Merge tag 'for-5.20/io_uring-2022-07-29' of git://git.kernel.dk/linux-block

Pull io_uring updates from Jens Axboe:

 - As per (valid) complaint in the last merge window, fs/io_uring.c has
   grown quite large these days. io_uring isn't really tied to fs
   either, as it supports a wide variety of functionality outside of
   that.

   Move the code to io_uring/ and split it into files that either
   implement a specific request type, and split some code into helpers
   as well. The code is organized a lot better like this, and io_uring.c
   is now < 4K LOC (me).

 - Deprecate the epoll_ctl opcode. It'll still work, just trigger a
   warning once if used. If we don't get any complaints on this, and I
   don't expect any, then we can fully remove it in a future release
   (me).

 - Improve the cancel hash locking (Hao)

 - kbuf cleanups (Hao)

 - Efficiency improvements to the task_work handling (Dylan, Pavel)

 - Provided buffer improvements (Dylan)

 - Add support for recv/recvmsg multishot support. This is similar to
   the accept (or poll) support for have for multishot, where a single
   SQE can trigger everytime data is received. For applications that
   expect to do more than a few receives on an instantiated socket, this
   greatly improves efficiency (Dylan).

 - Efficiency improvements for poll handling (Pavel)

 - Poll cancelation improvements (Pavel)

 - Allow specifiying a range for direct descriptor allocations (Pavel)

 - Cleanup the cqe32 handling (Pavel)

 - Move io_uring types to greatly cleanup the tracing (Pavel)

 - Tons of great code cleanups and improvements (Pavel)

 - Add a way to do sync cancelations rather than through the sqe -> cqe
   interface, as that's a lot easier to use for some use cases (me).

 - Add support to IORING_OP_MSG_RING for sending direct descriptors to a
   different ring. This avoids the usually problematic SCM case, as we
   disallow those. (me)

 - Make the per-command alloc cache we use for apoll generic, place
   limits on it, and use it for netmsg as well (me).

 - Various cleanups (me, Michal, Gustavo, Uros)

* tag 'for-5.20/io_uring-2022-07-29' of git://git.kernel.dk/linux-block: (172 commits)
  io_uring: ensure REQ_F_ISREG is set async offload
  net: fix compat pointer in get_compat_msghdr()
  io_uring: Don't require reinitable percpu_ref
  io_uring: fix types in io_recvmsg_multishot_overflow
  io_uring: Use atomic_long_try_cmpxchg in __io_account_mem
  io_uring: support multishot in recvmsg
  net: copy from user before calling __get_compat_msghdr
  net: copy from user before calling __copy_msghdr
  io_uring: support 0 length iov in buffer select in compat
  io_uring: fix multishot ending when not polled
  io_uring: add netmsg cache
  io_uring: impose max limit on apoll cache
  io_uring: add abstraction around apoll cache
  io_uring: move apoll cache to poll.c
  io_uring: consolidate hash_locked io-wq handling
  io_uring: clear REQ_F_HASH_LOCKED on hash removal
  io_uring: don't race double poll setting REQ_F_ASYNC_DATA
  io_uring: don't miss setting REQ_F_DOUBLE_POLL
  io_uring: disable multishot recvmsg
  io_uring: only trace one of complete or overflow
  ...

1 files changed, 67 insertions, 2 deletions

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 0ad3da28d2fc..4c9b11e2e991 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -10,6 +10,7 @@
 
 #include <linux/fs.h>
 #include <linux/types.h>
+#include <linux/time_types.h>
 
 /*
  * IO submission data structure (Submission Queue Entry)
@@ -50,6 +51,7 @@ struct io_uring_sqe {
 		__u32		unlink_flags;
 		__u32		hardlink_flags;
 		__u32		xattr_flags;
+		__u32		msg_ring_flags;
 	};
 	__u64	user_data;	/* data to be passed back at completion time */
 	/* pack this to avoid bogus arm OABI complaints */
@@ -140,9 +142,12 @@ enum {
  * IORING_SQ_TASKRUN in the sq ring flags. Not valid with COOP_TASKRUN.
  */
 #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 */
+/*
+ * Only one task is allowed to submit requests
+ */
+#define IORING_SETUP_SINGLE_ISSUER	(1U << 12)
 
 enum io_uring_op {
 	IORING_OP_NOP,
@@ -229,10 +234,13 @@ enum io_uring_op {
  *
  * IORING_POLL_UPDATE		Update existing poll request, matching
  *				sqe->addr as the old user_data field.
+ *
+ * IORING_POLL_LEVEL		Level triggered poll.
  */
 #define IORING_POLL_ADD_MULTI	(1U << 0)
 #define IORING_POLL_UPDATE_EVENTS	(1U << 1)
 #define IORING_POLL_UPDATE_USER_DATA	(1U << 2)
+#define IORING_POLL_ADD_LEVEL		(1U << 3)
 
 /*
  * ASYNC_CANCEL flags.
@@ -241,10 +249,12 @@ enum io_uring_op {
  * IORING_ASYNC_CANCEL_FD	Key off 'fd' for cancelation rather than the
  *				request 'user_data'
  * IORING_ASYNC_CANCEL_ANY	Match any request
+ * IORING_ASYNC_CANCEL_FD_FIXED	'fd' passed in is a fixed descriptor
  */
 #define IORING_ASYNC_CANCEL_ALL	(1U << 0)
 #define IORING_ASYNC_CANCEL_FD	(1U << 1)
 #define IORING_ASYNC_CANCEL_ANY	(1U << 2)
+#define IORING_ASYNC_CANCEL_FD_FIXED	(1U << 3)
 
 /*
  * send/sendmsg and recv/recvmsg flags (sqe->ioprio)
@@ -253,8 +263,13 @@ enum io_uring_op {
  *				or receive and arm poll if that yields an
  *				-EAGAIN result, arm poll upfront and skip
  *				the initial transfer attempt.
+ *
+ * IORING_RECV_MULTISHOT	Multishot recv. Sets IORING_CQE_F_MORE if
+ *				the handler will continue to report
+ *				CQEs on behalf of the same SQE.
  */
 #define IORING_RECVSEND_POLL_FIRST	(1U << 0)
+#define IORING_RECV_MULTISHOT	(1U << 1)
 
 /*
  * accept flags stored in sqe->ioprio
@@ -262,6 +277,22 @@ enum io_uring_op {
 #define IORING_ACCEPT_MULTISHOT	(1U << 0)
 
 /*
+ * IORING_OP_MSG_RING command types, stored in sqe->addr
+ */
+enum {
+	IORING_MSG_DATA,	/* pass sqe->len as 'res' and off as user_data */
+	IORING_MSG_SEND_FD,	/* send a registered fd to another ring */
+};
+
+/*
+ * IORING_OP_MSG_RING flags (sqe->msg_ring_flags)
+ *
+ * IORING_MSG_RING_CQE_SKIP	Don't post a CQE to the target ring. Not
+ *				applicable for IORING_MSG_DATA, obviously.
+ */
+#define IORING_MSG_RING_CQE_SKIP	(1U << 0)
+
+/*
  * IO completion data structure (Completion Queue Entry)
  */
 struct io_uring_cqe {
@@ -420,6 +451,12 @@ enum {
 	IORING_REGISTER_PBUF_RING		= 22,
 	IORING_UNREGISTER_PBUF_RING		= 23,
 
+	/* sync cancelation API */
+	IORING_REGISTER_SYNC_CANCEL		= 24,
+
+	/* register a range of fixed file slots for automatic slot allocation */
+	IORING_REGISTER_FILE_ALLOC_RANGE	= 25,
+
 	/* this goes last */
 	IORING_REGISTER_LAST
 };
@@ -483,7 +520,7 @@ struct io_uring_probe {
 	__u8 ops_len;	/* length of ops[] array below */
 	__u16 resv;
 	__u32 resv2[3];
-	struct io_uring_probe_op ops[0];
+	struct io_uring_probe_op ops[];
 };
 
 struct io_uring_restriction {
@@ -555,4 +592,32 @@ struct io_uring_getevents_arg {
 	__u64	ts;
 };
 
+/*
+ * Argument for IORING_REGISTER_SYNC_CANCEL
+ */
+struct io_uring_sync_cancel_reg {
+	__u64				addr;
+	__s32				fd;
+	__u32				flags;
+	struct __kernel_timespec	timeout;
+	__u64				pad[4];
+};
+
+/*
+ * Argument for IORING_REGISTER_FILE_ALLOC_RANGE
+ * The range is specified as [off, off + len)
+ */
+struct io_uring_file_index_range {
+	__u32	off;
+	__u32	len;
+	__u64	resv;
+};
+
+struct io_uring_recvmsg_out {
+	__u32 namelen;
+	__u32 controllen;
+	__u32 payloadlen;
+	__u32 flags;
+};
+
 #endif