aboutsummaryrefslogtreecommitdiffstats
path: root/net/xdp/xdp_umem.c
blob: f729d79b8d91550b9fbc161af1bb728b29ced893 (plain) (blame)
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
326
327
328
329
330
331
332
333
334
335
336
// SPDX-License-Identifier: GPL-2.0
/* XDP user-space packet buffer
 * Copyright(c) 2018 Intel Corporation.
 */

#include <linux/init.h>
#include <linux/sched/mm.h>
#include <linux/sched/signal.h>
#include <linux/sched/task.h>
#include <linux/uaccess.h>
#include <linux/slab.h>
#include <linux/bpf.h>
#include <linux/mm.h>

#include "xdp_umem.h"
#include "xsk_queue.h"

#define XDP_UMEM_MIN_CHUNK_SIZE 2048

int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
			u32 queue_id, u16 flags)
{
	bool force_zc, force_copy;
	struct netdev_bpf bpf;
	int err;

	force_zc = flags & XDP_ZEROCOPY;
	force_copy = flags & XDP_COPY;

	if (force_zc && force_copy)
		return -EINVAL;

	if (force_copy)
		return 0;

	dev_hold(dev);

	if (dev->netdev_ops->ndo_bpf) {
		bpf.command = XDP_QUERY_XSK_UMEM;

		rtnl_lock();
		err = dev->netdev_ops->ndo_bpf(dev, &bpf);
		rtnl_unlock();

		if (err) {
			dev_put(dev);
			return force_zc ? -ENOTSUPP : 0;
		}

		bpf.command = XDP_SETUP_XSK_UMEM;
		bpf.xsk.umem = umem;
		bpf.xsk.queue_id = queue_id;

		rtnl_lock();
		err = dev->netdev_ops->ndo_bpf(dev, &bpf);
		rtnl_unlock();

		if (err) {
			dev_put(dev);
			return force_zc ? err : 0; /* fail or fallback */
		}

		umem->dev = dev;
		umem->queue_id = queue_id;
		umem->zc = true;
		return 0;
	}

	dev_put(dev);
	return force_zc ? -ENOTSUPP : 0; /* fail or fallback */
}

void xdp_umem_clear_dev(struct xdp_umem *umem)
{
	struct netdev_bpf bpf;
	int err;

	if (umem->dev) {
		bpf.command = XDP_SETUP_XSK_UMEM;
		bpf.xsk.umem = NULL;
		bpf.xsk.queue_id = umem->queue_id;

		rtnl_lock();
		err = umem->dev->netdev_ops->ndo_bpf(umem->dev, &bpf);
		rtnl_unlock();

		if (err)
			WARN(1, "failed to disable umem!\n");

		dev_put(umem->dev);
		umem->dev = NULL;
	}
}

static void xdp_umem_unpin_pages(struct xdp_umem *umem)
{
	unsigned int i;

	for (i = 0; i < umem->npgs; i++) {
		struct page *page = umem->pgs[i];

		set_page_dirty_lock(page);
		put_page(page);
	}

	kfree(umem->pgs);
	umem->pgs = NULL;
}

static void xdp_umem_unaccount_pages(struct xdp_umem *umem)
{
	atomic_long_sub(umem->npgs, &umem->user->locked_vm);
	free_uid(umem->user);
}

static void xdp_umem_release(struct xdp_umem *umem)
{
	struct task_struct *task;
	struct mm_struct *mm;

	xdp_umem_clear_dev(umem);

	if (umem->fq) {
		xskq_destroy(umem->fq);
		umem->fq = NULL;
	}

	if (umem->cq) {
		xskq_destroy(umem->cq);
		umem->cq = NULL;
	}

	xdp_umem_unpin_pages(umem);

	task = get_pid_task(umem->pid, PIDTYPE_PID);
	put_pid(umem->pid);
	if (!task)
		goto out;
	mm = get_task_mm(task);
	put_task_struct(task);
	if (!mm)
		goto out;

	mmput(mm);
	kfree(umem->pages);
	umem->pages = NULL;

	xdp_umem_unaccount_pages(umem);
out:
	kfree(umem);
}

static void xdp_umem_release_deferred(struct work_struct *work)
{
	struct xdp_umem *umem = container_of(work, struct xdp_umem, work);

	xdp_umem_release(umem);
}

void xdp_get_umem(struct xdp_umem *umem)
{
	refcount_inc(&umem->users);
}

void xdp_put_umem(struct xdp_umem *umem)
{
	if (!umem)
		return;

	if (refcount_dec_and_test(&umem->users)) {
		INIT_WORK(&umem->work, xdp_umem_release_deferred);
		schedule_work(&umem->work);
	}
}

static int xdp_umem_pin_pages(struct xdp_umem *umem)
{
	unsigned int gup_flags = FOLL_WRITE;
	long npgs;
	int err;

	umem->pgs = kcalloc(umem->npgs, sizeof(*umem->pgs), GFP_KERNEL);
	if (!umem->pgs)
		return -ENOMEM;

	down_write(&current->mm->mmap_sem);
	npgs = get_user_pages(umem->address, umem->npgs,
			      gup_flags, &umem->pgs[0], NULL);
	up_write(&current->mm->mmap_sem);

	if (npgs != umem->npgs) {
		if (npgs >= 0) {
			umem->npgs = npgs;
			err = -ENOMEM;
			goto out_pin;
		}
		err = npgs;
		goto out_pgs;
	}
	return 0;

out_pin:
	xdp_umem_unpin_pages(umem);
out_pgs:
	kfree(umem->pgs);
	umem->pgs = NULL;
	return err;
}

static int xdp_umem_account_pages(struct xdp_umem *umem)
{
	unsigned long lock_limit, new_npgs, old_npgs;

	if (capable(CAP_IPC_LOCK))
		return 0;

	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
	umem->user = get_uid(current_user());

	do {
		old_npgs = atomic_long_read(&umem->user->locked_vm);
		new_npgs = old_npgs + umem->npgs;
		if (new_npgs > lock_limit) {
			free_uid(umem->user);
			umem->user = NULL;
			return -ENOBUFS;
		}
	} while (atomic_long_cmpxchg(&umem->user->locked_vm, old_npgs,
				     new_npgs) != old_npgs);
	return 0;
}

static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
{
	u32 chunk_size = mr->chunk_size, headroom = mr->headroom;
	unsigned int chunks, chunks_per_page;
	u64 addr = mr->addr, size = mr->len;
	int size_chk, err, i;

	if (chunk_size < XDP_UMEM_MIN_CHUNK_SIZE || chunk_size > PAGE_SIZE) {
		/* Strictly speaking we could support this, if:
		 * - huge pages, or*
		 * - using an IOMMU, or
		 * - making sure the memory area is consecutive
		 * but for now, we simply say "computer says no".
		 */
		return -EINVAL;
	}

	if (!is_power_of_2(chunk_size))
		return -EINVAL;

	if (!PAGE_ALIGNED(addr)) {
		/* Memory area has to be page size aligned. For
		 * simplicity, this might change.
		 */
		return -EINVAL;
	}

	if ((addr + size) < addr)
		return -EINVAL;

	chunks = (unsigned int)div_u64(size, chunk_size);
	if (chunks == 0)
		return -EINVAL;

	chunks_per_page = PAGE_SIZE / chunk_size;
	if (chunks < chunks_per_page || chunks % chunks_per_page)
		return -EINVAL;

	headroom = ALIGN(headroom, 64);

	size_chk = chunk_size - headroom - XDP_PACKET_HEADROOM;
	if (size_chk < 0)
		return -EINVAL;

	umem->pid = get_task_pid(current, PIDTYPE_PID);
	umem->address = (unsigned long)addr;
	umem->props.chunk_mask = ~((u64)chunk_size - 1);
	umem->props.size = size;
	umem->headroom = headroom;
	umem->chunk_size_nohr = chunk_size - headroom;
	umem->npgs = size / PAGE_SIZE;
	umem->pgs = NULL;
	umem->user = NULL;

	refcount_set(&umem->users, 1);

	err = xdp_umem_account_pages(umem);
	if (err)
		goto out;

	err = xdp_umem_pin_pages(umem);
	if (err)
		goto out_account;

	umem->pages = kcalloc(umem->npgs, sizeof(*umem->pages), GFP_KERNEL);
	if (!umem->pages) {
		err = -ENOMEM;
		goto out_account;
	}

	for (i = 0; i < umem->npgs; i++)
		umem->pages[i].addr = page_address(umem->pgs[i]);

	return 0;

out_account:
	xdp_umem_unaccount_pages(umem);
out:
	put_pid(umem->pid);
	return err;
}

struct xdp_umem *xdp_umem_create(struct xdp_umem_reg *mr)
{
	struct xdp_umem *umem;
	int err;

	umem = kzalloc(sizeof(*umem), GFP_KERNEL);
	if (!umem)
		return ERR_PTR(-ENOMEM);

	err = xdp_umem_reg(umem, mr);
	if (err) {
		kfree(umem);
		return ERR_PTR(err);
	}

	return umem;
}

bool xdp_umem_validate_queues(struct xdp_umem *umem)
{
	return umem->fq && umem->cq;
}