addr.c 33.6 KB
Newer Older
1
#include <linux/ceph/ceph_debug.h>
S
Sage Weil 已提交
2 3 4 5 6 7

#include <linux/backing-dev.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/writeback.h>	/* generic_writepages */
8
#include <linux/slab.h>
S
Sage Weil 已提交
9 10 11 12
#include <linux/pagevec.h>
#include <linux/task_io_accounting_ops.h>

#include "super.h"
13 14
#include "mds_client.h"
#include <linux/ceph/osd_client.h>
S
Sage Weil 已提交
15 16 17 18 19 20 21 22 23 24 25 26

/*
 * Ceph address space ops.
 *
 * There are a few funny things going on here.
 *
 * The page->private field is used to reference a struct
 * ceph_snap_context for _every_ dirty page.  This indicates which
 * snapshot the page was logically dirtied in, and thus which snap
 * context needs to be associated with the osd write during writeback.
 *
 * Similarly, struct ceph_inode_info maintains a set of counters to
L
Lucas De Marchi 已提交
27
 * count dirty pages on the inode.  In the absence of snapshots,
S
Sage Weil 已提交
28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51
 * i_wrbuffer_ref == i_wrbuffer_ref_head == the dirty page count.
 *
 * When a snapshot is taken (that is, when the client receives
 * notification that a snapshot was taken), each inode with caps and
 * with dirty pages (dirty pages implies there is a cap) gets a new
 * ceph_cap_snap in the i_cap_snaps list (which is sorted in ascending
 * order, new snaps go to the tail).  The i_wrbuffer_ref_head count is
 * moved to capsnap->dirty. (Unless a sync write is currently in
 * progress.  In that case, the capsnap is said to be "pending", new
 * writes cannot start, and the capsnap isn't "finalized" until the
 * write completes (or fails) and a final size/mtime for the inode for
 * that snap can be settled upon.)  i_wrbuffer_ref_head is reset to 0.
 *
 * On writeback, we must submit writes to the osd IN SNAP ORDER.  So,
 * we look for the first capsnap in i_cap_snaps and write out pages in
 * that snap context _only_.  Then we move on to the next capsnap,
 * eventually reaching the "live" or "head" context (i.e., pages that
 * are not yet snapped) and are writing the most recently dirtied
 * pages.
 *
 * Invalidate and so forth must take care to ensure the dirty page
 * accounting is preserved.
 */

Y
Yehuda Sadeh 已提交
52 53 54 55 56
#define CONGESTION_ON_THRESH(congestion_kb) (congestion_kb >> (PAGE_SHIFT-10))
#define CONGESTION_OFF_THRESH(congestion_kb)				\
	(CONGESTION_ON_THRESH(congestion_kb) -				\
	 (CONGESTION_ON_THRESH(congestion_kb) >> 2))

57 58 59 60 61 62
static inline struct ceph_snap_context *page_snap_context(struct page *page)
{
	if (PagePrivate(page))
		return (void *)page->private;
	return NULL;
}
S
Sage Weil 已提交
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

/*
 * Dirty a page.  Optimistically adjust accounting, on the assumption
 * that we won't race with invalidate.  If we do, readjust.
 */
static int ceph_set_page_dirty(struct page *page)
{
	struct address_space *mapping = page->mapping;
	struct inode *inode;
	struct ceph_inode_info *ci;
	int undo = 0;
	struct ceph_snap_context *snapc;

	if (unlikely(!mapping))
		return !TestSetPageDirty(page);

	if (TestSetPageDirty(page)) {
		dout("%p set_page_dirty %p idx %lu -- already dirty\n",
		     mapping->host, page, page->index);
		return 0;
	}

	inode = mapping->host;
	ci = ceph_inode(inode);

	/*
	 * Note that we're grabbing a snapc ref here without holding
	 * any locks!
	 */
	snapc = ceph_get_snap_context(ci->i_snap_realm->cached_context);

	/* dirty the head */
95
	spin_lock(&ci->i_ceph_lock);
96
	if (ci->i_head_snapc == NULL)
S
Sage Weil 已提交
97 98 99
		ci->i_head_snapc = ceph_get_snap_context(snapc);
	++ci->i_wrbuffer_ref_head;
	if (ci->i_wrbuffer_ref == 0)
100
		ihold(inode);
S
Sage Weil 已提交
101 102 103 104 105 106 107
	++ci->i_wrbuffer_ref;
	dout("%p set_page_dirty %p idx %lu head %d/%d -> %d/%d "
	     "snapc %p seq %lld (%d snaps)\n",
	     mapping->host, page, page->index,
	     ci->i_wrbuffer_ref-1, ci->i_wrbuffer_ref_head-1,
	     ci->i_wrbuffer_ref, ci->i_wrbuffer_ref_head,
	     snapc, snapc->seq, snapc->num_snaps);
108
	spin_unlock(&ci->i_ceph_lock);
S
Sage Weil 已提交
109 110 111 112 113

	/* now adjust page */
	spin_lock_irq(&mapping->tree_lock);
	if (page->mapping) {	/* Race with truncate? */
		WARN_ON_ONCE(!PageUptodate(page));
M
Michael Rubin 已提交
114
		account_page_dirtied(page, page->mapping);
S
Sage Weil 已提交
115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147
		radix_tree_tag_set(&mapping->page_tree,
				page_index(page), PAGECACHE_TAG_DIRTY);

		/*
		 * Reference snap context in page->private.  Also set
		 * PagePrivate so that we get invalidatepage callback.
		 */
		page->private = (unsigned long)snapc;
		SetPagePrivate(page);
	} else {
		dout("ANON set_page_dirty %p (raced truncate?)\n", page);
		undo = 1;
	}

	spin_unlock_irq(&mapping->tree_lock);

	if (undo)
		/* whoops, we failed to dirty the page */
		ceph_put_wrbuffer_cap_refs(ci, 1, snapc);

	__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);

	BUG_ON(!PageDirty(page));
	return 1;
}

/*
 * If we are truncating the full page (i.e. offset == 0), adjust the
 * dirty page counters appropriately.  Only called if there is private
 * data on the page.
 */
static void ceph_invalidatepage(struct page *page, unsigned long offset)
{
148
	struct inode *inode;
S
Sage Weil 已提交
149
	struct ceph_inode_info *ci;
150
	struct ceph_snap_context *snapc = page_snap_context(page);
S
Sage Weil 已提交
151 152 153 154 155

	BUG_ON(!PageLocked(page));
	BUG_ON(!PagePrivate(page));
	BUG_ON(!page->mapping);

156 157
	inode = page->mapping->host;

S
Sage Weil 已提交
158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197
	/*
	 * We can get non-dirty pages here due to races between
	 * set_page_dirty and truncate_complete_page; just spit out a
	 * warning, in case we end up with accounting problems later.
	 */
	if (!PageDirty(page))
		pr_err("%p invalidatepage %p page not dirty\n", inode, page);

	if (offset == 0)
		ClearPageChecked(page);

	ci = ceph_inode(inode);
	if (offset == 0) {
		dout("%p invalidatepage %p idx %lu full dirty page %lu\n",
		     inode, page, page->index, offset);
		ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
		ceph_put_snap_context(snapc);
		page->private = 0;
		ClearPagePrivate(page);
	} else {
		dout("%p invalidatepage %p idx %lu partial dirty page\n",
		     inode, page, page->index);
	}
}

/* just a sanity check */
static int ceph_releasepage(struct page *page, gfp_t g)
{
	struct inode *inode = page->mapping ? page->mapping->host : NULL;
	dout("%p releasepage %p idx %lu\n", inode, page, page->index);
	WARN_ON(PageDirty(page));
	WARN_ON(PagePrivate(page));
	return 0;
}

/*
 * read a single page, without unlocking it.
 */
static int readpage_nounlock(struct file *filp, struct page *page)
{
A
Al Viro 已提交
198
	struct inode *inode = file_inode(filp);
S
Sage Weil 已提交
199
	struct ceph_inode_info *ci = ceph_inode(inode);
200 201
	struct ceph_osd_client *osdc = 
		&ceph_inode_to_client(inode)->client->osdc;
S
Sage Weil 已提交
202 203 204 205 206 207
	int err = 0;
	u64 len = PAGE_CACHE_SIZE;

	dout("readpage inode %p file %p page %p index %lu\n",
	     inode, filp, page, page->index);
	err = ceph_osdc_readpages(osdc, ceph_vino(inode), &ci->i_layout,
208
				  (u64) page_offset(page), &len,
S
Sage Weil 已提交
209
				  ci->i_truncate_seq, ci->i_truncate_size,
210
				  &page, 1, 0);
S
Sage Weil 已提交
211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233
	if (err == -ENOENT)
		err = 0;
	if (err < 0) {
		SetPageError(page);
		goto out;
	} else if (err < PAGE_CACHE_SIZE) {
		/* zero fill remainder of page */
		zero_user_segment(page, err, PAGE_CACHE_SIZE);
	}
	SetPageUptodate(page);

out:
	return err < 0 ? err : 0;
}

static int ceph_readpage(struct file *filp, struct page *page)
{
	int r = readpage_nounlock(filp, page);
	unlock_page(page);
	return r;
}

/*
S
Sage Weil 已提交
234
 * Finish an async read(ahead) op.
S
Sage Weil 已提交
235
 */
S
Sage Weil 已提交
236
static void finish_read(struct ceph_osd_request *req, struct ceph_msg *msg)
S
Sage Weil 已提交
237
{
S
Sage Weil 已提交
238
	struct inode *inode = req->r_inode;
239 240
	int rc = req->r_result;
	int bytes = le32_to_cpu(msg->hdr.data_len);
241
	int num_pages;
S
Sage Weil 已提交
242
	int i;
S
Sage Weil 已提交
243

S
Sage Weil 已提交
244 245 246
	dout("finish_read %p req %p rc %d bytes %d\n", inode, req, rc, bytes);

	/* unlock all pages, zeroing any data we didn't read */
247
	BUG_ON(req->r_data_in.type != CEPH_OSD_DATA_TYPE_PAGES);
248 249 250
	num_pages = calc_pages_for((u64)req->r_data_in.alignment,
					(u64)req->r_data_in.length);
	for (i = 0; i < num_pages; i++) {
251
		struct page *page = req->r_data_in.pages[i];
S
Sage Weil 已提交
252 253 254 255 256

		if (bytes < (int)PAGE_CACHE_SIZE) {
			/* zero (remainder of) page */
			int s = bytes < 0 ? 0 : bytes;
			zero_user_segment(page, s, PAGE_CACHE_SIZE);
S
Sage Weil 已提交
257
		}
S
Sage Weil 已提交
258 259 260 261 262 263
 		dout("finish_read %p uptodate %p idx %lu\n", inode, page,
		     page->index);
		flush_dcache_page(page);
		SetPageUptodate(page);
		unlock_page(page);
		page_cache_release(page);
264
		bytes -= PAGE_CACHE_SIZE;
S
Sage Weil 已提交
265
	}
266
	kfree(req->r_data_in.pages);
S
Sage Weil 已提交
267 268
}

269 270 271 272 273 274 275 276
static void ceph_unlock_page_vector(struct page **pages, int num_pages)
{
	int i;

	for (i = 0; i < num_pages; i++)
		unlock_page(pages[i]);
}

S
Sage Weil 已提交
277
/*
S
Sage Weil 已提交
278 279
 * start an async read(ahead) operation.  return nr_pages we submitted
 * a read for on success, or negative error code.
S
Sage Weil 已提交
280
 */
281
static int start_read(struct inode *inode, struct list_head *page_list, int max)
S
Sage Weil 已提交
282
{
283 284
	struct ceph_osd_client *osdc =
		&ceph_inode_to_client(inode)->client->osdc;
S
Sage Weil 已提交
285 286 287 288
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct page *page = list_entry(page_list->prev, struct page, lru);
	struct ceph_osd_request *req;
	u64 off;
S
Sage Weil 已提交
289
	u64 len;
S
Sage Weil 已提交
290 291 292 293 294
	int i;
	struct page **pages;
	pgoff_t next_index;
	int nr_pages = 0;
	int ret;
S
Sage Weil 已提交
295

296
	off = (u64) page_offset(page);
S
Sage Weil 已提交
297

S
Sage Weil 已提交
298 299 300 301 302 303 304
	/* count pages */
	next_index = page->index;
	list_for_each_entry_reverse(page, page_list, lru) {
		if (page->index != next_index)
			break;
		nr_pages++;
		next_index++;
305 306
		if (max && nr_pages == max)
			break;
S
Sage Weil 已提交
307
	}
S
Sage Weil 已提交
308
	len = nr_pages << PAGE_CACHE_SHIFT;
S
Sage Weil 已提交
309 310 311 312 313 314 315 316
	dout("start_read %p nr_pages %d is %lld~%lld\n", inode, nr_pages,
	     off, len);

	req = ceph_osdc_new_request(osdc, &ci->i_layout, ceph_vino(inode),
				    off, &len,
				    CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ,
				    NULL, 0,
				    ci->i_truncate_seq, ci->i_truncate_size,
317
				    NULL, false);
318 319
	if (IS_ERR(req))
		return PTR_ERR(req);
S
Sage Weil 已提交
320

S
Sage Weil 已提交
321
	/* build page vector */
322
	nr_pages = calc_pages_for(0, len);
S
Sage Weil 已提交
323 324 325 326 327 328 329
	pages = kmalloc(sizeof(*pages) * nr_pages, GFP_NOFS);
	ret = -ENOMEM;
	if (!pages)
		goto out;
	for (i = 0; i < nr_pages; ++i) {
		page = list_entry(page_list->prev, struct page, lru);
		BUG_ON(PageLocked(page));
S
Sage Weil 已提交
330
		list_del(&page->lru);
S
Sage Weil 已提交
331 332 333 334
		
 		dout("start_read %p adding %p idx %lu\n", inode, page,
		     page->index);
		if (add_to_page_cache_lru(page, &inode->i_data, page->index,
S
Sage Weil 已提交
335
					  GFP_NOFS)) {
S
Sage Weil 已提交
336
			page_cache_release(page);
S
Sage Weil 已提交
337
			dout("start_read %p add_to_page_cache failed %p\n",
S
Sage Weil 已提交
338
			     inode, page);
S
Sage Weil 已提交
339 340
			nr_pages = i;
			goto out_pages;
S
Sage Weil 已提交
341
		}
S
Sage Weil 已提交
342
		pages[i] = page;
S
Sage Weil 已提交
343
	}
344 345
	req->r_data_in.type = CEPH_OSD_DATA_TYPE_PAGES;
	req->r_data_in.pages = pages;
346
	req->r_data_in.length = len;
347
	req->r_data_in.alignment = 0;
S
Sage Weil 已提交
348 349 350 351 352 353 354 355 356 357 358
	req->r_callback = finish_read;
	req->r_inode = inode;

	dout("start_read %p starting %p %lld~%lld\n", inode, req, off, len);
	ret = ceph_osdc_start_request(osdc, req, false);
	if (ret < 0)
		goto out_pages;
	ceph_osdc_put_request(req);
	return nr_pages;

out_pages:
359
	ceph_unlock_page_vector(pages, nr_pages);
S
Sage Weil 已提交
360 361 362 363 364
	ceph_release_page_vector(pages, nr_pages);
out:
	ceph_osdc_put_request(req);
	return ret;
}
S
Sage Weil 已提交
365

S
Sage Weil 已提交
366 367 368 369 370 371 372 373

/*
 * Read multiple pages.  Leave pages we don't read + unlock in page_list;
 * the caller (VM) cleans them up.
 */
static int ceph_readpages(struct file *file, struct address_space *mapping,
			  struct list_head *page_list, unsigned nr_pages)
{
A
Al Viro 已提交
374
	struct inode *inode = file_inode(file);
375
	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
S
Sage Weil 已提交
376
	int rc = 0;
377 378 379 380 381
	int max = 0;

	if (fsc->mount_options->rsize >= PAGE_CACHE_SIZE)
		max = (fsc->mount_options->rsize + PAGE_CACHE_SIZE - 1)
			>> PAGE_SHIFT;
S
Sage Weil 已提交
382

383 384
	dout("readpages %p file %p nr_pages %d max %d\n", inode,
		file, nr_pages,
385
	     max);
S
Sage Weil 已提交
386
	while (!list_empty(page_list)) {
387
		rc = start_read(inode, page_list, max);
S
Sage Weil 已提交
388 389 390 391
		if (rc < 0)
			goto out;
		BUG_ON(rc == 0);
	}
S
Sage Weil 已提交
392
out:
S
Sage Weil 已提交
393
	dout("readpages %p file %p ret %d\n", inode, file, rc);
S
Sage Weil 已提交
394 395 396 397 398 399 400
	return rc;
}

/*
 * Get ref for the oldest snapc for an inode with dirty data... that is, the
 * only snap context we are allowed to write back.
 */
401 402
static struct ceph_snap_context *get_oldest_context(struct inode *inode,
						    u64 *snap_size)
S
Sage Weil 已提交
403 404 405 406 407
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_snap_context *snapc = NULL;
	struct ceph_cap_snap *capsnap = NULL;

408
	spin_lock(&ci->i_ceph_lock);
S
Sage Weil 已提交
409 410 411 412 413 414 415 416 417 418
	list_for_each_entry(capsnap, &ci->i_cap_snaps, ci_item) {
		dout(" cap_snap %p snapc %p has %d dirty pages\n", capsnap,
		     capsnap->context, capsnap->dirty_pages);
		if (capsnap->dirty_pages) {
			snapc = ceph_get_snap_context(capsnap->context);
			if (snap_size)
				*snap_size = capsnap->size;
			break;
		}
	}
419
	if (!snapc && ci->i_wrbuffer_ref_head) {
420
		snapc = ceph_get_snap_context(ci->i_head_snapc);
S
Sage Weil 已提交
421 422 423
		dout(" head snapc %p has %d dirty pages\n",
		     snapc, ci->i_wrbuffer_ref_head);
	}
424
	spin_unlock(&ci->i_ceph_lock);
S
Sage Weil 已提交
425 426 427 428 429 430 431 432 433 434 435 436 437
	return snapc;
}

/*
 * Write a single page, but leave the page locked.
 *
 * If we get a write error, set the page error bit, but still adjust the
 * dirty page accounting (i.e., page is no longer dirty).
 */
static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
{
	struct inode *inode;
	struct ceph_inode_info *ci;
438
	struct ceph_fs_client *fsc;
S
Sage Weil 已提交
439
	struct ceph_osd_client *osdc;
440
	loff_t page_off = page_offset(page);
S
Sage Weil 已提交
441 442 443
	int len = PAGE_CACHE_SIZE;
	loff_t i_size;
	int err = 0;
444
	struct ceph_snap_context *snapc, *oldest;
S
Sage Weil 已提交
445
	u64 snap_size = 0;
Y
Yehuda Sadeh 已提交
446
	long writeback_stat;
S
Sage Weil 已提交
447 448 449 450 451 452 453 454 455

	dout("writepage %p idx %lu\n", page, page->index);

	if (!page->mapping || !page->mapping->host) {
		dout("writepage %p - no mapping\n", page);
		return -EFAULT;
	}
	inode = page->mapping->host;
	ci = ceph_inode(inode);
456 457
	fsc = ceph_inode_to_client(inode);
	osdc = &fsc->client->osdc;
S
Sage Weil 已提交
458 459

	/* verify this is a writeable snap context */
460
	snapc = page_snap_context(page);
S
Sage Weil 已提交
461 462 463 464
	if (snapc == NULL) {
		dout("writepage %p page %p not dirty?\n", inode, page);
		goto out;
	}
465 466
	oldest = get_oldest_context(inode, &snap_size);
	if (snapc->seq > oldest->seq) {
S
Sage Weil 已提交
467
		dout("writepage %p page %p snapc %p not writeable - noop\n",
468
		     inode, page, snapc);
S
Sage Weil 已提交
469 470
		/* we should only noop if called by kswapd */
		WARN_ON((current->flags & PF_MEMALLOC) == 0);
471
		ceph_put_snap_context(oldest);
S
Sage Weil 已提交
472 473
		goto out;
	}
474
	ceph_put_snap_context(oldest);
S
Sage Weil 已提交
475 476 477 478 479 480 481 482 483

	/* is this a partial page at end of file? */
	if (snap_size)
		i_size = snap_size;
	else
		i_size = i_size_read(inode);
	if (i_size < page_off + len)
		len = i_size - page_off;

S
Sage Weil 已提交
484 485
	dout("writepage %p page %p index %lu on %llu~%u snapc %p\n",
	     inode, page, page->index, page_off, len, snapc);
S
Sage Weil 已提交
486

487
	writeback_stat = atomic_long_inc_return(&fsc->writeback_count);
Y
Yehuda Sadeh 已提交
488
	if (writeback_stat >
489 490
	    CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb))
		set_bdi_congested(&fsc->backing_dev_info, BLK_RW_ASYNC);
Y
Yehuda Sadeh 已提交
491

S
Sage Weil 已提交
492 493 494 495 496
	set_page_writeback(page);
	err = ceph_osdc_writepages(osdc, ceph_vino(inode),
				   &ci->i_layout, snapc,
				   page_off, len,
				   ci->i_truncate_seq, ci->i_truncate_size,
497
				   &inode->i_mtime, &page, 1);
S
Sage Weil 已提交
498 499 500 501 502 503 504 505 506 507 508 509 510 511
	if (err < 0) {
		dout("writepage setting page/mapping error %d %p\n", err, page);
		SetPageError(page);
		mapping_set_error(&inode->i_data, err);
		if (wbc)
			wbc->pages_skipped++;
	} else {
		dout("writepage cleaned page %p\n", page);
		err = 0;  /* vfs expects us to return 0 */
	}
	page->private = 0;
	ClearPagePrivate(page);
	end_page_writeback(page);
	ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
512
	ceph_put_snap_context(snapc);  /* page's reference */
S
Sage Weil 已提交
513 514 515 516 517 518
out:
	return err;
}

static int ceph_writepage(struct page *page, struct writeback_control *wbc)
{
519 520 521
	int err;
	struct inode *inode = page->mapping->host;
	BUG_ON(!inode);
522
	ihold(inode);
523
	err = writepage_nounlock(page, wbc);
S
Sage Weil 已提交
524
	unlock_page(page);
525
	iput(inode);
S
Sage Weil 已提交
526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560
	return err;
}


/*
 * lame release_pages helper.  release_pages() isn't exported to
 * modules.
 */
static void ceph_release_pages(struct page **pages, int num)
{
	struct pagevec pvec;
	int i;

	pagevec_init(&pvec, 0);
	for (i = 0; i < num; i++) {
		if (pagevec_add(&pvec, pages[i]) == 0)
			pagevec_release(&pvec);
	}
	pagevec_release(&pvec);
}


/*
 * async writeback completion handler.
 *
 * If we get an error, set the mapping error bit, but not the individual
 * page error bits.
 */
static void writepages_finish(struct ceph_osd_request *req,
			      struct ceph_msg *msg)
{
	struct inode *inode = req->r_inode;
	struct ceph_inode_info *ci = ceph_inode(inode);
	unsigned wrote;
	struct page *page;
561
	int num_pages;
S
Sage Weil 已提交
562 563 564
	int i;
	struct ceph_snap_context *snapc = req->r_snapc;
	struct address_space *mapping = inode->i_mapping;
565 566
	int rc = req->r_result;
	u64 bytes = le64_to_cpu(req->r_request_ops[0].extent.length);
567
	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
Y
Yehuda Sadeh 已提交
568
	long writeback_stat;
S
Sage Weil 已提交
569
	unsigned issued = ceph_caps_issued(ci);
S
Sage Weil 已提交
570

571
	BUG_ON(req->r_data_out.type != CEPH_OSD_DATA_TYPE_PAGES);
572 573
	num_pages = calc_pages_for((u64)req->r_data_out.alignment,
					(u64)req->r_data_out.length);
S
Sage Weil 已提交
574
	if (rc >= 0) {
575 576 577 578 579 580
		/*
		 * Assume we wrote the pages we originally sent.  The
		 * osd might reply with fewer pages if our writeback
		 * raced with a truncation and was adjusted at the osd,
		 * so don't believe the reply.
		 */
581
		wrote = num_pages;
S
Sage Weil 已提交
582 583 584 585 586 587 588 589
	} else {
		wrote = 0;
		mapping_set_error(mapping, rc);
	}
	dout("writepages_finish %p rc %d bytes %llu wrote %d (pages)\n",
	     inode, rc, bytes, wrote);

	/* clean all pages */
590
	for (i = 0; i < num_pages; i++) {
591
		page = req->r_data_out.pages[i];
S
Sage Weil 已提交
592 593 594
		BUG_ON(!page);
		WARN_ON(!PageUptodate(page));

Y
Yehuda Sadeh 已提交
595
		writeback_stat =
596
			atomic_long_dec_return(&fsc->writeback_count);
Y
Yehuda Sadeh 已提交
597
		if (writeback_stat <
598 599
		    CONGESTION_OFF_THRESH(fsc->mount_options->congestion_kb))
			clear_bdi_congested(&fsc->backing_dev_info,
Y
Yehuda Sadeh 已提交
600 601
					    BLK_RW_ASYNC);

602
		ceph_put_snap_context(page_snap_context(page));
S
Sage Weil 已提交
603 604 605 606
		page->private = 0;
		ClearPagePrivate(page);
		dout("unlocking %d %p\n", i, page);
		end_page_writeback(page);
607 608 609 610 611 612 613

		/*
		 * We lost the cache cap, need to truncate the page before
		 * it is unlocked, otherwise we'd truncate it later in the
		 * page truncation thread, possibly losing some data that
		 * raced its way in
		 */
614
		if ((issued & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0)
615 616
			generic_error_remove_page(inode->i_mapping, page);

S
Sage Weil 已提交
617 618 619
		unlock_page(page);
	}
	dout("%p wrote+cleaned %d pages\n", inode, wrote);
620
	ceph_put_wrbuffer_cap_refs(ci, num_pages, snapc);
S
Sage Weil 已提交
621

622
	ceph_release_pages(req->r_data_out.pages, num_pages);
623 624
	if (req->r_data_out.pages_from_pool)
		mempool_free(req->r_data_out.pages,
625
			     ceph_sb_to_client(inode->i_sb)->wb_pagevec_pool);
S
Sage Weil 已提交
626
	else
627
		kfree(req->r_data_out.pages);
S
Sage Weil 已提交
628 629 630 631 632
	ceph_osdc_put_request(req);
}

/*
 * allocate a page vec, either directly, or if necessary, via a the
633
 * mempool.  we avoid the mempool if we can because req->r_data_out.length
S
Sage Weil 已提交
634 635
 * may be less than the maximum write size.
 */
636
static void alloc_page_vec(struct ceph_fs_client *fsc,
S
Sage Weil 已提交
637 638
			   struct ceph_osd_request *req)
{
639
	size_t size;
640
	int num_pages;
641

642 643 644
	num_pages = calc_pages_for((u64)req->r_data_out.alignment,
					(u64)req->r_data_out.length);
	size = sizeof (struct page *) * num_pages;
645 646 647 648 649 650
	req->r_data_out.pages = kmalloc(size, GFP_NOFS);
	if (!req->r_data_out.pages) {
		req->r_data_out.pages = mempool_alloc(fsc->wb_pagevec_pool,
							GFP_NOFS);
		req->r_data_out.pages_from_pool = 1;
		WARN_ON(!req->r_data_out.pages);
S
Sage Weil 已提交
651 652 653 654 655 656 657 658 659 660 661
	}
}

/*
 * initiate async writeback
 */
static int ceph_writepages_start(struct address_space *mapping,
				 struct writeback_control *wbc)
{
	struct inode *inode = mapping->host;
	struct ceph_inode_info *ci = ceph_inode(inode);
662
	struct ceph_fs_client *fsc;
S
Sage Weil 已提交
663 664 665 666
	pgoff_t index, start, end;
	int range_whole = 0;
	int should_loop = 1;
	pgoff_t max_pages = 0, max_pages_ever = 0;
667
	struct ceph_snap_context *snapc = NULL, *last_snapc = NULL, *pgsnapc;
S
Sage Weil 已提交
668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688
	struct pagevec pvec;
	int done = 0;
	int rc = 0;
	unsigned wsize = 1 << inode->i_blkbits;
	struct ceph_osd_request *req = NULL;
	int do_sync;
	u64 snap_size = 0;

	/*
	 * Include a 'sync' in the OSD request if this is a data
	 * integrity write (e.g., O_SYNC write or fsync()), or if our
	 * cap is being revoked.
	 */
	do_sync = wbc->sync_mode == WB_SYNC_ALL;
	if (ceph_caps_revoking(ci, CEPH_CAP_FILE_BUFFER))
		do_sync = 1;
	dout("writepages_start %p dosync=%d (mode=%s)\n",
	     inode, do_sync,
	     wbc->sync_mode == WB_SYNC_NONE ? "NONE" :
	     (wbc->sync_mode == WB_SYNC_ALL ? "ALL" : "HOLD"));

689 690
	fsc = ceph_inode_to_client(inode);
	if (fsc->mount_state == CEPH_MOUNT_SHUTDOWN) {
S
Sage Weil 已提交
691 692 693
		pr_warning("writepage_start %p on forced umount\n", inode);
		return -EIO; /* we're in a forced umount, don't write! */
	}
694 695
	if (fsc->mount_options->wsize && fsc->mount_options->wsize < wsize)
		wsize = fsc->mount_options->wsize;
S
Sage Weil 已提交
696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745
	if (wsize < PAGE_CACHE_SIZE)
		wsize = PAGE_CACHE_SIZE;
	max_pages_ever = wsize >> PAGE_CACHE_SHIFT;

	pagevec_init(&pvec, 0);

	/* where to start/end? */
	if (wbc->range_cyclic) {
		start = mapping->writeback_index; /* Start from prev offset */
		end = -1;
		dout(" cyclic, start at %lu\n", start);
	} else {
		start = wbc->range_start >> PAGE_CACHE_SHIFT;
		end = wbc->range_end >> PAGE_CACHE_SHIFT;
		if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
			range_whole = 1;
		should_loop = 0;
		dout(" not cyclic, %lu to %lu\n", start, end);
	}
	index = start;

retry:
	/* find oldest snap context with dirty data */
	ceph_put_snap_context(snapc);
	snapc = get_oldest_context(inode, &snap_size);
	if (!snapc) {
		/* hmm, why does writepages get called when there
		   is no dirty data? */
		dout(" no snap context with dirty data?\n");
		goto out;
	}
	dout(" oldest snapc is %p seq %lld (%d snaps)\n",
	     snapc, snapc->seq, snapc->num_snaps);
	if (last_snapc && snapc != last_snapc) {
		/* if we switched to a newer snapc, restart our scan at the
		 * start of the original file range. */
		dout("  snapc differs from last pass, restarting at %lu\n",
		     index);
		index = start;
	}
	last_snapc = snapc;

	while (!done && index <= end) {
		unsigned i;
		int first;
		pgoff_t next;
		int pvec_pages, locked_pages;
		struct page *page;
		int want;
		u64 offset, len;
Y
Yehuda Sadeh 已提交
746
		long writeback_stat;
S
Sage Weil 已提交
747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809

		next = 0;
		locked_pages = 0;
		max_pages = max_pages_ever;

get_more_pages:
		first = -1;
		want = min(end - index,
			   min((pgoff_t)PAGEVEC_SIZE,
			       max_pages - (pgoff_t)locked_pages) - 1)
			+ 1;
		pvec_pages = pagevec_lookup_tag(&pvec, mapping, &index,
						PAGECACHE_TAG_DIRTY,
						want);
		dout("pagevec_lookup_tag got %d\n", pvec_pages);
		if (!pvec_pages && !locked_pages)
			break;
		for (i = 0; i < pvec_pages && locked_pages < max_pages; i++) {
			page = pvec.pages[i];
			dout("? %p idx %lu\n", page, page->index);
			if (locked_pages == 0)
				lock_page(page);  /* first page */
			else if (!trylock_page(page))
				break;

			/* only dirty pages, or our accounting breaks */
			if (unlikely(!PageDirty(page)) ||
			    unlikely(page->mapping != mapping)) {
				dout("!dirty or !mapping %p\n", page);
				unlock_page(page);
				break;
			}
			if (!wbc->range_cyclic && page->index > end) {
				dout("end of range %p\n", page);
				done = 1;
				unlock_page(page);
				break;
			}
			if (next && (page->index != next)) {
				dout("not consecutive %p\n", page);
				unlock_page(page);
				break;
			}
			if (wbc->sync_mode != WB_SYNC_NONE) {
				dout("waiting on writeback %p\n", page);
				wait_on_page_writeback(page);
			}
			if ((snap_size && page_offset(page) > snap_size) ||
			    (!snap_size &&
			     page_offset(page) > i_size_read(inode))) {
				dout("%p page eof %llu\n", page, snap_size ?
				     snap_size : i_size_read(inode));
				done = 1;
				unlock_page(page);
				break;
			}
			if (PageWriteback(page)) {
				dout("%p under writeback\n", page);
				unlock_page(page);
				break;
			}

			/* only if matching snap context */
810
			pgsnapc = page_snap_context(page);
811 812 813
			if (pgsnapc->seq > snapc->seq) {
				dout("page snapc %p %lld > oldest %p %lld\n",
				     pgsnapc, pgsnapc->seq, snapc, snapc->seq);
S
Sage Weil 已提交
814 815 816 817 818 819 820 821 822 823 824 825 826 827 828
				unlock_page(page);
				if (!locked_pages)
					continue; /* keep looking for snap */
				break;
			}

			if (!clear_page_dirty_for_io(page)) {
				dout("%p !clear_page_dirty_for_io\n", page);
				unlock_page(page);
				break;
			}

			/* ok */
			if (locked_pages == 0) {
				/* prepare async write request */
829
				offset = (u64) page_offset(page);
S
Sage Weil 已提交
830
				len = wsize;
831
				req = ceph_osdc_new_request(&fsc->client->osdc,
S
Sage Weil 已提交
832 833 834 835 836 837 838 839 840
					    &ci->i_layout,
					    ceph_vino(inode),
					    offset, &len,
					    CEPH_OSD_OP_WRITE,
					    CEPH_OSD_FLAG_WRITE |
						    CEPH_OSD_FLAG_ONDISK,
					    snapc, do_sync,
					    ci->i_truncate_seq,
					    ci->i_truncate_size,
841
					    &inode->i_mtime, true);
842

843 844
				if (IS_ERR(req)) {
					rc = PTR_ERR(req);
845 846 847 848
					unlock_page(page);
					break;
				}

849
				req->r_data_out.type = CEPH_OSD_DATA_TYPE_PAGES;
850
				req->r_data_out.length = len;
851
				req->r_data_out.alignment = 0;
852
				max_pages = calc_pages_for(0, (u64)len);
853
				alloc_page_vec(fsc, req);
S
Sage Weil 已提交
854 855 856 857 858 859 860 861 862
				req->r_callback = writepages_finish;
				req->r_inode = inode;
			}

			/* note position of first page in pvec */
			if (first < 0)
				first = i;
			dout("%p will write page %p idx %lu\n",
			     inode, page, page->index);
Y
Yehuda Sadeh 已提交
863

S
Sage Weil 已提交
864
			writeback_stat =
865
			       atomic_long_inc_return(&fsc->writeback_count);
S
Sage Weil 已提交
866
			if (writeback_stat > CONGESTION_ON_THRESH(
867 868
				    fsc->mount_options->congestion_kb)) {
				set_bdi_congested(&fsc->backing_dev_info,
S
Sage Weil 已提交
869
						  BLK_RW_ASYNC);
Y
Yehuda Sadeh 已提交
870 871
			}

S
Sage Weil 已提交
872
			set_page_writeback(page);
873
			req->r_data_out.pages[locked_pages] = page;
S
Sage Weil 已提交
874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902
			locked_pages++;
			next = page->index + 1;
		}

		/* did we get anything? */
		if (!locked_pages)
			goto release_pvec_pages;
		if (i) {
			int j;
			BUG_ON(!locked_pages || first < 0);

			if (pvec_pages && i == pvec_pages &&
			    locked_pages < max_pages) {
				dout("reached end pvec, trying for more\n");
				pagevec_reinit(&pvec);
				goto get_more_pages;
			}

			/* shift unused pages over in the pvec...  we
			 * will need to release them below. */
			for (j = i; j < pvec_pages; j++) {
				dout(" pvec leftover page %p\n",
				     pvec.pages[j]);
				pvec.pages[j-i+first] = pvec.pages[j];
			}
			pvec.nr -= i-first;
		}

		/* submit the write */
903
		offset = page_offset(req->r_data_out.pages[0]);
S
Sage Weil 已提交
904 905 906 907 908 909
		len = min((snap_size ? snap_size : i_size_read(inode)) - offset,
			  (u64)locked_pages << PAGE_CACHE_SHIFT);
		dout("writepages got %d pages at %llu~%llu\n",
		     locked_pages, offset, len);

		/* revise final length, page count */
910
		req->r_data_out.length = len;
911 912
		req->r_request_ops[0].extent.length = cpu_to_le64(len);
		req->r_request_ops[0].payload_len = cpu_to_le32(len);
S
Sage Weil 已提交
913 914
		req->r_request->hdr.data_len = cpu_to_le32(len);

915 916
		rc = ceph_osdc_start_request(&fsc->client->osdc, req, true);
		BUG_ON(rc);
S
Sage Weil 已提交
917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961
		req = NULL;

		/* continue? */
		index = next;
		wbc->nr_to_write -= locked_pages;
		if (wbc->nr_to_write <= 0)
			done = 1;

release_pvec_pages:
		dout("pagevec_release on %d pages (%p)\n", (int)pvec.nr,
		     pvec.nr ? pvec.pages[0] : NULL);
		pagevec_release(&pvec);

		if (locked_pages && !done)
			goto retry;
	}

	if (should_loop && !done) {
		/* more to do; loop back to beginning of file */
		dout("writepages looping back to beginning of file\n");
		should_loop = 0;
		index = 0;
		goto retry;
	}

	if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
		mapping->writeback_index = index;

out:
	if (req)
		ceph_osdc_put_request(req);
	ceph_put_snap_context(snapc);
	dout("writepages done, rc = %d\n", rc);
	return rc;
}



/*
 * See if a given @snapc is either writeable, or already written.
 */
static int context_is_writeable_or_written(struct inode *inode,
					   struct ceph_snap_context *snapc)
{
	struct ceph_snap_context *oldest = get_oldest_context(inode, NULL);
962 963 964 965
	int ret = !oldest || snapc->seq <= oldest->seq;

	ceph_put_snap_context(oldest);
	return ret;
S
Sage Weil 已提交
966 967 968 969 970
}

/*
 * We are only allowed to write into/dirty the page if the page is
 * clean, or already dirty within the same snap context.
971 972 973 974
 *
 * called with page locked.
 * return success with page locked,
 * or any failure (incl -EAGAIN) with page unlocked.
S
Sage Weil 已提交
975
 */
976 977 978
static int ceph_update_writeable_page(struct file *file,
			    loff_t pos, unsigned len,
			    struct page *page)
S
Sage Weil 已提交
979
{
A
Al Viro 已提交
980
	struct inode *inode = file_inode(file);
S
Sage Weil 已提交
981
	struct ceph_inode_info *ci = ceph_inode(inode);
982
	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
S
Sage Weil 已提交
983 984 985 986 987
	loff_t page_off = pos & PAGE_CACHE_MASK;
	int pos_in_page = pos & ~PAGE_CACHE_MASK;
	int end_in_page = pos_in_page + len;
	loff_t i_size;
	int r;
988
	struct ceph_snap_context *snapc, *oldest;
S
Sage Weil 已提交
989 990 991 992 993 994 995 996 997

retry_locked:
	/* writepages currently holds page lock, but if we change that later, */
	wait_on_page_writeback(page);

	/* check snap context */
	BUG_ON(!ci->i_snap_realm);
	down_read(&mdsc->snap_rwsem);
	BUG_ON(!ci->i_snap_realm->cached_context);
998
	snapc = page_snap_context(page);
999
	if (snapc && snapc != ci->i_head_snapc) {
S
Sage Weil 已提交
1000 1001 1002 1003
		/*
		 * this page is already dirty in another (older) snap
		 * context!  is it writeable now?
		 */
1004
		oldest = get_oldest_context(inode, NULL);
S
Sage Weil 已提交
1005 1006
		up_read(&mdsc->snap_rwsem);

1007
		if (snapc->seq > oldest->seq) {
1008
			ceph_put_snap_context(oldest);
S
Sage Weil 已提交
1009
			dout(" page %p snapc %p not current or oldest\n",
1010
			     page, snapc);
S
Sage Weil 已提交
1011 1012 1013 1014
			/*
			 * queue for writeback, and wait for snapc to
			 * be writeable or written
			 */
1015
			snapc = ceph_get_snap_context(snapc);
S
Sage Weil 已提交
1016
			unlock_page(page);
1017
			ceph_queue_writeback(inode);
1018
			r = wait_event_interruptible(ci->i_cap_wq,
S
Sage Weil 已提交
1019 1020
			       context_is_writeable_or_written(inode, snapc));
			ceph_put_snap_context(snapc);
1021 1022
			if (r == -ERESTARTSYS)
				return r;
1023
			return -EAGAIN;
S
Sage Weil 已提交
1024
		}
1025
		ceph_put_snap_context(oldest);
S
Sage Weil 已提交
1026 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

		/* yay, writeable, do it now (without dropping page lock) */
		dout(" page %p snapc %p not current, but oldest\n",
		     page, snapc);
		if (!clear_page_dirty_for_io(page))
			goto retry_locked;
		r = writepage_nounlock(page, NULL);
		if (r < 0)
			goto fail_nosnap;
		goto retry_locked;
	}

	if (PageUptodate(page)) {
		dout(" page %p already uptodate\n", page);
		return 0;
	}

	/* full page? */
	if (pos_in_page == 0 && len == PAGE_CACHE_SIZE)
		return 0;

	/* past end of file? */
	i_size = inode->i_size;   /* caller holds i_mutex */

	if (i_size + len > inode->i_sb->s_maxbytes) {
		/* file is too big */
		r = -EINVAL;
		goto fail;
	}

	if (page_off >= i_size ||
	    (pos_in_page == 0 && (pos+len) >= i_size &&
	     end_in_page - pos_in_page != PAGE_CACHE_SIZE)) {
		dout(" zeroing %p 0 - %d and %d - %d\n",
		     page, pos_in_page, end_in_page, (int)PAGE_CACHE_SIZE);
		zero_user_segments(page,
				   0, pos_in_page,
				   end_in_page, PAGE_CACHE_SIZE);
		return 0;
	}

	/* we need to read it. */
	up_read(&mdsc->snap_rwsem);
	r = readpage_nounlock(file, page);
	if (r < 0)
		goto fail_nosnap;
	goto retry_locked;

fail:
	up_read(&mdsc->snap_rwsem);
fail_nosnap:
	unlock_page(page);
	return r;
}

1081 1082 1083 1084 1085 1086 1087 1088
/*
 * We are only allowed to write into/dirty the page if the page is
 * clean, or already dirty within the same snap context.
 */
static int ceph_write_begin(struct file *file, struct address_space *mapping,
			    loff_t pos, unsigned len, unsigned flags,
			    struct page **pagep, void **fsdata)
{
A
Al Viro 已提交
1089
	struct inode *inode = file_inode(file);
1090 1091
	struct page *page;
	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
S
Sage Weil 已提交
1092
	int r;
1093 1094

	do {
1095
		/* get a page */
1096
		page = grab_cache_page_write_begin(mapping, index, 0);
S
Sage Weil 已提交
1097 1098 1099
		if (!page)
			return -ENOMEM;
		*pagep = page;
1100 1101

		dout("write_begin file %p inode %p page %p %d~%d\n", file,
S
Sage Weil 已提交
1102
		     inode, page, (int)pos, (int)len);
1103 1104 1105 1106 1107 1108 1109

		r = ceph_update_writeable_page(file, pos, len, page);
	} while (r == -EAGAIN);

	return r;
}

S
Sage Weil 已提交
1110 1111 1112 1113 1114 1115 1116 1117 1118
/*
 * we don't do anything in here that simple_write_end doesn't do
 * except adjust dirty page accounting and drop read lock on
 * mdsc->snap_rwsem.
 */
static int ceph_write_end(struct file *file, struct address_space *mapping,
			  loff_t pos, unsigned len, unsigned copied,
			  struct page *page, void *fsdata)
{
A
Al Viro 已提交
1119
	struct inode *inode = file_inode(file);
1120 1121
	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
	struct ceph_mds_client *mdsc = fsc->mdsc;
S
Sage Weil 已提交
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 1152 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 1182 1183 1184 1185 1186 1187
	unsigned from = pos & (PAGE_CACHE_SIZE - 1);
	int check_cap = 0;

	dout("write_end file %p inode %p page %p %d~%d (%d)\n", file,
	     inode, page, (int)pos, (int)copied, (int)len);

	/* zero the stale part of the page if we did a short copy */
	if (copied < len)
		zero_user_segment(page, from+copied, len);

	/* did file size increase? */
	/* (no need for i_size_read(); we caller holds i_mutex */
	if (pos+copied > inode->i_size)
		check_cap = ceph_inode_set_size(inode, pos+copied);

	if (!PageUptodate(page))
		SetPageUptodate(page);

	set_page_dirty(page);

	unlock_page(page);
	up_read(&mdsc->snap_rwsem);
	page_cache_release(page);

	if (check_cap)
		ceph_check_caps(ceph_inode(inode), CHECK_CAPS_AUTHONLY, NULL);

	return copied;
}

/*
 * we set .direct_IO to indicate direct io is supported, but since we
 * intercept O_DIRECT reads and writes early, this function should
 * never get called.
 */
static ssize_t ceph_direct_io(int rw, struct kiocb *iocb,
			      const struct iovec *iov,
			      loff_t pos, unsigned long nr_segs)
{
	WARN_ON(1);
	return -EINVAL;
}

const struct address_space_operations ceph_aops = {
	.readpage = ceph_readpage,
	.readpages = ceph_readpages,
	.writepage = ceph_writepage,
	.writepages = ceph_writepages_start,
	.write_begin = ceph_write_begin,
	.write_end = ceph_write_end,
	.set_page_dirty = ceph_set_page_dirty,
	.invalidatepage = ceph_invalidatepage,
	.releasepage = ceph_releasepage,
	.direct_IO = ceph_direct_io,
};


/*
 * vm ops
 */

/*
 * Reuse write_begin here for simplicity.
 */
static int ceph_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
A
Al Viro 已提交
1188
	struct inode *inode = file_inode(vma->vm_file);
S
Sage Weil 已提交
1189
	struct page *page = vmf->page;
1190
	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
1191
	loff_t off = page_offset(page);
S
Sage Weil 已提交
1192 1193 1194
	loff_t size, len;
	int ret;

1195 1196 1197
	/* Update time before taking page lock */
	file_update_time(vma->vm_file);

S
Sage Weil 已提交
1198 1199 1200 1201 1202 1203 1204 1205
	size = i_size_read(inode);
	if (off + PAGE_CACHE_SIZE <= size)
		len = PAGE_CACHE_SIZE;
	else
		len = size & ~PAGE_CACHE_MASK;

	dout("page_mkwrite %p %llu~%llu page %p idx %lu\n", inode,
	     off, len, page, page->index);
1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216

	lock_page(page);

	ret = VM_FAULT_NOPAGE;
	if ((off > size) ||
	    (page->mapping != inode->i_mapping))
		goto out;

	ret = ceph_update_writeable_page(vma->vm_file, off, len, page);
	if (ret == 0) {
		/* success.  we'll keep the page locked. */
S
Sage Weil 已提交
1217 1218 1219 1220
		set_page_dirty(page);
		up_read(&mdsc->snap_rwsem);
		ret = VM_FAULT_LOCKED;
	} else {
1221 1222 1223 1224
		if (ret == -ENOMEM)
			ret = VM_FAULT_OOM;
		else
			ret = VM_FAULT_SIGBUS;
S
Sage Weil 已提交
1225
	}
1226
out:
S
Sage Weil 已提交
1227
	dout("page_mkwrite %p %llu~%llu = %d\n", inode, off, len, ret);
1228 1229
	if (ret != VM_FAULT_LOCKED)
		unlock_page(page);
S
Sage Weil 已提交
1230 1231 1232 1233 1234 1235
	return ret;
}

static struct vm_operations_struct ceph_vmops = {
	.fault		= filemap_fault,
	.page_mkwrite	= ceph_page_mkwrite,
1236
	.remap_pages	= generic_file_remap_pages,
S
Sage Weil 已提交
1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248
};

int ceph_mmap(struct file *file, struct vm_area_struct *vma)
{
	struct address_space *mapping = file->f_mapping;

	if (!mapping->a_ops->readpage)
		return -ENOEXEC;
	file_accessed(file);
	vma->vm_ops = &ceph_vmops;
	return 0;
}