1 files changed, 60 insertions, 109 deletions

diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
index a9ea7d29cdd9..053bac89b6c0 100644
--- a/io_uring/uring_cmd.c
+++ b/io_uring/uring_cmd.c
@@ -3,18 +3,16 @@
 #include <linux/errno.h>
 #include <linux/file.h>
 #include <linux/io_uring/cmd.h>
-#include <linux/io_uring/net.h>
 #include <linux/security.h>
 #include <linux/nospec.h>
-#include <net/sock.h>
 
 #include <uapi/linux/io_uring.h>
-#include <asm/ioctls.h>
 
 #include "io_uring.h"
 #include "alloc_cache.h"
 #include "rsrc.h"
 #include "uring_cmd.h"
+#include "poll.h"
 
 void io_cmd_cache_free(const void *entry)
 {
@@ -28,12 +26,6 @@ static void io_req_uring_cleanup(struct io_kiocb *req, unsigned int issue_flags)
 {
 	struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd);
 	struct io_async_cmd *ac = req->async_data;
-	struct io_uring_cmd_data *cache = &ac->data;
-
-	if (cache->op_data) {
-		kfree(cache->op_data);
-		cache->op_data = NULL;
-	}
 
 	if (issue_flags & IO_URING_F_UNLOCKED)
 		return;
@@ -42,7 +34,7 @@ static void io_req_uring_cleanup(struct io_kiocb *req, unsigned int issue_flags)
 	if (ac->vec.nr > IO_VEC_CACHE_SOFT_CAP)
 		io_vec_free(&ac->vec);
 
-	if (io_alloc_cache_put(&req->ctx->cmd_cache, cache)) {
+	if (io_alloc_cache_put(&req->ctx->cmd_cache, ac)) {
 		ioucmd->sqe = NULL;
 		req->async_data = NULL;
 		req->flags &= ~(REQ_F_ASYNC_DATA|REQ_F_NEED_CLEANUP);
@@ -139,6 +131,9 @@ void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd,
 {
 	struct io_kiocb *req = cmd_to_io_kiocb(ioucmd);
 
+	if (WARN_ON_ONCE(req->flags & REQ_F_APOLL_MULTISHOT))
+		return;
+
 	ioucmd->task_work_cb = task_work_cb;
 	req->io_task_work.func = io_uring_cmd_work;
 	__io_req_task_work_add(req, flags);
@@ -161,6 +156,9 @@ void io_uring_cmd_done(struct io_uring_cmd *ioucmd, ssize_t ret, u64 res2,
 {
 	struct io_kiocb *req = cmd_to_io_kiocb(ioucmd);
 
+	if (WARN_ON_ONCE(req->flags & REQ_F_APOLL_MULTISHOT))
+		return;
+
 	io_uring_cmd_del_cancelable(ioucmd, issue_flags);
 
 	if (ret < 0)
@@ -184,35 +182,10 @@ void io_uring_cmd_done(struct io_uring_cmd *ioucmd, ssize_t ret, u64 res2,
 }
 EXPORT_SYMBOL_GPL(io_uring_cmd_done);
 
-static int io_uring_cmd_prep_setup(struct io_kiocb *req,
-				   const struct io_uring_sqe *sqe)
-{
-	struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd);
-	struct io_async_cmd *ac;
-
-	/* see io_uring_cmd_get_async_data() */
-	BUILD_BUG_ON(offsetof(struct io_async_cmd, data) != 0);
-
-	ac = io_uring_alloc_async_data(&req->ctx->cmd_cache, req);
-	if (!ac)
-		return -ENOMEM;
-	ac->data.op_data = NULL;
-
-	/*
-	 * Unconditionally cache the SQE for now - this is only needed for
-	 * requests that go async, but prep handlers must ensure that any
-	 * sqe data is stable beyond prep. Since uring_cmd is special in
-	 * that it doesn't read in per-op data, play it safe and ensure that
-	 * any SQE data is stable beyond prep. This can later get relaxed.
-	 */
-	memcpy(ac->sqes, sqe, uring_sqe_size(req->ctx));
-	ioucmd->sqe = ac->sqes;
-	return 0;
-}
-
 int io_uring_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd);
+	struct io_async_cmd *ac;
 
 	if (sqe->__pad1)
 		return -EINVAL;
@@ -226,7 +199,23 @@ int io_uring_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 
 	ioucmd->cmd_op = READ_ONCE(sqe->cmd_op);
 
-	return io_uring_cmd_prep_setup(req, sqe);
+	ac = io_uring_alloc_async_data(&req->ctx->cmd_cache, req);
+	if (!ac)
+		return -ENOMEM;
+	ioucmd->sqe = sqe;
+	return 0;
+}
+
+void io_uring_cmd_sqe_copy(struct io_kiocb *req)
+{
+	struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd);
+	struct io_async_cmd *ac = req->async_data;
+
+	/* Should not happen, as REQ_F_SQE_COPIED covers this */
+	if (WARN_ON_ONCE(ioucmd->sqe == ac->sqes))
+		return;
+	memcpy(ac->sqes, ioucmd->sqe, uring_sqe_size(req->ctx));
+	ioucmd->sqe = ac->sqes;
 }
 
 int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags)
@@ -254,16 +243,25 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags)
 			return -EOPNOTSUPP;
 		issue_flags |= IO_URING_F_IOPOLL;
 		req->iopoll_completed = 0;
+		if (ctx->flags & IORING_SETUP_HYBRID_IOPOLL) {
+			/* make sure every req only blocks once */
+			req->flags &= ~REQ_F_IOPOLL_STATE;
+			req->iopoll_start = ktime_get_ns();
+		}
 	}
 
 	ret = file->f_op->uring_cmd(ioucmd, issue_flags);
-	if (ret == -EAGAIN || ret == -EIOCBQUEUED)
+	if (ret == -EAGAIN) {
+		ioucmd->flags |= IORING_URING_CMD_REISSUE;
+		return ret;
+	}
+	if (ret == -EIOCBQUEUED)
 		return ret;
 	if (ret < 0)
 		req_set_fail(req);
 	io_req_uring_cleanup(req, issue_flags);
 	io_req_set_res(req, ret, 0);
-	return IOU_OK;
+	return IOU_COMPLETE;
 }
 
 int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
@@ -273,6 +271,9 @@ int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
 {
 	struct io_kiocb *req = cmd_to_io_kiocb(ioucmd);
 
+	if (WARN_ON_ONCE(!(ioucmd->flags & IORING_URING_CMD_FIXED)))
+		return -EINVAL;
+
 	return io_import_reg_buf(req, iter, ubuf, len, rw, issue_flags);
 }
 EXPORT_SYMBOL_GPL(io_uring_cmd_import_fixed);
@@ -287,6 +288,9 @@ int io_uring_cmd_import_fixed_vec(struct io_uring_cmd *ioucmd,
 	struct io_async_cmd *ac = req->async_data;
 	int ret;
 
+	if (WARN_ON_ONCE(!(ioucmd->flags & IORING_URING_CMD_FIXED)))
+		return -EINVAL;
+
 	ret = io_prep_reg_iovec(req, &ac->vec, uvec, uvec_segs);
 	if (ret)
 		return ret;
@@ -303,82 +307,29 @@ void io_uring_cmd_issue_blocking(struct io_uring_cmd *ioucmd)
 	io_req_queue_iowq(req);
 }
 
-static inline int io_uring_cmd_getsockopt(struct socket *sock,
-					  struct io_uring_cmd *cmd,
-					  unsigned int issue_flags)
+int io_cmd_poll_multishot(struct io_uring_cmd *cmd,
+			  unsigned int issue_flags, __poll_t mask)
 {
-	const struct io_uring_sqe *sqe = cmd->sqe;
-	bool compat = !!(issue_flags & IO_URING_F_COMPAT);
-	int optlen, optname, level, err;
-	void __user *optval;
-
-	level = READ_ONCE(sqe->level);
-	if (level != SOL_SOCKET)
-		return -EOPNOTSUPP;
-
-	optval = u64_to_user_ptr(READ_ONCE(sqe->optval));
-	optname = READ_ONCE(sqe->optname);
-	optlen = READ_ONCE(sqe->optlen);
+	struct io_kiocb *req = cmd_to_io_kiocb(cmd);
+	int ret;
 
-	err = do_sock_getsockopt(sock, compat, level, optname,
-				 USER_SOCKPTR(optval),
-				 KERNEL_SOCKPTR(&optlen));
-	if (err)
-		return err;
+	if (likely(req->flags & REQ_F_APOLL_MULTISHOT))
+		return 0;
 
-	/* On success, return optlen */
-	return optlen;
-}
+	req->flags |= REQ_F_APOLL_MULTISHOT;
+	mask &= ~EPOLLONESHOT;
 
-static inline int io_uring_cmd_setsockopt(struct socket *sock,
-					  struct io_uring_cmd *cmd,
-					  unsigned int issue_flags)
-{
-	const struct io_uring_sqe *sqe = cmd->sqe;
-	bool compat = !!(issue_flags & IO_URING_F_COMPAT);
-	int optname, optlen, level;
-	void __user *optval;
-	sockptr_t optval_s;
-
-	optval = u64_to_user_ptr(READ_ONCE(sqe->optval));
-	optname = READ_ONCE(sqe->optname);
-	optlen = READ_ONCE(sqe->optlen);
-	level = READ_ONCE(sqe->level);
-	optval_s = USER_SOCKPTR(optval);
-
-	return do_sock_setsockopt(sock, compat, level, optname, optval_s,
-				  optlen);
+	ret = io_arm_apoll(req, issue_flags, mask);
+	return ret == IO_APOLL_OK ? -EIOCBQUEUED : -ECANCELED;
 }
 
-#if defined(CONFIG_NET)
-int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags)
+bool io_uring_cmd_post_mshot_cqe32(struct io_uring_cmd *cmd,
+				   unsigned int issue_flags,
+				   struct io_uring_cqe cqe[2])
 {
-	struct socket *sock = cmd->file->private_data;
-	struct sock *sk = sock->sk;
-	struct proto *prot = READ_ONCE(sk->sk_prot);
-	int ret, arg = 0;
-
-	if (!prot || !prot->ioctl)
-		return -EOPNOTSUPP;
+	struct io_kiocb *req = cmd_to_io_kiocb(cmd);
 
-	switch (cmd->cmd_op) {
-	case SOCKET_URING_OP_SIOCINQ:
-		ret = prot->ioctl(sk, SIOCINQ, &arg);
-		if (ret)
-			return ret;
-		return arg;
-	case SOCKET_URING_OP_SIOCOUTQ:
-		ret = prot->ioctl(sk, SIOCOUTQ, &arg);
-		if (ret)
-			return ret;
-		return arg;
-	case SOCKET_URING_OP_GETSOCKOPT:
-		return io_uring_cmd_getsockopt(sock, cmd, issue_flags);
-	case SOCKET_URING_OP_SETSOCKOPT:
-		return io_uring_cmd_setsockopt(sock, cmd, issue_flags);
-	default:
-		return -EOPNOTSUPP;
-	}
+	if (WARN_ON_ONCE(!(issue_flags & IO_URING_F_MULTISHOT)))
+		return false;
+	return io_req_post_cqe32(req, cqe);
 }
-EXPORT_SYMBOL_GPL(io_uring_cmd_sock);
-#endif