xref: /kernel/linux/linux-6.6/fs/nfsd/blocklayout.c (revision 62306a36)
1// SPDX-License-Identifier: GPL-2.0
2/*
3 * Copyright (c) 2014-2016 Christoph Hellwig.
4 */
5#include <linux/exportfs.h>
6#include <linux/iomap.h>
7#include <linux/slab.h>
8#include <linux/pr.h>
9
10#include <linux/nfsd/debug.h>
11
12#include "blocklayoutxdr.h"
13#include "pnfs.h"
14#include "filecache.h"
15#include "vfs.h"
16
17#define NFSDDBG_FACILITY	NFSDDBG_PNFS
18
19
20static __be32
21nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp,
22		struct nfsd4_layoutget *args)
23{
24	struct nfsd4_layout_seg *seg = &args->lg_seg;
25	struct super_block *sb = inode->i_sb;
26	u32 block_size = i_blocksize(inode);
27	struct pnfs_block_extent *bex;
28	struct iomap iomap;
29	u32 device_generation = 0;
30	int error;
31
32	if (seg->offset & (block_size - 1)) {
33		dprintk("pnfsd: I/O misaligned\n");
34		goto out_layoutunavailable;
35	}
36
37	/*
38	 * Some clients barf on non-zero block numbers for NONE or INVALID
39	 * layouts, so make sure to zero the whole structure.
40	 */
41	error = -ENOMEM;
42	bex = kzalloc(sizeof(*bex), GFP_KERNEL);
43	if (!bex)
44		goto out_error;
45	args->lg_content = bex;
46
47	error = sb->s_export_op->map_blocks(inode, seg->offset, seg->length,
48					    &iomap, seg->iomode != IOMODE_READ,
49					    &device_generation);
50	if (error) {
51		if (error == -ENXIO)
52			goto out_layoutunavailable;
53		goto out_error;
54	}
55
56	if (iomap.length < args->lg_minlength) {
57		dprintk("pnfsd: extent smaller than minlength\n");
58		goto out_layoutunavailable;
59	}
60
61	switch (iomap.type) {
62	case IOMAP_MAPPED:
63		if (seg->iomode == IOMODE_READ)
64			bex->es = PNFS_BLOCK_READ_DATA;
65		else
66			bex->es = PNFS_BLOCK_READWRITE_DATA;
67		bex->soff = iomap.addr;
68		break;
69	case IOMAP_UNWRITTEN:
70		if (seg->iomode & IOMODE_RW) {
71			/*
72			 * Crack monkey special case from section 2.3.1.
73			 */
74			if (args->lg_minlength == 0) {
75				dprintk("pnfsd: no soup for you!\n");
76				goto out_layoutunavailable;
77			}
78
79			bex->es = PNFS_BLOCK_INVALID_DATA;
80			bex->soff = iomap.addr;
81			break;
82		}
83		fallthrough;
84	case IOMAP_HOLE:
85		if (seg->iomode == IOMODE_READ) {
86			bex->es = PNFS_BLOCK_NONE_DATA;
87			break;
88		}
89		fallthrough;
90	case IOMAP_DELALLOC:
91	default:
92		WARN(1, "pnfsd: filesystem returned %d extent\n", iomap.type);
93		goto out_layoutunavailable;
94	}
95
96	error = nfsd4_set_deviceid(&bex->vol_id, fhp, device_generation);
97	if (error)
98		goto out_error;
99	bex->foff = iomap.offset;
100	bex->len = iomap.length;
101
102	seg->offset = iomap.offset;
103	seg->length = iomap.length;
104
105	dprintk("GET: 0x%llx:0x%llx %d\n", bex->foff, bex->len, bex->es);
106	return 0;
107
108out_error:
109	seg->length = 0;
110	return nfserrno(error);
111out_layoutunavailable:
112	seg->length = 0;
113	return nfserr_layoutunavailable;
114}
115
116static __be32
117nfsd4_block_commit_blocks(struct inode *inode, struct nfsd4_layoutcommit *lcp,
118		struct iomap *iomaps, int nr_iomaps)
119{
120	loff_t new_size = lcp->lc_last_wr + 1;
121	struct iattr iattr = { .ia_valid = 0 };
122	int error;
123
124	if (lcp->lc_mtime.tv_nsec == UTIME_NOW ||
125	    timespec64_compare(&lcp->lc_mtime, &inode->i_mtime) < 0)
126		lcp->lc_mtime = current_time(inode);
127	iattr.ia_valid |= ATTR_ATIME | ATTR_CTIME | ATTR_MTIME;
128	iattr.ia_atime = iattr.ia_ctime = iattr.ia_mtime = lcp->lc_mtime;
129
130	if (new_size > i_size_read(inode)) {
131		iattr.ia_valid |= ATTR_SIZE;
132		iattr.ia_size = new_size;
133	}
134
135	error = inode->i_sb->s_export_op->commit_blocks(inode, iomaps,
136			nr_iomaps, &iattr);
137	kfree(iomaps);
138	return nfserrno(error);
139}
140
141#ifdef CONFIG_NFSD_BLOCKLAYOUT
142static int
143nfsd4_block_get_device_info_simple(struct super_block *sb,
144		struct nfsd4_getdeviceinfo *gdp)
145{
146	struct pnfs_block_deviceaddr *dev;
147	struct pnfs_block_volume *b;
148
149	dev = kzalloc(sizeof(struct pnfs_block_deviceaddr) +
150		      sizeof(struct pnfs_block_volume), GFP_KERNEL);
151	if (!dev)
152		return -ENOMEM;
153	gdp->gd_device = dev;
154
155	dev->nr_volumes = 1;
156	b = &dev->volumes[0];
157
158	b->type = PNFS_BLOCK_VOLUME_SIMPLE;
159	b->simple.sig_len = PNFS_BLOCK_UUID_LEN;
160	return sb->s_export_op->get_uuid(sb, b->simple.sig, &b->simple.sig_len,
161			&b->simple.offset);
162}
163
164static __be32
165nfsd4_block_proc_getdeviceinfo(struct super_block *sb,
166		struct svc_rqst *rqstp,
167		struct nfs4_client *clp,
168		struct nfsd4_getdeviceinfo *gdp)
169{
170	if (bdev_is_partition(sb->s_bdev))
171		return nfserr_inval;
172	return nfserrno(nfsd4_block_get_device_info_simple(sb, gdp));
173}
174
175static __be32
176nfsd4_block_proc_layoutcommit(struct inode *inode,
177		struct nfsd4_layoutcommit *lcp)
178{
179	struct iomap *iomaps;
180	int nr_iomaps;
181
182	nr_iomaps = nfsd4_block_decode_layoutupdate(lcp->lc_up_layout,
183			lcp->lc_up_len, &iomaps, i_blocksize(inode));
184	if (nr_iomaps < 0)
185		return nfserrno(nr_iomaps);
186
187	return nfsd4_block_commit_blocks(inode, lcp, iomaps, nr_iomaps);
188}
189
190const struct nfsd4_layout_ops bl_layout_ops = {
191	/*
192	 * Pretend that we send notification to the client.  This is a blatant
193	 * lie to force recent Linux clients to cache our device IDs.
194	 * We rarely ever change the device ID, so the harm of leaking deviceids
195	 * for a while isn't too bad.  Unfortunately RFC5661 is a complete mess
196	 * in this regard, but I filed errata 4119 for this a while ago, and
197	 * hopefully the Linux client will eventually start caching deviceids
198	 * without this again.
199	 */
200	.notify_types		=
201			NOTIFY_DEVICEID4_DELETE | NOTIFY_DEVICEID4_CHANGE,
202	.proc_getdeviceinfo	= nfsd4_block_proc_getdeviceinfo,
203	.encode_getdeviceinfo	= nfsd4_block_encode_getdeviceinfo,
204	.proc_layoutget		= nfsd4_block_proc_layoutget,
205	.encode_layoutget	= nfsd4_block_encode_layoutget,
206	.proc_layoutcommit	= nfsd4_block_proc_layoutcommit,
207};
208#endif /* CONFIG_NFSD_BLOCKLAYOUT */
209
210#ifdef CONFIG_NFSD_SCSILAYOUT
211#define NFSD_MDS_PR_KEY		0x0100000000000000ULL
212
213/*
214 * We use the client ID as a unique key for the reservations.
215 * This allows us to easily fence a client when recalls fail.
216 */
217static u64 nfsd4_scsi_pr_key(struct nfs4_client *clp)
218{
219	return ((u64)clp->cl_clientid.cl_boot << 32) | clp->cl_clientid.cl_id;
220}
221
222static const u8 designator_types[] = {
223	PS_DESIGNATOR_EUI64,
224	PS_DESIGNATOR_NAA,
225};
226
227static int
228nfsd4_block_get_unique_id(struct gendisk *disk, struct pnfs_block_volume *b)
229{
230	int ret, i;
231
232	for (i = 0; i < ARRAY_SIZE(designator_types); i++) {
233		u8 type = designator_types[i];
234
235		ret = disk->fops->get_unique_id(disk, b->scsi.designator, type);
236		if (ret > 0) {
237			b->scsi.code_set = PS_CODE_SET_BINARY;
238			b->scsi.designator_type = type;
239			b->scsi.designator_len = ret;
240			return 0;
241		}
242	}
243
244	return -EINVAL;
245}
246
247static int
248nfsd4_block_get_device_info_scsi(struct super_block *sb,
249		struct nfs4_client *clp,
250		struct nfsd4_getdeviceinfo *gdp)
251{
252	struct pnfs_block_deviceaddr *dev;
253	struct pnfs_block_volume *b;
254	const struct pr_ops *ops;
255	int ret;
256
257	dev = kzalloc(sizeof(struct pnfs_block_deviceaddr) +
258		      sizeof(struct pnfs_block_volume), GFP_KERNEL);
259	if (!dev)
260		return -ENOMEM;
261	gdp->gd_device = dev;
262
263	dev->nr_volumes = 1;
264	b = &dev->volumes[0];
265
266	b->type = PNFS_BLOCK_VOLUME_SCSI;
267	b->scsi.pr_key = nfsd4_scsi_pr_key(clp);
268
269	ret = nfsd4_block_get_unique_id(sb->s_bdev->bd_disk, b);
270	if (ret < 0)
271		goto out_free_dev;
272
273	ret = -EINVAL;
274	ops = sb->s_bdev->bd_disk->fops->pr_ops;
275	if (!ops) {
276		pr_err("pNFS: device %s does not support PRs.\n",
277			sb->s_id);
278		goto out_free_dev;
279	}
280
281	ret = ops->pr_register(sb->s_bdev, 0, NFSD_MDS_PR_KEY, true);
282	if (ret) {
283		pr_err("pNFS: failed to register key for device %s.\n",
284			sb->s_id);
285		goto out_free_dev;
286	}
287
288	ret = ops->pr_reserve(sb->s_bdev, NFSD_MDS_PR_KEY,
289			PR_EXCLUSIVE_ACCESS_REG_ONLY, 0);
290	if (ret) {
291		pr_err("pNFS: failed to reserve device %s.\n",
292			sb->s_id);
293		goto out_free_dev;
294	}
295
296	return 0;
297
298out_free_dev:
299	kfree(dev);
300	gdp->gd_device = NULL;
301	return ret;
302}
303
304static __be32
305nfsd4_scsi_proc_getdeviceinfo(struct super_block *sb,
306		struct svc_rqst *rqstp,
307		struct nfs4_client *clp,
308		struct nfsd4_getdeviceinfo *gdp)
309{
310	if (bdev_is_partition(sb->s_bdev))
311		return nfserr_inval;
312	return nfserrno(nfsd4_block_get_device_info_scsi(sb, clp, gdp));
313}
314static __be32
315nfsd4_scsi_proc_layoutcommit(struct inode *inode,
316		struct nfsd4_layoutcommit *lcp)
317{
318	struct iomap *iomaps;
319	int nr_iomaps;
320
321	nr_iomaps = nfsd4_scsi_decode_layoutupdate(lcp->lc_up_layout,
322			lcp->lc_up_len, &iomaps, i_blocksize(inode));
323	if (nr_iomaps < 0)
324		return nfserrno(nr_iomaps);
325
326	return nfsd4_block_commit_blocks(inode, lcp, iomaps, nr_iomaps);
327}
328
329static void
330nfsd4_scsi_fence_client(struct nfs4_layout_stateid *ls)
331{
332	struct nfs4_client *clp = ls->ls_stid.sc_client;
333	struct block_device *bdev = ls->ls_file->nf_file->f_path.mnt->mnt_sb->s_bdev;
334
335	bdev->bd_disk->fops->pr_ops->pr_preempt(bdev, NFSD_MDS_PR_KEY,
336			nfsd4_scsi_pr_key(clp), 0, true);
337}
338
339const struct nfsd4_layout_ops scsi_layout_ops = {
340	/*
341	 * Pretend that we send notification to the client.  This is a blatant
342	 * lie to force recent Linux clients to cache our device IDs.
343	 * We rarely ever change the device ID, so the harm of leaking deviceids
344	 * for a while isn't too bad.  Unfortunately RFC5661 is a complete mess
345	 * in this regard, but I filed errata 4119 for this a while ago, and
346	 * hopefully the Linux client will eventually start caching deviceids
347	 * without this again.
348	 */
349	.notify_types		=
350			NOTIFY_DEVICEID4_DELETE | NOTIFY_DEVICEID4_CHANGE,
351	.proc_getdeviceinfo	= nfsd4_scsi_proc_getdeviceinfo,
352	.encode_getdeviceinfo	= nfsd4_block_encode_getdeviceinfo,
353	.proc_layoutget		= nfsd4_block_proc_layoutget,
354	.encode_layoutget	= nfsd4_block_encode_layoutget,
355	.proc_layoutcommit	= nfsd4_scsi_proc_layoutcommit,
356	.fence_client		= nfsd4_scsi_fence_client,
357};
358#endif /* CONFIG_NFSD_SCSILAYOUT */
359