From 87e5e6dab6c2a21fab2620f37786276d202e2ce0 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Tue, 14 May 2019 16:02:22 -0600
Subject: uio: make import_iovec()/compat_import_iovec() return bytes on
 success

Currently these functions return < 0 on error, and 0 for success.
Change that so that we return < 0 on error, but number of bytes
for success.

Some callers already treat the return value that way, others need a
slight tweak.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/aio.c            |  9 +++++----
 fs/io_uring.c       | 16 ++++++++--------
 fs/splice.c         |  8 ++++----
 include/linux/uio.h |  4 ++--
 lib/iov_iter.c      | 15 ++++++++-------
 net/compat.c        |  3 ++-
 net/socket.c        |  3 ++-
 7 files changed, 31 insertions(+), 27 deletions(-)

diff --git a/fs/aio.c b/fs/aio.c
index 3490d1fa0e16..41824c710b36 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1479,8 +1479,9 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb)
 	return 0;
 }
 
-static int aio_setup_rw(int rw, const struct iocb *iocb, struct iovec **iovec,
-		bool vectored, bool compat, struct iov_iter *iter)
+static ssize_t aio_setup_rw(int rw, const struct iocb *iocb,
+		struct iovec **iovec, bool vectored, bool compat,
+		struct iov_iter *iter)
 {
 	void __user *buf = (void __user *)(uintptr_t)iocb->aio_buf;
 	size_t len = iocb->aio_nbytes;
@@ -1537,7 +1538,7 @@ static int aio_read(struct kiocb *req, const struct iocb *iocb,
 		return -EINVAL;
 
 	ret = aio_setup_rw(READ, iocb, &iovec, vectored, compat, &iter);
-	if (ret)
+	if (ret < 0)
 		return ret;
 	ret = rw_verify_area(READ, file, &req->ki_pos, iov_iter_count(&iter));
 	if (!ret)
@@ -1565,7 +1566,7 @@ static int aio_write(struct kiocb *req, const struct iocb *iocb,
 		return -EINVAL;
 
 	ret = aio_setup_rw(WRITE, iocb, &iovec, vectored, compat, &iter);
-	if (ret)
+	if (ret < 0)
 		return ret;
 	ret = rw_verify_area(WRITE, file, &req->ki_pos, iov_iter_count(&iter));
 	if (!ret) {
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 0fbb486a320e..23e08c10f486 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1003,9 +1003,9 @@ static int io_import_fixed(struct io_ring_ctx *ctx, int rw,
 	return 0;
 }
 
-static int io_import_iovec(struct io_ring_ctx *ctx, int rw,
-			   const struct sqe_submit *s, struct iovec **iovec,
-			   struct iov_iter *iter)
+static ssize_t io_import_iovec(struct io_ring_ctx *ctx, int rw,
+			       const struct sqe_submit *s, struct iovec **iovec,
+			       struct iov_iter *iter)
 {
 	const struct io_uring_sqe *sqe = s->sqe;
 	void __user *buf = u64_to_user_ptr(READ_ONCE(sqe->addr));
@@ -1023,7 +1023,7 @@ static int io_import_iovec(struct io_ring_ctx *ctx, int rw,
 	opcode = READ_ONCE(sqe->opcode);
 	if (opcode == IORING_OP_READ_FIXED ||
 	    opcode == IORING_OP_WRITE_FIXED) {
-		int ret = io_import_fixed(ctx, rw, sqe, iter);
+		ssize_t ret = io_import_fixed(ctx, rw, sqe, iter);
 		*iovec = NULL;
 		return ret;
 	}
@@ -1089,7 +1089,7 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s,
 	struct iov_iter iter;
 	struct file *file;
 	size_t iov_count;
-	int ret;
+	ssize_t ret;
 
 	ret = io_prep_rw(req, s, force_nonblock);
 	if (ret)
@@ -1102,7 +1102,7 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s,
 		return -EINVAL;
 
 	ret = io_import_iovec(req->ctx, READ, s, &iovec, &iter);
-	if (ret)
+	if (ret < 0)
 		return ret;
 
 	iov_count = iov_iter_count(&iter);
@@ -1136,7 +1136,7 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s,
 	struct iov_iter iter;
 	struct file *file;
 	size_t iov_count;
-	int ret;
+	ssize_t ret;
 
 	ret = io_prep_rw(req, s, force_nonblock);
 	if (ret)
@@ -1149,7 +1149,7 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s,
 		return -EINVAL;
 
 	ret = io_import_iovec(req->ctx, WRITE, s, &iovec, &iter);
-	if (ret)
+	if (ret < 0)
 		return ret;
 
 	iov_count = iov_iter_count(&iter);
diff --git a/fs/splice.c b/fs/splice.c
index 14cb602d9a2f..98412721f056 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -1356,7 +1356,7 @@ SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, uiov,
 	struct iovec iovstack[UIO_FASTIOV];
 	struct iovec *iov = iovstack;
 	struct iov_iter iter;
-	long error;
+	ssize_t error;
 	struct fd f;
 	int type;
 
@@ -1367,7 +1367,7 @@ SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, uiov,
 
 	error = import_iovec(type, uiov, nr_segs,
 			     ARRAY_SIZE(iovstack), &iov, &iter);
-	if (!error) {
+	if (error >= 0) {
 		error = do_vmsplice(f.file, &iter, flags);
 		kfree(iov);
 	}
@@ -1382,7 +1382,7 @@ COMPAT_SYSCALL_DEFINE4(vmsplice, int, fd, const struct compat_iovec __user *, io
 	struct iovec iovstack[UIO_FASTIOV];
 	struct iovec *iov = iovstack;
 	struct iov_iter iter;
-	long error;
+	ssize_t error;
 	struct fd f;
 	int type;
 
@@ -1393,7 +1393,7 @@ COMPAT_SYSCALL_DEFINE4(vmsplice, int, fd, const struct compat_iovec __user *, io
 
 	error = compat_import_iovec(type, iov32, nr_segs,
 			     ARRAY_SIZE(iovstack), &iov, &iter);
-	if (!error) {
+	if (error >= 0) {
 		error = do_vmsplice(f.file, &iter, flags);
 		kfree(iov);
 	}
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 2d0131ad4604..a61ceb6575ab 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -279,13 +279,13 @@ bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct
 size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp,
 		struct iov_iter *i);
 
-int import_iovec(int type, const struct iovec __user * uvector,
+ssize_t import_iovec(int type, const struct iovec __user * uvector,
 		 unsigned nr_segs, unsigned fast_segs,
 		 struct iovec **iov, struct iov_iter *i);
 
 #ifdef CONFIG_COMPAT
 struct compat_iovec;
-int compat_import_iovec(int type, const struct compat_iovec __user * uvector,
+ssize_t compat_import_iovec(int type, const struct compat_iovec __user * uvector,
 		 unsigned nr_segs, unsigned fast_segs,
 		 struct iovec **iov, struct iov_iter *i);
 #endif
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index f99c41d4eb54..f1e0569b4539 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -1634,9 +1634,9 @@ EXPORT_SYMBOL(dup_iter);
  * on-stack array was used or not (and regardless of whether this function
  * returns an error or not).
  *
- * Return: 0 on success or negative error code on error.
+ * Return: Negative error code on error, bytes imported on success
  */
-int import_iovec(int type, const struct iovec __user * uvector,
+ssize_t import_iovec(int type, const struct iovec __user * uvector,
 		 unsigned nr_segs, unsigned fast_segs,
 		 struct iovec **iov, struct iov_iter *i)
 {
@@ -1652,16 +1652,17 @@ int import_iovec(int type, const struct iovec __user * uvector,
 	}
 	iov_iter_init(i, type, p, nr_segs, n);
 	*iov = p == *iov ? NULL : p;
-	return 0;
+	return n;
 }
 EXPORT_SYMBOL(import_iovec);
 
 #ifdef CONFIG_COMPAT
 #include <linux/compat.h>
 
-int compat_import_iovec(int type, const struct compat_iovec __user * uvector,
-		 unsigned nr_segs, unsigned fast_segs,
-		 struct iovec **iov, struct iov_iter *i)
+ssize_t compat_import_iovec(int type,
+		const struct compat_iovec __user * uvector,
+		unsigned nr_segs, unsigned fast_segs,
+		struct iovec **iov, struct iov_iter *i)
 {
 	ssize_t n;
 	struct iovec *p;
@@ -1675,7 +1676,7 @@ int compat_import_iovec(int type, const struct compat_iovec __user * uvector,
 	}
 	iov_iter_init(i, type, p, nr_segs, n);
 	*iov = p == *iov ? NULL : p;
-	return 0;
+	return n;
 }
 #endif
 
diff --git a/net/compat.c b/net/compat.c
index 3f9ce609397f..0f7ded26059e 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -80,9 +80,10 @@ int get_compat_msghdr(struct msghdr *kmsg,
 
 	kmsg->msg_iocb = NULL;
 
-	return compat_import_iovec(save_addr ? READ : WRITE,
+	err = compat_import_iovec(save_addr ? READ : WRITE,
 				   compat_ptr(msg.msg_iov), msg.msg_iovlen,
 				   UIO_FASTIOV, iov, &kmsg->msg_iter);
+	return err < 0 ? err : 0;
 }
 
 /* Bleech... */
diff --git a/net/socket.c b/net/socket.c
index 72372dc5dd70..bffec466b4f1 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2208,9 +2208,10 @@ static int copy_msghdr_from_user(struct msghdr *kmsg,
 
 	kmsg->msg_iocb = NULL;
 
-	return import_iovec(save_addr ? READ : WRITE,
+	err = import_iovec(save_addr ? READ : WRITE,
 			    msg.msg_iov, msg.msg_iovlen,
 			    UIO_FASTIOV, iov, &kmsg->msg_iter);
+	return err < 0 ? err : 0;
 }
 
 static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg,
-- 
cgit v1.2.3


From 9d93a3f5a0c0d0f79aebc597d47c7cedc852aeb5 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Wed, 15 May 2019 13:53:07 -0600
Subject: io_uring: punt short reads to async context

We can encounter a short read when we're doing buffered reads and the
data is partially cached. Right now we just return the short read, but
that forces the application to read that CQE, then issue another SQE
to finish the read. That read will not be cached, and hence will result
in an async punt.

It's more efficient to do that async punt from within the kernel, as
that will the not need two round trips more to the kernel.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 23e08c10f486..92debd8be535 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1089,7 +1089,7 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s,
 	struct iov_iter iter;
 	struct file *file;
 	size_t iov_count;
-	ssize_t ret;
+	ssize_t read_size, ret;
 
 	ret = io_prep_rw(req, s, force_nonblock);
 	if (ret)
@@ -1105,13 +1105,24 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s,
 	if (ret < 0)
 		return ret;
 
+	read_size = ret;
 	iov_count = iov_iter_count(&iter);
 	ret = rw_verify_area(READ, file, &kiocb->ki_pos, iov_count);
 	if (!ret) {
 		ssize_t ret2;
 
-		/* Catch -EAGAIN return for forced non-blocking submission */
 		ret2 = call_read_iter(file, kiocb, &iter);
+		/*
+		 * In case of a short read, punt to async. This can happen
+		 * if we have data partially cached. Alternatively we can
+		 * return the short read, in which case the application will
+		 * need to issue another SQE and wait for it. That SQE will
+		 * need async punt anyway, so it's more efficient to do it
+		 * here.
+		 */
+		if (force_nonblock && ret2 > 0 && ret2 < read_size)
+			ret2 = -EAGAIN;
+		/* Catch -EAGAIN return for forced non-blocking submission */
 		if (!force_nonblock || ret2 != -EAGAIN) {
 			io_rw_done(kiocb, ret2);
 		} else {
-- 
cgit v1.2.3


From 9e645e1105ca60fbbc6bddf2fd5ef7e57ed3dca8 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 10 May 2019 16:07:28 -0600
Subject: io_uring: add support for sqe links

With SQE links, we can create chains of dependent SQEs. One example
would be queueing an SQE that's a read from one file descriptor, with
the linked SQE being a write to another with the same set of buffers.

An SQE link will not stall the pipeline, it'll just ensure that
dependent SQEs aren't issued before the previous link has completed.

Any error at submission or completion time will break the chain of SQEs.
For completions, this also includes short reads or writes, as the next
SQE could depend on the previous one being fully completed.

Any SQE in a chain that gets canceled due to any of the above errors,
will get an CQE fill with -ECANCELED as the error value.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c                 | 241 +++++++++++++++++++++++++++++++++---------
 include/uapi/linux/io_uring.h |   1 +
 2 files changed, 194 insertions(+), 48 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 92debd8be535..9f0ef4956f87 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -322,6 +322,7 @@ struct io_kiocb {
 
 	struct io_ring_ctx	*ctx;
 	struct list_head	list;
+	struct list_head	link_list;
 	unsigned int		flags;
 	refcount_t		refs;
 #define REQ_F_NOWAIT		1	/* must not punt to workers */
@@ -330,8 +331,10 @@ struct io_kiocb {
 #define REQ_F_SEQ_PREV		8	/* sequential with previous */
 #define REQ_F_IO_DRAIN		16	/* drain existing IO first */
 #define REQ_F_IO_DRAINED	32	/* drain done */
+#define REQ_F_LINK		64	/* linked sqes */
+#define REQ_F_FAIL_LINK		128	/* fail rest of links */
 	u64			user_data;
-	u32			error;	/* iopoll result from callback */
+	u32			result;
 	u32			sequence;
 
 	struct work_struct	work;
@@ -583,6 +586,7 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx,
 	req->flags = 0;
 	/* one is dropped after submission, the other at completion */
 	refcount_set(&req->refs, 2);
+	req->result = 0;
 	return req;
 out:
 	io_ring_drop_ctx_refs(ctx, 1);
@@ -598,7 +602,7 @@ static void io_free_req_many(struct io_ring_ctx *ctx, void **reqs, int *nr)
 	}
 }
 
-static void io_free_req(struct io_kiocb *req)
+static void __io_free_req(struct io_kiocb *req)
 {
 	if (req->file && !(req->flags & REQ_F_FIXED_FILE))
 		fput(req->file);
@@ -606,6 +610,63 @@ static void io_free_req(struct io_kiocb *req)
 	kmem_cache_free(req_cachep, req);
 }
 
+static void io_req_link_next(struct io_kiocb *req)
+{
+	struct io_kiocb *nxt;
+
+	/*
+	 * The list should never be empty when we are called here. But could
+	 * potentially happen if the chain is messed up, check to be on the
+	 * safe side.
+	 */
+	nxt = list_first_entry_or_null(&req->link_list, struct io_kiocb, list);
+	if (nxt) {
+		list_del(&nxt->list);
+		if (!list_empty(&req->link_list)) {
+			INIT_LIST_HEAD(&nxt->link_list);
+			list_splice(&req->link_list, &nxt->link_list);
+			nxt->flags |= REQ_F_LINK;
+		}
+
+		INIT_WORK(&nxt->work, io_sq_wq_submit_work);
+		queue_work(req->ctx->sqo_wq, &nxt->work);
+	}
+}
+
+/*
+ * Called if REQ_F_LINK is set, and we fail the head request
+ */
+static void io_fail_links(struct io_kiocb *req)
+{
+	struct io_kiocb *link;
+
+	while (!list_empty(&req->link_list)) {
+		link = list_first_entry(&req->link_list, struct io_kiocb, list);
+		list_del(&link->list);
+
+		io_cqring_add_event(req->ctx, link->user_data, -ECANCELED);
+		__io_free_req(link);
+	}
+}
+
+static void io_free_req(struct io_kiocb *req)
+{
+	/*
+	 * If LINK is set, we have dependent requests in this chain. If we
+	 * didn't fail this request, queue the first one up, moving any other
+	 * dependencies to the next request. In case of failure, fail the rest
+	 * of the chain.
+	 */
+	if (req->flags & REQ_F_LINK) {
+		if (req->flags & REQ_F_FAIL_LINK)
+			io_fail_links(req);
+		else
+			io_req_link_next(req);
+	}
+
+	__io_free_req(req);
+}
+
 static void io_put_req(struct io_kiocb *req)
 {
 	if (refcount_dec_and_test(&req->refs))
@@ -627,16 +688,17 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
 		req = list_first_entry(done, struct io_kiocb, list);
 		list_del(&req->list);
 
-		io_cqring_fill_event(ctx, req->user_data, req->error);
+		io_cqring_fill_event(ctx, req->user_data, req->result);
 		(*nr_events)++;
 
 		if (refcount_dec_and_test(&req->refs)) {
 			/* If we're not using fixed files, we have to pair the
 			 * completion part with the file put. Use regular
 			 * completions for those, only batch free for fixed
-			 * file.
+			 * file and non-linked commands.
 			 */
-			if (req->flags & REQ_F_FIXED_FILE) {
+			if ((req->flags & (REQ_F_FIXED_FILE|REQ_F_LINK)) ==
+			    REQ_F_FIXED_FILE) {
 				reqs[to_free++] = req;
 				if (to_free == ARRAY_SIZE(reqs))
 					io_free_req_many(ctx, reqs, &to_free);
@@ -775,6 +837,8 @@ static void io_complete_rw(struct kiocb *kiocb, long res, long res2)
 
 	kiocb_end_write(kiocb);
 
+	if ((req->flags & REQ_F_LINK) && res != req->result)
+		req->flags |= REQ_F_FAIL_LINK;
 	io_cqring_add_event(req->ctx, req->user_data, res);
 	io_put_req(req);
 }
@@ -785,7 +849,9 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2)
 
 	kiocb_end_write(kiocb);
 
-	req->error = res;
+	if ((req->flags & REQ_F_LINK) && res != req->result)
+		req->flags |= REQ_F_FAIL_LINK;
+	req->result = res;
 	if (res != -EAGAIN)
 		req->flags |= REQ_F_IOPOLL_COMPLETED;
 }
@@ -928,7 +994,6 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s,
 		    !kiocb->ki_filp->f_op->iopoll)
 			return -EOPNOTSUPP;
 
-		req->error = 0;
 		kiocb->ki_flags |= IOCB_HIPRI;
 		kiocb->ki_complete = io_complete_rw_iopoll;
 	} else {
@@ -1106,6 +1171,9 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s,
 		return ret;
 
 	read_size = ret;
+	if (req->flags & REQ_F_LINK)
+		req->result = read_size;
+
 	iov_count = iov_iter_count(&iter);
 	ret = rw_verify_area(READ, file, &kiocb->ki_pos, iov_count);
 	if (!ret) {
@@ -1163,6 +1231,9 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s,
 	if (ret < 0)
 		return ret;
 
+	if (req->flags & REQ_F_LINK)
+		req->result = ret;
+
 	iov_count = iov_iter_count(&iter);
 
 	ret = -EAGAIN;
@@ -1266,6 +1337,8 @@ static int io_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 				end > 0 ? end : LLONG_MAX,
 				fsync_flags & IORING_FSYNC_DATASYNC);
 
+	if (ret < 0 && (req->flags & REQ_F_LINK))
+		req->flags |= REQ_F_FAIL_LINK;
 	io_cqring_add_event(req->ctx, sqe->user_data, ret);
 	io_put_req(req);
 	return 0;
@@ -1310,6 +1383,8 @@ static int io_sync_file_range(struct io_kiocb *req,
 
 	ret = sync_file_range(req->rw.ki_filp, sqe_off, sqe_len, flags);
 
+	if (ret < 0 && (req->flags & REQ_F_LINK))
+		req->flags |= REQ_F_FAIL_LINK;
 	io_cqring_add_event(req->ctx, sqe->user_data, ret);
 	io_put_req(req);
 	return 0;
@@ -1562,9 +1637,10 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 {
 	int ret, opcode;
 
+	req->user_data = READ_ONCE(s->sqe->user_data);
+
 	if (unlikely(s->index >= ctx->sq_entries))
 		return -EINVAL;
-	req->user_data = READ_ONCE(s->sqe->user_data);
 
 	opcode = READ_ONCE(s->sqe->opcode);
 	switch (opcode) {
@@ -1608,7 +1684,7 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 		return ret;
 
 	if (ctx->flags & IORING_SETUP_IOPOLL) {
-		if (req->error == -EAGAIN)
+		if (req->result == -EAGAIN)
 			return -EAGAIN;
 
 		/* workqueue context doesn't hold uring_lock, grab it now */
@@ -1834,31 +1910,11 @@ static int io_req_set_file(struct io_ring_ctx *ctx, const struct sqe_submit *s,
 	return 0;
 }
 
-static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s,
-			 struct io_submit_state *state)
+static int io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
+			struct sqe_submit *s)
 {
-	struct io_kiocb *req;
 	int ret;
 
-	/* enforce forwards compatibility on users */
-	if (unlikely(s->sqe->flags & ~(IOSQE_FIXED_FILE | IOSQE_IO_DRAIN)))
-		return -EINVAL;
-
-	req = io_get_req(ctx, state);
-	if (unlikely(!req))
-		return -EAGAIN;
-
-	ret = io_req_set_file(ctx, s, state, req);
-	if (unlikely(ret))
-		goto out;
-
-	ret = io_req_defer(ctx, req, s->sqe);
-	if (ret) {
-		if (ret == -EIOCBQUEUED)
-			ret = 0;
-		return ret;
-	}
-
 	ret = __io_submit_sqe(ctx, req, s, true);
 	if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) {
 		struct io_uring_sqe *sqe_copy;
@@ -1881,24 +1937,93 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s,
 
 			/*
 			 * Queued up for async execution, worker will release
-			 * submit reference when the iocb is actually
-			 * submitted.
+			 * submit reference when the iocb is actually submitted.
 			 */
 			return 0;
 		}
 	}
 
-out:
 	/* drop submission reference */
 	io_put_req(req);
 
 	/* and drop final reference, if we failed */
-	if (ret)
+	if (ret) {
+		io_cqring_add_event(ctx, req->user_data, ret);
+		if (req->flags & REQ_F_LINK)
+			req->flags |= REQ_F_FAIL_LINK;
 		io_put_req(req);
+	}
 
 	return ret;
 }
 
+#define SQE_VALID_FLAGS	(IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK)
+
+static void io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s,
+			  struct io_submit_state *state, struct io_kiocb **link)
+{
+	struct io_uring_sqe *sqe_copy;
+	struct io_kiocb *req;
+	int ret;
+
+	/* enforce forwards compatibility on users */
+	if (unlikely(s->sqe->flags & ~SQE_VALID_FLAGS)) {
+		ret = -EINVAL;
+		goto err;
+	}
+
+	req = io_get_req(ctx, state);
+	if (unlikely(!req)) {
+		ret = -EAGAIN;
+		goto err;
+	}
+
+	ret = io_req_set_file(ctx, s, state, req);
+	if (unlikely(ret)) {
+err_req:
+		io_free_req(req);
+err:
+		io_cqring_add_event(ctx, s->sqe->user_data, ret);
+		return;
+	}
+
+	ret = io_req_defer(ctx, req, s->sqe);
+	if (ret) {
+		if (ret != -EIOCBQUEUED)
+			goto err_req;
+		return;
+	}
+
+	/*
+	 * If we already have a head request, queue this one for async
+	 * submittal once the head completes. If we don't have a head but
+	 * IOSQE_IO_LINK is set in the sqe, start a new head. This one will be
+	 * submitted sync once the chain is complete. If none of those
+	 * conditions are true (normal request), then just queue it.
+	 */
+	if (*link) {
+		struct io_kiocb *prev = *link;
+
+		sqe_copy = kmemdup(s->sqe, sizeof(*sqe_copy), GFP_KERNEL);
+		if (!sqe_copy) {
+			ret = -EAGAIN;
+			goto err_req;
+		}
+
+		s->sqe = sqe_copy;
+		memcpy(&req->submit, s, sizeof(*s));
+		list_add_tail(&req->list, &prev->link_list);
+	} else if (s->sqe->flags & IOSQE_IO_LINK) {
+		req->flags |= REQ_F_LINK;
+
+		memcpy(&req->submit, s, sizeof(*s));
+		INIT_LIST_HEAD(&req->link_list);
+		*link = req;
+	} else {
+		io_queue_sqe(ctx, req, s);
+	}
+}
+
 /*
  * Batched submission is done, ensure local IO is flushed out.
  */
@@ -1981,7 +2106,9 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, struct sqe_submit *sqes,
 			  unsigned int nr, bool has_user, bool mm_fault)
 {
 	struct io_submit_state state, *statep = NULL;
-	int ret, i, submitted = 0;
+	struct io_kiocb *link = NULL;
+	bool prev_was_link = false;
+	int i, submitted = 0;
 
 	if (nr > IO_PLUG_THRESHOLD) {
 		io_submit_state_start(&state, ctx, nr);
@@ -1989,22 +2116,30 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, struct sqe_submit *sqes,
 	}
 
 	for (i = 0; i < nr; i++) {
+		/*
+		 * If previous wasn't linked and we have a linked command,
+		 * that's the end of the chain. Submit the previous link.
+		 */
+		if (!prev_was_link && link) {
+			io_queue_sqe(ctx, link, &link->submit);
+			link = NULL;
+		}
+		prev_was_link = (sqes[i].sqe->flags & IOSQE_IO_LINK) != 0;
+
 		if (unlikely(mm_fault)) {
-			ret = -EFAULT;
+			io_cqring_add_event(ctx, sqes[i].sqe->user_data,
+						-EFAULT);
 		} else {
 			sqes[i].has_user = has_user;
 			sqes[i].needs_lock = true;
 			sqes[i].needs_fixed_file = true;
-			ret = io_submit_sqe(ctx, &sqes[i], statep);
-		}
-		if (!ret) {
+			io_submit_sqe(ctx, &sqes[i], statep, &link);
 			submitted++;
-			continue;
 		}
-
-		io_cqring_add_event(ctx, sqes[i].sqe->user_data, ret);
 	}
 
+	if (link)
+		io_queue_sqe(ctx, link, &link->submit);
 	if (statep)
 		io_submit_state_end(&state);
 
@@ -2145,6 +2280,8 @@ static int io_sq_thread(void *data)
 static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
 {
 	struct io_submit_state state, *statep = NULL;
+	struct io_kiocb *link = NULL;
+	bool prev_was_link = false;
 	int i, submit = 0;
 
 	if (to_submit > IO_PLUG_THRESHOLD) {
@@ -2154,22 +2291,30 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
 
 	for (i = 0; i < to_submit; i++) {
 		struct sqe_submit s;
-		int ret;
 
 		if (!io_get_sqring(ctx, &s))
 			break;
 
+		/*
+		 * If previous wasn't linked and we have a linked command,
+		 * that's the end of the chain. Submit the previous link.
+		 */
+		if (!prev_was_link && link) {
+			io_queue_sqe(ctx, link, &link->submit);
+			link = NULL;
+		}
+		prev_was_link = (s.sqe->flags & IOSQE_IO_LINK) != 0;
+
 		s.has_user = true;
 		s.needs_lock = false;
 		s.needs_fixed_file = false;
 		submit++;
-
-		ret = io_submit_sqe(ctx, &s, statep);
-		if (ret)
-			io_cqring_add_event(ctx, s.sqe->user_data, ret);
+		io_submit_sqe(ctx, &s, statep, &link);
 	}
 	io_commit_sqring(ctx);
 
+	if (link)
+		io_queue_sqe(ctx, link, &link->submit);
 	if (statep)
 		io_submit_state_end(statep);
 
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index a0c460025036..10b7c45f6d57 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -40,6 +40,7 @@ struct io_uring_sqe {
  */
 #define IOSQE_FIXED_FILE	(1U << 0)	/* use fixed fileset */
 #define IOSQE_IO_DRAIN		(1U << 1)	/* issue after inflight IO */
+#define IOSQE_IO_LINK		(1U << 2)	/* links next sqe */
 
 /*
  * io_uring_setup() flags
-- 
cgit v1.2.3


From 0fa03c624d8fc9932d0f27c39a9deca6a37e0e17 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 19 Apr 2019 13:34:07 -0600
Subject: io_uring: add support for sendmsg()

This is done through IORING_OP_SENDMSG. There's a new sqe->msg_flags
for the flags argument, and the msghdr struct is passed in the
sqe->addr field.

We use MSG_DONTWAIT to force an inline fast path if sendmsg() doesn't
block, and punt to async execution if it would have.

Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c                 | 40 ++++++++++++++++++++++++++++++++++++++++
 include/linux/socket.h        |  4 ++++
 include/uapi/linux/io_uring.h |  2 ++
 net/socket.c                  |  7 +++++++
 4 files changed, 53 insertions(+)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 9f0ef4956f87..5d4cd8c4132d 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1390,6 +1390,43 @@ static int io_sync_file_range(struct io_kiocb *req,
 	return 0;
 }
 
+static int io_sendmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+		      bool force_nonblock)
+{
+#if defined(CONFIG_NET)
+	struct socket *sock;
+	int ret;
+
+	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+		return -EINVAL;
+
+	sock = sock_from_file(req->file, &ret);
+	if (sock) {
+		struct user_msghdr __user *msg;
+		unsigned flags;
+
+		flags = READ_ONCE(sqe->msg_flags);
+		if (flags & MSG_DONTWAIT)
+			req->flags |= REQ_F_NOWAIT;
+		else if (force_nonblock)
+			flags |= MSG_DONTWAIT;
+
+		msg = (struct user_msghdr __user *) (unsigned long)
+			READ_ONCE(sqe->addr);
+
+		ret = __sys_sendmsg_sock(sock, msg, flags);
+		if (force_nonblock && ret == -EAGAIN)
+			return ret;
+	}
+
+	io_cqring_add_event(req->ctx, sqe->user_data, ret);
+	io_put_req(req);
+	return 0;
+#else
+	return -EOPNOTSUPP;
+#endif
+}
+
 static void io_poll_remove_one(struct io_kiocb *req)
 {
 	struct io_poll_iocb *poll = &req->poll;
@@ -1675,6 +1712,9 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	case IORING_OP_SYNC_FILE_RANGE:
 		ret = io_sync_file_range(req, s->sqe, force_nonblock);
 		break;
+	case IORING_OP_SENDMSG:
+		ret = io_sendmsg(req, s->sqe, force_nonblock);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
diff --git a/include/linux/socket.h b/include/linux/socket.h
index b57cd8bf96e2..9d770ef3ced5 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -12,6 +12,7 @@
 
 struct pid;
 struct cred;
+struct socket;
 
 #define __sockaddr_check_size(size)	\
 	BUILD_BUG_ON(((size) > sizeof(struct __kernel_sockaddr_storage)))
@@ -374,6 +375,9 @@ extern int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg,
 extern int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg,
 			  unsigned int vlen, unsigned int flags,
 			  bool forbid_cmsg_compat);
+extern long __sys_sendmsg_sock(struct socket *sock,
+			       struct user_msghdr __user *msg,
+			       unsigned int flags);
 
 /* helpers which do the actual work for syscalls */
 extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size,
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 10b7c45f6d57..d74742d6269f 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -27,6 +27,7 @@ struct io_uring_sqe {
 		__u32		fsync_flags;
 		__u16		poll_events;
 		__u32		sync_range_flags;
+		__u32		msg_flags;
 	};
 	__u64	user_data;	/* data to be passed back at completion time */
 	union {
@@ -58,6 +59,7 @@ struct io_uring_sqe {
 #define IORING_OP_POLL_ADD	6
 #define IORING_OP_POLL_REMOVE	7
 #define IORING_OP_SYNC_FILE_RANGE	8
+#define IORING_OP_SENDMSG	9
 
 /*
  * sqe->fsync_flags
diff --git a/net/socket.c b/net/socket.c
index bffec466b4f1..b9536940255e 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2313,6 +2313,13 @@ out_freeiov:
 /*
  *	BSD sendmsg interface
  */
+long __sys_sendmsg_sock(struct socket *sock, struct user_msghdr __user *msg,
+			unsigned int flags)
+{
+	struct msghdr msg_sys;
+
+	return ___sys_sendmsg(sock, msg, &msg_sys, flags, NULL, 0);
+}
 
 long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned int flags,
 		   bool forbid_cmsg_compat)
-- 
cgit v1.2.3


From aa1fa28fc73ea6b740ee7b62bf3b07141883dbb8 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 19 Apr 2019 13:38:09 -0600
Subject: io_uring: add support for recvmsg()

This is done through IORING_OP_RECVMSG. This opcode uses the same
sqe->msg_flags that IORING_OP_SENDMSG added, and we pass in the
msghdr struct in the sqe->addr field as well.

We use MSG_DONTWAIT to force an inline fast path if recvmsg() doesn't
block, and punt to async execution if it would have.

Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c                 | 31 +++++++++++++++++++++++++++----
 include/linux/socket.h        |  3 +++
 include/uapi/linux/io_uring.h |  1 +
 net/socket.c                  |  8 ++++++++
 4 files changed, 39 insertions(+), 4 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 5d4cd8c4132d..8d86e31b0762 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1390,10 +1390,12 @@ static int io_sync_file_range(struct io_kiocb *req,
 	return 0;
 }
 
-static int io_sendmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
-		      bool force_nonblock)
-{
 #if defined(CONFIG_NET)
+static int io_send_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+			   bool force_nonblock,
+		   long (*fn)(struct socket *, struct user_msghdr __user *,
+				unsigned int))
+{
 	struct socket *sock;
 	int ret;
 
@@ -1414,7 +1416,7 @@ static int io_sendmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 		msg = (struct user_msghdr __user *) (unsigned long)
 			READ_ONCE(sqe->addr);
 
-		ret = __sys_sendmsg_sock(sock, msg, flags);
+		ret = fn(sock, msg, flags);
 		if (force_nonblock && ret == -EAGAIN)
 			return ret;
 	}
@@ -1422,6 +1424,24 @@ static int io_sendmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 	io_cqring_add_event(req->ctx, sqe->user_data, ret);
 	io_put_req(req);
 	return 0;
+}
+#endif
+
+static int io_sendmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+		      bool force_nonblock)
+{
+#if defined(CONFIG_NET)
+	return io_send_recvmsg(req, sqe, force_nonblock, __sys_sendmsg_sock);
+#else
+	return -EOPNOTSUPP;
+#endif
+}
+
+static int io_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+		      bool force_nonblock)
+{
+#if defined(CONFIG_NET)
+	return io_send_recvmsg(req, sqe, force_nonblock, __sys_recvmsg_sock);
 #else
 	return -EOPNOTSUPP;
 #endif
@@ -1715,6 +1735,9 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	case IORING_OP_SENDMSG:
 		ret = io_sendmsg(req, s->sqe, force_nonblock);
 		break;
+	case IORING_OP_RECVMSG:
+		ret = io_recvmsg(req, s->sqe, force_nonblock);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 9d770ef3ced5..97523818cb14 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -378,6 +378,9 @@ extern int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg,
 extern long __sys_sendmsg_sock(struct socket *sock,
 			       struct user_msghdr __user *msg,
 			       unsigned int flags);
+extern long __sys_recvmsg_sock(struct socket *sock,
+			       struct user_msghdr __user *msg,
+			       unsigned int flags);
 
 /* helpers which do the actual work for syscalls */
 extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size,
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index d74742d6269f..1e1652f25cc1 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -60,6 +60,7 @@ struct io_uring_sqe {
 #define IORING_OP_POLL_REMOVE	7
 #define IORING_OP_SYNC_FILE_RANGE	8
 #define IORING_OP_SENDMSG	9
+#define IORING_OP_RECVMSG	10
 
 /*
  * sqe->fsync_flags
diff --git a/net/socket.c b/net/socket.c
index b9536940255e..98354cc18840 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2494,6 +2494,14 @@ out_freeiov:
  *	BSD recvmsg interface
  */
 
+long __sys_recvmsg_sock(struct socket *sock, struct user_msghdr __user *msg,
+			unsigned int flags)
+{
+	struct msghdr msg_sys;
+
+	return ___sys_recvmsg(sock, msg, &msg_sys, flags, 0);
+}
+
 long __sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned int flags,
 		   bool forbid_cmsg_compat)
 {
-- 
cgit v1.2.3


From a4c0b3decb33fb4a2b5ecc6234a50680f0b21e7d Mon Sep 17 00:00:00 2001
From: Jackie Liu <liuyun01@kylinos.cn>
Date: Mon, 8 Jul 2019 13:41:12 +0800
Subject: io_uring: fix io_sq_thread_stop running in front of io_sq_thread

INFO: task syz-executor.5:8634 blocked for more than 143 seconds.
       Not tainted 5.2.0-rc5+ #3
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
syz-executor.5  D25632  8634   8224 0x00004004
Call Trace:
  context_switch kernel/sched/core.c:2818 [inline]
  __schedule+0x658/0x9e0 kernel/sched/core.c:3445
  schedule+0x131/0x1d0 kernel/sched/core.c:3509
  schedule_timeout+0x9a/0x2b0 kernel/time/timer.c:1783
  do_wait_for_common+0x35e/0x5a0 kernel/sched/completion.c:83
  __wait_for_common kernel/sched/completion.c:104 [inline]
  wait_for_common kernel/sched/completion.c:115 [inline]
  wait_for_completion+0x47/0x60 kernel/sched/completion.c:136
  kthread_stop+0xb4/0x150 kernel/kthread.c:559
  io_sq_thread_stop fs/io_uring.c:2252 [inline]
  io_finish_async fs/io_uring.c:2259 [inline]
  io_ring_ctx_free fs/io_uring.c:2770 [inline]
  io_ring_ctx_wait_and_kill+0x268/0x880 fs/io_uring.c:2834
  io_uring_release+0x5d/0x70 fs/io_uring.c:2842
  __fput+0x2e4/0x740 fs/file_table.c:280
  ____fput+0x15/0x20 fs/file_table.c:313
  task_work_run+0x17e/0x1b0 kernel/task_work.c:113
  tracehook_notify_resume include/linux/tracehook.h:185 [inline]
  exit_to_usermode_loop arch/x86/entry/common.c:168 [inline]
  prepare_exit_to_usermode+0x402/0x4f0 arch/x86/entry/common.c:199
  syscall_return_slowpath+0x110/0x440 arch/x86/entry/common.c:279
  do_syscall_64+0x126/0x140 arch/x86/entry/common.c:304
  entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x412fb1
Code: 80 3b 7c 0f 84 c7 02 00 00 c7 85 d0 00 00 00 00 00 00 00 48 8b 05 cf
a6 24 00 49 8b 14 24 41 b9 cb 2a 44 00 48 89 ee 48 89 df <48> 85 c0 4c 0f
45 c8 45 31 c0 31 c9 e8 0e 5b 00 00 85 c0 41 89 c7
RSP: 002b:00007ffe7ee6a180 EFLAGS: 00000293 ORIG_RAX: 0000000000000003
RAX: 0000000000000000 RBX: 0000000000000004 RCX: 0000000000412fb1
RDX: 0000001b2d920000 RSI: 0000000000000000 RDI: 0000000000000003
RBP: 0000000000000001 R08: 00000000f3a3e1f8 R09: 00000000f3a3e1fc
R10: 00007ffe7ee6a260 R11: 0000000000000293 R12: 000000000075c9a0
R13: 000000000075c9a0 R14: 0000000000024c00 R15: 000000000075bf2c

=============================================

There is an wrong logic, when kthread_park running
in front of io_sq_thread.

CPU#0					CPU#1

io_sq_thread_stop:			int kthread(void *_create):

kthread_park()
					__kthread_parkme(self);	 <<< Wrong
kthread_stop()
    << wait for self->exited
    << clear_bit KTHREAD_SHOULD_PARK

					ret = threadfn(data);
					   |
					   |- io_sq_thread
					       |- kthread_should_park()	<< false
					       |- schedule() <<< nobody wake up

stuck CPU#0				stuck CPU#1

So, use a new variable sqo_thread_started to ensure that io_sq_thread
run first, then io_sq_thread_stop.

Reported-by: syzbot+94324416c485d422fe15@syzkaller.appspotmail.com
Suggested-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Jackie Liu <liuyun01@kylinos.cn>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 8d86e31b0762..7e932c572f26 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -231,6 +231,7 @@ struct io_ring_ctx {
 	struct task_struct	*sqo_thread;	/* if using sq thread polling */
 	struct mm_struct	*sqo_mm;
 	wait_queue_head_t	sqo_wait;
+	struct completion	sqo_thread_started;
 
 	struct {
 		/* CQ ring */
@@ -406,6 +407,7 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 	ctx->flags = p->flags;
 	init_waitqueue_head(&ctx->cq_wait);
 	init_completion(&ctx->ctx_done);
+	init_completion(&ctx->sqo_thread_started);
 	mutex_init(&ctx->uring_lock);
 	init_waitqueue_head(&ctx->wait);
 	for (i = 0; i < ARRAY_SIZE(ctx->pending_async); i++) {
@@ -2219,6 +2221,8 @@ static int io_sq_thread(void *data)
 	unsigned inflight;
 	unsigned long timeout;
 
+	complete(&ctx->sqo_thread_started);
+
 	old_fs = get_fs();
 	set_fs(USER_DS);
 
@@ -2462,6 +2466,7 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx)
 static void io_sq_thread_stop(struct io_ring_ctx *ctx)
 {
 	if (ctx->sqo_thread) {
+		wait_for_completion(&ctx->sqo_thread_started);
 		/*
 		 * The park is a bit of a work-around, without it we get
 		 * warning spews on shutdown with SQPOLL set and affinity
-- 
cgit v1.2.3