Merge branch 'io_uring-6.18' into for-6.19/io_uring

Merge 6.18-rc io_uring fixes, as certain coming changes depend on some
of these.

* io_uring-6.18:
  io_uring/rsrc: don't use blk_rq_nr_phys_segments() as number of bvecs
  io_uring/query: return number of available queries
  io_uring/rw: ensure allocated iovec gets cleared for early failure
  io_uring: fix regbuf vector size truncation
  io_uring: fix types for region size calulation
  io_uring/zcrx: remove sync refill uapi
  io_uring: fix buffer auto-commit for multishot uring_cmd
  io_uring: correct __must_hold annotation in io_install_fixed_file
  io_uring zcrx: add MAINTAINERS entry
  io_uring: Fix code indentation error
  io_uring/sqpoll: be smarter on when to update the stime usage
  io_uring/sqpoll: switch away from getrusage() for CPU accounting
  io_uring: fix incorrect unlikely() usage in io_waitid_prep()

Signed-off-by: Jens Axboe <axboe@kernel.dk>

Author: axboe

MAINTAINERS

@@ -13111,6 +13111,15 @@ F:	include/uapi/linux/io_uring.h
 F:	include/uapi/linux/io_uring/
 F:	io_uring/
 
+IO_URING ZCRX
+M:	Pavel Begunkov <asml.silence@gmail.com>
+L:	io-uring@vger.kernel.org
+L:	netdev@vger.kernel.org
+T:	git https://github.com/isilence/linux.git zcrx/for-next
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux.git
+S:	Maintained
+F:	io_uring/zcrx.*
+
 IPMI SUBSYSTEM
 M:	Corey Minyard <corey@minyard.net>
 L:	openipmi-developer@lists.sourceforge.net (moderated for non-subscribers)

include/uapi/linux/io_uring.h

@@ -697,9 +697,6 @@ enum io_uring_register_op {
 	/* query various aspects of io_uring, see linux/io_uring/query.h */
 	IORING_REGISTER_QUERY			= 35,
 
-	/* return zcrx buffers back into circulation */
-	IORING_REGISTER_ZCRX_REFILL		= 36,
-
 	/* this goes last */
 	IORING_REGISTER_LAST,
 
@@ -1081,15 +1078,6 @@ struct io_uring_zcrx_ifq_reg {
 	__u64	__resv[3];
 };
 
-struct io_uring_zcrx_sync_refill {
-	__u32		zcrx_id;
-	/* the number of entries to return */
-	__u32		nr_entries;
-	/* pointer to an array of struct io_uring_zcrx_rqe */
-	__u64		rqes;
-	__u64		__resv[2];
-};
-
 #ifdef __cplusplus
 }
 #endif

include/uapi/linux/io_uring/query.h

@@ -36,6 +36,9 @@ struct io_uring_query_opcode {
 	__u64	enter_flags;
 	/* Bitmask of all supported IOSQE_* flags */
 	__u64	sqe_flags;
+	/* The number of available query opcodes */
+	__u32	nr_query_opcodes;
+	__u32	__pad;
 };
 
 #endif

io_uring/fdinfo.c

@@ -61,7 +61,6 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
 {
 	struct io_overflow_cqe *ocqe;
 	struct io_rings *r = ctx->rings;
-	struct rusage sq_usage;
 	unsigned int sq_mask = ctx->sq_entries - 1, cq_mask = ctx->cq_entries - 1;
 	unsigned int sq_head = READ_ONCE(r->sq.head);
 	unsigned int sq_tail = READ_ONCE(r->sq.tail);
@@ -179,14 +178,15 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
 		 * thread termination.
 		 */
 		if (tsk) {
+			u64 usec;
+
 			get_task_struct(tsk);
 			rcu_read_unlock();
-			getrusage(tsk, RUSAGE_SELF, &sq_usage);
+			usec = io_sq_cpu_usec(tsk);
 			put_task_struct(tsk);
 			sq_pid = sq->task_pid;
 			sq_cpu = sq->sq_cpu;
-			sq_total_time = (sq_usage.ru_stime.tv_sec * 1000000
-					 + sq_usage.ru_stime.tv_usec);
+			sq_total_time = usec;
 			sq_work_time = sq->work_time;
 		} else {
 			rcu_read_unlock();

io_uring/filetable.c

@@ -57,7 +57,7 @@ void io_free_file_tables(struct io_ring_ctx *ctx, struct io_file_table *table)
 
 static int io_install_fixed_file(struct io_ring_ctx *ctx, struct file *file,
 				 u32 slot_index)
-	__must_hold(&req->ctx->uring_lock)
+	__must_hold(&ctx->uring_lock)
 {
 	struct io_rsrc_node *node;
 

io_uring/io_uring.c

@@ -846,7 +846,7 @@ static inline struct io_cqe io_init_cqe(u64 user_data, s32 res, u32 cflags)
 }
 
 static __cold void io_cqe_overflow(struct io_ring_ctx *ctx, struct io_cqe *cqe,
-			           struct io_big_cqe *big_cqe)
+				   struct io_big_cqe *big_cqe)
 {
 	struct io_overflow_cqe *ocqe;
 

io_uring/kbuf.c

@@ -155,6 +155,27 @@ static int io_provided_buffers_select(struct io_kiocb *req, size_t *len,
 	return 1;
 }
 
+static bool io_should_commit(struct io_kiocb *req, unsigned int issue_flags)
+{
+	/*
+	* If we came in unlocked, we have no choice but to consume the
+	* buffer here, otherwise nothing ensures that the buffer won't
+	* get used by others. This does mean it'll be pinned until the
+	* IO completes, coming in unlocked means we're being called from
+	* io-wq context and there may be further retries in async hybrid
+	* mode. For the locked case, the caller must call commit when
+	* the transfer completes (or if we get -EAGAIN and must poll of
+	* retry).
+	*/
+	if (issue_flags & IO_URING_F_UNLOCKED)
+		return true;
+
+	/* uring_cmd commits kbuf upfront, no need to auto-commit */
+	if (!io_file_can_poll(req) && req->opcode != IORING_OP_URING_CMD)
+		return true;
+	return false;
+}
+
 static struct io_br_sel io_ring_buffer_select(struct io_kiocb *req, size_t *len,
 					      struct io_buffer_list *bl,
 					      unsigned int issue_flags)
@@ -181,17 +202,7 @@ static struct io_br_sel io_ring_buffer_select(struct io_kiocb *req, size_t *len,
 	sel.buf_list = bl;
 	sel.addr = u64_to_user_ptr(buf->addr);
 
-	if (issue_flags & IO_URING_F_UNLOCKED || !io_file_can_poll(req)) {
-		/*
-		 * If we came in unlocked, we have no choice but to consume the
-		 * buffer here, otherwise nothing ensures that the buffer won't
-		 * get used by others. This does mean it'll be pinned until the
-		 * IO completes, coming in unlocked means we're being called from
-		 * io-wq context and there may be further retries in async hybrid
-		 * mode. For the locked case, the caller must call commit when
-		 * the transfer completes (or if we get -EAGAIN and must poll of
-		 * retry).
-		 */
+	if (io_should_commit(req, issue_flags)) {
 		io_kbuf_commit(req, sel.buf_list, *len, 1);
 		sel.buf_list = NULL;
 	}

io_uring/net.c

@@ -383,7 +383,7 @@ static int io_send_setup(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		return 0;
 
 	if (sr->flags & IORING_SEND_VECTORIZED)
-               return io_net_import_vec(req, kmsg, sr->buf, sr->len, ITER_SOURCE);
+		return io_net_import_vec(req, kmsg, sr->buf, sr->len, ITER_SOURCE);
 
 	return import_ubuf(ITER_SOURCE, sr->buf, sr->len, &kmsg->msg.msg_iter);
 }

io_uring/query.c

@@ -22,6 +22,8 @@ static ssize_t io_query_ops(union io_query_data *data)
 	e->ring_setup_flags = IORING_SETUP_FLAGS;
 	e->enter_flags = IORING_ENTER_FLAGS;
 	e->sqe_flags = SQE_VALID_FLAGS;
+	e->nr_query_opcodes = __IO_URING_QUERY_MAX;
+	e->__pad = 0;
 	return sizeof(*e);
 }
 

io_uring/register.c

@@ -826,9 +826,6 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 	case IORING_REGISTER_QUERY:
 		ret = io_query(ctx, arg, nr_args);
 		break;
-	case IORING_REGISTER_ZCRX_REFILL:
-		ret = io_zcrx_return_bufs(ctx, arg, nr_args);
-		break;
 	default:
 		ret = -EINVAL;
 		break;