osd_client.c 118.5 KB
Newer Older
1

2
#include <linux/ceph/ceph_debug.h>
S
Sage Weil 已提交
3

4
#include <linux/module.h>
S
Sage Weil 已提交
5 6 7 8 9 10
#include <linux/err.h>
#include <linux/highmem.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
11 12 13
#ifdef CONFIG_BLOCK
#include <linux/bio.h>
#endif
S
Sage Weil 已提交
14

15 16 17 18 19 20
#include <linux/ceph/libceph.h>
#include <linux/ceph/osd_client.h>
#include <linux/ceph/messenger.h>
#include <linux/ceph/decode.h>
#include <linux/ceph/auth.h>
#include <linux/ceph/pagelist.h>
S
Sage Weil 已提交
21

S
Sage Weil 已提交
22
#define OSD_OPREPLY_FRONT_LEN	512
23

24 25
static struct kmem_cache	*ceph_osd_request_cache;

26
static const struct ceph_connection_operations osd_con_ops;
S
Sage Weil 已提交
27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45

/*
 * Implement client access to distributed object storage cluster.
 *
 * All data objects are stored within a cluster/cloud of OSDs, or
 * "object storage devices."  (Note that Ceph OSDs have _nothing_ to
 * do with the T10 OSD extensions to SCSI.)  Ceph OSDs are simply
 * remote daemons serving up and coordinating consistent and safe
 * access to storage.
 *
 * Cluster membership and the mapping of data objects onto storage devices
 * are described by the osd map.
 *
 * We keep track of pending OSD requests (read, write), resubmit
 * requests to different OSDs when the cluster topology/data layout
 * change, or retry the affected requests when the communications
 * channel with an OSD is reset.
 */

46 47
static void link_request(struct ceph_osd *osd, struct ceph_osd_request *req);
static void unlink_request(struct ceph_osd *osd, struct ceph_osd_request *req);
48 49 50 51
static void link_linger(struct ceph_osd *osd,
			struct ceph_osd_linger_request *lreq);
static void unlink_linger(struct ceph_osd *osd,
			  struct ceph_osd_linger_request *lreq);
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

#if 1
static inline bool rwsem_is_wrlocked(struct rw_semaphore *sem)
{
	bool wrlocked = true;

	if (unlikely(down_read_trylock(sem))) {
		wrlocked = false;
		up_read(sem);
	}

	return wrlocked;
}
static inline void verify_osdc_locked(struct ceph_osd_client *osdc)
{
	WARN_ON(!rwsem_is_locked(&osdc->lock));
}
static inline void verify_osdc_wrlocked(struct ceph_osd_client *osdc)
{
	WARN_ON(!rwsem_is_wrlocked(&osdc->lock));
}
static inline void verify_osd_locked(struct ceph_osd *osd)
{
	struct ceph_osd_client *osdc = osd->o_osdc;

	WARN_ON(!(mutex_is_locked(&osd->lock) &&
		  rwsem_is_locked(&osdc->lock)) &&
		!rwsem_is_wrlocked(&osdc->lock));
}
81 82 83 84
static inline void verify_lreq_locked(struct ceph_osd_linger_request *lreq)
{
	WARN_ON(!mutex_is_locked(&lreq->lock));
}
85 86 87 88
#else
static inline void verify_osdc_locked(struct ceph_osd_client *osdc) { }
static inline void verify_osdc_wrlocked(struct ceph_osd_client *osdc) { }
static inline void verify_osd_locked(struct ceph_osd *osd) { }
89
static inline void verify_lreq_locked(struct ceph_osd_linger_request *lreq) { }
90 91
#endif

S
Sage Weil 已提交
92 93 94 95 96 97 98
/*
 * calculate the mapping of a file extent onto an object, and fill out the
 * request accordingly.  shorten extent as necessary if it crosses an
 * object boundary.
 *
 * fill osd op in request message.
 */
99
static int calc_layout(struct ceph_file_layout *layout, u64 off, u64 *plen,
100
			u64 *objnum, u64 *objoff, u64 *objlen)
S
Sage Weil 已提交
101
{
102
	u64 orig_len = *plen;
S
Sage Weil 已提交
103
	int r;
S
Sage Weil 已提交
104

105
	/* object extent? */
106 107
	r = ceph_calc_file_object_mapping(layout, off, orig_len, objnum,
					  objoff, objlen);
S
Sage Weil 已提交
108 109
	if (r < 0)
		return r;
110 111
	if (*objlen < orig_len) {
		*plen = *objlen;
112 113 114 115
		dout(" skipping last %llu, final file extent %llu~%llu\n",
		     orig_len - *plen, off, *plen);
	}

116
	dout("calc_layout objnum=%llx %llu~%llu\n", *objnum, *objoff, *objlen);
S
Sage Weil 已提交
117

118
	return 0;
S
Sage Weil 已提交
119 120
}

A
Alex Elder 已提交
121 122 123 124 125 126
static void ceph_osd_data_init(struct ceph_osd_data *osd_data)
{
	memset(osd_data, 0, sizeof (*osd_data));
	osd_data->type = CEPH_OSD_DATA_TYPE_NONE;
}

127
static void ceph_osd_data_pages_init(struct ceph_osd_data *osd_data,
128 129 130 131 132 133 134 135 136 137 138
			struct page **pages, u64 length, u32 alignment,
			bool pages_from_pool, bool own_pages)
{
	osd_data->type = CEPH_OSD_DATA_TYPE_PAGES;
	osd_data->pages = pages;
	osd_data->length = length;
	osd_data->alignment = alignment;
	osd_data->pages_from_pool = pages_from_pool;
	osd_data->own_pages = own_pages;
}

139
static void ceph_osd_data_pagelist_init(struct ceph_osd_data *osd_data,
140 141 142 143 144 145 146
			struct ceph_pagelist *pagelist)
{
	osd_data->type = CEPH_OSD_DATA_TYPE_PAGELIST;
	osd_data->pagelist = pagelist;
}

#ifdef CONFIG_BLOCK
147
static void ceph_osd_data_bio_init(struct ceph_osd_data *osd_data,
148 149 150 151 152 153 154 155
			struct bio *bio, size_t bio_length)
{
	osd_data->type = CEPH_OSD_DATA_TYPE_BIO;
	osd_data->bio = bio;
	osd_data->bio_length = bio_length;
}
#endif /* CONFIG_BLOCK */

156 157 158 159 160 161 162
#define osd_req_op_data(oreq, whch, typ, fld)				\
({									\
	struct ceph_osd_request *__oreq = (oreq);			\
	unsigned int __whch = (whch);					\
	BUG_ON(__whch >= __oreq->r_num_ops);				\
	&__oreq->r_ops[__whch].typ.fld;					\
})
163

A
Alex Elder 已提交
164 165 166 167 168 169 170 171
static struct ceph_osd_data *
osd_req_op_raw_data_in(struct ceph_osd_request *osd_req, unsigned int which)
{
	BUG_ON(which >= osd_req->r_num_ops);

	return &osd_req->r_ops[which].raw_data_in;
}

172 173
struct ceph_osd_data *
osd_req_op_extent_osd_data(struct ceph_osd_request *osd_req,
174
			unsigned int which)
175
{
176
	return osd_req_op_data(osd_req, which, extent, osd_data);
177 178 179
}
EXPORT_SYMBOL(osd_req_op_extent_osd_data);

A
Alex Elder 已提交
180 181 182 183 184 185 186 187 188 189 190 191 192
void osd_req_op_raw_data_in_pages(struct ceph_osd_request *osd_req,
			unsigned int which, struct page **pages,
			u64 length, u32 alignment,
			bool pages_from_pool, bool own_pages)
{
	struct ceph_osd_data *osd_data;

	osd_data = osd_req_op_raw_data_in(osd_req, which);
	ceph_osd_data_pages_init(osd_data, pages, length, alignment,
				pages_from_pool, own_pages);
}
EXPORT_SYMBOL(osd_req_op_raw_data_in_pages);

193
void osd_req_op_extent_osd_data_pages(struct ceph_osd_request *osd_req,
194 195
			unsigned int which, struct page **pages,
			u64 length, u32 alignment,
196 197 198 199
			bool pages_from_pool, bool own_pages)
{
	struct ceph_osd_data *osd_data;

200
	osd_data = osd_req_op_data(osd_req, which, extent, osd_data);
201 202 203 204 205 206
	ceph_osd_data_pages_init(osd_data, pages, length, alignment,
				pages_from_pool, own_pages);
}
EXPORT_SYMBOL(osd_req_op_extent_osd_data_pages);

void osd_req_op_extent_osd_data_pagelist(struct ceph_osd_request *osd_req,
207
			unsigned int which, struct ceph_pagelist *pagelist)
208 209 210
{
	struct ceph_osd_data *osd_data;

211
	osd_data = osd_req_op_data(osd_req, which, extent, osd_data);
212 213 214 215 216 217
	ceph_osd_data_pagelist_init(osd_data, pagelist);
}
EXPORT_SYMBOL(osd_req_op_extent_osd_data_pagelist);

#ifdef CONFIG_BLOCK
void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *osd_req,
218
			unsigned int which, struct bio *bio, size_t bio_length)
219 220
{
	struct ceph_osd_data *osd_data;
221 222

	osd_data = osd_req_op_data(osd_req, which, extent, osd_data);
223 224 225 226 227 228 229 230 231 232 233
	ceph_osd_data_bio_init(osd_data, bio, bio_length);
}
EXPORT_SYMBOL(osd_req_op_extent_osd_data_bio);
#endif /* CONFIG_BLOCK */

static void osd_req_op_cls_request_info_pagelist(
			struct ceph_osd_request *osd_req,
			unsigned int which, struct ceph_pagelist *pagelist)
{
	struct ceph_osd_data *osd_data;

234
	osd_data = osd_req_op_data(osd_req, which, cls, request_info);
235 236 237
	ceph_osd_data_pagelist_init(osd_data, pagelist);
}

238 239 240 241 242 243
void osd_req_op_cls_request_data_pagelist(
			struct ceph_osd_request *osd_req,
			unsigned int which, struct ceph_pagelist *pagelist)
{
	struct ceph_osd_data *osd_data;

244
	osd_data = osd_req_op_data(osd_req, which, cls, request_data);
245
	ceph_osd_data_pagelist_init(osd_data, pagelist);
246 247
	osd_req->r_ops[which].cls.indata_len += pagelist->length;
	osd_req->r_ops[which].indata_len += pagelist->length;
248 249 250
}
EXPORT_SYMBOL(osd_req_op_cls_request_data_pagelist);

251 252 253 254 255 256 257 258 259
void osd_req_op_cls_request_data_pages(struct ceph_osd_request *osd_req,
			unsigned int which, struct page **pages, u64 length,
			u32 alignment, bool pages_from_pool, bool own_pages)
{
	struct ceph_osd_data *osd_data;

	osd_data = osd_req_op_data(osd_req, which, cls, request_data);
	ceph_osd_data_pages_init(osd_data, pages, length, alignment,
				pages_from_pool, own_pages);
260 261
	osd_req->r_ops[which].cls.indata_len += length;
	osd_req->r_ops[which].indata_len += length;
262 263 264
}
EXPORT_SYMBOL(osd_req_op_cls_request_data_pages);

265 266 267 268 269 270
void osd_req_op_cls_response_data_pages(struct ceph_osd_request *osd_req,
			unsigned int which, struct page **pages, u64 length,
			u32 alignment, bool pages_from_pool, bool own_pages)
{
	struct ceph_osd_data *osd_data;

271
	osd_data = osd_req_op_data(osd_req, which, cls, response_data);
272 273 274 275 276
	ceph_osd_data_pages_init(osd_data, pages, length, alignment,
				pages_from_pool, own_pages);
}
EXPORT_SYMBOL(osd_req_op_cls_response_data_pages);

277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295
static u64 ceph_osd_data_length(struct ceph_osd_data *osd_data)
{
	switch (osd_data->type) {
	case CEPH_OSD_DATA_TYPE_NONE:
		return 0;
	case CEPH_OSD_DATA_TYPE_PAGES:
		return osd_data->length;
	case CEPH_OSD_DATA_TYPE_PAGELIST:
		return (u64)osd_data->pagelist->length;
#ifdef CONFIG_BLOCK
	case CEPH_OSD_DATA_TYPE_BIO:
		return (u64)osd_data->bio_length;
#endif /* CONFIG_BLOCK */
	default:
		WARN(true, "unrecognized data type %d\n", (int)osd_data->type);
		return 0;
	}
}

A
Alex Elder 已提交
296 297
static void ceph_osd_data_release(struct ceph_osd_data *osd_data)
{
298
	if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGES && osd_data->own_pages) {
A
Alex Elder 已提交
299 300 301 302 303 304
		int num_pages;

		num_pages = calc_pages_for((u64)osd_data->alignment,
						(u64)osd_data->length);
		ceph_release_page_vector(osd_data->pages, num_pages);
	}
305 306 307 308 309 310 311 312 313 314 315 316 317 318
	ceph_osd_data_init(osd_data);
}

static void osd_req_op_data_release(struct ceph_osd_request *osd_req,
			unsigned int which)
{
	struct ceph_osd_req_op *op;

	BUG_ON(which >= osd_req->r_num_ops);
	op = &osd_req->r_ops[which];

	switch (op->op) {
	case CEPH_OSD_OP_READ:
	case CEPH_OSD_OP_WRITE:
319
	case CEPH_OSD_OP_WRITEFULL:
320 321 322 323
		ceph_osd_data_release(&op->extent.osd_data);
		break;
	case CEPH_OSD_OP_CALL:
		ceph_osd_data_release(&op->cls.request_info);
324
		ceph_osd_data_release(&op->cls.request_data);
325 326
		ceph_osd_data_release(&op->cls.response_data);
		break;
327 328 329 330
	case CEPH_OSD_OP_SETXATTR:
	case CEPH_OSD_OP_CMPXATTR:
		ceph_osd_data_release(&op->xattr.osd_data);
		break;
331 332 333
	case CEPH_OSD_OP_STAT:
		ceph_osd_data_release(&op->raw_data_in);
		break;
334 335 336
	case CEPH_OSD_OP_NOTIFY_ACK:
		ceph_osd_data_release(&op->notify_ack.request_data);
		break;
337 338 339 340
	case CEPH_OSD_OP_NOTIFY:
		ceph_osd_data_release(&op->notify.request_data);
		ceph_osd_data_release(&op->notify.response_data);
		break;
341 342 343
	case CEPH_OSD_OP_LIST_WATCHERS:
		ceph_osd_data_release(&op->list_watchers.response_data);
		break;
344 345 346
	default:
		break;
	}
A
Alex Elder 已提交
347 348
}

349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366
/*
 * Assumes @t is zero-initialized.
 */
static void target_init(struct ceph_osd_request_target *t)
{
	ceph_oid_init(&t->base_oid);
	ceph_oloc_init(&t->base_oloc);
	ceph_oid_init(&t->target_oid);
	ceph_oloc_init(&t->target_oloc);

	ceph_osds_init(&t->acting);
	ceph_osds_init(&t->up);
	t->size = -1;
	t->min_size = -1;

	t->osd = CEPH_HOMELESS_OSD;
}

367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386
static void target_copy(struct ceph_osd_request_target *dest,
			const struct ceph_osd_request_target *src)
{
	ceph_oid_copy(&dest->base_oid, &src->base_oid);
	ceph_oloc_copy(&dest->base_oloc, &src->base_oloc);
	ceph_oid_copy(&dest->target_oid, &src->target_oid);
	ceph_oloc_copy(&dest->target_oloc, &src->target_oloc);

	dest->pgid = src->pgid; /* struct */
	dest->pg_num = src->pg_num;
	dest->pg_num_mask = src->pg_num_mask;
	ceph_osds_copy(&dest->acting, &src->acting);
	ceph_osds_copy(&dest->up, &src->up);
	dest->size = src->size;
	dest->min_size = src->min_size;
	dest->sort_bitwise = src->sort_bitwise;

	dest->flags = src->flags;
	dest->paused = src->paused;

387 388
	dest->last_force_resend = src->last_force_resend;

389 390 391
	dest->osd = src->osd;
}

392 393 394
static void target_destroy(struct ceph_osd_request_target *t)
{
	ceph_oid_destroy(&t->base_oid);
395
	ceph_oloc_destroy(&t->base_oloc);
396
	ceph_oid_destroy(&t->target_oid);
397
	ceph_oloc_destroy(&t->target_oloc);
398 399
}

S
Sage Weil 已提交
400 401 402
/*
 * requests
 */
403 404 405
static void request_release_checks(struct ceph_osd_request *req)
{
	WARN_ON(!RB_EMPTY_NODE(&req->r_node));
I
Ilya Dryomov 已提交
406
	WARN_ON(!RB_EMPTY_NODE(&req->r_mc_node));
407 408 409 410
	WARN_ON(!list_empty(&req->r_unsafe_item));
	WARN_ON(req->r_osd);
}

411
static void ceph_osdc_release_request(struct kref *kref)
S
Sage Weil 已提交
412
{
413 414
	struct ceph_osd_request *req = container_of(kref,
					    struct ceph_osd_request, r_kref);
415
	unsigned int which;
S
Sage Weil 已提交
416

417 418
	dout("%s %p (r_request %p r_reply %p)\n", __func__, req,
	     req->r_request, req->r_reply);
419
	request_release_checks(req);
420

S
Sage Weil 已提交
421 422
	if (req->r_request)
		ceph_msg_put(req->r_request);
423
	if (req->r_reply)
424
		ceph_msg_put(req->r_reply);
425

426 427
	for (which = 0; which < req->r_num_ops; which++)
		osd_req_op_data_release(req, which);
428

429
	target_destroy(&req->r_t);
S
Sage Weil 已提交
430
	ceph_put_snap_context(req->r_snapc);
431

S
Sage Weil 已提交
432 433
	if (req->r_mempool)
		mempool_free(req, req->r_osdc->req_mempool);
434
	else if (req->r_num_ops <= CEPH_OSD_SLAB_OPS)
435
		kmem_cache_free(ceph_osd_request_cache, req);
436 437
	else
		kfree(req);
S
Sage Weil 已提交
438
}
439 440 441 442

void ceph_osdc_get_request(struct ceph_osd_request *req)
{
	dout("%s %p (was %d)\n", __func__, req,
443
	     kref_read(&req->r_kref));
444 445 446 447 448 449
	kref_get(&req->r_kref);
}
EXPORT_SYMBOL(ceph_osdc_get_request);

void ceph_osdc_put_request(struct ceph_osd_request *req)
{
450 451
	if (req) {
		dout("%s %p (was %d)\n", __func__, req,
452
		     kref_read(&req->r_kref));
453 454
		kref_put(&req->r_kref, ceph_osdc_release_request);
	}
455 456
}
EXPORT_SYMBOL(ceph_osdc_put_request);
457

458 459 460 461 462 463 464 465
static void request_init(struct ceph_osd_request *req)
{
	/* req only, each op is zeroed in _osd_req_op_init() */
	memset(req, 0, sizeof(*req));

	kref_init(&req->r_kref);
	init_completion(&req->r_completion);
	RB_CLEAR_NODE(&req->r_node);
I
Ilya Dryomov 已提交
466
	RB_CLEAR_NODE(&req->r_mc_node);
467 468 469 470 471
	INIT_LIST_HEAD(&req->r_unsafe_item);

	target_init(&req->r_t);
}

472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490
/*
 * This is ugly, but it allows us to reuse linger registration and ping
 * requests, keeping the structure of the code around send_linger{_ping}()
 * reasonable.  Setting up a min_nr=2 mempool for each linger request
 * and dealing with copying ops (this blasts req only, watch op remains
 * intact) isn't any better.
 */
static void request_reinit(struct ceph_osd_request *req)
{
	struct ceph_osd_client *osdc = req->r_osdc;
	bool mempool = req->r_mempool;
	unsigned int num_ops = req->r_num_ops;
	u64 snapid = req->r_snapid;
	struct ceph_snap_context *snapc = req->r_snapc;
	bool linger = req->r_linger;
	struct ceph_msg *request_msg = req->r_request;
	struct ceph_msg *reply_msg = req->r_reply;

	dout("%s req %p\n", __func__, req);
491
	WARN_ON(kref_read(&req->r_kref) != 1);
492 493
	request_release_checks(req);

494 495
	WARN_ON(kref_read(&request_msg->kref) != 1);
	WARN_ON(kref_read(&reply_msg->kref) != 1);
496 497 498 499 500 501 502 503 504 505 506 507 508
	target_destroy(&req->r_t);

	request_init(req);
	req->r_osdc = osdc;
	req->r_mempool = mempool;
	req->r_num_ops = num_ops;
	req->r_snapid = snapid;
	req->r_snapc = snapc;
	req->r_linger = linger;
	req->r_request = request_msg;
	req->r_reply = reply_msg;
}

509
struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
S
Sage Weil 已提交
510
					       struct ceph_snap_context *snapc,
511
					       unsigned int num_ops,
512
					       bool use_mempool,
513
					       gfp_t gfp_flags)
S
Sage Weil 已提交
514 515
{
	struct ceph_osd_request *req;
516

S
Sage Weil 已提交
517
	if (use_mempool) {
518
		BUG_ON(num_ops > CEPH_OSD_SLAB_OPS);
519
		req = mempool_alloc(osdc->req_mempool, gfp_flags);
520 521
	} else if (num_ops <= CEPH_OSD_SLAB_OPS) {
		req = kmem_cache_alloc(ceph_osd_request_cache, gfp_flags);
S
Sage Weil 已提交
522
	} else {
523 524 525
		BUG_ON(num_ops > CEPH_OSD_MAX_OPS);
		req = kmalloc(sizeof(*req) + num_ops * sizeof(req->r_ops[0]),
			      gfp_flags);
S
Sage Weil 已提交
526
	}
527
	if (unlikely(!req))
528
		return NULL;
S
Sage Weil 已提交
529

530
	request_init(req);
S
Sage Weil 已提交
531 532
	req->r_osdc = osdc;
	req->r_mempool = use_mempool;
533
	req->r_num_ops = num_ops;
534 535
	req->r_snapid = CEPH_NOSNAP;
	req->r_snapc = ceph_get_snap_context(snapc);
536

537 538 539 540
	dout("%s req %p\n", __func__, req);
	return req;
}
EXPORT_SYMBOL(ceph_osdc_alloc_request);
541

542 543 544 545 546
static int ceph_oloc_encoding_size(struct ceph_object_locator *oloc)
{
	return 8 + 4 + 4 + 4 + (oloc->pool_ns ? oloc->pool_ns->len : 0);
}

547 548 549 550 551
int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp)
{
	struct ceph_osd_client *osdc = req->r_osdc;
	struct ceph_msg *msg;
	int msg_size;
S
Sage Weil 已提交
552

553
	WARN_ON(ceph_oid_empty(&req->r_base_oid));
554
	WARN_ON(ceph_oloc_empty(&req->r_base_oloc));
555

556
	/* create request message */
557 558
	msg_size = 4 + 4 + 4; /* client_inc, osdmap_epoch, flags */
	msg_size += 4 + 4 + 4 + 8; /* mtime, reassert_version */
559 560
	msg_size += CEPH_ENCODING_START_BLK_LEN +
			ceph_oloc_encoding_size(&req->r_base_oloc); /* oloc */
561
	msg_size += 1 + 8 + 4 + 4; /* pgid */
562 563
	msg_size += 4 + req->r_base_oid.name_len; /* oid */
	msg_size += 2 + req->r_num_ops * sizeof(struct ceph_osd_op);
564 565
	msg_size += 8; /* snapid */
	msg_size += 8; /* snap_seq */
566
	msg_size += 4 + 8 * (req->r_snapc ? req->r_snapc->num_snaps : 0);
567 568
	msg_size += 4; /* retry_attempt */

569
	if (req->r_mempool)
570
		msg = ceph_msgpool_get(&osdc->msgpool_op, 0);
S
Sage Weil 已提交
571
	else
572 573 574
		msg = ceph_msg_new(CEPH_MSG_OSD_OP, msg_size, gfp, true);
	if (!msg)
		return -ENOMEM;
575

S
Sage Weil 已提交
576
	memset(msg->front.iov_base, 0, msg->front.iov_len);
577 578
	req->r_request = msg;

579 580
	/* create reply message */
	msg_size = OSD_OPREPLY_FRONT_LEN;
581 582
	msg_size += req->r_base_oid.name_len;
	msg_size += req->r_num_ops * sizeof(struct ceph_osd_op);
583 584 585 586 587 588 589 590 591 592 593

	if (req->r_mempool)
		msg = ceph_msgpool_get(&osdc->msgpool_op_reply, 0);
	else
		msg = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, msg_size, gfp, true);
	if (!msg)
		return -ENOMEM;

	req->r_reply = msg;

	return 0;
594
}
595
EXPORT_SYMBOL(ceph_osdc_alloc_messages);
596

597
static bool osd_req_opcode_valid(u16 opcode)
598
{
599
	switch (opcode) {
600 601 602
#define GENERATE_CASE(op, opcode, str)	case CEPH_OSD_OP_##op: return true;
__CEPH_FORALL_OSD_OPS(GENERATE_CASE)
#undef GENERATE_CASE
603 604 605 606 607
	default:
		return false;
	}
}

608 609 610 611 612
/*
 * This is an osd op init function for opcodes that have no data or
 * other information associated with them.  It also serves as a
 * common init routine for all the other init functions, below.
 */
613
static struct ceph_osd_req_op *
A
Alex Elder 已提交
614
_osd_req_op_init(struct ceph_osd_request *osd_req, unsigned int which,
615
		 u16 opcode, u32 flags)
616
{
617 618 619
	struct ceph_osd_req_op *op;

	BUG_ON(which >= osd_req->r_num_ops);
620 621
	BUG_ON(!osd_req_opcode_valid(opcode));

622
	op = &osd_req->r_ops[which];
623 624
	memset(op, 0, sizeof (*op));
	op->op = opcode;
625
	op->flags = flags;
626 627

	return op;
628 629
}

A
Alex Elder 已提交
630
void osd_req_op_init(struct ceph_osd_request *osd_req,
631
		     unsigned int which, u16 opcode, u32 flags)
A
Alex Elder 已提交
632
{
633
	(void)_osd_req_op_init(osd_req, which, opcode, flags);
A
Alex Elder 已提交
634 635 636
}
EXPORT_SYMBOL(osd_req_op_init);

637 638
void osd_req_op_extent_init(struct ceph_osd_request *osd_req,
				unsigned int which, u16 opcode,
639 640 641
				u64 offset, u64 length,
				u64 truncate_size, u32 truncate_seq)
{
642 643
	struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
						      opcode, 0);
644 645
	size_t payload_len = 0;

L
Li Wang 已提交
646
	BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE &&
647 648
	       opcode != CEPH_OSD_OP_WRITEFULL && opcode != CEPH_OSD_OP_ZERO &&
	       opcode != CEPH_OSD_OP_TRUNCATE);
649 650 651 652 653

	op->extent.offset = offset;
	op->extent.length = length;
	op->extent.truncate_size = truncate_size;
	op->extent.truncate_seq = truncate_seq;
654
	if (opcode == CEPH_OSD_OP_WRITE || opcode == CEPH_OSD_OP_WRITEFULL)
655 656
		payload_len += length;

657
	op->indata_len = payload_len;
658 659 660
}
EXPORT_SYMBOL(osd_req_op_extent_init);

661 662
void osd_req_op_extent_update(struct ceph_osd_request *osd_req,
				unsigned int which, u64 length)
663
{
664 665 666 667 668 669
	struct ceph_osd_req_op *op;
	u64 previous;

	BUG_ON(which >= osd_req->r_num_ops);
	op = &osd_req->r_ops[which];
	previous = op->extent.length;
670 671 672 673 674 675

	if (length == previous)
		return;		/* Nothing to do */
	BUG_ON(length > previous);

	op->extent.length = length;
676 677
	if (op->op == CEPH_OSD_OP_WRITE || op->op == CEPH_OSD_OP_WRITEFULL)
		op->indata_len -= previous - length;
678 679 680
}
EXPORT_SYMBOL(osd_req_op_extent_update);

681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702
void osd_req_op_extent_dup_last(struct ceph_osd_request *osd_req,
				unsigned int which, u64 offset_inc)
{
	struct ceph_osd_req_op *op, *prev_op;

	BUG_ON(which + 1 >= osd_req->r_num_ops);

	prev_op = &osd_req->r_ops[which];
	op = _osd_req_op_init(osd_req, which + 1, prev_op->op, prev_op->flags);
	/* dup previous one */
	op->indata_len = prev_op->indata_len;
	op->outdata_len = prev_op->outdata_len;
	op->extent = prev_op->extent;
	/* adjust offset */
	op->extent.offset += offset_inc;
	op->extent.length -= offset_inc;

	if (op->op == CEPH_OSD_OP_WRITE || op->op == CEPH_OSD_OP_WRITEFULL)
		op->indata_len -= offset_inc;
}
EXPORT_SYMBOL(osd_req_op_extent_dup_last);

703
void osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which,
704
			u16 opcode, const char *class, const char *method)
705
{
706 707
	struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
						      opcode, 0);
708
	struct ceph_pagelist *pagelist;
709 710 711 712 713
	size_t payload_len = 0;
	size_t size;

	BUG_ON(opcode != CEPH_OSD_OP_CALL);

714 715 716 717
	pagelist = kmalloc(sizeof (*pagelist), GFP_NOFS);
	BUG_ON(!pagelist);
	ceph_pagelist_init(pagelist);

718 719 720 721
	op->cls.class_name = class;
	size = strlen(class);
	BUG_ON(size > (size_t) U8_MAX);
	op->cls.class_len = size;
722
	ceph_pagelist_append(pagelist, class, size);
723 724 725 726 727 728
	payload_len += size;

	op->cls.method_name = method;
	size = strlen(method);
	BUG_ON(size > (size_t) U8_MAX);
	op->cls.method_len = size;
729
	ceph_pagelist_append(pagelist, method, size);
730 731
	payload_len += size;

732
	osd_req_op_cls_request_info_pagelist(osd_req, which, pagelist);
733

734
	op->indata_len = payload_len;
735 736
}
EXPORT_SYMBOL(osd_req_op_cls_init);
737

738 739 740 741
int osd_req_op_xattr_init(struct ceph_osd_request *osd_req, unsigned int which,
			  u16 opcode, const char *name, const void *value,
			  size_t size, u8 cmp_op, u8 cmp_mode)
{
742 743
	struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
						      opcode, 0);
744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766
	struct ceph_pagelist *pagelist;
	size_t payload_len;

	BUG_ON(opcode != CEPH_OSD_OP_SETXATTR && opcode != CEPH_OSD_OP_CMPXATTR);

	pagelist = kmalloc(sizeof(*pagelist), GFP_NOFS);
	if (!pagelist)
		return -ENOMEM;

	ceph_pagelist_init(pagelist);

	payload_len = strlen(name);
	op->xattr.name_len = payload_len;
	ceph_pagelist_append(pagelist, name, payload_len);

	op->xattr.value_len = size;
	ceph_pagelist_append(pagelist, value, size);
	payload_len += size;

	op->xattr.cmp_op = cmp_op;
	op->xattr.cmp_mode = cmp_mode;

	ceph_osd_data_pagelist_init(&op->xattr.osd_data, pagelist);
767
	op->indata_len = payload_len;
768 769 770 771
	return 0;
}
EXPORT_SYMBOL(osd_req_op_xattr_init);

772 773 774 775 776
/*
 * @watch_opcode: CEPH_OSD_WATCH_OP_*
 */
static void osd_req_op_watch_init(struct ceph_osd_request *req, int which,
				  u64 cookie, u8 watch_opcode)
777
{
778
	struct ceph_osd_req_op *op;
779

780
	op = _osd_req_op_init(req, which, CEPH_OSD_OP_WATCH, 0);
781
	op->watch.cookie = cookie;
782 783
	op->watch.op = watch_opcode;
	op->watch.gen = 0;
784 785
}

786 787 788 789 790 791
void osd_req_op_alloc_hint_init(struct ceph_osd_request *osd_req,
				unsigned int which,
				u64 expected_object_size,
				u64 expected_write_size)
{
	struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
792 793
						      CEPH_OSD_OP_SETALLOCHINT,
						      0);
794 795 796 797 798 799 800 801 802 803 804 805 806

	op->alloc_hint.expected_object_size = expected_object_size;
	op->alloc_hint.expected_write_size = expected_write_size;

	/*
	 * CEPH_OSD_OP_SETALLOCHINT op is advisory and therefore deemed
	 * not worth a feature bit.  Set FAILOK per-op flag to make
	 * sure older osds don't trip over an unsupported opcode.
	 */
	op->flags |= CEPH_OSD_OP_FLAG_FAILOK;
}
EXPORT_SYMBOL(osd_req_op_alloc_hint_init);

807
static void ceph_osdc_msg_data_add(struct ceph_msg *msg,
808 809 810 811 812 813 814
				struct ceph_osd_data *osd_data)
{
	u64 length = ceph_osd_data_length(osd_data);

	if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGES) {
		BUG_ON(length > (u64) SIZE_MAX);
		if (length)
815
			ceph_msg_data_add_pages(msg, osd_data->pages,
816 817 818
					length, osd_data->alignment);
	} else if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGELIST) {
		BUG_ON(!length);
819
		ceph_msg_data_add_pagelist(msg, osd_data->pagelist);
820 821
#ifdef CONFIG_BLOCK
	} else if (osd_data->type == CEPH_OSD_DATA_TYPE_BIO) {
822
		ceph_msg_data_add_bio(msg, osd_data->bio, length);
823 824 825 826 827 828
#endif
	} else {
		BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_NONE);
	}
}

829 830
static u32 osd_req_encode_op(struct ceph_osd_op *dst,
			     const struct ceph_osd_req_op *src)
831 832 833 834 835 836 837 838 839 840 841 842
{
	if (WARN_ON(!osd_req_opcode_valid(src->op))) {
		pr_err("unrecognized osd opcode %d\n", src->op);

		return 0;
	}

	switch (src->op) {
	case CEPH_OSD_OP_STAT:
		break;
	case CEPH_OSD_OP_READ:
	case CEPH_OSD_OP_WRITE:
843
	case CEPH_OSD_OP_WRITEFULL:
L
Li Wang 已提交
844 845
	case CEPH_OSD_OP_ZERO:
	case CEPH_OSD_OP_TRUNCATE:
846 847 848 849 850 851 852 853 854 855
		dst->extent.offset = cpu_to_le64(src->extent.offset);
		dst->extent.length = cpu_to_le64(src->extent.length);
		dst->extent.truncate_size =
			cpu_to_le64(src->extent.truncate_size);
		dst->extent.truncate_seq =
			cpu_to_le32(src->extent.truncate_seq);
		break;
	case CEPH_OSD_OP_CALL:
		dst->cls.class_len = src->cls.class_len;
		dst->cls.method_len = src->cls.method_len;
856
		dst->cls.indata_len = cpu_to_le32(src->cls.indata_len);
857 858 859 860 861
		break;
	case CEPH_OSD_OP_STARTSYNC:
		break;
	case CEPH_OSD_OP_WATCH:
		dst->watch.cookie = cpu_to_le64(src->watch.cookie);
862 863 864 865 866
		dst->watch.ver = cpu_to_le64(0);
		dst->watch.op = src->watch.op;
		dst->watch.gen = cpu_to_le32(src->watch.gen);
		break;
	case CEPH_OSD_OP_NOTIFY_ACK:
867
		break;
868 869 870
	case CEPH_OSD_OP_NOTIFY:
		dst->notify.cookie = cpu_to_le64(src->notify.cookie);
		break;
871 872
	case CEPH_OSD_OP_LIST_WATCHERS:
		break;
873 874 875 876 877 878
	case CEPH_OSD_OP_SETALLOCHINT:
		dst->alloc_hint.expected_object_size =
		    cpu_to_le64(src->alloc_hint.expected_object_size);
		dst->alloc_hint.expected_write_size =
		    cpu_to_le64(src->alloc_hint.expected_write_size);
		break;
879 880 881 882 883 884 885
	case CEPH_OSD_OP_SETXATTR:
	case CEPH_OSD_OP_CMPXATTR:
		dst->xattr.name_len = cpu_to_le32(src->xattr.name_len);
		dst->xattr.value_len = cpu_to_le32(src->xattr.value_len);
		dst->xattr.cmp_op = src->xattr.cmp_op;
		dst->xattr.cmp_mode = src->xattr.cmp_mode;
		break;
886 887 888
	case CEPH_OSD_OP_CREATE:
	case CEPH_OSD_OP_DELETE:
		break;
889
	default:
890
		pr_err("unsupported osd opcode %s\n",
891
			ceph_osd_op_name(src->op));
892
		WARN_ON(1);
893 894

		return 0;
895
	}
896

897
	dst->op = cpu_to_le16(src->op);
898
	dst->flags = cpu_to_le32(src->flags);
899
	dst->payload_len = cpu_to_le32(src->indata_len);
900

901
	return src->indata_len;
902 903
}

904 905 906 907 908 909 910 911 912 913 914 915 916 917
/*
 * build new request AND message, calculate layout, and adjust file
 * extent as needed.
 *
 * if the file was recently truncated, we include information about its
 * old and new size so that the object can be updated appropriately.  (we
 * avoid synchronously deleting truncated objects because it's slow.)
 *
 * if @do_sync, include a 'startsync' command so that the osd will flush
 * data quickly.
 */
struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
					       struct ceph_file_layout *layout,
					       struct ceph_vino vino,
918 919
					       u64 off, u64 *plen,
					       unsigned int which, int num_ops,
920 921 922 923
					       int opcode, int flags,
					       struct ceph_snap_context *snapc,
					       u32 truncate_seq,
					       u64 truncate_size,
924
					       bool use_mempool)
925
{
926
	struct ceph_osd_request *req;
927 928 929
	u64 objnum = 0;
	u64 objoff = 0;
	u64 objlen = 0;
930
	int r;
931

L
Li Wang 已提交
932
	BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE &&
933 934
	       opcode != CEPH_OSD_OP_ZERO && opcode != CEPH_OSD_OP_TRUNCATE &&
	       opcode != CEPH_OSD_OP_CREATE && opcode != CEPH_OSD_OP_DELETE);
935

936
	req = ceph_osdc_alloc_request(osdc, snapc, num_ops, use_mempool,
A
Alex Elder 已提交
937
					GFP_NOFS);
938 939 940 941
	if (!req) {
		r = -ENOMEM;
		goto fail;
	}
942

943
	/* calculate max write size */
944
	r = calc_layout(layout, off, plen, &objnum, &objoff, &objlen);
945 946
	if (r)
		goto fail;
947

948
	if (opcode == CEPH_OSD_OP_CREATE || opcode == CEPH_OSD_OP_DELETE) {
949
		osd_req_op_init(req, which, opcode, 0);
950
	} else {
951
		u32 object_size = layout->object_size;
952 953 954 955 956 957 958 959 960
		u32 object_base = off - objoff;
		if (!(truncate_seq == 1 && truncate_size == -1ULL)) {
			if (truncate_size <= object_base) {
				truncate_size = 0;
			} else {
				truncate_size -= object_base;
				if (truncate_size > object_size)
					truncate_size = object_size;
			}
961
		}
962
		osd_req_op_extent_init(req, which, opcode, objoff, objlen,
963 964
				       truncate_size, truncate_seq);
	}
965

966
	req->r_abort_on_full = true;
967
	req->r_flags = flags;
968
	req->r_base_oloc.pool = layout->pool_id;
969
	req->r_base_oloc.pool_ns = ceph_try_get_string(layout->pool_ns);
970
	ceph_oid_printf(&req->r_base_oid, "%llx.%08llx", vino.ino, objnum);
971

972 973 974 975
	req->r_snapid = vino.snap;
	if (flags & CEPH_OSD_FLAG_WRITE)
		req->r_data_offset = off;

976 977 978 979
	r = ceph_osdc_alloc_messages(req, GFP_NOFS);
	if (r)
		goto fail;

S
Sage Weil 已提交
980
	return req;
981 982 983 984

fail:
	ceph_osdc_put_request(req);
	return ERR_PTR(r);
S
Sage Weil 已提交
985
}
986
EXPORT_SYMBOL(ceph_osdc_new_request);
S
Sage Weil 已提交
987 988 989 990

/*
 * We keep osd requests in an rbtree, sorted by ->r_tid.
 */
I
Ilya Dryomov 已提交
991
DEFINE_RB_FUNCS(request, struct ceph_osd_request, r_tid, r_node)
I
Ilya Dryomov 已提交
992
DEFINE_RB_FUNCS(request_mc, struct ceph_osd_request, r_tid, r_mc_node)
S
Sage Weil 已提交
993

994 995 996 997 998
static bool osd_homeless(struct ceph_osd *osd)
{
	return osd->o_osd == CEPH_HOMELESS_OSD;
}

999
static bool osd_registered(struct ceph_osd *osd)
S
Sage Weil 已提交
1000
{
1001
	verify_osdc_locked(osd->o_osdc);
S
Sage Weil 已提交
1002

1003
	return !RB_EMPTY_NODE(&osd->o_node);
S
Sage Weil 已提交
1004 1005
}

1006 1007 1008 1009 1010
/*
 * Assumes @osd is zero-initialized.
 */
static void osd_init(struct ceph_osd *osd)
{
1011
	refcount_set(&osd->o_ref, 1);
1012
	RB_CLEAR_NODE(&osd->o_node);
1013
	osd->o_requests = RB_ROOT;
1014
	osd->o_linger_requests = RB_ROOT;
1015 1016 1017
	INIT_LIST_HEAD(&osd->o_osd_lru);
	INIT_LIST_HEAD(&osd->o_keepalive_item);
	osd->o_incarnation = 1;
1018
	mutex_init(&osd->lock);
1019 1020 1021 1022 1023
}

static void osd_cleanup(struct ceph_osd *osd)
{
	WARN_ON(!RB_EMPTY_NODE(&osd->o_node));
1024
	WARN_ON(!RB_EMPTY_ROOT(&osd->o_requests));
1025
	WARN_ON(!RB_EMPTY_ROOT(&osd->o_linger_requests));
1026 1027 1028 1029 1030 1031 1032 1033 1034
	WARN_ON(!list_empty(&osd->o_osd_lru));
	WARN_ON(!list_empty(&osd->o_keepalive_item));

	if (osd->o_auth.authorizer) {
		WARN_ON(osd_homeless(osd));
		ceph_auth_destroy_authorizer(osd->o_auth.authorizer);
	}
}

S
Sage Weil 已提交
1035 1036 1037
/*
 * Track open sessions with osds.
 */
1038
static struct ceph_osd *create_osd(struct ceph_osd_client *osdc, int onum)
S
Sage Weil 已提交
1039 1040 1041
{
	struct ceph_osd *osd;

1042 1043
	WARN_ON(onum == CEPH_HOMELESS_OSD);

1044
	osd = kzalloc(sizeof(*osd), GFP_NOIO | __GFP_NOFAIL);
1045
	osd_init(osd);
S
Sage Weil 已提交
1046
	osd->o_osdc = osdc;
1047
	osd->o_osd = onum;
S
Sage Weil 已提交
1048

1049
	ceph_con_init(&osd->o_con, osd, &osd_con_ops, &osdc->client->msgr);
1050

S
Sage Weil 已提交
1051 1052 1053 1054 1055
	return osd;
}

static struct ceph_osd *get_osd(struct ceph_osd *osd)
{
1056 1057 1058
	if (refcount_inc_not_zero(&osd->o_ref)) {
		dout("get_osd %p %d -> %d\n", osd, refcount_read(&osd->o_ref)-1,
		     refcount_read(&osd->o_ref));
S
Sage Weil 已提交
1059 1060 1061 1062 1063 1064 1065 1066 1067
		return osd;
	} else {
		dout("get_osd %p FAIL\n", osd);
		return NULL;
	}
}

static void put_osd(struct ceph_osd *osd)
{
1068 1069 1070
	dout("put_osd %p %d -> %d\n", osd, refcount_read(&osd->o_ref),
	     refcount_read(&osd->o_ref) - 1);
	if (refcount_dec_and_test(&osd->o_ref)) {
1071
		osd_cleanup(osd);
S
Sage Weil 已提交
1072
		kfree(osd);
S
Sage Weil 已提交
1073
	}
S
Sage Weil 已提交
1074 1075
}

I
Ilya Dryomov 已提交
1076 1077
DEFINE_RB_FUNCS(osd, struct ceph_osd, o_osd, o_node)

1078
static void __move_osd_to_lru(struct ceph_osd *osd)
1079
{
1080 1081 1082
	struct ceph_osd_client *osdc = osd->o_osdc;

	dout("%s osd %p osd%d\n", __func__, osd, osd->o_osd);
1083
	BUG_ON(!list_empty(&osd->o_osd_lru));
1084

1085
	spin_lock(&osdc->osd_lru_lock);
1086
	list_add_tail(&osd->o_osd_lru, &osdc->osd_lru);
1087 1088
	spin_unlock(&osdc->osd_lru_lock);

1089
	osd->lru_ttl = jiffies + osdc->client->options->osd_idle_ttl;
1090 1091
}

1092
static void maybe_move_osd_to_lru(struct ceph_osd *osd)
1093
{
1094
	if (RB_EMPTY_ROOT(&osd->o_requests) &&
1095
	    RB_EMPTY_ROOT(&osd->o_linger_requests))
1096
		__move_osd_to_lru(osd);
1097 1098
}

1099 1100
static void __remove_osd_from_lru(struct ceph_osd *osd)
{
1101 1102 1103 1104 1105
	struct ceph_osd_client *osdc = osd->o_osdc;

	dout("%s osd %p osd%d\n", __func__, osd, osd->o_osd);

	spin_lock(&osdc->osd_lru_lock);
1106 1107
	if (!list_empty(&osd->o_osd_lru))
		list_del_init(&osd->o_osd_lru);
1108
	spin_unlock(&osdc->osd_lru_lock);
1109 1110
}

1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134
/*
 * Close the connection and assign any leftover requests to the
 * homeless session.
 */
static void close_osd(struct ceph_osd *osd)
{
	struct ceph_osd_client *osdc = osd->o_osdc;
	struct rb_node *n;

	verify_osdc_wrlocked(osdc);
	dout("%s osd %p osd%d\n", __func__, osd, osd->o_osd);

	ceph_con_close(&osd->o_con);

	for (n = rb_first(&osd->o_requests); n; ) {
		struct ceph_osd_request *req =
		    rb_entry(n, struct ceph_osd_request, r_node);

		n = rb_next(n); /* unlink_request() */

		dout(" reassigning req %p tid %llu\n", req, req->r_tid);
		unlink_request(osd, req);
		link_request(&osdc->homeless_osd, req);
	}
1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145
	for (n = rb_first(&osd->o_linger_requests); n; ) {
		struct ceph_osd_linger_request *lreq =
		    rb_entry(n, struct ceph_osd_linger_request, node);

		n = rb_next(n); /* unlink_linger() */

		dout(" reassigning lreq %p linger_id %llu\n", lreq,
		     lreq->linger_id);
		unlink_linger(osd, lreq);
		link_linger(&osdc->homeless_osd, lreq);
	}
1146 1147 1148 1149 1150 1151

	__remove_osd_from_lru(osd);
	erase_osd(&osdc->osds, osd);
	put_osd(osd);
}

S
Sage Weil 已提交
1152 1153 1154
/*
 * reset osd connect
 */
1155
static int reopen_osd(struct ceph_osd *osd)
S
Sage Weil 已提交
1156
{
A
Alex Elder 已提交
1157
	struct ceph_entity_addr *peer_addr;
S
Sage Weil 已提交
1158

1159 1160 1161
	dout("%s osd %p osd%d\n", __func__, osd, osd->o_osd);

	if (RB_EMPTY_ROOT(&osd->o_requests) &&
1162
	    RB_EMPTY_ROOT(&osd->o_linger_requests)) {
1163
		close_osd(osd);
A
Alex Elder 已提交
1164 1165 1166
		return -ENODEV;
	}

1167
	peer_addr = &osd->o_osdc->osdmap->osd_addr[osd->o_osd];
A
Alex Elder 已提交
1168 1169
	if (!memcmp(peer_addr, &osd->o_con.peer_addr, sizeof (*peer_addr)) &&
			!ceph_con_opened(&osd->o_con)) {
1170
		struct rb_node *n;
A
Alex Elder 已提交
1171

1172 1173
		dout("osd addr hasn't changed and connection never opened, "
		     "letting msgr retry\n");
1174
		/* touch each r_stamp for handle_timeout()'s benfit */
1175 1176 1177
		for (n = rb_first(&osd->o_requests); n; n = rb_next(n)) {
			struct ceph_osd_request *req =
			    rb_entry(n, struct ceph_osd_request, r_node);
1178
			req->r_stamp = jiffies;
1179
		}
A
Alex Elder 已提交
1180 1181

		return -EAGAIN;
S
Sage Weil 已提交
1182
	}
A
Alex Elder 已提交
1183 1184 1185 1186 1187 1188

	ceph_con_close(&osd->o_con);
	ceph_con_open(&osd->o_con, CEPH_ENTITY_TYPE_OSD, osd->o_osd, peer_addr);
	osd->o_incarnation++;

	return 0;
S
Sage Weil 已提交
1189 1190
}

1191 1192
static struct ceph_osd *lookup_create_osd(struct ceph_osd_client *osdc, int o,
					  bool wrlocked)
S
Sage Weil 已提交
1193
{
1194
	struct ceph_osd *osd;
1195

1196 1197 1198 1199
	if (wrlocked)
		verify_osdc_wrlocked(osdc);
	else
		verify_osdc_locked(osdc);
S
Sage Weil 已提交
1200

1201 1202 1203 1204 1205 1206 1207
	if (o != CEPH_HOMELESS_OSD)
		osd = lookup_osd(&osdc->osds, o);
	else
		osd = &osdc->homeless_osd;
	if (!osd) {
		if (!wrlocked)
			return ERR_PTR(-EAGAIN);
1208

1209 1210 1211 1212
		osd = create_osd(osdc, o);
		insert_osd(&osdc->osds, osd);
		ceph_con_open(&osd->o_con, CEPH_ENTITY_TYPE_OSD, osd->o_osd,
			      &osdc->osdmap->osd_addr[osd->o_osd]);
1213
	}
S
Sage Weil 已提交
1214

1215 1216
	dout("%s osdc %p osd%d -> osd %p\n", __func__, osdc, o, osd);
	return osd;
S
Sage Weil 已提交
1217 1218 1219
}

/*
1220 1221 1222
 * Create request <-> OSD session relation.
 *
 * @req has to be assigned a tid, @osd may be homeless.
S
Sage Weil 已提交
1223
 */
1224
static void link_request(struct ceph_osd *osd, struct ceph_osd_request *req)
S
Sage Weil 已提交
1225
{
1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238
	verify_osd_locked(osd);
	WARN_ON(!req->r_tid || req->r_osd);
	dout("%s osd %p osd%d req %p tid %llu\n", __func__, osd, osd->o_osd,
	     req, req->r_tid);

	if (!osd_homeless(osd))
		__remove_osd_from_lru(osd);
	else
		atomic_inc(&osd->o_osdc->num_homeless);

	get_osd(osd);
	insert_request(&osd->o_requests, req);
	req->r_osd = osd;
S
Sage Weil 已提交
1239 1240
}

1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257
static void unlink_request(struct ceph_osd *osd, struct ceph_osd_request *req)
{
	verify_osd_locked(osd);
	WARN_ON(req->r_osd != osd);
	dout("%s osd %p osd%d req %p tid %llu\n", __func__, osd, osd->o_osd,
	     req, req->r_tid);

	req->r_osd = NULL;
	erase_request(&osd->o_requests, req);
	put_osd(osd);

	if (!osd_homeless(osd))
		maybe_move_osd_to_lru(osd);
	else
		atomic_dec(&osd->o_osdc->num_homeless);
}

1258 1259 1260 1261 1262
static bool __pool_full(struct ceph_pg_pool_info *pi)
{
	return pi->flags & CEPH_POOL_FLAG_FULL;
}

I
Ilya Dryomov 已提交
1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277
static bool have_pool_full(struct ceph_osd_client *osdc)
{
	struct rb_node *n;

	for (n = rb_first(&osdc->osdmap->pg_pools); n; n = rb_next(n)) {
		struct ceph_pg_pool_info *pi =
		    rb_entry(n, struct ceph_pg_pool_info, node);

		if (__pool_full(pi))
			return true;
	}

	return false;
}

1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288
static bool pool_full(struct ceph_osd_client *osdc, s64 pool_id)
{
	struct ceph_pg_pool_info *pi;

	pi = ceph_pg_pool_by_id(osdc->osdmap, pool_id);
	if (!pi)
		return false;

	return __pool_full(pi);
}

1289 1290 1291 1292
/*
 * Returns whether a request should be blocked from being sent
 * based on the current osdmap and osd_client settings.
 */
1293 1294 1295 1296
static bool target_should_be_paused(struct ceph_osd_client *osdc,
				    const struct ceph_osd_request_target *t,
				    struct ceph_pg_pool_info *pi)
{
1297 1298 1299
	bool pauserd = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD);
	bool pausewr = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR) ||
		       ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) ||
1300 1301 1302
		       __pool_full(pi);

	WARN_ON(pi->id != t->base_oloc.pool);
1303 1304 1305
	return ((t->flags & CEPH_OSD_FLAG_READ) && pauserd) ||
	       ((t->flags & CEPH_OSD_FLAG_WRITE) && pausewr) ||
	       (osdc->osdmap->epoch < osdc->epoch_barrier);
1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323
}

enum calc_target_result {
	CALC_TARGET_NO_ACTION = 0,
	CALC_TARGET_NEED_RESEND,
	CALC_TARGET_POOL_DNE,
};

static enum calc_target_result calc_target(struct ceph_osd_client *osdc,
					   struct ceph_osd_request_target *t,
					   bool any_change)
{
	struct ceph_pg_pool_info *pi;
	struct ceph_pg pgid, last_pgid;
	struct ceph_osds up, acting;
	bool force_resend = false;
	bool need_check_tiering = false;
	bool need_resend = false;
1324
	bool sort_bitwise = ceph_osdmap_flag(osdc, CEPH_OSDMAP_SORTBITWISE);
1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335
	enum calc_target_result ct_res;
	int ret;

	pi = ceph_pg_pool_by_id(osdc->osdmap, t->base_oloc.pool);
	if (!pi) {
		t->osd = CEPH_HOMELESS_OSD;
		ct_res = CALC_TARGET_POOL_DNE;
		goto out;
	}

	if (osdc->osdmap->epoch == pi->last_force_request_resend) {
1336 1337
		if (t->last_force_resend < pi->last_force_request_resend) {
			t->last_force_resend = pi->last_force_request_resend;
1338
			force_resend = true;
1339
		} else if (t->last_force_resend == 0) {
1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414
			force_resend = true;
		}
	}
	if (ceph_oid_empty(&t->target_oid) || force_resend) {
		ceph_oid_copy(&t->target_oid, &t->base_oid);
		need_check_tiering = true;
	}
	if (ceph_oloc_empty(&t->target_oloc) || force_resend) {
		ceph_oloc_copy(&t->target_oloc, &t->base_oloc);
		need_check_tiering = true;
	}

	if (need_check_tiering &&
	    (t->flags & CEPH_OSD_FLAG_IGNORE_OVERLAY) == 0) {
		if (t->flags & CEPH_OSD_FLAG_READ && pi->read_tier >= 0)
			t->target_oloc.pool = pi->read_tier;
		if (t->flags & CEPH_OSD_FLAG_WRITE && pi->write_tier >= 0)
			t->target_oloc.pool = pi->write_tier;
	}

	ret = ceph_object_locator_to_pg(osdc->osdmap, &t->target_oid,
					&t->target_oloc, &pgid);
	if (ret) {
		WARN_ON(ret != -ENOENT);
		t->osd = CEPH_HOMELESS_OSD;
		ct_res = CALC_TARGET_POOL_DNE;
		goto out;
	}
	last_pgid.pool = pgid.pool;
	last_pgid.seed = ceph_stable_mod(pgid.seed, t->pg_num, t->pg_num_mask);

	ceph_pg_to_up_acting_osds(osdc->osdmap, &pgid, &up, &acting);
	if (any_change &&
	    ceph_is_new_interval(&t->acting,
				 &acting,
				 &t->up,
				 &up,
				 t->size,
				 pi->size,
				 t->min_size,
				 pi->min_size,
				 t->pg_num,
				 pi->pg_num,
				 t->sort_bitwise,
				 sort_bitwise,
				 &last_pgid))
		force_resend = true;

	if (t->paused && !target_should_be_paused(osdc, t, pi)) {
		t->paused = false;
		need_resend = true;
	}

	if (ceph_pg_compare(&t->pgid, &pgid) ||
	    ceph_osds_changed(&t->acting, &acting, any_change) ||
	    force_resend) {
		t->pgid = pgid; /* struct */
		ceph_osds_copy(&t->acting, &acting);
		ceph_osds_copy(&t->up, &up);
		t->size = pi->size;
		t->min_size = pi->min_size;
		t->pg_num = pi->pg_num;
		t->pg_num_mask = pi->pg_num_mask;
		t->sort_bitwise = sort_bitwise;

		t->osd = acting.primary;
		need_resend = true;
	}

	ct_res = need_resend ? CALC_TARGET_NEED_RESEND : CALC_TARGET_NO_ACTION;
out:
	dout("%s t %p -> ct_res %d osd %d\n", __func__, t, ct_res, t->osd);
	return ct_res;
}

1415 1416
static void setup_request_data(struct ceph_osd_request *req,
			       struct ceph_msg *msg)
S
Sage Weil 已提交
1417
{
1418 1419 1420 1421 1422
	u32 data_len = 0;
	int i;

	if (!list_empty(&msg->data))
		return;
S
Sage Weil 已提交
1423

1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440
	WARN_ON(msg->data_length);
	for (i = 0; i < req->r_num_ops; i++) {
		struct ceph_osd_req_op *op = &req->r_ops[i];

		switch (op->op) {
		/* request */
		case CEPH_OSD_OP_WRITE:
		case CEPH_OSD_OP_WRITEFULL:
			WARN_ON(op->indata_len != op->extent.length);
			ceph_osdc_msg_data_add(msg, &op->extent.osd_data);
			break;
		case CEPH_OSD_OP_SETXATTR:
		case CEPH_OSD_OP_CMPXATTR:
			WARN_ON(op->indata_len != op->xattr.name_len +
						  op->xattr.value_len);
			ceph_osdc_msg_data_add(msg, &op->xattr.osd_data);
			break;
1441 1442 1443 1444
		case CEPH_OSD_OP_NOTIFY_ACK:
			ceph_osdc_msg_data_add(msg,
					       &op->notify_ack.request_data);
			break;
1445 1446 1447 1448 1449 1450 1451 1452 1453 1454

		/* reply */
		case CEPH_OSD_OP_STAT:
			ceph_osdc_msg_data_add(req->r_reply,
					       &op->raw_data_in);
			break;
		case CEPH_OSD_OP_READ:
			ceph_osdc_msg_data_add(req->r_reply,
					       &op->extent.osd_data);
			break;
1455 1456 1457 1458
		case CEPH_OSD_OP_LIST_WATCHERS:
			ceph_osdc_msg_data_add(req->r_reply,
					       &op->list_watchers.response_data);
			break;
1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471

		/* both */
		case CEPH_OSD_OP_CALL:
			WARN_ON(op->indata_len != op->cls.class_len +
						  op->cls.method_len +
						  op->cls.indata_len);
			ceph_osdc_msg_data_add(msg, &op->cls.request_info);
			/* optional, can be NONE */
			ceph_osdc_msg_data_add(msg, &op->cls.request_data);
			/* optional, can be NONE */
			ceph_osdc_msg_data_add(req->r_reply,
					       &op->cls.response_data);
			break;
1472 1473 1474 1475 1476 1477
		case CEPH_OSD_OP_NOTIFY:
			ceph_osdc_msg_data_add(msg,
					       &op->notify.request_data);
			ceph_osdc_msg_data_add(req->r_reply,
					       &op->notify.response_data);
			break;
1478 1479 1480 1481
		}

		data_len += op->indata_len;
	}
1482

1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507
	WARN_ON(data_len != msg->data_length);
}

static void encode_request(struct ceph_osd_request *req, struct ceph_msg *msg)
{
	void *p = msg->front.iov_base;
	void *const end = p + msg->front_alloc_len;
	u32 data_len = 0;
	int i;

	if (req->r_flags & CEPH_OSD_FLAG_WRITE) {
		/* snapshots aren't writeable */
		WARN_ON(req->r_snapid != CEPH_NOSNAP);
	} else {
		WARN_ON(req->r_mtime.tv_sec || req->r_mtime.tv_nsec ||
			req->r_data_offset || req->r_snapc);
	}

	setup_request_data(req, msg);

	ceph_encode_32(&p, 1); /* client_inc, always 1 */
	ceph_encode_32(&p, req->r_osdc->osdmap->epoch);
	ceph_encode_32(&p, req->r_flags);
	ceph_encode_timespec(p, &req->r_mtime);
	p += sizeof(struct ceph_timespec);
1508 1509 1510 1511

	/* reassert_version */
	memset(p, 0, sizeof(struct ceph_eversion));
	p += sizeof(struct ceph_eversion);
1512 1513

	/* oloc */
1514 1515
	ceph_start_encoding(&p, 5, 4,
			    ceph_oloc_encoding_size(&req->r_t.target_oloc));
1516 1517 1518
	ceph_encode_64(&p, req->r_t.target_oloc.pool);
	ceph_encode_32(&p, -1); /* preferred */
	ceph_encode_32(&p, 0); /* key len */
1519 1520 1521 1522 1523
	if (req->r_t.target_oloc.pool_ns)
		ceph_encode_string(&p, end, req->r_t.target_oloc.pool_ns->str,
				   req->r_t.target_oloc.pool_ns->len);
	else
		ceph_encode_32(&p, 0);
1524 1525 1526

	/* pgid */
	ceph_encode_8(&p, 1);
1527 1528
	ceph_encode_64(&p, req->r_t.pgid.pool);
	ceph_encode_32(&p, req->r_t.pgid.seed);
1529
	ceph_encode_32(&p, -1); /* preferred */
1530

1531 1532 1533 1534
	/* oid */
	ceph_encode_32(&p, req->r_t.target_oid.name_len);
	memcpy(p, req->r_t.target_oid.name, req->r_t.target_oid.name_len);
	p += req->r_t.target_oid.name_len;
S
Sage Weil 已提交
1535

1536 1537 1538 1539 1540 1541
	/* ops, can imply data */
	ceph_encode_16(&p, req->r_num_ops);
	for (i = 0; i < req->r_num_ops; i++) {
		data_len += osd_req_encode_op(p, &req->r_ops[i]);
		p += sizeof(struct ceph_osd_op);
	}
1542

1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566
	ceph_encode_64(&p, req->r_snapid); /* snapid */
	if (req->r_snapc) {
		ceph_encode_64(&p, req->r_snapc->seq);
		ceph_encode_32(&p, req->r_snapc->num_snaps);
		for (i = 0; i < req->r_snapc->num_snaps; i++)
			ceph_encode_64(&p, req->r_snapc->snaps[i]);
	} else {
		ceph_encode_64(&p, 0); /* snap_seq */
		ceph_encode_32(&p, 0); /* snaps len */
	}

	ceph_encode_32(&p, req->r_attempts); /* retry_attempt */

	BUG_ON(p > end);
	msg->front.iov_len = p - msg->front.iov_base;
	msg->hdr.version = cpu_to_le16(4); /* MOSDOp v4 */
	msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
	msg->hdr.data_len = cpu_to_le32(data_len);
	/*
	 * The header "data_off" is a hint to the receiver allowing it
	 * to align received data into its buffers such that there's no
	 * need to re-copy it before writing it to disk (direct I/O).
	 */
	msg->hdr.data_off = cpu_to_le16(req->r_data_offset);
1567

1568 1569 1570
	dout("%s req %p oid %s oid_len %d front %zu data %u\n", __func__,
	     req, req->r_t.target_oid.name, req->r_t.target_oid.name_len,
	     msg->front.iov_len, data_len);
1571 1572 1573 1574 1575 1576 1577 1578 1579
}

/*
 * @req has to be assigned a tid and registered.
 */
static void send_request(struct ceph_osd_request *req)
{
	struct ceph_osd *osd = req->r_osd;

1580
	verify_osd_locked(osd);
1581 1582
	WARN_ON(osd->o_osd != req->r_t.osd);

1583 1584 1585 1586 1587 1588 1589
	/*
	 * We may have a previously queued request message hanging
	 * around.  Cancel it to avoid corrupting the msgr.
	 */
	if (req->r_sent)
		ceph_msg_revoke(req->r_request);

1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608
	req->r_flags |= CEPH_OSD_FLAG_KNOWN_REDIR;
	if (req->r_attempts)
		req->r_flags |= CEPH_OSD_FLAG_RETRY;
	else
		WARN_ON(req->r_flags & CEPH_OSD_FLAG_RETRY);

	encode_request(req, req->r_request);

	dout("%s req %p tid %llu to pg %llu.%x osd%d flags 0x%x attempt %d\n",
	     __func__, req, req->r_tid, req->r_t.pgid.pool, req->r_t.pgid.seed,
	     req->r_t.osd, req->r_flags, req->r_attempts);

	req->r_t.paused = false;
	req->r_stamp = jiffies;
	req->r_attempts++;

	req->r_sent = osd->o_incarnation;
	req->r_request->hdr.tid = cpu_to_le64(req->r_tid);
	ceph_con_send(&osd->o_con, ceph_msg_get(req->r_request));
S
Sage Weil 已提交
1609 1610
}

I
Ilya Dryomov 已提交
1611 1612 1613 1614
static void maybe_request_map(struct ceph_osd_client *osdc)
{
	bool continuous = false;

1615
	verify_osdc_locked(osdc);
I
Ilya Dryomov 已提交
1616 1617
	WARN_ON(!osdc->osdmap->epoch);

1618 1619 1620
	if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) ||
	    ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD) ||
	    ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR)) {
I
Ilya Dryomov 已提交
1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631
		dout("%s osdc %p continuous\n", __func__, osdc);
		continuous = true;
	} else {
		dout("%s osdc %p onetime\n", __func__, osdc);
	}

	if (ceph_monc_want_map(&osdc->client->monc, CEPH_SUB_OSDMAP,
			       osdc->osdmap->epoch + 1, continuous))
		ceph_monc_renew_subs(&osdc->client->monc);
}

1632
static void complete_request(struct ceph_osd_request *req, int err);
I
Ilya Dryomov 已提交
1633 1634
static void send_map_check(struct ceph_osd_request *req);

1635
static void __submit_request(struct ceph_osd_request *req, bool wrlocked)
1636
{
1637 1638
	struct ceph_osd_client *osdc = req->r_osdc;
	struct ceph_osd *osd;
I
Ilya Dryomov 已提交
1639
	enum calc_target_result ct_res;
1640 1641
	bool need_send = false;
	bool promoted = false;
1642
	bool need_abort = false;
1643

I
Ilya Dryomov 已提交
1644
	WARN_ON(req->r_tid);
1645 1646 1647
	dout("%s req %p wrlocked %d\n", __func__, req, wrlocked);

again:
1648
	ct_res = calc_target(osdc, &req->r_t, false);
I
Ilya Dryomov 已提交
1649 1650 1651
	if (ct_res == CALC_TARGET_POOL_DNE && !wrlocked)
		goto promote;

1652 1653 1654 1655
	osd = lookup_create_osd(osdc, req->r_t.osd, wrlocked);
	if (IS_ERR(osd)) {
		WARN_ON(PTR_ERR(osd) != -EAGAIN || wrlocked);
		goto promote;
1656 1657
	}

1658 1659 1660 1661 1662 1663 1664
	if (osdc->osdmap->epoch < osdc->epoch_barrier) {
		dout("req %p epoch %u barrier %u\n", req, osdc->osdmap->epoch,
		     osdc->epoch_barrier);
		req->r_t.paused = true;
		maybe_request_map(osdc);
	} else if ((req->r_flags & CEPH_OSD_FLAG_WRITE) &&
		   ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR)) {
1665 1666 1667 1668
		dout("req %p pausewr\n", req);
		req->r_t.paused = true;
		maybe_request_map(osdc);
	} else if ((req->r_flags & CEPH_OSD_FLAG_READ) &&
1669
		   ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD)) {
1670 1671 1672 1673 1674 1675
		dout("req %p pauserd\n", req);
		req->r_t.paused = true;
		maybe_request_map(osdc);
	} else if ((req->r_flags & CEPH_OSD_FLAG_WRITE) &&
		   !(req->r_flags & (CEPH_OSD_FLAG_FULL_TRY |
				     CEPH_OSD_FLAG_FULL_FORCE)) &&
1676
		   (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) ||
1677 1678 1679 1680 1681
		    pool_full(osdc, req->r_t.base_oloc.pool))) {
		dout("req %p full/pool_full\n", req);
		pr_warn_ratelimited("FULL or reached pool quota\n");
		req->r_t.paused = true;
		maybe_request_map(osdc);
1682 1683
		if (req->r_abort_on_full)
			need_abort = true;
1684 1685
	} else if (!osd_homeless(osd)) {
		need_send = true;
1686
	} else {
1687
		maybe_request_map(osdc);
1688 1689
	}

1690 1691 1692 1693 1694 1695 1696 1697 1698 1699
	mutex_lock(&osd->lock);
	/*
	 * Assign the tid atomically with send_request() to protect
	 * multiple writes to the same object from racing with each
	 * other, resulting in out of order ops on the OSDs.
	 */
	req->r_tid = atomic64_inc_return(&osdc->last_tid);
	link_request(osd, req);
	if (need_send)
		send_request(req);
1700 1701
	else if (need_abort)
		complete_request(req, -ENOSPC);
1702 1703
	mutex_unlock(&osd->lock);

I
Ilya Dryomov 已提交
1704 1705 1706
	if (ct_res == CALC_TARGET_POOL_DNE)
		send_map_check(req);

1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720
	if (promoted)
		downgrade_write(&osdc->lock);
	return;

promote:
	up_read(&osdc->lock);
	down_write(&osdc->lock);
	wrlocked = true;
	promoted = true;
	goto again;
}

static void account_request(struct ceph_osd_request *req)
{
1721
	WARN_ON(req->r_flags & (CEPH_OSD_FLAG_ACK | CEPH_OSD_FLAG_ONDISK));
I
Ilya Dryomov 已提交
1722
	WARN_ON(!(req->r_flags & (CEPH_OSD_FLAG_READ | CEPH_OSD_FLAG_WRITE)));
1723

I
Ilya Dryomov 已提交
1724
	req->r_flags |= CEPH_OSD_FLAG_ONDISK;
1725
	atomic_inc(&req->r_osdc->num_requests);
1726 1727

	req->r_start_stamp = jiffies;
1728 1729 1730 1731 1732 1733 1734 1735 1736
}

static void submit_request(struct ceph_osd_request *req, bool wrlocked)
{
	ceph_osdc_get_request(req);
	account_request(req);
	__submit_request(req, wrlocked);
}

1737
static void finish_request(struct ceph_osd_request *req)
1738 1739 1740 1741 1742 1743 1744
{
	struct ceph_osd_client *osdc = req->r_osdc;
	struct ceph_osd *osd = req->r_osd;

	verify_osd_locked(osd);
	dout("%s req %p tid %llu\n", __func__, req, req->r_tid);

I
Ilya Dryomov 已提交
1745
	WARN_ON(lookup_request_mc(&osdc->map_checks, req->r_tid));
1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758
	unlink_request(osd, req);
	atomic_dec(&osdc->num_requests);

	/*
	 * If an OSD has failed or returned and a request has been sent
	 * twice, it's possible to get a reply and end up here while the
	 * request message is queued for delivery.  We will ignore the
	 * reply, so not a big deal, but better to try and catch it.
	 */
	ceph_msg_revoke(req->r_request);
	ceph_msg_revoke_incoming(req->r_reply);
}

1759 1760
static void __complete_request(struct ceph_osd_request *req)
{
I
Ilya Dryomov 已提交
1761 1762 1763
	if (req->r_callback) {
		dout("%s req %p tid %llu cb %pf result %d\n", __func__, req,
		     req->r_tid, req->r_callback, req->r_result);
1764
		req->r_callback(req);
I
Ilya Dryomov 已提交
1765
	}
1766 1767
}

I
Ilya Dryomov 已提交
1768
/*
I
Ilya Dryomov 已提交
1769
 * This is open-coded in handle_reply().
I
Ilya Dryomov 已提交
1770 1771 1772 1773 1774 1775
 */
static void complete_request(struct ceph_osd_request *req, int err)
{
	dout("%s req %p tid %llu err %d\n", __func__, req, req->r_tid, err);

	req->r_result = err;
1776
	finish_request(req);
I
Ilya Dryomov 已提交
1777
	__complete_request(req);
I
Ilya Dryomov 已提交
1778
	complete_all(&req->r_completion);
I
Ilya Dryomov 已提交
1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797
	ceph_osdc_put_request(req);
}

static void cancel_map_check(struct ceph_osd_request *req)
{
	struct ceph_osd_client *osdc = req->r_osdc;
	struct ceph_osd_request *lookup_req;

	verify_osdc_wrlocked(osdc);

	lookup_req = lookup_request_mc(&osdc->map_checks, req->r_tid);
	if (!lookup_req)
		return;

	WARN_ON(lookup_req != req);
	erase_request_mc(&osdc->map_checks, req);
	ceph_osdc_put_request(req);
}

1798 1799 1800 1801
static void cancel_request(struct ceph_osd_request *req)
{
	dout("%s req %p tid %llu\n", __func__, req, req->r_tid);

I
Ilya Dryomov 已提交
1802
	cancel_map_check(req);
1803
	finish_request(req);
I
Ilya Dryomov 已提交
1804
	complete_all(&req->r_completion);
1805
	ceph_osdc_put_request(req);
1806 1807
}

1808 1809 1810 1811 1812 1813 1814 1815
static void abort_request(struct ceph_osd_request *req, int err)
{
	dout("%s req %p tid %llu err %d\n", __func__, req, req->r_tid, err);

	cancel_map_check(req);
	complete_request(req, err);
}

1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841
static void update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb)
{
	if (likely(eb > osdc->epoch_barrier)) {
		dout("updating epoch_barrier from %u to %u\n",
				osdc->epoch_barrier, eb);
		osdc->epoch_barrier = eb;
		/* Request map if we're not to the barrier yet */
		if (eb > osdc->osdmap->epoch)
			maybe_request_map(osdc);
	}
}

void ceph_osdc_update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb)
{
	down_read(&osdc->lock);
	if (unlikely(eb > osdc->epoch_barrier)) {
		up_read(&osdc->lock);
		down_write(&osdc->lock);
		update_epoch_barrier(osdc, eb);
		up_write(&osdc->lock);
	} else {
		up_read(&osdc->lock);
	}
}
EXPORT_SYMBOL(ceph_osdc_update_epoch_barrier);

1842 1843
/*
 * Drop all pending requests that are stalled waiting on a full condition to
1844 1845 1846
 * clear, and complete them with ENOSPC as the return code. Set the
 * osdc->epoch_barrier to the latest map epoch that we've seen if any were
 * cancelled.
1847 1848 1849 1850
 */
static void ceph_osdc_abort_on_full(struct ceph_osd_client *osdc)
{
	struct rb_node *n;
1851
	bool victims = false;
1852 1853 1854 1855 1856 1857

	dout("enter abort_on_full\n");

	if (!ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) && !have_pool_full(osdc))
		goto out;

1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886
	/* Scan list and see if there is anything to abort */
	for (n = rb_first(&osdc->osds); n; n = rb_next(n)) {
		struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node);
		struct rb_node *m;

		m = rb_first(&osd->o_requests);
		while (m) {
			struct ceph_osd_request *req = rb_entry(m,
					struct ceph_osd_request, r_node);
			m = rb_next(m);

			if (req->r_abort_on_full) {
				victims = true;
				break;
			}
		}
		if (victims)
			break;
	}

	if (!victims)
		goto out;

	/*
	 * Update the barrier to current epoch if it's behind that point,
	 * since we know we have some calls to be aborted in the tree.
	 */
	update_epoch_barrier(osdc, osdc->osdmap->epoch);

1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903
	for (n = rb_first(&osdc->osds); n; n = rb_next(n)) {
		struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node);
		struct rb_node *m;

		m = rb_first(&osd->o_requests);
		while (m) {
			struct ceph_osd_request *req = rb_entry(m,
					struct ceph_osd_request, r_node);
			m = rb_next(m);

			if (req->r_abort_on_full &&
			    (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) ||
			     pool_full(osdc, req->r_t.target_oloc.pool)))
				abort_request(req, -ENOSPC);
		}
	}
out:
1904
	dout("return abort_on_full barrier=%u\n", osdc->epoch_barrier);
1905 1906
}

I
Ilya Dryomov 已提交
1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988
static void check_pool_dne(struct ceph_osd_request *req)
{
	struct ceph_osd_client *osdc = req->r_osdc;
	struct ceph_osdmap *map = osdc->osdmap;

	verify_osdc_wrlocked(osdc);
	WARN_ON(!map->epoch);

	if (req->r_attempts) {
		/*
		 * We sent a request earlier, which means that
		 * previously the pool existed, and now it does not
		 * (i.e., it was deleted).
		 */
		req->r_map_dne_bound = map->epoch;
		dout("%s req %p tid %llu pool disappeared\n", __func__, req,
		     req->r_tid);
	} else {
		dout("%s req %p tid %llu map_dne_bound %u have %u\n", __func__,
		     req, req->r_tid, req->r_map_dne_bound, map->epoch);
	}

	if (req->r_map_dne_bound) {
		if (map->epoch >= req->r_map_dne_bound) {
			/* we had a new enough map */
			pr_info_ratelimited("tid %llu pool does not exist\n",
					    req->r_tid);
			complete_request(req, -ENOENT);
		}
	} else {
		send_map_check(req);
	}
}

static void map_check_cb(struct ceph_mon_generic_request *greq)
{
	struct ceph_osd_client *osdc = &greq->monc->client->osdc;
	struct ceph_osd_request *req;
	u64 tid = greq->private_data;

	WARN_ON(greq->result || !greq->u.newest);

	down_write(&osdc->lock);
	req = lookup_request_mc(&osdc->map_checks, tid);
	if (!req) {
		dout("%s tid %llu dne\n", __func__, tid);
		goto out_unlock;
	}

	dout("%s req %p tid %llu map_dne_bound %u newest %llu\n", __func__,
	     req, req->r_tid, req->r_map_dne_bound, greq->u.newest);
	if (!req->r_map_dne_bound)
		req->r_map_dne_bound = greq->u.newest;
	erase_request_mc(&osdc->map_checks, req);
	check_pool_dne(req);

	ceph_osdc_put_request(req);
out_unlock:
	up_write(&osdc->lock);
}

static void send_map_check(struct ceph_osd_request *req)
{
	struct ceph_osd_client *osdc = req->r_osdc;
	struct ceph_osd_request *lookup_req;
	int ret;

	verify_osdc_wrlocked(osdc);

	lookup_req = lookup_request_mc(&osdc->map_checks, req->r_tid);
	if (lookup_req) {
		WARN_ON(lookup_req != req);
		return;
	}

	ceph_osdc_get_request(req);
	insert_request_mc(&osdc->map_checks, req);
	ret = ceph_monc_get_version_async(&osdc->client->monc, "osdmap",
					  map_check_cb, req->r_tid);
	WARN_ON(ret);
}

1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000
/*
 * lingering requests, watch/notify v2 infrastructure
 */
static void linger_release(struct kref *kref)
{
	struct ceph_osd_linger_request *lreq =
	    container_of(kref, struct ceph_osd_linger_request, kref);

	dout("%s lreq %p reg_req %p ping_req %p\n", __func__, lreq,
	     lreq->reg_req, lreq->ping_req);
	WARN_ON(!RB_EMPTY_NODE(&lreq->node));
	WARN_ON(!RB_EMPTY_NODE(&lreq->osdc_node));
I
Ilya Dryomov 已提交
2001
	WARN_ON(!RB_EMPTY_NODE(&lreq->mc_node));
2002
	WARN_ON(!list_empty(&lreq->scan_item));
2003
	WARN_ON(!list_empty(&lreq->pending_lworks));
2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039
	WARN_ON(lreq->osd);

	if (lreq->reg_req)
		ceph_osdc_put_request(lreq->reg_req);
	if (lreq->ping_req)
		ceph_osdc_put_request(lreq->ping_req);
	target_destroy(&lreq->t);
	kfree(lreq);
}

static void linger_put(struct ceph_osd_linger_request *lreq)
{
	if (lreq)
		kref_put(&lreq->kref, linger_release);
}

static struct ceph_osd_linger_request *
linger_get(struct ceph_osd_linger_request *lreq)
{
	kref_get(&lreq->kref);
	return lreq;
}

static struct ceph_osd_linger_request *
linger_alloc(struct ceph_osd_client *osdc)
{
	struct ceph_osd_linger_request *lreq;

	lreq = kzalloc(sizeof(*lreq), GFP_NOIO);
	if (!lreq)
		return NULL;

	kref_init(&lreq->kref);
	mutex_init(&lreq->lock);
	RB_CLEAR_NODE(&lreq->node);
	RB_CLEAR_NODE(&lreq->osdc_node);
I
Ilya Dryomov 已提交
2040
	RB_CLEAR_NODE(&lreq->mc_node);
2041
	INIT_LIST_HEAD(&lreq->scan_item);
2042
	INIT_LIST_HEAD(&lreq->pending_lworks);
2043
	init_completion(&lreq->reg_commit_wait);
2044
	init_completion(&lreq->notify_finish_wait);
2045 2046 2047 2048 2049 2050 2051 2052 2053 2054

	lreq->osdc = osdc;
	target_init(&lreq->t);

	dout("%s lreq %p\n", __func__, lreq);
	return lreq;
}

DEFINE_RB_INSDEL_FUNCS(linger, struct ceph_osd_linger_request, linger_id, node)
DEFINE_RB_FUNCS(linger_osdc, struct ceph_osd_linger_request, linger_id, osdc_node)
I
Ilya Dryomov 已提交
2055
DEFINE_RB_FUNCS(linger_mc, struct ceph_osd_linger_request, linger_id, mc_node)
2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150

/*
 * Create linger request <-> OSD session relation.
 *
 * @lreq has to be registered, @osd may be homeless.
 */
static void link_linger(struct ceph_osd *osd,
			struct ceph_osd_linger_request *lreq)
{
	verify_osd_locked(osd);
	WARN_ON(!lreq->linger_id || lreq->osd);
	dout("%s osd %p osd%d lreq %p linger_id %llu\n", __func__, osd,
	     osd->o_osd, lreq, lreq->linger_id);

	if (!osd_homeless(osd))
		__remove_osd_from_lru(osd);
	else
		atomic_inc(&osd->o_osdc->num_homeless);

	get_osd(osd);
	insert_linger(&osd->o_linger_requests, lreq);
	lreq->osd = osd;
}

static void unlink_linger(struct ceph_osd *osd,
			  struct ceph_osd_linger_request *lreq)
{
	verify_osd_locked(osd);
	WARN_ON(lreq->osd != osd);
	dout("%s osd %p osd%d lreq %p linger_id %llu\n", __func__, osd,
	     osd->o_osd, lreq, lreq->linger_id);

	lreq->osd = NULL;
	erase_linger(&osd->o_linger_requests, lreq);
	put_osd(osd);

	if (!osd_homeless(osd))
		maybe_move_osd_to_lru(osd);
	else
		atomic_dec(&osd->o_osdc->num_homeless);
}

static bool __linger_registered(struct ceph_osd_linger_request *lreq)
{
	verify_osdc_locked(lreq->osdc);

	return !RB_EMPTY_NODE(&lreq->osdc_node);
}

static bool linger_registered(struct ceph_osd_linger_request *lreq)
{
	struct ceph_osd_client *osdc = lreq->osdc;
	bool registered;

	down_read(&osdc->lock);
	registered = __linger_registered(lreq);
	up_read(&osdc->lock);

	return registered;
}

static void linger_register(struct ceph_osd_linger_request *lreq)
{
	struct ceph_osd_client *osdc = lreq->osdc;

	verify_osdc_wrlocked(osdc);
	WARN_ON(lreq->linger_id);

	linger_get(lreq);
	lreq->linger_id = ++osdc->last_linger_id;
	insert_linger_osdc(&osdc->linger_requests, lreq);
}

static void linger_unregister(struct ceph_osd_linger_request *lreq)
{
	struct ceph_osd_client *osdc = lreq->osdc;

	verify_osdc_wrlocked(osdc);

	erase_linger_osdc(&osdc->linger_requests, lreq);
	linger_put(lreq);
}

static void cancel_linger_request(struct ceph_osd_request *req)
{
	struct ceph_osd_linger_request *lreq = req->r_priv;

	WARN_ON(!req->r_linger);
	cancel_request(req);
	linger_put(lreq);
}

struct linger_work {
	struct work_struct work;
	struct ceph_osd_linger_request *lreq;
2151 2152
	struct list_head pending_item;
	unsigned long queued_stamp;
2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178

	union {
		struct {
			u64 notify_id;
			u64 notifier_id;
			void *payload; /* points into @msg front */
			size_t payload_len;

			struct ceph_msg *msg; /* for ceph_msg_put() */
		} notify;
		struct {
			int err;
		} error;
	};
};

static struct linger_work *lwork_alloc(struct ceph_osd_linger_request *lreq,
				       work_func_t workfn)
{
	struct linger_work *lwork;

	lwork = kzalloc(sizeof(*lwork), GFP_NOIO);
	if (!lwork)
		return NULL;

	INIT_WORK(&lwork->work, workfn);
2179
	INIT_LIST_HEAD(&lwork->pending_item);
2180 2181 2182 2183 2184 2185 2186 2187 2188
	lwork->lreq = linger_get(lreq);

	return lwork;
}

static void lwork_free(struct linger_work *lwork)
{
	struct ceph_osd_linger_request *lreq = lwork->lreq;

2189 2190 2191 2192
	mutex_lock(&lreq->lock);
	list_del(&lwork->pending_item);
	mutex_unlock(&lreq->lock);

2193 2194 2195 2196 2197 2198 2199 2200 2201 2202
	linger_put(lreq);
	kfree(lwork);
}

static void lwork_queue(struct linger_work *lwork)
{
	struct ceph_osd_linger_request *lreq = lwork->lreq;
	struct ceph_osd_client *osdc = lreq->osdc;

	verify_lreq_locked(lreq);
2203 2204 2205 2206
	WARN_ON(!list_empty(&lwork->pending_item));

	lwork->queued_stamp = jiffies;
	list_add_tail(&lwork->pending_item, &lreq->pending_lworks);
2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219
	queue_work(osdc->notify_wq, &lwork->work);
}

static void do_watch_notify(struct work_struct *w)
{
	struct linger_work *lwork = container_of(w, struct linger_work, work);
	struct ceph_osd_linger_request *lreq = lwork->lreq;

	if (!linger_registered(lreq)) {
		dout("%s lreq %p not registered\n", __func__, lreq);
		goto out;
	}

2220
	WARN_ON(!lreq->is_watch);
2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282
	dout("%s lreq %p notify_id %llu notifier_id %llu payload_len %zu\n",
	     __func__, lreq, lwork->notify.notify_id, lwork->notify.notifier_id,
	     lwork->notify.payload_len);
	lreq->wcb(lreq->data, lwork->notify.notify_id, lreq->linger_id,
		  lwork->notify.notifier_id, lwork->notify.payload,
		  lwork->notify.payload_len);

out:
	ceph_msg_put(lwork->notify.msg);
	lwork_free(lwork);
}

static void do_watch_error(struct work_struct *w)
{
	struct linger_work *lwork = container_of(w, struct linger_work, work);
	struct ceph_osd_linger_request *lreq = lwork->lreq;

	if (!linger_registered(lreq)) {
		dout("%s lreq %p not registered\n", __func__, lreq);
		goto out;
	}

	dout("%s lreq %p err %d\n", __func__, lreq, lwork->error.err);
	lreq->errcb(lreq->data, lreq->linger_id, lwork->error.err);

out:
	lwork_free(lwork);
}

static void queue_watch_error(struct ceph_osd_linger_request *lreq)
{
	struct linger_work *lwork;

	lwork = lwork_alloc(lreq, do_watch_error);
	if (!lwork) {
		pr_err("failed to allocate error-lwork\n");
		return;
	}

	lwork->error.err = lreq->last_error;
	lwork_queue(lwork);
}

static void linger_reg_commit_complete(struct ceph_osd_linger_request *lreq,
				       int result)
{
	if (!completion_done(&lreq->reg_commit_wait)) {
		lreq->reg_commit_error = (result <= 0 ? result : 0);
		complete_all(&lreq->reg_commit_wait);
	}
}

static void linger_commit_cb(struct ceph_osd_request *req)
{
	struct ceph_osd_linger_request *lreq = req->r_priv;

	mutex_lock(&lreq->lock);
	dout("%s lreq %p linger_id %llu result %d\n", __func__, lreq,
	     lreq->linger_id, req->r_result);
	linger_reg_commit_complete(lreq, req->r_result);
	lreq->committed = true;

2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300
	if (!lreq->is_watch) {
		struct ceph_osd_data *osd_data =
		    osd_req_op_data(req, 0, notify, response_data);
		void *p = page_address(osd_data->pages[0]);

		WARN_ON(req->r_ops[0].op != CEPH_OSD_OP_NOTIFY ||
			osd_data->type != CEPH_OSD_DATA_TYPE_PAGES);

		/* make note of the notify_id */
		if (req->r_ops[0].outdata_len >= sizeof(u64)) {
			lreq->notify_id = ceph_decode_64(&p);
			dout("lreq %p notify_id %llu\n", lreq,
			     lreq->notify_id);
		} else {
			dout("lreq %p no notify_id\n", lreq);
		}
	}

2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353
	mutex_unlock(&lreq->lock);
	linger_put(lreq);
}

static int normalize_watch_error(int err)
{
	/*
	 * Translate ENOENT -> ENOTCONN so that a delete->disconnection
	 * notification and a failure to reconnect because we raced with
	 * the delete appear the same to the user.
	 */
	if (err == -ENOENT)
		err = -ENOTCONN;

	return err;
}

static void linger_reconnect_cb(struct ceph_osd_request *req)
{
	struct ceph_osd_linger_request *lreq = req->r_priv;

	mutex_lock(&lreq->lock);
	dout("%s lreq %p linger_id %llu result %d last_error %d\n", __func__,
	     lreq, lreq->linger_id, req->r_result, lreq->last_error);
	if (req->r_result < 0) {
		if (!lreq->last_error) {
			lreq->last_error = normalize_watch_error(req->r_result);
			queue_watch_error(lreq);
		}
	}

	mutex_unlock(&lreq->lock);
	linger_put(lreq);
}

static void send_linger(struct ceph_osd_linger_request *lreq)
{
	struct ceph_osd_request *req = lreq->reg_req;
	struct ceph_osd_req_op *op = &req->r_ops[0];

	verify_osdc_wrlocked(req->r_osdc);
	dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id);

	if (req->r_osd)
		cancel_linger_request(req);

	request_reinit(req);
	ceph_oid_copy(&req->r_base_oid, &lreq->t.base_oid);
	ceph_oloc_copy(&req->r_base_oloc, &lreq->t.base_oloc);
	req->r_flags = lreq->t.flags;
	req->r_mtime = lreq->mtime;

	mutex_lock(&lreq->lock);
2354
	if (lreq->is_watch && lreq->committed) {
2355 2356 2357 2358 2359 2360 2361 2362
		WARN_ON(op->op != CEPH_OSD_OP_WATCH ||
			op->watch.cookie != lreq->linger_id);
		op->watch.op = CEPH_OSD_WATCH_OP_RECONNECT;
		op->watch.gen = ++lreq->register_gen;
		dout("lreq %p reconnect register_gen %u\n", lreq,
		     op->watch.gen);
		req->r_callback = linger_reconnect_cb;
	} else {
2363 2364 2365 2366
		if (!lreq->is_watch)
			lreq->notify_id = 0;
		else
			WARN_ON(op->watch.op != CEPH_OSD_WATCH_OP_WATCH);
2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386
		dout("lreq %p register\n", lreq);
		req->r_callback = linger_commit_cb;
	}
	mutex_unlock(&lreq->lock);

	req->r_priv = linger_get(lreq);
	req->r_linger = true;

	submit_request(req, true);
}

static void linger_ping_cb(struct ceph_osd_request *req)
{
	struct ceph_osd_linger_request *lreq = req->r_priv;

	mutex_lock(&lreq->lock);
	dout("%s lreq %p linger_id %llu result %d ping_sent %lu last_error %d\n",
	     __func__, lreq, lreq->linger_id, req->r_result, lreq->ping_sent,
	     lreq->last_error);
	if (lreq->register_gen == req->r_ops[0].watch.gen) {
2387 2388 2389
		if (!req->r_result) {
			lreq->watch_valid_thru = lreq->ping_sent;
		} else if (!lreq->last_error) {
2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407
			lreq->last_error = normalize_watch_error(req->r_result);
			queue_watch_error(lreq);
		}
	} else {
		dout("lreq %p register_gen %u ignoring old pong %u\n", lreq,
		     lreq->register_gen, req->r_ops[0].watch.gen);
	}

	mutex_unlock(&lreq->lock);
	linger_put(lreq);
}

static void send_linger_ping(struct ceph_osd_linger_request *lreq)
{
	struct ceph_osd_client *osdc = lreq->osdc;
	struct ceph_osd_request *req = lreq->ping_req;
	struct ceph_osd_req_op *op = &req->r_ops[0];

2408
	if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD)) {
2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443
		dout("%s PAUSERD\n", __func__);
		return;
	}

	lreq->ping_sent = jiffies;
	dout("%s lreq %p linger_id %llu ping_sent %lu register_gen %u\n",
	     __func__, lreq, lreq->linger_id, lreq->ping_sent,
	     lreq->register_gen);

	if (req->r_osd)
		cancel_linger_request(req);

	request_reinit(req);
	target_copy(&req->r_t, &lreq->t);

	WARN_ON(op->op != CEPH_OSD_OP_WATCH ||
		op->watch.cookie != lreq->linger_id ||
		op->watch.op != CEPH_OSD_WATCH_OP_PING);
	op->watch.gen = lreq->register_gen;
	req->r_callback = linger_ping_cb;
	req->r_priv = linger_get(lreq);
	req->r_linger = true;

	ceph_osdc_get_request(req);
	account_request(req);
	req->r_tid = atomic64_inc_return(&osdc->last_tid);
	link_request(lreq->osd, req);
	send_request(req);
}

static void linger_submit(struct ceph_osd_linger_request *lreq)
{
	struct ceph_osd_client *osdc = lreq->osdc;
	struct ceph_osd *osd;

2444
	calc_target(osdc, &lreq->t, false);
2445 2446 2447 2448 2449 2450
	osd = lookup_create_osd(osdc, lreq->t.osd, true);
	link_linger(osd, lreq);

	send_linger(lreq);
}

I
Ilya Dryomov 已提交
2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467
static void cancel_linger_map_check(struct ceph_osd_linger_request *lreq)
{
	struct ceph_osd_client *osdc = lreq->osdc;
	struct ceph_osd_linger_request *lookup_lreq;

	verify_osdc_wrlocked(osdc);

	lookup_lreq = lookup_linger_mc(&osdc->linger_map_checks,
				       lreq->linger_id);
	if (!lookup_lreq)
		return;

	WARN_ON(lookup_lreq != lreq);
	erase_linger_mc(&osdc->linger_map_checks, lreq);
	linger_put(lreq);
}

2468 2469 2470 2471 2472
/*
 * @lreq has to be both registered and linked.
 */
static void __linger_cancel(struct ceph_osd_linger_request *lreq)
{
2473
	if (lreq->is_watch && lreq->ping_req->r_osd)
2474 2475 2476
		cancel_linger_request(lreq->ping_req);
	if (lreq->reg_req->r_osd)
		cancel_linger_request(lreq->reg_req);
I
Ilya Dryomov 已提交
2477
	cancel_linger_map_check(lreq);
2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491
	unlink_linger(lreq->osd, lreq);
	linger_unregister(lreq);
}

static void linger_cancel(struct ceph_osd_linger_request *lreq)
{
	struct ceph_osd_client *osdc = lreq->osdc;

	down_write(&osdc->lock);
	if (__linger_registered(lreq))
		__linger_cancel(lreq);
	up_write(&osdc->lock);
}

I
Ilya Dryomov 已提交
2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574
static void send_linger_map_check(struct ceph_osd_linger_request *lreq);

static void check_linger_pool_dne(struct ceph_osd_linger_request *lreq)
{
	struct ceph_osd_client *osdc = lreq->osdc;
	struct ceph_osdmap *map = osdc->osdmap;

	verify_osdc_wrlocked(osdc);
	WARN_ON(!map->epoch);

	if (lreq->register_gen) {
		lreq->map_dne_bound = map->epoch;
		dout("%s lreq %p linger_id %llu pool disappeared\n", __func__,
		     lreq, lreq->linger_id);
	} else {
		dout("%s lreq %p linger_id %llu map_dne_bound %u have %u\n",
		     __func__, lreq, lreq->linger_id, lreq->map_dne_bound,
		     map->epoch);
	}

	if (lreq->map_dne_bound) {
		if (map->epoch >= lreq->map_dne_bound) {
			/* we had a new enough map */
			pr_info("linger_id %llu pool does not exist\n",
				lreq->linger_id);
			linger_reg_commit_complete(lreq, -ENOENT);
			__linger_cancel(lreq);
		}
	} else {
		send_linger_map_check(lreq);
	}
}

static void linger_map_check_cb(struct ceph_mon_generic_request *greq)
{
	struct ceph_osd_client *osdc = &greq->monc->client->osdc;
	struct ceph_osd_linger_request *lreq;
	u64 linger_id = greq->private_data;

	WARN_ON(greq->result || !greq->u.newest);

	down_write(&osdc->lock);
	lreq = lookup_linger_mc(&osdc->linger_map_checks, linger_id);
	if (!lreq) {
		dout("%s linger_id %llu dne\n", __func__, linger_id);
		goto out_unlock;
	}

	dout("%s lreq %p linger_id %llu map_dne_bound %u newest %llu\n",
	     __func__, lreq, lreq->linger_id, lreq->map_dne_bound,
	     greq->u.newest);
	if (!lreq->map_dne_bound)
		lreq->map_dne_bound = greq->u.newest;
	erase_linger_mc(&osdc->linger_map_checks, lreq);
	check_linger_pool_dne(lreq);

	linger_put(lreq);
out_unlock:
	up_write(&osdc->lock);
}

static void send_linger_map_check(struct ceph_osd_linger_request *lreq)
{
	struct ceph_osd_client *osdc = lreq->osdc;
	struct ceph_osd_linger_request *lookup_lreq;
	int ret;

	verify_osdc_wrlocked(osdc);

	lookup_lreq = lookup_linger_mc(&osdc->linger_map_checks,
				       lreq->linger_id);
	if (lookup_lreq) {
		WARN_ON(lookup_lreq != lreq);
		return;
	}

	linger_get(lreq);
	insert_linger_mc(&osdc->linger_map_checks, lreq);
	ret = ceph_monc_get_version_async(&osdc->client->monc, "osdmap",
					  linger_map_check_cb, lreq->linger_id);
	WARN_ON(ret);
}

2575 2576 2577 2578 2579 2580 2581 2582 2583
static int linger_reg_commit_wait(struct ceph_osd_linger_request *lreq)
{
	int ret;

	dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id);
	ret = wait_for_completion_interruptible(&lreq->reg_commit_wait);
	return ret ?: lreq->reg_commit_error;
}

2584 2585 2586 2587 2588 2589 2590 2591 2592
static int linger_notify_finish_wait(struct ceph_osd_linger_request *lreq)
{
	int ret;

	dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id);
	ret = wait_for_completion_interruptible(&lreq->notify_finish_wait);
	return ret ?: lreq->notify_finish_error;
}

S
Sage Weil 已提交
2593
/*
2594 2595 2596 2597
 * Timeout callback, called every N seconds.  When 1 or more OSD
 * requests has been active for more than N seconds, we send a keepalive
 * (tag + timestamp) to its OSD to ensure any communications channel
 * reset is detected.
S
Sage Weil 已提交
2598 2599 2600 2601 2602
 */
static void handle_timeout(struct work_struct *work)
{
	struct ceph_osd_client *osdc =
		container_of(work, struct ceph_osd_client, timeout_work.work);
2603
	struct ceph_options *opts = osdc->client->options;
2604
	unsigned long cutoff = jiffies - opts->osd_keepalive_timeout;
2605
	unsigned long expiry_cutoff = jiffies - opts->osd_request_timeout;
2606 2607
	LIST_HEAD(slow_osds);
	struct rb_node *n, *p;
S
Sage Weil 已提交
2608

2609 2610
	dout("%s osdc %p\n", __func__, osdc);
	down_write(&osdc->lock);
S
Sage Weil 已提交
2611

2612 2613 2614 2615 2616
	/*
	 * ping osds that are a bit slow.  this ensures that if there
	 * is a break in the TCP connection we will notice, and reopen
	 * a connection with that osd (from the fault callback).
	 */
2617 2618 2619 2620
	for (n = rb_first(&osdc->osds); n; n = rb_next(n)) {
		struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node);
		bool found = false;

2621
		for (p = rb_first(&osd->o_requests); p; ) {
2622 2623 2624
			struct ceph_osd_request *req =
			    rb_entry(p, struct ceph_osd_request, r_node);

2625 2626
			p = rb_next(p); /* abort_request() */

2627 2628 2629 2630 2631
			if (time_before(req->r_stamp, cutoff)) {
				dout(" req %p tid %llu on osd%d is laggy\n",
				     req, req->r_tid, osd->o_osd);
				found = true;
			}
2632 2633 2634 2635 2636 2637
			if (opts->osd_request_timeout &&
			    time_before(req->r_start_stamp, expiry_cutoff)) {
				pr_err_ratelimited("tid %llu on osd%d timeout\n",
				       req->r_tid, osd->o_osd);
				abort_request(req, -ETIMEDOUT);
			}
2638
		}
2639 2640 2641 2642 2643 2644 2645 2646 2647
		for (p = rb_first(&osd->o_linger_requests); p; p = rb_next(p)) {
			struct ceph_osd_linger_request *lreq =
			    rb_entry(p, struct ceph_osd_linger_request, node);

			dout(" lreq %p linger_id %llu is served by osd%d\n",
			     lreq, lreq->linger_id, osd->o_osd);
			found = true;

			mutex_lock(&lreq->lock);
2648
			if (lreq->is_watch && lreq->committed && !lreq->last_error)
2649 2650 2651
				send_linger_ping(lreq);
			mutex_unlock(&lreq->lock);
		}
2652

2653 2654
		if (found)
			list_move_tail(&osd->o_keepalive_item, &slow_osds);
2655
	}
2656

2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671
	if (opts->osd_request_timeout) {
		for (p = rb_first(&osdc->homeless_osd.o_requests); p; ) {
			struct ceph_osd_request *req =
			    rb_entry(p, struct ceph_osd_request, r_node);

			p = rb_next(p); /* abort_request() */

			if (time_before(req->r_start_stamp, expiry_cutoff)) {
				pr_err_ratelimited("tid %llu on osd%d timeout\n",
				       req->r_tid, osdc->homeless_osd.o_osd);
				abort_request(req, -ETIMEDOUT);
			}
		}
	}

2672 2673 2674
	if (atomic_read(&osdc->num_homeless) || !list_empty(&slow_osds))
		maybe_request_map(osdc);

2675
	while (!list_empty(&slow_osds)) {
2676 2677 2678
		struct ceph_osd *osd = list_first_entry(&slow_osds,
							struct ceph_osd,
							o_keepalive_item);
2679
		list_del_init(&osd->o_keepalive_item);
S
Sage Weil 已提交
2680 2681 2682
		ceph_con_keepalive(&osd->o_con);
	}

2683
	up_write(&osdc->lock);
2684 2685
	schedule_delayed_work(&osdc->timeout_work,
			      osdc->client->options->osd_keepalive_timeout);
S
Sage Weil 已提交
2686 2687
}

2688 2689 2690 2691 2692
static void handle_osds_timeout(struct work_struct *work)
{
	struct ceph_osd_client *osdc =
		container_of(work, struct ceph_osd_client,
			     osds_timeout_work.work);
2693
	unsigned long delay = osdc->client->options->osd_idle_ttl / 4;
2694
	struct ceph_osd *osd, *nosd;
2695

2696
	dout("%s osdc %p\n", __func__, osdc);
2697
	down_write(&osdc->lock);
2698 2699 2700 2701
	list_for_each_entry_safe(osd, nosd, &osdc->osd_lru, o_osd_lru) {
		if (time_before(jiffies, osd->lru_ttl))
			break;

2702
		WARN_ON(!RB_EMPTY_ROOT(&osd->o_requests));
2703
		WARN_ON(!RB_EMPTY_ROOT(&osd->o_linger_requests));
2704
		close_osd(osd);
2705
	}
2706

2707
	up_write(&osdc->lock);
2708 2709 2710 2711
	schedule_delayed_work(&osdc->osds_timeout_work,
			      round_jiffies_relative(delay));
}

2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746
static int ceph_oloc_decode(void **p, void *end,
			    struct ceph_object_locator *oloc)
{
	u8 struct_v, struct_cv;
	u32 len;
	void *struct_end;
	int ret = 0;

	ceph_decode_need(p, end, 1 + 1 + 4, e_inval);
	struct_v = ceph_decode_8(p);
	struct_cv = ceph_decode_8(p);
	if (struct_v < 3) {
		pr_warn("got v %d < 3 cv %d of ceph_object_locator\n",
			struct_v, struct_cv);
		goto e_inval;
	}
	if (struct_cv > 6) {
		pr_warn("got v %d cv %d > 6 of ceph_object_locator\n",
			struct_v, struct_cv);
		goto e_inval;
	}
	len = ceph_decode_32(p);
	ceph_decode_need(p, end, len, e_inval);
	struct_end = *p + len;

	oloc->pool = ceph_decode_64(p);
	*p += 4; /* skip preferred */

	len = ceph_decode_32(p);
	if (len > 0) {
		pr_warn("ceph_object_locator::key is set\n");
		goto e_inval;
	}

	if (struct_v >= 5) {
2747 2748
		bool changed = false;

2749 2750
		len = ceph_decode_32(p);
		if (len > 0) {
2751
			ceph_decode_need(p, end, len, e_inval);
2752 2753 2754
			if (!oloc->pool_ns ||
			    ceph_compare_string(oloc->pool_ns, *p, len))
				changed = true;
2755
			*p += len;
2756 2757 2758 2759 2760 2761 2762 2763
		} else {
			if (oloc->pool_ns)
				changed = true;
		}
		if (changed) {
			/* redirect changes namespace */
			pr_warn("ceph_object_locator::nspace is changed\n");
			goto e_inval;
2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827
		}
	}

	if (struct_v >= 6) {
		s64 hash = ceph_decode_64(p);
		if (hash != -1) {
			pr_warn("ceph_object_locator::hash is set\n");
			goto e_inval;
		}
	}

	/* skip the rest */
	*p = struct_end;
out:
	return ret;

e_inval:
	ret = -EINVAL;
	goto out;
}

static int ceph_redirect_decode(void **p, void *end,
				struct ceph_request_redirect *redir)
{
	u8 struct_v, struct_cv;
	u32 len;
	void *struct_end;
	int ret;

	ceph_decode_need(p, end, 1 + 1 + 4, e_inval);
	struct_v = ceph_decode_8(p);
	struct_cv = ceph_decode_8(p);
	if (struct_cv > 1) {
		pr_warn("got v %d cv %d > 1 of ceph_request_redirect\n",
			struct_v, struct_cv);
		goto e_inval;
	}
	len = ceph_decode_32(p);
	ceph_decode_need(p, end, len, e_inval);
	struct_end = *p + len;

	ret = ceph_oloc_decode(p, end, &redir->oloc);
	if (ret)
		goto out;

	len = ceph_decode_32(p);
	if (len > 0) {
		pr_warn("ceph_request_redirect::object_name is set\n");
		goto e_inval;
	}

	len = ceph_decode_32(p);
	*p += len; /* skip osd_instructions */

	/* skip the rest */
	*p = struct_end;
out:
	return ret;

e_inval:
	ret = -EINVAL;
	goto out;
}

2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840
struct MOSDOpReply {
	struct ceph_pg pgid;
	u64 flags;
	int result;
	u32 epoch;
	int num_ops;
	u32 outdata_len[CEPH_OSD_MAX_OPS];
	s32 rval[CEPH_OSD_MAX_OPS];
	int retry_attempt;
	struct ceph_eversion replay_version;
	u64 user_version;
	struct ceph_request_redirect redirect;
};
S
Sage Weil 已提交
2841

2842
static int decode_MOSDOpReply(const struct ceph_msg *msg, struct MOSDOpReply *m)
S
Sage Weil 已提交
2843
{
2844 2845 2846 2847
	void *p = msg->front.iov_base;
	void *const end = p + msg->front.iov_len;
	u16 version = le16_to_cpu(msg->hdr.version);
	struct ceph_eversion bad_replay_version;
I
Ilya Dryomov 已提交
2848
	u8 decode_redir;
2849 2850 2851
	u32 len;
	int ret;
	int i;
2852

2853 2854 2855
	ceph_decode_32_safe(&p, end, len, e_inval);
	ceph_decode_need(&p, end, len, e_inval);
	p += len; /* skip oid */
2856

2857 2858 2859
	ret = ceph_decode_pgid(&p, end, &m->pgid);
	if (ret)
		return ret;
2860

2861 2862 2863 2864 2865 2866
	ceph_decode_64_safe(&p, end, m->flags, e_inval);
	ceph_decode_32_safe(&p, end, m->result, e_inval);
	ceph_decode_need(&p, end, sizeof(bad_replay_version), e_inval);
	memcpy(&bad_replay_version, p, sizeof(bad_replay_version));
	p += sizeof(bad_replay_version);
	ceph_decode_32_safe(&p, end, m->epoch, e_inval);
2867

2868 2869 2870
	ceph_decode_32_safe(&p, end, m->num_ops, e_inval);
	if (m->num_ops > ARRAY_SIZE(m->outdata_len))
		goto e_inval;
2871

2872 2873 2874
	ceph_decode_need(&p, end, m->num_ops * sizeof(struct ceph_osd_op),
			 e_inval);
	for (i = 0; i < m->num_ops; i++) {
2875 2876
		struct ceph_osd_op *op = p;

2877
		m->outdata_len[i] = le32_to_cpu(op->payload_len);
2878 2879 2880
		p += sizeof(*op);
	}

2881 2882 2883
	ceph_decode_32_safe(&p, end, m->retry_attempt, e_inval);
	for (i = 0; i < m->num_ops; i++)
		ceph_decode_32_safe(&p, end, m->rval[i], e_inval);
S
Sage Weil 已提交
2884

2885 2886 2887 2888 2889 2890 2891 2892 2893
	if (version >= 5) {
		ceph_decode_need(&p, end, sizeof(m->replay_version), e_inval);
		memcpy(&m->replay_version, p, sizeof(m->replay_version));
		p += sizeof(m->replay_version);
		ceph_decode_64_safe(&p, end, m->user_version, e_inval);
	} else {
		m->replay_version = bad_replay_version; /* struct */
		m->user_version = le64_to_cpu(m->replay_version.version);
	}
Y
Yan, Zheng 已提交
2894

2895 2896 2897
	if (version >= 6) {
		if (version >= 7)
			ceph_decode_8_safe(&p, end, decode_redir, e_inval);
I
Ilya Dryomov 已提交
2898 2899 2900 2901 2902 2903 2904
		else
			decode_redir = 1;
	} else {
		decode_redir = 0;
	}

	if (decode_redir) {
2905 2906 2907
		ret = ceph_redirect_decode(&p, end, &m->redirect);
		if (ret)
			return ret;
2908
	} else {
2909
		ceph_oloc_init(&m->redirect.oloc);
2910
	}
S
Sage Weil 已提交
2911

2912 2913 2914 2915 2916 2917 2918
	return 0;

e_inval:
	return -EINVAL;
}

/*
I
Ilya Dryomov 已提交
2919 2920
 * Handle MOSDOpReply.  Set ->r_result and call the callback if it is
 * specified.
2921
 */
2922
static void handle_reply(struct ceph_osd *osd, struct ceph_msg *msg)
2923
{
2924
	struct ceph_osd_client *osdc = osd->o_osdc;
2925 2926 2927 2928 2929 2930 2931 2932 2933
	struct ceph_osd_request *req;
	struct MOSDOpReply m;
	u64 tid = le64_to_cpu(msg->hdr.tid);
	u32 data_len = 0;
	int ret;
	int i;

	dout("%s msg %p tid %llu\n", __func__, msg, tid);

2934 2935 2936 2937 2938 2939 2940 2941 2942
	down_read(&osdc->lock);
	if (!osd_registered(osd)) {
		dout("%s osd%d unknown\n", __func__, osd->o_osd);
		goto out_unlock_osdc;
	}
	WARN_ON(osd->o_osd != le64_to_cpu(msg->hdr.src.num));

	mutex_lock(&osd->lock);
	req = lookup_request(&osd->o_requests, tid);
2943
	if (!req) {
2944 2945
		dout("%s osd%d tid %llu unknown\n", __func__, osd->o_osd, tid);
		goto out_unlock_session;
2946 2947
	}

2948
	m.redirect.oloc.pool_ns = req->r_t.target_oloc.pool_ns;
2949
	ret = decode_MOSDOpReply(msg, &m);
2950
	m.redirect.oloc.pool_ns = NULL;
2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966
	if (ret) {
		pr_err("failed to decode MOSDOpReply for tid %llu: %d\n",
		       req->r_tid, ret);
		ceph_msg_dump(msg);
		goto fail_request;
	}
	dout("%s req %p tid %llu flags 0x%llx pgid %llu.%x epoch %u attempt %d v %u'%llu uv %llu\n",
	     __func__, req, req->r_tid, m.flags, m.pgid.pool, m.pgid.seed,
	     m.epoch, m.retry_attempt, le32_to_cpu(m.replay_version.epoch),
	     le64_to_cpu(m.replay_version.version), m.user_version);

	if (m.retry_attempt >= 0) {
		if (m.retry_attempt != req->r_attempts - 1) {
			dout("req %p tid %llu retry_attempt %d != %d, ignoring\n",
			     req, req->r_tid, m.retry_attempt,
			     req->r_attempts - 1);
2967
			goto out_unlock_session;
2968 2969 2970 2971 2972 2973 2974 2975
		}
	} else {
		WARN_ON(1); /* MOSDOpReply v4 is assumed */
	}

	if (!ceph_oloc_empty(&m.redirect.oloc)) {
		dout("req %p tid %llu redirect pool %lld\n", req, req->r_tid,
		     m.redirect.oloc.pool);
2976 2977
		unlink_request(osd, req);
		mutex_unlock(&osd->lock);
2978

2979 2980 2981 2982 2983
		/*
		 * Not ceph_oloc_copy() - changing pool_ns is not
		 * supported.
		 */
		req->r_t.target_oloc.pool = m.redirect.oloc.pool;
2984 2985 2986 2987
		req->r_flags |= CEPH_OSD_FLAG_REDIRECTED;
		req->r_tid = 0;
		__submit_request(req, false);
		goto out_unlock_osdc;
2988 2989
	}

2990 2991 2992 2993
	if (m.num_ops != req->r_num_ops) {
		pr_err("num_ops %d != %d for tid %llu\n", m.num_ops,
		       req->r_num_ops, req->r_tid);
		goto fail_request;
S
Sage Weil 已提交
2994
	}
2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006
	for (i = 0; i < req->r_num_ops; i++) {
		dout(" req %p tid %llu op %d rval %d len %u\n", req,
		     req->r_tid, i, m.rval[i], m.outdata_len[i]);
		req->r_ops[i].rval = m.rval[i];
		req->r_ops[i].outdata_len = m.outdata_len[i];
		data_len += m.outdata_len[i];
	}
	if (data_len != le32_to_cpu(msg->hdr.data_len)) {
		pr_err("sum of lens %u != %u for tid %llu\n", data_len,
		       le32_to_cpu(msg->hdr.data_len), req->r_tid);
		goto fail_request;
	}
I
Ilya Dryomov 已提交
3007 3008
	dout("%s req %p tid %llu result %d data_len %u\n", __func__,
	     req, req->r_tid, m.result, data_len);
S
Sage Weil 已提交
3009

I
Ilya Dryomov 已提交
3010 3011 3012 3013 3014 3015 3016
	/*
	 * Since we only ever request ONDISK, we should only ever get
	 * one (type of) reply back.
	 */
	WARN_ON(!(m.flags & CEPH_OSD_FLAG_ONDISK));
	req->r_result = m.result ?: data_len;
	finish_request(req);
3017 3018
	mutex_unlock(&osd->lock);
	up_read(&osdc->lock);
S
Sage Weil 已提交
3019

I
Ilya Dryomov 已提交
3020 3021 3022
	__complete_request(req);
	complete_all(&req->r_completion);
	ceph_osdc_put_request(req);
S
Sage Weil 已提交
3023 3024
	return;

3025
fail_request:
I
Ilya Dryomov 已提交
3026
	complete_request(req, -EIO);
3027 3028 3029 3030
out_unlock_session:
	mutex_unlock(&osd->lock);
out_unlock_osdc:
	up_read(&osdc->lock);
S
Sage Weil 已提交
3031 3032
}

I
Ilya Dryomov 已提交
3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044
static void set_pool_was_full(struct ceph_osd_client *osdc)
{
	struct rb_node *n;

	for (n = rb_first(&osdc->osdmap->pg_pools); n; n = rb_next(n)) {
		struct ceph_pg_pool_info *pi =
		    rb_entry(n, struct ceph_pg_pool_info, node);

		pi->was_full = __pool_full(pi);
	}
}

3045
static bool pool_cleared_full(struct ceph_osd_client *osdc, s64 pool_id)
S
Sage Weil 已提交
3046
{
3047
	struct ceph_pg_pool_info *pi;
S
Sage Weil 已提交
3048

3049 3050 3051
	pi = ceph_pg_pool_by_id(osdc->osdmap, pool_id);
	if (!pi)
		return false;
S
Sage Weil 已提交
3052

3053
	return pi->was_full && !__pool_full(pi);
3054 3055
}

3056 3057 3058 3059 3060 3061
static enum calc_target_result
recalc_linger_target(struct ceph_osd_linger_request *lreq)
{
	struct ceph_osd_client *osdc = lreq->osdc;
	enum calc_target_result ct_res;

3062
	ct_res = calc_target(osdc, &lreq->t, true);
3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075
	if (ct_res == CALC_TARGET_NEED_RESEND) {
		struct ceph_osd *osd;

		osd = lookup_create_osd(osdc, lreq->t.osd, true);
		if (osd != lreq->osd) {
			unlink_linger(lreq->osd, lreq);
			link_linger(osd, lreq);
		}
	}

	return ct_res;
}

3076
/*
3077
 * Requeue requests whose mapping to an OSD has changed.
3078
 */
3079 3080 3081 3082 3083 3084
static void scan_requests(struct ceph_osd *osd,
			  bool force_resend,
			  bool cleared_full,
			  bool check_pool_cleared_full,
			  struct rb_root *need_resend,
			  struct list_head *need_resend_linger)
3085
{
3086 3087 3088 3089
	struct ceph_osd_client *osdc = osd->o_osdc;
	struct rb_node *n;
	bool force_resend_writes;

3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109
	for (n = rb_first(&osd->o_linger_requests); n; ) {
		struct ceph_osd_linger_request *lreq =
		    rb_entry(n, struct ceph_osd_linger_request, node);
		enum calc_target_result ct_res;

		n = rb_next(n); /* recalc_linger_target() */

		dout("%s lreq %p linger_id %llu\n", __func__, lreq,
		     lreq->linger_id);
		ct_res = recalc_linger_target(lreq);
		switch (ct_res) {
		case CALC_TARGET_NO_ACTION:
			force_resend_writes = cleared_full ||
			    (check_pool_cleared_full &&
			     pool_cleared_full(osdc, lreq->t.base_oloc.pool));
			if (!force_resend && !force_resend_writes)
				break;

			/* fall through */
		case CALC_TARGET_NEED_RESEND:
I
Ilya Dryomov 已提交
3110
			cancel_linger_map_check(lreq);
3111 3112 3113 3114 3115 3116 3117 3118 3119
			/*
			 * scan_requests() for the previous epoch(s)
			 * may have already added it to the list, since
			 * it's not unlinked here.
			 */
			if (list_empty(&lreq->scan_item))
				list_add_tail(&lreq->scan_item, need_resend_linger);
			break;
		case CALC_TARGET_POOL_DNE:
I
Ilya Dryomov 已提交
3120
			check_linger_pool_dne(lreq);
3121 3122 3123 3124
			break;
		}
	}

3125 3126 3127 3128 3129
	for (n = rb_first(&osd->o_requests); n; ) {
		struct ceph_osd_request *req =
		    rb_entry(n, struct ceph_osd_request, r_node);
		enum calc_target_result ct_res;

I
Ilya Dryomov 已提交
3130
		n = rb_next(n); /* unlink_request(), check_pool_dne() */
3131 3132

		dout("%s req %p tid %llu\n", __func__, req, req->r_tid);
3133
		ct_res = calc_target(osdc, &req->r_t, false);
3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145
		switch (ct_res) {
		case CALC_TARGET_NO_ACTION:
			force_resend_writes = cleared_full ||
			    (check_pool_cleared_full &&
			     pool_cleared_full(osdc, req->r_t.base_oloc.pool));
			if (!force_resend &&
			    (!(req->r_flags & CEPH_OSD_FLAG_WRITE) ||
			     !force_resend_writes))
				break;

			/* fall through */
		case CALC_TARGET_NEED_RESEND:
I
Ilya Dryomov 已提交
3146
			cancel_map_check(req);
3147 3148 3149 3150
			unlink_request(osd, req);
			insert_request(need_resend, req);
			break;
		case CALC_TARGET_POOL_DNE:
I
Ilya Dryomov 已提交
3151
			check_pool_dne(req);
3152
			break;
3153
		}
3154
	}
3155
}
3156

I
Ilya Dryomov 已提交
3157
static int handle_one_map(struct ceph_osd_client *osdc,
3158 3159 3160
			  void *p, void *end, bool incremental,
			  struct rb_root *need_resend,
			  struct list_head *need_resend_linger)
I
Ilya Dryomov 已提交
3161 3162 3163 3164 3165 3166
{
	struct ceph_osdmap *newmap;
	struct rb_node *n;
	bool skipped_map = false;
	bool was_full;

3167
	was_full = ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL);
I
Ilya Dryomov 已提交
3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204
	set_pool_was_full(osdc);

	if (incremental)
		newmap = osdmap_apply_incremental(&p, end, osdc->osdmap);
	else
		newmap = ceph_osdmap_decode(&p, end);
	if (IS_ERR(newmap))
		return PTR_ERR(newmap);

	if (newmap != osdc->osdmap) {
		/*
		 * Preserve ->was_full before destroying the old map.
		 * For pools that weren't in the old map, ->was_full
		 * should be false.
		 */
		for (n = rb_first(&newmap->pg_pools); n; n = rb_next(n)) {
			struct ceph_pg_pool_info *pi =
			    rb_entry(n, struct ceph_pg_pool_info, node);
			struct ceph_pg_pool_info *old_pi;

			old_pi = ceph_pg_pool_by_id(osdc->osdmap, pi->id);
			if (old_pi)
				pi->was_full = old_pi->was_full;
			else
				WARN_ON(pi->was_full);
		}

		if (osdc->osdmap->epoch &&
		    osdc->osdmap->epoch + 1 < newmap->epoch) {
			WARN_ON(incremental);
			skipped_map = true;
		}

		ceph_osdmap_destroy(osdc->osdmap);
		osdc->osdmap = newmap;
	}

3205
	was_full &= !ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL);
3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221
	scan_requests(&osdc->homeless_osd, skipped_map, was_full, true,
		      need_resend, need_resend_linger);

	for (n = rb_first(&osdc->osds); n; ) {
		struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node);

		n = rb_next(n); /* close_osd() */

		scan_requests(osd, skipped_map, was_full, true, need_resend,
			      need_resend_linger);
		if (!ceph_osd_is_up(osdc->osdmap, osd->o_osd) ||
		    memcmp(&osd->o_con.peer_addr,
			   ceph_osd_addr(osdc->osdmap, osd->o_osd),
			   sizeof(struct ceph_entity_addr)))
			close_osd(osd);
	}
I
Ilya Dryomov 已提交
3222 3223 3224

	return 0;
}
3225

3226 3227 3228 3229
static void kick_requests(struct ceph_osd_client *osdc,
			  struct rb_root *need_resend,
			  struct list_head *need_resend_linger)
{
3230
	struct ceph_osd_linger_request *lreq, *nlreq;
3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241
	struct rb_node *n;

	for (n = rb_first(need_resend); n; ) {
		struct ceph_osd_request *req =
		    rb_entry(n, struct ceph_osd_request, r_node);
		struct ceph_osd *osd;

		n = rb_next(n);
		erase_request(need_resend, req); /* before link_request() */

		WARN_ON(req->r_osd);
3242
		calc_target(osdc, &req->r_t, false);
3243 3244 3245 3246 3247
		osd = lookup_create_osd(osdc, req->r_t.osd, true);
		link_request(osd, req);
		if (!req->r_linger) {
			if (!osd_homeless(osd) && !req->r_t.paused)
				send_request(req);
3248 3249
		} else {
			cancel_linger_request(req);
3250 3251
		}
	}
3252 3253 3254 3255 3256 3257 3258

	list_for_each_entry_safe(lreq, nlreq, need_resend_linger, scan_item) {
		if (!osd_homeless(lreq->osd))
			send_linger(lreq);

		list_del_init(&lreq->scan_item);
	}
3259 3260
}

S
Sage Weil 已提交
3261 3262 3263 3264 3265 3266 3267 3268 3269
/*
 * Process updated osd map.
 *
 * The message contains any number of incremental and full maps, normally
 * indicating some sort of topology change in the cluster.  Kick requests
 * off to different OSDs as needed.
 */
void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg)
{
I
Ilya Dryomov 已提交
3270 3271
	void *p = msg->front.iov_base;
	void *const end = p + msg->front.iov_len;
S
Sage Weil 已提交
3272 3273 3274
	u32 nr_maps, maplen;
	u32 epoch;
	struct ceph_fsid fsid;
3275 3276
	struct rb_root need_resend = RB_ROOT;
	LIST_HEAD(need_resend_linger);
I
Ilya Dryomov 已提交
3277 3278 3279 3280
	bool handled_incremental = false;
	bool was_pauserd, was_pausewr;
	bool pauserd, pausewr;
	int err;
S
Sage Weil 已提交
3281

I
Ilya Dryomov 已提交
3282
	dout("%s have %u\n", __func__, osdc->osdmap->epoch);
3283
	down_write(&osdc->lock);
S
Sage Weil 已提交
3284 3285 3286 3287

	/* verify fsid */
	ceph_decode_need(&p, end, sizeof(fsid), bad);
	ceph_decode_copy(&p, &fsid, sizeof(fsid));
3288
	if (ceph_check_fsid(osdc->client, &fsid) < 0)
I
Ilya Dryomov 已提交
3289
		goto bad;
S
Sage Weil 已提交
3290

3291 3292 3293
	was_pauserd = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD);
	was_pausewr = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR) ||
		      ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) ||
I
Ilya Dryomov 已提交
3294
		      have_pool_full(osdc);
3295

S
Sage Weil 已提交
3296 3297 3298 3299 3300
	/* incremental maps */
	ceph_decode_32_safe(&p, end, nr_maps, bad);
	dout(" %d inc maps\n", nr_maps);
	while (nr_maps > 0) {
		ceph_decode_need(&p, end, 2*sizeof(u32), bad);
3301 3302
		epoch = ceph_decode_32(&p);
		maplen = ceph_decode_32(&p);
S
Sage Weil 已提交
3303
		ceph_decode_need(&p, end, maplen, bad);
I
Ilya Dryomov 已提交
3304 3305
		if (osdc->osdmap->epoch &&
		    osdc->osdmap->epoch + 1 == epoch) {
S
Sage Weil 已提交
3306 3307
			dout("applying incremental map %u len %d\n",
			     epoch, maplen);
3308 3309
			err = handle_one_map(osdc, p, p + maplen, true,
					     &need_resend, &need_resend_linger);
I
Ilya Dryomov 已提交
3310
			if (err)
S
Sage Weil 已提交
3311
				goto bad;
I
Ilya Dryomov 已提交
3312
			handled_incremental = true;
S
Sage Weil 已提交
3313 3314 3315 3316
		} else {
			dout("ignoring incremental map %u len %d\n",
			     epoch, maplen);
		}
I
Ilya Dryomov 已提交
3317
		p += maplen;
S
Sage Weil 已提交
3318 3319
		nr_maps--;
	}
I
Ilya Dryomov 已提交
3320
	if (handled_incremental)
S
Sage Weil 已提交
3321 3322 3323 3324 3325 3326 3327
		goto done;

	/* full maps */
	ceph_decode_32_safe(&p, end, nr_maps, bad);
	dout(" %d full maps\n", nr_maps);
	while (nr_maps) {
		ceph_decode_need(&p, end, 2*sizeof(u32), bad);
3328 3329
		epoch = ceph_decode_32(&p);
		maplen = ceph_decode_32(&p);
S
Sage Weil 已提交
3330 3331 3332 3333
		ceph_decode_need(&p, end, maplen, bad);
		if (nr_maps > 1) {
			dout("skipping non-latest full map %u len %d\n",
			     epoch, maplen);
3334
		} else if (osdc->osdmap->epoch >= epoch) {
S
Sage Weil 已提交
3335 3336 3337 3338 3339
			dout("skipping full map %u len %d, "
			     "older than our %u\n", epoch, maplen,
			     osdc->osdmap->epoch);
		} else {
			dout("taking full map %u len %d\n", epoch, maplen);
3340 3341
			err = handle_one_map(osdc, p, p + maplen, false,
					     &need_resend, &need_resend_linger);
I
Ilya Dryomov 已提交
3342
			if (err)
S
Sage Weil 已提交
3343 3344 3345 3346 3347 3348 3349
				goto bad;
		}
		p += maplen;
		nr_maps--;
	}

done:
3350 3351 3352 3353 3354
	/*
	 * subscribe to subsequent osdmap updates if full to ensure
	 * we find out when we are no longer full and stop returning
	 * ENOSPC.
	 */
3355 3356 3357
	pauserd = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD);
	pausewr = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR) ||
		  ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) ||
I
Ilya Dryomov 已提交
3358
		  have_pool_full(osdc);
3359 3360
	if (was_pauserd || was_pausewr || pauserd || pausewr ||
	    osdc->osdmap->epoch < osdc->epoch_barrier)
I
Ilya Dryomov 已提交
3361
		maybe_request_map(osdc);
3362

3363
	kick_requests(osdc, &need_resend, &need_resend_linger);
I
Ilya Dryomov 已提交
3364

3365
	ceph_osdc_abort_on_full(osdc);
I
Ilya Dryomov 已提交
3366 3367
	ceph_monc_got_map(&osdc->client->monc, CEPH_SUB_OSDMAP,
			  osdc->osdmap->epoch);
3368
	up_write(&osdc->lock);
3369
	wake_up_all(&osdc->client->auth_wq);
S
Sage Weil 已提交
3370 3371 3372 3373
	return;

bad:
	pr_err("osdc handle_map corrupt msg\n");
3374
	ceph_msg_dump(msg);
3375 3376 3377 3378 3379 3380 3381 3382 3383 3384
	up_write(&osdc->lock);
}

/*
 * Resubmit requests pending on the given osd.
 */
static void kick_osd_requests(struct ceph_osd *osd)
{
	struct rb_node *n;

3385
	for (n = rb_first(&osd->o_requests); n; ) {
3386 3387 3388
		struct ceph_osd_request *req =
		    rb_entry(n, struct ceph_osd_request, r_node);

3389 3390
		n = rb_next(n); /* cancel_linger_request() */

3391 3392 3393
		if (!req->r_linger) {
			if (!req->r_t.paused)
				send_request(req);
3394 3395
		} else {
			cancel_linger_request(req);
3396 3397
		}
	}
3398 3399 3400 3401 3402 3403
	for (n = rb_first(&osd->o_linger_requests); n; n = rb_next(n)) {
		struct ceph_osd_linger_request *lreq =
		    rb_entry(n, struct ceph_osd_linger_request, node);

		send_linger(lreq);
	}
3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427
}

/*
 * If the osd connection drops, we need to resubmit all requests.
 */
static void osd_fault(struct ceph_connection *con)
{
	struct ceph_osd *osd = con->private;
	struct ceph_osd_client *osdc = osd->o_osdc;

	dout("%s osd %p osd%d\n", __func__, osd, osd->o_osd);

	down_write(&osdc->lock);
	if (!osd_registered(osd)) {
		dout("%s osd%d unknown\n", __func__, osd->o_osd);
		goto out_unlock;
	}

	if (!reopen_osd(osd))
		kick_osd_requests(osd);
	maybe_request_map(osdc);

out_unlock:
	up_write(&osdc->lock);
S
Sage Weil 已提交
3428 3429
}

3430 3431 3432
/*
 * Process osd watch notifications
 */
3433 3434
static void handle_watch_notify(struct ceph_osd_client *osdc,
				struct ceph_msg *msg)
3435
{
3436 3437 3438 3439 3440 3441 3442
	void *p = msg->front.iov_base;
	void *const end = p + msg->front.iov_len;
	struct ceph_osd_linger_request *lreq;
	struct linger_work *lwork;
	u8 proto_ver, opcode;
	u64 cookie, notify_id;
	u64 notifier_id = 0;
3443
	s32 return_code = 0;
3444 3445
	void *payload = NULL;
	u32 payload_len = 0;
3446 3447 3448 3449

	ceph_decode_8_safe(&p, end, proto_ver, bad);
	ceph_decode_8_safe(&p, end, opcode, bad);
	ceph_decode_64_safe(&p, end, cookie, bad);
3450
	p += 8; /* skip ver */
3451 3452
	ceph_decode_64_safe(&p, end, notify_id, bad);

3453 3454 3455 3456 3457 3458 3459 3460
	if (proto_ver >= 1) {
		ceph_decode_32_safe(&p, end, payload_len, bad);
		ceph_decode_need(&p, end, payload_len, bad);
		payload = p;
		p += payload_len;
	}

	if (le16_to_cpu(msg->hdr.version) >= 2)
3461
		ceph_decode_32_safe(&p, end, return_code, bad);
3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474

	if (le16_to_cpu(msg->hdr.version) >= 3)
		ceph_decode_64_safe(&p, end, notifier_id, bad);

	down_read(&osdc->lock);
	lreq = lookup_linger_osdc(&osdc->linger_requests, cookie);
	if (!lreq) {
		dout("%s opcode %d cookie %llu dne\n", __func__, opcode,
		     cookie);
		goto out_unlock_osdc;
	}

	mutex_lock(&lreq->lock);
3475 3476
	dout("%s opcode %d cookie %llu lreq %p is_watch %d\n", __func__,
	     opcode, cookie, lreq, lreq->is_watch);
3477 3478 3479 3480 3481
	if (opcode == CEPH_WATCH_EVENT_DISCONNECT) {
		if (!lreq->last_error) {
			lreq->last_error = -ENOTCONN;
			queue_watch_error(lreq);
		}
3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506
	} else if (!lreq->is_watch) {
		/* CEPH_WATCH_EVENT_NOTIFY_COMPLETE */
		if (lreq->notify_id && lreq->notify_id != notify_id) {
			dout("lreq %p notify_id %llu != %llu, ignoring\n", lreq,
			     lreq->notify_id, notify_id);
		} else if (!completion_done(&lreq->notify_finish_wait)) {
			struct ceph_msg_data *data =
			    list_first_entry_or_null(&msg->data,
						     struct ceph_msg_data,
						     links);

			if (data) {
				if (lreq->preply_pages) {
					WARN_ON(data->type !=
							CEPH_MSG_DATA_PAGES);
					*lreq->preply_pages = data->pages;
					*lreq->preply_len = data->length;
				} else {
					ceph_release_page_vector(data->pages,
					       calc_pages_for(0, data->length));
				}
			}
			lreq->notify_finish_error = return_code;
			complete_all(&lreq->notify_finish_wait);
		}
3507 3508 3509 3510 3511 3512
	} else {
		/* CEPH_WATCH_EVENT_NOTIFY */
		lwork = lwork_alloc(lreq, do_watch_notify);
		if (!lwork) {
			pr_err("failed to allocate notify-lwork\n");
			goto out_unlock_lreq;
3513 3514
		}

3515 3516 3517 3518 3519 3520
		lwork->notify.notify_id = notify_id;
		lwork->notify.notifier_id = notifier_id;
		lwork->notify.payload = payload;
		lwork->notify.payload_len = payload_len;
		lwork->notify.msg = ceph_msg_get(msg);
		lwork_queue(lwork);
3521
	}
3522

3523 3524 3525 3526
out_unlock_lreq:
	mutex_unlock(&lreq->lock);
out_unlock_osdc:
	up_read(&osdc->lock);
3527 3528 3529 3530 3531 3532
	return;

bad:
	pr_err("osdc handle_watch_notify corrupt msg\n");
}

3533 3534 3535 3536 3537 3538 3539
/*
 * Register request, send initial attempt.
 */
int ceph_osdc_start_request(struct ceph_osd_client *osdc,
			    struct ceph_osd_request *req,
			    bool nofail)
{
3540 3541 3542
	down_read(&osdc->lock);
	submit_request(req, false);
	up_read(&osdc->lock);
3543

3544
	return 0;
S
Sage Weil 已提交
3545
}
3546
EXPORT_SYMBOL(ceph_osdc_start_request);
S
Sage Weil 已提交
3547

3548
/*
3549 3550
 * Unregister a registered request.  The request is not completed:
 * ->r_result isn't set and __complete_request() isn't called.
3551 3552 3553 3554 3555
 */
void ceph_osdc_cancel_request(struct ceph_osd_request *req)
{
	struct ceph_osd_client *osdc = req->r_osdc;

3556 3557 3558 3559
	down_write(&osdc->lock);
	if (req->r_osd)
		cancel_request(req);
	up_write(&osdc->lock);
3560 3561 3562
}
EXPORT_SYMBOL(ceph_osdc_cancel_request);

S
Sage Weil 已提交
3563
/*
I
Ilya Dryomov 已提交
3564
 * @timeout: in jiffies, 0 means "wait forever"
S
Sage Weil 已提交
3565
 */
I
Ilya Dryomov 已提交
3566 3567
static int wait_request_timeout(struct ceph_osd_request *req,
				unsigned long timeout)
S
Sage Weil 已提交
3568
{
I
Ilya Dryomov 已提交
3569
	long left;
3570

I
Ilya Dryomov 已提交
3571
	dout("%s req %p tid %llu\n", __func__, req, req->r_tid);
3572
	left = wait_for_completion_killable_timeout(&req->r_completion,
I
Ilya Dryomov 已提交
3573 3574 3575
						ceph_timeout_jiffies(timeout));
	if (left <= 0) {
		left = left ?: -ETIMEDOUT;
3576
		ceph_osdc_cancel_request(req);
I
Ilya Dryomov 已提交
3577 3578
	} else {
		left = req->r_result; /* completed */
S
Sage Weil 已提交
3579 3580
	}

I
Ilya Dryomov 已提交
3581 3582 3583 3584 3585 3586 3587 3588 3589 3590
	return left;
}

/*
 * wait for a request to complete
 */
int ceph_osdc_wait_request(struct ceph_osd_client *osdc,
			   struct ceph_osd_request *req)
{
	return wait_request_timeout(req, 0);
S
Sage Weil 已提交
3591
}
3592
EXPORT_SYMBOL(ceph_osdc_wait_request);
S
Sage Weil 已提交
3593 3594 3595 3596 3597 3598

/*
 * sync - wait for all in-flight requests to flush.  avoid starvation.
 */
void ceph_osdc_sync(struct ceph_osd_client *osdc)
{
3599 3600
	struct rb_node *n, *p;
	u64 last_tid = atomic64_read(&osdc->last_tid);
S
Sage Weil 已提交
3601

3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616
again:
	down_read(&osdc->lock);
	for (n = rb_first(&osdc->osds); n; n = rb_next(n)) {
		struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node);

		mutex_lock(&osd->lock);
		for (p = rb_first(&osd->o_requests); p; p = rb_next(p)) {
			struct ceph_osd_request *req =
			    rb_entry(p, struct ceph_osd_request, r_node);

			if (req->r_tid > last_tid)
				break;

			if (!(req->r_flags & CEPH_OSD_FLAG_WRITE))
				continue;
S
Sage Weil 已提交
3617

3618 3619 3620 3621 3622
			ceph_osdc_get_request(req);
			mutex_unlock(&osd->lock);
			up_read(&osdc->lock);
			dout("%s waiting on req %p tid %llu last_tid %llu\n",
			     __func__, req, req->r_tid, last_tid);
I
Ilya Dryomov 已提交
3623
			wait_for_completion(&req->r_completion);
3624 3625 3626
			ceph_osdc_put_request(req);
			goto again;
		}
S
Sage Weil 已提交
3627

3628
		mutex_unlock(&osd->lock);
S
Sage Weil 已提交
3629
	}
3630 3631 3632

	up_read(&osdc->lock);
	dout("%s done last_tid %llu\n", __func__, last_tid);
S
Sage Weil 已提交
3633
}
3634
EXPORT_SYMBOL(ceph_osdc_sync);
S
Sage Weil 已提交
3635

3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673
static struct ceph_osd_request *
alloc_linger_request(struct ceph_osd_linger_request *lreq)
{
	struct ceph_osd_request *req;

	req = ceph_osdc_alloc_request(lreq->osdc, NULL, 1, false, GFP_NOIO);
	if (!req)
		return NULL;

	ceph_oid_copy(&req->r_base_oid, &lreq->t.base_oid);
	ceph_oloc_copy(&req->r_base_oloc, &lreq->t.base_oloc);

	if (ceph_osdc_alloc_messages(req, GFP_NOIO)) {
		ceph_osdc_put_request(req);
		return NULL;
	}

	return req;
}

/*
 * Returns a handle, caller owns a ref.
 */
struct ceph_osd_linger_request *
ceph_osdc_watch(struct ceph_osd_client *osdc,
		struct ceph_object_id *oid,
		struct ceph_object_locator *oloc,
		rados_watchcb2_t wcb,
		rados_watcherrcb_t errcb,
		void *data)
{
	struct ceph_osd_linger_request *lreq;
	int ret;

	lreq = linger_alloc(osdc);
	if (!lreq)
		return ERR_PTR(-ENOMEM);

3674
	lreq->is_watch = true;
3675 3676 3677
	lreq->wcb = wcb;
	lreq->errcb = errcb;
	lreq->data = data;
3678
	lreq->watch_valid_thru = jiffies;
3679 3680 3681

	ceph_oid_copy(&lreq->t.base_oid, oid);
	ceph_oloc_copy(&lreq->t.base_oloc, oloc);
3682
	lreq->t.flags = CEPH_OSD_FLAG_WRITE;
3683
	ktime_get_real_ts(&lreq->mtime);
3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739

	lreq->reg_req = alloc_linger_request(lreq);
	if (!lreq->reg_req) {
		ret = -ENOMEM;
		goto err_put_lreq;
	}

	lreq->ping_req = alloc_linger_request(lreq);
	if (!lreq->ping_req) {
		ret = -ENOMEM;
		goto err_put_lreq;
	}

	down_write(&osdc->lock);
	linger_register(lreq); /* before osd_req_op_* */
	osd_req_op_watch_init(lreq->reg_req, 0, lreq->linger_id,
			      CEPH_OSD_WATCH_OP_WATCH);
	osd_req_op_watch_init(lreq->ping_req, 0, lreq->linger_id,
			      CEPH_OSD_WATCH_OP_PING);
	linger_submit(lreq);
	up_write(&osdc->lock);

	ret = linger_reg_commit_wait(lreq);
	if (ret) {
		linger_cancel(lreq);
		goto err_put_lreq;
	}

	return lreq;

err_put_lreq:
	linger_put(lreq);
	return ERR_PTR(ret);
}
EXPORT_SYMBOL(ceph_osdc_watch);

/*
 * Releases a ref.
 *
 * Times out after mount_timeout to preserve rbd unmap behaviour
 * introduced in 2894e1d76974 ("rbd: timeout watch teardown on unmap
 * with mount_timeout").
 */
int ceph_osdc_unwatch(struct ceph_osd_client *osdc,
		      struct ceph_osd_linger_request *lreq)
{
	struct ceph_options *opts = osdc->client->options;
	struct ceph_osd_request *req;
	int ret;

	req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_NOIO);
	if (!req)
		return -ENOMEM;

	ceph_oid_copy(&req->r_base_oid, &lreq->t.base_oid);
	ceph_oloc_copy(&req->r_base_oloc, &lreq->t.base_oloc);
3740
	req->r_flags = CEPH_OSD_FLAG_WRITE;
3741
	ktime_get_real_ts(&req->r_mtime);
3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829
	osd_req_op_watch_init(req, 0, lreq->linger_id,
			      CEPH_OSD_WATCH_OP_UNWATCH);

	ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
	if (ret)
		goto out_put_req;

	ceph_osdc_start_request(osdc, req, false);
	linger_cancel(lreq);
	linger_put(lreq);
	ret = wait_request_timeout(req, opts->mount_timeout);

out_put_req:
	ceph_osdc_put_request(req);
	return ret;
}
EXPORT_SYMBOL(ceph_osdc_unwatch);

static int osd_req_op_notify_ack_init(struct ceph_osd_request *req, int which,
				      u64 notify_id, u64 cookie, void *payload,
				      size_t payload_len)
{
	struct ceph_osd_req_op *op;
	struct ceph_pagelist *pl;
	int ret;

	op = _osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY_ACK, 0);

	pl = kmalloc(sizeof(*pl), GFP_NOIO);
	if (!pl)
		return -ENOMEM;

	ceph_pagelist_init(pl);
	ret = ceph_pagelist_encode_64(pl, notify_id);
	ret |= ceph_pagelist_encode_64(pl, cookie);
	if (payload) {
		ret |= ceph_pagelist_encode_32(pl, payload_len);
		ret |= ceph_pagelist_append(pl, payload, payload_len);
	} else {
		ret |= ceph_pagelist_encode_32(pl, 0);
	}
	if (ret) {
		ceph_pagelist_release(pl);
		return -ENOMEM;
	}

	ceph_osd_data_pagelist_init(&op->notify_ack.request_data, pl);
	op->indata_len = pl->length;
	return 0;
}

int ceph_osdc_notify_ack(struct ceph_osd_client *osdc,
			 struct ceph_object_id *oid,
			 struct ceph_object_locator *oloc,
			 u64 notify_id,
			 u64 cookie,
			 void *payload,
			 size_t payload_len)
{
	struct ceph_osd_request *req;
	int ret;

	req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_NOIO);
	if (!req)
		return -ENOMEM;

	ceph_oid_copy(&req->r_base_oid, oid);
	ceph_oloc_copy(&req->r_base_oloc, oloc);
	req->r_flags = CEPH_OSD_FLAG_READ;

	ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
	if (ret)
		goto out_put_req;

	ret = osd_req_op_notify_ack_init(req, 0, notify_id, cookie, payload,
					 payload_len);
	if (ret)
		goto out_put_req;

	ceph_osdc_start_request(osdc, req, false);
	ret = ceph_osdc_wait_request(osdc, req);

out_put_req:
	ceph_osdc_put_request(req);
	return ret;
}
EXPORT_SYMBOL(ceph_osdc_notify_ack);

3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939
static int osd_req_op_notify_init(struct ceph_osd_request *req, int which,
				  u64 cookie, u32 prot_ver, u32 timeout,
				  void *payload, size_t payload_len)
{
	struct ceph_osd_req_op *op;
	struct ceph_pagelist *pl;
	int ret;

	op = _osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY, 0);
	op->notify.cookie = cookie;

	pl = kmalloc(sizeof(*pl), GFP_NOIO);
	if (!pl)
		return -ENOMEM;

	ceph_pagelist_init(pl);
	ret = ceph_pagelist_encode_32(pl, 1); /* prot_ver */
	ret |= ceph_pagelist_encode_32(pl, timeout);
	ret |= ceph_pagelist_encode_32(pl, payload_len);
	ret |= ceph_pagelist_append(pl, payload, payload_len);
	if (ret) {
		ceph_pagelist_release(pl);
		return -ENOMEM;
	}

	ceph_osd_data_pagelist_init(&op->notify.request_data, pl);
	op->indata_len = pl->length;
	return 0;
}

/*
 * @timeout: in seconds
 *
 * @preply_{pages,len} are initialized both on success and error.
 * The caller is responsible for:
 *
 *     ceph_release_page_vector(reply_pages, calc_pages_for(0, reply_len))
 */
int ceph_osdc_notify(struct ceph_osd_client *osdc,
		     struct ceph_object_id *oid,
		     struct ceph_object_locator *oloc,
		     void *payload,
		     size_t payload_len,
		     u32 timeout,
		     struct page ***preply_pages,
		     size_t *preply_len)
{
	struct ceph_osd_linger_request *lreq;
	struct page **pages;
	int ret;

	WARN_ON(!timeout);
	if (preply_pages) {
		*preply_pages = NULL;
		*preply_len = 0;
	}

	lreq = linger_alloc(osdc);
	if (!lreq)
		return -ENOMEM;

	lreq->preply_pages = preply_pages;
	lreq->preply_len = preply_len;

	ceph_oid_copy(&lreq->t.base_oid, oid);
	ceph_oloc_copy(&lreq->t.base_oloc, oloc);
	lreq->t.flags = CEPH_OSD_FLAG_READ;

	lreq->reg_req = alloc_linger_request(lreq);
	if (!lreq->reg_req) {
		ret = -ENOMEM;
		goto out_put_lreq;
	}

	/* for notify_id */
	pages = ceph_alloc_page_vector(1, GFP_NOIO);
	if (IS_ERR(pages)) {
		ret = PTR_ERR(pages);
		goto out_put_lreq;
	}

	down_write(&osdc->lock);
	linger_register(lreq); /* before osd_req_op_* */
	ret = osd_req_op_notify_init(lreq->reg_req, 0, lreq->linger_id, 1,
				     timeout, payload, payload_len);
	if (ret) {
		linger_unregister(lreq);
		up_write(&osdc->lock);
		ceph_release_page_vector(pages, 1);
		goto out_put_lreq;
	}
	ceph_osd_data_pages_init(osd_req_op_data(lreq->reg_req, 0, notify,
						 response_data),
				 pages, PAGE_SIZE, 0, false, true);
	linger_submit(lreq);
	up_write(&osdc->lock);

	ret = linger_reg_commit_wait(lreq);
	if (!ret)
		ret = linger_notify_finish_wait(lreq);
	else
		dout("lreq %p failed to initiate notify %d\n", lreq, ret);

	linger_cancel(lreq);
out_put_lreq:
	linger_put(lreq);
	return ret;
}
EXPORT_SYMBOL(ceph_osdc_notify);

3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973
/*
 * Return the number of milliseconds since the watch was last
 * confirmed, or an error.  If there is an error, the watch is no
 * longer valid, and should be destroyed with ceph_osdc_unwatch().
 */
int ceph_osdc_watch_check(struct ceph_osd_client *osdc,
			  struct ceph_osd_linger_request *lreq)
{
	unsigned long stamp, age;
	int ret;

	down_read(&osdc->lock);
	mutex_lock(&lreq->lock);
	stamp = lreq->watch_valid_thru;
	if (!list_empty(&lreq->pending_lworks)) {
		struct linger_work *lwork =
		    list_first_entry(&lreq->pending_lworks,
				     struct linger_work,
				     pending_item);

		if (time_before(lwork->queued_stamp, stamp))
			stamp = lwork->queued_stamp;
	}
	age = jiffies - stamp;
	dout("%s lreq %p linger_id %llu age %lu last_error %d\n", __func__,
	     lreq, lreq->linger_id, age, lreq->last_error);
	/* we are truncating to msecs, so return a safe upper bound */
	ret = lreq->last_error ?: 1 + jiffies_to_msecs(age);

	mutex_unlock(&lreq->lock);
	up_read(&osdc->lock);
	return ret;
}

3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081
static int decode_watcher(void **p, void *end, struct ceph_watch_item *item)
{
	u8 struct_v;
	u32 struct_len;
	int ret;

	ret = ceph_start_decoding(p, end, 2, "watch_item_t",
				  &struct_v, &struct_len);
	if (ret)
		return ret;

	ceph_decode_copy(p, &item->name, sizeof(item->name));
	item->cookie = ceph_decode_64(p);
	*p += 4; /* skip timeout_seconds */
	if (struct_v >= 2) {
		ceph_decode_copy(p, &item->addr, sizeof(item->addr));
		ceph_decode_addr(&item->addr);
	}

	dout("%s %s%llu cookie %llu addr %s\n", __func__,
	     ENTITY_NAME(item->name), item->cookie,
	     ceph_pr_addr(&item->addr.in_addr));
	return 0;
}

static int decode_watchers(void **p, void *end,
			   struct ceph_watch_item **watchers,
			   u32 *num_watchers)
{
	u8 struct_v;
	u32 struct_len;
	int i;
	int ret;

	ret = ceph_start_decoding(p, end, 1, "obj_list_watch_response_t",
				  &struct_v, &struct_len);
	if (ret)
		return ret;

	*num_watchers = ceph_decode_32(p);
	*watchers = kcalloc(*num_watchers, sizeof(**watchers), GFP_NOIO);
	if (!*watchers)
		return -ENOMEM;

	for (i = 0; i < *num_watchers; i++) {
		ret = decode_watcher(p, end, *watchers + i);
		if (ret) {
			kfree(*watchers);
			return ret;
		}
	}

	return 0;
}

/*
 * On success, the caller is responsible for:
 *
 *     kfree(watchers);
 */
int ceph_osdc_list_watchers(struct ceph_osd_client *osdc,
			    struct ceph_object_id *oid,
			    struct ceph_object_locator *oloc,
			    struct ceph_watch_item **watchers,
			    u32 *num_watchers)
{
	struct ceph_osd_request *req;
	struct page **pages;
	int ret;

	req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_NOIO);
	if (!req)
		return -ENOMEM;

	ceph_oid_copy(&req->r_base_oid, oid);
	ceph_oloc_copy(&req->r_base_oloc, oloc);
	req->r_flags = CEPH_OSD_FLAG_READ;

	ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
	if (ret)
		goto out_put_req;

	pages = ceph_alloc_page_vector(1, GFP_NOIO);
	if (IS_ERR(pages)) {
		ret = PTR_ERR(pages);
		goto out_put_req;
	}

	osd_req_op_init(req, 0, CEPH_OSD_OP_LIST_WATCHERS, 0);
	ceph_osd_data_pages_init(osd_req_op_data(req, 0, list_watchers,
						 response_data),
				 pages, PAGE_SIZE, 0, false, true);

	ceph_osdc_start_request(osdc, req, false);
	ret = ceph_osdc_wait_request(osdc, req);
	if (ret >= 0) {
		void *p = page_address(pages[0]);
		void *const end = p + req->r_ops[0].outdata_len;

		ret = decode_watchers(&p, end, watchers, num_watchers);
	}

out_put_req:
	ceph_osdc_put_request(req);
	return ret;
}
EXPORT_SYMBOL(ceph_osdc_list_watchers);

4082 4083 4084 4085
/*
 * Call all pending notify callbacks - for use after a watch is
 * unregistered, to make sure no more callbacks for it will be invoked
 */
S
stephen hemminger 已提交
4086
void ceph_osdc_flush_notifies(struct ceph_osd_client *osdc)
4087
{
4088
	dout("%s osdc %p\n", __func__, osdc);
4089 4090 4091 4092
	flush_workqueue(osdc->notify_wq);
}
EXPORT_SYMBOL(ceph_osdc_flush_notifies);

4093 4094 4095 4096 4097 4098 4099
void ceph_osdc_maybe_request_map(struct ceph_osd_client *osdc)
{
	down_read(&osdc->lock);
	maybe_request_map(osdc);
	up_read(&osdc->lock);
}
EXPORT_SYMBOL(ceph_osdc_maybe_request_map);
4100

4101 4102 4103 4104
/*
 * Execute an OSD class method on an object.
 *
 * @flags: CEPH_OSD_FLAG_*
4105
 * @resp_len: in/out param for reply length
4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117
 */
int ceph_osdc_call(struct ceph_osd_client *osdc,
		   struct ceph_object_id *oid,
		   struct ceph_object_locator *oloc,
		   const char *class, const char *method,
		   unsigned int flags,
		   struct page *req_page, size_t req_len,
		   struct page *resp_page, size_t *resp_len)
{
	struct ceph_osd_request *req;
	int ret;

4118 4119 4120
	if (req_len > PAGE_SIZE || (resp_page && *resp_len > PAGE_SIZE))
		return -E2BIG;

4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138
	req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_NOIO);
	if (!req)
		return -ENOMEM;

	ceph_oid_copy(&req->r_base_oid, oid);
	ceph_oloc_copy(&req->r_base_oloc, oloc);
	req->r_flags = flags;

	ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
	if (ret)
		goto out_put_req;

	osd_req_op_cls_init(req, 0, CEPH_OSD_OP_CALL, class, method);
	if (req_page)
		osd_req_op_cls_request_data_pages(req, 0, &req_page, req_len,
						  0, false, false);
	if (resp_page)
		osd_req_op_cls_response_data_pages(req, 0, &resp_page,
4139
						   *resp_len, 0, false, false);
4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154

	ceph_osdc_start_request(osdc, req, false);
	ret = ceph_osdc_wait_request(osdc, req);
	if (ret >= 0) {
		ret = req->r_ops[0].rval;
		if (resp_page)
			*resp_len = req->r_ops[0].outdata_len;
	}

out_put_req:
	ceph_osdc_put_request(req);
	return ret;
}
EXPORT_SYMBOL(ceph_osdc_call);

S
Sage Weil 已提交
4155 4156 4157 4158 4159 4160 4161 4162 4163
/*
 * init, shutdown
 */
int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client)
{
	int err;

	dout("init\n");
	osdc->client = client;
4164
	init_rwsem(&osdc->lock);
S
Sage Weil 已提交
4165
	osdc->osds = RB_ROOT;
4166
	INIT_LIST_HEAD(&osdc->osd_lru);
4167
	spin_lock_init(&osdc->osd_lru_lock);
4168 4169 4170
	osd_init(&osdc->homeless_osd);
	osdc->homeless_osd.o_osdc = osdc;
	osdc->homeless_osd.o_osd = CEPH_HOMELESS_OSD;
4171
	osdc->last_linger_id = CEPH_LINGER_ID_START;
4172
	osdc->linger_requests = RB_ROOT;
I
Ilya Dryomov 已提交
4173 4174
	osdc->map_checks = RB_ROOT;
	osdc->linger_map_checks = RB_ROOT;
S
Sage Weil 已提交
4175
	INIT_DELAYED_WORK(&osdc->timeout_work, handle_timeout);
4176 4177
	INIT_DELAYED_WORK(&osdc->osds_timeout_work, handle_osds_timeout);

4178
	err = -ENOMEM;
4179 4180 4181 4182
	osdc->osdmap = ceph_osdmap_alloc();
	if (!osdc->osdmap)
		goto out;

4183 4184
	osdc->req_mempool = mempool_create_slab_pool(10,
						     ceph_osd_request_cache);
S
Sage Weil 已提交
4185
	if (!osdc->req_mempool)
4186
		goto out_map;
S
Sage Weil 已提交
4187

4188
	err = ceph_msgpool_init(&osdc->msgpool_op, CEPH_MSG_OSD_OP,
4189
				PAGE_SIZE, 10, true, "osd_op");
S
Sage Weil 已提交
4190
	if (err < 0)
4191
		goto out_mempool;
4192
	err = ceph_msgpool_init(&osdc->msgpool_op_reply, CEPH_MSG_OSD_OPREPLY,
4193
				PAGE_SIZE, 10, true, "osd_op_reply");
S
Sage Weil 已提交
4194 4195
	if (err < 0)
		goto out_msgpool;
4196

4197
	err = -ENOMEM;
4198
	osdc->notify_wq = create_singlethread_workqueue("ceph-watch-notify");
4199
	if (!osdc->notify_wq)
4200 4201
		goto out_msgpool_reply;

4202 4203
	schedule_delayed_work(&osdc->timeout_work,
			      osdc->client->options->osd_keepalive_timeout);
4204 4205 4206
	schedule_delayed_work(&osdc->osds_timeout_work,
	    round_jiffies_relative(osdc->client->options->osd_idle_ttl));

S
Sage Weil 已提交
4207
	return 0;
4208

4209 4210
out_msgpool_reply:
	ceph_msgpool_destroy(&osdc->msgpool_op_reply);
S
Sage Weil 已提交
4211 4212
out_msgpool:
	ceph_msgpool_destroy(&osdc->msgpool_op);
4213 4214
out_mempool:
	mempool_destroy(osdc->req_mempool);
4215 4216
out_map:
	ceph_osdmap_destroy(osdc->osdmap);
4217 4218
out:
	return err;
S
Sage Weil 已提交
4219 4220 4221 4222
}

void ceph_osdc_stop(struct ceph_osd_client *osdc)
{
4223 4224
	flush_workqueue(osdc->notify_wq);
	destroy_workqueue(osdc->notify_wq);
S
Sage Weil 已提交
4225
	cancel_delayed_work_sync(&osdc->timeout_work);
4226
	cancel_delayed_work_sync(&osdc->osds_timeout_work);
4227

4228
	down_write(&osdc->lock);
4229 4230 4231
	while (!RB_EMPTY_ROOT(&osdc->osds)) {
		struct ceph_osd *osd = rb_entry(rb_first(&osdc->osds),
						struct ceph_osd, o_node);
4232
		close_osd(osd);
4233
	}
4234
	up_write(&osdc->lock);
4235
	WARN_ON(refcount_read(&osdc->homeless_osd.o_ref) != 1);
4236 4237 4238
	osd_cleanup(&osdc->homeless_osd);

	WARN_ON(!list_empty(&osdc->osd_lru));
4239
	WARN_ON(!RB_EMPTY_ROOT(&osdc->linger_requests));
I
Ilya Dryomov 已提交
4240 4241
	WARN_ON(!RB_EMPTY_ROOT(&osdc->map_checks));
	WARN_ON(!RB_EMPTY_ROOT(&osdc->linger_map_checks));
4242 4243
	WARN_ON(atomic_read(&osdc->num_requests));
	WARN_ON(atomic_read(&osdc->num_homeless));
4244

4245
	ceph_osdmap_destroy(osdc->osdmap);
S
Sage Weil 已提交
4246 4247
	mempool_destroy(osdc->req_mempool);
	ceph_msgpool_destroy(&osdc->msgpool_op);
S
Sage Weil 已提交
4248
	ceph_msgpool_destroy(&osdc->msgpool_op_reply);
S
Sage Weil 已提交
4249 4250 4251 4252 4253 4254 4255 4256 4257 4258
}

/*
 * Read some contiguous pages.  If we cross a stripe boundary, shorten
 * *plen.  Return number of bytes read, or error.
 */
int ceph_osdc_readpages(struct ceph_osd_client *osdc,
			struct ceph_vino vino, struct ceph_file_layout *layout,
			u64 off, u64 *plen,
			u32 truncate_seq, u64 truncate_size,
4259
			struct page **pages, int num_pages, int page_align)
S
Sage Weil 已提交
4260 4261 4262 4263 4264 4265
{
	struct ceph_osd_request *req;
	int rc = 0;

	dout("readpages on ino %llx.%llx on %llu~%llu\n", vino.ino,
	     vino.snap, off, *plen);
4266
	req = ceph_osdc_new_request(osdc, layout, vino, off, plen, 0, 1,
S
Sage Weil 已提交
4267
				    CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ,
4268
				    NULL, truncate_seq, truncate_size,
4269
				    false);
4270 4271
	if (IS_ERR(req))
		return PTR_ERR(req);
S
Sage Weil 已提交
4272 4273

	/* it may be a short read due to an object boundary */
4274
	osd_req_op_extent_osd_data_pages(req, 0,
4275
				pages, *plen, page_align, false, false);
S
Sage Weil 已提交
4276

4277
	dout("readpages  final extent is %llu~%llu (%llu bytes align %d)\n",
4278
	     off, *plen, *plen, page_align);
S
Sage Weil 已提交
4279 4280 4281 4282 4283 4284 4285 4286 4287

	rc = ceph_osdc_start_request(osdc, req, false);
	if (!rc)
		rc = ceph_osdc_wait_request(osdc, req);

	ceph_osdc_put_request(req);
	dout("readpages result %d\n", rc);
	return rc;
}
4288
EXPORT_SYMBOL(ceph_osdc_readpages);
S
Sage Weil 已提交
4289 4290 4291 4292 4293 4294 4295 4296 4297 4298

/*
 * do a synchronous write on N pages
 */
int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino,
			 struct ceph_file_layout *layout,
			 struct ceph_snap_context *snapc,
			 u64 off, u64 len,
			 u32 truncate_seq, u64 truncate_size,
			 struct timespec *mtime,
4299
			 struct page **pages, int num_pages)
S
Sage Weil 已提交
4300 4301 4302
{
	struct ceph_osd_request *req;
	int rc = 0;
4303
	int page_align = off & ~PAGE_MASK;
S
Sage Weil 已提交
4304

4305
	req = ceph_osdc_new_request(osdc, layout, vino, off, &len, 0, 1,
4306
				    CEPH_OSD_OP_WRITE, CEPH_OSD_FLAG_WRITE,
4307
				    snapc, truncate_seq, truncate_size,
4308
				    true);
4309 4310
	if (IS_ERR(req))
		return PTR_ERR(req);
S
Sage Weil 已提交
4311 4312

	/* it may be a short write due to an object boundary */
4313
	osd_req_op_extent_osd_data_pages(req, 0, pages, len, page_align,
4314 4315
				false, false);
	dout("writepages %llu~%llu (%llu bytes)\n", off, len, len);
S
Sage Weil 已提交
4316

4317
	req->r_mtime = *mtime;
4318
	rc = ceph_osdc_start_request(osdc, req, true);
S
Sage Weil 已提交
4319 4320 4321 4322 4323 4324 4325 4326 4327
	if (!rc)
		rc = ceph_osdc_wait_request(osdc, req);

	ceph_osdc_put_request(req);
	if (rc == 0)
		rc = len;
	dout("writepages result %d\n", rc);
	return rc;
}
4328
EXPORT_SYMBOL(ceph_osdc_writepages);
S
Sage Weil 已提交
4329

4330 4331
int ceph_osdc_setup(void)
{
4332 4333 4334
	size_t size = sizeof(struct ceph_osd_request) +
	    CEPH_OSD_SLAB_OPS * sizeof(struct ceph_osd_req_op);

4335
	BUG_ON(ceph_osd_request_cache);
4336 4337
	ceph_osd_request_cache = kmem_cache_create("ceph_osd_request", size,
						   0, 0, NULL);
4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350

	return ceph_osd_request_cache ? 0 : -ENOMEM;
}
EXPORT_SYMBOL(ceph_osdc_setup);

void ceph_osdc_cleanup(void)
{
	BUG_ON(!ceph_osd_request_cache);
	kmem_cache_destroy(ceph_osd_request_cache);
	ceph_osd_request_cache = NULL;
}
EXPORT_SYMBOL(ceph_osdc_cleanup);

S
Sage Weil 已提交
4351 4352 4353 4354 4355 4356
/*
 * handle incoming message
 */
static void dispatch(struct ceph_connection *con, struct ceph_msg *msg)
{
	struct ceph_osd *osd = con->private;
4357
	struct ceph_osd_client *osdc = osd->o_osdc;
S
Sage Weil 已提交
4358 4359 4360 4361 4362 4363 4364
	int type = le16_to_cpu(msg->hdr.type);

	switch (type) {
	case CEPH_MSG_OSD_MAP:
		ceph_osdc_handle_map(osdc, msg);
		break;
	case CEPH_MSG_OSD_OPREPLY:
4365
		handle_reply(osd, msg);
S
Sage Weil 已提交
4366
		break;
4367 4368 4369
	case CEPH_MSG_WATCH_NOTIFY:
		handle_watch_notify(osdc, msg);
		break;
S
Sage Weil 已提交
4370 4371 4372 4373 4374

	default:
		pr_err("received unknown message type %d %s\n", type,
		       ceph_msg_type_name(type));
	}
4375

S
Sage Weil 已提交
4376 4377 4378
	ceph_msg_put(msg);
}

4379
/*
4380 4381 4382
 * Lookup and return message for incoming reply.  Don't try to do
 * anything about a larger than preallocated data portion of the
 * message at the moment - for now, just skip the message.
4383 4384
 */
static struct ceph_msg *get_reply(struct ceph_connection *con,
4385 4386
				  struct ceph_msg_header *hdr,
				  int *skip)
S
Sage Weil 已提交
4387 4388 4389
{
	struct ceph_osd *osd = con->private;
	struct ceph_osd_client *osdc = osd->o_osdc;
4390
	struct ceph_msg *m = NULL;
4391
	struct ceph_osd_request *req;
4392
	int front_len = le32_to_cpu(hdr->front_len);
4393
	int data_len = le32_to_cpu(hdr->data_len);
4394
	u64 tid = le64_to_cpu(hdr->tid);
S
Sage Weil 已提交
4395

4396 4397 4398 4399 4400 4401 4402 4403 4404 4405
	down_read(&osdc->lock);
	if (!osd_registered(osd)) {
		dout("%s osd%d unknown, skipping\n", __func__, osd->o_osd);
		*skip = 1;
		goto out_unlock_osdc;
	}
	WARN_ON(osd->o_osd != le64_to_cpu(hdr->src.num));

	mutex_lock(&osd->lock);
	req = lookup_request(&osd->o_requests, tid);
4406
	if (!req) {
4407 4408
		dout("%s osd%d tid %llu unknown, skipping\n", __func__,
		     osd->o_osd, tid);
4409
		*skip = 1;
4410
		goto out_unlock_session;
4411
	}
S
Sage Weil 已提交
4412

4413
	ceph_msg_revoke_incoming(req->r_reply);
4414

4415
	if (front_len > req->r_reply->front_alloc_len) {
4416 4417 4418
		pr_warn("%s osd%d tid %llu front %d > preallocated %d\n",
			__func__, osd->o_osd, req->r_tid, front_len,
			req->r_reply->front_alloc_len);
4419 4420
		m = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, front_len, GFP_NOFS,
				 false);
4421
		if (!m)
4422
			goto out_unlock_session;
S
Sage Weil 已提交
4423 4424 4425
		ceph_msg_put(req->r_reply);
		req->r_reply = m;
	}
4426

4427 4428 4429 4430 4431 4432
	if (data_len > req->r_reply->data_length) {
		pr_warn("%s osd%d tid %llu data %d > preallocated %zu, skipping\n",
			__func__, osd->o_osd, req->r_tid, data_len,
			req->r_reply->data_length);
		m = NULL;
		*skip = 1;
4433
		goto out_unlock_session;
4434
	}
4435 4436

	m = ceph_msg_get(req->r_reply);
S
Sage Weil 已提交
4437
	dout("get_reply tid %lld %p\n", tid, m);
4438

4439 4440 4441 4442
out_unlock_session:
	mutex_unlock(&osd->lock);
out_unlock_osdc:
	up_read(&osdc->lock);
4443
	return m;
4444 4445
}

4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465
/*
 * TODO: switch to a msg-owned pagelist
 */
static struct ceph_msg *alloc_msg_with_page_vector(struct ceph_msg_header *hdr)
{
	struct ceph_msg *m;
	int type = le16_to_cpu(hdr->type);
	u32 front_len = le32_to_cpu(hdr->front_len);
	u32 data_len = le32_to_cpu(hdr->data_len);

	m = ceph_msg_new(type, front_len, GFP_NOIO, false);
	if (!m)
		return NULL;

	if (data_len) {
		struct page **pages;
		struct ceph_osd_data osd_data;

		pages = ceph_alloc_page_vector(calc_pages_for(0, data_len),
					       GFP_NOIO);
4466
		if (IS_ERR(pages)) {
4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478
			ceph_msg_put(m);
			return NULL;
		}

		ceph_osd_data_pages_init(&osd_data, pages, data_len, 0, false,
					 false);
		ceph_osdc_msg_data_add(m, &osd_data);
	}

	return m;
}

4479 4480 4481 4482 4483 4484 4485
static struct ceph_msg *alloc_msg(struct ceph_connection *con,
				  struct ceph_msg_header *hdr,
				  int *skip)
{
	struct ceph_osd *osd = con->private;
	int type = le16_to_cpu(hdr->type);

A
Alex Elder 已提交
4486
	*skip = 0;
4487 4488
	switch (type) {
	case CEPH_MSG_OSD_MAP:
4489
	case CEPH_MSG_WATCH_NOTIFY:
4490
		return alloc_msg_with_page_vector(hdr);
4491 4492 4493
	case CEPH_MSG_OSD_OPREPLY:
		return get_reply(con, hdr, skip);
	default:
4494 4495
		pr_warn("%s osd%d unknown msg type %d, skipping\n", __func__,
			osd->o_osd, type);
4496 4497 4498
		*skip = 1;
		return NULL;
	}
S
Sage Weil 已提交
4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517
}

/*
 * Wrappers to refcount containing ceph_osd struct
 */
static struct ceph_connection *get_osd_con(struct ceph_connection *con)
{
	struct ceph_osd *osd = con->private;
	if (get_osd(osd))
		return con;
	return NULL;
}

static void put_osd_con(struct ceph_connection *con)
{
	struct ceph_osd *osd = con->private;
	put_osd(osd);
}

4518 4519 4520
/*
 * authentication
 */
4521 4522 4523 4524 4525
/*
 * Note: returned pointer is the address of a structure that's
 * managed separately.  Caller must *not* attempt to free it.
 */
static struct ceph_auth_handshake *get_authorizer(struct ceph_connection *con,
4526
					int *proto, int force_new)
4527 4528 4529 4530
{
	struct ceph_osd *o = con->private;
	struct ceph_osd_client *osdc = o->o_osdc;
	struct ceph_auth_client *ac = osdc->client->monc.auth;
4531
	struct ceph_auth_handshake *auth = &o->o_auth;
4532

4533
	if (force_new && auth->authorizer) {
4534
		ceph_auth_destroy_authorizer(auth->authorizer);
4535 4536
		auth->authorizer = NULL;
	}
4537 4538 4539
	if (!auth->authorizer) {
		int ret = ceph_auth_create_authorizer(ac, CEPH_ENTITY_TYPE_OSD,
						      auth);
4540
		if (ret)
4541
			return ERR_PTR(ret);
4542 4543
	} else {
		int ret = ceph_auth_update_authorizer(ac, CEPH_ENTITY_TYPE_OSD,
4544 4545 4546
						     auth);
		if (ret)
			return ERR_PTR(ret);
4547 4548
	}
	*proto = ac->protocol;
4549

4550
	return auth;
4551 4552 4553
}


4554
static int verify_authorizer_reply(struct ceph_connection *con)
4555 4556 4557 4558 4559
{
	struct ceph_osd *o = con->private;
	struct ceph_osd_client *osdc = o->o_osdc;
	struct ceph_auth_client *ac = osdc->client->monc.auth;

4560
	return ceph_auth_verify_authorizer_reply(ac, o->o_auth.authorizer);
4561 4562
}

4563 4564 4565 4566 4567 4568
static int invalidate_authorizer(struct ceph_connection *con)
{
	struct ceph_osd *o = con->private;
	struct ceph_osd_client *osdc = o->o_osdc;
	struct ceph_auth_client *ac = osdc->client->monc.auth;

4569
	ceph_auth_invalidate_authorizer(ac, CEPH_ENTITY_TYPE_OSD);
4570 4571
	return ceph_monc_validate_auth(&osdc->client->monc);
}
4572

4573
static int osd_sign_message(struct ceph_msg *msg)
Y
Yan, Zheng 已提交
4574
{
4575
	struct ceph_osd *o = msg->con->private;
Y
Yan, Zheng 已提交
4576
	struct ceph_auth_handshake *auth = &o->o_auth;
4577

Y
Yan, Zheng 已提交
4578 4579 4580
	return ceph_auth_sign_message(auth, msg);
}

4581
static int osd_check_message_signature(struct ceph_msg *msg)
Y
Yan, Zheng 已提交
4582
{
4583
	struct ceph_osd *o = msg->con->private;
Y
Yan, Zheng 已提交
4584
	struct ceph_auth_handshake *auth = &o->o_auth;
4585

Y
Yan, Zheng 已提交
4586 4587 4588
	return ceph_auth_check_message_signature(auth, msg);
}

4589
static const struct ceph_connection_operations osd_con_ops = {
S
Sage Weil 已提交
4590 4591 4592
	.get = get_osd_con,
	.put = put_osd_con,
	.dispatch = dispatch,
4593 4594
	.get_authorizer = get_authorizer,
	.verify_authorizer_reply = verify_authorizer_reply,
4595
	.invalidate_authorizer = invalidate_authorizer,
S
Sage Weil 已提交
4596
	.alloc_msg = alloc_msg,
4597 4598
	.sign_message = osd_sign_message,
	.check_message_signature = osd_check_message_signature,
4599
	.fault = osd_fault,
S
Sage Weil 已提交
4600
};