From bc24d6bd32df0be19df3d30e74be4ba56493c0e2 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Tue, 12 Jul 2022 21:52:42 +0100
Subject: io_uring: add notification slot registration

Let the userspace to register and unregister notification slots.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/a0aa8161fe3ebb2a4cc6e5dbd0cffb96e6881cf5.1657643355.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/uapi/linux/io_uring.h | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

(limited to 'include/uapi/linux')

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 4c9b11e2e991..dcfc7a0bda0c 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -457,6 +457,10 @@ enum {
 	/* register a range of fixed file slots for automatic slot allocation */
 	IORING_REGISTER_FILE_ALLOC_RANGE	= 25,
 
+	/* zerocopy notification API */
+	IORING_REGISTER_NOTIFIERS		= 26,
+	IORING_UNREGISTER_NOTIFIERS		= 27,
+
 	/* this goes last */
 	IORING_REGISTER_LAST
 };
@@ -503,6 +507,19 @@ struct io_uring_rsrc_update2 {
 	__u32 resv2;
 };
 
+struct io_uring_notification_slot {
+	__u64 tag;
+	__u64 resv[3];
+};
+
+struct io_uring_notification_register {
+	__u32 nr_slots;
+	__u32 resv;
+	__u64 resv2;
+	__u64 data;
+	__u64 resv3;
+};
+
 /* Skip updating fd indexes set to this value in the fd table */
 #define IORING_REGISTER_FILES_SKIP	(-2)
 
-- 
cgit v1.2.3


From 06a5464be84e4ae48394d34441baf34bf9706827 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Tue, 12 Jul 2022 21:52:43 +0100
Subject: io_uring: wire send zc request type

Add a new io_uring opcode IORING_OP_SENDZC. The main distinction from
IORING_OP_SEND is that the user should specify a notification slot
index in sqe::notification_idx and the buffers are safe to reuse only
when the used notification is flushed and completes.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/a80387c6a68ce9cf99b3b6ef6f71068468761fb7.1657643355.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/uapi/linux/io_uring.h |  5 +++
 io_uring/net.c                | 94 +++++++++++++++++++++++++++++++++++++++++++
 io_uring/net.h                |  3 ++
 io_uring/opdef.c              | 15 +++++++
 4 files changed, 117 insertions(+)

(limited to 'include/uapi/linux')

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index dcfc7a0bda0c..82bf2991e9bd 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -66,6 +66,10 @@ struct io_uring_sqe {
 	union {
 		__s32	splice_fd_in;
 		__u32	file_index;
+		struct {
+			__u16	notification_idx;
+			__u16	__pad;
+		};
 	};
 	union {
 		struct {
@@ -197,6 +201,7 @@ enum io_uring_op {
 	IORING_OP_GETXATTR,
 	IORING_OP_SOCKET,
 	IORING_OP_URING_CMD,
+	IORING_OP_SENDZC_NOTIF,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
diff --git a/io_uring/net.c b/io_uring/net.c
index bbc9c603641a..89a8678ce69b 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -14,6 +14,7 @@
 #include "kbuf.h"
 #include "alloc_cache.h"
 #include "net.h"
+#include "notif.h"
 
 #if defined(CONFIG_NET)
 struct io_shutdown {
@@ -59,6 +60,15 @@ struct io_sr_msg {
 	unsigned int			flags;
 };
 
+struct io_sendzc {
+	struct file			*file;
+	void __user			*buf;
+	size_t				len;
+	u16				slot_idx;
+	unsigned			msg_flags;
+	unsigned			flags;
+};
+
 #define IO_APOLL_MULTI_POLLED (REQ_F_APOLL_MULTISHOT | REQ_F_POLLED)
 
 int io_shutdown_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
@@ -834,6 +844,90 @@ out_free:
 	return ret;
 }
 
+int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_sendzc *zc = io_kiocb_to_cmd(req);
+
+	if (READ_ONCE(sqe->addr2) || READ_ONCE(sqe->__pad2[0]) ||
+	    READ_ONCE(sqe->addr3))
+		return -EINVAL;
+
+	zc->flags = READ_ONCE(sqe->ioprio);
+	if (zc->flags & ~IORING_RECVSEND_POLL_FIRST)
+		return -EINVAL;
+
+	zc->buf = u64_to_user_ptr(READ_ONCE(sqe->addr));
+	zc->len = READ_ONCE(sqe->len);
+	zc->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL;
+	zc->slot_idx = READ_ONCE(sqe->notification_idx);
+	if (zc->msg_flags & MSG_DONTWAIT)
+		req->flags |= REQ_F_NOWAIT;
+#ifdef CONFIG_COMPAT
+	if (req->ctx->compat)
+		zc->msg_flags |= MSG_CMSG_COMPAT;
+#endif
+	return 0;
+}
+
+int io_sendzc(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_ring_ctx *ctx = req->ctx;
+	struct io_sendzc *zc = io_kiocb_to_cmd(req);
+	struct io_notif_slot *notif_slot;
+	struct io_notif *notif;
+	struct msghdr msg;
+	struct iovec iov;
+	struct socket *sock;
+	unsigned msg_flags;
+	int ret, min_ret = 0;
+
+	if (!(req->flags & REQ_F_POLLED) &&
+	    (zc->flags & IORING_RECVSEND_POLL_FIRST))
+		return -EAGAIN;
+
+	if (issue_flags & IO_URING_F_UNLOCKED)
+		return -EAGAIN;
+	sock = sock_from_file(req->file);
+	if (unlikely(!sock))
+		return -ENOTSOCK;
+
+	notif_slot = io_get_notif_slot(ctx, zc->slot_idx);
+	if (!notif_slot)
+		return -EINVAL;
+	notif = io_get_notif(ctx, notif_slot);
+	if (!notif)
+		return -ENOMEM;
+
+	msg.msg_name = NULL;
+	msg.msg_control = NULL;
+	msg.msg_controllen = 0;
+	msg.msg_namelen = 0;
+
+	ret = import_single_range(WRITE, zc->buf, zc->len, &iov, &msg.msg_iter);
+	if (unlikely(ret))
+		return ret;
+
+	msg_flags = zc->msg_flags | MSG_ZEROCOPY;
+	if (issue_flags & IO_URING_F_NONBLOCK)
+		msg_flags |= MSG_DONTWAIT;
+	if (msg_flags & MSG_WAITALL)
+		min_ret = iov_iter_count(&msg.msg_iter);
+
+	msg.msg_flags = msg_flags;
+	msg.msg_ubuf = &notif->uarg;
+	msg.sg_from_iter = NULL;
+	ret = sock_sendmsg(sock, &msg);
+
+	if (unlikely(ret < min_ret)) {
+		if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK))
+			return -EAGAIN;
+		return ret == -ERESTARTSYS ? -EINTR : ret;
+	}
+
+	io_req_set_res(req, ret, 0);
+	return IOU_OK;
+}
+
 int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_accept *accept = io_kiocb_to_cmd(req);
diff --git a/io_uring/net.h b/io_uring/net.h
index db20ce9d6546..7c438d39c089 100644
--- a/io_uring/net.h
+++ b/io_uring/net.h
@@ -52,6 +52,9 @@ int io_connect_prep_async(struct io_kiocb *req);
 int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
 int io_connect(struct io_kiocb *req, unsigned int issue_flags);
 
+int io_sendzc(struct io_kiocb *req, unsigned int issue_flags);
+int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+
 void io_netmsg_cache_free(struct io_cache_entry *entry);
 #else
 static inline void io_netmsg_cache_free(struct io_cache_entry *entry)
diff --git a/io_uring/opdef.c b/io_uring/opdef.c
index a7b84b43e6c2..7ab19bbf3126 100644
--- a/io_uring/opdef.c
+++ b/io_uring/opdef.c
@@ -470,6 +470,21 @@ const struct io_op_def io_op_defs[] = {
 		.issue			= io_uring_cmd,
 		.prep_async		= io_uring_cmd_prep_async,
 	},
+	[IORING_OP_SENDZC_NOTIF] = {
+		.name			= "SENDZC_NOTIF",
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+		.pollout		= 1,
+		.audit_skip		= 1,
+		.ioprio			= 1,
+#if defined(CONFIG_NET)
+		.prep			= io_sendzc_prep,
+		.issue			= io_sendzc,
+#else
+		.prep			= io_eopnotsupp_prep,
+#endif
+
+	},
 };
 
 const char *io_uring_get_opcode(u8 opcode)
-- 
cgit v1.2.3


From 092aeedb750a9fad0f0252d6067fc91d76ca44bd Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Tue, 12 Jul 2022 21:52:45 +0100
Subject: io_uring: allow to pass addr into sendzc

Allow to specify an address to zerocopy sends making it more like
sendto(2).

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/70417a8f7c5b51ab454690bae08adc0c187f89e8.1657643355.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/uapi/linux/io_uring.h |  2 +-
 io_uring/net.c                | 18 ++++++++++++++++--
 2 files changed, 17 insertions(+), 3 deletions(-)

(limited to 'include/uapi/linux')

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 82bf2991e9bd..0736e2773a5d 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -68,7 +68,7 @@ struct io_uring_sqe {
 		__u32	file_index;
 		struct {
 			__u16	notification_idx;
-			__u16	__pad;
+			__u16	addr_len;
 		};
 	};
 	union {
diff --git a/io_uring/net.c b/io_uring/net.c
index 2d04a70b0632..61414d865cd7 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -67,6 +67,8 @@ struct io_sendzc {
 	u16				slot_idx;
 	unsigned			msg_flags;
 	unsigned			flags;
+	unsigned			addr_len;
+	void __user			*addr;
 };
 
 #define IO_APOLL_MULTI_POLLED (REQ_F_APOLL_MULTISHOT | REQ_F_POLLED)
@@ -848,8 +850,7 @@ int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_sendzc *zc = io_kiocb_to_cmd(req);
 
-	if (READ_ONCE(sqe->addr2) || READ_ONCE(sqe->__pad2[0]) ||
-	    READ_ONCE(sqe->addr3))
+	if (READ_ONCE(sqe->__pad2[0]) || READ_ONCE(sqe->addr3))
 		return -EINVAL;
 
 	zc->flags = READ_ONCE(sqe->ioprio);
@@ -862,6 +863,10 @@ int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	zc->slot_idx = READ_ONCE(sqe->notification_idx);
 	if (zc->msg_flags & MSG_DONTWAIT)
 		req->flags |= REQ_F_NOWAIT;
+
+	zc->addr = u64_to_user_ptr(READ_ONCE(sqe->addr2));
+	zc->addr_len = READ_ONCE(sqe->addr_len);
+
 #ifdef CONFIG_COMPAT
 	if (req->ctx->compat)
 		zc->msg_flags |= MSG_CMSG_COMPAT;
@@ -871,6 +876,7 @@ int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 
 int io_sendzc(struct io_kiocb *req, unsigned int issue_flags)
 {
+	struct sockaddr_storage address;
 	struct io_ring_ctx *ctx = req->ctx;
 	struct io_sendzc *zc = io_kiocb_to_cmd(req);
 	struct io_notif_slot *notif_slot;
@@ -908,6 +914,14 @@ int io_sendzc(struct io_kiocb *req, unsigned int issue_flags)
 		return ret;
 	mm_account_pinned_pages(&notif->uarg.mmp, zc->len);
 
+	if (zc->addr) {
+		ret = move_addr_to_kernel(zc->addr, zc->addr_len, &address);
+		if (unlikely(ret < 0))
+			return ret;
+		msg.msg_name = (struct sockaddr *)&address;
+		msg.msg_namelen = zc->addr_len;
+	}
+
 	msg_flags = zc->msg_flags | MSG_ZEROCOPY;
 	if (issue_flags & IO_URING_F_NONBLOCK)
 		msg_flags |= MSG_DONTWAIT;
-- 
cgit v1.2.3


From 10c7d33ecd51619e453cf6aeee8e326f8ba5cfea Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Tue, 12 Jul 2022 21:52:46 +0100
Subject: io_uring: sendzc with fixed buffers

Allow zerocopy sends to use fixed buffers. There is an optimisation for
this case, the network layer don't need to reference the pages, see
SKBFL_MANAGED_FRAG_REFS, so io_uring have to ensure validity of fixed
buffers until the notifier is released.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/e1d8bd1b5934e541d90c1824eb4020ae3f5f43f3.1657643355.git.asml.silence@gmail.com
[axboe: fold in 32-bit pointer cast warning fix]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/uapi/linux/io_uring.h |  6 +++++-
 io_uring/net.c                | 29 ++++++++++++++++++++++++-----
 2 files changed, 29 insertions(+), 6 deletions(-)

(limited to 'include/uapi/linux')

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 0736e2773a5d..f1a9ff9b9ea7 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -272,9 +272,13 @@ enum io_uring_op {
  * IORING_RECV_MULTISHOT	Multishot recv. Sets IORING_CQE_F_MORE if
  *				the handler will continue to report
  *				CQEs on behalf of the same SQE.
+ *
+ * IORING_RECVSEND_FIXED_BUF	Use registered buffers, the index is stored in
+ *				the buf_index field.
  */
 #define IORING_RECVSEND_POLL_FIRST	(1U << 0)
-#define IORING_RECV_MULTISHOT	(1U << 1)
+#define IORING_RECV_MULTISHOT		(1U << 1)
+#define IORING_RECVSEND_FIXED_BUF	(1U << 2)
 
 /*
  * accept flags stored in sqe->ioprio
diff --git a/io_uring/net.c b/io_uring/net.c
index 61414d865cd7..ab443c52dcfd 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -15,6 +15,7 @@
 #include "alloc_cache.h"
 #include "net.h"
 #include "notif.h"
+#include "rsrc.h"
 
 #if defined(CONFIG_NET)
 struct io_shutdown {
@@ -849,13 +850,23 @@ out_free:
 int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_sendzc *zc = io_kiocb_to_cmd(req);
+	struct io_ring_ctx *ctx = req->ctx;
 
 	if (READ_ONCE(sqe->__pad2[0]) || READ_ONCE(sqe->addr3))
 		return -EINVAL;
 
 	zc->flags = READ_ONCE(sqe->ioprio);
-	if (zc->flags & ~IORING_RECVSEND_POLL_FIRST)
+	if (zc->flags & ~(IORING_RECVSEND_POLL_FIRST | IORING_RECVSEND_FIXED_BUF))
 		return -EINVAL;
+	if (zc->flags & IORING_RECVSEND_FIXED_BUF) {
+		unsigned idx = READ_ONCE(sqe->buf_index);
+
+		if (unlikely(idx >= ctx->nr_user_bufs))
+			return -EFAULT;
+		idx = array_index_nospec(idx, ctx->nr_user_bufs);
+		req->imu = READ_ONCE(ctx->user_bufs[idx]);
+		io_req_set_rsrc_node(req, ctx, 0);
+	}
 
 	zc->buf = u64_to_user_ptr(READ_ONCE(sqe->addr));
 	zc->len = READ_ONCE(sqe->len);
@@ -909,10 +920,18 @@ int io_sendzc(struct io_kiocb *req, unsigned int issue_flags)
 	msg.msg_controllen = 0;
 	msg.msg_namelen = 0;
 
-	ret = import_single_range(WRITE, zc->buf, zc->len, &iov, &msg.msg_iter);
-	if (unlikely(ret))
-		return ret;
-	mm_account_pinned_pages(&notif->uarg.mmp, zc->len);
+	if (zc->flags & IORING_RECVSEND_FIXED_BUF) {
+		ret = io_import_fixed(WRITE, &msg.msg_iter, req->imu,
+					(u64)(uintptr_t)zc->buf, zc->len);
+		if (unlikely(ret))
+				return ret;
+	} else {
+		ret = import_single_range(WRITE, zc->buf, zc->len, &iov,
+					  &msg.msg_iter);
+		if (unlikely(ret))
+			return ret;
+		mm_account_pinned_pages(&notif->uarg.mmp, zc->len);
+	}
 
 	if (zc->addr) {
 		ret = move_addr_to_kernel(zc->addr, zc->addr_len, &address);
-- 
cgit v1.2.3


From 63809137ebb58f0aa2ce359117422686e3304f45 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Tue, 12 Jul 2022 21:52:47 +0100
Subject: io_uring: flush notifiers after sendzc

Allow to flush notifiers as a part of sendzc request by setting
IORING_SENDZC_FLUSH flag. When the sendzc request succeedes it will
flush the used [active] notifier.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/e0b4d9a6797e2fd6092824fe42953db7a519bbc8.1657643355.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/uapi/linux/io_uring.h |  4 ++++
 io_uring/io_uring.c           | 11 +----------
 io_uring/io_uring.h           | 10 ++++++++++
 io_uring/net.c                |  5 ++++-
 io_uring/notif.c              |  2 +-
 io_uring/notif.h              | 11 +++++++++++
 6 files changed, 31 insertions(+), 12 deletions(-)

(limited to 'include/uapi/linux')

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index f1a9ff9b9ea7..45272eb37d10 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -275,10 +275,14 @@ enum io_uring_op {
  *
  * IORING_RECVSEND_FIXED_BUF	Use registered buffers, the index is stored in
  *				the buf_index field.
+ *
+ * IORING_RECVSEND_NOTIF_FLUSH	Flush a notification after a successful
+ *				successful. Only for zerocopy sends.
  */
 #define IORING_RECVSEND_POLL_FIRST	(1U << 0)
 #define IORING_RECV_MULTISHOT		(1U << 1)
 #define IORING_RECVSEND_FIXED_BUF	(1U << 2)
+#define IORING_RECVSEND_NOTIF_FLUSH	(1U << 3)
 
 /*
  * accept flags stored in sqe->ioprio
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index cae11374456e..1d600a63643b 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -621,7 +621,7 @@ void __io_put_task(struct task_struct *task, int nr)
 	put_task_struct_many(task, nr);
 }
 
-static void io_task_refs_refill(struct io_uring_task *tctx)
+void io_task_refs_refill(struct io_uring_task *tctx)
 {
 	unsigned int refill = -tctx->cached_refs + IO_TCTX_REFS_CACHE_NR;
 
@@ -630,15 +630,6 @@ static void io_task_refs_refill(struct io_uring_task *tctx)
 	tctx->cached_refs += refill;
 }
 
-static inline void io_get_task_refs(int nr)
-{
-	struct io_uring_task *tctx = current->io_uring;
-
-	tctx->cached_refs -= nr;
-	if (unlikely(tctx->cached_refs < 0))
-		io_task_refs_refill(tctx);
-}
-
 static __cold void io_uring_drop_tctx_refs(struct task_struct *task)
 {
 	struct io_uring_task *tctx = task->io_uring;
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index 66bfd880d07f..cc81a9d1fd4d 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -74,6 +74,7 @@ void io_wq_submit_work(struct io_wq_work *work);
 void io_free_req(struct io_kiocb *req);
 void io_queue_next(struct io_kiocb *req);
 void __io_put_task(struct task_struct *task, int nr);
+void io_task_refs_refill(struct io_uring_task *tctx);
 
 bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task,
 			bool cancel_all);
@@ -270,4 +271,13 @@ static inline void io_put_task(struct task_struct *task, int nr)
 		__io_put_task(task, nr);
 }
 
+static inline void io_get_task_refs(int nr)
+{
+	struct io_uring_task *tctx = current->io_uring;
+
+	tctx->cached_refs -= nr;
+	if (unlikely(tctx->cached_refs < 0))
+		io_task_refs_refill(tctx);
+}
+
 #endif
diff --git a/io_uring/net.c b/io_uring/net.c
index ab443c52dcfd..9ac2ce37c522 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -856,7 +856,8 @@ int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		return -EINVAL;
 
 	zc->flags = READ_ONCE(sqe->ioprio);
-	if (zc->flags & ~(IORING_RECVSEND_POLL_FIRST | IORING_RECVSEND_FIXED_BUF))
+	if (zc->flags & ~(IORING_RECVSEND_POLL_FIRST |
+			  IORING_RECVSEND_FIXED_BUF | IORING_RECVSEND_NOTIF_FLUSH))
 		return -EINVAL;
 	if (zc->flags & IORING_RECVSEND_FIXED_BUF) {
 		unsigned idx = READ_ONCE(sqe->buf_index);
@@ -958,6 +959,8 @@ int io_sendzc(struct io_kiocb *req, unsigned int issue_flags)
 		return ret == -ERESTARTSYS ? -EINTR : ret;
 	}
 
+	if (zc->flags & IORING_RECVSEND_NOTIF_FLUSH)
+		io_notif_slot_flush_submit(notif_slot, 0);
 	io_req_set_res(req, ret, 0);
 	return IOU_OK;
 }
diff --git a/io_uring/notif.c b/io_uring/notif.c
index c5179e5c1cd6..a93887451bbb 100644
--- a/io_uring/notif.c
+++ b/io_uring/notif.c
@@ -133,7 +133,7 @@ struct io_notif *io_alloc_notif(struct io_ring_ctx *ctx,
 	return notif;
 }
 
-static void io_notif_slot_flush(struct io_notif_slot *slot)
+void io_notif_slot_flush(struct io_notif_slot *slot)
 	__must_hold(&ctx->uring_lock)
 {
 	struct io_notif *notif = slot->notif;
diff --git a/io_uring/notif.h b/io_uring/notif.h
index 00efe164bdc4..6cd73d7b965b 100644
--- a/io_uring/notif.h
+++ b/io_uring/notif.h
@@ -54,6 +54,7 @@ int io_notif_register(struct io_ring_ctx *ctx,
 int io_notif_unregister(struct io_ring_ctx *ctx);
 void io_notif_cache_purge(struct io_ring_ctx *ctx);
 
+void io_notif_slot_flush(struct io_notif_slot *slot);
 struct io_notif *io_alloc_notif(struct io_ring_ctx *ctx,
 				struct io_notif_slot *slot);
 
@@ -74,3 +75,13 @@ static inline struct io_notif_slot *io_get_notif_slot(struct io_ring_ctx *ctx,
 	idx = array_index_nospec(idx, ctx->nr_notif_slots);
 	return &ctx->notif_slots[idx];
 }
+
+static inline void io_notif_slot_flush_submit(struct io_notif_slot *slot,
+					      unsigned int issue_flags)
+{
+	if (!(issue_flags & IO_URING_F_UNLOCKED)) {
+		slot->notif->task = current;
+		io_get_task_refs(1);
+	}
+	io_notif_slot_flush(slot);
+}
-- 
cgit v1.2.3


From 4379d5f15b3fd4224c37841029178aa8082a242e Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Tue, 12 Jul 2022 21:52:48 +0100
Subject: io_uring: rename IORING_OP_FILES_UPDATE

IORING_OP_FILES_UPDATE will be a more generic opcode serving different
resource types, rename it into IORING_OP_RSRC_UPDATE and add subtype
handling.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/0a907133907d9af3415a8a7aa1802c6aa97c03c6.1657643355.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/uapi/linux/io_uring.h | 12 +++++++++++-
 io_uring/opdef.c              |  9 +++++----
 io_uring/rsrc.c               | 17 +++++++++++++++--
 io_uring/rsrc.h               |  4 ++--
 4 files changed, 33 insertions(+), 9 deletions(-)

(limited to 'include/uapi/linux')

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 45272eb37d10..210a00ab6301 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -174,7 +174,8 @@ enum io_uring_op {
 	IORING_OP_FALLOCATE,
 	IORING_OP_OPENAT,
 	IORING_OP_CLOSE,
-	IORING_OP_FILES_UPDATE,
+	IORING_OP_RSRC_UPDATE,
+	IORING_OP_FILES_UPDATE = IORING_OP_RSRC_UPDATE,
 	IORING_OP_STATX,
 	IORING_OP_READ,
 	IORING_OP_WRITE,
@@ -223,6 +224,7 @@ enum io_uring_op {
 #define IORING_TIMEOUT_ETIME_SUCCESS	(1U << 5)
 #define IORING_TIMEOUT_CLOCK_MASK	(IORING_TIMEOUT_BOOTTIME | IORING_TIMEOUT_REALTIME)
 #define IORING_TIMEOUT_UPDATE_MASK	(IORING_TIMEOUT_UPDATE | IORING_LINK_TIMEOUT_UPDATE)
+
 /*
  * sqe->splice_flags
  * extends splice(2) flags
@@ -289,6 +291,14 @@ enum io_uring_op {
  */
 #define IORING_ACCEPT_MULTISHOT	(1U << 0)
 
+
+/*
+ * IORING_OP_RSRC_UPDATE flags
+ */
+enum {
+	IORING_RSRC_UPDATE_FILES,
+};
+
 /*
  * IORING_OP_MSG_RING command types, stored in sqe->addr
  */
diff --git a/io_uring/opdef.c b/io_uring/opdef.c
index 7ab19bbf3126..72dd2b2d8a9d 100644
--- a/io_uring/opdef.c
+++ b/io_uring/opdef.c
@@ -246,12 +246,13 @@ const struct io_op_def io_op_defs[] = {
 		.prep			= io_close_prep,
 		.issue			= io_close,
 	},
-	[IORING_OP_FILES_UPDATE] = {
+	[IORING_OP_RSRC_UPDATE] = {
 		.audit_skip		= 1,
 		.iopoll			= 1,
-		.name			= "FILES_UPDATE",
-		.prep			= io_files_update_prep,
-		.issue			= io_files_update,
+		.name			= "RSRC_UPDATE",
+		.prep			= io_rsrc_update_prep,
+		.issue			= io_rsrc_update,
+		.ioprio			= 1,
 	},
 	[IORING_OP_STATX] = {
 		.audit_skip		= 1,
diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index 7f66b0e25674..fc2b337e6c25 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -21,6 +21,7 @@ struct io_rsrc_update {
 	u64				arg;
 	u32				nr_args;
 	u32				offset;
+	int				type;
 };
 
 static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov,
@@ -657,7 +658,7 @@ __cold int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg,
 	return -EINVAL;
 }
 
-int io_files_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+int io_rsrc_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_rsrc_update *up = io_kiocb_to_cmd(req);
 
@@ -671,6 +672,7 @@ int io_files_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	if (!up->nr_args)
 		return -EINVAL;
 	up->arg = READ_ONCE(sqe->addr);
+	up->type = READ_ONCE(sqe->ioprio);
 	return 0;
 }
 
@@ -713,7 +715,7 @@ static int io_files_update_with_index_alloc(struct io_kiocb *req,
 	return ret;
 }
 
-int io_files_update(struct io_kiocb *req, unsigned int issue_flags)
+static int io_files_update(struct io_kiocb *req, unsigned int issue_flags)
 {
 	struct io_rsrc_update *up = io_kiocb_to_cmd(req);
 	struct io_ring_ctx *ctx = req->ctx;
@@ -742,6 +744,17 @@ int io_files_update(struct io_kiocb *req, unsigned int issue_flags)
 	return IOU_OK;
 }
 
+int io_rsrc_update(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_rsrc_update *up = io_kiocb_to_cmd(req);
+
+	switch (up->type) {
+	case IORING_RSRC_UPDATE_FILES:
+		return io_files_update(req, issue_flags);
+	}
+	return -EINVAL;
+}
+
 int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx,
 			  struct io_rsrc_node *node, void *rsrc)
 {
diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h
index af342fd239d0..21813a23215f 100644
--- a/io_uring/rsrc.h
+++ b/io_uring/rsrc.h
@@ -167,6 +167,6 @@ static inline u64 *io_get_tag_slot(struct io_rsrc_data *data, unsigned int idx)
 	return &data->tags[table_idx][off];
 }
 
-int io_files_update(struct io_kiocb *req, unsigned int issue_flags);
-int io_files_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_rsrc_update(struct io_kiocb *req, unsigned int issue_flags);
+int io_rsrc_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
 #endif
-- 
cgit v1.2.3


From 492dddb4f6e3a5839c27d41ff1fecdbe6c3ab851 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Tue, 12 Jul 2022 21:52:49 +0100
Subject: io_uring: add zc notification flush requests

Overlay notification control onto IORING_OP_RSRC_UPDATE (former
IORING_OP_FILES_UPDATE). It allows to flush a range of zc notifications
from slots with indexes [sqe->off, sqe->off+sqe->len). If sqe->arg is
not zero, it also copies sqe->arg as a new tag for all flushed
notifications.

Note, it doesn't flush a notification of a slot if there was no requests
attached to it (since last flush or registration).

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/df13e2363400682a73dd9e71c3b990b8d1ff0333.1657643355.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/uapi/linux/io_uring.h |  1 +
 io_uring/rsrc.c               | 38 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 39 insertions(+)

(limited to 'include/uapi/linux')

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 210a00ab6301..1463cfecb56b 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -297,6 +297,7 @@ enum io_uring_op {
  */
 enum {
 	IORING_RSRC_UPDATE_FILES,
+	IORING_RSRC_UPDATE_NOTIF,
 };
 
 /*
diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index fc2b337e6c25..9165fdf64269 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -15,6 +15,7 @@
 #include "io_uring.h"
 #include "openclose.h"
 #include "rsrc.h"
+#include "notif.h"
 
 struct io_rsrc_update {
 	struct file			*file;
@@ -744,6 +745,41 @@ static int io_files_update(struct io_kiocb *req, unsigned int issue_flags)
 	return IOU_OK;
 }
 
+static int io_notif_update(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_rsrc_update *up = io_kiocb_to_cmd(req);
+	struct io_ring_ctx *ctx = req->ctx;
+	unsigned len = up->nr_args;
+	unsigned idx_end, idx = up->offset;
+	int ret = 0;
+
+	io_ring_submit_lock(ctx, issue_flags);
+	if (unlikely(check_add_overflow(idx, len, &idx_end))) {
+		ret = -EOVERFLOW;
+		goto out;
+	}
+	if (unlikely(idx_end > ctx->nr_notif_slots)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	for (; idx < idx_end; idx++) {
+		struct io_notif_slot *slot = &ctx->notif_slots[idx];
+
+		if (!slot->notif)
+			continue;
+		if (up->arg)
+			slot->tag = up->arg;
+		io_notif_slot_flush_submit(slot, issue_flags);
+	}
+out:
+	io_ring_submit_unlock(ctx, issue_flags);
+	if (ret < 0)
+		req_set_fail(req);
+	io_req_set_res(req, ret, 0);
+	return IOU_OK;
+}
+
 int io_rsrc_update(struct io_kiocb *req, unsigned int issue_flags)
 {
 	struct io_rsrc_update *up = io_kiocb_to_cmd(req);
@@ -751,6 +787,8 @@ int io_rsrc_update(struct io_kiocb *req, unsigned int issue_flags)
 	switch (up->type) {
 	case IORING_RSRC_UPDATE_FILES:
 		return io_files_update(req, issue_flags);
+	case IORING_RSRC_UPDATE_NOTIF:
+		return io_notif_update(req, issue_flags);
 	}
 	return -EINVAL;
 }
-- 
cgit v1.2.3