osd_client.c 140.8 KB
Newer Older
1
// SPDX-License-Identifier: GPL-2.0
2

3
#include <linux/ceph/ceph_debug.h>
S
Sage Weil 已提交
4

5
#include <linux/module.h>
S
Sage Weil 已提交
6 7 8 9 10 11
#include <linux/err.h>
#include <linux/highmem.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
12 13 14
#ifdef CONFIG_BLOCK
#include <linux/bio.h>
#endif
S
Sage Weil 已提交
15

16
#include <linux/ceph/ceph_features.h>
17 18 19 20 21 22
#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>
23
#include <linux/ceph/striper.h>
S
Sage Weil 已提交
24

S
Sage Weil 已提交
25
#define OSD_OPREPLY_FRONT_LEN	512
26

27 28
static struct kmem_cache	*ceph_osd_request_cache;

29
static const struct ceph_connection_operations osd_con_ops;
S
Sage Weil 已提交
30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48

/*
 * 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.
 */

49 50
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);
51 52 53 54
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);
55
static void clear_backoffs(struct ceph_osd *osd);
56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84

#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));
}
85 86 87 88
static inline void verify_lreq_locked(struct ceph_osd_linger_request *lreq)
{
	WARN_ON(!mutex_is_locked(&lreq->lock));
}
89 90 91 92
#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) { }
93
static inline void verify_lreq_locked(struct ceph_osd_linger_request *lreq) { }
94 95
#endif

S
Sage Weil 已提交
96 97 98 99 100 101 102
/*
 * 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.
 */
103
static int calc_layout(struct ceph_file_layout *layout, u64 off, u64 *plen,
104
			u64 *objnum, u64 *objoff, u64 *objlen)
S
Sage Weil 已提交
105
{
106
	u64 orig_len = *plen;
107
	u32 xlen;
S
Sage Weil 已提交
108

109
	/* object extent? */
110 111 112
	ceph_calc_file_object_mapping(layout, off, orig_len, objnum,
					  objoff, &xlen);
	*objlen = xlen;
113 114
	if (*objlen < orig_len) {
		*plen = *objlen;
115 116 117 118
		dout(" skipping last %llu, final file extent %llu~%llu\n",
		     orig_len - *plen, off, *plen);
	}

119
	dout("calc_layout objnum=%llx %llu~%llu\n", *objnum, *objoff, *objlen);
120
	return 0;
S
Sage Weil 已提交
121 122
}

A
Alex Elder 已提交
123 124 125 126 127 128
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;
}

129
static void ceph_osd_data_pages_init(struct ceph_osd_data *osd_data,
130 131 132 133 134 135 136 137 138 139 140
			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;
}

141
static void ceph_osd_data_pagelist_init(struct ceph_osd_data *osd_data,
142 143 144 145 146 147 148
			struct ceph_pagelist *pagelist)
{
	osd_data->type = CEPH_OSD_DATA_TYPE_PAGELIST;
	osd_data->pagelist = pagelist;
}

#ifdef CONFIG_BLOCK
149
static void ceph_osd_data_bio_init(struct ceph_osd_data *osd_data,
150 151
				   struct ceph_bio_iter *bio_pos,
				   u32 bio_length)
152 153
{
	osd_data->type = CEPH_OSD_DATA_TYPE_BIO;
154
	osd_data->bio_pos = *bio_pos;
155 156 157 158
	osd_data->bio_length = bio_length;
}
#endif /* CONFIG_BLOCK */

159
static void ceph_osd_data_bvecs_init(struct ceph_osd_data *osd_data,
160 161
				     struct ceph_bvec_iter *bvec_pos,
				     u32 num_bvecs)
162 163 164
{
	osd_data->type = CEPH_OSD_DATA_TYPE_BVECS;
	osd_data->bvec_pos = *bvec_pos;
165
	osd_data->num_bvecs = num_bvecs;
166 167
}

168 169 170 171 172 173 174
#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;					\
})
175

A
Alex Elder 已提交
176 177 178 179 180 181 182 183
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;
}

184 185
struct ceph_osd_data *
osd_req_op_extent_osd_data(struct ceph_osd_request *osd_req,
186
			unsigned int which)
187
{
188
	return osd_req_op_data(osd_req, which, extent, osd_data);
189 190 191
}
EXPORT_SYMBOL(osd_req_op_extent_osd_data);

A
Alex Elder 已提交
192 193 194 195 196 197 198 199 200 201 202 203 204
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);

205
void osd_req_op_extent_osd_data_pages(struct ceph_osd_request *osd_req,
206 207
			unsigned int which, struct page **pages,
			u64 length, u32 alignment,
208 209 210 211
			bool pages_from_pool, bool own_pages)
{
	struct ceph_osd_data *osd_data;

212
	osd_data = osd_req_op_data(osd_req, which, extent, osd_data);
213 214 215 216 217 218
	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,
219
			unsigned int which, struct ceph_pagelist *pagelist)
220 221 222
{
	struct ceph_osd_data *osd_data;

223
	osd_data = osd_req_op_data(osd_req, which, extent, osd_data);
224 225 226 227 228 229
	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,
230 231 232
				    unsigned int which,
				    struct ceph_bio_iter *bio_pos,
				    u32 bio_length)
233 234
{
	struct ceph_osd_data *osd_data;
235 236

	osd_data = osd_req_op_data(osd_req, which, extent, osd_data);
237
	ceph_osd_data_bio_init(osd_data, bio_pos, bio_length);
238 239 240 241
}
EXPORT_SYMBOL(osd_req_op_extent_osd_data_bio);
#endif /* CONFIG_BLOCK */

242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257
void osd_req_op_extent_osd_data_bvecs(struct ceph_osd_request *osd_req,
				      unsigned int which,
				      struct bio_vec *bvecs, u32 num_bvecs,
				      u32 bytes)
{
	struct ceph_osd_data *osd_data;
	struct ceph_bvec_iter it = {
		.bvecs = bvecs,
		.iter = { .bi_size = bytes },
	};

	osd_data = osd_req_op_data(osd_req, which, extent, osd_data);
	ceph_osd_data_bvecs_init(osd_data, &it, num_bvecs);
}
EXPORT_SYMBOL(osd_req_op_extent_osd_data_bvecs);

258 259 260 261 262 263 264
void osd_req_op_extent_osd_data_bvec_pos(struct ceph_osd_request *osd_req,
					 unsigned int which,
					 struct ceph_bvec_iter *bvec_pos)
{
	struct ceph_osd_data *osd_data;

	osd_data = osd_req_op_data(osd_req, which, extent, osd_data);
265
	ceph_osd_data_bvecs_init(osd_data, bvec_pos, 0);
266 267 268
}
EXPORT_SYMBOL(osd_req_op_extent_osd_data_bvec_pos);

269 270 271 272 273 274
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;

275
	osd_data = osd_req_op_data(osd_req, which, cls, request_info);
276 277 278
	ceph_osd_data_pagelist_init(osd_data, pagelist);
}

279 280 281 282 283 284
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;

285
	osd_data = osd_req_op_data(osd_req, which, cls, request_data);
286
	ceph_osd_data_pagelist_init(osd_data, pagelist);
287 288
	osd_req->r_ops[which].cls.indata_len += pagelist->length;
	osd_req->r_ops[which].indata_len += pagelist->length;
289 290 291
}
EXPORT_SYMBOL(osd_req_op_cls_request_data_pagelist);

292 293 294 295 296 297 298 299 300
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);
301 302
	osd_req->r_ops[which].cls.indata_len += length;
	osd_req->r_ops[which].indata_len += length;
303 304 305
}
EXPORT_SYMBOL(osd_req_op_cls_request_data_pages);

306 307
void osd_req_op_cls_request_data_bvecs(struct ceph_osd_request *osd_req,
				       unsigned int which,
308 309
				       struct bio_vec *bvecs, u32 num_bvecs,
				       u32 bytes)
310 311 312 313 314 315 316 317
{
	struct ceph_osd_data *osd_data;
	struct ceph_bvec_iter it = {
		.bvecs = bvecs,
		.iter = { .bi_size = bytes },
	};

	osd_data = osd_req_op_data(osd_req, which, cls, request_data);
318
	ceph_osd_data_bvecs_init(osd_data, &it, num_bvecs);
319 320 321 322 323
	osd_req->r_ops[which].cls.indata_len += bytes;
	osd_req->r_ops[which].indata_len += bytes;
}
EXPORT_SYMBOL(osd_req_op_cls_request_data_bvecs);

324 325 326 327 328 329
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;

330
	osd_data = osd_req_op_data(osd_req, which, cls, response_data);
331 332 333 334 335
	ceph_osd_data_pages_init(osd_data, pages, length, alignment,
				pages_from_pool, own_pages);
}
EXPORT_SYMBOL(osd_req_op_cls_response_data_pages);

336 337 338 339 340 341 342 343 344 345 346 347 348
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 */
349 350
	case CEPH_OSD_DATA_TYPE_BVECS:
		return osd_data->bvec_pos.iter.bi_size;
351 352 353 354 355 356
	default:
		WARN(true, "unrecognized data type %d\n", (int)osd_data->type);
		return 0;
	}
}

A
Alex Elder 已提交
357 358
static void ceph_osd_data_release(struct ceph_osd_data *osd_data)
{
359
	if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGES && osd_data->own_pages) {
A
Alex Elder 已提交
360 361 362 363 364 365
		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);
	}
366 367 368 369 370 371 372 373 374 375 376 377 378 379
	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:
380
	case CEPH_OSD_OP_WRITEFULL:
381 382 383 384
		ceph_osd_data_release(&op->extent.osd_data);
		break;
	case CEPH_OSD_OP_CALL:
		ceph_osd_data_release(&op->cls.request_info);
385
		ceph_osd_data_release(&op->cls.request_data);
386 387
		ceph_osd_data_release(&op->cls.response_data);
		break;
388 389 390 391
	case CEPH_OSD_OP_SETXATTR:
	case CEPH_OSD_OP_CMPXATTR:
		ceph_osd_data_release(&op->xattr.osd_data);
		break;
392 393 394
	case CEPH_OSD_OP_STAT:
		ceph_osd_data_release(&op->raw_data_in);
		break;
395 396 397
	case CEPH_OSD_OP_NOTIFY_ACK:
		ceph_osd_data_release(&op->notify_ack.request_data);
		break;
398 399 400 401
	case CEPH_OSD_OP_NOTIFY:
		ceph_osd_data_release(&op->notify.request_data);
		ceph_osd_data_release(&op->notify.response_data);
		break;
402 403 404
	case CEPH_OSD_OP_LIST_WATCHERS:
		ceph_osd_data_release(&op->list_watchers.response_data);
		break;
405 406 407
	default:
		break;
	}
A
Alex Elder 已提交
408 409
}

410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427
/*
 * 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;
}

428 429 430 431 432 433 434 435 436
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 */
437
	dest->spgid = src->spgid; /* struct */
438 439 440 441 442 443 444 445 446 447 448
	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;

449
	dest->epoch = src->epoch;
450 451
	dest->last_force_resend = src->last_force_resend;

452 453 454
	dest->osd = src->osd;
}

455 456 457
static void target_destroy(struct ceph_osd_request_target *t)
{
	ceph_oid_destroy(&t->base_oid);
458
	ceph_oloc_destroy(&t->base_oloc);
459
	ceph_oid_destroy(&t->target_oid);
460
	ceph_oloc_destroy(&t->target_oloc);
461 462
}

S
Sage Weil 已提交
463 464 465
/*
 * requests
 */
466 467 468
static void request_release_checks(struct ceph_osd_request *req)
{
	WARN_ON(!RB_EMPTY_NODE(&req->r_node));
I
Ilya Dryomov 已提交
469
	WARN_ON(!RB_EMPTY_NODE(&req->r_mc_node));
470 471 472 473
	WARN_ON(!list_empty(&req->r_unsafe_item));
	WARN_ON(req->r_osd);
}

474
static void ceph_osdc_release_request(struct kref *kref)
S
Sage Weil 已提交
475
{
476 477
	struct ceph_osd_request *req = container_of(kref,
					    struct ceph_osd_request, r_kref);
478
	unsigned int which;
S
Sage Weil 已提交
479

480 481
	dout("%s %p (r_request %p r_reply %p)\n", __func__, req,
	     req->r_request, req->r_reply);
482
	request_release_checks(req);
483

S
Sage Weil 已提交
484 485
	if (req->r_request)
		ceph_msg_put(req->r_request);
486
	if (req->r_reply)
487
		ceph_msg_put(req->r_reply);
488

489 490
	for (which = 0; which < req->r_num_ops; which++)
		osd_req_op_data_release(req, which);
491

492
	target_destroy(&req->r_t);
S
Sage Weil 已提交
493
	ceph_put_snap_context(req->r_snapc);
494

S
Sage Weil 已提交
495 496
	if (req->r_mempool)
		mempool_free(req, req->r_osdc->req_mempool);
497
	else if (req->r_num_ops <= CEPH_OSD_SLAB_OPS)
498
		kmem_cache_free(ceph_osd_request_cache, req);
499 500
	else
		kfree(req);
S
Sage Weil 已提交
501
}
502 503 504 505

void ceph_osdc_get_request(struct ceph_osd_request *req)
{
	dout("%s %p (was %d)\n", __func__, req,
506
	     kref_read(&req->r_kref));
507 508 509 510 511 512
	kref_get(&req->r_kref);
}
EXPORT_SYMBOL(ceph_osdc_get_request);

void ceph_osdc_put_request(struct ceph_osd_request *req)
{
513 514
	if (req) {
		dout("%s %p (was %d)\n", __func__, req,
515
		     kref_read(&req->r_kref));
516 517
		kref_put(&req->r_kref, ceph_osdc_release_request);
	}
518 519
}
EXPORT_SYMBOL(ceph_osdc_put_request);
520

521 522 523 524 525 526 527 528
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
529
	RB_CLEAR_NODE(&req->r_mc_node);
530 531 532 533 534
	INIT_LIST_HEAD(&req->r_unsafe_item);

	target_init(&req->r_t);
}

535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553
/*
 * 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);
554
	WARN_ON(kref_read(&req->r_kref) != 1);
555 556
	request_release_checks(req);

557 558
	WARN_ON(kref_read(&request_msg->kref) != 1);
	WARN_ON(kref_read(&reply_msg->kref) != 1);
559 560 561 562 563 564 565 566 567 568 569 570 571
	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;
}

572
struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
S
Sage Weil 已提交
573
					       struct ceph_snap_context *snapc,
574
					       unsigned int num_ops,
575
					       bool use_mempool,
576
					       gfp_t gfp_flags)
S
Sage Weil 已提交
577 578
{
	struct ceph_osd_request *req;
579

S
Sage Weil 已提交
580
	if (use_mempool) {
581
		BUG_ON(num_ops > CEPH_OSD_SLAB_OPS);
582
		req = mempool_alloc(osdc->req_mempool, gfp_flags);
583 584
	} else if (num_ops <= CEPH_OSD_SLAB_OPS) {
		req = kmem_cache_alloc(ceph_osd_request_cache, gfp_flags);
S
Sage Weil 已提交
585
	} else {
586 587 588
		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
589
	}
590
	if (unlikely(!req))
591
		return NULL;
S
Sage Weil 已提交
592

593
	request_init(req);
S
Sage Weil 已提交
594 595
	req->r_osdc = osdc;
	req->r_mempool = use_mempool;
596
	req->r_num_ops = num_ops;
597 598
	req->r_snapid = CEPH_NOSNAP;
	req->r_snapc = ceph_get_snap_context(snapc);
599

600 601 602 603
	dout("%s req %p\n", __func__, req);
	return req;
}
EXPORT_SYMBOL(ceph_osdc_alloc_request);
604

605
static int ceph_oloc_encoding_size(const struct ceph_object_locator *oloc)
606 607 608 609
{
	return 8 + 4 + 4 + 4 + (oloc->pool_ns ? oloc->pool_ns->len : 0);
}

610 611 612 613 614
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
615

616
	WARN_ON(ceph_oid_empty(&req->r_base_oid));
617
	WARN_ON(ceph_oloc_empty(&req->r_base_oloc));
618

619
	/* create request message */
620 621 622 623 624 625 626
	msg_size = CEPH_ENCODING_START_BLK_LEN +
			CEPH_PGID_ENCODING_LEN + 1; /* spgid */
	msg_size += 4 + 4 + 4; /* hash, osdmap_epoch, flags */
	msg_size += CEPH_ENCODING_START_BLK_LEN +
			sizeof(struct ceph_osd_reqid); /* reqid */
	msg_size += sizeof(struct ceph_blkin_trace_info); /* trace */
	msg_size += 4 + sizeof(struct ceph_timespec); /* client_inc, mtime */
627 628
	msg_size += CEPH_ENCODING_START_BLK_LEN +
			ceph_oloc_encoding_size(&req->r_base_oloc); /* oloc */
629 630
	msg_size += 4 + req->r_base_oid.name_len; /* oid */
	msg_size += 2 + req->r_num_ops * sizeof(struct ceph_osd_op);
631 632
	msg_size += 8; /* snapid */
	msg_size += 8; /* snap_seq */
633
	msg_size += 4 + 8 * (req->r_snapc ? req->r_snapc->num_snaps : 0);
634
	msg_size += 4 + 8; /* retry_attempt, features */
635

636
	if (req->r_mempool)
637
		msg = ceph_msgpool_get(&osdc->msgpool_op, 0);
S
Sage Weil 已提交
638
	else
639 640 641
		msg = ceph_msg_new(CEPH_MSG_OSD_OP, msg_size, gfp, true);
	if (!msg)
		return -ENOMEM;
642

S
Sage Weil 已提交
643
	memset(msg->front.iov_base, 0, msg->front.iov_len);
644 645
	req->r_request = msg;

646 647
	/* create reply message */
	msg_size = OSD_OPREPLY_FRONT_LEN;
648 649
	msg_size += req->r_base_oid.name_len;
	msg_size += req->r_num_ops * sizeof(struct ceph_osd_op);
650 651 652 653 654 655 656 657 658 659 660

	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;
661
}
662
EXPORT_SYMBOL(ceph_osdc_alloc_messages);
663

664
static bool osd_req_opcode_valid(u16 opcode)
665
{
666
	switch (opcode) {
667 668 669
#define GENERATE_CASE(op, opcode, str)	case CEPH_OSD_OP_##op: return true;
__CEPH_FORALL_OSD_OPS(GENERATE_CASE)
#undef GENERATE_CASE
670 671 672 673 674
	default:
		return false;
	}
}

675 676 677 678 679
/*
 * 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.
 */
680
static struct ceph_osd_req_op *
A
Alex Elder 已提交
681
_osd_req_op_init(struct ceph_osd_request *osd_req, unsigned int which,
682
		 u16 opcode, u32 flags)
683
{
684 685 686
	struct ceph_osd_req_op *op;

	BUG_ON(which >= osd_req->r_num_ops);
687 688
	BUG_ON(!osd_req_opcode_valid(opcode));

689
	op = &osd_req->r_ops[which];
690 691
	memset(op, 0, sizeof (*op));
	op->op = opcode;
692
	op->flags = flags;
693 694

	return op;
695 696
}

A
Alex Elder 已提交
697
void osd_req_op_init(struct ceph_osd_request *osd_req,
698
		     unsigned int which, u16 opcode, u32 flags)
A
Alex Elder 已提交
699
{
700
	(void)_osd_req_op_init(osd_req, which, opcode, flags);
A
Alex Elder 已提交
701 702 703
}
EXPORT_SYMBOL(osd_req_op_init);

704 705
void osd_req_op_extent_init(struct ceph_osd_request *osd_req,
				unsigned int which, u16 opcode,
706 707 708
				u64 offset, u64 length,
				u64 truncate_size, u32 truncate_seq)
{
709 710
	struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
						      opcode, 0);
711 712
	size_t payload_len = 0;

L
Li Wang 已提交
713
	BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE &&
714 715
	       opcode != CEPH_OSD_OP_WRITEFULL && opcode != CEPH_OSD_OP_ZERO &&
	       opcode != CEPH_OSD_OP_TRUNCATE);
716 717 718 719 720

	op->extent.offset = offset;
	op->extent.length = length;
	op->extent.truncate_size = truncate_size;
	op->extent.truncate_seq = truncate_seq;
721
	if (opcode == CEPH_OSD_OP_WRITE || opcode == CEPH_OSD_OP_WRITEFULL)
722 723
		payload_len += length;

724
	op->indata_len = payload_len;
725 726 727
}
EXPORT_SYMBOL(osd_req_op_extent_init);

728 729
void osd_req_op_extent_update(struct ceph_osd_request *osd_req,
				unsigned int which, u64 length)
730
{
731 732 733 734 735 736
	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;
737 738 739 740 741 742

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

	op->extent.length = length;
743 744
	if (op->op == CEPH_OSD_OP_WRITE || op->op == CEPH_OSD_OP_WRITEFULL)
		op->indata_len -= previous - length;
745 746 747
}
EXPORT_SYMBOL(osd_req_op_extent_update);

748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769
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);

770
int osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which,
771
			u16 opcode, const char *class, const char *method)
772
{
773 774
	struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
						      opcode, 0);
775
	struct ceph_pagelist *pagelist;
776 777 778 779 780
	size_t payload_len = 0;
	size_t size;

	BUG_ON(opcode != CEPH_OSD_OP_CALL);

781
	pagelist = kmalloc(sizeof (*pagelist), GFP_NOFS);
782 783 784
	if (!pagelist)
		return -ENOMEM;

785 786
	ceph_pagelist_init(pagelist);

787 788 789 790
	op->cls.class_name = class;
	size = strlen(class);
	BUG_ON(size > (size_t) U8_MAX);
	op->cls.class_len = size;
791
	ceph_pagelist_append(pagelist, class, size);
792 793 794 795 796 797
	payload_len += size;

	op->cls.method_name = method;
	size = strlen(method);
	BUG_ON(size > (size_t) U8_MAX);
	op->cls.method_len = size;
798
	ceph_pagelist_append(pagelist, method, size);
799 800
	payload_len += size;

801
	osd_req_op_cls_request_info_pagelist(osd_req, which, pagelist);
802

803
	op->indata_len = payload_len;
804
	return 0;
805 806
}
EXPORT_SYMBOL(osd_req_op_cls_init);
807

808 809 810 811
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)
{
812 813
	struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
						      opcode, 0);
814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836
	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);
837
	op->indata_len = payload_len;
838 839 840 841
	return 0;
}
EXPORT_SYMBOL(osd_req_op_xattr_init);

842 843 844 845 846
/*
 * @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)
847
{
848
	struct ceph_osd_req_op *op;
849

850
	op = _osd_req_op_init(req, which, CEPH_OSD_OP_WATCH, 0);
851
	op->watch.cookie = cookie;
852 853
	op->watch.op = watch_opcode;
	op->watch.gen = 0;
854 855
}

856 857 858 859 860 861
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,
862 863
						      CEPH_OSD_OP_SETALLOCHINT,
						      0);
864 865 866 867 868 869 870 871 872 873 874 875 876

	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);

877
static void ceph_osdc_msg_data_add(struct ceph_msg *msg,
878 879 880 881 882 883 884
				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)
885
			ceph_msg_data_add_pages(msg, osd_data->pages,
886 887 888
					length, osd_data->alignment);
	} else if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGELIST) {
		BUG_ON(!length);
889
		ceph_msg_data_add_pagelist(msg, osd_data->pagelist);
890 891
#ifdef CONFIG_BLOCK
	} else if (osd_data->type == CEPH_OSD_DATA_TYPE_BIO) {
892
		ceph_msg_data_add_bio(msg, &osd_data->bio_pos, length);
893
#endif
894 895
	} else if (osd_data->type == CEPH_OSD_DATA_TYPE_BVECS) {
		ceph_msg_data_add_bvecs(msg, &osd_data->bvec_pos);
896 897 898 899 900
	} else {
		BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_NONE);
	}
}

901 902
static u32 osd_req_encode_op(struct ceph_osd_op *dst,
			     const struct ceph_osd_req_op *src)
903 904 905 906 907 908 909 910 911 912 913 914
{
	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:
915
	case CEPH_OSD_OP_WRITEFULL:
L
Li Wang 已提交
916 917
	case CEPH_OSD_OP_ZERO:
	case CEPH_OSD_OP_TRUNCATE:
918 919 920 921 922 923 924 925 926 927
		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;
928
		dst->cls.indata_len = cpu_to_le32(src->cls.indata_len);
929 930 931
		break;
	case CEPH_OSD_OP_WATCH:
		dst->watch.cookie = cpu_to_le64(src->watch.cookie);
932 933 934 935 936
		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:
937
		break;
938 939 940
	case CEPH_OSD_OP_NOTIFY:
		dst->notify.cookie = cpu_to_le64(src->notify.cookie);
		break;
941 942
	case CEPH_OSD_OP_LIST_WATCHERS:
		break;
943 944 945 946 947 948
	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;
949 950 951 952 953 954 955
	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;
956 957 958
	case CEPH_OSD_OP_CREATE:
	case CEPH_OSD_OP_DELETE:
		break;
959
	default:
960
		pr_err("unsupported osd opcode %s\n",
961
			ceph_osd_op_name(src->op));
962
		WARN_ON(1);
963 964

		return 0;
965
	}
966

967
	dst->op = cpu_to_le16(src->op);
968
	dst->flags = cpu_to_le32(src->flags);
969
	dst->payload_len = cpu_to_le32(src->indata_len);
970

971
	return src->indata_len;
972 973
}

974 975 976 977 978 979 980 981 982 983 984
/*
 * 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.)
 */
struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
					       struct ceph_file_layout *layout,
					       struct ceph_vino vino,
985 986
					       u64 off, u64 *plen,
					       unsigned int which, int num_ops,
987 988 989 990
					       int opcode, int flags,
					       struct ceph_snap_context *snapc,
					       u32 truncate_seq,
					       u64 truncate_size,
991
					       bool use_mempool)
992
{
993
	struct ceph_osd_request *req;
994 995 996
	u64 objnum = 0;
	u64 objoff = 0;
	u64 objlen = 0;
997
	int r;
998

L
Li Wang 已提交
999
	BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE &&
1000 1001
	       opcode != CEPH_OSD_OP_ZERO && opcode != CEPH_OSD_OP_TRUNCATE &&
	       opcode != CEPH_OSD_OP_CREATE && opcode != CEPH_OSD_OP_DELETE);
1002

1003
	req = ceph_osdc_alloc_request(osdc, snapc, num_ops, use_mempool,
A
Alex Elder 已提交
1004
					GFP_NOFS);
1005 1006 1007 1008
	if (!req) {
		r = -ENOMEM;
		goto fail;
	}
1009

1010
	/* calculate max write size */
1011
	r = calc_layout(layout, off, plen, &objnum, &objoff, &objlen);
1012 1013
	if (r)
		goto fail;
1014

1015
	if (opcode == CEPH_OSD_OP_CREATE || opcode == CEPH_OSD_OP_DELETE) {
1016
		osd_req_op_init(req, which, opcode, 0);
1017
	} else {
1018
		u32 object_size = layout->object_size;
1019 1020 1021 1022 1023 1024 1025 1026 1027
		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;
			}
1028
		}
1029
		osd_req_op_extent_init(req, which, opcode, objoff, objlen,
1030 1031
				       truncate_size, truncate_seq);
	}
1032

1033
	req->r_abort_on_full = true;
1034
	req->r_flags = flags;
1035
	req->r_base_oloc.pool = layout->pool_id;
1036
	req->r_base_oloc.pool_ns = ceph_try_get_string(layout->pool_ns);
1037
	ceph_oid_printf(&req->r_base_oid, "%llx.%08llx", vino.ino, objnum);
1038

1039 1040 1041 1042
	req->r_snapid = vino.snap;
	if (flags & CEPH_OSD_FLAG_WRITE)
		req->r_data_offset = off;

1043 1044 1045 1046
	r = ceph_osdc_alloc_messages(req, GFP_NOFS);
	if (r)
		goto fail;

S
Sage Weil 已提交
1047
	return req;
1048 1049 1050 1051

fail:
	ceph_osdc_put_request(req);
	return ERR_PTR(r);
S
Sage Weil 已提交
1052
}
1053
EXPORT_SYMBOL(ceph_osdc_new_request);
S
Sage Weil 已提交
1054 1055 1056 1057

/*
 * We keep osd requests in an rbtree, sorted by ->r_tid.
 */
I
Ilya Dryomov 已提交
1058
DEFINE_RB_FUNCS(request, struct ceph_osd_request, r_tid, r_node)
I
Ilya Dryomov 已提交
1059
DEFINE_RB_FUNCS(request_mc, struct ceph_osd_request, r_tid, r_mc_node)
S
Sage Weil 已提交
1060

1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092
/*
 * Call @fn on each OSD request as long as @fn returns 0.
 */
static void for_each_request(struct ceph_osd_client *osdc,
			int (*fn)(struct ceph_osd_request *req, void *arg),
			void *arg)
{
	struct rb_node *n, *p;

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

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

			p = rb_next(p);
			if (fn(req, arg))
				return;
		}
	}

	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);
		if (fn(req, arg))
			return;
	}
}

1093 1094 1095 1096 1097
static bool osd_homeless(struct ceph_osd *osd)
{
	return osd->o_osd == CEPH_HOMELESS_OSD;
}

1098
static bool osd_registered(struct ceph_osd *osd)
S
Sage Weil 已提交
1099
{
1100
	verify_osdc_locked(osd->o_osdc);
S
Sage Weil 已提交
1101

1102
	return !RB_EMPTY_NODE(&osd->o_node);
S
Sage Weil 已提交
1103 1104
}

1105 1106 1107 1108 1109
/*
 * Assumes @osd is zero-initialized.
 */
static void osd_init(struct ceph_osd *osd)
{
1110
	refcount_set(&osd->o_ref, 1);
1111
	RB_CLEAR_NODE(&osd->o_node);
1112
	osd->o_requests = RB_ROOT;
1113
	osd->o_linger_requests = RB_ROOT;
1114 1115
	osd->o_backoff_mappings = RB_ROOT;
	osd->o_backoffs_by_id = RB_ROOT;
1116 1117 1118
	INIT_LIST_HEAD(&osd->o_osd_lru);
	INIT_LIST_HEAD(&osd->o_keepalive_item);
	osd->o_incarnation = 1;
1119
	mutex_init(&osd->lock);
1120 1121 1122 1123 1124
}

static void osd_cleanup(struct ceph_osd *osd)
{
	WARN_ON(!RB_EMPTY_NODE(&osd->o_node));
1125
	WARN_ON(!RB_EMPTY_ROOT(&osd->o_requests));
1126
	WARN_ON(!RB_EMPTY_ROOT(&osd->o_linger_requests));
1127 1128
	WARN_ON(!RB_EMPTY_ROOT(&osd->o_backoff_mappings));
	WARN_ON(!RB_EMPTY_ROOT(&osd->o_backoffs_by_id));
1129 1130 1131 1132 1133 1134 1135 1136 1137
	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
1138 1139 1140
/*
 * Track open sessions with osds.
 */
1141
static struct ceph_osd *create_osd(struct ceph_osd_client *osdc, int onum)
S
Sage Weil 已提交
1142 1143 1144
{
	struct ceph_osd *osd;

1145 1146
	WARN_ON(onum == CEPH_HOMELESS_OSD);

1147
	osd = kzalloc(sizeof(*osd), GFP_NOIO | __GFP_NOFAIL);
1148
	osd_init(osd);
S
Sage Weil 已提交
1149
	osd->o_osdc = osdc;
1150
	osd->o_osd = onum;
S
Sage Weil 已提交
1151

1152
	ceph_con_init(&osd->o_con, osd, &osd_con_ops, &osdc->client->msgr);
1153

S
Sage Weil 已提交
1154 1155 1156 1157 1158
	return osd;
}

static struct ceph_osd *get_osd(struct ceph_osd *osd)
{
1159 1160 1161
	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
1162 1163 1164 1165 1166 1167 1168 1169 1170
		return osd;
	} else {
		dout("get_osd %p FAIL\n", osd);
		return NULL;
	}
}

static void put_osd(struct ceph_osd *osd)
{
1171 1172 1173
	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)) {
1174
		osd_cleanup(osd);
S
Sage Weil 已提交
1175
		kfree(osd);
S
Sage Weil 已提交
1176
	}
S
Sage Weil 已提交
1177 1178
}

I
Ilya Dryomov 已提交
1179 1180
DEFINE_RB_FUNCS(osd, struct ceph_osd, o_osd, o_node)

1181
static void __move_osd_to_lru(struct ceph_osd *osd)
1182
{
1183 1184 1185
	struct ceph_osd_client *osdc = osd->o_osdc;

	dout("%s osd %p osd%d\n", __func__, osd, osd->o_osd);
1186
	BUG_ON(!list_empty(&osd->o_osd_lru));
1187

1188
	spin_lock(&osdc->osd_lru_lock);
1189
	list_add_tail(&osd->o_osd_lru, &osdc->osd_lru);
1190 1191
	spin_unlock(&osdc->osd_lru_lock);

1192
	osd->lru_ttl = jiffies + osdc->client->options->osd_idle_ttl;
1193 1194
}

1195
static void maybe_move_osd_to_lru(struct ceph_osd *osd)
1196
{
1197
	if (RB_EMPTY_ROOT(&osd->o_requests) &&
1198
	    RB_EMPTY_ROOT(&osd->o_linger_requests))
1199
		__move_osd_to_lru(osd);
1200 1201
}

1202 1203
static void __remove_osd_from_lru(struct ceph_osd *osd)
{
1204 1205 1206 1207 1208
	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);
1209 1210
	if (!list_empty(&osd->o_osd_lru))
		list_del_init(&osd->o_osd_lru);
1211
	spin_unlock(&osdc->osd_lru_lock);
1212 1213
}

1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237
/*
 * 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);
	}
1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248
	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);
	}
1249
	clear_backoffs(osd);
1250 1251 1252 1253 1254 1255

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

S
Sage Weil 已提交
1256 1257 1258
/*
 * reset osd connect
 */
1259
static int reopen_osd(struct ceph_osd *osd)
S
Sage Weil 已提交
1260
{
A
Alex Elder 已提交
1261
	struct ceph_entity_addr *peer_addr;
S
Sage Weil 已提交
1262

1263 1264 1265
	dout("%s osd %p osd%d\n", __func__, osd, osd->o_osd);

	if (RB_EMPTY_ROOT(&osd->o_requests) &&
1266
	    RB_EMPTY_ROOT(&osd->o_linger_requests)) {
1267
		close_osd(osd);
A
Alex Elder 已提交
1268 1269 1270
		return -ENODEV;
	}

1271
	peer_addr = &osd->o_osdc->osdmap->osd_addr[osd->o_osd];
A
Alex Elder 已提交
1272 1273
	if (!memcmp(peer_addr, &osd->o_con.peer_addr, sizeof (*peer_addr)) &&
			!ceph_con_opened(&osd->o_con)) {
1274
		struct rb_node *n;
A
Alex Elder 已提交
1275

1276 1277
		dout("osd addr hasn't changed and connection never opened, "
		     "letting msgr retry\n");
1278
		/* touch each r_stamp for handle_timeout()'s benfit */
1279 1280 1281
		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);
1282
			req->r_stamp = jiffies;
1283
		}
A
Alex Elder 已提交
1284 1285

		return -EAGAIN;
S
Sage Weil 已提交
1286
	}
A
Alex Elder 已提交
1287 1288 1289 1290 1291 1292

	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
1293 1294
}

1295 1296
static struct ceph_osd *lookup_create_osd(struct ceph_osd_client *osdc, int o,
					  bool wrlocked)
S
Sage Weil 已提交
1297
{
1298
	struct ceph_osd *osd;
1299

1300 1301 1302 1303
	if (wrlocked)
		verify_osdc_wrlocked(osdc);
	else
		verify_osdc_locked(osdc);
S
Sage Weil 已提交
1304

1305 1306 1307 1308 1309 1310 1311
	if (o != CEPH_HOMELESS_OSD)
		osd = lookup_osd(&osdc->osds, o);
	else
		osd = &osdc->homeless_osd;
	if (!osd) {
		if (!wrlocked)
			return ERR_PTR(-EAGAIN);
1312

1313 1314 1315 1316
		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]);
1317
	}
S
Sage Weil 已提交
1318

1319 1320
	dout("%s osdc %p osd%d -> osd %p\n", __func__, osdc, o, osd);
	return osd;
S
Sage Weil 已提交
1321 1322 1323
}

/*
1324 1325 1326
 * Create request <-> OSD session relation.
 *
 * @req has to be assigned a tid, @osd may be homeless.
S
Sage Weil 已提交
1327
 */
1328
static void link_request(struct ceph_osd *osd, struct ceph_osd_request *req)
S
Sage Weil 已提交
1329
{
1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342
	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
1343 1344
}

1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361
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);
}

1362 1363 1364 1365 1366
static bool __pool_full(struct ceph_pg_pool_info *pi)
{
	return pi->flags & CEPH_POOL_FLAG_FULL;
}

I
Ilya Dryomov 已提交
1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381
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;
}

1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392
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);
}

1393 1394 1395 1396
/*
 * Returns whether a request should be blocked from being sent
 * based on the current osdmap and osd_client settings.
 */
1397 1398 1399 1400
static bool target_should_be_paused(struct ceph_osd_client *osdc,
				    const struct ceph_osd_request_target *t,
				    struct ceph_pg_pool_info *pi)
{
1401 1402 1403
	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) ||
1404 1405
		       __pool_full(pi);

1406
	WARN_ON(pi->id != t->target_oloc.pool);
1407 1408 1409
	return ((t->flags & CEPH_OSD_FLAG_READ) && pauserd) ||
	       ((t->flags & CEPH_OSD_FLAG_WRITE) && pausewr) ||
	       (osdc->osdmap->epoch < osdc->epoch_barrier);
1410 1411 1412 1413 1414 1415 1416 1417 1418 1419
}

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,
1420
					   struct ceph_connection *con,
1421 1422 1423 1424 1425 1426
					   bool any_change)
{
	struct ceph_pg_pool_info *pi;
	struct ceph_pg pgid, last_pgid;
	struct ceph_osds up, acting;
	bool force_resend = false;
1427 1428
	bool unpaused = false;
	bool legacy_change;
1429
	bool split = false;
1430
	bool sort_bitwise = ceph_osdmap_flag(osdc, CEPH_OSDMAP_SORTBITWISE);
1431 1432
	bool recovery_deletes = ceph_osdmap_flag(osdc,
						 CEPH_OSDMAP_RECOVERY_DELETES);
1433 1434 1435
	enum calc_target_result ct_res;
	int ret;

1436
	t->epoch = osdc->osdmap->epoch;
1437 1438 1439 1440 1441 1442 1443 1444
	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) {
1445 1446
		if (t->last_force_resend < pi->last_force_request_resend) {
			t->last_force_resend = pi->last_force_request_resend;
1447
			force_resend = true;
1448
		} else if (t->last_force_resend == 0) {
1449 1450 1451 1452
			force_resend = true;
		}
	}

1453 1454 1455 1456
	/* apply tiering */
	ceph_oid_copy(&t->target_oid, &t->base_oid);
	ceph_oloc_copy(&t->target_oloc, &t->base_oloc);
	if ((t->flags & CEPH_OSD_FLAG_IGNORE_OVERLAY) == 0) {
1457 1458 1459 1460
		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;
1461 1462 1463 1464 1465 1466 1467

		pi = ceph_pg_pool_by_id(osdc->osdmap, t->target_oloc.pool);
		if (!pi) {
			t->osd = CEPH_HOMELESS_OSD;
			ct_res = CALC_TARGET_POOL_DNE;
			goto out;
		}
1468 1469
	}

1470 1471
	ret = __ceph_object_locator_to_pg(pi, &t->target_oid, &t->target_oloc,
					  &pgid);
1472 1473 1474 1475 1476 1477 1478 1479 1480
	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);

1481
	ceph_pg_to_up_acting_osds(osdc->osdmap, pi, &pgid, &up, &acting);
1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494
	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,
1495 1496
				 t->recovery_deletes,
				 recovery_deletes,
1497 1498 1499 1500 1501
				 &last_pgid))
		force_resend = true;

	if (t->paused && !target_should_be_paused(osdc, t, pi)) {
		t->paused = false;
1502
		unpaused = true;
1503
	}
1504 1505
	legacy_change = ceph_pg_compare(&t->pgid, &pgid) ||
			ceph_osds_changed(&t->acting, &acting, any_change);
1506 1507
	if (t->pg_num)
		split = ceph_pg_is_split(&last_pgid, t->pg_num, pi->pg_num);
1508

1509
	if (legacy_change || force_resend || split) {
1510
		t->pgid = pgid; /* struct */
1511
		ceph_pg_to_primary_shard(osdc->osdmap, pi, &pgid, &t->spgid);
1512 1513 1514 1515 1516 1517 1518
		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;
1519
		t->recovery_deletes = recovery_deletes;
1520 1521 1522 1523

		t->osd = acting.primary;
	}

1524 1525 1526
	if (unpaused || legacy_change || force_resend ||
	    (split && con && CEPH_HAVE_FEATURE(con->peer_features,
					       RESEND_ON_SPLIT)))
1527 1528 1529 1530
		ct_res = CALC_TARGET_NEED_RESEND;
	else
		ct_res = CALC_TARGET_NO_ACTION;

1531 1532 1533 1534 1535
out:
	dout("%s t %p -> ct_res %d osd %d\n", __func__, t, ct_res, t->osd);
	return ct_res;
}

1536 1537 1538 1539 1540 1541 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 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 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 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857
static struct ceph_spg_mapping *alloc_spg_mapping(void)
{
	struct ceph_spg_mapping *spg;

	spg = kmalloc(sizeof(*spg), GFP_NOIO);
	if (!spg)
		return NULL;

	RB_CLEAR_NODE(&spg->node);
	spg->backoffs = RB_ROOT;
	return spg;
}

static void free_spg_mapping(struct ceph_spg_mapping *spg)
{
	WARN_ON(!RB_EMPTY_NODE(&spg->node));
	WARN_ON(!RB_EMPTY_ROOT(&spg->backoffs));

	kfree(spg);
}

/*
 * rbtree of ceph_spg_mapping for handling map<spg_t, ...>, similar to
 * ceph_pg_mapping.  Used to track OSD backoffs -- a backoff [range] is
 * defined only within a specific spgid; it does not pass anything to
 * children on split, or to another primary.
 */
DEFINE_RB_FUNCS2(spg_mapping, struct ceph_spg_mapping, spgid, ceph_spg_compare,
		 RB_BYPTR, const struct ceph_spg *, node)

static u64 hoid_get_bitwise_key(const struct ceph_hobject_id *hoid)
{
	return hoid->is_max ? 0x100000000ull : hoid->hash_reverse_bits;
}

static void hoid_get_effective_key(const struct ceph_hobject_id *hoid,
				   void **pkey, size_t *pkey_len)
{
	if (hoid->key_len) {
		*pkey = hoid->key;
		*pkey_len = hoid->key_len;
	} else {
		*pkey = hoid->oid;
		*pkey_len = hoid->oid_len;
	}
}

static int compare_names(const void *name1, size_t name1_len,
			 const void *name2, size_t name2_len)
{
	int ret;

	ret = memcmp(name1, name2, min(name1_len, name2_len));
	if (!ret) {
		if (name1_len < name2_len)
			ret = -1;
		else if (name1_len > name2_len)
			ret = 1;
	}
	return ret;
}

static int hoid_compare(const struct ceph_hobject_id *lhs,
			const struct ceph_hobject_id *rhs)
{
	void *effective_key1, *effective_key2;
	size_t effective_key1_len, effective_key2_len;
	int ret;

	if (lhs->is_max < rhs->is_max)
		return -1;
	if (lhs->is_max > rhs->is_max)
		return 1;

	if (lhs->pool < rhs->pool)
		return -1;
	if (lhs->pool > rhs->pool)
		return 1;

	if (hoid_get_bitwise_key(lhs) < hoid_get_bitwise_key(rhs))
		return -1;
	if (hoid_get_bitwise_key(lhs) > hoid_get_bitwise_key(rhs))
		return 1;

	ret = compare_names(lhs->nspace, lhs->nspace_len,
			    rhs->nspace, rhs->nspace_len);
	if (ret)
		return ret;

	hoid_get_effective_key(lhs, &effective_key1, &effective_key1_len);
	hoid_get_effective_key(rhs, &effective_key2, &effective_key2_len);
	ret = compare_names(effective_key1, effective_key1_len,
			    effective_key2, effective_key2_len);
	if (ret)
		return ret;

	ret = compare_names(lhs->oid, lhs->oid_len, rhs->oid, rhs->oid_len);
	if (ret)
		return ret;

	if (lhs->snapid < rhs->snapid)
		return -1;
	if (lhs->snapid > rhs->snapid)
		return 1;

	return 0;
}

/*
 * For decoding ->begin and ->end of MOSDBackoff only -- no MIN/MAX
 * compat stuff here.
 *
 * Assumes @hoid is zero-initialized.
 */
static int decode_hoid(void **p, void *end, struct ceph_hobject_id *hoid)
{
	u8 struct_v;
	u32 struct_len;
	int ret;

	ret = ceph_start_decoding(p, end, 4, "hobject_t", &struct_v,
				  &struct_len);
	if (ret)
		return ret;

	if (struct_v < 4) {
		pr_err("got struct_v %d < 4 of hobject_t\n", struct_v);
		goto e_inval;
	}

	hoid->key = ceph_extract_encoded_string(p, end, &hoid->key_len,
						GFP_NOIO);
	if (IS_ERR(hoid->key)) {
		ret = PTR_ERR(hoid->key);
		hoid->key = NULL;
		return ret;
	}

	hoid->oid = ceph_extract_encoded_string(p, end, &hoid->oid_len,
						GFP_NOIO);
	if (IS_ERR(hoid->oid)) {
		ret = PTR_ERR(hoid->oid);
		hoid->oid = NULL;
		return ret;
	}

	ceph_decode_64_safe(p, end, hoid->snapid, e_inval);
	ceph_decode_32_safe(p, end, hoid->hash, e_inval);
	ceph_decode_8_safe(p, end, hoid->is_max, e_inval);

	hoid->nspace = ceph_extract_encoded_string(p, end, &hoid->nspace_len,
						   GFP_NOIO);
	if (IS_ERR(hoid->nspace)) {
		ret = PTR_ERR(hoid->nspace);
		hoid->nspace = NULL;
		return ret;
	}

	ceph_decode_64_safe(p, end, hoid->pool, e_inval);

	ceph_hoid_build_hash_cache(hoid);
	return 0;

e_inval:
	return -EINVAL;
}

static int hoid_encoding_size(const struct ceph_hobject_id *hoid)
{
	return 8 + 4 + 1 + 8 + /* snapid, hash, is_max, pool */
	       4 + hoid->key_len + 4 + hoid->oid_len + 4 + hoid->nspace_len;
}

static void encode_hoid(void **p, void *end, const struct ceph_hobject_id *hoid)
{
	ceph_start_encoding(p, 4, 3, hoid_encoding_size(hoid));
	ceph_encode_string(p, end, hoid->key, hoid->key_len);
	ceph_encode_string(p, end, hoid->oid, hoid->oid_len);
	ceph_encode_64(p, hoid->snapid);
	ceph_encode_32(p, hoid->hash);
	ceph_encode_8(p, hoid->is_max);
	ceph_encode_string(p, end, hoid->nspace, hoid->nspace_len);
	ceph_encode_64(p, hoid->pool);
}

static void free_hoid(struct ceph_hobject_id *hoid)
{
	if (hoid) {
		kfree(hoid->key);
		kfree(hoid->oid);
		kfree(hoid->nspace);
		kfree(hoid);
	}
}

static struct ceph_osd_backoff *alloc_backoff(void)
{
	struct ceph_osd_backoff *backoff;

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

	RB_CLEAR_NODE(&backoff->spg_node);
	RB_CLEAR_NODE(&backoff->id_node);
	return backoff;
}

static void free_backoff(struct ceph_osd_backoff *backoff)
{
	WARN_ON(!RB_EMPTY_NODE(&backoff->spg_node));
	WARN_ON(!RB_EMPTY_NODE(&backoff->id_node));

	free_hoid(backoff->begin);
	free_hoid(backoff->end);
	kfree(backoff);
}

/*
 * Within a specific spgid, backoffs are managed by ->begin hoid.
 */
DEFINE_RB_INSDEL_FUNCS2(backoff, struct ceph_osd_backoff, begin, hoid_compare,
			RB_BYVAL, spg_node);

static struct ceph_osd_backoff *lookup_containing_backoff(struct rb_root *root,
					    const struct ceph_hobject_id *hoid)
{
	struct rb_node *n = root->rb_node;

	while (n) {
		struct ceph_osd_backoff *cur =
		    rb_entry(n, struct ceph_osd_backoff, spg_node);
		int cmp;

		cmp = hoid_compare(hoid, cur->begin);
		if (cmp < 0) {
			n = n->rb_left;
		} else if (cmp > 0) {
			if (hoid_compare(hoid, cur->end) < 0)
				return cur;

			n = n->rb_right;
		} else {
			return cur;
		}
	}

	return NULL;
}

/*
 * Each backoff has a unique id within its OSD session.
 */
DEFINE_RB_FUNCS(backoff_by_id, struct ceph_osd_backoff, id, id_node)

static void clear_backoffs(struct ceph_osd *osd)
{
	while (!RB_EMPTY_ROOT(&osd->o_backoff_mappings)) {
		struct ceph_spg_mapping *spg =
		    rb_entry(rb_first(&osd->o_backoff_mappings),
			     struct ceph_spg_mapping, node);

		while (!RB_EMPTY_ROOT(&spg->backoffs)) {
			struct ceph_osd_backoff *backoff =
			    rb_entry(rb_first(&spg->backoffs),
				     struct ceph_osd_backoff, spg_node);

			erase_backoff(&spg->backoffs, backoff);
			erase_backoff_by_id(&osd->o_backoffs_by_id, backoff);
			free_backoff(backoff);
		}
		erase_spg_mapping(&osd->o_backoff_mappings, spg);
		free_spg_mapping(spg);
	}
}

/*
 * Set up a temporary, non-owning view into @t.
 */
static void hoid_fill_from_target(struct ceph_hobject_id *hoid,
				  const struct ceph_osd_request_target *t)
{
	hoid->key = NULL;
	hoid->key_len = 0;
	hoid->oid = t->target_oid.name;
	hoid->oid_len = t->target_oid.name_len;
	hoid->snapid = CEPH_NOSNAP;
	hoid->hash = t->pgid.seed;
	hoid->is_max = false;
	if (t->target_oloc.pool_ns) {
		hoid->nspace = t->target_oloc.pool_ns->str;
		hoid->nspace_len = t->target_oloc.pool_ns->len;
	} else {
		hoid->nspace = NULL;
		hoid->nspace_len = 0;
	}
	hoid->pool = t->target_oloc.pool;
	ceph_hoid_build_hash_cache(hoid);
}

static bool should_plug_request(struct ceph_osd_request *req)
{
	struct ceph_osd *osd = req->r_osd;
	struct ceph_spg_mapping *spg;
	struct ceph_osd_backoff *backoff;
	struct ceph_hobject_id hoid;

	spg = lookup_spg_mapping(&osd->o_backoff_mappings, &req->r_t.spgid);
	if (!spg)
		return false;

	hoid_fill_from_target(&hoid, &req->r_t);
	backoff = lookup_containing_backoff(&spg->backoffs, &hoid);
	if (!backoff)
		return false;

	dout("%s req %p tid %llu backoff osd%d spgid %llu.%xs%d id %llu\n",
	     __func__, req, req->r_tid, osd->o_osd, backoff->spgid.pgid.pool,
	     backoff->spgid.pgid.seed, backoff->spgid.shard, backoff->id);
	return true;
}

1858 1859
static void setup_request_data(struct ceph_osd_request *req,
			       struct ceph_msg *msg)
S
Sage Weil 已提交
1860
{
1861 1862 1863 1864 1865
	u32 data_len = 0;
	int i;

	if (!list_empty(&msg->data))
		return;
S
Sage Weil 已提交
1866

1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883
	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;
1884 1885 1886 1887
		case CEPH_OSD_OP_NOTIFY_ACK:
			ceph_osdc_msg_data_add(msg,
					       &op->notify_ack.request_data);
			break;
1888 1889 1890 1891 1892 1893 1894 1895 1896 1897

		/* 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;
1898 1899 1900 1901
		case CEPH_OSD_OP_LIST_WATCHERS:
			ceph_osdc_msg_data_add(req->r_reply,
					       &op->list_watchers.response_data);
			break;
1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914

		/* 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;
1915 1916 1917 1918 1919 1920
		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;
1921 1922 1923 1924
		}

		data_len += op->indata_len;
	}
1925

1926 1927 1928
	WARN_ON(data_len != msg->data_length);
}

1929 1930 1931 1932 1933 1934 1935 1936
static void encode_pgid(void **p, const struct ceph_pg *pgid)
{
	ceph_encode_8(p, 1);
	ceph_encode_64(p, pgid->pool);
	ceph_encode_32(p, pgid->seed);
	ceph_encode_32(p, -1); /* preferred */
}

1937 1938 1939 1940 1941 1942 1943
static void encode_spgid(void **p, const struct ceph_spg *spgid)
{
	ceph_start_encoding(p, 1, 1, CEPH_PGID_ENCODING_LEN + 1);
	encode_pgid(p, &spgid->pgid);
	ceph_encode_8(p, spgid->shard);
}

1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957
static void encode_oloc(void **p, void *end,
			const struct ceph_object_locator *oloc)
{
	ceph_start_encoding(p, 5, 4, ceph_oloc_encoding_size(oloc));
	ceph_encode_64(p, oloc->pool);
	ceph_encode_32(p, -1); /* preferred */
	ceph_encode_32(p, 0);  /* key len */
	if (oloc->pool_ns)
		ceph_encode_string(p, end, oloc->pool_ns->str,
				   oloc->pool_ns->len);
	else
		ceph_encode_32(p, 0);
}

1958 1959
static void encode_request_partial(struct ceph_osd_request *req,
				   struct ceph_msg *msg)
1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975
{
	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);

1976 1977
	encode_spgid(&p, &req->r_t.spgid); /* actual spg */
	ceph_encode_32(&p, req->r_t.pgid.seed); /* raw hash */
1978 1979
	ceph_encode_32(&p, req->r_osdc->osdmap->epoch);
	ceph_encode_32(&p, req->r_flags);
1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990

	/* reqid */
	ceph_start_encoding(&p, 2, 2, sizeof(struct ceph_osd_reqid));
	memset(p, 0, sizeof(struct ceph_osd_reqid));
	p += sizeof(struct ceph_osd_reqid);

	/* trace */
	memset(p, 0, sizeof(struct ceph_blkin_trace_info));
	p += sizeof(struct ceph_blkin_trace_info);

	ceph_encode_32(&p, 0); /* client_inc, always 0 */
1991 1992
	ceph_encode_timespec(p, &req->r_mtime);
	p += sizeof(struct ceph_timespec);
1993

1994 1995 1996
	encode_oloc(&p, end, &req->r_t.target_oloc);
	ceph_encode_string(&p, end, req->r_t.target_oid.name,
			   req->r_t.target_oid.name_len);
S
Sage Weil 已提交
1997

1998 1999 2000 2001 2002 2003
	/* 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);
	}
2004

2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016
	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 */
2017
	BUG_ON(p > end - 8); /* space for features */
2018

2019 2020
	msg->hdr.version = cpu_to_le16(8); /* MOSDOp v8 */
	/* front_len is finalized in encode_request_finish() */
2021 2022
	msg->front.iov_len = p - msg->front.iov_base;
	msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
2023 2024 2025 2026 2027 2028 2029
	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);
2030

2031 2032 2033 2034 2035 2036 2037
	dout("%s req %p msg %p oid %s oid_len %d\n", __func__, req, msg,
	     req->r_t.target_oid.name, req->r_t.target_oid.name_len);
}

static void encode_request_finish(struct ceph_msg *msg)
{
	void *p = msg->front.iov_base;
2038
	void *const partial_end = p + msg->front.iov_len;
2039 2040 2041 2042
	void *const end = p + msg->front_alloc_len;

	if (CEPH_HAVE_FEATURE(msg->con->peer_features, RESEND_ON_SPLIT)) {
		/* luminous OSD -- encode features and be done */
2043
		p = partial_end;
2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 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
		ceph_encode_64(&p, msg->con->peer_features);
	} else {
		struct {
			char spgid[CEPH_ENCODING_START_BLK_LEN +
				   CEPH_PGID_ENCODING_LEN + 1];
			__le32 hash;
			__le32 epoch;
			__le32 flags;
			char reqid[CEPH_ENCODING_START_BLK_LEN +
				   sizeof(struct ceph_osd_reqid)];
			char trace[sizeof(struct ceph_blkin_trace_info)];
			__le32 client_inc;
			struct ceph_timespec mtime;
		} __packed head;
		struct ceph_pg pgid;
		void *oloc, *oid, *tail;
		int oloc_len, oid_len, tail_len;
		int len;

		/*
		 * Pre-luminous OSD -- reencode v8 into v4 using @head
		 * as a temporary buffer.  Encode the raw PG; the rest
		 * is just a matter of moving oloc, oid and tail blobs
		 * around.
		 */
		memcpy(&head, p, sizeof(head));
		p += sizeof(head);

		oloc = p;
		p += CEPH_ENCODING_START_BLK_LEN;
		pgid.pool = ceph_decode_64(&p);
		p += 4 + 4; /* preferred, key len */
		len = ceph_decode_32(&p);
		p += len;   /* nspace */
		oloc_len = p - oloc;

		oid = p;
		len = ceph_decode_32(&p);
		p += len;
		oid_len = p - oid;

		tail = p;
2086
		tail_len = partial_end - p;
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

		p = msg->front.iov_base;
		ceph_encode_copy(&p, &head.client_inc, sizeof(head.client_inc));
		ceph_encode_copy(&p, &head.epoch, sizeof(head.epoch));
		ceph_encode_copy(&p, &head.flags, sizeof(head.flags));
		ceph_encode_copy(&p, &head.mtime, sizeof(head.mtime));

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

		BUG_ON(p >= oloc);
		memmove(p, oloc, oloc_len);
		p += oloc_len;

		pgid.seed = le32_to_cpu(head.hash);
		encode_pgid(&p, &pgid); /* raw pg */

		BUG_ON(p >= oid);
		memmove(p, oid, oid_len);
		p += oid_len;

		/* tail -- ops, snapid, snapc, retry_attempt */
		BUG_ON(p >= tail);
		memmove(p, tail, tail_len);
		p += tail_len;

		msg->hdr.version = cpu_to_le16(4); /* MOSDOp v4 */
	}

	BUG_ON(p > end);
	msg->front.iov_len = p - msg->front.iov_base;
	msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);

	dout("%s msg %p tid %llu %u+%u+%u v%d\n", __func__, msg,
	     le64_to_cpu(msg->hdr.tid), le32_to_cpu(msg->hdr.front_len),
	     le32_to_cpu(msg->hdr.middle_len), le32_to_cpu(msg->hdr.data_len),
	     le16_to_cpu(msg->hdr.version));
2125 2126 2127 2128 2129 2130 2131 2132 2133
}

/*
 * @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;

2134
	verify_osd_locked(osd);
2135 2136
	WARN_ON(osd->o_osd != req->r_t.osd);

2137 2138 2139 2140
	/* backoff? */
	if (should_plug_request(req))
		return;

2141 2142 2143 2144 2145 2146 2147
	/*
	 * 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);

2148 2149 2150 2151 2152 2153
	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);

2154
	encode_request_partial(req, req->r_request);
2155

2156
	dout("%s req %p tid %llu to pgid %llu.%x spgid %llu.%xs%d osd%d e%u flags 0x%x attempt %d\n",
2157
	     __func__, req, req->r_tid, req->r_t.pgid.pool, req->r_t.pgid.seed,
2158
	     req->r_t.spgid.pgid.pool, req->r_t.spgid.pgid.seed,
2159 2160
	     req->r_t.spgid.shard, osd->o_osd, req->r_t.epoch, req->r_flags,
	     req->r_attempts);
2161 2162 2163 2164 2165 2166 2167 2168

	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
2169 2170
}

I
Ilya Dryomov 已提交
2171 2172 2173 2174
static void maybe_request_map(struct ceph_osd_client *osdc)
{
	bool continuous = false;

2175
	verify_osdc_locked(osdc);
I
Ilya Dryomov 已提交
2176 2177
	WARN_ON(!osdc->osdmap->epoch);

2178 2179 2180
	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
2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191
		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);
}

2192
static void complete_request(struct ceph_osd_request *req, int err);
I
Ilya Dryomov 已提交
2193 2194
static void send_map_check(struct ceph_osd_request *req);

2195
static void __submit_request(struct ceph_osd_request *req, bool wrlocked)
2196
{
2197 2198
	struct ceph_osd_client *osdc = req->r_osdc;
	struct ceph_osd *osd;
I
Ilya Dryomov 已提交
2199
	enum calc_target_result ct_res;
2200
	int err = 0;
2201 2202
	bool need_send = false;
	bool promoted = false;
2203

I
Ilya Dryomov 已提交
2204
	WARN_ON(req->r_tid);
2205 2206 2207
	dout("%s req %p wrlocked %d\n", __func__, req, wrlocked);

again:
2208
	ct_res = calc_target(osdc, &req->r_t, NULL, false);
I
Ilya Dryomov 已提交
2209 2210 2211
	if (ct_res == CALC_TARGET_POOL_DNE && !wrlocked)
		goto promote;

2212 2213 2214 2215
	osd = lookup_create_osd(osdc, req->r_t.osd, wrlocked);
	if (IS_ERR(osd)) {
		WARN_ON(PTR_ERR(osd) != -EAGAIN || wrlocked);
		goto promote;
2216 2217
	}

2218 2219 2220 2221
	if (osdc->abort_err) {
		dout("req %p abort_err %d\n", req, osdc->abort_err);
		err = osdc->abort_err;
	} else if (osdc->osdmap->epoch < osdc->epoch_barrier) {
2222 2223 2224 2225 2226 2227
		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)) {
2228 2229 2230 2231
		dout("req %p pausewr\n", req);
		req->r_t.paused = true;
		maybe_request_map(osdc);
	} else if ((req->r_flags & CEPH_OSD_FLAG_READ) &&
2232
		   ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD)) {
2233 2234 2235 2236 2237 2238
		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)) &&
2239
		   (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) ||
2240 2241 2242 2243 2244
		    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);
2245
		if (req->r_abort_on_full)
2246
			err = -ENOSPC;
2247 2248
	} else if (!osd_homeless(osd)) {
		need_send = true;
2249
	} else {
2250
		maybe_request_map(osdc);
2251 2252
	}

2253 2254 2255 2256 2257 2258 2259 2260 2261 2262
	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);
2263 2264
	else if (err)
		complete_request(req, err);
2265 2266
	mutex_unlock(&osd->lock);

I
Ilya Dryomov 已提交
2267 2268 2269
	if (ct_res == CALC_TARGET_POOL_DNE)
		send_map_check(req);

2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283
	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)
{
2284
	WARN_ON(req->r_flags & (CEPH_OSD_FLAG_ACK | CEPH_OSD_FLAG_ONDISK));
I
Ilya Dryomov 已提交
2285
	WARN_ON(!(req->r_flags & (CEPH_OSD_FLAG_READ | CEPH_OSD_FLAG_WRITE)));
2286

I
Ilya Dryomov 已提交
2287
	req->r_flags |= CEPH_OSD_FLAG_ONDISK;
2288
	atomic_inc(&req->r_osdc->num_requests);
2289 2290

	req->r_start_stamp = jiffies;
2291 2292 2293 2294 2295 2296 2297 2298 2299
}

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

2300
static void finish_request(struct ceph_osd_request *req)
2301 2302 2303
{
	struct ceph_osd_client *osdc = req->r_osdc;

2304
	WARN_ON(lookup_request_mc(&osdc->map_checks, req->r_tid));
2305 2306
	dout("%s req %p tid %llu\n", __func__, req, req->r_tid);

2307 2308
	if (req->r_osd)
		unlink_request(req->r_osd, req);
2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320
	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);
}

2321 2322
static void __complete_request(struct ceph_osd_request *req)
{
2323 2324 2325 2326
	dout("%s req %p tid %llu cb %pf result %d\n", __func__, req,
	     req->r_tid, req->r_callback, req->r_result);

	if (req->r_callback)
2327
		req->r_callback(req);
2328 2329
	complete_all(&req->r_completion);
	ceph_osdc_put_request(req);
2330 2331
}

2332 2333 2334 2335 2336 2337 2338 2339
static void complete_request_workfn(struct work_struct *work)
{
	struct ceph_osd_request *req =
	    container_of(work, struct ceph_osd_request, r_complete_work);

	__complete_request(req);
}

I
Ilya Dryomov 已提交
2340
/*
I
Ilya Dryomov 已提交
2341
 * This is open-coded in handle_reply().
I
Ilya Dryomov 已提交
2342 2343 2344 2345 2346 2347
 */
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;
2348
	finish_request(req);
2349 2350 2351

	INIT_WORK(&req->r_complete_work, complete_request_workfn);
	queue_work(req->r_osdc->completion_wq, &req->r_complete_work);
I
Ilya Dryomov 已提交
2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369
}

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);
}

2370 2371 2372 2373
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
2374
	cancel_map_check(req);
2375
	finish_request(req);
I
Ilya Dryomov 已提交
2376
	complete_all(&req->r_completion);
2377
	ceph_osdc_put_request(req);
2378 2379
}

2380 2381 2382 2383 2384 2385 2386 2387
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);
}

2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409
static int abort_fn(struct ceph_osd_request *req, void *arg)
{
	int err = *(int *)arg;

	abort_request(req, err);
	return 0; /* continue iteration */
}

/*
 * Abort all in-flight requests with @err and arrange for all future
 * requests to be failed immediately.
 */
void ceph_osdc_abort_requests(struct ceph_osd_client *osdc, int err)
{
	dout("%s osdc %p err %d\n", __func__, osdc, err);
	down_write(&osdc->lock);
	for_each_request(osdc, abort_fn, &err);
	osdc->abort_err = err;
	up_write(&osdc->lock);
}
EXPORT_SYMBOL(ceph_osdc_abort_requests);

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
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);

2436 2437
/*
 * Drop all pending requests that are stalled waiting on a full condition to
2438 2439 2440
 * 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.
2441 2442 2443 2444
 */
static void ceph_osdc_abort_on_full(struct ceph_osd_client *osdc)
{
	struct rb_node *n;
2445
	bool victims = false;
2446 2447 2448 2449 2450 2451

	dout("enter abort_on_full\n");

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

2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480
	/* 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);

2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497
	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:
2498
	dout("return abort_on_full barrier=%u\n", osdc->epoch_barrier);
2499 2500
}

I
Ilya Dryomov 已提交
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 2575 2576 2577 2578 2579 2580 2581 2582
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);
}

2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594
/*
 * 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
2595
	WARN_ON(!RB_EMPTY_NODE(&lreq->mc_node));
2596
	WARN_ON(!list_empty(&lreq->scan_item));
2597
	WARN_ON(!list_empty(&lreq->pending_lworks));
2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633
	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
2634
	RB_CLEAR_NODE(&lreq->mc_node);
2635
	INIT_LIST_HEAD(&lreq->scan_item);
2636
	INIT_LIST_HEAD(&lreq->pending_lworks);
2637
	init_completion(&lreq->reg_commit_wait);
2638
	init_completion(&lreq->notify_finish_wait);
2639 2640 2641 2642 2643 2644 2645 2646 2647 2648

	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
2649
DEFINE_RB_FUNCS(linger_mc, struct ceph_osd_linger_request, linger_id, mc_node)
2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 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

/*
 * 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;
2745 2746
	struct list_head pending_item;
	unsigned long queued_stamp;
2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772

	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);
2773
	INIT_LIST_HEAD(&lwork->pending_item);
2774 2775 2776 2777 2778 2779 2780 2781 2782
	lwork->lreq = linger_get(lreq);

	return lwork;
}

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

2783 2784 2785 2786
	mutex_lock(&lreq->lock);
	list_del(&lwork->pending_item);
	mutex_unlock(&lreq->lock);

2787 2788 2789 2790 2791 2792 2793 2794 2795 2796
	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);
2797 2798 2799 2800
	WARN_ON(!list_empty(&lwork->pending_item));

	lwork->queued_stamp = jiffies;
	list_add_tail(&lwork->pending_item, &lreq->pending_lworks);
2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813
	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;
	}

2814
	WARN_ON(!lreq->is_watch);
2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876
	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;

2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894
	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);
		}
	}

2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947
	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);
2948
	if (lreq->is_watch && lreq->committed) {
2949 2950 2951 2952 2953 2954 2955 2956
		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 {
2957 2958 2959 2960
		if (!lreq->is_watch)
			lreq->notify_id = 0;
		else
			WARN_ON(op->watch.op != CEPH_OSD_WATCH_OP_WATCH);
2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980
		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) {
2981 2982 2983
		if (!req->r_result) {
			lreq->watch_valid_thru = lreq->ping_sent;
		} else if (!lreq->last_error) {
2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001
			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];

3002
	if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD)) {
3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037
		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;

3038
	calc_target(osdc, &lreq->t, NULL, false);
3039 3040 3041 3042 3043 3044
	osd = lookup_create_osd(osdc, lreq->t.osd, true);
	link_linger(osd, lreq);

	send_linger(lreq);
}

I
Ilya Dryomov 已提交
3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061
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);
}

3062 3063 3064 3065 3066
/*
 * @lreq has to be both registered and linked.
 */
static void __linger_cancel(struct ceph_osd_linger_request *lreq)
{
3067
	if (lreq->is_watch && lreq->ping_req->r_osd)
3068 3069 3070
		cancel_linger_request(lreq->ping_req);
	if (lreq->reg_req->r_osd)
		cancel_linger_request(lreq->reg_req);
I
Ilya Dryomov 已提交
3071
	cancel_linger_map_check(lreq);
3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085
	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
3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168
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);
}

3169 3170 3171 3172 3173 3174 3175 3176 3177
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;
}

3178 3179 3180 3181 3182 3183 3184 3185 3186
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
3187
/*
3188 3189 3190 3191
 * 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
3192 3193 3194 3195 3196
 */
static void handle_timeout(struct work_struct *work)
{
	struct ceph_osd_client *osdc =
		container_of(work, struct ceph_osd_client, timeout_work.work);
3197
	struct ceph_options *opts = osdc->client->options;
3198
	unsigned long cutoff = jiffies - opts->osd_keepalive_timeout;
3199
	unsigned long expiry_cutoff = jiffies - opts->osd_request_timeout;
3200 3201
	LIST_HEAD(slow_osds);
	struct rb_node *n, *p;
S
Sage Weil 已提交
3202

3203 3204
	dout("%s osdc %p\n", __func__, osdc);
	down_write(&osdc->lock);
S
Sage Weil 已提交
3205

3206 3207 3208 3209 3210
	/*
	 * 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).
	 */
3211 3212 3213 3214
	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;

3215
		for (p = rb_first(&osd->o_requests); p; ) {
3216 3217 3218
			struct ceph_osd_request *req =
			    rb_entry(p, struct ceph_osd_request, r_node);

3219 3220
			p = rb_next(p); /* abort_request() */

3221 3222 3223 3224 3225
			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;
			}
3226 3227 3228 3229 3230 3231
			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);
			}
3232
		}
3233 3234 3235 3236 3237 3238 3239 3240 3241
		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);
3242
			if (lreq->is_watch && lreq->committed && !lreq->last_error)
3243 3244 3245
				send_linger_ping(lreq);
			mutex_unlock(&lreq->lock);
		}
3246

3247 3248
		if (found)
			list_move_tail(&osd->o_keepalive_item, &slow_osds);
3249
	}
3250

3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265
	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);
			}
		}
	}

3266 3267 3268
	if (atomic_read(&osdc->num_homeless) || !list_empty(&slow_osds))
		maybe_request_map(osdc);

3269
	while (!list_empty(&slow_osds)) {
3270 3271 3272
		struct ceph_osd *osd = list_first_entry(&slow_osds,
							struct ceph_osd,
							o_keepalive_item);
3273
		list_del_init(&osd->o_keepalive_item);
S
Sage Weil 已提交
3274 3275 3276
		ceph_con_keepalive(&osd->o_con);
	}

3277
	up_write(&osdc->lock);
3278 3279
	schedule_delayed_work(&osdc->timeout_work,
			      osdc->client->options->osd_keepalive_timeout);
S
Sage Weil 已提交
3280 3281
}

3282 3283 3284 3285 3286
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);
3287
	unsigned long delay = osdc->client->options->osd_idle_ttl / 4;
3288
	struct ceph_osd *osd, *nosd;
3289

3290
	dout("%s osdc %p\n", __func__, osdc);
3291
	down_write(&osdc->lock);
3292 3293 3294 3295
	list_for_each_entry_safe(osd, nosd, &osdc->osd_lru, o_osd_lru) {
		if (time_before(jiffies, osd->lru_ttl))
			break;

3296
		WARN_ON(!RB_EMPTY_ROOT(&osd->o_requests));
3297
		WARN_ON(!RB_EMPTY_ROOT(&osd->o_linger_requests));
3298
		close_osd(osd);
3299
	}
3300

3301
	up_write(&osdc->lock);
3302 3303 3304 3305
	schedule_delayed_work(&osdc->osds_timeout_work,
			      round_jiffies_relative(delay));
}

3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340
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) {
3341 3342
		bool changed = false;

3343 3344
		len = ceph_decode_32(p);
		if (len > 0) {
3345
			ceph_decode_need(p, end, len, e_inval);
3346 3347 3348
			if (!oloc->pool_ns ||
			    ceph_compare_string(oloc->pool_ns, *p, len))
				changed = true;
3349
			*p += len;
3350 3351 3352 3353 3354 3355 3356 3357
		} else {
			if (oloc->pool_ns)
				changed = true;
		}
		if (changed) {
			/* redirect changes namespace */
			pr_warn("ceph_object_locator::nspace is changed\n");
			goto e_inval;
3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421
		}
	}

	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;
}

3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434
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
3435

3436
static int decode_MOSDOpReply(const struct ceph_msg *msg, struct MOSDOpReply *m)
S
Sage Weil 已提交
3437
{
3438 3439 3440 3441
	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
3442
	u8 decode_redir;
3443 3444 3445
	u32 len;
	int ret;
	int i;
3446

3447 3448 3449
	ceph_decode_32_safe(&p, end, len, e_inval);
	ceph_decode_need(&p, end, len, e_inval);
	p += len; /* skip oid */
3450

3451 3452 3453
	ret = ceph_decode_pgid(&p, end, &m->pgid);
	if (ret)
		return ret;
3454

3455 3456 3457 3458 3459 3460
	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);
3461

3462 3463 3464
	ceph_decode_32_safe(&p, end, m->num_ops, e_inval);
	if (m->num_ops > ARRAY_SIZE(m->outdata_len))
		goto e_inval;
3465

3466 3467 3468
	ceph_decode_need(&p, end, m->num_ops * sizeof(struct ceph_osd_op),
			 e_inval);
	for (i = 0; i < m->num_ops; i++) {
3469 3470
		struct ceph_osd_op *op = p;

3471
		m->outdata_len[i] = le32_to_cpu(op->payload_len);
3472 3473 3474
		p += sizeof(*op);
	}

3475 3476 3477
	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
3478

3479 3480 3481 3482 3483 3484 3485 3486 3487
	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
3488

3489 3490 3491
	if (version >= 6) {
		if (version >= 7)
			ceph_decode_8_safe(&p, end, decode_redir, e_inval);
I
Ilya Dryomov 已提交
3492 3493 3494 3495 3496 3497 3498
		else
			decode_redir = 1;
	} else {
		decode_redir = 0;
	}

	if (decode_redir) {
3499 3500 3501
		ret = ceph_redirect_decode(&p, end, &m->redirect);
		if (ret)
			return ret;
3502
	} else {
3503
		ceph_oloc_init(&m->redirect.oloc);
3504
	}
S
Sage Weil 已提交
3505

3506 3507 3508 3509 3510 3511 3512
	return 0;

e_inval:
	return -EINVAL;
}

/*
I
Ilya Dryomov 已提交
3513 3514
 * Handle MOSDOpReply.  Set ->r_result and call the callback if it is
 * specified.
3515
 */
3516
static void handle_reply(struct ceph_osd *osd, struct ceph_msg *msg)
3517
{
3518
	struct ceph_osd_client *osdc = osd->o_osdc;
3519 3520 3521 3522 3523 3524 3525 3526 3527
	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);

3528 3529 3530 3531 3532 3533 3534 3535 3536
	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);
3537
	if (!req) {
3538 3539
		dout("%s osd%d tid %llu unknown\n", __func__, osd->o_osd, tid);
		goto out_unlock_session;
3540 3541
	}

3542
	m.redirect.oloc.pool_ns = req->r_t.target_oloc.pool_ns;
3543
	ret = decode_MOSDOpReply(msg, &m);
3544
	m.redirect.oloc.pool_ns = NULL;
3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560
	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);
3561
			goto out_unlock_session;
3562 3563 3564 3565 3566 3567 3568 3569
		}
	} 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);
3570 3571
		unlink_request(osd, req);
		mutex_unlock(&osd->lock);
3572

3573 3574 3575 3576 3577
		/*
		 * Not ceph_oloc_copy() - changing pool_ns is not
		 * supported.
		 */
		req->r_t.target_oloc.pool = m.redirect.oloc.pool;
3578 3579 3580 3581
		req->r_flags |= CEPH_OSD_FLAG_REDIRECTED;
		req->r_tid = 0;
		__submit_request(req, false);
		goto out_unlock_osdc;
3582 3583
	}

3584 3585 3586 3587
	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
3588
	}
3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600
	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
3601 3602
	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
3603

I
Ilya Dryomov 已提交
3604 3605 3606 3607 3608 3609 3610
	/*
	 * 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);
3611 3612
	mutex_unlock(&osd->lock);
	up_read(&osdc->lock);
S
Sage Weil 已提交
3613

I
Ilya Dryomov 已提交
3614
	__complete_request(req);
S
Sage Weil 已提交
3615 3616
	return;

3617
fail_request:
I
Ilya Dryomov 已提交
3618
	complete_request(req, -EIO);
3619 3620 3621 3622
out_unlock_session:
	mutex_unlock(&osd->lock);
out_unlock_osdc:
	up_read(&osdc->lock);
S
Sage Weil 已提交
3623 3624
}

I
Ilya Dryomov 已提交
3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636
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);
	}
}

3637
static bool pool_cleared_full(struct ceph_osd_client *osdc, s64 pool_id)
S
Sage Weil 已提交
3638
{
3639
	struct ceph_pg_pool_info *pi;
S
Sage Weil 已提交
3640

3641 3642 3643
	pi = ceph_pg_pool_by_id(osdc->osdmap, pool_id);
	if (!pi)
		return false;
S
Sage Weil 已提交
3644

3645
	return pi->was_full && !__pool_full(pi);
3646 3647
}

3648 3649 3650 3651 3652 3653
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;

3654
	ct_res = calc_target(osdc, &lreq->t, NULL, true);
3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667
	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;
}

3668
/*
3669
 * Requeue requests whose mapping to an OSD has changed.
3670
 */
3671 3672 3673 3674 3675 3676
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)
3677
{
3678 3679 3680 3681
	struct ceph_osd_client *osdc = osd->o_osdc;
	struct rb_node *n;
	bool force_resend_writes;

3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701
	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
3702
			cancel_linger_map_check(lreq);
3703 3704 3705 3706 3707 3708 3709 3710 3711
			/*
			 * 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:
3712
			list_del_init(&lreq->scan_item);
I
Ilya Dryomov 已提交
3713
			check_linger_pool_dne(lreq);
3714 3715 3716 3717
			break;
		}
	}

3718 3719 3720 3721 3722
	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
3723
		n = rb_next(n); /* unlink_request(), check_pool_dne() */
3724 3725

		dout("%s req %p tid %llu\n", __func__, req, req->r_tid);
3726 3727
		ct_res = calc_target(osdc, &req->r_t, &req->r_osd->o_con,
				     false);
3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739
		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
3740
			cancel_map_check(req);
3741 3742 3743 3744
			unlink_request(osd, req);
			insert_request(need_resend, req);
			break;
		case CALC_TARGET_POOL_DNE:
I
Ilya Dryomov 已提交
3745
			check_pool_dne(req);
3746
			break;
3747
		}
3748
	}
3749
}
3750

I
Ilya Dryomov 已提交
3751
static int handle_one_map(struct ceph_osd_client *osdc,
3752 3753 3754
			  void *p, void *end, bool incremental,
			  struct rb_root *need_resend,
			  struct list_head *need_resend_linger)
I
Ilya Dryomov 已提交
3755 3756 3757 3758 3759 3760
{
	struct ceph_osdmap *newmap;
	struct rb_node *n;
	bool skipped_map = false;
	bool was_full;

3761
	was_full = ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL);
I
Ilya Dryomov 已提交
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
	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;
	}

3799
	was_full &= !ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL);
3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815
	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
3816 3817 3818

	return 0;
}
3819

3820 3821 3822 3823
static void kick_requests(struct ceph_osd_client *osdc,
			  struct rb_root *need_resend,
			  struct list_head *need_resend_linger)
{
3824
	struct ceph_osd_linger_request *lreq, *nlreq;
3825
	enum calc_target_result ct_res;
3826 3827
	struct rb_node *n;

3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843
	/* make sure need_resend targets reflect latest map */
	for (n = rb_first(need_resend); n; ) {
		struct ceph_osd_request *req =
		    rb_entry(n, struct ceph_osd_request, r_node);

		n = rb_next(n);

		if (req->r_t.epoch < osdc->osdmap->epoch) {
			ct_res = calc_target(osdc, &req->r_t, NULL, false);
			if (ct_res == CALC_TARGET_POOL_DNE) {
				erase_request(need_resend, req);
				check_pool_dne(req);
			}
		}
	}

3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856
	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() */

		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);
3857 3858
		} else {
			cancel_linger_request(req);
3859 3860
		}
	}
3861 3862 3863 3864 3865 3866 3867

	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);
	}
3868 3869
}

S
Sage Weil 已提交
3870 3871 3872 3873 3874 3875 3876 3877 3878
/*
 * 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
3879 3880
	void *p = msg->front.iov_base;
	void *const end = p + msg->front.iov_len;
S
Sage Weil 已提交
3881 3882 3883
	u32 nr_maps, maplen;
	u32 epoch;
	struct ceph_fsid fsid;
3884 3885
	struct rb_root need_resend = RB_ROOT;
	LIST_HEAD(need_resend_linger);
I
Ilya Dryomov 已提交
3886 3887 3888 3889
	bool handled_incremental = false;
	bool was_pauserd, was_pausewr;
	bool pauserd, pausewr;
	int err;
S
Sage Weil 已提交
3890

I
Ilya Dryomov 已提交
3891
	dout("%s have %u\n", __func__, osdc->osdmap->epoch);
3892
	down_write(&osdc->lock);
S
Sage Weil 已提交
3893 3894 3895 3896

	/* verify fsid */
	ceph_decode_need(&p, end, sizeof(fsid), bad);
	ceph_decode_copy(&p, &fsid, sizeof(fsid));
3897
	if (ceph_check_fsid(osdc->client, &fsid) < 0)
I
Ilya Dryomov 已提交
3898
		goto bad;
S
Sage Weil 已提交
3899

3900 3901 3902
	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
3903
		      have_pool_full(osdc);
3904

S
Sage Weil 已提交
3905 3906 3907 3908 3909
	/* 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);
3910 3911
		epoch = ceph_decode_32(&p);
		maplen = ceph_decode_32(&p);
S
Sage Weil 已提交
3912
		ceph_decode_need(&p, end, maplen, bad);
I
Ilya Dryomov 已提交
3913 3914
		if (osdc->osdmap->epoch &&
		    osdc->osdmap->epoch + 1 == epoch) {
S
Sage Weil 已提交
3915 3916
			dout("applying incremental map %u len %d\n",
			     epoch, maplen);
3917 3918
			err = handle_one_map(osdc, p, p + maplen, true,
					     &need_resend, &need_resend_linger);
I
Ilya Dryomov 已提交
3919
			if (err)
S
Sage Weil 已提交
3920
				goto bad;
I
Ilya Dryomov 已提交
3921
			handled_incremental = true;
S
Sage Weil 已提交
3922 3923 3924 3925
		} else {
			dout("ignoring incremental map %u len %d\n",
			     epoch, maplen);
		}
I
Ilya Dryomov 已提交
3926
		p += maplen;
S
Sage Weil 已提交
3927 3928
		nr_maps--;
	}
I
Ilya Dryomov 已提交
3929
	if (handled_incremental)
S
Sage Weil 已提交
3930 3931 3932 3933 3934 3935 3936
		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);
3937 3938
		epoch = ceph_decode_32(&p);
		maplen = ceph_decode_32(&p);
S
Sage Weil 已提交
3939 3940 3941 3942
		ceph_decode_need(&p, end, maplen, bad);
		if (nr_maps > 1) {
			dout("skipping non-latest full map %u len %d\n",
			     epoch, maplen);
3943
		} else if (osdc->osdmap->epoch >= epoch) {
S
Sage Weil 已提交
3944 3945 3946 3947 3948
			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);
3949 3950
			err = handle_one_map(osdc, p, p + maplen, false,
					     &need_resend, &need_resend_linger);
I
Ilya Dryomov 已提交
3951
			if (err)
S
Sage Weil 已提交
3952 3953 3954 3955 3956 3957 3958
				goto bad;
		}
		p += maplen;
		nr_maps--;
	}

done:
3959 3960 3961 3962 3963
	/*
	 * subscribe to subsequent osdmap updates if full to ensure
	 * we find out when we are no longer full and stop returning
	 * ENOSPC.
	 */
3964 3965 3966
	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
3967
		  have_pool_full(osdc);
3968 3969
	if (was_pauserd || was_pausewr || pauserd || pausewr ||
	    osdc->osdmap->epoch < osdc->epoch_barrier)
I
Ilya Dryomov 已提交
3970
		maybe_request_map(osdc);
3971

3972
	kick_requests(osdc, &need_resend, &need_resend_linger);
I
Ilya Dryomov 已提交
3973

3974
	ceph_osdc_abort_on_full(osdc);
I
Ilya Dryomov 已提交
3975 3976
	ceph_monc_got_map(&osdc->client->monc, CEPH_SUB_OSDMAP,
			  osdc->osdmap->epoch);
3977
	up_write(&osdc->lock);
3978
	wake_up_all(&osdc->client->auth_wq);
S
Sage Weil 已提交
3979 3980 3981 3982
	return;

bad:
	pr_err("osdc handle_map corrupt msg\n");
3983
	ceph_msg_dump(msg);
3984 3985 3986 3987 3988 3989 3990 3991 3992 3993
	up_write(&osdc->lock);
}

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

3994 3995
	clear_backoffs(osd);

3996
	for (n = rb_first(&osd->o_requests); n; ) {
3997 3998 3999
		struct ceph_osd_request *req =
		    rb_entry(n, struct ceph_osd_request, r_node);

4000 4001
		n = rb_next(n); /* cancel_linger_request() */

4002 4003 4004
		if (!req->r_linger) {
			if (!req->r_t.paused)
				send_request(req);
4005 4006
		} else {
			cancel_linger_request(req);
4007 4008
		}
	}
4009 4010 4011 4012 4013 4014
	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);
	}
4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038
}

/*
 * 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
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 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295
struct MOSDBackoff {
	struct ceph_spg spgid;
	u32 map_epoch;
	u8 op;
	u64 id;
	struct ceph_hobject_id *begin;
	struct ceph_hobject_id *end;
};

static int decode_MOSDBackoff(const struct ceph_msg *msg, struct MOSDBackoff *m)
{
	void *p = msg->front.iov_base;
	void *const end = p + msg->front.iov_len;
	u8 struct_v;
	u32 struct_len;
	int ret;

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

	ret = ceph_decode_pgid(&p, end, &m->spgid.pgid);
	if (ret)
		return ret;

	ceph_decode_8_safe(&p, end, m->spgid.shard, e_inval);
	ceph_decode_32_safe(&p, end, m->map_epoch, e_inval);
	ceph_decode_8_safe(&p, end, m->op, e_inval);
	ceph_decode_64_safe(&p, end, m->id, e_inval);

	m->begin = kzalloc(sizeof(*m->begin), GFP_NOIO);
	if (!m->begin)
		return -ENOMEM;

	ret = decode_hoid(&p, end, m->begin);
	if (ret) {
		free_hoid(m->begin);
		return ret;
	}

	m->end = kzalloc(sizeof(*m->end), GFP_NOIO);
	if (!m->end) {
		free_hoid(m->begin);
		return -ENOMEM;
	}

	ret = decode_hoid(&p, end, m->end);
	if (ret) {
		free_hoid(m->begin);
		free_hoid(m->end);
		return ret;
	}

	return 0;

e_inval:
	return -EINVAL;
}

static struct ceph_msg *create_backoff_message(
				const struct ceph_osd_backoff *backoff,
				u32 map_epoch)
{
	struct ceph_msg *msg;
	void *p, *end;
	int msg_size;

	msg_size = CEPH_ENCODING_START_BLK_LEN +
			CEPH_PGID_ENCODING_LEN + 1; /* spgid */
	msg_size += 4 + 1 + 8; /* map_epoch, op, id */
	msg_size += CEPH_ENCODING_START_BLK_LEN +
			hoid_encoding_size(backoff->begin);
	msg_size += CEPH_ENCODING_START_BLK_LEN +
			hoid_encoding_size(backoff->end);

	msg = ceph_msg_new(CEPH_MSG_OSD_BACKOFF, msg_size, GFP_NOIO, true);
	if (!msg)
		return NULL;

	p = msg->front.iov_base;
	end = p + msg->front_alloc_len;

	encode_spgid(&p, &backoff->spgid);
	ceph_encode_32(&p, map_epoch);
	ceph_encode_8(&p, CEPH_OSD_BACKOFF_OP_ACK_BLOCK);
	ceph_encode_64(&p, backoff->id);
	encode_hoid(&p, end, backoff->begin);
	encode_hoid(&p, end, backoff->end);
	BUG_ON(p != end);

	msg->front.iov_len = p - msg->front.iov_base;
	msg->hdr.version = cpu_to_le16(1); /* MOSDBackoff v1 */
	msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);

	return msg;
}

static void handle_backoff_block(struct ceph_osd *osd, struct MOSDBackoff *m)
{
	struct ceph_spg_mapping *spg;
	struct ceph_osd_backoff *backoff;
	struct ceph_msg *msg;

	dout("%s osd%d spgid %llu.%xs%d id %llu\n", __func__, osd->o_osd,
	     m->spgid.pgid.pool, m->spgid.pgid.seed, m->spgid.shard, m->id);

	spg = lookup_spg_mapping(&osd->o_backoff_mappings, &m->spgid);
	if (!spg) {
		spg = alloc_spg_mapping();
		if (!spg) {
			pr_err("%s failed to allocate spg\n", __func__);
			return;
		}
		spg->spgid = m->spgid; /* struct */
		insert_spg_mapping(&osd->o_backoff_mappings, spg);
	}

	backoff = alloc_backoff();
	if (!backoff) {
		pr_err("%s failed to allocate backoff\n", __func__);
		return;
	}
	backoff->spgid = m->spgid; /* struct */
	backoff->id = m->id;
	backoff->begin = m->begin;
	m->begin = NULL; /* backoff now owns this */
	backoff->end = m->end;
	m->end = NULL;   /* ditto */

	insert_backoff(&spg->backoffs, backoff);
	insert_backoff_by_id(&osd->o_backoffs_by_id, backoff);

	/*
	 * Ack with original backoff's epoch so that the OSD can
	 * discard this if there was a PG split.
	 */
	msg = create_backoff_message(backoff, m->map_epoch);
	if (!msg) {
		pr_err("%s failed to allocate msg\n", __func__);
		return;
	}
	ceph_con_send(&osd->o_con, msg);
}

static bool target_contained_by(const struct ceph_osd_request_target *t,
				const struct ceph_hobject_id *begin,
				const struct ceph_hobject_id *end)
{
	struct ceph_hobject_id hoid;
	int cmp;

	hoid_fill_from_target(&hoid, t);
	cmp = hoid_compare(&hoid, begin);
	return !cmp || (cmp > 0 && hoid_compare(&hoid, end) < 0);
}

static void handle_backoff_unblock(struct ceph_osd *osd,
				   const struct MOSDBackoff *m)
{
	struct ceph_spg_mapping *spg;
	struct ceph_osd_backoff *backoff;
	struct rb_node *n;

	dout("%s osd%d spgid %llu.%xs%d id %llu\n", __func__, osd->o_osd,
	     m->spgid.pgid.pool, m->spgid.pgid.seed, m->spgid.shard, m->id);

	backoff = lookup_backoff_by_id(&osd->o_backoffs_by_id, m->id);
	if (!backoff) {
		pr_err("%s osd%d spgid %llu.%xs%d id %llu backoff dne\n",
		       __func__, osd->o_osd, m->spgid.pgid.pool,
		       m->spgid.pgid.seed, m->spgid.shard, m->id);
		return;
	}

	if (hoid_compare(backoff->begin, m->begin) &&
	    hoid_compare(backoff->end, m->end)) {
		pr_err("%s osd%d spgid %llu.%xs%d id %llu bad range?\n",
		       __func__, osd->o_osd, m->spgid.pgid.pool,
		       m->spgid.pgid.seed, m->spgid.shard, m->id);
		/* unblock it anyway... */
	}

	spg = lookup_spg_mapping(&osd->o_backoff_mappings, &backoff->spgid);
	BUG_ON(!spg);

	erase_backoff(&spg->backoffs, backoff);
	erase_backoff_by_id(&osd->o_backoffs_by_id, backoff);
	free_backoff(backoff);

	if (RB_EMPTY_ROOT(&spg->backoffs)) {
		erase_spg_mapping(&osd->o_backoff_mappings, spg);
		free_spg_mapping(spg);
	}

	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);

		if (!ceph_spg_compare(&req->r_t.spgid, &m->spgid)) {
			/*
			 * Match against @m, not @backoff -- the PG may
			 * have split on the OSD.
			 */
			if (target_contained_by(&req->r_t, m->begin, m->end)) {
				/*
				 * If no other installed backoff applies,
				 * resend.
				 */
				send_request(req);
			}
		}
	}
}

static void handle_backoff(struct ceph_osd *osd, struct ceph_msg *msg)
{
	struct ceph_osd_client *osdc = osd->o_osdc;
	struct MOSDBackoff m;
	int ret;

	down_read(&osdc->lock);
	if (!osd_registered(osd)) {
		dout("%s osd%d unknown\n", __func__, osd->o_osd);
		up_read(&osdc->lock);
		return;
	}
	WARN_ON(osd->o_osd != le64_to_cpu(msg->hdr.src.num));

	mutex_lock(&osd->lock);
	ret = decode_MOSDBackoff(msg, &m);
	if (ret) {
		pr_err("failed to decode MOSDBackoff: %d\n", ret);
		ceph_msg_dump(msg);
		goto out_unlock;
	}

	switch (m.op) {
	case CEPH_OSD_BACKOFF_OP_BLOCK:
		handle_backoff_block(osd, &m);
		break;
	case CEPH_OSD_BACKOFF_OP_UNBLOCK:
		handle_backoff_unblock(osd, &m);
		break;
	default:
		pr_err("%s osd%d unknown op %d\n", __func__, osd->o_osd, m.op);
	}

	free_hoid(m.begin);
	free_hoid(m.end);

out_unlock:
	mutex_unlock(&osd->lock);
	up_read(&osdc->lock);
}

4296 4297 4298
/*
 * Process osd watch notifications
 */
4299 4300
static void handle_watch_notify(struct ceph_osd_client *osdc,
				struct ceph_msg *msg)
4301
{
4302 4303 4304 4305 4306 4307 4308
	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;
4309
	s32 return_code = 0;
4310 4311
	void *payload = NULL;
	u32 payload_len = 0;
4312 4313 4314 4315

	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);
4316
	p += 8; /* skip ver */
4317 4318
	ceph_decode_64_safe(&p, end, notify_id, bad);

4319 4320 4321 4322 4323 4324 4325 4326
	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)
4327
		ceph_decode_32_safe(&p, end, return_code, bad);
4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340

	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);
4341 4342
	dout("%s opcode %d cookie %llu lreq %p is_watch %d\n", __func__,
	     opcode, cookie, lreq, lreq->is_watch);
4343 4344 4345 4346 4347
	if (opcode == CEPH_WATCH_EVENT_DISCONNECT) {
		if (!lreq->last_error) {
			lreq->last_error = -ENOTCONN;
			queue_watch_error(lreq);
		}
4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372
	} 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);
		}
4373 4374 4375 4376 4377 4378
	} 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;
4379 4380
		}

4381 4382 4383 4384 4385 4386
		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);
4387
	}
4388

4389 4390 4391 4392
out_unlock_lreq:
	mutex_unlock(&lreq->lock);
out_unlock_osdc:
	up_read(&osdc->lock);
4393 4394 4395 4396 4397 4398
	return;

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

4399 4400 4401 4402 4403 4404 4405
/*
 * Register request, send initial attempt.
 */
int ceph_osdc_start_request(struct ceph_osd_client *osdc,
			    struct ceph_osd_request *req,
			    bool nofail)
{
4406 4407 4408
	down_read(&osdc->lock);
	submit_request(req, false);
	up_read(&osdc->lock);
4409

4410
	return 0;
S
Sage Weil 已提交
4411
}
4412
EXPORT_SYMBOL(ceph_osdc_start_request);
S
Sage Weil 已提交
4413

4414
/*
4415 4416
 * Unregister a registered request.  The request is not completed:
 * ->r_result isn't set and __complete_request() isn't called.
4417 4418 4419 4420 4421
 */
void ceph_osdc_cancel_request(struct ceph_osd_request *req)
{
	struct ceph_osd_client *osdc = req->r_osdc;

4422 4423 4424 4425
	down_write(&osdc->lock);
	if (req->r_osd)
		cancel_request(req);
	up_write(&osdc->lock);
4426 4427 4428
}
EXPORT_SYMBOL(ceph_osdc_cancel_request);

S
Sage Weil 已提交
4429
/*
I
Ilya Dryomov 已提交
4430
 * @timeout: in jiffies, 0 means "wait forever"
S
Sage Weil 已提交
4431
 */
I
Ilya Dryomov 已提交
4432 4433
static int wait_request_timeout(struct ceph_osd_request *req,
				unsigned long timeout)
S
Sage Weil 已提交
4434
{
I
Ilya Dryomov 已提交
4435
	long left;
4436

I
Ilya Dryomov 已提交
4437
	dout("%s req %p tid %llu\n", __func__, req, req->r_tid);
4438
	left = wait_for_completion_killable_timeout(&req->r_completion,
I
Ilya Dryomov 已提交
4439 4440 4441
						ceph_timeout_jiffies(timeout));
	if (left <= 0) {
		left = left ?: -ETIMEDOUT;
4442
		ceph_osdc_cancel_request(req);
I
Ilya Dryomov 已提交
4443 4444
	} else {
		left = req->r_result; /* completed */
S
Sage Weil 已提交
4445 4446
	}

I
Ilya Dryomov 已提交
4447 4448 4449 4450 4451 4452 4453 4454 4455 4456
	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
4457
}
4458
EXPORT_SYMBOL(ceph_osdc_wait_request);
S
Sage Weil 已提交
4459 4460 4461 4462 4463 4464

/*
 * sync - wait for all in-flight requests to flush.  avoid starvation.
 */
void ceph_osdc_sync(struct ceph_osd_client *osdc)
{
4465 4466
	struct rb_node *n, *p;
	u64 last_tid = atomic64_read(&osdc->last_tid);
S
Sage Weil 已提交
4467

4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482
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
4483

4484 4485 4486 4487 4488
			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
4489
			wait_for_completion(&req->r_completion);
4490 4491 4492
			ceph_osdc_put_request(req);
			goto again;
		}
S
Sage Weil 已提交
4493

4494
		mutex_unlock(&osd->lock);
S
Sage Weil 已提交
4495
	}
4496 4497 4498

	up_read(&osdc->lock);
	dout("%s done last_tid %llu\n", __func__, last_tid);
S
Sage Weil 已提交
4499
}
4500
EXPORT_SYMBOL(ceph_osdc_sync);
S
Sage Weil 已提交
4501

4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539
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);

4540
	lreq->is_watch = true;
4541 4542 4543
	lreq->wcb = wcb;
	lreq->errcb = errcb;
	lreq->data = data;
4544
	lreq->watch_valid_thru = jiffies;
4545 4546 4547

	ceph_oid_copy(&lreq->t.base_oid, oid);
	ceph_oloc_copy(&lreq->t.base_oloc, oloc);
4548
	lreq->t.flags = CEPH_OSD_FLAG_WRITE;
4549
	ktime_get_real_ts(&lreq->mtime);
4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605

	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);
4606
	req->r_flags = CEPH_OSD_FLAG_WRITE;
4607
	ktime_get_real_ts(&req->r_mtime);
4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695
	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);

4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805
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);

4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839
/*
 * 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;
}

4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947
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);

4948 4949 4950 4951
/*
 * 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
4952
void ceph_osdc_flush_notifies(struct ceph_osd_client *osdc)
4953
{
4954
	dout("%s osdc %p\n", __func__, osdc);
4955 4956 4957 4958
	flush_workqueue(osdc->notify_wq);
}
EXPORT_SYMBOL(ceph_osdc_flush_notifies);

4959 4960 4961 4962 4963 4964 4965
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);
4966

4967 4968 4969 4970
/*
 * Execute an OSD class method on an object.
 *
 * @flags: CEPH_OSD_FLAG_*
4971
 * @resp_len: in/out param for reply length
4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983
 */
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;

4984 4985 4986
	if (req_len > PAGE_SIZE || (resp_page && *resp_len > PAGE_SIZE))
		return -E2BIG;

4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998
	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;

4999 5000 5001 5002
	ret = osd_req_op_cls_init(req, 0, CEPH_OSD_OP_CALL, class, method);
	if (ret)
		goto out_put_req;

5003 5004 5005 5006 5007
	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,
5008
						   *resp_len, 0, false, false);
5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023

	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
5024 5025 5026 5027 5028 5029 5030 5031 5032
/*
 * init, shutdown
 */
int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client)
{
	int err;

	dout("init\n");
	osdc->client = client;
5033
	init_rwsem(&osdc->lock);
S
Sage Weil 已提交
5034
	osdc->osds = RB_ROOT;
5035
	INIT_LIST_HEAD(&osdc->osd_lru);
5036
	spin_lock_init(&osdc->osd_lru_lock);
5037 5038 5039
	osd_init(&osdc->homeless_osd);
	osdc->homeless_osd.o_osdc = osdc;
	osdc->homeless_osd.o_osd = CEPH_HOMELESS_OSD;
5040
	osdc->last_linger_id = CEPH_LINGER_ID_START;
5041
	osdc->linger_requests = RB_ROOT;
I
Ilya Dryomov 已提交
5042 5043
	osdc->map_checks = RB_ROOT;
	osdc->linger_map_checks = RB_ROOT;
S
Sage Weil 已提交
5044
	INIT_DELAYED_WORK(&osdc->timeout_work, handle_timeout);
5045 5046
	INIT_DELAYED_WORK(&osdc->osds_timeout_work, handle_osds_timeout);

5047
	err = -ENOMEM;
5048 5049 5050 5051
	osdc->osdmap = ceph_osdmap_alloc();
	if (!osdc->osdmap)
		goto out;

5052 5053
	osdc->req_mempool = mempool_create_slab_pool(10,
						     ceph_osd_request_cache);
S
Sage Weil 已提交
5054
	if (!osdc->req_mempool)
5055
		goto out_map;
S
Sage Weil 已提交
5056

5057
	err = ceph_msgpool_init(&osdc->msgpool_op, CEPH_MSG_OSD_OP,
5058
				PAGE_SIZE, 10, true, "osd_op");
S
Sage Weil 已提交
5059
	if (err < 0)
5060
		goto out_mempool;
5061
	err = ceph_msgpool_init(&osdc->msgpool_op_reply, CEPH_MSG_OSD_OPREPLY,
5062
				PAGE_SIZE, 10, true, "osd_op_reply");
S
Sage Weil 已提交
5063 5064
	if (err < 0)
		goto out_msgpool;
5065

5066
	err = -ENOMEM;
5067
	osdc->notify_wq = create_singlethread_workqueue("ceph-watch-notify");
5068
	if (!osdc->notify_wq)
5069 5070
		goto out_msgpool_reply;

5071 5072 5073 5074
	osdc->completion_wq = create_singlethread_workqueue("ceph-completion");
	if (!osdc->completion_wq)
		goto out_notify_wq;

5075 5076
	schedule_delayed_work(&osdc->timeout_work,
			      osdc->client->options->osd_keepalive_timeout);
5077 5078 5079
	schedule_delayed_work(&osdc->osds_timeout_work,
	    round_jiffies_relative(osdc->client->options->osd_idle_ttl));

S
Sage Weil 已提交
5080
	return 0;
5081

5082 5083
out_notify_wq:
	destroy_workqueue(osdc->notify_wq);
5084 5085
out_msgpool_reply:
	ceph_msgpool_destroy(&osdc->msgpool_op_reply);
S
Sage Weil 已提交
5086 5087
out_msgpool:
	ceph_msgpool_destroy(&osdc->msgpool_op);
5088 5089
out_mempool:
	mempool_destroy(osdc->req_mempool);
5090 5091
out_map:
	ceph_osdmap_destroy(osdc->osdmap);
5092 5093
out:
	return err;
S
Sage Weil 已提交
5094 5095 5096 5097
}

void ceph_osdc_stop(struct ceph_osd_client *osdc)
{
5098
	destroy_workqueue(osdc->completion_wq);
5099
	destroy_workqueue(osdc->notify_wq);
S
Sage Weil 已提交
5100
	cancel_delayed_work_sync(&osdc->timeout_work);
5101
	cancel_delayed_work_sync(&osdc->osds_timeout_work);
5102

5103
	down_write(&osdc->lock);
5104 5105 5106
	while (!RB_EMPTY_ROOT(&osdc->osds)) {
		struct ceph_osd *osd = rb_entry(rb_first(&osdc->osds),
						struct ceph_osd, o_node);
5107
		close_osd(osd);
5108
	}
5109
	up_write(&osdc->lock);
5110
	WARN_ON(refcount_read(&osdc->homeless_osd.o_ref) != 1);
5111 5112 5113
	osd_cleanup(&osdc->homeless_osd);

	WARN_ON(!list_empty(&osdc->osd_lru));
5114
	WARN_ON(!RB_EMPTY_ROOT(&osdc->linger_requests));
I
Ilya Dryomov 已提交
5115 5116
	WARN_ON(!RB_EMPTY_ROOT(&osdc->map_checks));
	WARN_ON(!RB_EMPTY_ROOT(&osdc->linger_map_checks));
5117 5118
	WARN_ON(atomic_read(&osdc->num_requests));
	WARN_ON(atomic_read(&osdc->num_homeless));
5119

5120
	ceph_osdmap_destroy(osdc->osdmap);
S
Sage Weil 已提交
5121 5122
	mempool_destroy(osdc->req_mempool);
	ceph_msgpool_destroy(&osdc->msgpool_op);
S
Sage Weil 已提交
5123
	ceph_msgpool_destroy(&osdc->msgpool_op_reply);
S
Sage Weil 已提交
5124 5125 5126 5127 5128 5129 5130 5131 5132 5133
}

/*
 * 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,
5134
			struct page **pages, int num_pages, int page_align)
S
Sage Weil 已提交
5135 5136 5137 5138 5139 5140
{
	struct ceph_osd_request *req;
	int rc = 0;

	dout("readpages on ino %llx.%llx on %llu~%llu\n", vino.ino,
	     vino.snap, off, *plen);
5141
	req = ceph_osdc_new_request(osdc, layout, vino, off, plen, 0, 1,
S
Sage Weil 已提交
5142
				    CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ,
5143
				    NULL, truncate_seq, truncate_size,
5144
				    false);
5145 5146
	if (IS_ERR(req))
		return PTR_ERR(req);
S
Sage Weil 已提交
5147 5148

	/* it may be a short read due to an object boundary */
5149
	osd_req_op_extent_osd_data_pages(req, 0,
5150
				pages, *plen, page_align, false, false);
S
Sage Weil 已提交
5151

5152
	dout("readpages  final extent is %llu~%llu (%llu bytes align %d)\n",
5153
	     off, *plen, *plen, page_align);
S
Sage Weil 已提交
5154 5155 5156 5157 5158 5159 5160 5161 5162

	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;
}
5163
EXPORT_SYMBOL(ceph_osdc_readpages);
S
Sage Weil 已提交
5164 5165 5166 5167 5168 5169 5170 5171 5172 5173

/*
 * 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,
5174
			 struct page **pages, int num_pages)
S
Sage Weil 已提交
5175 5176 5177
{
	struct ceph_osd_request *req;
	int rc = 0;
5178
	int page_align = off & ~PAGE_MASK;
S
Sage Weil 已提交
5179

5180
	req = ceph_osdc_new_request(osdc, layout, vino, off, &len, 0, 1,
5181
				    CEPH_OSD_OP_WRITE, CEPH_OSD_FLAG_WRITE,
5182
				    snapc, truncate_seq, truncate_size,
5183
				    true);
5184 5185
	if (IS_ERR(req))
		return PTR_ERR(req);
S
Sage Weil 已提交
5186 5187

	/* it may be a short write due to an object boundary */
5188
	osd_req_op_extent_osd_data_pages(req, 0, pages, len, page_align,
5189 5190
				false, false);
	dout("writepages %llu~%llu (%llu bytes)\n", off, len, len);
S
Sage Weil 已提交
5191

5192
	req->r_mtime = *mtime;
5193
	rc = ceph_osdc_start_request(osdc, req, true);
S
Sage Weil 已提交
5194 5195 5196 5197 5198 5199 5200 5201 5202
	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;
}
5203
EXPORT_SYMBOL(ceph_osdc_writepages);
S
Sage Weil 已提交
5204

5205
int __init ceph_osdc_setup(void)
5206
{
5207 5208 5209
	size_t size = sizeof(struct ceph_osd_request) +
	    CEPH_OSD_SLAB_OPS * sizeof(struct ceph_osd_req_op);

5210
	BUG_ON(ceph_osd_request_cache);
5211 5212
	ceph_osd_request_cache = kmem_cache_create("ceph_osd_request", size,
						   0, 0, NULL);
5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223

	return ceph_osd_request_cache ? 0 : -ENOMEM;
}

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

S
Sage Weil 已提交
5224 5225 5226 5227 5228 5229
/*
 * handle incoming message
 */
static void dispatch(struct ceph_connection *con, struct ceph_msg *msg)
{
	struct ceph_osd *osd = con->private;
5230
	struct ceph_osd_client *osdc = osd->o_osdc;
S
Sage Weil 已提交
5231 5232 5233 5234 5235 5236 5237
	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:
5238
		handle_reply(osd, msg);
S
Sage Weil 已提交
5239
		break;
5240 5241 5242
	case CEPH_MSG_OSD_BACKOFF:
		handle_backoff(osd, msg);
		break;
5243 5244 5245
	case CEPH_MSG_WATCH_NOTIFY:
		handle_watch_notify(osdc, msg);
		break;
S
Sage Weil 已提交
5246 5247 5248 5249 5250

	default:
		pr_err("received unknown message type %d %s\n", type,
		       ceph_msg_type_name(type));
	}
5251

S
Sage Weil 已提交
5252 5253 5254
	ceph_msg_put(msg);
}

5255
/*
5256 5257 5258
 * 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.
5259 5260
 */
static struct ceph_msg *get_reply(struct ceph_connection *con,
5261 5262
				  struct ceph_msg_header *hdr,
				  int *skip)
S
Sage Weil 已提交
5263 5264 5265
{
	struct ceph_osd *osd = con->private;
	struct ceph_osd_client *osdc = osd->o_osdc;
5266
	struct ceph_msg *m = NULL;
5267
	struct ceph_osd_request *req;
5268
	int front_len = le32_to_cpu(hdr->front_len);
5269
	int data_len = le32_to_cpu(hdr->data_len);
5270
	u64 tid = le64_to_cpu(hdr->tid);
S
Sage Weil 已提交
5271

5272 5273 5274 5275 5276 5277 5278 5279 5280 5281
	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);
5282
	if (!req) {
5283 5284
		dout("%s osd%d tid %llu unknown, skipping\n", __func__,
		     osd->o_osd, tid);
5285
		*skip = 1;
5286
		goto out_unlock_session;
5287
	}
S
Sage Weil 已提交
5288

5289
	ceph_msg_revoke_incoming(req->r_reply);
5290

5291
	if (front_len > req->r_reply->front_alloc_len) {
5292 5293 5294
		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);
5295 5296
		m = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, front_len, GFP_NOFS,
				 false);
5297
		if (!m)
5298
			goto out_unlock_session;
S
Sage Weil 已提交
5299 5300 5301
		ceph_msg_put(req->r_reply);
		req->r_reply = m;
	}
5302

5303 5304 5305 5306 5307 5308
	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;
5309
		goto out_unlock_session;
5310
	}
5311 5312

	m = ceph_msg_get(req->r_reply);
S
Sage Weil 已提交
5313
	dout("get_reply tid %lld %p\n", tid, m);
5314

5315 5316 5317 5318
out_unlock_session:
	mutex_unlock(&osd->lock);
out_unlock_osdc:
	up_read(&osdc->lock);
5319
	return m;
5320 5321
}

5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341
/*
 * 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);
5342
		if (IS_ERR(pages)) {
5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354
			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;
}

5355 5356 5357 5358 5359 5360 5361
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
5362
	*skip = 0;
5363 5364
	switch (type) {
	case CEPH_MSG_OSD_MAP:
5365
	case CEPH_MSG_OSD_BACKOFF:
5366
	case CEPH_MSG_WATCH_NOTIFY:
5367
		return alloc_msg_with_page_vector(hdr);
5368 5369 5370
	case CEPH_MSG_OSD_OPREPLY:
		return get_reply(con, hdr, skip);
	default:
5371 5372
		pr_warn("%s osd%d unknown msg type %d, skipping\n", __func__,
			osd->o_osd, type);
5373 5374 5375
		*skip = 1;
		return NULL;
	}
S
Sage Weil 已提交
5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394
}

/*
 * 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);
}

5395 5396 5397
/*
 * authentication
 */
5398 5399 5400 5401 5402
/*
 * 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,
5403
					int *proto, int force_new)
5404 5405 5406 5407
{
	struct ceph_osd *o = con->private;
	struct ceph_osd_client *osdc = o->o_osdc;
	struct ceph_auth_client *ac = osdc->client->monc.auth;
5408
	struct ceph_auth_handshake *auth = &o->o_auth;
5409

5410
	if (force_new && auth->authorizer) {
5411
		ceph_auth_destroy_authorizer(auth->authorizer);
5412 5413
		auth->authorizer = NULL;
	}
5414 5415 5416
	if (!auth->authorizer) {
		int ret = ceph_auth_create_authorizer(ac, CEPH_ENTITY_TYPE_OSD,
						      auth);
5417
		if (ret)
5418
			return ERR_PTR(ret);
5419 5420
	} else {
		int ret = ceph_auth_update_authorizer(ac, CEPH_ENTITY_TYPE_OSD,
5421 5422 5423
						     auth);
		if (ret)
			return ERR_PTR(ret);
5424 5425
	}
	*proto = ac->protocol;
5426

5427
	return auth;
5428 5429 5430
}


5431
static int verify_authorizer_reply(struct ceph_connection *con)
5432 5433 5434 5435 5436
{
	struct ceph_osd *o = con->private;
	struct ceph_osd_client *osdc = o->o_osdc;
	struct ceph_auth_client *ac = osdc->client->monc.auth;

5437
	return ceph_auth_verify_authorizer_reply(ac, o->o_auth.authorizer);
5438 5439
}

5440 5441 5442 5443 5444 5445
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;

5446
	ceph_auth_invalidate_authorizer(ac, CEPH_ENTITY_TYPE_OSD);
5447 5448
	return ceph_monc_validate_auth(&osdc->client->monc);
}
5449

5450 5451
static void osd_reencode_message(struct ceph_msg *msg)
{
5452 5453 5454 5455
	int type = le16_to_cpu(msg->hdr.type);

	if (type == CEPH_MSG_OSD_OP)
		encode_request_finish(msg);
5456 5457
}

5458
static int osd_sign_message(struct ceph_msg *msg)
Y
Yan, Zheng 已提交
5459
{
5460
	struct ceph_osd *o = msg->con->private;
Y
Yan, Zheng 已提交
5461
	struct ceph_auth_handshake *auth = &o->o_auth;
5462

Y
Yan, Zheng 已提交
5463 5464 5465
	return ceph_auth_sign_message(auth, msg);
}

5466
static int osd_check_message_signature(struct ceph_msg *msg)
Y
Yan, Zheng 已提交
5467
{
5468
	struct ceph_osd *o = msg->con->private;
Y
Yan, Zheng 已提交
5469
	struct ceph_auth_handshake *auth = &o->o_auth;
5470

Y
Yan, Zheng 已提交
5471 5472 5473
	return ceph_auth_check_message_signature(auth, msg);
}

5474
static const struct ceph_connection_operations osd_con_ops = {
S
Sage Weil 已提交
5475 5476 5477
	.get = get_osd_con,
	.put = put_osd_con,
	.dispatch = dispatch,
5478 5479
	.get_authorizer = get_authorizer,
	.verify_authorizer_reply = verify_authorizer_reply,
5480
	.invalidate_authorizer = invalidate_authorizer,
S
Sage Weil 已提交
5481
	.alloc_msg = alloc_msg,
5482
	.reencode_message = osd_reencode_message,
5483 5484
	.sign_message = osd_sign_message,
	.check_message_signature = osd_check_message_signature,
5485
	.fault = osd_fault,
S
Sage Weil 已提交
5486
};