __io_read(struct io_kiocb *req, unsigned int issue_flags)
 {
 	struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
 	struct io_rw_state __s, *s = &__s;
@@ -780,8 +827,11 @@ int io_read(struct io_kiocb *req, unsigned int issue_flags)
 
 	if (ret == -EAGAIN || (req->flags & REQ_F_REISSUE)) {
 		req->flags &= ~REQ_F_REISSUE;
-		/* if we can poll, just do that */
-		if (req->opcode == IORING_OP_READ && file_can_poll(req->file))
+		/*
+		 * If we can poll, just do that. For a vectored read, we'll
+		 * need to copy state first.
+		 */
+		if (file_can_poll(req->file) && !io_issue_defs[req->opcode].vectored)
 			return -EAGAIN;
 		/* IOPOLL retry should happen for io-wq threads */
 		if (!force_nonblock && !(req->ctx->flags & IORING_SETUP_IOPOLL))
@@ -857,7 +907,92 @@ done:
 	/* it's faster to check here then delegate to kfree */
 	if (iovec)
 		kfree(iovec);
-	return kiocb_done(req, ret, issue_flags);
+	return ret;
+}
+
+int io_read(struct io_kiocb *req, unsigned int issue_flags)
+{
+	int ret;
+
+	ret = __io_read(req, issue_flags);
+	if (ret >= 0)
+		return kiocb_done(req, ret, issue_flags);
+
+	return ret;
+}
+
+int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
+	unsigned int cflags = 0;
+	int ret;
+
+	/*
+	 * Multishot MUST be used on a pollable file
+	 */
+	if (!file_can_poll(req->file))
+		return -EBADFD;
+
+	ret = __io_read(req, issue_flags);
+
+	/*
+	 * If the file doesn't support proper NOWAIT, then disable multishot
+	 * and stay in single shot mode.
+	 */
+	if (!io_file_supports_nowait(req))
+		req->flags &= ~REQ_F_APOLL_MULTISHOT;
+
+	/*
+	 * If we get -EAGAIN, recycle our buffer and just let normal poll
+	 * handling arm it.
+	 */
+	if (ret == -EAGAIN) {
+		/*
+		 * Reset rw->len to 0 again to avoid clamping future mshot
+		 * reads, in case the buffer size varies.
+		 */
+		if (io_kbuf_recycle(req, issue_flags))
+			rw->len = 0;
+		if (issue_flags & IO_URING_F_MULTISHOT)
+			return IOU_ISSUE_SKIP_COMPLETE;
+		return -EAGAIN;
+	}
+
+	/*
+	 * Any successful return value will keep the multishot read armed.
+	 */
+	if (ret > 0 && req->flags & REQ_F_APOLL_MULTISHOT) {
+		/*
+		 * Put our buffer and post a CQE. If we fail to post a CQE, then
+		 * jump to the termination path. This request is then done.
+		 */
+		cflags = io_put_kbuf(req, issue_flags);
+		rw->len = 0; /* similarly to above, reset len to 0 */
+
+		if (io_fill_cqe_req_aux(req,
+					issue_flags & IO_URING_F_COMPLETE_DEFER,
+					ret, cflags | IORING_CQE_F_MORE)) {
+			if (issue_flags & IO_URING_F_MULTISHOT) {
+				/*
+				 * Force retry, as we might have more data to
+				 * be read and otherwise it won't get retried
+				 * until (if ever) another poll is triggered.
+				 */
+				io_poll_multishot_retry(req);
+				return IOU_ISSUE_SKIP_COMPLETE;
+			}
+			return -EAGAIN;
+		}
+	}
+
+	/*
+	 * Either an error, or we've hit overflow posting the CQE. For any
+	 * multishot request, hitting overflow will terminate it.
+	 */
+	io_req_set_res(req, ret, cflags);
+	if (issue_flags & IO_URING_F_MULTISHOT)
+		return IOU_STOP_MULTISHOT;
+	return IOU_OK;
 }
 
 int io_write(struct io_kiocb *req, unsigned int issue_flags)