1 files changed, 145 insertions, 112 deletions

diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
index c33fca585dde..929cad6ee326 100644
--- a/io_uring/uring_cmd.c
+++ b/io_uring/uring_cmd.c
@@ -7,12 +7,78 @@
 #include <linux/nospec.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"
 
+void io_cmd_cache_free(const void *entry)
+{
+	struct io_async_cmd *ac = (struct io_async_cmd *)entry;
+
+	io_vec_free(&ac->vec);
+	kfree(ac);
+}
+
+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;
+
+	io_alloc_cache_vec_kasan(&ac->vec);
+	if (ac->vec.nr > IO_VEC_CACHE_SOFT_CAP)
+		io_vec_free(&ac->vec);
+
+	if (io_alloc_cache_put(&req->ctx->cmd_cache, cache)) {
+		ioucmd->sqe = NULL;
+		req->async_data = NULL;
+		req->flags &= ~(REQ_F_ASYNC_DATA|REQ_F_NEED_CLEANUP);
+	}
+}
+
+void io_uring_cmd_cleanup(struct io_kiocb *req)
+{
+	io_req_uring_cleanup(req, 0);
+}
+
+bool io_uring_try_cancel_uring_cmd(struct io_ring_ctx *ctx,
+				   struct io_uring_task *tctx, bool cancel_all)
+{
+	struct hlist_node *tmp;
+	struct io_kiocb *req;
+	bool ret = false;
+
+	lockdep_assert_held(&ctx->uring_lock);
+
+	hlist_for_each_entry_safe(req, tmp, &ctx->cancelable_uring_cmd,
+			hash_node) {
+		struct io_uring_cmd *cmd = io_kiocb_to_cmd(req,
+				struct io_uring_cmd);
+		struct file *file = req->file;
+
+		if (!cancel_all && req->tctx != tctx)
+			continue;
+
+		if (cmd->flags & IORING_URING_CMD_CANCELABLE) {
+			file->f_op->uring_cmd(cmd, IO_URING_F_CANCEL |
+						   IO_URING_F_COMPLETE_DEFER);
+			ret = true;
+		}
+	}
+	io_submit_flush_completions(ctx);
+	return ret;
+}
+
 static void io_uring_cmd_del_cancelable(struct io_uring_cmd *cmd,
 		unsigned int issue_flags)
 {
@@ -52,12 +118,16 @@ void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd,
 }
 EXPORT_SYMBOL_GPL(io_uring_cmd_mark_cancelable);
 
-static void io_uring_cmd_work(struct io_kiocb *req, struct io_tw_state *ts)
+static void io_uring_cmd_work(struct io_kiocb *req, io_tw_token_t tw)
 {
 	struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd);
-	unsigned issue_flags = ts->locked ? 0 : IO_URING_F_UNLOCKED;
+	unsigned int flags = IO_URING_F_COMPLETE_DEFER;
 
-	ioucmd->task_work_cb(ioucmd, issue_flags);
+	if (io_should_terminate_tw())
+		flags |= IO_URING_F_TASK_DEAD;
+
+	/* task_work executor checks the deffered list completion */
+	ioucmd->task_work_cb(ioucmd, flags);
 }
 
 void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd,
@@ -83,7 +153,7 @@ static inline void io_req_set_cqe32_extra(struct io_kiocb *req,
  * Called by consumers of io_uring_cmd, if they originally returned
  * -EIOCBQUEUED upon receiving the command.
  */
-void io_uring_cmd_done(struct io_uring_cmd *ioucmd, ssize_t ret, ssize_t res2,
+void io_uring_cmd_done(struct io_uring_cmd *ioucmd, ssize_t ret, u64 res2,
 		       unsigned issue_flags)
 {
 	struct io_kiocb *req = cmd_to_io_kiocb(ioucmd);
@@ -96,24 +166,44 @@ void io_uring_cmd_done(struct io_uring_cmd *ioucmd, ssize_t ret, ssize_t res2,
 	io_req_set_res(req, ret, 0);
 	if (req->ctx->flags & IORING_SETUP_CQE32)
 		io_req_set_cqe32_extra(req, res2, 0);
+	io_req_uring_cleanup(req, issue_flags);
 	if (req->ctx->flags & IORING_SETUP_IOPOLL) {
 		/* order with io_iopoll_req_issued() checking ->iopoll_complete */
 		smp_store_release(&req->iopoll_completed, 1);
+	} else if (issue_flags & IO_URING_F_COMPLETE_DEFER) {
+		if (WARN_ON_ONCE(issue_flags & IO_URING_F_UNLOCKED))
+			return;
+		io_req_complete_defer(req);
 	} else {
-		struct io_tw_state ts = {
-			.locked = !(issue_flags & IO_URING_F_UNLOCKED),
-		};
-		io_req_task_complete(req, &ts);
+		req->io_task_work.func = io_req_task_complete;
+		io_req_task_work_add(req);
 	}
 }
 EXPORT_SYMBOL_GPL(io_uring_cmd_done);
 
-int io_uring_cmd_prep_async(struct io_kiocb *req)
+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);
-
-	memcpy(req->async_data, ioucmd->sqe, uring_sqe_size(req->ctx));
-	ioucmd->sqe = req->async_data;
+	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;
 }
 
@@ -128,20 +218,12 @@ int io_uring_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	if (ioucmd->flags & ~IORING_URING_CMD_MASK)
 		return -EINVAL;
 
-	if (ioucmd->flags & IORING_URING_CMD_FIXED) {
-		struct io_ring_ctx *ctx = req->ctx;
-		u16 index;
-
+	if (ioucmd->flags & IORING_URING_CMD_FIXED)
 		req->buf_index = READ_ONCE(sqe->buf_index);
-		if (unlikely(req->buf_index >= ctx->nr_user_bufs))
-			return -EFAULT;
-		index = array_index_nospec(req->buf_index, ctx->nr_user_bufs);
-		req->imu = ctx->user_bufs[index];
-		io_req_set_rsrc_node(req, ctx, 0);
-	}
-	ioucmd->sqe = sqe;
+
 	ioucmd->cmd_op = READ_ONCE(sqe->cmd_op);
-	return 0;
+
+	return io_uring_cmd_prep_setup(req, sqe);
 }
 
 int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags)
@@ -162,118 +244,69 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags)
 		issue_flags |= IO_URING_F_SQE128;
 	if (ctx->flags & IORING_SETUP_CQE32)
 		issue_flags |= IO_URING_F_CQE32;
-	if (ctx->compat)
+	if (io_is_compat(ctx))
 		issue_flags |= IO_URING_F_COMPAT;
 	if (ctx->flags & IORING_SETUP_IOPOLL) {
 		if (!file->f_op->uring_cmd_iopoll)
 			return -EOPNOTSUPP;
 		issue_flags |= IO_URING_F_IOPOLL;
 		req->iopoll_completed = 0;
-	}
-
-	ret = file->f_op->uring_cmd(ioucmd, issue_flags);
-	if (ret == -EAGAIN) {
-		if (!req_has_async_data(req)) {
-			if (io_alloc_async_data(req))
-				return -ENOMEM;
-			io_uring_cmd_prep_async(req);
+		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();
 		}
-		return -EAGAIN;
 	}
 
-	if (ret != -EIOCBQUEUED) {
-		if (ret < 0)
-			req_set_fail(req);
-		io_req_set_res(req, ret, 0);
+	ret = file->f_op->uring_cmd(ioucmd, issue_flags);
+	if (ret == -EAGAIN || ret == -EIOCBQUEUED)
 		return ret;
-	}
-
-	return IOU_ISSUE_SKIP_COMPLETE;
+	if (ret < 0)
+		req_set_fail(req);
+	io_req_uring_cleanup(req, issue_flags);
+	io_req_set_res(req, ret, 0);
+	return IOU_COMPLETE;
 }
 
 int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
-			      struct iov_iter *iter, void *ioucmd)
+			      struct iov_iter *iter,
+			      struct io_uring_cmd *ioucmd,
+			      unsigned int issue_flags)
 {
 	struct io_kiocb *req = cmd_to_io_kiocb(ioucmd);
 
-	return io_import_fixed(rw, iter, req->imu, ubuf, len);
+	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);
 
-static inline int io_uring_cmd_getsockopt(struct socket *sock,
-					  struct io_uring_cmd *cmd,
-					  unsigned int issue_flags)
+int io_uring_cmd_import_fixed_vec(struct io_uring_cmd *ioucmd,
+				  const struct iovec __user *uvec,
+				  size_t uvec_segs,
+				  int ddir, struct iov_iter *iter,
+				  unsigned issue_flags)
 {
-	bool compat = !!(issue_flags & IO_URING_F_COMPAT);
-	int optlen, optname, level, err;
-	void __user *optval;
-
-	level = READ_ONCE(cmd->sqe->level);
-	if (level != SOL_SOCKET)
-		return -EOPNOTSUPP;
-
-	optval = u64_to_user_ptr(READ_ONCE(cmd->sqe->optval));
-	optname = READ_ONCE(cmd->sqe->optname);
-	optlen = READ_ONCE(cmd->sqe->optlen);
+	struct io_kiocb *req = cmd_to_io_kiocb(ioucmd);
+	struct io_async_cmd *ac = req->async_data;
+	int ret;
 
-	err = do_sock_getsockopt(sock, compat, level, optname,
-				 USER_SOCKPTR(optval),
-				 KERNEL_SOCKPTR(&optlen));
-	if (err)
-		return err;
+	if (WARN_ON_ONCE(!(ioucmd->flags & IORING_URING_CMD_FIXED)))
+		return -EINVAL;
 
-	/* On success, return optlen */
-	return optlen;
-}
+	ret = io_prep_reg_iovec(req, &ac->vec, uvec, uvec_segs);
+	if (ret)
+		return ret;
 
-static inline int io_uring_cmd_setsockopt(struct socket *sock,
-					  struct io_uring_cmd *cmd,
-					  unsigned int issue_flags)
-{
-	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(cmd->sqe->optval));
-	optname = READ_ONCE(cmd->sqe->optname);
-	optlen = READ_ONCE(cmd->sqe->optlen);
-	level = READ_ONCE(cmd->sqe->level);
-	optval_s = USER_SOCKPTR(optval);
-
-	return do_sock_setsockopt(sock, compat, level, optname, optval_s,
-				  optlen);
+	return io_import_reg_vec(ddir, iter, req, &ac->vec, uvec_segs,
+				 issue_flags);
 }
+EXPORT_SYMBOL_GPL(io_uring_cmd_import_fixed_vec);
 
-#if defined(CONFIG_NET)
-int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags)
+void io_uring_cmd_issue_blocking(struct io_uring_cmd *ioucmd)
 {
-	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(ioucmd);
 
-	switch (cmd->sqe->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;
-	}
+	io_req_queue_iowq(req);
 }
-EXPORT_SYMBOL_GPL(io_uring_cmd_sock);
-#endif