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, 293 insertions, 0 deletions

diff --git a/io_uring/fs.c b/io_uring/fs.c
new file mode 100644
index 000000000000..0de4f549bb7d
--- /dev/null
+++ b/io_uring/fs.c
@@ -0,0 +1,293 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/namei.h>
+#include <linux/io_uring.h>
+
+#include <uapi/linux/io_uring.h>
+
+#include "../fs/internal.h"
+
+#include "io_uring.h"
+#include "fs.h"
+
+struct io_rename {
+	struct file			*file;
+	int				old_dfd;
+	int				new_dfd;
+	struct filename			*oldpath;
+	struct filename			*newpath;
+	int				flags;
+};
+
+struct io_unlink {
+	struct file			*file;
+	int				dfd;
+	int				flags;
+	struct filename			*filename;
+};
+
+struct io_mkdir {
+	struct file			*file;
+	int				dfd;
+	umode_t				mode;
+	struct filename			*filename;
+};
+
+struct io_link {
+	struct file			*file;
+	int				old_dfd;
+	int				new_dfd;
+	struct filename			*oldpath;
+	struct filename			*newpath;
+	int				flags;
+};
+
+int io_renameat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_rename *ren = io_kiocb_to_cmd(req);
+	const char __user *oldf, *newf;
+
+	if (sqe->buf_index || sqe->splice_fd_in)
+		return -EINVAL;
+	if (unlikely(req->flags & REQ_F_FIXED_FILE))
+		return -EBADF;
+
+	ren->old_dfd = READ_ONCE(sqe->fd);
+	oldf = u64_to_user_ptr(READ_ONCE(sqe->addr));
+	newf = u64_to_user_ptr(READ_ONCE(sqe->addr2));
+	ren->new_dfd = READ_ONCE(sqe->len);
+	ren->flags = READ_ONCE(sqe->rename_flags);
+
+	ren->oldpath = getname(oldf);
+	if (IS_ERR(ren->oldpath))
+		return PTR_ERR(ren->oldpath);
+
+	ren->newpath = getname(newf);
+	if (IS_ERR(ren->newpath)) {
+		putname(ren->oldpath);
+		return PTR_ERR(ren->newpath);
+	}
+
+	req->flags |= REQ_F_NEED_CLEANUP;
+	return 0;
+}
+
+int io_renameat(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_rename *ren = io_kiocb_to_cmd(req);
+	int ret;
+
+	if (issue_flags & IO_URING_F_NONBLOCK)
+		return -EAGAIN;
+
+	ret = do_renameat2(ren->old_dfd, ren->oldpath, ren->new_dfd,
+				ren->newpath, ren->flags);
+
+	req->flags &= ~REQ_F_NEED_CLEANUP;
+	io_req_set_res(req, ret, 0);
+	return IOU_OK;
+}
+
+void io_renameat_cleanup(struct io_kiocb *req)
+{
+	struct io_rename *ren = io_kiocb_to_cmd(req);
+
+	putname(ren->oldpath);
+	putname(ren->newpath);
+}
+
+int io_unlinkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_unlink *un = io_kiocb_to_cmd(req);
+	const char __user *fname;
+
+	if (sqe->off || sqe->len || sqe->buf_index || sqe->splice_fd_in)
+		return -EINVAL;
+	if (unlikely(req->flags & REQ_F_FIXED_FILE))
+		return -EBADF;
+
+	un->dfd = READ_ONCE(sqe->fd);
+
+	un->flags = READ_ONCE(sqe->unlink_flags);
+	if (un->flags & ~AT_REMOVEDIR)
+		return -EINVAL;
+
+	fname = u64_to_user_ptr(READ_ONCE(sqe->addr));
+	un->filename = getname(fname);
+	if (IS_ERR(un->filename))
+		return PTR_ERR(un->filename);
+
+	req->flags |= REQ_F_NEED_CLEANUP;
+	return 0;
+}
+
+int io_unlinkat(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_unlink *un = io_kiocb_to_cmd(req);
+	int ret;
+
+	if (issue_flags & IO_URING_F_NONBLOCK)
+		return -EAGAIN;
+
+	if (un->flags & AT_REMOVEDIR)
+		ret = do_rmdir(un->dfd, un->filename);
+	else
+		ret = do_unlinkat(un->dfd, un->filename);
+
+	req->flags &= ~REQ_F_NEED_CLEANUP;
+	io_req_set_res(req, ret, 0);
+	return IOU_OK;
+}
+
+void io_unlinkat_cleanup(struct io_kiocb *req)
+{
+	struct io_unlink *ul = io_kiocb_to_cmd(req);
+
+	putname(ul->filename);
+}
+
+int io_mkdirat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_mkdir *mkd = io_kiocb_to_cmd(req);
+	const char __user *fname;
+
+	if (sqe->off || sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in)
+		return -EINVAL;
+	if (unlikely(req->flags & REQ_F_FIXED_FILE))
+		return -EBADF;
+
+	mkd->dfd = READ_ONCE(sqe->fd);
+	mkd->mode = READ_ONCE(sqe->len);
+
+	fname = u64_to_user_ptr(READ_ONCE(sqe->addr));
+	mkd->filename = getname(fname);
+	if (IS_ERR(mkd->filename))
+		return PTR_ERR(mkd->filename);
+
+	req->flags |= REQ_F_NEED_CLEANUP;
+	return 0;
+}
+
+int io_mkdirat(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_mkdir *mkd = io_kiocb_to_cmd(req);
+	int ret;
+
+	if (issue_flags & IO_URING_F_NONBLOCK)
+		return -EAGAIN;
+
+	ret = do_mkdirat(mkd->dfd, mkd->filename, mkd->mode);
+
+	req->flags &= ~REQ_F_NEED_CLEANUP;
+	io_req_set_res(req, ret, 0);
+	return IOU_OK;
+}
+
+void io_mkdirat_cleanup(struct io_kiocb *req)
+{
+	struct io_mkdir *md = io_kiocb_to_cmd(req);
+
+	putname(md->filename);
+}
+
+int io_symlinkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_link *sl = io_kiocb_to_cmd(req);
+	const char __user *oldpath, *newpath;
+
+	if (sqe->len || sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in)
+		return -EINVAL;
+	if (unlikely(req->flags & REQ_F_FIXED_FILE))
+		return -EBADF;
+
+	sl->new_dfd = READ_ONCE(sqe->fd);
+	oldpath = u64_to_user_ptr(READ_ONCE(sqe->addr));
+	newpath = u64_to_user_ptr(READ_ONCE(sqe->addr2));
+
+	sl->oldpath = getname(oldpath);
+	if (IS_ERR(sl->oldpath))
+		return PTR_ERR(sl->oldpath);
+
+	sl->newpath = getname(newpath);
+	if (IS_ERR(sl->newpath)) {
+		putname(sl->oldpath);
+		return PTR_ERR(sl->newpath);
+	}
+
+	req->flags |= REQ_F_NEED_CLEANUP;
+	return 0;
+}
+
+int io_symlinkat(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_link *sl = io_kiocb_to_cmd(req);
+	int ret;
+
+	if (issue_flags & IO_URING_F_NONBLOCK)
+		return -EAGAIN;
+
+	ret = do_symlinkat(sl->oldpath, sl->new_dfd, sl->newpath);
+
+	req->flags &= ~REQ_F_NEED_CLEANUP;
+	io_req_set_res(req, ret, 0);
+	return IOU_OK;
+}
+
+int io_linkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_link *lnk = io_kiocb_to_cmd(req);
+	const char __user *oldf, *newf;
+
+	if (sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in)
+		return -EINVAL;
+	if (unlikely(req->flags & REQ_F_FIXED_FILE))
+		return -EBADF;
+
+	lnk->old_dfd = READ_ONCE(sqe->fd);
+	lnk->new_dfd = READ_ONCE(sqe->len);
+	oldf = u64_to_user_ptr(READ_ONCE(sqe->addr));
+	newf = u64_to_user_ptr(READ_ONCE(sqe->addr2));
+	lnk->flags = READ_ONCE(sqe->hardlink_flags);
+
+	lnk->oldpath = getname(oldf);
+	if (IS_ERR(lnk->oldpath))
+		return PTR_ERR(lnk->oldpath);
+
+	lnk->newpath = getname(newf);
+	if (IS_ERR(lnk->newpath)) {
+		putname(lnk->oldpath);
+		return PTR_ERR(lnk->newpath);
+	}
+
+	req->flags |= REQ_F_NEED_CLEANUP;
+	return 0;
+}
+
+int io_linkat(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_link *lnk = io_kiocb_to_cmd(req);
+	int ret;
+
+	if (issue_flags & IO_URING_F_NONBLOCK)
+		return -EAGAIN;
+
+	ret = do_linkat(lnk->old_dfd, lnk->oldpath, lnk->new_dfd,
+				lnk->newpath, lnk->flags);
+
+	req->flags &= ~REQ_F_NEED_CLEANUP;
+	io_req_set_res(req, ret, 0);
+	return IOU_OK;
+}
+
+void io_link_cleanup(struct io_kiocb *req)
+{
+	struct io_link *sl = io_kiocb_to_cmd(req);
+
+	putname(sl->oldpath);
+	putname(sl->newpath);
+}