flexfilelayout.c 59.7 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16
/*
 * Module for pnfs flexfile layout driver.
 *
 * Copyright (c) 2014, Primary Data, Inc. All rights reserved.
 *
 * Tao Peng <bergwolf@primarydata.com>
 */

#include <linux/nfs_fs.h>
#include <linux/nfs_page.h>
#include <linux/module.h>

#include <linux/sunrpc/metrics.h>

#include "flexfilelayout.h"
#include "../nfs4session.h"
17
#include "../nfs4idmap.h"
18 19 20 21 22
#include "../internal.h"
#include "../delegation.h"
#include "../nfs4trace.h"
#include "../iostat.h"
#include "../nfs.h"
23
#include "../nfs42.h"
24 25 26 27 28

#define NFSDBG_FACILITY         NFSDBG_PNFS_LD

#define FF_LAYOUT_POLL_RETRY_MAX     (15*HZ)

29 30
static struct group_info	*ff_zero_group;

31 32 33
static void ff_layout_read_record_layoutstats_done(struct rpc_task *task,
		struct nfs_pgio_header *hdr);

34 35 36 37 38 39 40 41
static struct pnfs_layout_hdr *
ff_layout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags)
{
	struct nfs4_flexfile_layout *ffl;

	ffl = kzalloc(sizeof(*ffl), gfp_flags);
	if (ffl) {
		INIT_LIST_HEAD(&ffl->error_list);
42
		INIT_LIST_HEAD(&ffl->mirrors);
43
		ffl->last_report_time = ktime_get();
44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61
		return &ffl->generic_hdr;
	} else
		return NULL;
}

static void
ff_layout_free_layout_hdr(struct pnfs_layout_hdr *lo)
{
	struct nfs4_ff_layout_ds_err *err, *n;

	list_for_each_entry_safe(err, n, &FF_LAYOUT_FROM_HDR(lo)->error_list,
				 list) {
		list_del(&err->list);
		kfree(err);
	}
	kfree(FF_LAYOUT_FROM_HDR(lo));
}

62
static int decode_pnfs_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
63 64 65 66 67 68
{
	__be32 *p;

	p = xdr_inline_decode(xdr, NFS4_STATEID_SIZE);
	if (unlikely(p == NULL))
		return -ENOBUFS;
69 70
	stateid->type = NFS4_PNFS_DS_STATEID_TYPE;
	memcpy(stateid->data, p, NFS4_STATEID_SIZE);
71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145
	dprintk("%s: stateid id= [%x%x%x%x]\n", __func__,
		p[0], p[1], p[2], p[3]);
	return 0;
}

static int decode_deviceid(struct xdr_stream *xdr, struct nfs4_deviceid *devid)
{
	__be32 *p;

	p = xdr_inline_decode(xdr, NFS4_DEVICEID4_SIZE);
	if (unlikely(!p))
		return -ENOBUFS;
	memcpy(devid, p, NFS4_DEVICEID4_SIZE);
	nfs4_print_deviceid(devid);
	return 0;
}

static int decode_nfs_fh(struct xdr_stream *xdr, struct nfs_fh *fh)
{
	__be32 *p;

	p = xdr_inline_decode(xdr, 4);
	if (unlikely(!p))
		return -ENOBUFS;
	fh->size = be32_to_cpup(p++);
	if (fh->size > sizeof(struct nfs_fh)) {
		printk(KERN_ERR "NFS flexfiles: Too big fh received %d\n",
		       fh->size);
		return -EOVERFLOW;
	}
	/* fh.data */
	p = xdr_inline_decode(xdr, fh->size);
	if (unlikely(!p))
		return -ENOBUFS;
	memcpy(&fh->data, p, fh->size);
	dprintk("%s: fh len %d\n", __func__, fh->size);

	return 0;
}

/*
 * Currently only stringified uids and gids are accepted.
 * I.e., kerberos is not supported to the DSes, so no pricipals.
 *
 * That means that one common function will suffice, but when
 * principals are added, this should be split to accomodate
 * calls to both nfs_map_name_to_uid() and nfs_map_group_to_gid().
 */
static int
decode_name(struct xdr_stream *xdr, u32 *id)
{
	__be32 *p;
	int len;

	/* opaque_length(4)*/
	p = xdr_inline_decode(xdr, 4);
	if (unlikely(!p))
		return -ENOBUFS;
	len = be32_to_cpup(p++);
	if (len < 0)
		return -EINVAL;

	dprintk("%s: len %u\n", __func__, len);

	/* opaque body */
	p = xdr_inline_decode(xdr, len);
	if (unlikely(!p))
		return -ENOBUFS;

	if (!nfs_map_string_to_numeric((char *)p, len, id))
		return -EINVAL;

	return 0;
}

146 147 148 149 150 151 152 153 154
static bool ff_mirror_match_fh(const struct nfs4_ff_layout_mirror *m1,
		const struct nfs4_ff_layout_mirror *m2)
{
	int i, j;

	if (m1->fh_versions_cnt != m2->fh_versions_cnt)
		return false;
	for (i = 0; i < m1->fh_versions_cnt; i++) {
		bool found_fh = false;
155
		for (j = 0; j < m2->fh_versions_cnt; j++) {
156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192
			if (nfs_compare_fh(&m1->fh_versions[i],
					&m2->fh_versions[j]) == 0) {
				found_fh = true;
				break;
			}
		}
		if (!found_fh)
			return false;
	}
	return true;
}

static struct nfs4_ff_layout_mirror *
ff_layout_add_mirror(struct pnfs_layout_hdr *lo,
		struct nfs4_ff_layout_mirror *mirror)
{
	struct nfs4_flexfile_layout *ff_layout = FF_LAYOUT_FROM_HDR(lo);
	struct nfs4_ff_layout_mirror *pos;
	struct inode *inode = lo->plh_inode;

	spin_lock(&inode->i_lock);
	list_for_each_entry(pos, &ff_layout->mirrors, mirrors) {
		if (mirror->mirror_ds != pos->mirror_ds)
			continue;
		if (!ff_mirror_match_fh(mirror, pos))
			continue;
		if (atomic_inc_not_zero(&pos->ref)) {
			spin_unlock(&inode->i_lock);
			return pos;
		}
	}
	list_add(&mirror->mirrors, &ff_layout->mirrors);
	mirror->layout = lo;
	spin_unlock(&inode->i_lock);
	return mirror;
}

193
static void
194 195 196 197 198 199 200 201 202 203 204 205
ff_layout_remove_mirror(struct nfs4_ff_layout_mirror *mirror)
{
	struct inode *inode;
	if (mirror->layout == NULL)
		return;
	inode = mirror->layout->plh_inode;
	spin_lock(&inode->i_lock);
	list_del(&mirror->mirrors);
	spin_unlock(&inode->i_lock);
	mirror->layout = NULL;
}

206 207 208 209 210 211 212 213
static struct nfs4_ff_layout_mirror *ff_layout_alloc_mirror(gfp_t gfp_flags)
{
	struct nfs4_ff_layout_mirror *mirror;

	mirror = kzalloc(sizeof(*mirror), gfp_flags);
	if (mirror != NULL) {
		spin_lock_init(&mirror->lock);
		atomic_set(&mirror->ref, 1);
214
		INIT_LIST_HEAD(&mirror->mirrors);
215 216 217 218 219 220
	}
	return mirror;
}

static void ff_layout_free_mirror(struct nfs4_ff_layout_mirror *mirror)
{
221 222
	struct rpc_cred	*cred;

223
	ff_layout_remove_mirror(mirror);
224
	kfree(mirror->fh_versions);
225 226 227 228 229 230
	cred = rcu_access_pointer(mirror->ro_cred);
	if (cred)
		put_rpccred(cred);
	cred = rcu_access_pointer(mirror->rw_cred);
	if (cred)
		put_rpccred(cred);
231 232 233 234 235 236 237 238 239 240
	nfs4_ff_layout_put_deviceid(mirror->mirror_ds);
	kfree(mirror);
}

static void ff_layout_put_mirror(struct nfs4_ff_layout_mirror *mirror)
{
	if (mirror != NULL && atomic_dec_and_test(&mirror->ref))
		ff_layout_free_mirror(mirror);
}

241 242 243 244 245 246 247 248 249
static void ff_layout_free_mirror_array(struct nfs4_ff_layout_segment *fls)
{
	int i;

	if (fls->mirror_array) {
		for (i = 0; i < fls->mirror_array_cnt; i++) {
			/* normally mirror_ds is freed in
			 * .free_deviceid_node but we still do it here
			 * for .alloc_lseg error path */
250
			ff_layout_put_mirror(fls->mirror_array[i]);
251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282
		}
		kfree(fls->mirror_array);
		fls->mirror_array = NULL;
	}
}

static int ff_layout_check_layout(struct nfs4_layoutget_res *lgr)
{
	int ret = 0;

	dprintk("--> %s\n", __func__);

	/* FIXME: remove this check when layout segment support is added */
	if (lgr->range.offset != 0 ||
	    lgr->range.length != NFS4_MAX_UINT64) {
		dprintk("%s Only whole file layouts supported. Use MDS i/o\n",
			__func__);
		ret = -EINVAL;
	}

	dprintk("--> %s returns %d\n", __func__, ret);
	return ret;
}

static void _ff_layout_free_lseg(struct nfs4_ff_layout_segment *fls)
{
	if (fls) {
		ff_layout_free_mirror_array(fls);
		kfree(fls);
	}
}

283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305
static bool
ff_lseg_range_is_after(const struct pnfs_layout_range *l1,
		const struct pnfs_layout_range *l2)
{
	u64 end1, end2;

	if (l1->iomode != l2->iomode)
		return l1->iomode != IOMODE_READ;
	end1 = pnfs_calc_offset_end(l1->offset, l1->length);
	end2 = pnfs_calc_offset_end(l2->offset, l2->length);
	if (end1 < l2->offset)
		return false;
	if (end2 < l1->offset)
		return true;
	return l2->offset <= l1->offset;
}

static bool
ff_lseg_merge(struct pnfs_layout_segment *new,
		struct pnfs_layout_segment *old)
{
	u64 new_end, old_end;

306 307
	if (test_bit(NFS_LSEG_LAYOUTRETURN, &old->pls_flags))
		return false;
308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341
	if (new->pls_range.iomode != old->pls_range.iomode)
		return false;
	old_end = pnfs_calc_offset_end(old->pls_range.offset,
			old->pls_range.length);
	if (old_end < new->pls_range.offset)
		return false;
	new_end = pnfs_calc_offset_end(new->pls_range.offset,
			new->pls_range.length);
	if (new_end < old->pls_range.offset)
		return false;

	/* Mergeable: copy info from 'old' to 'new' */
	if (new_end < old_end)
		new_end = old_end;
	if (new->pls_range.offset < old->pls_range.offset)
		new->pls_range.offset = old->pls_range.offset;
	new->pls_range.length = pnfs_calc_offset_length(new->pls_range.offset,
			new_end);
	if (test_bit(NFS_LSEG_ROC, &old->pls_flags))
		set_bit(NFS_LSEG_ROC, &new->pls_flags);
	return true;
}

static void
ff_layout_add_lseg(struct pnfs_layout_hdr *lo,
		struct pnfs_layout_segment *lseg,
		struct list_head *free_me)
{
	pnfs_generic_layout_insert_lseg(lo, lseg,
			ff_lseg_range_is_after,
			ff_lseg_merge,
			free_me);
}

342 343 344 345 346 347 348
static void ff_layout_sort_mirrors(struct nfs4_ff_layout_segment *fls)
{
	int i, j;

	for (i = 0; i < fls->mirror_array_cnt - 1; i++) {
		for (j = i + 1; j < fls->mirror_array_cnt; j++)
			if (fls->mirror_array[i]->efficiency <
349 350 351
			    fls->mirror_array[j]->efficiency)
				swap(fls->mirror_array[i],
				     fls->mirror_array[j]);
352 353 354
	}
}

355 356 357 358 359 360 361 362 363 364 365 366 367
static void ff_layout_mark_devices_valid(struct nfs4_ff_layout_segment *fls)
{
	struct nfs4_deviceid_node *node;
	int i;

	if (!(fls->flags & FF_FLAGS_NO_IO_THRU_MDS))
		return;
	for (i = 0; i < fls->mirror_array_cnt; i++) {
		node = &fls->mirror_array[i]->mirror_ds->id_node;
		clear_bit(NFS_DEVICEID_UNAVAILABLE, &node->flags);
	}
}

368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419
static struct pnfs_layout_segment *
ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh,
		     struct nfs4_layoutget_res *lgr,
		     gfp_t gfp_flags)
{
	struct pnfs_layout_segment *ret;
	struct nfs4_ff_layout_segment *fls = NULL;
	struct xdr_stream stream;
	struct xdr_buf buf;
	struct page *scratch;
	u64 stripe_unit;
	u32 mirror_array_cnt;
	__be32 *p;
	int i, rc;

	dprintk("--> %s\n", __func__);
	scratch = alloc_page(gfp_flags);
	if (!scratch)
		return ERR_PTR(-ENOMEM);

	xdr_init_decode_pages(&stream, &buf, lgr->layoutp->pages,
			      lgr->layoutp->len);
	xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);

	/* stripe unit and mirror_array_cnt */
	rc = -EIO;
	p = xdr_inline_decode(&stream, 8 + 4);
	if (!p)
		goto out_err_free;

	p = xdr_decode_hyper(p, &stripe_unit);
	mirror_array_cnt = be32_to_cpup(p++);
	dprintk("%s: stripe_unit=%llu mirror_array_cnt=%u\n", __func__,
		stripe_unit, mirror_array_cnt);

	if (mirror_array_cnt > NFS4_FLEXFILE_LAYOUT_MAX_MIRROR_CNT ||
	    mirror_array_cnt == 0)
		goto out_err_free;

	rc = -ENOMEM;
	fls = kzalloc(sizeof(*fls), gfp_flags);
	if (!fls)
		goto out_err_free;

	fls->mirror_array_cnt = mirror_array_cnt;
	fls->stripe_unit = stripe_unit;
	fls->mirror_array = kcalloc(fls->mirror_array_cnt,
				    sizeof(fls->mirror_array[0]), gfp_flags);
	if (fls->mirror_array == NULL)
		goto out_err_free;

	for (i = 0; i < fls->mirror_array_cnt; i++) {
420
		struct nfs4_ff_layout_mirror *mirror;
421 422
		struct nfs4_deviceid devid;
		struct nfs4_deviceid_node *idnode;
423
		struct auth_cred acred = { .group_info = ff_zero_group };
424
		struct rpc_cred	__rcu *cred;
425
		u32 ds_count, fh_count, id;
426 427 428 429 430 431 432 433 434 435 436 437
		int j;

		rc = -EIO;
		p = xdr_inline_decode(&stream, 4);
		if (!p)
			goto out_err_free;
		ds_count = be32_to_cpup(p);

		/* FIXME: allow for striping? */
		if (ds_count != 1)
			goto out_err_free;

438
		fls->mirror_array[i] = ff_layout_alloc_mirror(gfp_flags);
439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472
		if (fls->mirror_array[i] == NULL) {
			rc = -ENOMEM;
			goto out_err_free;
		}

		fls->mirror_array[i]->ds_count = ds_count;

		/* deviceid */
		rc = decode_deviceid(&stream, &devid);
		if (rc)
			goto out_err_free;

		idnode = nfs4_find_get_deviceid(NFS_SERVER(lh->plh_inode),
						&devid, lh->plh_lc_cred,
						gfp_flags);
		/*
		 * upon success, mirror_ds is allocated by previous
		 * getdeviceinfo, or newly by .alloc_deviceid_node
		 * nfs4_find_get_deviceid failure is indeed getdeviceinfo falure
		 */
		if (idnode)
			fls->mirror_array[i]->mirror_ds =
				FF_LAYOUT_MIRROR_DS(idnode);
		else
			goto out_err_free;

		/* efficiency */
		rc = -EIO;
		p = xdr_inline_decode(&stream, 4);
		if (!p)
			goto out_err_free;
		fls->mirror_array[i]->efficiency = be32_to_cpup(p);

		/* stateid */
473
		rc = decode_pnfs_stateid(&stream, &fls->mirror_array[i]->stateid);
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
		if (rc)
			goto out_err_free;

		/* fh */
		p = xdr_inline_decode(&stream, 4);
		if (!p)
			goto out_err_free;
		fh_count = be32_to_cpup(p);

		fls->mirror_array[i]->fh_versions =
			kzalloc(fh_count * sizeof(struct nfs_fh),
				gfp_flags);
		if (fls->mirror_array[i]->fh_versions == NULL) {
			rc = -ENOMEM;
			goto out_err_free;
		}

		for (j = 0; j < fh_count; j++) {
			rc = decode_nfs_fh(&stream,
					   &fls->mirror_array[i]->fh_versions[j]);
			if (rc)
				goto out_err_free;
		}

		fls->mirror_array[i]->fh_versions_cnt = fh_count;

		/* user */
501
		rc = decode_name(&stream, &id);
502 503 504
		if (rc)
			goto out_err_free;

505 506
		acred.uid = make_kuid(&init_user_ns, id);

507
		/* group */
508
		rc = decode_name(&stream, &id);
509 510 511
		if (rc)
			goto out_err_free;

512 513 514
		acred.gid = make_kgid(&init_user_ns, id);

		/* find the cred for it */
515
		rcu_assign_pointer(cred, rpc_lookup_generic_cred(&acred, 0, gfp_flags));
516 517 518 519 520
		if (IS_ERR(cred)) {
			rc = PTR_ERR(cred);
			goto out_err_free;
		}

521 522 523 524
		if (lgr->range.iomode == IOMODE_READ)
			rcu_assign_pointer(fls->mirror_array[i]->ro_cred, cred);
		else
			rcu_assign_pointer(fls->mirror_array[i]->rw_cred, cred);
525

526 527
		mirror = ff_layout_add_mirror(lh, fls->mirror_array[i]);
		if (mirror != fls->mirror_array[i]) {
528
			/* swap cred ptrs so free_mirror will clean up old */
529 530 531 532 533 534 535
			if (lgr->range.iomode == IOMODE_READ) {
				cred = xchg(&mirror->ro_cred, cred);
				rcu_assign_pointer(fls->mirror_array[i]->ro_cred, cred);
			} else {
				cred = xchg(&mirror->rw_cred, cred);
				rcu_assign_pointer(fls->mirror_array[i]->rw_cred, cred);
			}
536 537 538 539
			ff_layout_free_mirror(fls->mirror_array[i]);
			fls->mirror_array[i] = mirror;
		}

540 541
		dprintk("%s: iomode %s uid %u gid %u\n", __func__,
			lgr->range.iomode == IOMODE_READ ? "READ" : "RW",
542 543
			from_kuid(&init_user_ns, acred.uid),
			from_kgid(&init_user_ns, acred.gid));
544 545
	}

546
	p = xdr_inline_decode(&stream, 4);
547 548 549 550 551 552 553 554 555
	if (!p)
		goto out_sort_mirrors;
	fls->flags = be32_to_cpup(p);

	p = xdr_inline_decode(&stream, 4);
	if (!p)
		goto out_sort_mirrors;
	for (i=0; i < fls->mirror_array_cnt; i++)
		fls->mirror_array[i]->report_interval = be32_to_cpup(p);
556

557
out_sort_mirrors:
558 559 560 561
	ff_layout_sort_mirrors(fls);
	rc = ff_layout_check_layout(lgr);
	if (rc)
		goto out_err_free;
562
	ff_layout_mark_devices_valid(fls);
563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617

	ret = &fls->generic_hdr;
	dprintk("<-- %s (success)\n", __func__);
out_free_page:
	__free_page(scratch);
	return ret;
out_err_free:
	_ff_layout_free_lseg(fls);
	ret = ERR_PTR(rc);
	dprintk("<-- %s (%d)\n", __func__, rc);
	goto out_free_page;
}

static bool ff_layout_has_rw_segments(struct pnfs_layout_hdr *layout)
{
	struct pnfs_layout_segment *lseg;

	list_for_each_entry(lseg, &layout->plh_segs, pls_list)
		if (lseg->pls_range.iomode == IOMODE_RW)
			return true;

	return false;
}

static void
ff_layout_free_lseg(struct pnfs_layout_segment *lseg)
{
	struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg);

	dprintk("--> %s\n", __func__);

	if (lseg->pls_range.iomode == IOMODE_RW) {
		struct nfs4_flexfile_layout *ffl;
		struct inode *inode;

		ffl = FF_LAYOUT_FROM_HDR(lseg->pls_layout);
		inode = ffl->generic_hdr.plh_inode;
		spin_lock(&inode->i_lock);
		if (!ff_layout_has_rw_segments(lseg->pls_layout)) {
			ffl->commit_info.nbuckets = 0;
			kfree(ffl->commit_info.buckets);
			ffl->commit_info.buckets = NULL;
		}
		spin_unlock(&inode->i_lock);
	}
	_ff_layout_free_lseg(fls);
}

/* Return 1 until we have multiple lsegs support */
static int
ff_layout_get_lseg_count(struct nfs4_ff_layout_segment *fls)
{
	return 1;
}

618
static void
619
nfs4_ff_start_busy_timer(struct nfs4_ff_busy_timer *timer, ktime_t now)
620
{
621 622
	/* first IO request? */
	if (atomic_inc_return(&timer->n_ops) == 1) {
623
		timer->start_time = now;
624 625 626 627
	}
}

static ktime_t
628
nfs4_ff_end_busy_timer(struct nfs4_ff_busy_timer *timer, ktime_t now)
629
{
630
	ktime_t start;
631

632 633 634 635 636
	if (atomic_dec_return(&timer->n_ops) < 0)
		WARN_ON_ONCE(1);

	start = timer->start_time;
	timer->start_time = now;
637 638 639
	return ktime_sub(now, start);
}

640
static bool
641
nfs4_ff_layoutstat_start_io(struct nfs4_ff_layout_mirror *mirror,
642 643
			    struct nfs4_ff_layoutstat *layoutstat,
			    ktime_t now)
644
{
645
	static const ktime_t notime = {0};
646
	s64 report_interval = FF_LAYOUTSTATS_REPORT_INTERVAL;
647
	struct nfs4_flexfile_layout *ffl = FF_LAYOUT_FROM_HDR(mirror->layout);
648

649
	nfs4_ff_start_busy_timer(&layoutstat->busy_timer, now);
650 651
	if (ktime_equal(mirror->start_time, notime))
		mirror->start_time = now;
652 653 654
	if (mirror->report_interval != 0)
		report_interval = (s64)mirror->report_interval * 1000LL;
	else if (layoutstats_timer != 0)
655
		report_interval = (s64)layoutstats_timer * 1000LL;
656
	if (ktime_to_ms(ktime_sub(now, ffl->last_report_time)) >=
657
			report_interval) {
658
		ffl->last_report_time = now;
659 660 661 662
		return true;
	}

	return false;
663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678
}

static void
nfs4_ff_layout_stat_io_update_requested(struct nfs4_ff_layoutstat *layoutstat,
		__u64 requested)
{
	struct nfs4_ff_io_stat *iostat = &layoutstat->io_stat;

	iostat->ops_requested++;
	iostat->bytes_requested += requested;
}

static void
nfs4_ff_layout_stat_io_update_completed(struct nfs4_ff_layoutstat *layoutstat,
		__u64 requested,
		__u64 completed,
679 680
		ktime_t time_completed,
		ktime_t time_started)
681 682
{
	struct nfs4_ff_io_stat *iostat = &layoutstat->io_stat;
683
	ktime_t completion_time = ktime_sub(time_completed, time_started);
684 685 686 687 688 689
	ktime_t timer;

	iostat->ops_completed++;
	iostat->bytes_completed += completed;
	iostat->bytes_not_delivered += requested - completed;

690
	timer = nfs4_ff_end_busy_timer(&layoutstat->busy_timer, time_completed);
691 692 693
	iostat->total_busy_time =
			ktime_add(iostat->total_busy_time, timer);
	iostat->aggregate_completion_time =
694 695
			ktime_add(iostat->aggregate_completion_time,
					completion_time);
696 697 698
}

static void
699 700
nfs4_ff_layout_stat_io_start_read(struct inode *inode,
		struct nfs4_ff_layout_mirror *mirror,
701
		__u64 requested, ktime_t now)
702
{
703 704
	bool report;

705
	spin_lock(&mirror->lock);
706
	report = nfs4_ff_layoutstat_start_io(mirror, &mirror->read_stat, now);
707 708
	nfs4_ff_layout_stat_io_update_requested(&mirror->read_stat, requested);
	spin_unlock(&mirror->lock);
709 710

	if (report)
711
		pnfs_report_layoutstat(inode, GFP_KERNEL);
712 713 714 715 716 717 718 719 720 721 722
}

static void
nfs4_ff_layout_stat_io_end_read(struct rpc_task *task,
		struct nfs4_ff_layout_mirror *mirror,
		__u64 requested,
		__u64 completed)
{
	spin_lock(&mirror->lock);
	nfs4_ff_layout_stat_io_update_completed(&mirror->read_stat,
			requested, completed,
723
			ktime_get(), task->tk_start);
724 725 726 727
	spin_unlock(&mirror->lock);
}

static void
728 729
nfs4_ff_layout_stat_io_start_write(struct inode *inode,
		struct nfs4_ff_layout_mirror *mirror,
730
		__u64 requested, ktime_t now)
731
{
732 733
	bool report;

734
	spin_lock(&mirror->lock);
735
	report = nfs4_ff_layoutstat_start_io(mirror , &mirror->write_stat, now);
736 737
	nfs4_ff_layout_stat_io_update_requested(&mirror->write_stat, requested);
	spin_unlock(&mirror->lock);
738 739

	if (report)
740
		pnfs_report_layoutstat(inode, GFP_NOIO);
741 742 743 744 745 746 747 748 749 750 751 752 753 754
}

static void
nfs4_ff_layout_stat_io_end_write(struct rpc_task *task,
		struct nfs4_ff_layout_mirror *mirror,
		__u64 requested,
		__u64 completed,
		enum nfs3_stable_how committed)
{
	if (committed == NFS_UNSTABLE)
		requested = completed = 0;

	spin_lock(&mirror->lock);
	nfs4_ff_layout_stat_io_update_completed(&mirror->write_stat,
755
			requested, completed, ktime_get(), task->tk_start);
756 757 758
	spin_unlock(&mirror->lock);
}

759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785
static int
ff_layout_alloc_commit_info(struct pnfs_layout_segment *lseg,
			    struct nfs_commit_info *cinfo,
			    gfp_t gfp_flags)
{
	struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg);
	struct pnfs_commit_bucket *buckets;
	int size;

	if (cinfo->ds->nbuckets != 0) {
		/* This assumes there is only one RW lseg per file.
		 * To support multiple lseg per file, we need to
		 * change struct pnfs_commit_bucket to allow dynamic
		 * increasing nbuckets.
		 */
		return 0;
	}

	size = ff_layout_get_lseg_count(fls) * FF_LAYOUT_MIRROR_COUNT(lseg);

	buckets = kcalloc(size, sizeof(struct pnfs_commit_bucket),
			  gfp_flags);
	if (!buckets)
		return -ENOMEM;
	else {
		int i;

786
		spin_lock(&cinfo->inode->i_lock);
787 788 789 790 791 792 793 794 795 796 797 798 799
		if (cinfo->ds->nbuckets != 0)
			kfree(buckets);
		else {
			cinfo->ds->buckets = buckets;
			cinfo->ds->nbuckets = size;
			for (i = 0; i < size; i++) {
				INIT_LIST_HEAD(&buckets[i].written);
				INIT_LIST_HEAD(&buckets[i].committing);
				/* mark direct verifier as unset */
				buckets[i].direct_verf.committed =
					NFS_INVALID_STABLE_HOW;
			}
		}
800
		spin_unlock(&cinfo->inode->i_lock);
801 802 803 804 805
		return 0;
	}
}

static struct nfs4_pnfs_ds *
806 807
ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg,
				  int start_idx,
808 809
				  int *best_idx)
{
810
	struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg);
811
	struct nfs4_pnfs_ds *ds;
812
	bool fail_return = false;
813 814 815
	int idx;

	/* mirrors are sorted by efficiency */
816
	for (idx = start_idx; idx < fls->mirror_array_cnt; idx++) {
817 818 819
		if (idx+1 == fls->mirror_array_cnt)
			fail_return = true;
		ds = nfs4_ff_layout_prepare_ds(lseg, idx, fail_return);
820 821 822 823 824 825 826 827 828
		if (ds) {
			*best_idx = idx;
			return ds;
		}
	}

	return NULL;
}

829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858
static void
ff_layout_pg_get_read(struct nfs_pageio_descriptor *pgio,
		      struct nfs_page *req,
		      bool strict_iomode)
{
retry_strict:
	pnfs_put_lseg(pgio->pg_lseg);
	pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
					   req->wb_context,
					   0,
					   NFS4_MAX_UINT64,
					   IOMODE_READ,
					   strict_iomode,
					   GFP_KERNEL);
	if (IS_ERR(pgio->pg_lseg)) {
		pgio->pg_error = PTR_ERR(pgio->pg_lseg);
		pgio->pg_lseg = NULL;
	}

	/* If we don't have checking, do get a IOMODE_RW
	 * segment, and the server wants to avoid READs
	 * there, then retry!
	 */
	if (pgio->pg_lseg && !strict_iomode &&
	    ff_layout_avoid_read_on_rw(pgio->pg_lseg)) {
		strict_iomode = true;
		goto retry_strict;
	}
}

859 860 861 862 863 864 865 866 867
static void
ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
			struct nfs_page *req)
{
	struct nfs_pgio_mirror *pgm;
	struct nfs4_ff_layout_mirror *mirror;
	struct nfs4_pnfs_ds *ds;
	int ds_idx;

868
retry:
869
	/* Use full layout for now */
870 871 872 873
	if (!pgio->pg_lseg)
		ff_layout_pg_get_read(pgio, req, false);
	else if (ff_layout_avoid_read_on_rw(pgio->pg_lseg))
		ff_layout_pg_get_read(pgio, req, true);
874

875 876 877 878
	/* If no lseg, fall back to read through mds */
	if (pgio->pg_lseg == NULL)
		goto out_mds;

879
	ds = ff_layout_choose_best_ds_for_read(pgio->pg_lseg, 0, &ds_idx);
880
	if (!ds) {
881
		if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg))
882
			goto out_mds;
883 884 885 886 887
		pnfs_put_lseg(pgio->pg_lseg);
		pgio->pg_lseg = NULL;
		/* Sleep for 1 second before retrying */
		ssleep(1);
		goto retry;
888 889
	}

890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915
	mirror = FF_LAYOUT_COMP(pgio->pg_lseg, ds_idx);

	pgio->pg_mirror_idx = ds_idx;

	/* read always uses only one mirror - idx 0 for pgio layer */
	pgm = &pgio->pg_mirrors[0];
	pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].rsize;

	return;
out_mds:
	pnfs_put_lseg(pgio->pg_lseg);
	pgio->pg_lseg = NULL;
	nfs_pageio_reset_read_mds(pgio);
}

static void
ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio,
			struct nfs_page *req)
{
	struct nfs4_ff_layout_mirror *mirror;
	struct nfs_pgio_mirror *pgm;
	struct nfs_commit_info cinfo;
	struct nfs4_pnfs_ds *ds;
	int i;
	int status;

916
retry:
917
	if (!pgio->pg_lseg) {
918 919 920 921 922
		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
						   req->wb_context,
						   0,
						   NFS4_MAX_UINT64,
						   IOMODE_RW,
923
						   false,
924
						   GFP_NOFS);
925 926 927 928 929 930
		if (IS_ERR(pgio->pg_lseg)) {
			pgio->pg_error = PTR_ERR(pgio->pg_lseg);
			pgio->pg_lseg = NULL;
			return;
		}
	}
931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946
	/* If no lseg, fall back to write through mds */
	if (pgio->pg_lseg == NULL)
		goto out_mds;

	nfs_init_cinfo(&cinfo, pgio->pg_inode, pgio->pg_dreq);
	status = ff_layout_alloc_commit_info(pgio->pg_lseg, &cinfo, GFP_NOFS);
	if (status < 0)
		goto out_mds;

	/* Use a direct mapping of ds_idx to pgio mirror_idx */
	if (WARN_ON_ONCE(pgio->pg_mirror_count !=
	    FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg)))
		goto out_mds;

	for (i = 0; i < pgio->pg_mirror_count; i++) {
		ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, i, true);
947
		if (!ds) {
948
			if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg))
949
				goto out_mds;
950 951 952 953 954
			pnfs_put_lseg(pgio->pg_lseg);
			pgio->pg_lseg = NULL;
			/* Sleep for 1 second before retrying */
			ssleep(1);
			goto retry;
955
		}
956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972
		pgm = &pgio->pg_mirrors[i];
		mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i);
		pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].wsize;
	}

	return;

out_mds:
	pnfs_put_lseg(pgio->pg_lseg);
	pgio->pg_lseg = NULL;
	nfs_pageio_reset_write_mds(pgio);
}

static unsigned int
ff_layout_pg_get_mirror_count_write(struct nfs_pageio_descriptor *pgio,
				    struct nfs_page *req)
{
973
	if (!pgio->pg_lseg) {
974 975 976 977 978
		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
						   req->wb_context,
						   0,
						   NFS4_MAX_UINT64,
						   IOMODE_RW,
979
						   false,
980
						   GFP_NOFS);
981 982 983 984 985 986
		if (IS_ERR(pgio->pg_lseg)) {
			pgio->pg_error = PTR_ERR(pgio->pg_lseg);
			pgio->pg_lseg = NULL;
			goto out;
		}
	}
987 988 989 990 991
	if (pgio->pg_lseg)
		return FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg);

	/* no lseg means that pnfs is not in use, so no mirroring here */
	nfs_pageio_reset_write_mds(pgio);
992
out:
993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025
	return 1;
}

static const struct nfs_pageio_ops ff_layout_pg_read_ops = {
	.pg_init = ff_layout_pg_init_read,
	.pg_test = pnfs_generic_pg_test,
	.pg_doio = pnfs_generic_pg_readpages,
	.pg_cleanup = pnfs_generic_pg_cleanup,
};

static const struct nfs_pageio_ops ff_layout_pg_write_ops = {
	.pg_init = ff_layout_pg_init_write,
	.pg_test = pnfs_generic_pg_test,
	.pg_doio = pnfs_generic_pg_writepages,
	.pg_get_mirror_count = ff_layout_pg_get_mirror_count_write,
	.pg_cleanup = pnfs_generic_pg_cleanup,
};

static void ff_layout_reset_write(struct nfs_pgio_header *hdr, bool retry_pnfs)
{
	struct rpc_task *task = &hdr->task;

	pnfs_layoutcommit_inode(hdr->inode, false);

	if (retry_pnfs) {
		dprintk("%s Reset task %5u for i/o through pNFS "
			"(req %s/%llu, %u bytes @ offset %llu)\n", __func__,
			hdr->task.tk_pid,
			hdr->inode->i_sb->s_id,
			(unsigned long long)NFS_FILEID(hdr->inode),
			hdr->args.count,
			(unsigned long long)hdr->args.offset);

1026
		hdr->completion_ops->reschedule_io(hdr);
1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085
		return;
	}

	if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
		dprintk("%s Reset task %5u for i/o through MDS "
			"(req %s/%llu, %u bytes @ offset %llu)\n", __func__,
			hdr->task.tk_pid,
			hdr->inode->i_sb->s_id,
			(unsigned long long)NFS_FILEID(hdr->inode),
			hdr->args.count,
			(unsigned long long)hdr->args.offset);

		task->tk_status = pnfs_write_done_resend_to_mds(hdr);
	}
}

static void ff_layout_reset_read(struct nfs_pgio_header *hdr)
{
	struct rpc_task *task = &hdr->task;

	pnfs_layoutcommit_inode(hdr->inode, false);

	if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
		dprintk("%s Reset task %5u for i/o through MDS "
			"(req %s/%llu, %u bytes @ offset %llu)\n", __func__,
			hdr->task.tk_pid,
			hdr->inode->i_sb->s_id,
			(unsigned long long)NFS_FILEID(hdr->inode),
			hdr->args.count,
			(unsigned long long)hdr->args.offset);

		task->tk_status = pnfs_read_done_resend_to_mds(hdr);
	}
}

static int ff_layout_async_handle_error_v4(struct rpc_task *task,
					   struct nfs4_state *state,
					   struct nfs_client *clp,
					   struct pnfs_layout_segment *lseg,
					   int idx)
{
	struct pnfs_layout_hdr *lo = lseg->pls_layout;
	struct inode *inode = lo->plh_inode;
	struct nfs_server *mds_server = NFS_SERVER(inode);

	struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx);
	struct nfs_client *mds_client = mds_server->nfs_client;
	struct nfs4_slot_table *tbl = &clp->cl_session->fc_slot_table;

	if (task->tk_status >= 0)
		return 0;

	switch (task->tk_status) {
	/* MDS state errors */
	case -NFS4ERR_DELEG_REVOKED:
	case -NFS4ERR_ADMIN_REVOKED:
	case -NFS4ERR_BAD_STATEID:
		if (state == NULL)
			break;
1086
		nfs_remove_bad_delegation(state->inode, NULL);
1087 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 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151
	case -NFS4ERR_OPENMODE:
		if (state == NULL)
			break;
		if (nfs4_schedule_stateid_recovery(mds_server, state) < 0)
			goto out_bad_stateid;
		goto wait_on_recovery;
	case -NFS4ERR_EXPIRED:
		if (state != NULL) {
			if (nfs4_schedule_stateid_recovery(mds_server, state) < 0)
				goto out_bad_stateid;
		}
		nfs4_schedule_lease_recovery(mds_client);
		goto wait_on_recovery;
	/* DS session errors */
	case -NFS4ERR_BADSESSION:
	case -NFS4ERR_BADSLOT:
	case -NFS4ERR_BAD_HIGH_SLOT:
	case -NFS4ERR_DEADSESSION:
	case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
	case -NFS4ERR_SEQ_FALSE_RETRY:
	case -NFS4ERR_SEQ_MISORDERED:
		dprintk("%s ERROR %d, Reset session. Exchangeid "
			"flags 0x%x\n", __func__, task->tk_status,
			clp->cl_exchange_flags);
		nfs4_schedule_session_recovery(clp->cl_session, task->tk_status);
		break;
	case -NFS4ERR_DELAY:
	case -NFS4ERR_GRACE:
		rpc_delay(task, FF_LAYOUT_POLL_RETRY_MAX);
		break;
	case -NFS4ERR_RETRY_UNCACHED_REP:
		break;
	/* Invalidate Layout errors */
	case -NFS4ERR_PNFS_NO_LAYOUT:
	case -ESTALE:           /* mapped NFS4ERR_STALE */
	case -EBADHANDLE:       /* mapped NFS4ERR_BADHANDLE */
	case -EISDIR:           /* mapped NFS4ERR_ISDIR */
	case -NFS4ERR_FHEXPIRED:
	case -NFS4ERR_WRONG_TYPE:
		dprintk("%s Invalid layout error %d\n", __func__,
			task->tk_status);
		/*
		 * Destroy layout so new i/o will get a new layout.
		 * Layout will not be destroyed until all current lseg
		 * references are put. Mark layout as invalid to resend failed
		 * i/o and all i/o waiting on the slot table to the MDS until
		 * layout is destroyed and a new valid layout is obtained.
		 */
		pnfs_destroy_layout(NFS_I(inode));
		rpc_wake_up(&tbl->slot_tbl_waitq);
		goto reset;
	/* RPC connection errors */
	case -ECONNREFUSED:
	case -EHOSTDOWN:
	case -EHOSTUNREACH:
	case -ENETUNREACH:
	case -EIO:
	case -ETIMEDOUT:
	case -EPIPE:
		dprintk("%s DS connection error %d\n", __func__,
			task->tk_status);
		nfs4_mark_deviceid_unavailable(devid);
		rpc_wake_up(&tbl->slot_tbl_waitq);
		/* fall through */
	default:
1152
		if (ff_layout_avoid_mds_available_ds(lseg))
1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181
			return -NFS4ERR_RESET_TO_PNFS;
reset:
		dprintk("%s Retry through MDS. Error %d\n", __func__,
			task->tk_status);
		return -NFS4ERR_RESET_TO_MDS;
	}
out:
	task->tk_status = 0;
	return -EAGAIN;
out_bad_stateid:
	task->tk_status = -EIO;
	return 0;
wait_on_recovery:
	rpc_sleep_on(&mds_client->cl_rpcwaitq, task, NULL);
	if (test_bit(NFS4CLNT_MANAGER_RUNNING, &mds_client->cl_state) == 0)
		rpc_wake_up_queued_task(&mds_client->cl_rpcwaitq, task);
	goto out;
}

/* Retry all errors through either pNFS or MDS except for -EJUKEBOX */
static int ff_layout_async_handle_error_v3(struct rpc_task *task,
					   struct pnfs_layout_segment *lseg,
					   int idx)
{
	struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx);

	if (task->tk_status >= 0)
		return 0;

1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194
	switch (task->tk_status) {
	/* File access problems. Don't mark the device as unavailable */
	case -EACCES:
	case -ESTALE:
	case -EISDIR:
	case -EBADHANDLE:
	case -ELOOP:
	case -ENOSPC:
		break;
	case -EJUKEBOX:
		nfs_inc_stats(lseg->pls_layout->plh_inode, NFSIOS_DELAY);
		goto out_retry;
	default:
1195 1196 1197 1198
		dprintk("%s DS connection error %d\n", __func__,
			task->tk_status);
		nfs4_mark_deviceid_unavailable(devid);
	}
1199 1200 1201
	/* FIXME: Need to prevent infinite looping here. */
	return -NFS4ERR_RESET_TO_PNFS;
out_retry:
1202
	task->tk_status = 0;
1203
	rpc_restart_call_prepare(task);
1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230
	rpc_delay(task, NFS_JUKEBOX_RETRY_TIME);
	return -EAGAIN;
}

static int ff_layout_async_handle_error(struct rpc_task *task,
					struct nfs4_state *state,
					struct nfs_client *clp,
					struct pnfs_layout_segment *lseg,
					int idx)
{
	int vers = clp->cl_nfs_mod->rpc_vers->number;

	switch (vers) {
	case 3:
		return ff_layout_async_handle_error_v3(task, lseg, idx);
	case 4:
		return ff_layout_async_handle_error_v4(task, state, clp,
						       lseg, idx);
	default:
		/* should never happen */
		WARN_ON_ONCE(1);
		return 0;
	}
}

static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg,
					int idx, u64 offset, u64 length,
1231
					u32 status, int opnum, int error)
1232 1233 1234 1235
{
	struct nfs4_ff_layout_mirror *mirror;
	int err;

1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260
	if (status == 0) {
		switch (error) {
		case -ETIMEDOUT:
		case -EPFNOSUPPORT:
		case -EPROTONOSUPPORT:
		case -EOPNOTSUPP:
		case -ECONNREFUSED:
		case -ECONNRESET:
		case -EHOSTDOWN:
		case -EHOSTUNREACH:
		case -ENETUNREACH:
		case -EADDRINUSE:
		case -ENOBUFS:
		case -EPIPE:
		case -EPERM:
			status = NFS4ERR_NXIO;
			break;
		case -EACCES:
			status = NFS4ERR_ACCESS;
			break;
		default:
			return;
		}
	}

1261 1262 1263 1264 1265 1266 1267 1268
	switch (status) {
	case NFS4ERR_DELAY:
	case NFS4ERR_GRACE:
		return;
	default:
		break;
	}

1269 1270 1271 1272
	mirror = FF_LAYOUT_COMP(lseg, idx);
	err = ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout),
				       mirror, offset, length, status, opnum,
				       GFP_NOIO);
1273
	pnfs_error_mark_layout_for_return(lseg->pls_layout->plh_inode, lseg);
1274 1275 1276 1277 1278 1279 1280 1281 1282 1283
	dprintk("%s: err %d op %d status %u\n", __func__, err, opnum, status);
}

/* NFS_PROTO call done callback routines */
static int ff_layout_read_done_cb(struct rpc_task *task,
				struct nfs_pgio_header *hdr)
{
	int err;

	trace_nfs4_pnfs_read(hdr, task->tk_status);
1284
	if (task->tk_status < 0)
1285 1286
		ff_layout_io_track_ds_error(hdr->lseg, hdr->pgio_mirror_idx,
					    hdr->args.offset, hdr->args.count,
1287 1288
					    hdr->res.op_status, OP_READ,
					    task->tk_status);
1289 1290 1291 1292 1293 1294
	err = ff_layout_async_handle_error(task, hdr->args.context->state,
					   hdr->ds_clp, hdr->lseg,
					   hdr->pgio_mirror_idx);

	switch (err) {
	case -NFS4ERR_RESET_TO_PNFS:
1295 1296 1297 1298
		if (ff_layout_choose_best_ds_for_read(hdr->lseg,
					hdr->pgio_mirror_idx + 1,
					&hdr->pgio_mirror_idx))
			goto out_eagain;
1299
		ff_layout_read_record_layoutstats_done(task, hdr);
1300 1301 1302 1303 1304 1305
		pnfs_read_resend_pnfs(hdr);
		return task->tk_status;
	case -NFS4ERR_RESET_TO_MDS:
		ff_layout_reset_read(hdr);
		return task->tk_status;
	case -EAGAIN:
1306
		goto out_eagain;
1307 1308 1309
	}

	return 0;
1310 1311 1312
out_eagain:
	rpc_restart_call_prepare(task);
	return -EAGAIN;
1313 1314
}

1315 1316 1317 1318 1319 1320
static bool
ff_layout_need_layoutcommit(struct pnfs_layout_segment *lseg)
{
	return !(FF_LAYOUT_LSEG(lseg)->flags & FF_FLAGS_NO_LAYOUTCOMMIT);
}

1321 1322 1323 1324 1325 1326 1327 1328 1329 1330
/*
 * We reference the rpc_cred of the first WRITE that triggers the need for
 * a LAYOUTCOMMIT, and use it to send the layoutcommit compound.
 * rfc5661 is not clear about which credential should be used.
 *
 * Flexlayout client should treat DS replied FILE_SYNC as DATA_SYNC, so
 * to follow http://www.rfc-editor.org/errata_search.php?rfc=5661&eid=2751
 * we always send layoutcommit after DS writes.
 */
static void
1331 1332 1333
ff_layout_set_layoutcommit(struct inode *inode,
		struct pnfs_layout_segment *lseg,
		loff_t end_offset)
1334
{
1335
	if (!ff_layout_need_layoutcommit(lseg))
1336 1337
		return;

1338 1339 1340
	pnfs_set_layoutcommit(inode, lseg, end_offset);
	dprintk("%s inode %lu pls_end_pos %llu\n", __func__, inode->i_ino,
		(unsigned long long) NFS_I(inode)->layout->plh_lwb);
1341 1342 1343
}

static bool
1344
ff_layout_device_unavailable(struct pnfs_layout_segment *lseg, int idx)
1345 1346 1347 1348 1349 1350 1351
{
	/* No mirroring for now */
	struct nfs4_deviceid_node *node = FF_LAYOUT_DEVID_NODE(lseg, idx);

	return ff_layout_test_devid_unavailable(node);
}

1352 1353
static void ff_layout_read_record_layoutstats_start(struct rpc_task *task,
		struct nfs_pgio_header *hdr)
1354
{
1355 1356
	if (test_and_set_bit(NFS_IOHDR_STAT, &hdr->flags))
		return;
1357
	nfs4_ff_layout_stat_io_start_read(hdr->inode,
1358
			FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx),
1359 1360
			hdr->args.count,
			task->tk_start);
1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372
}

static void ff_layout_read_record_layoutstats_done(struct rpc_task *task,
		struct nfs_pgio_header *hdr)
{
	if (!test_and_clear_bit(NFS_IOHDR_STAT, &hdr->flags))
		return;
	nfs4_ff_layout_stat_io_end_read(task,
			FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx),
			hdr->args.count,
			hdr->res.count);
}
1373

1374 1375 1376
static int ff_layout_read_prepare_common(struct rpc_task *task,
					 struct nfs_pgio_header *hdr)
{
1377 1378 1379 1380
	if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags))) {
		rpc_exit(task, -EIO);
		return -EIO;
	}
1381 1382
	if (ff_layout_device_unavailable(hdr->lseg, hdr->pgio_mirror_idx)) {
		rpc_exit(task, -EHOSTDOWN);
1383 1384 1385
		return -EAGAIN;
	}

1386
	ff_layout_read_record_layoutstats_start(task, hdr);
1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430
	return 0;
}

/*
 * Call ops for the async read/write cases
 * In the case of dense layouts, the offset needs to be reset to its
 * original value.
 */
static void ff_layout_read_prepare_v3(struct rpc_task *task, void *data)
{
	struct nfs_pgio_header *hdr = data;

	if (ff_layout_read_prepare_common(task, hdr))
		return;

	rpc_call_start(task);
}

static int ff_layout_setup_sequence(struct nfs_client *ds_clp,
				    struct nfs4_sequence_args *args,
				    struct nfs4_sequence_res *res,
				    struct rpc_task *task)
{
	if (ds_clp->cl_session)
		return nfs41_setup_sequence(ds_clp->cl_session,
					   args,
					   res,
					   task);
	return nfs40_setup_sequence(ds_clp->cl_slot_tbl,
				   args,
				   res,
				   task);
}

static void ff_layout_read_prepare_v4(struct rpc_task *task, void *data)
{
	struct nfs_pgio_header *hdr = data;

	if (ff_layout_setup_sequence(hdr->ds_clp,
				     &hdr->args.seq_args,
				     &hdr->res.seq_res,
				     task))
		return;

1431 1432 1433
	if (ff_layout_read_prepare_common(task, hdr))
		return;

1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458
	if (nfs4_set_rw_stateid(&hdr->args.stateid, hdr->args.context,
			hdr->args.lock_context, FMODE_READ) == -EIO)
		rpc_exit(task, -EIO); /* lost lock, terminate I/O */
}

static void ff_layout_read_call_done(struct rpc_task *task, void *data)
{
	struct nfs_pgio_header *hdr = data;

	dprintk("--> %s task->tk_status %d\n", __func__, task->tk_status);

	if (test_bit(NFS_IOHDR_REDO, &hdr->flags) &&
	    task->tk_status == 0) {
		nfs4_sequence_done(task, &hdr->res.seq_res);
		return;
	}

	/* Note this may cause RPC to be resent */
	hdr->mds_ops->rpc_call_done(task, hdr);
}

static void ff_layout_read_count_stats(struct rpc_task *task, void *data)
{
	struct nfs_pgio_header *hdr = data;

1459
	ff_layout_read_record_layoutstats_done(task, hdr);
1460 1461 1462 1463
	rpc_count_iostats_metrics(task,
	    &NFS_CLIENT(hdr->inode)->cl_metrics[NFSPROC4_CLNT_READ]);
}

1464 1465 1466 1467 1468 1469 1470 1471 1472
static void ff_layout_read_release(void *data)
{
	struct nfs_pgio_header *hdr = data;

	ff_layout_read_record_layoutstats_done(&hdr->task, hdr);
	pnfs_generic_rw_release(data);
}


1473 1474 1475
static int ff_layout_write_done_cb(struct rpc_task *task,
				struct nfs_pgio_header *hdr)
{
1476
	loff_t end_offs = 0;
1477 1478 1479
	int err;

	trace_nfs4_pnfs_write(hdr, task->tk_status);
1480
	if (task->tk_status < 0)
1481 1482
		ff_layout_io_track_ds_error(hdr->lseg, hdr->pgio_mirror_idx,
					    hdr->args.offset, hdr->args.count,
1483 1484
					    hdr->res.op_status, OP_WRITE,
					    task->tk_status);
1485 1486 1487 1488 1489 1490
	err = ff_layout_async_handle_error(task, hdr->args.context->state,
					   hdr->ds_clp, hdr->lseg,
					   hdr->pgio_mirror_idx);

	switch (err) {
	case -NFS4ERR_RESET_TO_PNFS:
1491 1492
		ff_layout_reset_write(hdr, true);
		return task->tk_status;
1493
	case -NFS4ERR_RESET_TO_MDS:
1494
		ff_layout_reset_write(hdr, false);
1495 1496 1497 1498 1499 1500 1501
		return task->tk_status;
	case -EAGAIN:
		return -EAGAIN;
	}

	if (hdr->res.verf->committed == NFS_FILE_SYNC ||
	    hdr->res.verf->committed == NFS_DATA_SYNC)
1502 1503 1504 1505
		end_offs = hdr->mds_offset + (loff_t)hdr->res.count;

	/* Note: if the write is unstable, don't set end_offs until commit */
	ff_layout_set_layoutcommit(hdr->inode, hdr->lseg, end_offs);
1506

1507 1508
	/* zero out fattr since we don't care DS attr at all */
	hdr->fattr.valid = 0;
1509 1510 1511
	if (task->tk_status >= 0)
		nfs_writeback_update_inode(hdr);

1512 1513 1514 1515 1516 1517 1518 1519 1520
	return 0;
}

static int ff_layout_commit_done_cb(struct rpc_task *task,
				     struct nfs_commit_data *data)
{
	int err;

	trace_nfs4_pnfs_commit_ds(data, task->tk_status);
1521
	if (task->tk_status < 0)
1522 1523
		ff_layout_io_track_ds_error(data->lseg, data->ds_commit_index,
					    data->args.offset, data->args.count,
1524 1525
					    data->res.op_status, OP_COMMIT,
					    task->tk_status);
1526 1527 1528 1529 1530
	err = ff_layout_async_handle_error(task, NULL, data->ds_clp,
					   data->lseg, data->ds_commit_index);

	switch (err) {
	case -NFS4ERR_RESET_TO_PNFS:
1531 1532
		pnfs_generic_prepare_to_resend_writes(data);
		return -EAGAIN;
1533 1534 1535 1536 1537 1538 1539 1540
	case -NFS4ERR_RESET_TO_MDS:
		pnfs_generic_prepare_to_resend_writes(data);
		return -EAGAIN;
	case -EAGAIN:
		rpc_restart_call_prepare(task);
		return -EAGAIN;
	}

1541
	ff_layout_set_layoutcommit(data->inode, data->lseg, data->lwb);
1542 1543 1544 1545

	return 0;
}

1546 1547
static void ff_layout_write_record_layoutstats_start(struct rpc_task *task,
		struct nfs_pgio_header *hdr)
1548
{
1549 1550
	if (test_and_set_bit(NFS_IOHDR_STAT, &hdr->flags))
		return;
1551
	nfs4_ff_layout_stat_io_start_write(hdr->inode,
1552
			FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx),
1553 1554
			hdr->args.count,
			task->tk_start);
1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566
}

static void ff_layout_write_record_layoutstats_done(struct rpc_task *task,
		struct nfs_pgio_header *hdr)
{
	if (!test_and_clear_bit(NFS_IOHDR_STAT, &hdr->flags))
		return;
	nfs4_ff_layout_stat_io_end_write(task,
			FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx),
			hdr->args.count, hdr->res.count,
			hdr->res.verf->committed);
}
1567

1568 1569 1570
static int ff_layout_write_prepare_common(struct rpc_task *task,
					  struct nfs_pgio_header *hdr)
{
1571 1572 1573 1574 1575
	if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags))) {
		rpc_exit(task, -EIO);
		return -EIO;
	}

1576 1577
	if (ff_layout_device_unavailable(hdr->lseg, hdr->pgio_mirror_idx)) {
		rpc_exit(task, -EHOSTDOWN);
1578 1579 1580
		return -EAGAIN;
	}

1581
	ff_layout_write_record_layoutstats_start(task, hdr);
1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604
	return 0;
}

static void ff_layout_write_prepare_v3(struct rpc_task *task, void *data)
{
	struct nfs_pgio_header *hdr = data;

	if (ff_layout_write_prepare_common(task, hdr))
		return;

	rpc_call_start(task);
}

static void ff_layout_write_prepare_v4(struct rpc_task *task, void *data)
{
	struct nfs_pgio_header *hdr = data;

	if (ff_layout_setup_sequence(hdr->ds_clp,
				     &hdr->args.seq_args,
				     &hdr->res.seq_res,
				     task))
		return;

1605 1606 1607
	if (ff_layout_write_prepare_common(task, hdr))
		return;

1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630
	if (nfs4_set_rw_stateid(&hdr->args.stateid, hdr->args.context,
			hdr->args.lock_context, FMODE_WRITE) == -EIO)
		rpc_exit(task, -EIO); /* lost lock, terminate I/O */
}

static void ff_layout_write_call_done(struct rpc_task *task, void *data)
{
	struct nfs_pgio_header *hdr = data;

	if (test_bit(NFS_IOHDR_REDO, &hdr->flags) &&
	    task->tk_status == 0) {
		nfs4_sequence_done(task, &hdr->res.seq_res);
		return;
	}

	/* Note this may cause RPC to be resent */
	hdr->mds_ops->rpc_call_done(task, hdr);
}

static void ff_layout_write_count_stats(struct rpc_task *task, void *data)
{
	struct nfs_pgio_header *hdr = data;

1631
	ff_layout_write_record_layoutstats_done(task, hdr);
1632 1633 1634 1635
	rpc_count_iostats_metrics(task,
	    &NFS_CLIENT(hdr->inode)->cl_metrics[NFSPROC4_CLNT_WRITE]);
}

1636 1637 1638 1639 1640 1641 1642 1643
static void ff_layout_write_release(void *data)
{
	struct nfs_pgio_header *hdr = data;

	ff_layout_write_record_layoutstats_done(&hdr->task, hdr);
	pnfs_generic_rw_release(data);
}

1644
static void ff_layout_commit_record_layoutstats_start(struct rpc_task *task,
1645 1646
		struct nfs_commit_data *cdata)
{
1647 1648
	if (test_and_set_bit(NFS_IOHDR_STAT, &cdata->flags))
		return;
1649
	nfs4_ff_layout_stat_io_start_write(cdata->inode,
1650
			FF_LAYOUT_COMP(cdata->lseg, cdata->ds_commit_index),
1651
			0, task->tk_start);
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
static void ff_layout_commit_record_layoutstats_done(struct rpc_task *task,
		struct nfs_commit_data *cdata)
{
	struct nfs_page *req;
	__u64 count = 0;

	if (!test_and_clear_bit(NFS_IOHDR_STAT, &cdata->flags))
		return;

	if (task->tk_status == 0) {
		list_for_each_entry(req, &cdata->pages, wb_list)
			count += req->wb_bytes;
	}
	nfs4_ff_layout_stat_io_end_write(task,
			FF_LAYOUT_COMP(cdata->lseg, cdata->ds_commit_index),
			count, count, NFS_FILE_SYNC);
}

static void ff_layout_commit_prepare_common(struct rpc_task *task,
		struct nfs_commit_data *cdata)
{
	ff_layout_commit_record_layoutstats_start(task, cdata);
}

1678 1679
static void ff_layout_commit_prepare_v3(struct rpc_task *task, void *data)
{
1680
	ff_layout_commit_prepare_common(task, data);
1681 1682 1683 1684 1685 1686 1687
	rpc_call_start(task);
}

static void ff_layout_commit_prepare_v4(struct rpc_task *task, void *data)
{
	struct nfs_commit_data *wdata = data;

1688
	if (ff_layout_setup_sequence(wdata->ds_clp,
1689 1690
				 &wdata->args.seq_args,
				 &wdata->res.seq_res,
1691 1692 1693 1694 1695 1696
				 task))
		return;
	ff_layout_commit_prepare_common(task, data);
}

static void ff_layout_commit_done(struct rpc_task *task, void *data)
1697 1698 1699 1700 1701
{
	pnfs_generic_write_commit_done(task, data);
}

static void ff_layout_commit_count_stats(struct rpc_task *task, void *data)
1702 1703 1704
{
	struct nfs_commit_data *cdata = data;

1705
	ff_layout_commit_record_layoutstats_done(task, cdata);
1706 1707 1708 1709
	rpc_count_iostats_metrics(task,
	    &NFS_CLIENT(cdata->inode)->cl_metrics[NFSPROC4_CLNT_COMMIT]);
}

1710 1711 1712 1713 1714 1715 1716 1717
static void ff_layout_commit_release(void *data)
{
	struct nfs_commit_data *cdata = data;

	ff_layout_commit_record_layoutstats_done(&cdata->task, cdata);
	pnfs_generic_commit_release(data);
}

1718 1719 1720 1721
static const struct rpc_call_ops ff_layout_read_call_ops_v3 = {
	.rpc_call_prepare = ff_layout_read_prepare_v3,
	.rpc_call_done = ff_layout_read_call_done,
	.rpc_count_stats = ff_layout_read_count_stats,
1722
	.rpc_release = ff_layout_read_release,
1723 1724 1725 1726 1727 1728
};

static const struct rpc_call_ops ff_layout_read_call_ops_v4 = {
	.rpc_call_prepare = ff_layout_read_prepare_v4,
	.rpc_call_done = ff_layout_read_call_done,
	.rpc_count_stats = ff_layout_read_count_stats,
1729
	.rpc_release = ff_layout_read_release,
1730 1731 1732 1733 1734 1735
};

static const struct rpc_call_ops ff_layout_write_call_ops_v3 = {
	.rpc_call_prepare = ff_layout_write_prepare_v3,
	.rpc_call_done = ff_layout_write_call_done,
	.rpc_count_stats = ff_layout_write_count_stats,
1736
	.rpc_release = ff_layout_write_release,
1737 1738 1739 1740 1741 1742
};

static const struct rpc_call_ops ff_layout_write_call_ops_v4 = {
	.rpc_call_prepare = ff_layout_write_prepare_v4,
	.rpc_call_done = ff_layout_write_call_done,
	.rpc_count_stats = ff_layout_write_count_stats,
1743
	.rpc_release = ff_layout_write_release,
1744 1745 1746 1747
};

static const struct rpc_call_ops ff_layout_commit_call_ops_v3 = {
	.rpc_call_prepare = ff_layout_commit_prepare_v3,
1748
	.rpc_call_done = ff_layout_commit_done,
1749
	.rpc_count_stats = ff_layout_commit_count_stats,
1750
	.rpc_release = ff_layout_commit_release,
1751 1752 1753 1754
};

static const struct rpc_call_ops ff_layout_commit_call_ops_v4 = {
	.rpc_call_prepare = ff_layout_commit_prepare_v4,
1755
	.rpc_call_done = ff_layout_commit_done,
1756
	.rpc_count_stats = ff_layout_commit_count_stats,
1757
	.rpc_release = ff_layout_commit_release,
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
};

static enum pnfs_try_status
ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
{
	struct pnfs_layout_segment *lseg = hdr->lseg;
	struct nfs4_pnfs_ds *ds;
	struct rpc_clnt *ds_clnt;
	struct rpc_cred *ds_cred;
	loff_t offset = hdr->args.offset;
	u32 idx = hdr->pgio_mirror_idx;
	int vers;
	struct nfs_fh *fh;

	dprintk("--> %s ino %lu pgbase %u req %Zu@%llu\n",
		__func__, hdr->inode->i_ino,
		hdr->args.pgbase, (size_t)hdr->args.count, offset);

	ds = nfs4_ff_layout_prepare_ds(lseg, idx, false);
	if (!ds)
		goto out_failed;

	ds_clnt = nfs4_ff_find_or_create_ds_client(lseg, idx, ds->ds_clp,
						   hdr->inode);
	if (IS_ERR(ds_clnt))
		goto out_failed;

	ds_cred = ff_layout_get_ds_cred(lseg, idx, hdr->cred);
1786
	if (!ds_cred)
1787 1788 1789 1790 1791 1792 1793
		goto out_failed;

	vers = nfs4_ff_layout_ds_version(lseg, idx);

	dprintk("%s USE DS: %s cl_count %d vers %d\n", __func__,
		ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count), vers);

1794
	hdr->pgio_done_cb = ff_layout_read_done_cb;
1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811
	atomic_inc(&ds->ds_clp->cl_count);
	hdr->ds_clp = ds->ds_clp;
	fh = nfs4_ff_layout_select_ds_fh(lseg, idx);
	if (fh)
		hdr->args.fh = fh;
	/*
	 * Note that if we ever decide to split across DSes,
	 * then we may need to handle dense-like offsets.
	 */
	hdr->args.offset = offset;
	hdr->mds_offset = offset;

	/* Perform an asynchronous read to ds */
	nfs_initiate_pgio(ds_clnt, hdr, ds_cred, ds->ds_clp->rpc_ops,
			  vers == 3 ? &ff_layout_read_call_ops_v3 :
				      &ff_layout_read_call_ops_v4,
			  0, RPC_TASK_SOFTCONN);
1812
	put_rpccred(ds_cred);
1813 1814 1815
	return PNFS_ATTEMPTED;

out_failed:
1816
	if (ff_layout_avoid_mds_available_ds(lseg))
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
		return PNFS_TRY_AGAIN;
	return PNFS_NOT_ATTEMPTED;
}

/* Perform async writes. */
static enum pnfs_try_status
ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
{
	struct pnfs_layout_segment *lseg = hdr->lseg;
	struct nfs4_pnfs_ds *ds;
	struct rpc_clnt *ds_clnt;
	struct rpc_cred *ds_cred;
	loff_t offset = hdr->args.offset;
	int vers;
	struct nfs_fh *fh;
	int idx = hdr->pgio_mirror_idx;

	ds = nfs4_ff_layout_prepare_ds(lseg, idx, true);
	if (!ds)
		return PNFS_NOT_ATTEMPTED;

	ds_clnt = nfs4_ff_find_or_create_ds_client(lseg, idx, ds->ds_clp,
						   hdr->inode);
	if (IS_ERR(ds_clnt))
		return PNFS_NOT_ATTEMPTED;

	ds_cred = ff_layout_get_ds_cred(lseg, idx, hdr->cred);
1844
	if (!ds_cred)
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
		return PNFS_NOT_ATTEMPTED;

	vers = nfs4_ff_layout_ds_version(lseg, idx);

	dprintk("%s ino %lu sync %d req %Zu@%llu DS: %s cl_count %d vers %d\n",
		__func__, hdr->inode->i_ino, sync, (size_t) hdr->args.count,
		offset, ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count),
		vers);

	hdr->pgio_done_cb = ff_layout_write_done_cb;
	atomic_inc(&ds->ds_clp->cl_count);
	hdr->ds_clp = ds->ds_clp;
	hdr->ds_commit_idx = idx;
	fh = nfs4_ff_layout_select_ds_fh(lseg, idx);
	if (fh)
		hdr->args.fh = fh;

	/*
	 * Note that if we ever decide to split across DSes,
	 * then we may need to handle dense-like offsets.
	 */
	hdr->args.offset = offset;

	/* Perform an asynchronous write */
	nfs_initiate_pgio(ds_clnt, hdr, ds_cred, ds->ds_clp->rpc_ops,
			  vers == 3 ? &ff_layout_write_call_ops_v3 :
				      &ff_layout_write_call_ops_v4,
			  sync, RPC_TASK_SOFTCONN);
1873
	put_rpccred(ds_cred);
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
	return PNFS_ATTEMPTED;
}

static u32 calc_ds_index_from_commit(struct pnfs_layout_segment *lseg, u32 i)
{
	return i;
}

static struct nfs_fh *
select_ds_fh_from_commit(struct pnfs_layout_segment *lseg, u32 i)
{
	struct nfs4_ff_layout_segment *flseg = FF_LAYOUT_LSEG(lseg);

	/* FIXME: Assume that there is only one NFS version available
	 * for the DS.
	 */
	return &flseg->mirror_array[i]->fh_versions[0];
}

static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how)
{
	struct pnfs_layout_segment *lseg = data->lseg;
	struct nfs4_pnfs_ds *ds;
	struct rpc_clnt *ds_clnt;
	struct rpc_cred *ds_cred;
	u32 idx;
1900
	int vers, ret;
1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913
	struct nfs_fh *fh;

	idx = calc_ds_index_from_commit(lseg, data->ds_commit_index);
	ds = nfs4_ff_layout_prepare_ds(lseg, idx, true);
	if (!ds)
		goto out_err;

	ds_clnt = nfs4_ff_find_or_create_ds_client(lseg, idx, ds->ds_clp,
						   data->inode);
	if (IS_ERR(ds_clnt))
		goto out_err;

	ds_cred = ff_layout_get_ds_cred(lseg, idx, data->cred);
1914
	if (!ds_cred)
1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928
		goto out_err;

	vers = nfs4_ff_layout_ds_version(lseg, idx);

	dprintk("%s ino %lu, how %d cl_count %d vers %d\n", __func__,
		data->inode->i_ino, how, atomic_read(&ds->ds_clp->cl_count),
		vers);
	data->commit_done_cb = ff_layout_commit_done_cb;
	data->cred = ds_cred;
	atomic_inc(&ds->ds_clp->cl_count);
	data->ds_clp = ds->ds_clp;
	fh = select_ds_fh_from_commit(lseg, data->ds_commit_index);
	if (fh)
		data->args.fh = fh;
1929

1930
	ret = nfs_initiate_commit(ds_clnt, data, ds->ds_clp->rpc_ops,
1931 1932 1933
				   vers == 3 ? &ff_layout_commit_call_ops_v3 :
					       &ff_layout_commit_call_ops_v4,
				   how, RPC_TASK_SOFTCONN);
1934 1935
	put_rpccred(ds_cred);
	return ret;
1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961
out_err:
	pnfs_generic_prepare_to_resend_writes(data);
	pnfs_generic_commit_release(data);
	return -EAGAIN;
}

static int
ff_layout_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
			   int how, struct nfs_commit_info *cinfo)
{
	return pnfs_generic_commit_pagelist(inode, mds_pages, how, cinfo,
					    ff_layout_initiate_commit);
}

static struct pnfs_ds_commit_info *
ff_layout_get_ds_info(struct inode *inode)
{
	struct pnfs_layout_hdr *layout = NFS_I(inode)->layout;

	if (layout == NULL)
		return NULL;

	return &FF_LAYOUT_FROM_HDR(layout)->commit_info;
}

static void
1962
ff_layout_free_deviceid_node(struct nfs4_deviceid_node *d)
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
{
	nfs4_ff_layout_free_deviceid(container_of(d, struct nfs4_ff_layout_ds,
						  id_node));
}

static int ff_layout_encode_ioerr(struct nfs4_flexfile_layout *flo,
				  struct xdr_stream *xdr,
				  const struct nfs4_layoutreturn_args *args)
{
	struct pnfs_layout_hdr *hdr = &flo->generic_hdr;
	__be32 *start;
	int count = 0, ret = 0;

	start = xdr_reserve_space(xdr, 4);
	if (unlikely(!start))
		return -E2BIG;

	/* This assume we always return _ALL_ layouts */
	spin_lock(&hdr->plh_inode->i_lock);
	ret = ff_layout_encode_ds_ioerr(flo, xdr, &count, &args->range);
	spin_unlock(&hdr->plh_inode->i_lock);

	*start = cpu_to_be32(count);

	return ret;
}

/* report nothing for now */
static void ff_layout_encode_iostats(struct nfs4_flexfile_layout *flo,
				     struct xdr_stream *xdr,
				     const struct nfs4_layoutreturn_args *args)
{
	__be32 *p;

	p = xdr_reserve_space(xdr, 4);
	if (likely(p))
		*p = cpu_to_be32(0);
}

static struct nfs4_deviceid_node *
ff_layout_alloc_deviceid_node(struct nfs_server *server,
			      struct pnfs_device *pdev, gfp_t gfp_flags)
{
	struct nfs4_ff_layout_ds *dsaddr;

	dsaddr = nfs4_ff_alloc_deviceid_node(server, pdev, gfp_flags);
	if (!dsaddr)
		return NULL;
	return &dsaddr->id_node;
}

static void
2015
ff_layout_encode_layoutreturn(struct xdr_stream *xdr,
2016 2017
			      const struct nfs4_layoutreturn_args *args)
{
2018
	struct pnfs_layout_hdr *lo = args->layout;
2019 2020 2021 2022 2023 2024 2025
	struct nfs4_flexfile_layout *flo = FF_LAYOUT_FROM_HDR(lo);
	__be32 *start;

	dprintk("%s: Begin\n", __func__);
	start = xdr_reserve_space(xdr, 4);
	BUG_ON(!start);

2026
	ff_layout_encode_ioerr(flo, xdr, args);
2027
	ff_layout_encode_iostats(flo, xdr, args);
2028

2029 2030 2031 2032
	*start = cpu_to_be32((xdr->p - start - 1) * 4);
	dprintk("%s: Return\n", __func__);
}

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 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 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 2186 2187
static int
ff_layout_ntop4(const struct sockaddr *sap, char *buf, const size_t buflen)
{
	const struct sockaddr_in *sin = (struct sockaddr_in *)sap;

	return snprintf(buf, buflen, "%pI4", &sin->sin_addr);
}

static size_t
ff_layout_ntop6_noscopeid(const struct sockaddr *sap, char *buf,
			  const int buflen)
{
	const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap;
	const struct in6_addr *addr = &sin6->sin6_addr;

	/*
	 * RFC 4291, Section 2.2.2
	 *
	 * Shorthanded ANY address
	 */
	if (ipv6_addr_any(addr))
		return snprintf(buf, buflen, "::");

	/*
	 * RFC 4291, Section 2.2.2
	 *
	 * Shorthanded loopback address
	 */
	if (ipv6_addr_loopback(addr))
		return snprintf(buf, buflen, "::1");

	/*
	 * RFC 4291, Section 2.2.3
	 *
	 * Special presentation address format for mapped v4
	 * addresses.
	 */
	if (ipv6_addr_v4mapped(addr))
		return snprintf(buf, buflen, "::ffff:%pI4",
					&addr->s6_addr32[3]);

	/*
	 * RFC 4291, Section 2.2.1
	 */
	return snprintf(buf, buflen, "%pI6c", addr);
}

/* Derived from rpc_sockaddr2uaddr */
static void
ff_layout_encode_netaddr(struct xdr_stream *xdr, struct nfs4_pnfs_ds_addr *da)
{
	struct sockaddr *sap = (struct sockaddr *)&da->da_addr;
	char portbuf[RPCBIND_MAXUADDRPLEN];
	char addrbuf[RPCBIND_MAXUADDRLEN];
	char *netid;
	unsigned short port;
	int len, netid_len;
	__be32 *p;

	switch (sap->sa_family) {
	case AF_INET:
		if (ff_layout_ntop4(sap, addrbuf, sizeof(addrbuf)) == 0)
			return;
		port = ntohs(((struct sockaddr_in *)sap)->sin_port);
		netid = "tcp";
		netid_len = 3;
		break;
	case AF_INET6:
		if (ff_layout_ntop6_noscopeid(sap, addrbuf, sizeof(addrbuf)) == 0)
			return;
		port = ntohs(((struct sockaddr_in6 *)sap)->sin6_port);
		netid = "tcp6";
		netid_len = 4;
		break;
	default:
		/* we only support tcp and tcp6 */
		WARN_ON_ONCE(1);
		return;
	}

	snprintf(portbuf, sizeof(portbuf), ".%u.%u", port >> 8, port & 0xff);
	len = strlcat(addrbuf, portbuf, sizeof(addrbuf));

	p = xdr_reserve_space(xdr, 4 + netid_len);
	xdr_encode_opaque(p, netid, netid_len);

	p = xdr_reserve_space(xdr, 4 + len);
	xdr_encode_opaque(p, addrbuf, len);
}

static void
ff_layout_encode_nfstime(struct xdr_stream *xdr,
			 ktime_t t)
{
	struct timespec64 ts;
	__be32 *p;

	p = xdr_reserve_space(xdr, 12);
	ts = ktime_to_timespec64(t);
	p = xdr_encode_hyper(p, ts.tv_sec);
	*p++ = cpu_to_be32(ts.tv_nsec);
}

static void
ff_layout_encode_io_latency(struct xdr_stream *xdr,
			    struct nfs4_ff_io_stat *stat)
{
	__be32 *p;

	p = xdr_reserve_space(xdr, 5 * 8);
	p = xdr_encode_hyper(p, stat->ops_requested);
	p = xdr_encode_hyper(p, stat->bytes_requested);
	p = xdr_encode_hyper(p, stat->ops_completed);
	p = xdr_encode_hyper(p, stat->bytes_completed);
	p = xdr_encode_hyper(p, stat->bytes_not_delivered);
	ff_layout_encode_nfstime(xdr, stat->total_busy_time);
	ff_layout_encode_nfstime(xdr, stat->aggregate_completion_time);
}

static void
ff_layout_encode_layoutstats(struct xdr_stream *xdr,
			     struct nfs42_layoutstat_args *args,
			     struct nfs42_layoutstat_devinfo *devinfo)
{
	struct nfs4_ff_layout_mirror *mirror = devinfo->layout_private;
	struct nfs4_pnfs_ds_addr *da;
	struct nfs4_pnfs_ds *ds = mirror->mirror_ds->ds;
	struct nfs_fh *fh = &mirror->fh_versions[0];
	__be32 *p, *start;

	da = list_first_entry(&ds->ds_addrs, struct nfs4_pnfs_ds_addr, da_node);
	dprintk("%s: DS %s: encoding address %s\n",
		__func__, ds->ds_remotestr, da->da_remotestr);
	/* layoutupdate length */
	start = xdr_reserve_space(xdr, 4);
	/* netaddr4 */
	ff_layout_encode_netaddr(xdr, da);
	/* nfs_fh4 */
	p = xdr_reserve_space(xdr, 4 + fh->size);
	xdr_encode_opaque(p, fh->data, fh->size);
	/* ff_io_latency4 read */
	spin_lock(&mirror->lock);
	ff_layout_encode_io_latency(xdr, &mirror->read_stat.io_stat);
	/* ff_io_latency4 write */
	ff_layout_encode_io_latency(xdr, &mirror->write_stat.io_stat);
	spin_unlock(&mirror->lock);
	/* nfstime4 */
	ff_layout_encode_nfstime(xdr, ktime_sub(ktime_get(), mirror->start_time));
	/* bool */
	p = xdr_reserve_space(xdr, 4);
	*p = cpu_to_be32(false);

	*start = cpu_to_be32((xdr->p - start - 1) * 4);
}

2188
static int
2189
ff_layout_mirror_prepare_stats(struct nfs42_layoutstat_args *args,
2190 2191
			       struct pnfs_layout_hdr *lo,
			       int dev_limit)
2192
{
2193
	struct nfs4_flexfile_layout *ff_layout = FF_LAYOUT_FROM_HDR(lo);
2194 2195 2196
	struct nfs4_ff_layout_mirror *mirror;
	struct nfs4_deviceid_node *dev;
	struct nfs42_layoutstat_devinfo *devinfo;
2197
	int i = 0;
2198

2199 2200
	list_for_each_entry(mirror, &ff_layout->mirrors, mirrors) {
		if (i >= dev_limit)
2201
			break;
2202
		if (!mirror->mirror_ds)
2203
			continue;
2204 2205 2206 2207 2208
		/* mirror refcount put in cleanup_layoutstats */
		if (!atomic_inc_not_zero(&mirror->ref))
			continue;
		dev = &mirror->mirror_ds->id_node; 
		devinfo = &args->devinfo[i];
2209
		memcpy(&devinfo->dev_id, &dev->deviceid, NFS4_DEVICEID4_SIZE);
2210 2211
		devinfo->offset = 0;
		devinfo->length = NFS4_MAX_UINT64;
2212
		devinfo->read_count = mirror->read_stat.io_stat.ops_completed;
2213
		devinfo->read_bytes = mirror->read_stat.io_stat.bytes_completed;
2214
		devinfo->write_count = mirror->write_stat.io_stat.ops_completed;
2215 2216
		devinfo->write_bytes = mirror->write_stat.io_stat.bytes_completed;
		devinfo->layout_type = LAYOUT_FLEX_FILES;
2217 2218
		devinfo->layoutstats_encode = ff_layout_encode_layoutstats;
		devinfo->layout_private = mirror;
2219

2220
		i++;
2221
	}
2222
	return i;
2223 2224 2225 2226 2227
}

static int
ff_layout_prepare_layoutstats(struct nfs42_layoutstat_args *args)
{
2228 2229
	struct nfs4_flexfile_layout *ff_layout;
	struct nfs4_ff_layout_mirror *mirror;
2230 2231 2232
	int dev_count = 0;

	spin_lock(&args->inode->i_lock);
2233 2234 2235 2236
	ff_layout = FF_LAYOUT_FROM_HDR(NFS_I(args->inode)->layout);
	list_for_each_entry(mirror, &ff_layout->mirrors, mirrors) {
		if (atomic_read(&mirror->ref) != 0)
			dev_count ++;
2237 2238 2239 2240 2241 2242 2243 2244
	}
	spin_unlock(&args->inode->i_lock);
	/* For now, send at most PNFS_LAYOUTSTATS_MAXDEV statistics */
	if (dev_count > PNFS_LAYOUTSTATS_MAXDEV) {
		dprintk("%s: truncating devinfo to limit (%d:%d)\n",
			__func__, dev_count, PNFS_LAYOUTSTATS_MAXDEV);
		dev_count = PNFS_LAYOUTSTATS_MAXDEV;
	}
2245
	args->devinfo = kmalloc_array(dev_count, sizeof(*args->devinfo), GFP_NOIO);
2246 2247 2248 2249
	if (!args->devinfo)
		return -ENOMEM;

	spin_lock(&args->inode->i_lock);
2250 2251
	args->num_dev = ff_layout_mirror_prepare_stats(args,
			&ff_layout->generic_hdr, dev_count);
2252 2253 2254 2255 2256
	spin_unlock(&args->inode->i_lock);

	return 0;
}

2257 2258 2259 2260 2261 2262 2263 2264 2265
static void
ff_layout_cleanup_layoutstats(struct nfs42_layoutstat_data *data)
{
	struct nfs4_ff_layout_mirror *mirror;
	int i;

	for (i = 0; i < data->args.num_dev; i++) {
		mirror = data->args.devinfo[i].layout_private;
		data->args.devinfo[i].layout_private = NULL;
2266
		ff_layout_put_mirror(mirror);
2267 2268 2269
	}
}

2270 2271 2272 2273 2274 2275 2276 2277
static struct pnfs_layoutdriver_type flexfilelayout_type = {
	.id			= LAYOUT_FLEX_FILES,
	.name			= "LAYOUT_FLEX_FILES",
	.owner			= THIS_MODULE,
	.alloc_layout_hdr	= ff_layout_alloc_layout_hdr,
	.free_layout_hdr	= ff_layout_free_layout_hdr,
	.alloc_lseg		= ff_layout_alloc_lseg,
	.free_lseg		= ff_layout_free_lseg,
2278
	.add_lseg		= ff_layout_add_lseg,
2279 2280 2281
	.pg_read_ops		= &ff_layout_pg_read_ops,
	.pg_write_ops		= &ff_layout_pg_write_ops,
	.get_ds_info		= ff_layout_get_ds_info,
2282
	.free_deviceid_node	= ff_layout_free_deviceid_node,
2283
	.mark_request_commit	= pnfs_layout_mark_request_commit,
2284 2285 2286 2287 2288 2289 2290 2291
	.clear_request_commit	= pnfs_generic_clear_request_commit,
	.scan_commit_lists	= pnfs_generic_scan_commit_lists,
	.recover_commit_reqs	= pnfs_generic_recover_commit_reqs,
	.commit_pagelist	= ff_layout_commit_pagelist,
	.read_pagelist		= ff_layout_read_pagelist,
	.write_pagelist		= ff_layout_write_pagelist,
	.alloc_deviceid_node    = ff_layout_alloc_deviceid_node,
	.encode_layoutreturn    = ff_layout_encode_layoutreturn,
2292
	.sync			= pnfs_nfs_generic_sync,
2293
	.prepare_layoutstats	= ff_layout_prepare_layoutstats,
2294
	.cleanup_layoutstats	= ff_layout_cleanup_layoutstats,
2295 2296 2297 2298 2299 2300
};

static int __init nfs4flexfilelayout_init(void)
{
	printk(KERN_INFO "%s: NFSv4 Flexfile Layout Driver Registering...\n",
	       __func__);
2301 2302 2303 2304 2305
	if (!ff_zero_group) {
		ff_zero_group = groups_alloc(0);
		if (!ff_zero_group)
			return -ENOMEM;
	}
2306 2307 2308 2309 2310 2311 2312 2313
	return pnfs_register_layoutdriver(&flexfilelayout_type);
}

static void __exit nfs4flexfilelayout_exit(void)
{
	printk(KERN_INFO "%s: NFSv4 Flexfile Layout Driver Unregistering...\n",
	       __func__);
	pnfs_unregister_layoutdriver(&flexfilelayout_type);
2314 2315 2316 2317
	if (ff_zero_group) {
		put_group_info(ff_zero_group);
		ff_zero_group = NULL;
	}
2318 2319 2320 2321 2322 2323 2324 2325 2326
}

MODULE_ALIAS("nfs-layouttype4-4");

MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("The NFSv4 flexfile layout driver");

module_init(nfs4flexfilelayout_init);
module_exit(nfs4flexfilelayout_exit);