summaryrefslogtreecommitdiffstats
path: root/io_uring/openclose.c
blob: 10ca57f5bd249522755db6ce5baf28cc83aca8a7 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
// SPDX-License-Identifier: GPL-2.0
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/fsnotify.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 "rsrc.h"
#include "openclose.h"

struct io_open {
	struct file			*file;
	int				dfd;
	u32				file_slot;
	struct filename			*filename;
	struct open_how			how;
	unsigned long			nofile;
};

struct io_close {
	struct file			*file;
	int				fd;
	u32				file_slot;
};

static bool io_openat_force_async(struct io_open *open)
{
	/*
	 * Don't bother trying for O_TRUNC, O_CREAT, or O_TMPFILE open,
	 * it'll always -EAGAIN
	 */
	return open->how.flags & (O_TRUNC | O_CREAT | O_TMPFILE);
}

static int __io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	struct io_open *open = io_kiocb_to_cmd(req, struct io_open);
	const char __user *fname;
	int ret;

	if (unlikely(sqe->buf_index))
		return -EINVAL;
	if (unlikely(req->flags & REQ_F_FIXED_FILE))
		return -EBADF;

	/* open.how should be already initialised */
	if (!(open->how.flags & O_PATH) && force_o_largefile())
		open->how.flags |= O_LARGEFILE;

	open->dfd = READ_ONCE(sqe->fd);
	fname = u64_to_user_ptr(READ_ONCE(sqe->addr));
	open->filename = getname(fname);
	if (IS_ERR(open->filename)) {
		ret = PTR_ERR(open->filename);
		open->filename = NULL;
		return ret;
	}

	open->file_slot = READ_ONCE(sqe->file_index);
	if (open->file_slot && (open->how.flags & O_CLOEXEC))
		return -EINVAL;

	open->nofile = rlimit(RLIMIT_NOFILE);
	req->flags |= REQ_F_NEED_CLEANUP;
	if (io_openat_force_async(open))
		req->flags |= REQ_F_FORCE_ASYNC;
	return 0;
}

int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	struct io_open *open = io_kiocb_to_cmd(req, struct io_open);
	u64 mode = READ_ONCE(sqe->len);
	u64 flags = READ_ONCE(sqe->open_flags);

	open->how = build_open_how(flags, mode);
	return __io_openat_prep(req, sqe);
}

int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	struct io_open *open = io_kiocb_to_cmd(req, struct io_open);
	struct open_how __user *how;
	size_t len;
	int ret;

	how = u64_to_user_ptr(READ_ONCE(sqe->addr2));
	len = READ_ONCE(sqe->len);
	if (len < OPEN_HOW_SIZE_VER0)
		return -EINVAL;

	ret = copy_struct_from_user(&open->how, sizeof(open->how), how, len);
	if (ret)
		return ret;

	return __io_openat_prep(req, sqe);
}

int io_openat2(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_open *open = io_kiocb_to_cmd(req, struct io_open);
	struct open_flags op;
	struct file *file;
	bool resolve_nonblock, nonblock_set;
	bool fixed = !!open->file_slot;
	int ret;

	ret = build_open_flags(&open->how, &op);
	if (ret)
		goto err;
	nonblock_set = op.open_flag & O_NONBLOCK;
	resolve_nonblock = open->how.resolve & RESOLVE_CACHED;
	if (issue_flags & IO_URING_F_NONBLOCK) {
		WARN_ON_ONCE(io_openat_force_async(open));
		op.lookup_flags |= LOOKUP_CACHED;
		op.open_flag |= O_NONBLOCK;
	}

	if (!fixed) {
		ret = __get_unused_fd_flags(open->how.flags, open->nofile);
		if (ret < 0)
			goto err;
	}

	file = do_filp_open(open->dfd, open->filename, &op);
	if (IS_ERR(file)) {
		/*
		 * We could hang on to this 'fd' on retrying, but seems like
		 * marginal gain for something that is now known to be a slower
		 * path. So just put it, and we'll get a new one when we retry.
		 */
		if (!fixed)
			put_unused_fd(ret);

		ret = PTR_ERR(file);
		/* only retry if RESOLVE_CACHED wasn't already set by application */
		if (ret == -EAGAIN &&
		    (!resolve_nonblock && (issue_flags & IO_URING_F_NONBLOCK)))
			return -EAGAIN;
		goto err;
	}

	if ((issue_flags & IO_URING_F_NONBLOCK) && !nonblock_set)
		file->f_flags &= ~O_NONBLOCK;

	if (!fixed)
		fd_install(ret, file);
	else
		ret = io_fixed_fd_install(req, issue_flags, file,
						open->file_slot);
err:
	putname(open->filename);
	req->flags &= ~REQ_F_NEED_CLEANUP;
	if (ret < 0)
		req_set_fail(req);
	io_req_set_res(req, ret, 0);
	return IOU_OK;
}

int io_openat(struct io_kiocb *req, unsigned int issue_flags)
{
	return io_openat2(req, issue_flags);
}

void io_open_cleanup(struct io_kiocb *req)
{
	struct io_open *open = io_kiocb_to_cmd(req, struct io_open);

	if (open->filename)
		putname(open->filename);
}

int __io_close_fixed(struct io_ring_ctx *ctx, unsigned int issue_flags,
		     unsigned int offset)
{
	int ret;

	io_ring_submit_lock(ctx, issue_flags);
	ret = io_fixed_fd_remove(ctx, offset);
	io_ring_submit_unlock(ctx, issue_flags);

	return ret;
}

static inline int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_close *close = io_kiocb_to_cmd(req, struct io_close);

	return __io_close_fixed(req->ctx, issue_flags, close->file_slot - 1);
}

int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	struct io_close *close = io_kiocb_to_cmd(req, struct io_close);

	if (sqe->off || sqe->addr || sqe->len || sqe->rw_flags || sqe->buf_index)
		return -EINVAL;
	if (req->flags & REQ_F_FIXED_FILE)
		return -EBADF;

	close->fd = READ_ONCE(sqe->fd);
	close->file_slot = READ_ONCE(sqe->file_index);
	if (close->file_slot && close->fd)
		return -EINVAL;

	return 0;
}

int io_close(struct io_kiocb *req, unsigned int issue_flags)
{
	struct files_struct *files = current->files;
	struct io_close *close = io_kiocb_to_cmd(req, struct io_close);
	struct fdtable *fdt;
	struct file *file;
	int ret = -EBADF;

	if (close->file_slot) {
		ret = io_close_fixed(req, issue_flags);
		goto err;
	}

	spin_lock(&files->file_lock);
	fdt = files_fdtable(files);
	if (close->fd >= fdt->max_fds) {
		spin_unlock(&files->file_lock);
		goto err;
	}
	file = rcu_dereference_protected(fdt->fd[close->fd],
			lockdep_is_held(&files->file_lock));
	if (!file || io_is_uring_fops(file)) {
		spin_unlock(&files->file_lock);
		goto err;
	}

	/* if the file has a flush method, be safe and punt to async */
	if (file->f_op->flush && (issue_flags & IO_URING_F_NONBLOCK)) {
		spin_unlock(&files->file_lock);
		return -EAGAIN;
	}

	file = __close_fd_get_file(close->fd);
	spin_unlock(&files->file_lock);
	if (!file)
		goto err;

	/* No ->flush() or already async, safely close from here */
	ret = filp_close(file, current->files);
err:
	if (ret < 0)
		req_set_fail(req);
	io_req_set_res(req, ret, 0);
	return IOU_OK;
}