super.c 24.7 KB
Newer Older
S
Sage Weil 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13

#include "ceph_debug.h"

#include <linux/backing-dev.h>
#include <linux/fs.h>
#include <linux/inet.h>
#include <linux/in6.h>
#include <linux/module.h>
#include <linux/mount.h>
#include <linux/parser.h>
#include <linux/rwsem.h>
#include <linux/sched.h>
#include <linux/seq_file.h>
14
#include <linux/slab.h>
S
Sage Weil 已提交
15 16 17 18 19 20 21 22
#include <linux/statfs.h>
#include <linux/string.h>
#include <linux/version.h>
#include <linux/vmalloc.h>

#include "decode.h"
#include "super.h"
#include "mon_client.h"
23
#include "auth.h"
S
Sage Weil 已提交
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

/*
 * Ceph superblock operations
 *
 * Handle the basics of mounting, unmounting.
 */


/*
 * find filename portion of a path (/foo/bar/baz -> baz)
 */
const char *ceph_file_part(const char *s, int len)
{
	const char *e = s + len;

	while (e != s && *(e-1) != '/')
		e--;
	return e;
}


/*
 * super ops
 */
static void ceph_put_super(struct super_block *s)
{
	struct ceph_client *cl = ceph_client(s);

	dout("put_super\n");
	ceph_mdsc_close_sessions(&cl->mdsc);
	return;
}

static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
{
	struct ceph_client *client = ceph_inode_to_client(dentry->d_inode);
	struct ceph_monmap *monmap = client->monc.monmap;
	struct ceph_statfs st;
	u64 fsid;
	int err;

	dout("statfs\n");
	err = ceph_monc_do_statfs(&client->monc, &st);
	if (err < 0)
		return err;

	/* fill in kstatfs */
	buf->f_type = CEPH_SUPER_MAGIC;  /* ?? */

	/*
	 * express utilization in terms of large blocks to avoid
	 * overflow on 32-bit machines.
	 */
	buf->f_bsize = 1 << CEPH_BLOCK_SHIFT;
	buf->f_blocks = le64_to_cpu(st.kb) >> (CEPH_BLOCK_SHIFT-10);
	buf->f_bfree = (le64_to_cpu(st.kb) - le64_to_cpu(st.kb_used)) >>
		(CEPH_BLOCK_SHIFT-10);
	buf->f_bavail = le64_to_cpu(st.kb_avail) >> (CEPH_BLOCK_SHIFT-10);

	buf->f_files = le64_to_cpu(st.num_objects);
	buf->f_ffree = -1;
	buf->f_namelen = PATH_MAX;
	buf->f_frsize = PAGE_CACHE_SIZE;

	/* leave fsid little-endian, regardless of host endianness */
	fsid = *(u64 *)(&monmap->fsid) ^ *((u64 *)&monmap->fsid + 1);
	buf->f_fsid.val[0] = fsid & 0xffffffff;
	buf->f_fsid.val[1] = fsid >> 32;

	return 0;
}


static int ceph_syncfs(struct super_block *sb, int wait)
{
	dout("sync_fs %d\n", wait);
	ceph_osdc_sync(&ceph_client(sb)->osdc);
	ceph_mdsc_sync(&ceph_client(sb)->mdsc);
102
	dout("sync_fs %d done\n", wait);
S
Sage Weil 已提交
103 104 105 106 107 108 109 110 111 112 113 114
	return 0;
}


/**
 * ceph_show_options - Show mount options in /proc/mounts
 * @m: seq_file to write to
 * @mnt: mount descriptor
 */
static int ceph_show_options(struct seq_file *m, struct vfsmount *mnt)
{
	struct ceph_client *client = ceph_sb_to_client(mnt->mnt_sb);
115
	struct ceph_mount_args *args = client->mount_args;
S
Sage Weil 已提交
116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132

	if (args->flags & CEPH_OPT_FSID)
		seq_printf(m, ",fsidmajor=%llu,fsidminor%llu",
			   le64_to_cpu(*(__le64 *)&args->fsid.fsid[0]),
			   le64_to_cpu(*(__le64 *)&args->fsid.fsid[8]));
	if (args->flags & CEPH_OPT_NOSHARE)
		seq_puts(m, ",noshare");
	if (args->flags & CEPH_OPT_DIRSTAT)
		seq_puts(m, ",dirstat");
	if ((args->flags & CEPH_OPT_RBYTES) == 0)
		seq_puts(m, ",norbytes");
	if (args->flags & CEPH_OPT_NOCRC)
		seq_puts(m, ",nocrc");
	if (args->flags & CEPH_OPT_NOASYNCREADDIR)
		seq_puts(m, ",noasyncreaddir");
	if (strcmp(args->snapdir_name, CEPH_SNAPDIRNAME_DEFAULT))
		seq_printf(m, ",snapdirname=%s", args->snapdir_name);
133 134
	if (args->name)
		seq_printf(m, ",name=%s", args->name);
S
Sage Weil 已提交
135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153
	if (args->secret)
		seq_puts(m, ",secret=<hidden>");
	return 0;
}

/*
 * caches
 */
struct kmem_cache *ceph_inode_cachep;
struct kmem_cache *ceph_cap_cachep;
struct kmem_cache *ceph_dentry_cachep;
struct kmem_cache *ceph_file_cachep;

static void ceph_inode_init_once(void *foo)
{
	struct ceph_inode_info *ci = foo;
	inode_init_once(&ci->vfs_inode);
}

Y
Yehuda Sadeh 已提交
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
static int default_congestion_kb(void)
{
	int congestion_kb;

	/*
	 * Copied from NFS
	 *
	 * congestion size, scale with available memory.
	 *
	 *  64MB:    8192k
	 * 128MB:   11585k
	 * 256MB:   16384k
	 * 512MB:   23170k
	 *   1GB:   32768k
	 *   2GB:   46340k
	 *   4GB:   65536k
	 *   8GB:   92681k
	 *  16GB:  131072k
	 *
	 * This allows larger machines to have larger/more transfers.
	 * Limit the default to 256M
	 */
	congestion_kb = (16*int_sqrt(totalram_pages)) << (PAGE_SHIFT-10);
	if (congestion_kb > 256*1024)
		congestion_kb = 256*1024;

	return congestion_kb;
}

S
Sage Weil 已提交
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
static int __init init_caches(void)
{
	ceph_inode_cachep = kmem_cache_create("ceph_inode_info",
				      sizeof(struct ceph_inode_info),
				      __alignof__(struct ceph_inode_info),
				      (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD),
				      ceph_inode_init_once);
	if (ceph_inode_cachep == NULL)
		return -ENOMEM;

	ceph_cap_cachep = KMEM_CACHE(ceph_cap,
				     SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD);
	if (ceph_cap_cachep == NULL)
		goto bad_cap;

	ceph_dentry_cachep = KMEM_CACHE(ceph_dentry_info,
					SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD);
	if (ceph_dentry_cachep == NULL)
		goto bad_dentry;

	ceph_file_cachep = KMEM_CACHE(ceph_file_info,
				      SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD);
	if (ceph_file_cachep == NULL)
		goto bad_file;

	return 0;

bad_file:
	kmem_cache_destroy(ceph_dentry_cachep);
bad_dentry:
	kmem_cache_destroy(ceph_cap_cachep);
bad_cap:
	kmem_cache_destroy(ceph_inode_cachep);
	return -ENOMEM;
}

static void destroy_caches(void)
{
	kmem_cache_destroy(ceph_inode_cachep);
	kmem_cache_destroy(ceph_cap_cachep);
	kmem_cache_destroy(ceph_dentry_cachep);
	kmem_cache_destroy(ceph_file_cachep);
}


/*
 * ceph_umount_begin - initiate forced umount.  Tear down down the
 * mount, skipping steps that may hang while waiting for server(s).
 */
static void ceph_umount_begin(struct super_block *sb)
{
	struct ceph_client *client = ceph_sb_to_client(sb);

	dout("ceph_umount_begin - starting forced umount\n");
	if (!client)
		return;
	client->mount_state = CEPH_MOUNT_SHUTDOWN;
	return;
}

static const struct super_operations ceph_super_ops = {
	.alloc_inode	= ceph_alloc_inode,
	.destroy_inode	= ceph_destroy_inode,
	.write_inode    = ceph_write_inode,
	.sync_fs        = ceph_syncfs,
	.put_super	= ceph_put_super,
	.show_options   = ceph_show_options,
	.statfs		= ceph_statfs,
	.umount_begin   = ceph_umount_begin,
};


const char *ceph_msg_type_name(int type)
{
	switch (type) {
	case CEPH_MSG_SHUTDOWN: return "shutdown";
	case CEPH_MSG_PING: return "ping";
260 261
	case CEPH_MSG_AUTH: return "auth";
	case CEPH_MSG_AUTH_REPLY: return "auth_reply";
S
Sage Weil 已提交
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
	case CEPH_MSG_MON_MAP: return "mon_map";
	case CEPH_MSG_MON_GET_MAP: return "mon_get_map";
	case CEPH_MSG_MON_SUBSCRIBE: return "mon_subscribe";
	case CEPH_MSG_MON_SUBSCRIBE_ACK: return "mon_subscribe_ack";
	case CEPH_MSG_STATFS: return "statfs";
	case CEPH_MSG_STATFS_REPLY: return "statfs_reply";
	case CEPH_MSG_MDS_MAP: return "mds_map";
	case CEPH_MSG_CLIENT_SESSION: return "client_session";
	case CEPH_MSG_CLIENT_RECONNECT: return "client_reconnect";
	case CEPH_MSG_CLIENT_REQUEST: return "client_request";
	case CEPH_MSG_CLIENT_REQUEST_FORWARD: return "client_request_forward";
	case CEPH_MSG_CLIENT_REPLY: return "client_reply";
	case CEPH_MSG_CLIENT_CAPS: return "client_caps";
	case CEPH_MSG_CLIENT_CAPRELEASE: return "client_cap_release";
	case CEPH_MSG_CLIENT_SNAP: return "client_snap";
	case CEPH_MSG_CLIENT_LEASE: return "client_lease";
	case CEPH_MSG_OSD_MAP: return "osd_map";
	case CEPH_MSG_OSD_OP: return "osd_op";
	case CEPH_MSG_OSD_OPREPLY: return "osd_opreply";
	default: return "unknown";
	}
}


/*
 * mount options
 */
enum {
	Opt_fsidmajor,
	Opt_fsidminor,
	Opt_monport,
	Opt_wsize,
	Opt_rsize,
	Opt_osdtimeout,
296
	Opt_osdkeepalivetimeout,
S
Sage Weil 已提交
297
	Opt_mount_timeout,
298
	Opt_osd_idle_ttl,
S
Sage Weil 已提交
299 300 301
	Opt_caps_wanted_delay_min,
	Opt_caps_wanted_delay_max,
	Opt_readdir_max_entries,
Y
Yehuda Sadeh 已提交
302
	Opt_congestion_kb,
303
	Opt_last_int,
S
Sage Weil 已提交
304 305
	/* int args above */
	Opt_snapdirname,
306
	Opt_name,
S
Sage Weil 已提交
307
	Opt_secret,
308
	Opt_last_string,
S
Sage Weil 已提交
309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326
	/* string args above */
	Opt_ip,
	Opt_noshare,
	Opt_dirstat,
	Opt_nodirstat,
	Opt_rbytes,
	Opt_norbytes,
	Opt_nocrc,
	Opt_noasyncreaddir,
};

static match_table_t arg_tokens = {
	{Opt_fsidmajor, "fsidmajor=%ld"},
	{Opt_fsidminor, "fsidminor=%ld"},
	{Opt_monport, "monport=%d"},
	{Opt_wsize, "wsize=%d"},
	{Opt_rsize, "rsize=%d"},
	{Opt_osdtimeout, "osdtimeout=%d"},
327
	{Opt_osdkeepalivetimeout, "osdkeepalive=%d"},
S
Sage Weil 已提交
328
	{Opt_mount_timeout, "mount_timeout=%d"},
329
	{Opt_osd_idle_ttl, "osd_idle_ttl=%d"},
S
Sage Weil 已提交
330 331 332
	{Opt_caps_wanted_delay_min, "caps_wanted_delay_min=%d"},
	{Opt_caps_wanted_delay_max, "caps_wanted_delay_max=%d"},
	{Opt_readdir_max_entries, "readdir_max_entries=%d"},
Y
Yehuda Sadeh 已提交
333
	{Opt_congestion_kb, "write_congestion_kb=%d"},
S
Sage Weil 已提交
334 335
	/* int args above */
	{Opt_snapdirname, "snapdirname=%s"},
336
	{Opt_name, "name=%s"},
S
Sage Weil 已提交
337 338 339 340 341 342 343 344 345 346 347 348 349 350
	{Opt_secret, "secret=%s"},
	/* string args above */
	{Opt_ip, "ip=%s"},
	{Opt_noshare, "noshare"},
	{Opt_dirstat, "dirstat"},
	{Opt_nodirstat, "nodirstat"},
	{Opt_rbytes, "rbytes"},
	{Opt_norbytes, "norbytes"},
	{Opt_nocrc, "nocrc"},
	{Opt_noasyncreaddir, "noasyncreaddir"},
	{-1, NULL}
};


351 352 353
static struct ceph_mount_args *parse_mount_args(int flags, char *options,
						const char *dev_name,
						const char **path)
S
Sage Weil 已提交
354
{
355
	struct ceph_mount_args *args;
S
Sage Weil 已提交
356
	const char *c;
357
	int err = -ENOMEM;
S
Sage Weil 已提交
358 359
	substring_t argstr[MAX_OPT_ARGS];

360 361 362 363 364 365 366
	args = kzalloc(sizeof(*args), GFP_KERNEL);
	if (!args)
		return ERR_PTR(-ENOMEM);
	args->mon_addr = kcalloc(CEPH_MAX_MON, sizeof(*args->mon_addr),
				 GFP_KERNEL);
	if (!args->mon_addr)
		goto out;
S
Sage Weil 已提交
367

368
	dout("parse_mount_args %p, dev_name '%s'\n", args, dev_name);
369

S
Sage Weil 已提交
370 371 372
	/* start with defaults */
	args->sb_flags = flags;
	args->flags = CEPH_OPT_DEFAULT;
373 374
	args->osd_timeout = CEPH_OSD_TIMEOUT_DEFAULT;
	args->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT;
S
Sage Weil 已提交
375
	args->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT; /* seconds */
376
	args->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT;   /* seconds */
S
Sage Weil 已提交
377 378
	args->caps_wanted_delay_min = CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT;
	args->caps_wanted_delay_max = CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT;
S
Sage Weil 已提交
379
	args->rsize = CEPH_MOUNT_RSIZE_DEFAULT;
S
Sage Weil 已提交
380 381 382
	args->snapdir_name = kstrdup(CEPH_SNAPDIRNAME_DEFAULT, GFP_KERNEL);
	args->cap_release_safety = CEPH_CAPS_PER_RELEASE * 4;
	args->max_readdir = 1024;
Y
Yehuda Sadeh 已提交
383
	args->congestion_kb = default_congestion_kb();
S
Sage Weil 已提交
384 385

	/* ip1[:port1][,ip2[:port2]...]:/subdir/in/fs */
386
	err = -EINVAL;
S
Sage Weil 已提交
387
	if (!dev_name)
388
		goto out;
S
Sage Weil 已提交
389 390 391 392
	*path = strstr(dev_name, ":/");
	if (*path == NULL) {
		pr_err("device name is missing path (no :/ in %s)\n",
		       dev_name);
393
		goto out;
S
Sage Weil 已提交
394 395 396
	}

	/* get mon ip(s) */
397 398
	err = ceph_parse_ips(dev_name, *path, args->mon_addr,
			     CEPH_MAX_MON, &args->num_mon);
S
Sage Weil 已提交
399
	if (err < 0)
400
		goto out;
S
Sage Weil 已提交
401 402 403 404 405 406 407 408 409 410

	/* path on server */
	*path += 2;
	dout("server path '%s'\n", *path);

	/* parse mount options */
	while ((c = strsep(&options, ",")) != NULL) {
		int token, intval, ret;
		if (!*c)
			continue;
411
		err = -EINVAL;
S
Sage Weil 已提交
412 413 414
		token = match_token((char *)c, arg_tokens, argstr);
		if (token < 0) {
			pr_err("bad mount option at '%s'\n", c);
415
			goto out;
S
Sage Weil 已提交
416
		}
417
		if (token < Opt_last_int) {
S
Sage Weil 已提交
418 419 420 421 422 423
			ret = match_int(&argstr[0], &intval);
			if (ret < 0) {
				pr_err("bad mount option arg (not int) "
				       "at '%s'\n", c);
				continue;
			}
424 425 426 427 428 429
			dout("got int token %d val %d\n", token, intval);
		} else if (token > Opt_last_int && token < Opt_last_string) {
			dout("got string token %d val %s\n", token,
			     argstr[0].from);
		} else {
			dout("got token %d\n", token);
S
Sage Weil 已提交
430 431 432 433 434 435 436 437 438 439 440 441 442 443
		}
		switch (token) {
		case Opt_fsidmajor:
			*(__le64 *)&args->fsid.fsid[0] = cpu_to_le64(intval);
			break;
		case Opt_fsidminor:
			*(__le64 *)&args->fsid.fsid[8] = cpu_to_le64(intval);
			break;
		case Opt_ip:
			err = ceph_parse_ips(argstr[0].from,
					     argstr[0].to,
					     &args->my_addr,
					     1, NULL);
			if (err < 0)
444
				goto out;
S
Sage Weil 已提交
445 446 447 448 449 450 451 452 453
			args->flags |= CEPH_OPT_MYIP;
			break;

		case Opt_snapdirname:
			kfree(args->snapdir_name);
			args->snapdir_name = kstrndup(argstr[0].from,
					      argstr[0].to-argstr[0].from,
					      GFP_KERNEL);
			break;
454 455 456 457 458
		case Opt_name:
			args->name = kstrndup(argstr[0].from,
					      argstr[0].to-argstr[0].from,
					      GFP_KERNEL);
			break;
S
Sage Weil 已提交
459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474
		case Opt_secret:
			args->secret = kstrndup(argstr[0].from,
						argstr[0].to-argstr[0].from,
						GFP_KERNEL);
			break;

			/* misc */
		case Opt_wsize:
			args->wsize = intval;
			break;
		case Opt_rsize:
			args->rsize = intval;
			break;
		case Opt_osdtimeout:
			args->osd_timeout = intval;
			break;
475 476 477
		case Opt_osdkeepalivetimeout:
			args->osd_keepalive_timeout = intval;
			break;
S
Sage Weil 已提交
478 479 480 481 482 483 484 485 486 487 488 489
		case Opt_mount_timeout:
			args->mount_timeout = intval;
			break;
		case Opt_caps_wanted_delay_min:
			args->caps_wanted_delay_min = intval;
			break;
		case Opt_caps_wanted_delay_max:
			args->caps_wanted_delay_max = intval;
			break;
		case Opt_readdir_max_entries:
			args->max_readdir = intval;
			break;
Y
Yehuda Sadeh 已提交
490 491 492
		case Opt_congestion_kb:
			args->congestion_kb = intval;
			break;
S
Sage Weil 已提交
493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520

		case Opt_noshare:
			args->flags |= CEPH_OPT_NOSHARE;
			break;

		case Opt_dirstat:
			args->flags |= CEPH_OPT_DIRSTAT;
			break;
		case Opt_nodirstat:
			args->flags &= ~CEPH_OPT_DIRSTAT;
			break;
		case Opt_rbytes:
			args->flags |= CEPH_OPT_RBYTES;
			break;
		case Opt_norbytes:
			args->flags &= ~CEPH_OPT_RBYTES;
			break;
		case Opt_nocrc:
			args->flags |= CEPH_OPT_NOCRC;
			break;
		case Opt_noasyncreaddir:
			args->flags |= CEPH_OPT_NOASYNCREADDIR;
			break;

		default:
			BUG_ON(token);
		}
	}
521
	return args;
S
Sage Weil 已提交
522

523
out:
524 525 526
	kfree(args->mon_addr);
	kfree(args);
	return ERR_PTR(err);
S
Sage Weil 已提交
527 528
}

529
static void destroy_mount_args(struct ceph_mount_args *args)
S
Sage Weil 已提交
530
{
531
	dout("destroy_mount_args %p\n", args);
S
Sage Weil 已提交
532 533
	kfree(args->snapdir_name);
	args->snapdir_name = NULL;
534 535
	kfree(args->name);
	args->name = NULL;
S
Sage Weil 已提交
536 537
	kfree(args->secret);
	args->secret = NULL;
538
	kfree(args);
S
Sage Weil 已提交
539 540 541 542 543
}

/*
 * create a fresh client instance
 */
544
static struct ceph_client *ceph_create_client(struct ceph_mount_args *args)
S
Sage Weil 已提交
545 546 547 548 549 550 551 552 553 554
{
	struct ceph_client *client;
	int err = -ENOMEM;

	client = kzalloc(sizeof(*client), GFP_KERNEL);
	if (client == NULL)
		return ERR_PTR(-ENOMEM);

	mutex_init(&client->mount_mutex);

555
	init_waitqueue_head(&client->auth_wq);
S
Sage Weil 已提交
556 557 558

	client->sb = NULL;
	client->mount_state = CEPH_MOUNT_MOUNTING;
559
	client->mount_args = args;
S
Sage Weil 已提交
560 561 562

	client->msgr = NULL;

563
	client->auth_err = 0;
Y
Yehuda Sadeh 已提交
564
	atomic_long_set(&client->writeback_count, 0);
S
Sage Weil 已提交
565

566 567 568 569
	err = bdi_init(&client->backing_dev_info);
	if (err < 0)
		goto fail;

S
Sage Weil 已提交
570 571 572
	err = -ENOMEM;
	client->wb_wq = create_workqueue("ceph-writeback");
	if (client->wb_wq == NULL)
573
		goto fail_bdi;
S
Sage Weil 已提交
574 575 576 577 578 579 580
	client->pg_inv_wq = create_singlethread_workqueue("ceph-pg-invalid");
	if (client->pg_inv_wq == NULL)
		goto fail_wb_wq;
	client->trunc_wq = create_singlethread_workqueue("ceph-trunc");
	if (client->trunc_wq == NULL)
		goto fail_pg_inv_wq;

581 582 583 584 585 586 587
	/* set up mempools */
	err = -ENOMEM;
	client->wb_pagevec_pool = mempool_create_kmalloc_pool(10,
			      client->mount_args->wsize >> PAGE_CACHE_SHIFT);
	if (!client->wb_pagevec_pool)
		goto fail_trunc_wq;

588 589 590
	/* caps */
	client->min_caps = args->max_readdir;
	ceph_adjust_min_caps(client->min_caps);
591

S
Sage Weil 已提交
592 593 594
	/* subsystems */
	err = ceph_monc_init(&client->monc, client);
	if (err < 0)
595
		goto fail_mempool;
S
Sage Weil 已提交
596 597 598
	err = ceph_osdc_init(&client->osdc, client);
	if (err < 0)
		goto fail_monc;
599 600 601
	err = ceph_mdsc_init(&client->mdsc, client);
	if (err < 0)
		goto fail_osdc;
S
Sage Weil 已提交
602 603
	return client;

604 605
fail_osdc:
	ceph_osdc_stop(&client->osdc);
S
Sage Weil 已提交
606 607
fail_monc:
	ceph_monc_stop(&client->monc);
608 609
fail_mempool:
	mempool_destroy(client->wb_pagevec_pool);
S
Sage Weil 已提交
610 611 612 613 614 615
fail_trunc_wq:
	destroy_workqueue(client->trunc_wq);
fail_pg_inv_wq:
	destroy_workqueue(client->pg_inv_wq);
fail_wb_wq:
	destroy_workqueue(client->wb_wq);
616 617
fail_bdi:
	bdi_destroy(&client->backing_dev_info);
S
Sage Weil 已提交
618 619 620 621 622 623 624 625 626 627 628 629 630 631
fail:
	kfree(client);
	return ERR_PTR(err);
}

static void ceph_destroy_client(struct ceph_client *client)
{
	dout("destroy_client %p\n", client);

	/* unmount */
	ceph_mdsc_stop(&client->mdsc);
	ceph_monc_stop(&client->monc);
	ceph_osdc_stop(&client->osdc);

632 633
	ceph_adjust_min_caps(-client->min_caps);

S
Sage Weil 已提交
634 635 636 637 638 639 640
	ceph_debugfs_client_cleanup(client);
	destroy_workqueue(client->wb_wq);
	destroy_workqueue(client->pg_inv_wq);
	destroy_workqueue(client->trunc_wq);

	if (client->msgr)
		ceph_messenger_destroy(client->msgr);
641
	mempool_destroy(client->wb_pagevec_pool);
S
Sage Weil 已提交
642

643
	destroy_mount_args(client->mount_args);
S
Sage Weil 已提交
644 645 646 647 648

	kfree(client);
	dout("destroy_client %p done\n", client);
}

649 650 651 652 653 654 655
/*
 * Initially learn our fsid, or verify an fsid matches.
 */
int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid)
{
	if (client->have_fsid) {
		if (ceph_fsid_compare(&client->fsid, fsid)) {
656 657
			pr_err("bad fsid, had " FSID_FORMAT " got " FSID_FORMAT,
			       PR_FSID(&client->fsid), PR_FSID(fsid));
658 659 660 661 662 663 664 665 666 667 668 669
			return -1;
		}
	} else {
		pr_info("client%lld fsid " FSID_FORMAT "\n",
			client->monc.auth->global_id, PR_FSID(fsid));
		memcpy(&client->fsid, fsid, sizeof(*fsid));
		ceph_debugfs_client_init(client);
		client->have_fsid = true;
	}
	return 0;
}

S
Sage Weil 已提交
670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699
/*
 * true if we have the mon map (and have thus joined the cluster)
 */
static int have_mon_map(struct ceph_client *client)
{
	return client->monc.monmap && client->monc.monmap->epoch;
}

/*
 * Bootstrap mount by opening the root directory.  Note the mount
 * @started time from caller, and time out if this takes too long.
 */
static struct dentry *open_root_dentry(struct ceph_client *client,
				       const char *path,
				       unsigned long started)
{
	struct ceph_mds_client *mdsc = &client->mdsc;
	struct ceph_mds_request *req = NULL;
	int err;
	struct dentry *root;

	/* open dir */
	dout("open_root_inode opening '%s'\n", path);
	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_GETATTR, USE_ANY_MDS);
	if (IS_ERR(req))
		return ERR_PTR(PTR_ERR(req));
	req->r_path1 = kstrdup(path, GFP_NOFS);
	req->r_ino1.ino = CEPH_INO_ROOT;
	req->r_ino1.snap = CEPH_NOSNAP;
	req->r_started = started;
700
	req->r_timeout = client->mount_args->mount_timeout * HZ;
S
Sage Weil 已提交
701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727
	req->r_args.getattr.mask = cpu_to_le32(CEPH_STAT_CAP_INODE);
	req->r_num_caps = 2;
	err = ceph_mdsc_do_request(mdsc, NULL, req);
	if (err == 0) {
		dout("open_root_inode success\n");
		if (ceph_ino(req->r_target_inode) == CEPH_INO_ROOT &&
		    client->sb->s_root == NULL)
			root = d_alloc_root(req->r_target_inode);
		else
			root = d_obtain_alias(req->r_target_inode);
		req->r_target_inode = NULL;
		dout("open_root_inode success, root dentry is %p\n", root);
	} else {
		root = ERR_PTR(err);
	}
	ceph_mdsc_put_request(req);
	return root;
}

/*
 * mount: join the ceph cluster, and open root directory.
 */
static int ceph_mount(struct ceph_client *client, struct vfsmount *mnt,
		      const char *path)
{
	struct ceph_entity_addr *myaddr = NULL;
	int err;
728
	unsigned long timeout = client->mount_args->mount_timeout * HZ;
S
Sage Weil 已提交
729 730 731 732 733 734 735 736 737
	unsigned long started = jiffies;  /* note the start time */
	struct dentry *root;

	dout("mount start\n");
	mutex_lock(&client->mount_mutex);

	/* initialize the messenger */
	if (client->msgr == NULL) {
		if (ceph_test_opt(client, MYIP))
738
			myaddr = &client->mount_args->my_addr;
S
Sage Weil 已提交
739 740 741 742 743 744 745 746 747
		client->msgr = ceph_messenger_create(myaddr);
		if (IS_ERR(client->msgr)) {
			err = PTR_ERR(client->msgr);
			client->msgr = NULL;
			goto out;
		}
		client->msgr->nocrc = ceph_test_opt(client, NOCRC);
	}

748 749
	/* open session, and wait for mon, mds, and osd maps */
	err = ceph_monc_open_session(&client->monc);
S
Sage Weil 已提交
750 751 752
	if (err < 0)
		goto out;

753
	while (!have_mon_map(client)) {
S
Sage Weil 已提交
754 755 756 757 758
		err = -EIO;
		if (timeout && time_after_eq(jiffies, started + timeout))
			goto out;

		/* wait */
759
		dout("mount waiting for mon_map\n");
760 761
		err = wait_event_interruptible_timeout(client->auth_wq,
			       have_mon_map(client) || (client->auth_err < 0),
S
Sage Weil 已提交
762 763 764
			       timeout);
		if (err == -EINTR || err == -ERESTARTSYS)
			goto out;
765 766
		if (client->auth_err < 0) {
			err = client->auth_err;
767 768
			goto out;
		}
S
Sage Weil 已提交
769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813
	}

	dout("mount opening root\n");
	root = open_root_dentry(client, "", started);
	if (IS_ERR(root)) {
		err = PTR_ERR(root);
		goto out;
	}
	if (client->sb->s_root)
		dput(root);
	else
		client->sb->s_root = root;

	if (path[0] == 0) {
		dget(root);
	} else {
		dout("mount opening base mountpoint\n");
		root = open_root_dentry(client, path, started);
		if (IS_ERR(root)) {
			err = PTR_ERR(root);
			dput(client->sb->s_root);
			client->sb->s_root = NULL;
			goto out;
		}
	}

	mnt->mnt_root = root;
	mnt->mnt_sb = client->sb;

	client->mount_state = CEPH_MOUNT_MOUNTED;
	dout("mount success\n");
	err = 0;

out:
	mutex_unlock(&client->mount_mutex);
	return err;
}

static int ceph_set_super(struct super_block *s, void *data)
{
	struct ceph_client *client = data;
	int ret;

	dout("set_super %p data %p\n", s, data);

814
	s->s_flags = client->mount_args->sb_flags;
S
Sage Weil 已提交
815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842
	s->s_maxbytes = 1ULL << 40;  /* temp value until we get mdsmap */

	s->s_fs_info = client;
	client->sb = s;

	s->s_op = &ceph_super_ops;
	s->s_export_op = &ceph_export_ops;

	s->s_time_gran = 1000;  /* 1000 ns == 1 us */

	ret = set_anon_super(s, NULL);  /* what is that second arg for? */
	if (ret != 0)
		goto fail;

	return ret;

fail:
	s->s_fs_info = NULL;
	client->sb = NULL;
	return ret;
}

/*
 * share superblock if same fs AND options
 */
static int ceph_compare_super(struct super_block *sb, void *data)
{
	struct ceph_client *new = data;
843
	struct ceph_mount_args *args = new->mount_args;
S
Sage Weil 已提交
844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864
	struct ceph_client *other = ceph_sb_to_client(sb);
	int i;

	dout("ceph_compare_super %p\n", sb);
	if (args->flags & CEPH_OPT_FSID) {
		if (ceph_fsid_compare(&args->fsid, &other->fsid)) {
			dout("fsid doesn't match\n");
			return 0;
		}
	} else {
		/* do we share (a) monitor? */
		for (i = 0; i < new->monc.monmap->num_mon; i++)
			if (ceph_monmap_contains(other->monc.monmap,
					 &new->monc.monmap->mon_inst[i].addr))
				break;
		if (i == new->monc.monmap->num_mon) {
			dout("mon ip not part of monmap\n");
			return 0;
		}
		dout("mon ip matches existing sb %p\n", sb);
	}
865
	if (args->sb_flags != other->mount_args->sb_flags) {
S
Sage Weil 已提交
866 867 868 869 870 871 872 873 874
		dout("flags differ\n");
		return 0;
	}
	return 1;
}

/*
 * construct our own bdi so we can control readahead, etc.
 */
875
static int ceph_register_bdi(struct super_block *sb, struct ceph_client *client)
S
Sage Weil 已提交
876 877 878
{
	int err;

879
	sb->s_bdi = &client->backing_dev_info;
S
Sage Weil 已提交
880 881

	/* set ra_pages based on rsize mount option? */
882
	if (client->mount_args->rsize >= PAGE_CACHE_SIZE)
S
Sage Weil 已提交
883
		client->backing_dev_info.ra_pages =
884
			(client->mount_args->rsize + PAGE_CACHE_SIZE - 1)
S
Sage Weil 已提交
885 886 887 888 889 890 891 892 893 894 895 896 897
			>> PAGE_SHIFT;
	err = bdi_register_dev(&client->backing_dev_info, sb->s_dev);
	return err;
}

static int ceph_get_sb(struct file_system_type *fs_type,
		       int flags, const char *dev_name, void *data,
		       struct vfsmount *mnt)
{
	struct super_block *sb;
	struct ceph_client *client;
	int err;
	int (*compare_super)(struct super_block *, void *) = ceph_compare_super;
S
Sage Weil 已提交
898
	const char *path = NULL;
899
	struct ceph_mount_args *args;
S
Sage Weil 已提交
900 901

	dout("ceph_get_sb\n");
902 903 904 905 906
	args = parse_mount_args(flags, data, dev_name, &path);
	if (IS_ERR(args)) {
		err = PTR_ERR(args);
		goto out_final;
	}
S
Sage Weil 已提交
907 908

	/* create client (which we may/may not use) */
909 910 911 912 913
	client = ceph_create_client(args);
	if (IS_ERR(client)) {
		err = PTR_ERR(client);
		goto out_final;
	}
S
Sage Weil 已提交
914

915
	if (client->mount_args->flags & CEPH_OPT_NOSHARE)
S
Sage Weil 已提交
916 917 918 919 920 921 922 923 924 925 926 927 928
		compare_super = NULL;
	sb = sget(fs_type, compare_super, ceph_set_super, client);
	if (IS_ERR(sb)) {
		err = PTR_ERR(sb);
		goto out;
	}

	if (ceph_client(sb) != client) {
		ceph_destroy_client(client);
		client = ceph_client(sb);
		dout("get_sb got existing client %p\n", client);
	} else {
		dout("get_sb using new client %p\n", client);
929
		err = ceph_register_bdi(sb, client);
S
Sage Weil 已提交
930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959
		if (err < 0)
			goto out_splat;
	}

	err = ceph_mount(client, mnt, path);
	if (err < 0)
		goto out_splat;
	dout("root %p inode %p ino %llx.%llx\n", mnt->mnt_root,
	     mnt->mnt_root->d_inode, ceph_vinop(mnt->mnt_root->d_inode));
	return 0;

out_splat:
	ceph_mdsc_close_sessions(&client->mdsc);
	up_write(&sb->s_umount);
	deactivate_super(sb);
	goto out_final;

out:
	ceph_destroy_client(client);
out_final:
	dout("ceph_get_sb fail %d\n", err);
	return err;
}

static void ceph_kill_sb(struct super_block *s)
{
	struct ceph_client *client = ceph_sb_to_client(s);
	dout("kill_sb %p\n", s);
	ceph_mdsc_pre_umount(&client->mdsc);
	kill_anon_super(s);    /* will call put_super after sb is r/o */
S
Sage Weil 已提交
960 961
	if (s->s_bdi == &client->backing_dev_info)
		bdi_unregister(&client->backing_dev_info);
S
Sage Weil 已提交
962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998
	bdi_destroy(&client->backing_dev_info);
	ceph_destroy_client(client);
}

static struct file_system_type ceph_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "ceph",
	.get_sb		= ceph_get_sb,
	.kill_sb	= ceph_kill_sb,
	.fs_flags	= FS_RENAME_DOES_D_MOVE,
};

#define _STRINGIFY(x) #x
#define STRINGIFY(x) _STRINGIFY(x)

static int __init init_ceph(void)
{
	int ret = 0;

	ret = ceph_debugfs_init();
	if (ret < 0)
		goto out;

	ret = ceph_msgr_init();
	if (ret < 0)
		goto out_debugfs;

	ret = init_caches();
	if (ret)
		goto out_msgr;

	ceph_caps_init();

	ret = register_filesystem(&ceph_fs_type);
	if (ret)
		goto out_icache;

999 1000 1001
	pr_info("loaded %d.%d.%d (mon/mds/osd proto %d/%d/%d)\n",
		CEPH_VERSION_MAJOR, CEPH_VERSION_MINOR, CEPH_VERSION_PATCH,
		CEPH_MONC_PROTOCOL, CEPH_MDSC_PROTOCOL, CEPH_OSDC_PROTOCOL);
S
Sage Weil 已提交
1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031
	return 0;

out_icache:
	destroy_caches();
out_msgr:
	ceph_msgr_exit();
out_debugfs:
	ceph_debugfs_cleanup();
out:
	return ret;
}

static void __exit exit_ceph(void)
{
	dout("exit_ceph\n");
	unregister_filesystem(&ceph_fs_type);
	ceph_caps_finalize();
	destroy_caches();
	ceph_msgr_exit();
	ceph_debugfs_cleanup();
}

module_init(init_ceph);
module_exit(exit_ceph);

MODULE_AUTHOR("Sage Weil <sage@newdream.net>");
MODULE_AUTHOR("Yehuda Sadeh <yehuda@hq.newdream.net>");
MODULE_AUTHOR("Patience Warnick <patience@newdream.net>");
MODULE_DESCRIPTION("Ceph filesystem for Linux");
MODULE_LICENSE("GPL");