osd_client.c 104.0 KB
Newer Older
1

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

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

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

S
Sage Weil 已提交
22
#define OSD_OPREPLY_FRONT_LEN	512
23

24 25
static struct kmem_cache	*ceph_osd_request_cache;

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

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

46 47
static void link_request(struct ceph_osd *osd, struct ceph_osd_request *req);
static void unlink_request(struct ceph_osd *osd, struct ceph_osd_request *req);
48 49 50 51
static void link_linger(struct ceph_osd *osd,
			struct ceph_osd_linger_request *lreq);
static void unlink_linger(struct ceph_osd *osd,
			  struct ceph_osd_linger_request *lreq);
52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363
/*
 * 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;
}

364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386
static void target_copy(struct ceph_osd_request_target *dest,
			const struct ceph_osd_request_target *src)
{
	ceph_oid_copy(&dest->base_oid, &src->base_oid);
	ceph_oloc_copy(&dest->base_oloc, &src->base_oloc);
	ceph_oid_copy(&dest->target_oid, &src->target_oid);
	ceph_oloc_copy(&dest->target_oloc, &src->target_oloc);

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

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

	dest->osd = src->osd;
}

387 388 389 390 391 392
static void target_destroy(struct ceph_osd_request_target *t)
{
	ceph_oid_destroy(&t->base_oid);
	ceph_oid_destroy(&t->target_oid);
}

S
Sage Weil 已提交
393 394 395
/*
 * requests
 */
396 397 398 399 400 401 402
static void request_release_checks(struct ceph_osd_request *req)
{
	WARN_ON(!RB_EMPTY_NODE(&req->r_node));
	WARN_ON(!list_empty(&req->r_unsafe_item));
	WARN_ON(req->r_osd);
}

403
static void ceph_osdc_release_request(struct kref *kref)
S
Sage Weil 已提交
404
{
405 406
	struct ceph_osd_request *req = container_of(kref,
					    struct ceph_osd_request, r_kref);
407
	unsigned int which;
S
Sage Weil 已提交
408

409 410
	dout("%s %p (r_request %p r_reply %p)\n", __func__, req,
	     req->r_request, req->r_reply);
411
	request_release_checks(req);
412

S
Sage Weil 已提交
413 414
	if (req->r_request)
		ceph_msg_put(req->r_request);
415
	if (req->r_reply)
416
		ceph_msg_put(req->r_reply);
417

418 419
	for (which = 0; which < req->r_num_ops; which++)
		osd_req_op_data_release(req, which);
420

421
	target_destroy(&req->r_t);
S
Sage Weil 已提交
422
	ceph_put_snap_context(req->r_snapc);
423

S
Sage Weil 已提交
424 425
	if (req->r_mempool)
		mempool_free(req, req->r_osdc->req_mempool);
426
	else if (req->r_num_ops <= CEPH_OSD_SLAB_OPS)
427
		kmem_cache_free(ceph_osd_request_cache, req);
428 429
	else
		kfree(req);
S
Sage Weil 已提交
430
}
431 432 433 434 435 436 437 438 439 440 441

void ceph_osdc_get_request(struct ceph_osd_request *req)
{
	dout("%s %p (was %d)\n", __func__, req,
	     atomic_read(&req->r_kref.refcount));
	kref_get(&req->r_kref);
}
EXPORT_SYMBOL(ceph_osdc_get_request);

void ceph_osdc_put_request(struct ceph_osd_request *req)
{
442 443 444 445 446
	if (req) {
		dout("%s %p (was %d)\n", __func__, req,
		     atomic_read(&req->r_kref.refcount));
		kref_put(&req->r_kref, ceph_osdc_release_request);
	}
447 448
}
EXPORT_SYMBOL(ceph_osdc_put_request);
449

450 451 452 453 454 455 456 457 458 459 460 461 462 463
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);
	init_completion(&req->r_safe_completion);
	RB_CLEAR_NODE(&req->r_node);
	INIT_LIST_HEAD(&req->r_unsafe_item);

	target_init(&req->r_t);
}

464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500
/*
 * 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);
	WARN_ON(atomic_read(&req->r_kref.refcount) != 1);
	request_release_checks(req);

	WARN_ON(atomic_read(&request_msg->kref.refcount) != 1);
	WARN_ON(atomic_read(&reply_msg->kref.refcount) != 1);
	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;
}

501
struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
S
Sage Weil 已提交
502
					       struct ceph_snap_context *snapc,
503
					       unsigned int num_ops,
504
					       bool use_mempool,
505
					       gfp_t gfp_flags)
S
Sage Weil 已提交
506 507
{
	struct ceph_osd_request *req;
508

S
Sage Weil 已提交
509
	if (use_mempool) {
510
		BUG_ON(num_ops > CEPH_OSD_SLAB_OPS);
511
		req = mempool_alloc(osdc->req_mempool, gfp_flags);
512 513
	} else if (num_ops <= CEPH_OSD_SLAB_OPS) {
		req = kmem_cache_alloc(ceph_osd_request_cache, gfp_flags);
S
Sage Weil 已提交
514
	} else {
515 516 517
		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
518
	}
519
	if (unlikely(!req))
520
		return NULL;
S
Sage Weil 已提交
521

522
	request_init(req);
S
Sage Weil 已提交
523 524
	req->r_osdc = osdc;
	req->r_mempool = use_mempool;
525
	req->r_num_ops = num_ops;
526 527
	req->r_snapid = CEPH_NOSNAP;
	req->r_snapc = ceph_get_snap_context(snapc);
528

529 530 531 532
	dout("%s req %p\n", __func__, req);
	return req;
}
EXPORT_SYMBOL(ceph_osdc_alloc_request);
533

534 535 536 537 538
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
539

540 541
	WARN_ON(ceph_oid_empty(&req->r_base_oid));

542
	/* create request message */
543 544 545 546
	msg_size = 4 + 4 + 4; /* client_inc, osdmap_epoch, flags */
	msg_size += 4 + 4 + 4 + 8; /* mtime, reassert_version */
	msg_size += 2 + 4 + 8 + 4 + 4; /* oloc */
	msg_size += 1 + 8 + 4 + 4; /* pgid */
547 548
	msg_size += 4 + req->r_base_oid.name_len; /* oid */
	msg_size += 2 + req->r_num_ops * sizeof(struct ceph_osd_op);
549 550
	msg_size += 8; /* snapid */
	msg_size += 8; /* snap_seq */
551
	msg_size += 4 + 8 * (req->r_snapc ? req->r_snapc->num_snaps : 0);
552 553
	msg_size += 4; /* retry_attempt */

554
	if (req->r_mempool)
555
		msg = ceph_msgpool_get(&osdc->msgpool_op, 0);
S
Sage Weil 已提交
556
	else
557 558 559
		msg = ceph_msg_new(CEPH_MSG_OSD_OP, msg_size, gfp, true);
	if (!msg)
		return -ENOMEM;
560

S
Sage Weil 已提交
561
	memset(msg->front.iov_base, 0, msg->front.iov_len);
562 563
	req->r_request = msg;

564 565
	/* create reply message */
	msg_size = OSD_OPREPLY_FRONT_LEN;
566 567
	msg_size += req->r_base_oid.name_len;
	msg_size += req->r_num_ops * sizeof(struct ceph_osd_op);
568 569 570 571 572 573 574 575 576 577 578

	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;
579
}
580
EXPORT_SYMBOL(ceph_osdc_alloc_messages);
581

582
static bool osd_req_opcode_valid(u16 opcode)
583
{
584
	switch (opcode) {
585 586 587
#define GENERATE_CASE(op, opcode, str)	case CEPH_OSD_OP_##op: return true;
__CEPH_FORALL_OSD_OPS(GENERATE_CASE)
#undef GENERATE_CASE
588 589 590 591 592
	default:
		return false;
	}
}

593 594 595 596 597
/*
 * 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.
 */
598
static struct ceph_osd_req_op *
A
Alex Elder 已提交
599
_osd_req_op_init(struct ceph_osd_request *osd_req, unsigned int which,
600
		 u16 opcode, u32 flags)
601
{
602 603 604
	struct ceph_osd_req_op *op;

	BUG_ON(which >= osd_req->r_num_ops);
605 606
	BUG_ON(!osd_req_opcode_valid(opcode));

607
	op = &osd_req->r_ops[which];
608 609
	memset(op, 0, sizeof (*op));
	op->op = opcode;
610
	op->flags = flags;
611 612

	return op;
613 614
}

A
Alex Elder 已提交
615
void osd_req_op_init(struct ceph_osd_request *osd_req,
616
		     unsigned int which, u16 opcode, u32 flags)
A
Alex Elder 已提交
617
{
618
	(void)_osd_req_op_init(osd_req, which, opcode, flags);
A
Alex Elder 已提交
619 620 621
}
EXPORT_SYMBOL(osd_req_op_init);

622 623
void osd_req_op_extent_init(struct ceph_osd_request *osd_req,
				unsigned int which, u16 opcode,
624 625 626
				u64 offset, u64 length,
				u64 truncate_size, u32 truncate_seq)
{
627 628
	struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
						      opcode, 0);
629 630
	size_t payload_len = 0;

L
Li Wang 已提交
631
	BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE &&
632 633
	       opcode != CEPH_OSD_OP_WRITEFULL && opcode != CEPH_OSD_OP_ZERO &&
	       opcode != CEPH_OSD_OP_TRUNCATE);
634 635 636 637 638

	op->extent.offset = offset;
	op->extent.length = length;
	op->extent.truncate_size = truncate_size;
	op->extent.truncate_seq = truncate_seq;
639
	if (opcode == CEPH_OSD_OP_WRITE || opcode == CEPH_OSD_OP_WRITEFULL)
640 641
		payload_len += length;

642
	op->indata_len = payload_len;
643 644 645
}
EXPORT_SYMBOL(osd_req_op_extent_init);

646 647
void osd_req_op_extent_update(struct ceph_osd_request *osd_req,
				unsigned int which, u64 length)
648
{
649 650 651 652 653 654
	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;
655 656 657 658 659 660

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

	op->extent.length = length;
661
	op->indata_len -= previous - length;
662 663 664
}
EXPORT_SYMBOL(osd_req_op_extent_update);

665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686
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);

687
void osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which,
688
			u16 opcode, const char *class, const char *method)
689
{
690 691
	struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
						      opcode, 0);
692
	struct ceph_pagelist *pagelist;
693 694 695 696 697
	size_t payload_len = 0;
	size_t size;

	BUG_ON(opcode != CEPH_OSD_OP_CALL);

698 699 700 701
	pagelist = kmalloc(sizeof (*pagelist), GFP_NOFS);
	BUG_ON(!pagelist);
	ceph_pagelist_init(pagelist);

702 703 704 705
	op->cls.class_name = class;
	size = strlen(class);
	BUG_ON(size > (size_t) U8_MAX);
	op->cls.class_len = size;
706
	ceph_pagelist_append(pagelist, class, size);
707 708 709 710 711 712
	payload_len += size;

	op->cls.method_name = method;
	size = strlen(method);
	BUG_ON(size > (size_t) U8_MAX);
	op->cls.method_len = size;
713
	ceph_pagelist_append(pagelist, method, size);
714 715
	payload_len += size;

716
	osd_req_op_cls_request_info_pagelist(osd_req, which, pagelist);
717

718
	op->indata_len = payload_len;
719 720
}
EXPORT_SYMBOL(osd_req_op_cls_init);
721

722 723 724 725
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)
{
726 727
	struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
						      opcode, 0);
728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750
	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);
751
	op->indata_len = payload_len;
752 753 754 755
	return 0;
}
EXPORT_SYMBOL(osd_req_op_xattr_init);

756 757 758 759 760
/*
 * @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)
761
{
762
	struct ceph_osd_req_op *op;
763

764
	op = _osd_req_op_init(req, which, CEPH_OSD_OP_WATCH, 0);
765
	op->watch.cookie = cookie;
766 767
	op->watch.op = watch_opcode;
	op->watch.gen = 0;
768 769
}

770 771 772 773 774 775
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,
776 777
						      CEPH_OSD_OP_SETALLOCHINT,
						      0);
778 779 780 781 782 783 784 785 786 787 788 789 790

	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);

791
static void ceph_osdc_msg_data_add(struct ceph_msg *msg,
792 793 794 795 796 797 798
				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)
799
			ceph_msg_data_add_pages(msg, osd_data->pages,
800 801 802
					length, osd_data->alignment);
	} else if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGELIST) {
		BUG_ON(!length);
803
		ceph_msg_data_add_pagelist(msg, osd_data->pagelist);
804 805
#ifdef CONFIG_BLOCK
	} else if (osd_data->type == CEPH_OSD_DATA_TYPE_BIO) {
806
		ceph_msg_data_add_bio(msg, osd_data->bio, length);
807 808 809 810 811 812
#endif
	} else {
		BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_NONE);
	}
}

813 814
static u32 osd_req_encode_op(struct ceph_osd_op *dst,
			     const struct ceph_osd_req_op *src)
815 816 817 818 819 820 821 822 823 824 825 826
{
	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:
827
	case CEPH_OSD_OP_WRITEFULL:
L
Li Wang 已提交
828 829
	case CEPH_OSD_OP_ZERO:
	case CEPH_OSD_OP_TRUNCATE:
830 831 832 833 834 835 836 837 838 839
		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;
840
		dst->cls.indata_len = cpu_to_le32(src->cls.indata_len);
841 842 843 844 845
		break;
	case CEPH_OSD_OP_STARTSYNC:
		break;
	case CEPH_OSD_OP_WATCH:
		dst->watch.cookie = cpu_to_le64(src->watch.cookie);
846 847 848 849 850
		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:
851
		break;
852 853 854
	case CEPH_OSD_OP_NOTIFY:
		dst->notify.cookie = cpu_to_le64(src->notify.cookie);
		break;
855 856 857 858 859 860
	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;
861 862 863 864 865 866 867
	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;
868 869 870
	case CEPH_OSD_OP_CREATE:
	case CEPH_OSD_OP_DELETE:
		break;
871
	default:
872
		pr_err("unsupported osd opcode %s\n",
873
			ceph_osd_op_name(src->op));
874
		WARN_ON(1);
875 876

		return 0;
877
	}
878

879
	dst->op = cpu_to_le16(src->op);
880
	dst->flags = cpu_to_le32(src->flags);
881
	dst->payload_len = cpu_to_le32(src->indata_len);
882

883
	return src->indata_len;
884 885
}

886 887 888 889 890 891 892 893 894 895 896 897 898 899
/*
 * build new request AND message, calculate layout, and adjust file
 * extent as needed.
 *
 * if the file was recently truncated, we include information about its
 * old and new size so that the object can be updated appropriately.  (we
 * avoid synchronously deleting truncated objects because it's slow.)
 *
 * if @do_sync, include a 'startsync' command so that the osd will flush
 * data quickly.
 */
struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
					       struct ceph_file_layout *layout,
					       struct ceph_vino vino,
900 901
					       u64 off, u64 *plen,
					       unsigned int which, int num_ops,
902 903 904 905
					       int opcode, int flags,
					       struct ceph_snap_context *snapc,
					       u32 truncate_seq,
					       u64 truncate_size,
906
					       bool use_mempool)
907
{
908
	struct ceph_osd_request *req;
909 910 911
	u64 objnum = 0;
	u64 objoff = 0;
	u64 objlen = 0;
912
	int r;
913

L
Li Wang 已提交
914
	BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE &&
915 916
	       opcode != CEPH_OSD_OP_ZERO && opcode != CEPH_OSD_OP_TRUNCATE &&
	       opcode != CEPH_OSD_OP_CREATE && opcode != CEPH_OSD_OP_DELETE);
917

918
	req = ceph_osdc_alloc_request(osdc, snapc, num_ops, use_mempool,
A
Alex Elder 已提交
919
					GFP_NOFS);
920 921 922 923
	if (!req) {
		r = -ENOMEM;
		goto fail;
	}
924

925
	/* calculate max write size */
926
	r = calc_layout(layout, off, plen, &objnum, &objoff, &objlen);
927 928
	if (r)
		goto fail;
929

930
	if (opcode == CEPH_OSD_OP_CREATE || opcode == CEPH_OSD_OP_DELETE) {
931
		osd_req_op_init(req, which, opcode, 0);
932 933 934 935 936 937 938 939 940 941 942
	} else {
		u32 object_size = le32_to_cpu(layout->fl_object_size);
		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;
			}
943
		}
944
		osd_req_op_extent_init(req, which, opcode, objoff, objlen,
945 946
				       truncate_size, truncate_seq);
	}
947

948
	req->r_flags = flags;
949
	req->r_base_oloc.pool = ceph_file_layout_pg_pool(*layout);
950
	ceph_oid_printf(&req->r_base_oid, "%llx.%08llx", vino.ino, objnum);
951

952 953 954 955
	req->r_snapid = vino.snap;
	if (flags & CEPH_OSD_FLAG_WRITE)
		req->r_data_offset = off;

956 957 958 959
	r = ceph_osdc_alloc_messages(req, GFP_NOFS);
	if (r)
		goto fail;

S
Sage Weil 已提交
960
	return req;
961 962 963 964

fail:
	ceph_osdc_put_request(req);
	return ERR_PTR(r);
S
Sage Weil 已提交
965
}
966
EXPORT_SYMBOL(ceph_osdc_new_request);
S
Sage Weil 已提交
967 968 969 970

/*
 * We keep osd requests in an rbtree, sorted by ->r_tid.
 */
I
Ilya Dryomov 已提交
971
DEFINE_RB_FUNCS(request, struct ceph_osd_request, r_tid, r_node)
S
Sage Weil 已提交
972

973 974 975 976 977
static bool osd_homeless(struct ceph_osd *osd)
{
	return osd->o_osd == CEPH_HOMELESS_OSD;
}

978
static bool osd_registered(struct ceph_osd *osd)
S
Sage Weil 已提交
979
{
980
	verify_osdc_locked(osd->o_osdc);
S
Sage Weil 已提交
981

982
	return !RB_EMPTY_NODE(&osd->o_node);
S
Sage Weil 已提交
983 984
}

985 986 987 988 989 990 991
/*
 * Assumes @osd is zero-initialized.
 */
static void osd_init(struct ceph_osd *osd)
{
	atomic_set(&osd->o_ref, 1);
	RB_CLEAR_NODE(&osd->o_node);
992
	osd->o_requests = RB_ROOT;
993
	osd->o_linger_requests = RB_ROOT;
994 995 996
	INIT_LIST_HEAD(&osd->o_osd_lru);
	INIT_LIST_HEAD(&osd->o_keepalive_item);
	osd->o_incarnation = 1;
997
	mutex_init(&osd->lock);
998 999 1000 1001 1002
}

static void osd_cleanup(struct ceph_osd *osd)
{
	WARN_ON(!RB_EMPTY_NODE(&osd->o_node));
1003
	WARN_ON(!RB_EMPTY_ROOT(&osd->o_requests));
1004
	WARN_ON(!RB_EMPTY_ROOT(&osd->o_linger_requests));
1005 1006 1007 1008 1009 1010 1011 1012 1013
	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
1014 1015 1016
/*
 * Track open sessions with osds.
 */
1017
static struct ceph_osd *create_osd(struct ceph_osd_client *osdc, int onum)
S
Sage Weil 已提交
1018 1019 1020
{
	struct ceph_osd *osd;

1021 1022
	WARN_ON(onum == CEPH_HOMELESS_OSD);

1023
	osd = kzalloc(sizeof(*osd), GFP_NOIO | __GFP_NOFAIL);
1024
	osd_init(osd);
S
Sage Weil 已提交
1025
	osd->o_osdc = osdc;
1026
	osd->o_osd = onum;
S
Sage Weil 已提交
1027

1028
	ceph_con_init(&osd->o_con, osd, &osd_con_ops, &osdc->client->msgr);
1029

S
Sage Weil 已提交
1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048
	return osd;
}

static struct ceph_osd *get_osd(struct ceph_osd *osd)
{
	if (atomic_inc_not_zero(&osd->o_ref)) {
		dout("get_osd %p %d -> %d\n", osd, atomic_read(&osd->o_ref)-1,
		     atomic_read(&osd->o_ref));
		return osd;
	} else {
		dout("get_osd %p FAIL\n", osd);
		return NULL;
	}
}

static void put_osd(struct ceph_osd *osd)
{
	dout("put_osd %p %d -> %d\n", osd, atomic_read(&osd->o_ref),
	     atomic_read(&osd->o_ref) - 1);
1049
	if (atomic_dec_and_test(&osd->o_ref)) {
1050
		osd_cleanup(osd);
S
Sage Weil 已提交
1051
		kfree(osd);
S
Sage Weil 已提交
1052
	}
S
Sage Weil 已提交
1053 1054
}

I
Ilya Dryomov 已提交
1055 1056
DEFINE_RB_FUNCS(osd, struct ceph_osd, o_osd, o_node)

1057
static void __move_osd_to_lru(struct ceph_osd *osd)
1058
{
1059 1060 1061
	struct ceph_osd_client *osdc = osd->o_osdc;

	dout("%s osd %p osd%d\n", __func__, osd, osd->o_osd);
1062
	BUG_ON(!list_empty(&osd->o_osd_lru));
1063

1064
	spin_lock(&osdc->osd_lru_lock);
1065
	list_add_tail(&osd->o_osd_lru, &osdc->osd_lru);
1066 1067
	spin_unlock(&osdc->osd_lru_lock);

1068
	osd->lru_ttl = jiffies + osdc->client->options->osd_idle_ttl;
1069 1070
}

1071
static void maybe_move_osd_to_lru(struct ceph_osd *osd)
1072
{
1073
	if (RB_EMPTY_ROOT(&osd->o_requests) &&
1074
	    RB_EMPTY_ROOT(&osd->o_linger_requests))
1075
		__move_osd_to_lru(osd);
1076 1077
}

1078 1079
static void __remove_osd_from_lru(struct ceph_osd *osd)
{
1080 1081 1082 1083 1084
	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);
1085 1086
	if (!list_empty(&osd->o_osd_lru))
		list_del_init(&osd->o_osd_lru);
1087
	spin_unlock(&osdc->osd_lru_lock);
1088 1089
}

1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113
/*
 * 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);
	}
1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124
	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);
	}
1125 1126 1127 1128 1129 1130

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

S
Sage Weil 已提交
1131 1132 1133
/*
 * reset osd connect
 */
1134
static int reopen_osd(struct ceph_osd *osd)
S
Sage Weil 已提交
1135
{
A
Alex Elder 已提交
1136
	struct ceph_entity_addr *peer_addr;
S
Sage Weil 已提交
1137

1138 1139 1140
	dout("%s osd %p osd%d\n", __func__, osd, osd->o_osd);

	if (RB_EMPTY_ROOT(&osd->o_requests) &&
1141
	    RB_EMPTY_ROOT(&osd->o_linger_requests)) {
1142
		close_osd(osd);
A
Alex Elder 已提交
1143 1144 1145
		return -ENODEV;
	}

1146
	peer_addr = &osd->o_osdc->osdmap->osd_addr[osd->o_osd];
A
Alex Elder 已提交
1147 1148
	if (!memcmp(peer_addr, &osd->o_con.peer_addr, sizeof (*peer_addr)) &&
			!ceph_con_opened(&osd->o_con)) {
1149
		struct rb_node *n;
A
Alex Elder 已提交
1150

1151 1152
		dout("osd addr hasn't changed and connection never opened, "
		     "letting msgr retry\n");
1153
		/* touch each r_stamp for handle_timeout()'s benfit */
1154 1155 1156
		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);
1157
			req->r_stamp = jiffies;
1158
		}
A
Alex Elder 已提交
1159 1160

		return -EAGAIN;
S
Sage Weil 已提交
1161
	}
A
Alex Elder 已提交
1162 1163 1164 1165 1166 1167

	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
1168 1169
}

1170 1171
static struct ceph_osd *lookup_create_osd(struct ceph_osd_client *osdc, int o,
					  bool wrlocked)
S
Sage Weil 已提交
1172
{
1173
	struct ceph_osd *osd;
1174

1175 1176 1177 1178
	if (wrlocked)
		verify_osdc_wrlocked(osdc);
	else
		verify_osdc_locked(osdc);
S
Sage Weil 已提交
1179

1180 1181 1182 1183 1184 1185 1186
	if (o != CEPH_HOMELESS_OSD)
		osd = lookup_osd(&osdc->osds, o);
	else
		osd = &osdc->homeless_osd;
	if (!osd) {
		if (!wrlocked)
			return ERR_PTR(-EAGAIN);
1187

1188 1189 1190 1191
		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]);
1192
	}
S
Sage Weil 已提交
1193

1194 1195
	dout("%s osdc %p osd%d -> osd %p\n", __func__, osdc, o, osd);
	return osd;
S
Sage Weil 已提交
1196 1197 1198
}

/*
1199 1200 1201
 * Create request <-> OSD session relation.
 *
 * @req has to be assigned a tid, @osd may be homeless.
S
Sage Weil 已提交
1202
 */
1203
static void link_request(struct ceph_osd *osd, struct ceph_osd_request *req)
S
Sage Weil 已提交
1204
{
1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217
	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
1218 1219
}

1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236
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);
}

1237 1238 1239 1240 1241
static bool __pool_full(struct ceph_pg_pool_info *pi)
{
	return pi->flags & CEPH_POOL_FLAG_FULL;
}

I
Ilya Dryomov 已提交
1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256
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;
}

1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267
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);
}

1268 1269 1270 1271
/*
 * Returns whether a request should be blocked from being sent
 * based on the current osdmap and osd_client settings.
 */
1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395
static bool target_should_be_paused(struct ceph_osd_client *osdc,
				    const struct ceph_osd_request_target *t,
				    struct ceph_pg_pool_info *pi)
{
	bool pauserd = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSERD);
	bool pausewr = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSEWR) ||
		       ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL) ||
		       __pool_full(pi);

	WARN_ON(pi->id != t->base_oloc.pool);
	return (t->flags & CEPH_OSD_FLAG_READ && pauserd) ||
	       (t->flags & CEPH_OSD_FLAG_WRITE && pausewr);
}

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,
					   u32 *last_force_resend,
					   bool any_change)
{
	struct ceph_pg_pool_info *pi;
	struct ceph_pg pgid, last_pgid;
	struct ceph_osds up, acting;
	bool force_resend = false;
	bool need_check_tiering = false;
	bool need_resend = false;
	bool sort_bitwise = ceph_osdmap_flag(osdc->osdmap,
					     CEPH_OSDMAP_SORTBITWISE);
	enum calc_target_result ct_res;
	int ret;

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

	if (osdc->osdmap->epoch == pi->last_force_request_resend) {
		if (last_force_resend &&
		    *last_force_resend < pi->last_force_request_resend) {
			*last_force_resend = pi->last_force_request_resend;
			force_resend = true;
		} else if (!last_force_resend) {
			force_resend = true;
		}
	}
	if (ceph_oid_empty(&t->target_oid) || force_resend) {
		ceph_oid_copy(&t->target_oid, &t->base_oid);
		need_check_tiering = true;
	}
	if (ceph_oloc_empty(&t->target_oloc) || force_resend) {
		ceph_oloc_copy(&t->target_oloc, &t->base_oloc);
		need_check_tiering = true;
	}

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

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

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

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

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

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

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

1396 1397
static void setup_request_data(struct ceph_osd_request *req,
			       struct ceph_msg *msg)
S
Sage Weil 已提交
1398
{
1399 1400 1401 1402 1403
	u32 data_len = 0;
	int i;

	if (!list_empty(&msg->data))
		return;
S
Sage Weil 已提交
1404

1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421
	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;
1422 1423 1424 1425
		case CEPH_OSD_OP_NOTIFY_ACK:
			ceph_osdc_msg_data_add(msg,
					       &op->notify_ack.request_data);
			break;
1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448

		/* 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;

		/* 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;
1449 1450 1451 1452 1453 1454
		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;
1455 1456 1457 1458
		}

		data_len += op->indata_len;
	}
1459

1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498
	WARN_ON(data_len != msg->data_length);
}

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

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

	setup_request_data(req, msg);

	ceph_encode_32(&p, 1); /* client_inc, always 1 */
	ceph_encode_32(&p, req->r_osdc->osdmap->epoch);
	ceph_encode_32(&p, req->r_flags);
	ceph_encode_timespec(p, &req->r_mtime);
	p += sizeof(struct ceph_timespec);
	/* aka reassert_version */
	memcpy(p, &req->r_replay_version, sizeof(req->r_replay_version));
	p += sizeof(req->r_replay_version);

	/* oloc */
	ceph_encode_8(&p, 4);
	ceph_encode_8(&p, 4);
	ceph_encode_32(&p, 8 + 4 + 4);
	ceph_encode_64(&p, req->r_t.target_oloc.pool);
	ceph_encode_32(&p, -1); /* preferred */
	ceph_encode_32(&p, 0); /* key len */

	/* pgid */
	ceph_encode_8(&p, 1);
1499 1500
	ceph_encode_64(&p, req->r_t.pgid.pool);
	ceph_encode_32(&p, req->r_t.pgid.seed);
1501
	ceph_encode_32(&p, -1); /* preferred */
1502

1503 1504 1505 1506
	/* oid */
	ceph_encode_32(&p, req->r_t.target_oid.name_len);
	memcpy(p, req->r_t.target_oid.name, req->r_t.target_oid.name_len);
	p += req->r_t.target_oid.name_len;
S
Sage Weil 已提交
1507

1508 1509 1510 1511 1512 1513
	/* 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);
	}
1514

1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538
	ceph_encode_64(&p, req->r_snapid); /* snapid */
	if (req->r_snapc) {
		ceph_encode_64(&p, req->r_snapc->seq);
		ceph_encode_32(&p, req->r_snapc->num_snaps);
		for (i = 0; i < req->r_snapc->num_snaps; i++)
			ceph_encode_64(&p, req->r_snapc->snaps[i]);
	} else {
		ceph_encode_64(&p, 0); /* snap_seq */
		ceph_encode_32(&p, 0); /* snaps len */
	}

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

	BUG_ON(p > end);
	msg->front.iov_len = p - msg->front.iov_base;
	msg->hdr.version = cpu_to_le16(4); /* MOSDOp v4 */
	msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
	msg->hdr.data_len = cpu_to_le32(data_len);
	/*
	 * The header "data_off" is a hint to the receiver allowing it
	 * to align received data into its buffers such that there's no
	 * need to re-copy it before writing it to disk (direct I/O).
	 */
	msg->hdr.data_off = cpu_to_le16(req->r_data_offset);
1539

1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551
	dout("%s req %p oid %*pE oid_len %d front %zu data %u\n", __func__,
	     req, req->r_t.target_oid.name_len, req->r_t.target_oid.name,
	     req->r_t.target_oid.name_len, msg->front.iov_len, data_len);
}

/*
 * @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;

1552
	verify_osd_locked(osd);
1553 1554
	WARN_ON(osd->o_osd != req->r_t.osd);

1555 1556 1557 1558 1559 1560 1561
	/*
	 * 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);

1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580
	req->r_flags |= CEPH_OSD_FLAG_KNOWN_REDIR;
	if (req->r_attempts)
		req->r_flags |= CEPH_OSD_FLAG_RETRY;
	else
		WARN_ON(req->r_flags & CEPH_OSD_FLAG_RETRY);

	encode_request(req, req->r_request);

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

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

	req->r_sent = osd->o_incarnation;
	req->r_request->hdr.tid = cpu_to_le64(req->r_tid);
	ceph_con_send(&osd->o_con, ceph_msg_get(req->r_request));
S
Sage Weil 已提交
1581 1582
}

I
Ilya Dryomov 已提交
1583 1584 1585 1586
static void maybe_request_map(struct ceph_osd_client *osdc)
{
	bool continuous = false;

1587
	verify_osdc_locked(osdc);
I
Ilya Dryomov 已提交
1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603
	WARN_ON(!osdc->osdmap->epoch);

	if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL) ||
	    ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSERD) ||
	    ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSEWR)) {
		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);
}

1604
static void __submit_request(struct ceph_osd_request *req, bool wrlocked)
1605
{
1606 1607 1608 1609
	struct ceph_osd_client *osdc = req->r_osdc;
	struct ceph_osd *osd;
	bool need_send = false;
	bool promoted = false;
1610

1611 1612 1613 1614 1615 1616 1617 1618 1619
	WARN_ON(req->r_tid || req->r_got_reply);
	dout("%s req %p wrlocked %d\n", __func__, req, wrlocked);

again:
	calc_target(osdc, &req->r_t, &req->r_last_force_resend, false);
	osd = lookup_create_osd(osdc, req->r_t.osd, wrlocked);
	if (IS_ERR(osd)) {
		WARN_ON(PTR_ERR(osd) != -EAGAIN || wrlocked);
		goto promote;
1620 1621
	}

1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642
	if ((req->r_flags & CEPH_OSD_FLAG_WRITE) &&
	    ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSEWR)) {
		dout("req %p pausewr\n", req);
		req->r_t.paused = true;
		maybe_request_map(osdc);
	} else if ((req->r_flags & CEPH_OSD_FLAG_READ) &&
		   ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSERD)) {
		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)) &&
		   (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL) ||
		    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);
	} else if (!osd_homeless(osd)) {
		need_send = true;
1643
	} else {
1644
		maybe_request_map(osdc);
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
	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);
	mutex_unlock(&osd->lock);

	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)
{
	unsigned int mask = CEPH_OSD_FLAG_ACK | CEPH_OSD_FLAG_ONDISK;

	if (req->r_flags & CEPH_OSD_FLAG_READ) {
		WARN_ON(req->r_flags & mask);
		req->r_flags |= CEPH_OSD_FLAG_ACK;
	} else if (req->r_flags & CEPH_OSD_FLAG_WRITE)
		WARN_ON(!(req->r_flags & mask));
	else
		WARN_ON(1);

	WARN_ON(req->r_unsafe_callback && (req->r_flags & mask) != mask);
	atomic_inc(&req->r_osdc->num_requests);
}

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

static void __finish_request(struct ceph_osd_request *req)
{
	struct ceph_osd_client *osdc = req->r_osdc;
	struct ceph_osd *osd = req->r_osd;

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

	unlink_request(osd, req);
	atomic_dec(&osdc->num_requests);

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

static void finish_request(struct ceph_osd_request *req)
{
	__finish_request(req);
	ceph_osdc_put_request(req);
1719 1720
}

1721 1722 1723 1724 1725 1726 1727 1728
static void __complete_request(struct ceph_osd_request *req)
{
	if (req->r_callback)
		req->r_callback(req);
	else
		complete_all(&req->r_completion);
}

1729 1730 1731 1732 1733 1734 1735
static void cancel_request(struct ceph_osd_request *req)
{
	dout("%s req %p tid %llu\n", __func__, req, req->r_tid);

	finish_request(req);
}

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
/*
 * 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));
	WARN_ON(!list_empty(&lreq->scan_item));
	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);
	INIT_LIST_HEAD(&lreq->scan_item);
	init_completion(&lreq->reg_commit_wait);
1787
	init_completion(&lreq->notify_finish_wait);
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 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950

	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)

/*
 * 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;

	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);
	lwork->lreq = linger_get(lreq);

	return lwork;
}

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

	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);
	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;
	}

1951
	WARN_ON(!lreq->is_watch);
1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014
	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);
	WARN_ON(!__linger_registered(lreq));
	linger_reg_commit_complete(lreq, req->r_result);
	lreq->committed = true;

2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032
	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);
		}
	}

2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 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
	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);
2086
	if (lreq->is_watch && lreq->committed) {
2087 2088 2089 2090 2091 2092 2093 2094
		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 {
2095 2096 2097 2098
		if (!lreq->is_watch)
			lreq->notify_id = 0;
		else
			WARN_ON(op->watch.op != CEPH_OSD_WATCH_OP_WATCH);
2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185
		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) {
		if (req->r_result && !lreq->last_error) {
			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];

	if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSERD)) {
		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;

	calc_target(osdc, &lreq->t, &lreq->last_force_resend, false);
	osd = lookup_create_osd(osdc, lreq->t.osd, true);
	link_linger(osd, lreq);

	send_linger(lreq);
}

/*
 * @lreq has to be both registered and linked.
 */
static void __linger_cancel(struct ceph_osd_linger_request *lreq)
{
2186
	if (lreq->is_watch && lreq->ping_req->r_osd)
2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212
		cancel_linger_request(lreq->ping_req);
	if (lreq->reg_req->r_osd)
		cancel_linger_request(lreq->reg_req);
	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);
}

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;
}

2213 2214 2215 2216 2217 2218 2219 2220 2221
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
2222
/*
2223 2224 2225 2226
 * 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
2227 2228 2229 2230 2231
 */
static void handle_timeout(struct work_struct *work)
{
	struct ceph_osd_client *osdc =
		container_of(work, struct ceph_osd_client, timeout_work.work);
2232
	struct ceph_options *opts = osdc->client->options;
2233 2234 2235
	unsigned long cutoff = jiffies - opts->osd_keepalive_timeout;
	LIST_HEAD(slow_osds);
	struct rb_node *n, *p;
S
Sage Weil 已提交
2236

2237 2238
	dout("%s osdc %p\n", __func__, osdc);
	down_write(&osdc->lock);
S
Sage Weil 已提交
2239

2240 2241 2242 2243 2244
	/*
	 * 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).
	 */
2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258
	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;

		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 (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;
			}
		}
2259 2260 2261 2262 2263 2264 2265 2266 2267
		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);
2268
			if (lreq->is_watch && lreq->committed && !lreq->last_error)
2269 2270 2271
				send_linger_ping(lreq);
			mutex_unlock(&lreq->lock);
		}
2272

2273 2274
		if (found)
			list_move_tail(&osd->o_keepalive_item, &slow_osds);
2275
	}
2276 2277 2278 2279

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

2280
	while (!list_empty(&slow_osds)) {
2281 2282 2283
		struct ceph_osd *osd = list_first_entry(&slow_osds,
							struct ceph_osd,
							o_keepalive_item);
2284
		list_del_init(&osd->o_keepalive_item);
S
Sage Weil 已提交
2285 2286 2287
		ceph_con_keepalive(&osd->o_con);
	}

2288
	up_write(&osdc->lock);
2289 2290
	schedule_delayed_work(&osdc->timeout_work,
			      osdc->client->options->osd_keepalive_timeout);
S
Sage Weil 已提交
2291 2292
}

2293 2294 2295 2296 2297
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);
2298
	unsigned long delay = osdc->client->options->osd_idle_ttl / 4;
2299
	struct ceph_osd *osd, *nosd;
2300

2301
	dout("%s osdc %p\n", __func__, osdc);
2302
	down_write(&osdc->lock);
2303 2304 2305 2306
	list_for_each_entry_safe(osd, nosd, &osdc->osd_lru, o_osd_lru) {
		if (time_before(jiffies, osd->lru_ttl))
			break;

2307
		WARN_ON(!RB_EMPTY_ROOT(&osd->o_requests));
2308
		WARN_ON(!RB_EMPTY_ROOT(&osd->o_linger_requests));
2309
		close_osd(osd);
2310
	}
2311

2312
	up_write(&osdc->lock);
2313 2314 2315 2316
	schedule_delayed_work(&osdc->osds_timeout_work,
			      round_jiffies_relative(delay));
}

2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419
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) {
		len = ceph_decode_32(p);
		if (len > 0) {
			pr_warn("ceph_object_locator::nspace is set\n");
			goto e_inval;
		}
	}

	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;
}

2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432
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
2433

2434
static int decode_MOSDOpReply(const struct ceph_msg *msg, struct MOSDOpReply *m)
S
Sage Weil 已提交
2435
{
2436 2437 2438 2439
	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
2440
	u8 decode_redir;
2441 2442 2443
	u32 len;
	int ret;
	int i;
2444

2445 2446 2447
	ceph_decode_32_safe(&p, end, len, e_inval);
	ceph_decode_need(&p, end, len, e_inval);
	p += len; /* skip oid */
2448

2449 2450 2451
	ret = ceph_decode_pgid(&p, end, &m->pgid);
	if (ret)
		return ret;
2452

2453 2454 2455 2456 2457 2458
	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);
2459

2460 2461 2462
	ceph_decode_32_safe(&p, end, m->num_ops, e_inval);
	if (m->num_ops > ARRAY_SIZE(m->outdata_len))
		goto e_inval;
2463

2464 2465 2466
	ceph_decode_need(&p, end, m->num_ops * sizeof(struct ceph_osd_op),
			 e_inval);
	for (i = 0; i < m->num_ops; i++) {
2467 2468
		struct ceph_osd_op *op = p;

2469
		m->outdata_len[i] = le32_to_cpu(op->payload_len);
2470 2471 2472
		p += sizeof(*op);
	}

2473 2474 2475
	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
2476

2477 2478 2479 2480 2481 2482 2483 2484 2485
	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
2486

2487 2488 2489
	if (version >= 6) {
		if (version >= 7)
			ceph_decode_8_safe(&p, end, decode_redir, e_inval);
I
Ilya Dryomov 已提交
2490 2491 2492 2493 2494 2495 2496
		else
			decode_redir = 1;
	} else {
		decode_redir = 0;
	}

	if (decode_redir) {
2497 2498 2499
		ret = ceph_redirect_decode(&p, end, &m->redirect);
		if (ret)
			return ret;
2500
	} else {
2501
		ceph_oloc_init(&m->redirect.oloc);
2502
	}
S
Sage Weil 已提交
2503

2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521
	return 0;

e_inval:
	return -EINVAL;
}

/*
 * We are done with @req if
 *   - @m is a safe reply, or
 *   - @m is an unsafe reply and we didn't want a safe one
 */
static bool done_request(const struct ceph_osd_request *req,
			 const struct MOSDOpReply *m)
{
	return (m->result < 0 ||
		(m->flags & CEPH_OSD_FLAG_ONDISK) ||
		!(req->r_flags & CEPH_OSD_FLAG_ONDISK));
}
2522

2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536
/*
 * handle osd op reply.  either call the callback if it is specified,
 * or do the completion to wake up the waiting thread.
 *
 * ->r_unsafe_callback is set?	yes			no
 *
 * first reply is OK (needed	r_cb/r_completion,	r_cb/r_completion,
 * any or needed/got safe)	r_safe_completion	r_safe_completion
 *
 * first reply is unsafe	r_unsafe_cb(true)	(nothing)
 *
 * when we get the safe reply	r_unsafe_cb(false),	r_cb/r_completion,
 *				r_safe_completion	r_safe_completion
 */
2537
static void handle_reply(struct ceph_osd *osd, struct ceph_msg *msg)
2538
{
2539
	struct ceph_osd_client *osdc = osd->o_osdc;
2540 2541 2542 2543 2544 2545 2546 2547 2548 2549
	struct ceph_osd_request *req;
	struct MOSDOpReply m;
	u64 tid = le64_to_cpu(msg->hdr.tid);
	u32 data_len = 0;
	bool already_acked;
	int ret;
	int i;

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

2550 2551 2552 2553 2554 2555 2556 2557 2558
	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);
2559
	if (!req) {
2560 2561
		dout("%s osd%d tid %llu unknown\n", __func__, osd->o_osd, tid);
		goto out_unlock_session;
2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580
	}

	ret = decode_MOSDOpReply(msg, &m);
	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);
2581
			goto out_unlock_session;
2582 2583 2584 2585 2586 2587 2588 2589
		}
	} 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);
2590 2591
		unlink_request(osd, req);
		mutex_unlock(&osd->lock);
2592

2593
		ceph_oloc_copy(&req->r_t.target_oloc, &m.redirect.oloc);
2594 2595 2596 2597
		req->r_flags |= CEPH_OSD_FLAG_REDIRECTED;
		req->r_tid = 0;
		__submit_request(req, false);
		goto out_unlock_osdc;
2598 2599
	}

2600 2601 2602 2603
	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
2604
	}
2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626
	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;
	}
	dout("%s req %p tid %llu acked %d result %d data_len %u\n", __func__,
	     req, req->r_tid, req->r_got_reply, m.result, data_len);

	already_acked = req->r_got_reply;
	if (!already_acked) {
		req->r_result = m.result ?: data_len;
		req->r_replay_version = m.replay_version; /* struct */
		req->r_got_reply = true;
	} else if (!(m.flags & CEPH_OSD_FLAG_ONDISK)) {
		dout("req %p tid %llu dup ack\n", req, req->r_tid);
2627
		goto out_unlock_session;
2628 2629 2630
	}

	if (done_request(req, &m)) {
2631
		__finish_request(req);
2632 2633
		if (req->r_linger) {
			WARN_ON(req->r_unsafe_callback);
2634 2635
			dout("req %p tid %llu cb (locked)\n", req, req->r_tid);
			__complete_request(req);
2636 2637
		}
	}
S
Sage Weil 已提交
2638

2639 2640
	mutex_unlock(&osd->lock);
	up_read(&osdc->lock);
S
Sage Weil 已提交
2641

2642 2643 2644
	if (done_request(req, &m)) {
		if (already_acked && req->r_unsafe_callback) {
			dout("req %p tid %llu safe-cb\n", req, req->r_tid);
2645
			req->r_unsafe_callback(req, false);
2646
		} else if (!req->r_linger) {
2647 2648 2649 2650 2651 2652 2653 2654 2655 2656
			dout("req %p tid %llu cb\n", req, req->r_tid);
			__complete_request(req);
		}
	} else {
		if (req->r_unsafe_callback) {
			dout("req %p tid %llu unsafe-cb\n", req, req->r_tid);
			req->r_unsafe_callback(req, true);
		} else {
			WARN_ON(1);
		}
2657
	}
2658 2659
	if (m.flags & CEPH_OSD_FLAG_ONDISK)
		complete_all(&req->r_safe_completion);
S
Sage Weil 已提交
2660 2661 2662 2663

	ceph_osdc_put_request(req);
	return;

2664
fail_request:
2665
	req->r_result = -EIO;
2666
	__finish_request(req);
2667 2668
	__complete_request(req);
	complete_all(&req->r_safe_completion);
2669 2670 2671 2672
out_unlock_session:
	mutex_unlock(&osd->lock);
out_unlock_osdc:
	up_read(&osdc->lock);
S
Sage Weil 已提交
2673 2674
}

I
Ilya Dryomov 已提交
2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686
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);
	}
}

2687
static bool pool_cleared_full(struct ceph_osd_client *osdc, s64 pool_id)
S
Sage Weil 已提交
2688
{
2689
	struct ceph_pg_pool_info *pi;
S
Sage Weil 已提交
2690

2691 2692 2693
	pi = ceph_pg_pool_by_id(osdc->osdmap, pool_id);
	if (!pi)
		return false;
S
Sage Weil 已提交
2694

2695
	return pi->was_full && !__pool_full(pi);
2696 2697
}

2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717
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;

	ct_res = calc_target(osdc, &lreq->t, &lreq->last_force_resend, true);
	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;
}

2718
/*
2719
 * Requeue requests whose mapping to an OSD has changed.
2720
 */
2721 2722 2723 2724 2725 2726
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)
2727
{
2728 2729 2730 2731
	struct ceph_osd_client *osdc = osd->o_osdc;
	struct rb_node *n;
	bool force_resend_writes;

2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764
	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:
			/*
			 * 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:
			break;
		}
	}

2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791
	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;

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

		dout("%s req %p tid %llu\n", __func__, req, req->r_tid);
		ct_res = calc_target(osdc, &req->r_t,
				     &req->r_last_force_resend, false);
		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:
			unlink_request(osd, req);
			insert_request(need_resend, req);
			break;
		case CALC_TARGET_POOL_DNE:
			break;
2792
		}
2793
	}
2794
}
2795

I
Ilya Dryomov 已提交
2796
static int handle_one_map(struct ceph_osd_client *osdc,
2797 2798 2799
			  void *p, void *end, bool incremental,
			  struct rb_root *need_resend,
			  struct list_head *need_resend_linger)
I
Ilya Dryomov 已提交
2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844
{
	struct ceph_osdmap *newmap;
	struct rb_node *n;
	bool skipped_map = false;
	bool was_full;

	was_full = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL);
	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;
	}

	was_full &= !ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL);
2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860
	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
2861 2862 2863

	return 0;
}
2864

2865 2866 2867 2868
static void kick_requests(struct ceph_osd_client *osdc,
			  struct rb_root *need_resend,
			  struct list_head *need_resend_linger)
{
2869
	struct ceph_osd_linger_request *lreq, *nlreq;
2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886
	struct rb_node *n;

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

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

		WARN_ON(req->r_osd);
		calc_target(osdc, &req->r_t, NULL, false);
		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);
2887 2888
		} else {
			cancel_linger_request(req);
2889 2890
		}
	}
2891 2892 2893 2894 2895 2896 2897

	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);
	}
2898 2899
}

S
Sage Weil 已提交
2900 2901 2902 2903 2904 2905 2906 2907 2908
/*
 * 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
2909 2910
	void *p = msg->front.iov_base;
	void *const end = p + msg->front.iov_len;
S
Sage Weil 已提交
2911 2912 2913
	u32 nr_maps, maplen;
	u32 epoch;
	struct ceph_fsid fsid;
2914 2915
	struct rb_root need_resend = RB_ROOT;
	LIST_HEAD(need_resend_linger);
I
Ilya Dryomov 已提交
2916 2917 2918 2919
	bool handled_incremental = false;
	bool was_pauserd, was_pausewr;
	bool pauserd, pausewr;
	int err;
S
Sage Weil 已提交
2920

I
Ilya Dryomov 已提交
2921
	dout("%s have %u\n", __func__, osdc->osdmap->epoch);
2922
	down_write(&osdc->lock);
S
Sage Weil 已提交
2923 2924 2925 2926

	/* verify fsid */
	ceph_decode_need(&p, end, sizeof(fsid), bad);
	ceph_decode_copy(&p, &fsid, sizeof(fsid));
2927
	if (ceph_check_fsid(osdc->client, &fsid) < 0)
I
Ilya Dryomov 已提交
2928
		goto bad;
S
Sage Weil 已提交
2929

I
Ilya Dryomov 已提交
2930 2931 2932 2933
	was_pauserd = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSERD);
	was_pausewr = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSEWR) ||
		      ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL) ||
		      have_pool_full(osdc);
2934

S
Sage Weil 已提交
2935 2936 2937 2938 2939
	/* 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);
2940 2941
		epoch = ceph_decode_32(&p);
		maplen = ceph_decode_32(&p);
S
Sage Weil 已提交
2942
		ceph_decode_need(&p, end, maplen, bad);
I
Ilya Dryomov 已提交
2943 2944
		if (osdc->osdmap->epoch &&
		    osdc->osdmap->epoch + 1 == epoch) {
S
Sage Weil 已提交
2945 2946
			dout("applying incremental map %u len %d\n",
			     epoch, maplen);
2947 2948
			err = handle_one_map(osdc, p, p + maplen, true,
					     &need_resend, &need_resend_linger);
I
Ilya Dryomov 已提交
2949
			if (err)
S
Sage Weil 已提交
2950
				goto bad;
I
Ilya Dryomov 已提交
2951
			handled_incremental = true;
S
Sage Weil 已提交
2952 2953 2954 2955
		} else {
			dout("ignoring incremental map %u len %d\n",
			     epoch, maplen);
		}
I
Ilya Dryomov 已提交
2956
		p += maplen;
S
Sage Weil 已提交
2957 2958
		nr_maps--;
	}
I
Ilya Dryomov 已提交
2959
	if (handled_incremental)
S
Sage Weil 已提交
2960 2961 2962 2963 2964 2965 2966
		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);
2967 2968
		epoch = ceph_decode_32(&p);
		maplen = ceph_decode_32(&p);
S
Sage Weil 已提交
2969 2970 2971 2972
		ceph_decode_need(&p, end, maplen, bad);
		if (nr_maps > 1) {
			dout("skipping non-latest full map %u len %d\n",
			     epoch, maplen);
2973
		} else if (osdc->osdmap->epoch >= epoch) {
S
Sage Weil 已提交
2974 2975 2976 2977 2978
			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);
2979 2980
			err = handle_one_map(osdc, p, p + maplen, false,
					     &need_resend, &need_resend_linger);
I
Ilya Dryomov 已提交
2981
			if (err)
S
Sage Weil 已提交
2982 2983 2984 2985 2986 2987 2988
				goto bad;
		}
		p += maplen;
		nr_maps--;
	}

done:
2989 2990 2991 2992 2993
	/*
	 * subscribe to subsequent osdmap updates if full to ensure
	 * we find out when we are no longer full and stop returning
	 * ENOSPC.
	 */
I
Ilya Dryomov 已提交
2994 2995 2996 2997 2998 2999
	pauserd = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSERD);
	pausewr = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSEWR) ||
		  ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL) ||
		  have_pool_full(osdc);
	if (was_pauserd || was_pausewr || pauserd || pausewr)
		maybe_request_map(osdc);
3000

3001
	kick_requests(osdc, &need_resend, &need_resend_linger);
I
Ilya Dryomov 已提交
3002 3003 3004

	ceph_monc_got_map(&osdc->client->monc, CEPH_SUB_OSDMAP,
			  osdc->osdmap->epoch);
3005
	up_write(&osdc->lock);
3006
	wake_up_all(&osdc->client->auth_wq);
S
Sage Weil 已提交
3007 3008 3009 3010
	return;

bad:
	pr_err("osdc handle_map corrupt msg\n");
3011
	ceph_msg_dump(msg);
3012 3013 3014 3015 3016 3017 3018 3019 3020 3021
	up_write(&osdc->lock);
}

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

3022
	for (n = rb_first(&osd->o_requests); n; ) {
3023 3024 3025
		struct ceph_osd_request *req =
		    rb_entry(n, struct ceph_osd_request, r_node);

3026 3027
		n = rb_next(n); /* cancel_linger_request() */

3028 3029 3030
		if (!req->r_linger) {
			if (!req->r_t.paused)
				send_request(req);
3031 3032
		} else {
			cancel_linger_request(req);
3033 3034
		}
	}
3035 3036 3037 3038 3039 3040
	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);
	}
3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064
}

/*
 * 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
3065 3066
}

3067 3068 3069
/*
 * Process osd watch notifications
 */
3070 3071
static void handle_watch_notify(struct ceph_osd_client *osdc,
				struct ceph_msg *msg)
3072
{
3073 3074 3075 3076 3077 3078 3079
	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;
3080
	s32 return_code = 0;
3081 3082
	void *payload = NULL;
	u32 payload_len = 0;
3083 3084 3085 3086

	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);
3087
	p += 8; /* skip ver */
3088 3089
	ceph_decode_64_safe(&p, end, notify_id, bad);

3090 3091 3092 3093 3094 3095 3096 3097
	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)
3098
		ceph_decode_32_safe(&p, end, return_code, bad);
3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111

	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);
3112 3113
	dout("%s opcode %d cookie %llu lreq %p is_watch %d\n", __func__,
	     opcode, cookie, lreq, lreq->is_watch);
3114 3115 3116 3117 3118
	if (opcode == CEPH_WATCH_EVENT_DISCONNECT) {
		if (!lreq->last_error) {
			lreq->last_error = -ENOTCONN;
			queue_watch_error(lreq);
		}
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
	} 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);
		}
3144 3145 3146 3147 3148 3149
	} 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;
3150 3151
		}

3152 3153 3154 3155 3156 3157
		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);
3158
	}
3159

3160 3161 3162 3163
out_unlock_lreq:
	mutex_unlock(&lreq->lock);
out_unlock_osdc:
	up_read(&osdc->lock);
3164 3165 3166 3167 3168 3169
	return;

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

3170 3171 3172 3173 3174 3175 3176
/*
 * Register request, send initial attempt.
 */
int ceph_osdc_start_request(struct ceph_osd_client *osdc,
			    struct ceph_osd_request *req,
			    bool nofail)
{
3177 3178 3179
	down_read(&osdc->lock);
	submit_request(req, false);
	up_read(&osdc->lock);
3180

3181
	return 0;
S
Sage Weil 已提交
3182
}
3183
EXPORT_SYMBOL(ceph_osdc_start_request);
S
Sage Weil 已提交
3184

3185 3186 3187 3188 3189 3190 3191 3192 3193
/*
 * Unregister a registered request.  The request is not completed (i.e.
 * no callbacks or wakeups) - higher layers are supposed to know what
 * they are canceling.
 */
void ceph_osdc_cancel_request(struct ceph_osd_request *req)
{
	struct ceph_osd_client *osdc = req->r_osdc;

3194 3195 3196 3197
	down_write(&osdc->lock);
	if (req->r_osd)
		cancel_request(req);
	up_write(&osdc->lock);
3198 3199 3200
}
EXPORT_SYMBOL(ceph_osdc_cancel_request);

S
Sage Weil 已提交
3201
/*
I
Ilya Dryomov 已提交
3202
 * @timeout: in jiffies, 0 means "wait forever"
S
Sage Weil 已提交
3203
 */
I
Ilya Dryomov 已提交
3204 3205
static int wait_request_timeout(struct ceph_osd_request *req,
				unsigned long timeout)
S
Sage Weil 已提交
3206
{
I
Ilya Dryomov 已提交
3207
	long left;
3208

I
Ilya Dryomov 已提交
3209 3210 3211 3212 3213
	dout("%s req %p tid %llu\n", __func__, req, req->r_tid);
	left = wait_for_completion_interruptible_timeout(&req->r_completion,
						ceph_timeout_jiffies(timeout));
	if (left <= 0) {
		left = left ?: -ETIMEDOUT;
3214
		ceph_osdc_cancel_request(req);
3215 3216 3217

		/* kludge - need to to wake ceph_osdc_sync() */
		complete_all(&req->r_safe_completion);
I
Ilya Dryomov 已提交
3218 3219
	} else {
		left = req->r_result; /* completed */
S
Sage Weil 已提交
3220 3221
	}

I
Ilya Dryomov 已提交
3222 3223 3224 3225 3226 3227 3228 3229 3230 3231
	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
3232
}
3233
EXPORT_SYMBOL(ceph_osdc_wait_request);
S
Sage Weil 已提交
3234 3235 3236 3237 3238 3239

/*
 * sync - wait for all in-flight requests to flush.  avoid starvation.
 */
void ceph_osdc_sync(struct ceph_osd_client *osdc)
{
3240 3241
	struct rb_node *n, *p;
	u64 last_tid = atomic64_read(&osdc->last_tid);
S
Sage Weil 已提交
3242

3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257
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
3258

3259 3260 3261 3262 3263 3264 3265 3266 3267
			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);
			wait_for_completion(&req->r_safe_completion);
			ceph_osdc_put_request(req);
			goto again;
		}
S
Sage Weil 已提交
3268

3269
		mutex_unlock(&osd->lock);
S
Sage Weil 已提交
3270
	}
3271 3272 3273

	up_read(&osdc->lock);
	dout("%s done last_tid %llu\n", __func__, last_tid);
S
Sage Weil 已提交
3274
}
3275
EXPORT_SYMBOL(ceph_osdc_sync);
S
Sage Weil 已提交
3276

3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314
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);

3315
	lreq->is_watch = true;
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 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 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 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469
	lreq->wcb = wcb;
	lreq->errcb = errcb;
	lreq->data = data;

	ceph_oid_copy(&lreq->t.base_oid, oid);
	ceph_oloc_copy(&lreq->t.base_oloc, oloc);
	lreq->t.flags = CEPH_OSD_FLAG_WRITE | CEPH_OSD_FLAG_ONDISK;
	lreq->mtime = CURRENT_TIME;

	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);
	req->r_flags = CEPH_OSD_FLAG_WRITE | CEPH_OSD_FLAG_ONDISK;
	req->r_mtime = CURRENT_TIME;
	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);

3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579
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);

3580 3581 3582 3583
/*
 * 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
3584
void ceph_osdc_flush_notifies(struct ceph_osd_client *osdc)
3585 3586 3587 3588 3589 3590
{
	flush_workqueue(osdc->notify_wq);
}
EXPORT_SYMBOL(ceph_osdc_flush_notifies);


S
Sage Weil 已提交
3591 3592 3593 3594 3595 3596 3597 3598 3599
/*
 * init, shutdown
 */
int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client)
{
	int err;

	dout("init\n");
	osdc->client = client;
3600
	init_rwsem(&osdc->lock);
S
Sage Weil 已提交
3601
	osdc->osds = RB_ROOT;
3602
	INIT_LIST_HEAD(&osdc->osd_lru);
3603
	spin_lock_init(&osdc->osd_lru_lock);
3604 3605 3606
	osd_init(&osdc->homeless_osd);
	osdc->homeless_osd.o_osdc = osdc;
	osdc->homeless_osd.o_osd = CEPH_HOMELESS_OSD;
3607
	osdc->linger_requests = RB_ROOT;
S
Sage Weil 已提交
3608
	INIT_DELAYED_WORK(&osdc->timeout_work, handle_timeout);
3609 3610
	INIT_DELAYED_WORK(&osdc->osds_timeout_work, handle_osds_timeout);

3611
	err = -ENOMEM;
3612 3613 3614 3615
	osdc->osdmap = ceph_osdmap_alloc();
	if (!osdc->osdmap)
		goto out;

3616 3617
	osdc->req_mempool = mempool_create_slab_pool(10,
						     ceph_osd_request_cache);
S
Sage Weil 已提交
3618
	if (!osdc->req_mempool)
3619
		goto out_map;
S
Sage Weil 已提交
3620

3621
	err = ceph_msgpool_init(&osdc->msgpool_op, CEPH_MSG_OSD_OP,
3622
				PAGE_SIZE, 10, true, "osd_op");
S
Sage Weil 已提交
3623
	if (err < 0)
3624
		goto out_mempool;
3625
	err = ceph_msgpool_init(&osdc->msgpool_op_reply, CEPH_MSG_OSD_OPREPLY,
3626
				PAGE_SIZE, 10, true, "osd_op_reply");
S
Sage Weil 已提交
3627 3628
	if (err < 0)
		goto out_msgpool;
3629

3630
	err = -ENOMEM;
3631
	osdc->notify_wq = create_singlethread_workqueue("ceph-watch-notify");
3632
	if (!osdc->notify_wq)
3633 3634
		goto out_msgpool_reply;

3635 3636
	schedule_delayed_work(&osdc->timeout_work,
			      osdc->client->options->osd_keepalive_timeout);
3637 3638 3639
	schedule_delayed_work(&osdc->osds_timeout_work,
	    round_jiffies_relative(osdc->client->options->osd_idle_ttl));

S
Sage Weil 已提交
3640
	return 0;
3641

3642 3643
out_msgpool_reply:
	ceph_msgpool_destroy(&osdc->msgpool_op_reply);
S
Sage Weil 已提交
3644 3645
out_msgpool:
	ceph_msgpool_destroy(&osdc->msgpool_op);
3646 3647
out_mempool:
	mempool_destroy(osdc->req_mempool);
3648 3649
out_map:
	ceph_osdmap_destroy(osdc->osdmap);
3650 3651
out:
	return err;
S
Sage Weil 已提交
3652 3653 3654 3655
}

void ceph_osdc_stop(struct ceph_osd_client *osdc)
{
3656 3657
	flush_workqueue(osdc->notify_wq);
	destroy_workqueue(osdc->notify_wq);
S
Sage Weil 已提交
3658
	cancel_delayed_work_sync(&osdc->timeout_work);
3659
	cancel_delayed_work_sync(&osdc->osds_timeout_work);
3660

3661
	down_write(&osdc->lock);
3662 3663 3664
	while (!RB_EMPTY_ROOT(&osdc->osds)) {
		struct ceph_osd *osd = rb_entry(rb_first(&osdc->osds),
						struct ceph_osd, o_node);
3665
		close_osd(osd);
3666
	}
3667 3668 3669 3670 3671
	up_write(&osdc->lock);
	WARN_ON(atomic_read(&osdc->homeless_osd.o_ref) != 1);
	osd_cleanup(&osdc->homeless_osd);

	WARN_ON(!list_empty(&osdc->osd_lru));
3672
	WARN_ON(!RB_EMPTY_ROOT(&osdc->linger_requests));
3673 3674
	WARN_ON(atomic_read(&osdc->num_requests));
	WARN_ON(atomic_read(&osdc->num_homeless));
3675

3676
	ceph_osdmap_destroy(osdc->osdmap);
S
Sage Weil 已提交
3677 3678
	mempool_destroy(osdc->req_mempool);
	ceph_msgpool_destroy(&osdc->msgpool_op);
S
Sage Weil 已提交
3679
	ceph_msgpool_destroy(&osdc->msgpool_op_reply);
S
Sage Weil 已提交
3680 3681 3682 3683 3684 3685 3686 3687 3688 3689
}

/*
 * 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,
3690
			struct page **pages, int num_pages, int page_align)
S
Sage Weil 已提交
3691 3692 3693 3694 3695 3696
{
	struct ceph_osd_request *req;
	int rc = 0;

	dout("readpages on ino %llx.%llx on %llu~%llu\n", vino.ino,
	     vino.snap, off, *plen);
3697
	req = ceph_osdc_new_request(osdc, layout, vino, off, plen, 0, 1,
S
Sage Weil 已提交
3698
				    CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ,
3699
				    NULL, truncate_seq, truncate_size,
3700
				    false);
3701 3702
	if (IS_ERR(req))
		return PTR_ERR(req);
S
Sage Weil 已提交
3703 3704

	/* it may be a short read due to an object boundary */
3705
	osd_req_op_extent_osd_data_pages(req, 0,
3706
				pages, *plen, page_align, false, false);
S
Sage Weil 已提交
3707

3708
	dout("readpages  final extent is %llu~%llu (%llu bytes align %d)\n",
3709
	     off, *plen, *plen, page_align);
S
Sage Weil 已提交
3710 3711 3712 3713 3714 3715 3716 3717 3718

	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;
}
3719
EXPORT_SYMBOL(ceph_osdc_readpages);
S
Sage Weil 已提交
3720 3721 3722 3723 3724 3725 3726 3727 3728 3729

/*
 * 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,
3730
			 struct page **pages, int num_pages)
S
Sage Weil 已提交
3731 3732 3733
{
	struct ceph_osd_request *req;
	int rc = 0;
3734
	int page_align = off & ~PAGE_MASK;
S
Sage Weil 已提交
3735

3736
	req = ceph_osdc_new_request(osdc, layout, vino, off, &len, 0, 1,
S
Sage Weil 已提交
3737
				    CEPH_OSD_OP_WRITE,
3738
				    CEPH_OSD_FLAG_ONDISK | CEPH_OSD_FLAG_WRITE,
3739
				    snapc, truncate_seq, truncate_size,
3740
				    true);
3741 3742
	if (IS_ERR(req))
		return PTR_ERR(req);
S
Sage Weil 已提交
3743 3744

	/* it may be a short write due to an object boundary */
3745
	osd_req_op_extent_osd_data_pages(req, 0, pages, len, page_align,
3746 3747
				false, false);
	dout("writepages %llu~%llu (%llu bytes)\n", off, len, len);
S
Sage Weil 已提交
3748

3749
	req->r_mtime = *mtime;
3750
	rc = ceph_osdc_start_request(osdc, req, true);
S
Sage Weil 已提交
3751 3752 3753 3754 3755 3756 3757 3758 3759
	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;
}
3760
EXPORT_SYMBOL(ceph_osdc_writepages);
S
Sage Weil 已提交
3761

3762 3763
int ceph_osdc_setup(void)
{
3764 3765 3766
	size_t size = sizeof(struct ceph_osd_request) +
	    CEPH_OSD_SLAB_OPS * sizeof(struct ceph_osd_req_op);

3767
	BUG_ON(ceph_osd_request_cache);
3768 3769
	ceph_osd_request_cache = kmem_cache_create("ceph_osd_request", size,
						   0, 0, NULL);
3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782

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

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

S
Sage Weil 已提交
3783 3784 3785 3786 3787 3788
/*
 * handle incoming message
 */
static void dispatch(struct ceph_connection *con, struct ceph_msg *msg)
{
	struct ceph_osd *osd = con->private;
3789
	struct ceph_osd_client *osdc = osd->o_osdc;
S
Sage Weil 已提交
3790 3791 3792 3793 3794 3795 3796
	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:
3797
		handle_reply(osd, msg);
S
Sage Weil 已提交
3798
		break;
3799 3800 3801
	case CEPH_MSG_WATCH_NOTIFY:
		handle_watch_notify(osdc, msg);
		break;
S
Sage Weil 已提交
3802 3803 3804 3805 3806

	default:
		pr_err("received unknown message type %d %s\n", type,
		       ceph_msg_type_name(type));
	}
3807

S
Sage Weil 已提交
3808 3809 3810
	ceph_msg_put(msg);
}

3811
/*
3812 3813 3814
 * 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.
3815 3816
 */
static struct ceph_msg *get_reply(struct ceph_connection *con,
3817 3818
				  struct ceph_msg_header *hdr,
				  int *skip)
S
Sage Weil 已提交
3819 3820 3821
{
	struct ceph_osd *osd = con->private;
	struct ceph_osd_client *osdc = osd->o_osdc;
3822
	struct ceph_msg *m = NULL;
3823
	struct ceph_osd_request *req;
3824
	int front_len = le32_to_cpu(hdr->front_len);
3825
	int data_len = le32_to_cpu(hdr->data_len);
3826
	u64 tid = le64_to_cpu(hdr->tid);
S
Sage Weil 已提交
3827

3828 3829 3830 3831 3832 3833 3834 3835 3836 3837
	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);
3838
	if (!req) {
3839 3840
		dout("%s osd%d tid %llu unknown, skipping\n", __func__,
		     osd->o_osd, tid);
3841
		*skip = 1;
3842
		goto out_unlock_session;
3843
	}
S
Sage Weil 已提交
3844

3845
	ceph_msg_revoke_incoming(req->r_reply);
3846

3847
	if (front_len > req->r_reply->front_alloc_len) {
3848 3849 3850
		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);
3851 3852
		m = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, front_len, GFP_NOFS,
				 false);
3853
		if (!m)
3854
			goto out_unlock_session;
S
Sage Weil 已提交
3855 3856 3857
		ceph_msg_put(req->r_reply);
		req->r_reply = m;
	}
3858

3859 3860 3861 3862 3863 3864
	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;
3865
		goto out_unlock_session;
3866
	}
3867 3868

	m = ceph_msg_get(req->r_reply);
S
Sage Weil 已提交
3869
	dout("get_reply tid %lld %p\n", tid, m);
3870

3871 3872 3873 3874
out_unlock_session:
	mutex_unlock(&osd->lock);
out_unlock_osdc:
	up_read(&osdc->lock);
3875
	return m;
3876 3877
}

3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910
/*
 * 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);
		if (!pages) {
			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;
}

3911 3912 3913 3914 3915 3916 3917
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
3918
	*skip = 0;
3919 3920
	switch (type) {
	case CEPH_MSG_OSD_MAP:
3921
	case CEPH_MSG_WATCH_NOTIFY:
3922
		return alloc_msg_with_page_vector(hdr);
3923 3924 3925
	case CEPH_MSG_OSD_OPREPLY:
		return get_reply(con, hdr, skip);
	default:
3926 3927
		pr_warn("%s osd%d unknown msg type %d, skipping\n", __func__,
			osd->o_osd, type);
3928 3929 3930
		*skip = 1;
		return NULL;
	}
S
Sage Weil 已提交
3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949
}

/*
 * 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);
}

3950 3951 3952
/*
 * authentication
 */
3953 3954 3955 3956 3957
/*
 * 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,
3958
					int *proto, int force_new)
3959 3960 3961 3962
{
	struct ceph_osd *o = con->private;
	struct ceph_osd_client *osdc = o->o_osdc;
	struct ceph_auth_client *ac = osdc->client->monc.auth;
3963
	struct ceph_auth_handshake *auth = &o->o_auth;
3964

3965
	if (force_new && auth->authorizer) {
3966
		ceph_auth_destroy_authorizer(auth->authorizer);
3967 3968
		auth->authorizer = NULL;
	}
3969 3970 3971
	if (!auth->authorizer) {
		int ret = ceph_auth_create_authorizer(ac, CEPH_ENTITY_TYPE_OSD,
						      auth);
3972
		if (ret)
3973
			return ERR_PTR(ret);
3974 3975
	} else {
		int ret = ceph_auth_update_authorizer(ac, CEPH_ENTITY_TYPE_OSD,
3976 3977 3978
						     auth);
		if (ret)
			return ERR_PTR(ret);
3979 3980
	}
	*proto = ac->protocol;
3981

3982
	return auth;
3983 3984 3985 3986 3987 3988 3989 3990 3991
}


static int verify_authorizer_reply(struct ceph_connection *con, int len)
{
	struct ceph_osd *o = con->private;
	struct ceph_osd_client *osdc = o->o_osdc;
	struct ceph_auth_client *ac = osdc->client->monc.auth;

3992
	return ceph_auth_verify_authorizer_reply(ac, o->o_auth.authorizer, len);
3993 3994
}

3995 3996 3997 3998 3999 4000
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;

4001
	ceph_auth_invalidate_authorizer(ac, CEPH_ENTITY_TYPE_OSD);
4002 4003
	return ceph_monc_validate_auth(&osdc->client->monc);
}
4004

4005
static int osd_sign_message(struct ceph_msg *msg)
Y
Yan, Zheng 已提交
4006
{
4007
	struct ceph_osd *o = msg->con->private;
Y
Yan, Zheng 已提交
4008
	struct ceph_auth_handshake *auth = &o->o_auth;
4009

Y
Yan, Zheng 已提交
4010 4011 4012
	return ceph_auth_sign_message(auth, msg);
}

4013
static int osd_check_message_signature(struct ceph_msg *msg)
Y
Yan, Zheng 已提交
4014
{
4015
	struct ceph_osd *o = msg->con->private;
Y
Yan, Zheng 已提交
4016
	struct ceph_auth_handshake *auth = &o->o_auth;
4017

Y
Yan, Zheng 已提交
4018 4019 4020
	return ceph_auth_check_message_signature(auth, msg);
}

4021
static const struct ceph_connection_operations osd_con_ops = {
S
Sage Weil 已提交
4022 4023 4024
	.get = get_osd_con,
	.put = put_osd_con,
	.dispatch = dispatch,
4025 4026
	.get_authorizer = get_authorizer,
	.verify_authorizer_reply = verify_authorizer_reply,
4027
	.invalidate_authorizer = invalidate_authorizer,
S
Sage Weil 已提交
4028
	.alloc_msg = alloc_msg,
4029 4030
	.sign_message = osd_sign_message,
	.check_message_signature = osd_check_message_signature,
4031
	.fault = osd_fault,
S
Sage Weil 已提交
4032
};