file.c 23.2 KB
Newer Older
1
#include <linux/ceph/ceph_debug.h>
S
Sage Weil 已提交
2

3
#include <linux/module.h>
S
Sage Weil 已提交
4
#include <linux/sched.h>
5
#include <linux/slab.h>
S
Sage Weil 已提交
6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41
#include <linux/file.h>
#include <linux/namei.h>
#include <linux/writeback.h>

#include "super.h"
#include "mds_client.h"

/*
 * Ceph file operations
 *
 * Implement basic open/close functionality, and implement
 * read/write.
 *
 * We implement three modes of file I/O:
 *  - buffered uses the generic_file_aio_{read,write} helpers
 *
 *  - synchronous is used when there is multi-client read/write
 *    sharing, avoids the page cache, and synchronously waits for an
 *    ack from the OSD.
 *
 *  - direct io takes the variant of the sync path that references
 *    user pages directly.
 *
 * fsync() flushes and waits on dirty pages, but just queues metadata
 * for writeback: since the MDS can recover size and mtime there is no
 * need to wait for MDS acknowledgement.
 */


/*
 * Prepare an open request.  Preallocate ceph_cap to avoid an
 * inopportune ENOMEM later.
 */
static struct ceph_mds_request *
prepare_open_request(struct super_block *sb, int flags, int create_mode)
{
42 43
	struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
	struct ceph_mds_client *mdsc = fsc->mdsc;
S
Sage Weil 已提交
44 45 46 47 48 49 50 51 52 53 54 55 56
	struct ceph_mds_request *req;
	int want_auth = USE_ANY_MDS;
	int op = (flags & O_CREAT) ? CEPH_MDS_OP_CREATE : CEPH_MDS_OP_OPEN;

	if (flags & (O_WRONLY|O_RDWR|O_CREAT|O_TRUNC))
		want_auth = USE_AUTH_MDS;

	req = ceph_mdsc_create_request(mdsc, op, want_auth);
	if (IS_ERR(req))
		goto out;
	req->r_fmode = ceph_flags_to_mode(flags);
	req->r_args.open.flags = cpu_to_le32(flags);
	req->r_args.open.mode = cpu_to_le32(create_mode);
S
Sage Weil 已提交
57
	req->r_args.open.preferred = cpu_to_le32(-1);
S
Sage Weil 已提交
58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120
out:
	return req;
}

/*
 * initialize private struct file data.
 * if we fail, clean up by dropping fmode reference on the ceph_inode
 */
static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
{
	struct ceph_file_info *cf;
	int ret = 0;

	switch (inode->i_mode & S_IFMT) {
	case S_IFREG:
	case S_IFDIR:
		dout("init_file %p %p 0%o (regular)\n", inode, file,
		     inode->i_mode);
		cf = kmem_cache_alloc(ceph_file_cachep, GFP_NOFS | __GFP_ZERO);
		if (cf == NULL) {
			ceph_put_fmode(ceph_inode(inode), fmode); /* clean up */
			return -ENOMEM;
		}
		cf->fmode = fmode;
		cf->next_offset = 2;
		file->private_data = cf;
		BUG_ON(inode->i_fop->release != ceph_release);
		break;

	case S_IFLNK:
		dout("init_file %p %p 0%o (symlink)\n", inode, file,
		     inode->i_mode);
		ceph_put_fmode(ceph_inode(inode), fmode); /* clean up */
		break;

	default:
		dout("init_file %p %p 0%o (special)\n", inode, file,
		     inode->i_mode);
		/*
		 * we need to drop the open ref now, since we don't
		 * have .release set to ceph_release.
		 */
		ceph_put_fmode(ceph_inode(inode), fmode); /* clean up */
		BUG_ON(inode->i_fop->release == ceph_release);

		/* call the proper open fop */
		ret = inode->i_fop->open(inode, file);
	}
	return ret;
}

/*
 * If the filp already has private_data, that means the file was
 * already opened by intent during lookup, and we do nothing.
 *
 * If we already have the requisite capabilities, we can satisfy
 * the open request locally (no need to request new caps from the
 * MDS).  We do, however, need to inform the MDS (asynchronously)
 * if our wanted caps set expands.
 */
int ceph_open(struct inode *inode, struct file *file)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
121 122
	struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
	struct ceph_mds_client *mdsc = fsc->mdsc;
S
Sage Weil 已提交
123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156
	struct ceph_mds_request *req;
	struct ceph_file_info *cf = file->private_data;
	struct inode *parent_inode = file->f_dentry->d_parent->d_inode;
	int err;
	int flags, fmode, wanted;

	if (cf) {
		dout("open file %p is already opened\n", file);
		return 0;
	}

	/* filter out O_CREAT|O_EXCL; vfs did that already.  yuck. */
	flags = file->f_flags & ~(O_CREAT|O_EXCL);
	if (S_ISDIR(inode->i_mode))
		flags = O_DIRECTORY;  /* mds likes to know */

	dout("open inode %p ino %llx.%llx file %p flags %d (%d)\n", inode,
	     ceph_vinop(inode), file, flags, file->f_flags);
	fmode = ceph_flags_to_mode(flags);
	wanted = ceph_caps_for_mode(fmode);

	/* snapped files are read-only */
	if (ceph_snap(inode) != CEPH_NOSNAP && (file->f_mode & FMODE_WRITE))
		return -EROFS;

	/* trivially open snapdir */
	if (ceph_snap(inode) == CEPH_SNAPDIR) {
		spin_lock(&inode->i_lock);
		__ceph_get_fmode(ci, fmode);
		spin_unlock(&inode->i_lock);
		return ceph_init_file(inode, file, fmode);
	}

	/*
157 158
	 * No need to block if we have caps on the auth MDS (for
	 * write) or any MDS (for read).  Update wanted set
S
Sage Weil 已提交
159 160 161
	 * asynchronously.
	 */
	spin_lock(&inode->i_lock);
162 163
	if (__ceph_is_any_real_caps(ci) &&
	    (((fmode & CEPH_FILE_MODE_WR) == 0) || ci->i_auth_cap)) {
S
Sage Weil 已提交
164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193
		int mds_wanted = __ceph_caps_mds_wanted(ci);
		int issued = __ceph_caps_issued(ci, NULL);

		dout("open %p fmode %d want %s issued %s using existing\n",
		     inode, fmode, ceph_cap_string(wanted),
		     ceph_cap_string(issued));
		__ceph_get_fmode(ci, fmode);
		spin_unlock(&inode->i_lock);

		/* adjust wanted? */
		if ((issued & wanted) != wanted &&
		    (mds_wanted & wanted) != wanted &&
		    ceph_snap(inode) != CEPH_SNAPDIR)
			ceph_check_caps(ci, 0, NULL);

		return ceph_init_file(inode, file, fmode);
	} else if (ceph_snap(inode) != CEPH_NOSNAP &&
		   (ci->i_snap_caps & wanted) == wanted) {
		__ceph_get_fmode(ci, fmode);
		spin_unlock(&inode->i_lock);
		return ceph_init_file(inode, file, fmode);
	}
	spin_unlock(&inode->i_lock);

	dout("open fmode %d wants %s\n", fmode, ceph_cap_string(wanted));
	req = prepare_open_request(inode->i_sb, flags, 0);
	if (IS_ERR(req)) {
		err = PTR_ERR(req);
		goto out;
	}
194 195
	req->r_inode = inode;
	ihold(inode);
S
Sage Weil 已提交
196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222
	req->r_num_caps = 1;
	err = ceph_mdsc_do_request(mdsc, parent_inode, req);
	if (!err)
		err = ceph_init_file(inode, file, req->r_fmode);
	ceph_mdsc_put_request(req);
	dout("open result=%d on %llx.%llx\n", err, ceph_vinop(inode));
out:
	return err;
}


/*
 * Do a lookup + open with a single request.
 *
 * If this succeeds, but some subsequent check in the vfs
 * may_open() fails, the struct *file gets cleaned up (i.e.
 * ceph_release gets called).  So fear not!
 */
/*
 * flags
 *  path_lookup_open   -> LOOKUP_OPEN
 *  path_lookup_create -> LOOKUP_OPEN|LOOKUP_CREATE
 */
struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry,
				struct nameidata *nd, int mode,
				int locked_dir)
{
223 224
	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
	struct ceph_mds_client *mdsc = fsc->mdsc;
S
Sage Weil 已提交
225 226 227 228 229 230 231 232 233 234 235 236
	struct file *file = nd->intent.open.file;
	struct inode *parent_inode = get_dentry_parent_inode(file->f_dentry);
	struct ceph_mds_request *req;
	int err;
	int flags = nd->intent.open.flags - 1;  /* silly vfs! */

	dout("ceph_lookup_open dentry %p '%.*s' flags %d mode 0%o\n",
	     dentry, dentry->d_name.len, dentry->d_name.name, flags, mode);

	/* do the open */
	req = prepare_open_request(dir->i_sb, flags, mode);
	if (IS_ERR(req))
J
Julia Lawall 已提交
237
		return ERR_CAST(req);
S
Sage Weil 已提交
238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269
	req->r_dentry = dget(dentry);
	req->r_num_caps = 2;
	if (flags & O_CREAT) {
		req->r_dentry_drop = CEPH_CAP_FILE_SHARED;
		req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
	}
	req->r_locked_dir = dir;           /* caller holds dir->i_mutex */
	err = ceph_mdsc_do_request(mdsc, parent_inode, req);
	dentry = ceph_finish_lookup(req, dentry, err);
	if (!err && (flags & O_CREAT) && !req->r_reply_info.head->is_dentry)
		err = ceph_handle_notrace_create(dir, dentry);
	if (!err)
		err = ceph_init_file(req->r_dentry->d_inode, file,
				     req->r_fmode);
	ceph_mdsc_put_request(req);
	dout("ceph_lookup_open result=%p\n", dentry);
	return dentry;
}

int ceph_release(struct inode *inode, struct file *file)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_file_info *cf = file->private_data;

	dout("release inode %p file %p\n", inode, file);
	ceph_put_fmode(ci, cf->fmode);
	if (cf->last_readdir)
		ceph_mdsc_put_request(cf->last_readdir);
	kfree(cf->last_name);
	kfree(cf->dir_info);
	dput(cf->dentry);
	kmem_cache_free(ceph_file_cachep, cf);
270 271

	/* wake up anyone waiting for caps on this inode */
272
	wake_up_all(&ci->i_cap_wq);
S
Sage Weil 已提交
273 274 275 276 277 278 279 280 281 282 283 284
	return 0;
}

/*
 * Read a range of bytes striped over one or more objects.  Iterate over
 * objects we stripe over.  (That's not atomic, but good enough for now.)
 *
 * If we get a short result from the OSD, check against i_size; we need to
 * only return a short read to the caller if we hit EOF.
 */
static int striped_read(struct inode *inode,
			u64 off, u64 len,
285
			struct page **pages, int num_pages,
286
			int *checkeof, bool o_direct,
287
			unsigned long buf_align)
S
Sage Weil 已提交
288
{
289
	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
S
Sage Weil 已提交
290 291
	struct ceph_inode_info *ci = ceph_inode(inode);
	u64 pos, this_len;
292
	int io_align, page_align;
S
Sage Weil 已提交
293 294 295 296 297 298 299 300 301 302 303 304 305 306
	int left, pages_left;
	int read;
	struct page **page_pos;
	int ret;
	bool hit_stripe, was_short;

	/*
	 * we may need to do multiple reads.  not atomic, unfortunately.
	 */
	pos = off;
	left = len;
	page_pos = pages;
	pages_left = num_pages;
	read = 0;
307
	io_align = off & ~PAGE_MASK;
S
Sage Weil 已提交
308 309

more:
310
	if (o_direct)
311
		page_align = (pos - io_align + buf_align) & ~PAGE_MASK;
312 313
	else
		page_align = pos & ~PAGE_MASK;
S
Sage Weil 已提交
314
	this_len = left;
315
	ret = ceph_osdc_readpages(&fsc->client->osdc, ceph_vino(inode),
S
Sage Weil 已提交
316 317 318
				  &ci->i_layout, pos, &this_len,
				  ci->i_truncate_seq,
				  ci->i_truncate_size,
319
				  page_pos, pages_left, page_align);
S
Sage Weil 已提交
320 321
	if (ret == -ENOENT)
		ret = 0;
322 323
	hit_stripe = this_len < left;
	was_short = ret >= 0 && ret < this_len;
S
Sage Weil 已提交
324 325 326 327
	dout("striped_read %llu~%u (read %u) got %d%s%s\n", pos, left, read,
	     ret, hit_stripe ? " HITSTRIPE" : "", was_short ? " SHORT" : "");

	if (ret > 0) {
S
Sage Weil 已提交
328
		int didpages = (page_align + ret) >> PAGE_CACHE_SHIFT;
S
Sage Weil 已提交
329 330 331

		if (read < pos - off) {
			dout(" zero gap %llu to %llu\n", off + read, pos);
S
Sage Weil 已提交
332
			ceph_zero_page_vector_range(page_align + read,
333
						    pos - off - read, pages);
S
Sage Weil 已提交
334 335 336 337 338 339 340 341 342 343 344 345 346
		}
		pos += ret;
		read = pos - off;
		left -= ret;
		page_pos += didpages;
		pages_left -= didpages;

		/* hit stripe? */
		if (left && hit_stripe)
			goto more;
	}

	if (was_short) {
347 348 349 350 351 352 353 354 355 356
		/* did we bounce off eof? */
		if (pos + left > inode->i_size)
			*checkeof = 1;

		/* zero trailing bytes (inside i_size) */
		if (left > 0 && pos < inode->i_size) {
			if (pos + left > inode->i_size)
				left = inode->i_size - pos;

			dout("zero tail %d\n", left);
S
Sage Weil 已提交
357
			ceph_zero_page_vector_range(page_align + read, left,
358
						    pages);
359
			read += left;
S
Sage Weil 已提交
360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375
		}
	}

	if (ret >= 0)
		ret = read;
	dout("striped_read returns %d\n", ret);
	return ret;
}

/*
 * Completely synchronous read and write methods.  Direct from __user
 * buffer to osd, or directly to user pages (if O_DIRECT).
 *
 * If the read spans object boundary, just do multiple reads.
 */
static ssize_t ceph_sync_read(struct file *file, char __user *data,
376
			      unsigned len, loff_t *poff, int *checkeof)
S
Sage Weil 已提交
377 378 379 380
{
	struct inode *inode = file->f_dentry->d_inode;
	struct page **pages;
	u64 off = *poff;
381
	int num_pages, ret;
S
Sage Weil 已提交
382 383 384 385

	dout("sync_read on file %p %llu~%u %s\n", file, off, len,
	     (file->f_flags & O_DIRECT) ? "O_DIRECT" : "");

386 387
	if (file->f_flags & O_DIRECT) {
		num_pages = calc_pages_for((unsigned long)data, len);
388
		pages = ceph_get_direct_page_vector(data, num_pages, true);
389 390
	} else {
		num_pages = calc_pages_for(off, len);
391
		pages = ceph_alloc_page_vector(num_pages, GFP_NOFS);
392
	}
S
Sage Weil 已提交
393 394 395
	if (IS_ERR(pages))
		return PTR_ERR(pages);

396 397 398 399 400 401
	/*
	 * flush any page cache pages in this range.  this
	 * will make concurrent normal and sync io slow,
	 * but it will at least behave sensibly when they are
	 * in sequence.
	 */
402 403 404 405
	ret = filemap_write_and_wait(inode->i_mapping);
	if (ret < 0)
		goto done;

406
	ret = striped_read(inode, off, len, pages, num_pages, checkeof,
407 408
			   file->f_flags & O_DIRECT,
			   (unsigned long)data & ~PAGE_MASK);
S
Sage Weil 已提交
409 410

	if (ret >= 0 && (file->f_flags & O_DIRECT) == 0)
411
		ret = ceph_copy_page_vector_to_user(pages, data, off, ret);
S
Sage Weil 已提交
412 413 414
	if (ret >= 0)
		*poff = off + ret;

415
done:
S
Sage Weil 已提交
416
	if (file->f_flags & O_DIRECT)
417
		ceph_put_page_vector(pages, num_pages, true);
S
Sage Weil 已提交
418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452
	else
		ceph_release_page_vector(pages, num_pages);
	dout("sync_read result %d\n", ret);
	return ret;
}

/*
 * Write commit callback, called if we requested both an ACK and
 * ONDISK commit reply from the OSD.
 */
static void sync_write_commit(struct ceph_osd_request *req,
			      struct ceph_msg *msg)
{
	struct ceph_inode_info *ci = ceph_inode(req->r_inode);

	dout("sync_write_commit %p tid %llu\n", req, req->r_tid);
	spin_lock(&ci->i_unsafe_lock);
	list_del_init(&req->r_unsafe_item);
	spin_unlock(&ci->i_unsafe_lock);
	ceph_put_cap_refs(ci, CEPH_CAP_FILE_WR);
}

/*
 * Synchronous write, straight from __user pointer or user pages (if
 * O_DIRECT).
 *
 * If write spans object boundary, just do multiple writes.  (For a
 * correct atomic write, we should e.g. take write locks on all
 * objects, rollback on failure, etc.)
 */
static ssize_t ceph_sync_write(struct file *file, const char __user *data,
			       size_t left, loff_t *offset)
{
	struct inode *inode = file->f_dentry->d_inode;
	struct ceph_inode_info *ci = ceph_inode(inode);
453
	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
S
Sage Weil 已提交
454 455 456 457 458 459 460 461 462
	struct ceph_osd_request *req;
	struct page **pages;
	int num_pages;
	long long unsigned pos;
	u64 len;
	int written = 0;
	int flags;
	int do_sync = 0;
	int check_caps = 0;
463
	int page_align, io_align;
464
	unsigned long buf_align;
S
Sage Weil 已提交
465 466 467 468 469 470 471 472 473 474 475 476 477 478
	int ret;
	struct timespec mtime = CURRENT_TIME;

	if (ceph_snap(file->f_dentry->d_inode) != CEPH_NOSNAP)
		return -EROFS;

	dout("sync_write on file %p %lld~%u %s\n", file, *offset,
	     (unsigned)left, (file->f_flags & O_DIRECT) ? "O_DIRECT" : "");

	if (file->f_flags & O_APPEND)
		pos = i_size_read(inode);
	else
		pos = *offset;

479 480 481 482 483 484 485 486 487 488
	ret = filemap_write_and_wait_range(inode->i_mapping, pos, pos + left);
	if (ret < 0)
		return ret;

	ret = invalidate_inode_pages2_range(inode->i_mapping,
					    pos >> PAGE_CACHE_SHIFT,
					    (pos + left) >> PAGE_CACHE_SHIFT);
	if (ret < 0)
		dout("invalidate_inode_pages2_range returned %d\n", ret);

S
Sage Weil 已提交
489 490 491 492 493 494 495 496 497 498 499 500 501
	flags = CEPH_OSD_FLAG_ORDERSNAP |
		CEPH_OSD_FLAG_ONDISK |
		CEPH_OSD_FLAG_WRITE;
	if ((file->f_flags & (O_SYNC|O_DIRECT)) == 0)
		flags |= CEPH_OSD_FLAG_ACK;
	else
		do_sync = 1;

	/*
	 * we may need to do multiple writes here if we span an object
	 * boundary.  this isn't atomic, unfortunately.  :(
	 */
more:
502 503
	io_align = pos & ~PAGE_MASK;
	buf_align = (unsigned long)data & ~PAGE_MASK;
S
Sage Weil 已提交
504
	len = left;
505
	if (file->f_flags & O_DIRECT) {
506 507
		/* write from beginning of first page, regardless of
		   io alignment */
508 509 510
		page_align = (pos - io_align + buf_align) & ~PAGE_MASK;
		num_pages = calc_pages_for((unsigned long)data, len);
	} else {
511
		page_align = pos & ~PAGE_MASK;
512 513
		num_pages = calc_pages_for(pos, len);
	}
514
	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
S
Sage Weil 已提交
515 516 517 518 519
				    ceph_vino(inode), pos, &len,
				    CEPH_OSD_OP_WRITE, flags,
				    ci->i_snap_realm->cached_context,
				    do_sync,
				    ci->i_truncate_seq, ci->i_truncate_size,
520
				    &mtime, false, 2, page_align);
521 522
	if (!req)
		return -ENOMEM;
S
Sage Weil 已提交
523 524

	if (file->f_flags & O_DIRECT) {
525
		pages = ceph_get_direct_page_vector(data, num_pages, false);
S
Sage Weil 已提交
526 527 528 529 530 531 532 533 534
		if (IS_ERR(pages)) {
			ret = PTR_ERR(pages);
			goto out;
		}

		/*
		 * throw out any page cache pages in this range. this
		 * may block.
		 */
S
Sage Weil 已提交
535
		truncate_inode_pages_range(inode->i_mapping, pos,
S
Sage Weil 已提交
536
					   (pos+len) | (PAGE_CACHE_SIZE-1));
S
Sage Weil 已提交
537
	} else {
538
		pages = ceph_alloc_page_vector(num_pages, GFP_NOFS);
S
Sage Weil 已提交
539 540 541 542
		if (IS_ERR(pages)) {
			ret = PTR_ERR(pages);
			goto out;
		}
543
		ret = ceph_copy_user_to_page_vector(pages, data, pos, len);
S
Sage Weil 已提交
544 545 546 547 548 549 550 551 552 553 554 555 556 557 558
		if (ret < 0) {
			ceph_release_page_vector(pages, num_pages);
			goto out;
		}

		if ((file->f_flags & O_SYNC) == 0) {
			/* get a second commit callback */
			req->r_safe_callback = sync_write_commit;
			req->r_own_pages = 1;
		}
	}
	req->r_pages = pages;
	req->r_num_pages = num_pages;
	req->r_inode = inode;

559
	ret = ceph_osdc_start_request(&fsc->client->osdc, req, false);
S
Sage Weil 已提交
560 561 562 563 564 565 566
	if (!ret) {
		if (req->r_safe_callback) {
			/*
			 * Add to inode unsafe list only after we
			 * start_request so that a tid has been assigned.
			 */
			spin_lock(&ci->i_unsafe_lock);
567 568
			list_add_tail(&req->r_unsafe_item,
				      &ci->i_unsafe_writes);
S
Sage Weil 已提交
569 570 571
			spin_unlock(&ci->i_unsafe_lock);
			ceph_get_cap_refs(ci, CEPH_CAP_FILE_WR);
		}
572
		
573
		ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
574 575 576 577 578 579
		if (ret < 0 && req->r_safe_callback) {
			spin_lock(&ci->i_unsafe_lock);
			list_del_init(&req->r_unsafe_item);
			spin_unlock(&ci->i_unsafe_lock);
			ceph_put_cap_refs(ci, CEPH_CAP_FILE_WR);
		}
S
Sage Weil 已提交
580 581 582
	}

	if (file->f_flags & O_DIRECT)
583
		ceph_put_page_vector(pages, num_pages, false);
S
Sage Weil 已提交
584 585 586 587 588 589 590 591 592
	else if (file->f_flags & O_SYNC)
		ceph_release_page_vector(pages, num_pages);

out:
	ceph_osdc_put_request(req);
	if (ret == 0) {
		pos += len;
		written += len;
		left -= len;
593
		data += written;
S
Sage Weil 已提交
594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618
		if (left)
			goto more;

		ret = written;
		*offset = pos;
		if (pos > i_size_read(inode))
			check_caps = ceph_inode_set_size(inode, pos);
		if (check_caps)
			ceph_check_caps(ceph_inode(inode), CHECK_CAPS_AUTHONLY,
					NULL);
	}
	return ret;
}

/*
 * Wrap generic_file_aio_read with checks for cap bits on the inode.
 * Atomically grab references, so that those bits are not released
 * back to the MDS mid-read.
 *
 * Hmm, the sync read case isn't actually async... should it be?
 */
static ssize_t ceph_aio_read(struct kiocb *iocb, const struct iovec *iov,
			     unsigned long nr_segs, loff_t pos)
{
	struct file *filp = iocb->ki_filp;
619
	struct ceph_file_info *fi = filp->private_data;
S
Sage Weil 已提交
620 621 622 623
	loff_t *ppos = &iocb->ki_pos;
	size_t len = iov->iov_len;
	struct inode *inode = filp->f_dentry->d_inode;
	struct ceph_inode_info *ci = ceph_inode(inode);
Y
Yehuda Sadeh 已提交
624
	void __user *base = iov->iov_base;
S
Sage Weil 已提交
625
	ssize_t ret;
626
	int want, got = 0;
627
	int checkeof = 0, read = 0;
S
Sage Weil 已提交
628 629 630

	dout("aio_read %p %llx.%llx %llu~%u trying to get caps on %p\n",
	     inode, ceph_vinop(inode), pos, (unsigned)len, inode);
631
again:
S
Sage Weil 已提交
632
	__ceph_do_pending_vmtruncate(inode);
633 634 635 636 637
	if (fi->fmode & CEPH_FILE_MODE_LAZY)
		want = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO;
	else
		want = CEPH_CAP_FILE_CACHE;
	ret = ceph_get_caps(ci, CEPH_CAP_FILE_RD, want, &got, -1);
S
Sage Weil 已提交
638 639 640 641 642 643
	if (ret < 0)
		goto out;
	dout("aio_read %p %llx.%llx %llu~%u got cap refs on %s\n",
	     inode, ceph_vinop(inode), pos, (unsigned)len,
	     ceph_cap_string(got));

644
	if ((got & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0 ||
S
Sage Weil 已提交
645
	    (iocb->ki_filp->f_flags & O_DIRECT) ||
646 647
	    (inode->i_sb->s_flags & MS_SYNCHRONOUS) ||
	    (fi->flags & CEPH_F_SYNC))
S
Sage Weil 已提交
648
		/* hmm, this isn't really async... */
649
		ret = ceph_sync_read(filp, base, len, ppos, &checkeof);
S
Sage Weil 已提交
650 651 652 653 654 655 656
	else
		ret = generic_file_aio_read(iocb, iov, nr_segs, pos);

out:
	dout("aio_read %p %llx.%llx dropping cap refs on %s = %d\n",
	     inode, ceph_vinop(inode), ceph_cap_string(got), (int)ret);
	ceph_put_cap_refs(ci, got);
657 658 659 660 661 662

	if (checkeof && ret >= 0) {
		int statret = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE);

		/* hit EOF or hole? */
		if (statret == 0 && *ppos < inode->i_size) {
663
			dout("aio_read sync_read hit hole, ppos %lld < size %lld, reading more\n", *ppos, inode->i_size);
664 665 666 667 668 669 670 671 672 673
			read += ret;
			base += ret;
			len -= ret;
			checkeof = 0;
			goto again;
		}
	}
	if (ret >= 0)
		ret += read;

S
Sage Weil 已提交
674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690
	return ret;
}

/*
 * Take cap references to avoid releasing caps to MDS mid-write.
 *
 * If we are synchronous, and write with an old snap context, the OSD
 * may return EOLDSNAPC.  In that case, retry the write.. _after_
 * dropping our cap refs and allowing the pending snap to logically
 * complete _before_ this write occurs.
 *
 * If we are near ENOSPC, write synchronously.
 */
static ssize_t ceph_aio_write(struct kiocb *iocb, const struct iovec *iov,
		       unsigned long nr_segs, loff_t pos)
{
	struct file *file = iocb->ki_filp;
691
	struct ceph_file_info *fi = file->private_data;
S
Sage Weil 已提交
692 693
	struct inode *inode = file->f_dentry->d_inode;
	struct ceph_inode_info *ci = ceph_inode(inode);
694 695
	struct ceph_osd_client *osdc =
		&ceph_sb_to_client(inode->i_sb)->client->osdc;
S
Sage Weil 已提交
696
	loff_t endoff = pos + iov->iov_len;
697
	int want, got = 0;
698
	int ret, err;
S
Sage Weil 已提交
699 700 701 702 703 704 705 706 707 708 709

	if (ceph_snap(inode) != CEPH_NOSNAP)
		return -EROFS;

retry_snap:
	if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL))
		return -ENOSPC;
	__ceph_do_pending_vmtruncate(inode);
	dout("aio_write %p %llx.%llx %llu~%u getting caps. i_size %llu\n",
	     inode, ceph_vinop(inode), pos, (unsigned)iov->iov_len,
	     inode->i_size);
710 711 712 713 714
	if (fi->fmode & CEPH_FILE_MODE_LAZY)
		want = CEPH_CAP_FILE_BUFFER | CEPH_CAP_FILE_LAZYIO;
	else
		want = CEPH_CAP_FILE_BUFFER;
	ret = ceph_get_caps(ci, CEPH_CAP_FILE_WR, want, &got, endoff);
S
Sage Weil 已提交
715
	if (ret < 0)
716
		goto out_put;
S
Sage Weil 已提交
717 718 719 720 721

	dout("aio_write %p %llx.%llx %llu~%u  got cap refs on %s\n",
	     inode, ceph_vinop(inode), pos, (unsigned)iov->iov_len,
	     ceph_cap_string(got));

722
	if ((got & (CEPH_CAP_FILE_BUFFER|CEPH_CAP_FILE_LAZYIO)) == 0 ||
S
Sage Weil 已提交
723
	    (iocb->ki_filp->f_flags & O_DIRECT) ||
724 725
	    (inode->i_sb->s_flags & MS_SYNCHRONOUS) ||
	    (fi->flags & CEPH_F_SYNC)) {
S
Sage Weil 已提交
726 727 728
		ret = ceph_sync_write(file, iov->iov_base, iov->iov_len,
			&iocb->ki_pos);
	} else {
729 730 731 732 733 734 735 736 737 738
		/*
		 * buffered write; drop Fw early to avoid slow
		 * revocation if we get stuck on balance_dirty_pages
		 */
		int dirty;

		spin_lock(&inode->i_lock);
		dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR);
		spin_unlock(&inode->i_lock);
		ceph_put_cap_refs(ci, got);
S
Sage Weil 已提交
739

740
		ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
S
Sage Weil 已提交
741 742
		if ((ret >= 0 || ret == -EIOCBQUEUED) &&
		    ((file->f_flags & O_SYNC) || IS_SYNC(file->f_mapping->host)
743
		     || ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_NEARFULL))) {
744
			err = vfs_fsync_range(file, pos, pos + ret - 1, 1);
745 746 747
			if (err < 0)
				ret = err;
		}
748 749 750 751

		if (dirty)
			__mark_inode_dirty(inode, dirty);
		goto out;
S
Sage Weil 已提交
752
	}
753

S
Sage Weil 已提交
754
	if (ret >= 0) {
755
		int dirty;
S
Sage Weil 已提交
756
		spin_lock(&inode->i_lock);
757
		dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR);
S
Sage Weil 已提交
758
		spin_unlock(&inode->i_lock);
759 760
		if (dirty)
			__mark_inode_dirty(inode, dirty);
S
Sage Weil 已提交
761 762
	}

763
out_put:
S
Sage Weil 已提交
764 765 766 767 768
	dout("aio_write %p %llx.%llx %llu~%u  dropping cap refs on %s\n",
	     inode, ceph_vinop(inode), pos, (unsigned)iov->iov_len,
	     ceph_cap_string(got));
	ceph_put_cap_refs(ci, got);

769
out:
S
Sage Weil 已提交
770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838
	if (ret == -EOLDSNAPC) {
		dout("aio_write %p %llx.%llx %llu~%u got EOLDSNAPC, retrying\n",
		     inode, ceph_vinop(inode), pos, (unsigned)iov->iov_len);
		goto retry_snap;
	}

	return ret;
}

/*
 * llseek.  be sure to verify file size on SEEK_END.
 */
static loff_t ceph_llseek(struct file *file, loff_t offset, int origin)
{
	struct inode *inode = file->f_mapping->host;
	int ret;

	mutex_lock(&inode->i_mutex);
	__ceph_do_pending_vmtruncate(inode);
	switch (origin) {
	case SEEK_END:
		ret = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE);
		if (ret < 0) {
			offset = ret;
			goto out;
		}
		offset += inode->i_size;
		break;
	case SEEK_CUR:
		/*
		 * Here we special-case the lseek(fd, 0, SEEK_CUR)
		 * position-querying operation.  Avoid rewriting the "same"
		 * f_pos value back to the file because a concurrent read(),
		 * write() or lseek() might have altered it
		 */
		if (offset == 0) {
			offset = file->f_pos;
			goto out;
		}
		offset += file->f_pos;
		break;
	}

	if (offset < 0 || offset > inode->i_sb->s_maxbytes) {
		offset = -EINVAL;
		goto out;
	}

	/* Special lock needed here? */
	if (offset != file->f_pos) {
		file->f_pos = offset;
		file->f_version = 0;
	}

out:
	mutex_unlock(&inode->i_mutex);
	return offset;
}

const struct file_operations ceph_file_fops = {
	.open = ceph_open,
	.release = ceph_release,
	.llseek = ceph_llseek,
	.read = do_sync_read,
	.write = do_sync_write,
	.aio_read = ceph_aio_read,
	.aio_write = ceph_aio_write,
	.mmap = ceph_mmap,
	.fsync = ceph_fsync,
G
Greg Farnum 已提交
839 840
	.lock = ceph_lock,
	.flock = ceph_flock,
S
Sage Weil 已提交
841 842 843 844 845 846
	.splice_read = generic_file_splice_read,
	.splice_write = generic_file_splice_write,
	.unlocked_ioctl = ceph_ioctl,
	.compat_ioctl	= ceph_ioctl,
};