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
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
|
// SPDX-License-Identifier: GPL-2.0
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/file.h>
#include <linux/slab.h>
#include <linux/nospec.h>
#include <linux/io_uring.h>
#include <uapi/linux/io_uring.h>
#include "io_uring.h"
#include "rsrc.h"
#include "filetable.h"
#include "alloc_cache.h"
#include "msg_ring.h"
/* All valid masks for MSG_RING */
#define IORING_MSG_RING_MASK (IORING_MSG_RING_CQE_SKIP | \
IORING_MSG_RING_FLAGS_PASS)
struct io_msg {
struct file *file;
struct file *src_file;
struct callback_head tw;
u64 user_data;
u32 len;
u32 cmd;
u32 src_fd;
union {
u32 dst_fd;
u32 cqe_flags;
};
u32 flags;
};
static void io_double_unlock_ctx(struct io_ring_ctx *octx)
{
mutex_unlock(&octx->uring_lock);
}
static int io_double_lock_ctx(struct io_ring_ctx *octx,
unsigned int issue_flags)
{
/*
* To ensure proper ordering between the two ctxs, we can only
* attempt a trylock on the target. If that fails and we already have
* the source ctx lock, punt to io-wq.
*/
if (!(issue_flags & IO_URING_F_UNLOCKED)) {
if (!mutex_trylock(&octx->uring_lock))
return -EAGAIN;
return 0;
}
mutex_lock(&octx->uring_lock);
return 0;
}
void io_msg_ring_cleanup(struct io_kiocb *req)
{
struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg);
if (WARN_ON_ONCE(!msg->src_file))
return;
fput(msg->src_file);
msg->src_file = NULL;
}
static inline bool io_msg_need_remote(struct io_ring_ctx *target_ctx)
{
return target_ctx->task_complete;
}
static void io_msg_tw_complete(struct io_kiocb *req, struct io_tw_state *ts)
{
struct io_ring_ctx *ctx = req->ctx;
io_add_aux_cqe(ctx, req->cqe.user_data, req->cqe.res, req->cqe.flags);
if (spin_trylock(&ctx->msg_lock)) {
if (io_alloc_cache_put(&ctx->msg_cache, req))
req = NULL;
spin_unlock(&ctx->msg_lock);
}
if (req)
kfree(req);
percpu_ref_put(&ctx->refs);
}
static void io_msg_remote_post(struct io_ring_ctx *ctx, struct io_kiocb *req,
int res, u32 cflags, u64 user_data)
{
req->cqe.user_data = user_data;
io_req_set_res(req, res, cflags);
percpu_ref_get(&ctx->refs);
req->ctx = ctx;
req->task = READ_ONCE(ctx->submitter_task);
req->io_task_work.func = io_msg_tw_complete;
io_req_task_work_add_remote(req, ctx, IOU_F_TWQ_LAZY_WAKE);
}
static struct io_kiocb *io_msg_get_kiocb(struct io_ring_ctx *ctx)
{
struct io_kiocb *req = NULL;
if (spin_trylock(&ctx->msg_lock)) {
req = io_alloc_cache_get(&ctx->msg_cache);
spin_unlock(&ctx->msg_lock);
}
if (req)
return req;
return kmem_cache_alloc(req_cachep, GFP_KERNEL | __GFP_NOWARN);
}
static int io_msg_data_remote(struct io_kiocb *req)
{
struct io_ring_ctx *target_ctx = req->file->private_data;
struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg);
struct io_kiocb *target;
u32 flags = 0;
target = io_msg_get_kiocb(req->ctx);
if (unlikely(!target))
return -ENOMEM;
if (msg->flags & IORING_MSG_RING_FLAGS_PASS)
flags = msg->cqe_flags;
io_msg_remote_post(target_ctx, target, msg->len, flags, msg->user_data);
return 0;
}
static int io_msg_ring_data(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_ring_ctx *target_ctx = req->file->private_data;
struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg);
u32 flags = 0;
int ret;
if (msg->src_fd || msg->flags & ~IORING_MSG_RING_FLAGS_PASS)
return -EINVAL;
if (!(msg->flags & IORING_MSG_RING_FLAGS_PASS) && msg->dst_fd)
return -EINVAL;
if (target_ctx->flags & IORING_SETUP_R_DISABLED)
return -EBADFD;
if (io_msg_need_remote(target_ctx))
return io_msg_data_remote(req);
if (msg->flags & IORING_MSG_RING_FLAGS_PASS)
flags = msg->cqe_flags;
ret = -EOVERFLOW;
if (target_ctx->flags & IORING_SETUP_IOPOLL) {
if (unlikely(io_double_lock_ctx(target_ctx, issue_flags)))
return -EAGAIN;
}
if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, flags))
ret = 0;
if (target_ctx->flags & IORING_SETUP_IOPOLL)
io_double_unlock_ctx(target_ctx);
return ret;
}
static struct file *io_msg_grab_file(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg);
struct io_ring_ctx *ctx = req->ctx;
struct file *file = NULL;
int idx = msg->src_fd;
io_ring_submit_lock(ctx, issue_flags);
if (likely(idx < ctx->nr_user_files)) {
idx = array_index_nospec(idx, ctx->nr_user_files);
file = io_file_from_index(&ctx->file_table, idx);
if (file)
get_file(file);
}
io_ring_submit_unlock(ctx, issue_flags);
return file;
}
static int io_msg_install_complete(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_ring_ctx *target_ctx = req->file->private_data;
struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg);
struct file *src_file = msg->src_file;
int ret;
if (unlikely(io_double_lock_ctx(target_ctx, issue_flags)))
return -EAGAIN;
ret = __io_fixed_fd_install(target_ctx, src_file, msg->dst_fd);
if (ret < 0)
goto out_unlock;
msg->src_file = NULL;
req->flags &= ~REQ_F_NEED_CLEANUP;
if (msg->flags & IORING_MSG_RING_CQE_SKIP)
goto out_unlock;
/*
* If this fails, the target still received the file descriptor but
* wasn't notified of the fact. This means that if this request
* completes with -EOVERFLOW, then the sender must ensure that a
* later IORING_OP_MSG_RING delivers the message.
*/
if (!io_post_aux_cqe(target_ctx, msg->user_data, ret, 0))
ret = -EOVERFLOW;
out_unlock:
io_double_unlock_ctx(target_ctx);
return ret;
}
static void io_msg_tw_fd_complete(struct callback_head *head)
{
struct io_msg *msg = container_of(head, struct io_msg, tw);
struct io_kiocb *req = cmd_to_io_kiocb(msg);
int ret = -EOWNERDEAD;
if (!(current->flags & PF_EXITING))
ret = io_msg_install_complete(req, IO_URING_F_UNLOCKED);
if (ret < 0)
req_set_fail(req);
io_req_queue_tw_complete(req, ret);
}
static int io_msg_fd_remote(struct io_kiocb *req)
{
struct io_ring_ctx *ctx = req->file->private_data;
struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg);
struct task_struct *task = READ_ONCE(ctx->submitter_task);
if (unlikely(!task))
return -EOWNERDEAD;
init_task_work(&msg->tw, io_msg_tw_fd_complete);
if (task_work_add(task, &msg->tw, TWA_SIGNAL))
return -EOWNERDEAD;
return IOU_ISSUE_SKIP_COMPLETE;
}
static int io_msg_send_fd(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_ring_ctx *target_ctx = req->file->private_data;
struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg);
struct io_ring_ctx *ctx = req->ctx;
struct file *src_file = msg->src_file;
if (msg->len)
return -EINVAL;
if (target_ctx == ctx)
return -EINVAL;
if (target_ctx->flags & IORING_SETUP_R_DISABLED)
return -EBADFD;
if (!src_file) {
src_file = io_msg_grab_file(req, issue_flags);
if (!src_file)
return -EBADF;
msg->src_file = src_file;
req->flags |= REQ_F_NEED_CLEANUP;
}
if (io_msg_need_remote(target_ctx))
return io_msg_fd_remote(req);
return io_msg_install_complete(req, issue_flags);
}
int io_msg_ring_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg);
if (unlikely(sqe->buf_index || sqe->personality))
return -EINVAL;
msg->src_file = NULL;
msg->user_data = READ_ONCE(sqe->off);
msg->len = READ_ONCE(sqe->len);
msg->cmd = READ_ONCE(sqe->addr);
msg->src_fd = READ_ONCE(sqe->addr3);
msg->dst_fd = READ_ONCE(sqe->file_index);
msg->flags = READ_ONCE(sqe->msg_ring_flags);
if (msg->flags & ~IORING_MSG_RING_MASK)
return -EINVAL;
return 0;
}
int io_msg_ring(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg);
int ret;
ret = -EBADFD;
if (!io_is_uring_fops(req->file))
goto done;
switch (msg->cmd) {
case IORING_MSG_DATA:
ret = io_msg_ring_data(req, issue_flags);
break;
case IORING_MSG_SEND_FD:
ret = io_msg_send_fd(req, issue_flags);
break;
default:
ret = -EINVAL;
break;
}
done:
if (ret < 0) {
if (ret == -EAGAIN || ret == IOU_ISSUE_SKIP_COMPLETE)
return ret;
req_set_fail(req);
}
io_req_set_res(req, ret, 0);
return IOU_OK;
}
void io_msg_cache_free(const void *entry)
{
struct io_kiocb *req = (struct io_kiocb *) entry;
kmem_cache_free(req_cachep, req);
}
|
