Blame view
fs/ceph/addr.c
33.1 KB
3d14c5d2b ceph: factor out ... |
1 |
#include <linux/ceph/ceph_debug.h> |
1d3576fd1 ceph: address spa... |
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 */ |
5a0e3ad6a include cleanup: ... |
8 |
#include <linux/slab.h> |
1d3576fd1 ceph: address spa... |
9 10 11 12 |
#include <linux/pagevec.h> #include <linux/task_io_accounting_ops.h> #include "super.h" |
3d14c5d2b ceph: factor out ... |
13 14 |
#include "mds_client.h" #include <linux/ceph/osd_client.h> |
1d3576fd1 ceph: address spa... |
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 |
25985edce Fix common misspe... |
27 |
* count dirty pages on the inode. In the absence of snapshots, |
1d3576fd1 ceph: address spa... |
28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 |
* 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. */ |
2baba2501 ceph: writeback c... |
51 52 53 54 |
#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)) |
1d3576fd1 ceph: address spa... |
55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 |
/* * 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 ", 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 */ |
be655596b ceph: use i_ceph_... |
88 |
spin_lock(&ci->i_ceph_lock); |
7d8cb26d7 ceph: maintain i_... |
89 |
if (ci->i_head_snapc == NULL) |
1d3576fd1 ceph: address spa... |
90 91 92 |
ci->i_head_snapc = ceph_get_snap_context(snapc); ++ci->i_wrbuffer_ref_head; if (ci->i_wrbuffer_ref == 0) |
0444d76ae fs: don't use igr... |
93 |
ihold(inode); |
1d3576fd1 ceph: address spa... |
94 95 96 97 98 99 100 101 |
++ci->i_wrbuffer_ref; dout("%p set_page_dirty %p idx %lu head %d/%d -> %d/%d " "snapc %p seq %lld (%d snaps) ", 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); |
be655596b ceph: use i_ceph_... |
102 |
spin_unlock(&ci->i_ceph_lock); |
1d3576fd1 ceph: address spa... |
103 104 105 106 107 |
/* now adjust page */ spin_lock_irq(&mapping->tree_lock); if (page->mapping) { /* Race with truncate? */ WARN_ON_ONCE(!PageUptodate(page)); |
679ceace8 mm: exporting acc... |
108 |
account_page_dirtied(page, page->mapping); |
1d3576fd1 ceph: address spa... |
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 |
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?) ", 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) { |
4ce1e9ada ceph: move derefe... |
143 |
struct inode *inode; |
1d3576fd1 ceph: address spa... |
144 145 146 147 148 149 150 |
struct ceph_inode_info *ci; struct ceph_snap_context *snapc = (void *)page->private; BUG_ON(!PageLocked(page)); BUG_ON(!page->private); BUG_ON(!PagePrivate(page)); BUG_ON(!page->mapping); |
4ce1e9ada ceph: move derefe... |
151 |
inode = page->mapping->host; |
1d3576fd1 ceph: address spa... |
152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 |
/* * 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 ", inode, page); if (offset == 0) ClearPageChecked(page); ci = ceph_inode(inode); if (offset == 0) { dout("%p invalidatepage %p idx %lu full dirty page %lu ", 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 ", 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 ", inode, page, page->index); WARN_ON(PageDirty(page)); WARN_ON(page->private); WARN_ON(PagePrivate(page)); return 0; } /* * read a single page, without unlocking it. */ static int readpage_nounlock(struct file *filp, struct page *page) { struct inode *inode = filp->f_dentry->d_inode; struct ceph_inode_info *ci = ceph_inode(inode); |
3d14c5d2b ceph: factor out ... |
199 200 |
struct ceph_osd_client *osdc = &ceph_inode_to_client(inode)->client->osdc; |
1d3576fd1 ceph: address spa... |
201 202 203 204 205 206 207 208 209 |
int err = 0; u64 len = PAGE_CACHE_SIZE; dout("readpage inode %p file %p page %p index %lu ", inode, filp, page, page->index); err = ceph_osdc_readpages(osdc, ceph_vino(inode), &ci->i_layout, page->index << PAGE_CACHE_SHIFT, &len, ci->i_truncate_seq, ci->i_truncate_size, |
b7495fc2f ceph: make page a... |
210 |
&page, 1, 0); |
1d3576fd1 ceph: address spa... |
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; } /* |
7c272194e ceph: make readpa... |
234 |
* Finish an async read(ahead) op. |
1d3576fd1 ceph: address spa... |
235 |
*/ |
7c272194e ceph: make readpa... |
236 |
static void finish_read(struct ceph_osd_request *req, struct ceph_msg *msg) |
1d3576fd1 ceph: address spa... |
237 |
{ |
7c272194e ceph: make readpa... |
238 239 240 241 |
struct inode *inode = req->r_inode; struct ceph_osd_reply_head *replyhead; int rc, bytes; int i; |
1d3576fd1 ceph: address spa... |
242 |
|
7c272194e ceph: make readpa... |
243 244 245 246 247 |
/* parse reply */ replyhead = msg->front.iov_base; WARN_ON(le32_to_cpu(replyhead->num_ops) == 0); rc = le32_to_cpu(replyhead->result); bytes = le32_to_cpu(msg->hdr.data_len); |
1d3576fd1 ceph: address spa... |
248 |
|
7c272194e ceph: make readpa... |
249 250 251 252 253 254 255 256 257 258 259 |
dout("finish_read %p req %p rc %d bytes %d ", inode, req, rc, bytes); /* unlock all pages, zeroing any data we didn't read */ for (i = 0; i < req->r_num_pages; i++, bytes -= PAGE_CACHE_SIZE) { struct page *page = req->r_pages[i]; if (bytes < (int)PAGE_CACHE_SIZE) { /* zero (remainder of) page */ int s = bytes < 0 ? 0 : bytes; zero_user_segment(page, s, PAGE_CACHE_SIZE); |
1d3576fd1 ceph: address spa... |
260 |
} |
7c272194e ceph: make readpa... |
261 262 263 264 265 266 267 |
dout("finish_read %p uptodate %p idx %lu ", inode, page, page->index); flush_dcache_page(page); SetPageUptodate(page); unlock_page(page); page_cache_release(page); |
1d3576fd1 ceph: address spa... |
268 |
} |
7c272194e ceph: make readpa... |
269 |
kfree(req->r_pages); |
1d3576fd1 ceph: address spa... |
270 271 272 |
} /* |
7c272194e ceph: make readpa... |
273 274 |
* start an async read(ahead) operation. return nr_pages we submitted * a read for on success, or negative error code. |
1d3576fd1 ceph: address spa... |
275 |
*/ |
0d66a487c ceph: implement (... |
276 |
static int start_read(struct inode *inode, struct list_head *page_list, int max) |
1d3576fd1 ceph: address spa... |
277 |
{ |
3d14c5d2b ceph: factor out ... |
278 279 |
struct ceph_osd_client *osdc = &ceph_inode_to_client(inode)->client->osdc; |
7c272194e ceph: make readpa... |
280 281 282 283 |
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; |
1d3576fd1 ceph: address spa... |
284 |
u64 len; |
7c272194e ceph: make readpa... |
285 286 287 288 289 |
int i; struct page **pages; pgoff_t next_index; int nr_pages = 0; int ret; |
1d3576fd1 ceph: address spa... |
290 |
|
7c272194e ceph: make readpa... |
291 |
off = page->index << PAGE_CACHE_SHIFT; |
1d3576fd1 ceph: address spa... |
292 |
|
7c272194e ceph: make readpa... |
293 294 295 296 297 298 299 |
/* 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++; |
0d66a487c ceph: implement (... |
300 301 |
if (max && nr_pages == max) break; |
7c272194e ceph: make readpa... |
302 |
} |
1d3576fd1 ceph: address spa... |
303 |
len = nr_pages << PAGE_CACHE_SHIFT; |
7c272194e ceph: make readpa... |
304 305 306 307 308 309 310 311 312 313 314 315 |
dout("start_read %p nr_pages %d is %lld~%lld ", 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, NULL, false, 1, 0); if (!req) return -ENOMEM; |
1d3576fd1 ceph: address spa... |
316 |
|
7c272194e ceph: make readpa... |
317 318 319 320 321 322 323 324 325 |
/* build page vector */ nr_pages = len >> PAGE_CACHE_SHIFT; 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)); |
1d3576fd1 ceph: address spa... |
326 |
list_del(&page->lru); |
7c272194e ceph: make readpa... |
327 328 329 330 331 |
dout("start_read %p adding %p idx %lu ", inode, page, page->index); if (add_to_page_cache_lru(page, &inode->i_data, page->index, |
213c99ee0 ceph: whitespace ... |
332 |
GFP_NOFS)) { |
1d3576fd1 ceph: address spa... |
333 |
page_cache_release(page); |
7c272194e ceph: make readpa... |
334 335 |
dout("start_read %p add_to_page_cache failed %p ", |
1d3576fd1 ceph: address spa... |
336 |
inode, page); |
7c272194e ceph: make readpa... |
337 338 |
nr_pages = i; goto out_pages; |
1d3576fd1 ceph: address spa... |
339 |
} |
7c272194e ceph: make readpa... |
340 |
pages[i] = page; |
1d3576fd1 ceph: address spa... |
341 |
} |
7c272194e ceph: make readpa... |
342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 |
req->r_pages = pages; req->r_num_pages = nr_pages; req->r_callback = finish_read; req->r_inode = inode; dout("start_read %p starting %p %lld~%lld ", 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: ceph_release_page_vector(pages, nr_pages); |
7c272194e ceph: make readpa... |
357 358 359 360 |
out: ceph_osdc_put_request(req); return ret; } |
1d3576fd1 ceph: address spa... |
361 |
|
7c272194e ceph: make readpa... |
362 363 364 365 366 367 368 369 370 |
/* * 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) { struct inode *inode = file->f_dentry->d_inode; |
0d66a487c ceph: implement (... |
371 |
struct ceph_fs_client *fsc = ceph_inode_to_client(inode); |
7c272194e ceph: make readpa... |
372 |
int rc = 0; |
0d66a487c ceph: implement (... |
373 374 375 376 377 |
int max = 0; if (fsc->mount_options->rsize >= PAGE_CACHE_SIZE) max = (fsc->mount_options->rsize + PAGE_CACHE_SIZE - 1) >> PAGE_SHIFT; |
7c272194e ceph: make readpa... |
378 |
|
0d66a487c ceph: implement (... |
379 380 381 |
dout("readpages %p file %p nr_pages %d max %d ", inode, file, nr_pages, max); |
7c272194e ceph: make readpa... |
382 |
while (!list_empty(page_list)) { |
0d66a487c ceph: implement (... |
383 |
rc = start_read(inode, page_list, max); |
7c272194e ceph: make readpa... |
384 385 386 387 |
if (rc < 0) goto out; BUG_ON(rc == 0); } |
1d3576fd1 ceph: address spa... |
388 |
out: |
7c272194e ceph: make readpa... |
389 390 |
dout("readpages %p file %p ret %d ", inode, file, rc); |
1d3576fd1 ceph: address spa... |
391 392 393 394 395 396 |
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. |
1d3576fd1 ceph: address spa... |
397 |
*/ |
6298a3375 ceph: fix snap co... |
398 399 |
static struct ceph_snap_context *get_oldest_context(struct inode *inode, u64 *snap_size) |
1d3576fd1 ceph: address spa... |
400 401 402 403 |
{ struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_snap_context *snapc = NULL; struct ceph_cap_snap *capsnap = NULL; |
be655596b ceph: use i_ceph_... |
404 |
spin_lock(&ci->i_ceph_lock); |
1d3576fd1 ceph: address spa... |
405 406 407 408 409 410 411 412 413 414 415 |
list_for_each_entry(capsnap, &ci->i_cap_snaps, ci_item) { dout(" cap_snap %p snapc %p has %d dirty pages ", 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; } } |
7d8cb26d7 ceph: maintain i_... |
416 |
if (!snapc && ci->i_wrbuffer_ref_head) { |
80e755fed ceph: allow write... |
417 |
snapc = ceph_get_snap_context(ci->i_head_snapc); |
1d3576fd1 ceph: address spa... |
418 419 420 421 |
dout(" head snapc %p has %d dirty pages ", snapc, ci->i_wrbuffer_ref_head); } |
be655596b ceph: use i_ceph_... |
422 |
spin_unlock(&ci->i_ceph_lock); |
1d3576fd1 ceph: address spa... |
423 424 425 426 427 428 429 430 431 432 433 434 435 |
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; |
3d14c5d2b ceph: factor out ... |
436 |
struct ceph_fs_client *fsc; |
1d3576fd1 ceph: address spa... |
437 438 439 440 441 |
struct ceph_osd_client *osdc; loff_t page_off = page->index << PAGE_CACHE_SHIFT; int len = PAGE_CACHE_SIZE; loff_t i_size; int err = 0; |
6298a3375 ceph: fix snap co... |
442 |
struct ceph_snap_context *snapc, *oldest; |
1d3576fd1 ceph: address spa... |
443 |
u64 snap_size = 0; |
2baba2501 ceph: writeback c... |
444 |
long writeback_stat; |
1d3576fd1 ceph: address spa... |
445 446 447 448 449 450 451 452 453 454 455 |
dout("writepage %p idx %lu ", page, page->index); if (!page->mapping || !page->mapping->host) { dout("writepage %p - no mapping ", page); return -EFAULT; } inode = page->mapping->host; ci = ceph_inode(inode); |
3d14c5d2b ceph: factor out ... |
456 457 |
fsc = ceph_inode_to_client(inode); osdc = &fsc->client->osdc; |
1d3576fd1 ceph: address spa... |
458 459 460 461 462 463 464 465 |
/* verify this is a writeable snap context */ snapc = (void *)page->private; if (snapc == NULL) { dout("writepage %p page %p not dirty? ", inode, page); goto out; } |
6298a3375 ceph: fix snap co... |
466 467 |
oldest = get_oldest_context(inode, &snap_size); if (snapc->seq > oldest->seq) { |
1d3576fd1 ceph: address spa... |
468 469 470 471 472 |
dout("writepage %p page %p snapc %p not writeable - noop ", inode, page, (void *)page->private); /* we should only noop if called by kswapd */ WARN_ON((current->flags & PF_MEMALLOC) == 0); |
6298a3375 ceph: fix snap co... |
473 |
ceph_put_snap_context(oldest); |
1d3576fd1 ceph: address spa... |
474 475 |
goto out; } |
6298a3375 ceph: fix snap co... |
476 |
ceph_put_snap_context(oldest); |
1d3576fd1 ceph: address spa... |
477 478 479 480 481 482 483 484 |
/* 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; |
ae00d4f37 ceph: fix cap_sna... |
485 486 487 |
dout("writepage %p page %p index %lu on %llu~%u snapc %p ", inode, page, page->index, page_off, len, snapc); |
1d3576fd1 ceph: address spa... |
488 |
|
3d14c5d2b ceph: factor out ... |
489 |
writeback_stat = atomic_long_inc_return(&fsc->writeback_count); |
2baba2501 ceph: writeback c... |
490 |
if (writeback_stat > |
3d14c5d2b ceph: factor out ... |
491 492 |
CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb)) set_bdi_congested(&fsc->backing_dev_info, BLK_RW_ASYNC); |
2baba2501 ceph: writeback c... |
493 |
|
1d3576fd1 ceph: address spa... |
494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 |
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, &inode->i_mtime, &page, 1, 0, 0, true); if (err < 0) { dout("writepage setting page/mapping error %d %p ", err, page); SetPageError(page); mapping_set_error(&inode->i_data, err); if (wbc) wbc->pages_skipped++; } else { dout("writepage cleaned page %p ", 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); |
6298a3375 ceph: fix snap co... |
517 |
ceph_put_snap_context(snapc); /* page's reference */ |
1d3576fd1 ceph: address spa... |
518 519 520 521 522 523 |
out: return err; } static int ceph_writepage(struct page *page, struct writeback_control *wbc) { |
dbd646a85 ceph: writepage g... |
524 525 526 |
int err; struct inode *inode = page->mapping->host; BUG_ON(!inode); |
70b666c3b ceph: use ihold w... |
527 |
ihold(inode); |
dbd646a85 ceph: writepage g... |
528 |
err = writepage_nounlock(page, wbc); |
1d3576fd1 ceph: address spa... |
529 |
unlock_page(page); |
dbd646a85 ceph: writepage g... |
530 |
iput(inode); |
1d3576fd1 ceph: address spa... |
531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 |
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_osd_reply_head *replyhead; struct ceph_osd_op *op; struct ceph_inode_info *ci = ceph_inode(inode); unsigned wrote; |
1d3576fd1 ceph: address spa... |
567 568 569 570 |
struct page *page; int i; struct ceph_snap_context *snapc = req->r_snapc; struct address_space *mapping = inode->i_mapping; |
1d3576fd1 ceph: address spa... |
571 572 |
__s32 rc = -EIO; u64 bytes = 0; |
3d14c5d2b ceph: factor out ... |
573 |
struct ceph_fs_client *fsc = ceph_inode_to_client(inode); |
2baba2501 ceph: writeback c... |
574 |
long writeback_stat; |
7ff899da0 ceph: fix lockles... |
575 |
unsigned issued = ceph_caps_issued(ci); |
1d3576fd1 ceph: address spa... |
576 577 578 579 580 581 582 583 584 |
/* parse reply */ replyhead = msg->front.iov_base; WARN_ON(le32_to_cpu(replyhead->num_ops) == 0); op = (void *)(replyhead + 1); rc = le32_to_cpu(replyhead->result); bytes = le64_to_cpu(op->extent.length); if (rc >= 0) { |
79788c698 ceph: release all... |
585 586 587 588 589 590 591 |
/* * 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. */ wrote = req->r_num_pages; |
1d3576fd1 ceph: address spa... |
592 593 594 595 596 597 598 599 600 601 602 603 604 |
} else { wrote = 0; mapping_set_error(mapping, rc); } dout("writepages_finish %p rc %d bytes %llu wrote %d (pages) ", inode, rc, bytes, wrote); /* clean all pages */ for (i = 0; i < req->r_num_pages; i++) { page = req->r_pages[i]; BUG_ON(!page); WARN_ON(!PageUptodate(page)); |
2baba2501 ceph: writeback c... |
605 |
writeback_stat = |
3d14c5d2b ceph: factor out ... |
606 |
atomic_long_dec_return(&fsc->writeback_count); |
2baba2501 ceph: writeback c... |
607 |
if (writeback_stat < |
3d14c5d2b ceph: factor out ... |
608 609 |
CONGESTION_OFF_THRESH(fsc->mount_options->congestion_kb)) clear_bdi_congested(&fsc->backing_dev_info, |
2baba2501 ceph: writeback c... |
610 |
BLK_RW_ASYNC); |
80e755fed ceph: allow write... |
611 |
ceph_put_snap_context((void *)page->private); |
1d3576fd1 ceph: address spa... |
612 613 |
page->private = 0; ClearPagePrivate(page); |
1d3576fd1 ceph: address spa... |
614 615 616 |
dout("unlocking %d %p ", i, page); end_page_writeback(page); |
e63dc5c78 ceph: remove page... |
617 618 619 620 621 622 623 |
/* * 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 */ |
2962507ca ceph: perform laz... |
624 |
if ((issued & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0) |
e63dc5c78 ceph: remove page... |
625 |
generic_error_remove_page(inode->i_mapping, page); |
1d3576fd1 ceph: address spa... |
626 627 628 629 630 631 632 633 634 |
unlock_page(page); } dout("%p wrote+cleaned %d pages ", inode, wrote); ceph_put_wrbuffer_cap_refs(ci, req->r_num_pages, snapc); ceph_release_pages(req->r_pages, req->r_num_pages); if (req->r_pages_from_pool) mempool_free(req->r_pages, |
640ef79d2 ceph: use ceph_sb... |
635 |
ceph_sb_to_client(inode->i_sb)->wb_pagevec_pool); |
1d3576fd1 ceph: address spa... |
636 637 638 639 640 641 642 643 644 645 |
else kfree(req->r_pages); ceph_osdc_put_request(req); } /* * allocate a page vec, either directly, or if necessary, via a the * mempool. we avoid the mempool if we can because req->r_num_pages * may be less than the maximum write size. */ |
3d14c5d2b ceph: factor out ... |
646 |
static void alloc_page_vec(struct ceph_fs_client *fsc, |
1d3576fd1 ceph: address spa... |
647 648 649 650 651 |
struct ceph_osd_request *req) { req->r_pages = kmalloc(sizeof(struct page *) * req->r_num_pages, GFP_NOFS); if (!req->r_pages) { |
3d14c5d2b ceph: factor out ... |
652 |
req->r_pages = mempool_alloc(fsc->wb_pagevec_pool, GFP_NOFS); |
1d3576fd1 ceph: address spa... |
653 654 655 656 657 658 659 660 661 662 663 664 |
req->r_pages_from_pool = 1; WARN_ON(!req->r_pages); } } /* * initiate async writeback */ static int ceph_writepages_start(struct address_space *mapping, struct writeback_control *wbc) { struct inode *inode = mapping->host; |
1d3576fd1 ceph: address spa... |
665 |
struct ceph_inode_info *ci = ceph_inode(inode); |
3d14c5d2b ceph: factor out ... |
666 |
struct ceph_fs_client *fsc; |
1d3576fd1 ceph: address spa... |
667 668 669 670 |
pgoff_t index, start, end; int range_whole = 0; int should_loop = 1; pgoff_t max_pages = 0, max_pages_ever = 0; |
80e755fed ceph: allow write... |
671 |
struct ceph_snap_context *snapc = NULL, *last_snapc = NULL, *pgsnapc; |
1d3576fd1 ceph: address spa... |
672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 |
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) ", inode, do_sync, wbc->sync_mode == WB_SYNC_NONE ? "NONE" : (wbc->sync_mode == WB_SYNC_ALL ? "ALL" : "HOLD")); |
3d14c5d2b ceph: factor out ... |
693 694 |
fsc = ceph_inode_to_client(inode); if (fsc->mount_state == CEPH_MOUNT_SHUTDOWN) { |
1d3576fd1 ceph: address spa... |
695 696 697 698 |
pr_warning("writepage_start %p on forced umount ", inode); return -EIO; /* we're in a forced umount, don't write! */ } |
3d14c5d2b ceph: factor out ... |
699 700 |
if (fsc->mount_options->wsize && fsc->mount_options->wsize < wsize) wsize = fsc->mount_options->wsize; |
1d3576fd1 ceph: address spa... |
701 702 703 704 705 |
if (wsize < PAGE_CACHE_SIZE) wsize = PAGE_CACHE_SIZE; max_pages_ever = wsize >> PAGE_CACHE_SHIFT; pagevec_init(&pvec, 0); |
1d3576fd1 ceph: address spa... |
706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 |
/* where to start/end? */ if (wbc->range_cyclic) { start = mapping->writeback_index; /* Start from prev offset */ end = -1; dout(" cyclic, start at %lu ", 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 ", 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? "); goto out; } dout(" oldest snapc is %p seq %lld (%d snaps) ", 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 ", 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; struct ceph_osd_request_head *reqhead; struct ceph_osd_op *op; |
2baba2501 ceph: writeback c... |
757 |
long writeback_stat; |
1d3576fd1 ceph: address spa... |
758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 |
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 ", 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 ", 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 ", page); unlock_page(page); break; } if (!wbc->range_cyclic && page->index > end) { dout("end of range %p ", page); done = 1; unlock_page(page); break; } if (next && (page->index != next)) { dout("not consecutive %p ", page); unlock_page(page); break; } if (wbc->sync_mode != WB_SYNC_NONE) { dout("waiting on writeback %p ", 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 ", page, snap_size ? snap_size : i_size_read(inode)); done = 1; unlock_page(page); break; } if (PageWriteback(page)) { dout("%p under writeback ", page); unlock_page(page); break; } /* only if matching snap context */ |
80e755fed ceph: allow write... |
829 830 831 832 833 |
pgsnapc = (void *)page->private; if (pgsnapc->seq > snapc->seq) { dout("page snapc %p %lld > oldest %p %lld ", pgsnapc, pgsnapc->seq, snapc, snapc->seq); |
1d3576fd1 ceph: address spa... |
834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 |
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 ", page); unlock_page(page); break; } /* ok */ if (locked_pages == 0) { /* prepare async write request */ |
a77d9f7dc ceph: fix file of... |
850 851 |
offset = (unsigned long long)page->index << PAGE_CACHE_SHIFT; |
1d3576fd1 ceph: address spa... |
852 |
len = wsize; |
3d14c5d2b ceph: factor out ... |
853 |
req = ceph_osdc_new_request(&fsc->client->osdc, |
1d3576fd1 ceph: address spa... |
854 855 856 857 858 859 860 861 862 |
&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, |
b7495fc2f ceph: make page a... |
863 |
&inode->i_mtime, true, 1, 0); |
8c71897be ceph: handle ceph... |
864 865 866 867 868 869 |
if (!req) { rc = -ENOMEM; unlock_page(page); break; } |
1d3576fd1 ceph: address spa... |
870 |
max_pages = req->r_num_pages; |
3d14c5d2b ceph: factor out ... |
871 |
alloc_page_vec(fsc, req); |
1d3576fd1 ceph: address spa... |
872 873 |
req->r_callback = writepages_finish; req->r_inode = inode; |
1d3576fd1 ceph: address spa... |
874 875 876 877 878 879 880 881 |
} /* note position of first page in pvec */ if (first < 0) first = i; dout("%p will write page %p idx %lu ", inode, page, page->index); |
2baba2501 ceph: writeback c... |
882 |
|
213c99ee0 ceph: whitespace ... |
883 |
writeback_stat = |
3d14c5d2b ceph: factor out ... |
884 |
atomic_long_inc_return(&fsc->writeback_count); |
213c99ee0 ceph: whitespace ... |
885 |
if (writeback_stat > CONGESTION_ON_THRESH( |
3d14c5d2b ceph: factor out ... |
886 887 |
fsc->mount_options->congestion_kb)) { set_bdi_congested(&fsc->backing_dev_info, |
213c99ee0 ceph: whitespace ... |
888 |
BLK_RW_ASYNC); |
2baba2501 ceph: writeback c... |
889 |
} |
1d3576fd1 ceph: address spa... |
890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 |
set_page_writeback(page); req->r_pages[locked_pages] = page; 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 "); 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 ", pvec.pages[j]); pvec.pages[j-i+first] = pvec.pages[j]; } pvec.nr -= i-first; } /* submit the write */ offset = req->r_pages[0]->index << PAGE_CACHE_SHIFT; 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 ", locked_pages, offset, len); /* revise final length, page count */ req->r_num_pages = locked_pages; reqhead = req->r_request->front.iov_base; op = (void *)(reqhead + 1); op->extent.length = cpu_to_le64(len); op->payload_len = cpu_to_le32(len); req->r_request->hdr.data_len = cpu_to_le32(len); |
9d6fcb081 ceph: check retur... |
937 938 |
rc = ceph_osdc_start_request(&fsc->client->osdc, req, true); BUG_ON(rc); |
1d3576fd1 ceph: address spa... |
939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 |
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) ", (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 "); 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); |
1d3576fd1 ceph: address spa... |
972 973 974 |
ceph_put_snap_context(snapc); dout("writepages done, rc = %d ", rc); |
1d3576fd1 ceph: address spa... |
975 976 977 978 979 980 981 982 983 984 985 986 |
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); |
6298a3375 ceph: fix snap co... |
987 988 989 990 |
int ret = !oldest || snapc->seq <= oldest->seq; ceph_put_snap_context(oldest); return ret; |
1d3576fd1 ceph: address spa... |
991 992 993 994 995 |
} /* * We are only allowed to write into/dirty the page if the page is * clean, or already dirty within the same snap context. |
8f883c24d ceph: make write_... |
996 997 998 999 |
* * called with page locked. * return success with page locked, * or any failure (incl -EAGAIN) with page unlocked. |
1d3576fd1 ceph: address spa... |
1000 |
*/ |
4af6b2257 ceph: refactor ce... |
1001 1002 1003 |
static int ceph_update_writeable_page(struct file *file, loff_t pos, unsigned len, struct page *page) |
1d3576fd1 ceph: address spa... |
1004 1005 1006 |
{ struct inode *inode = file->f_dentry->d_inode; struct ceph_inode_info *ci = ceph_inode(inode); |
3d14c5d2b ceph: factor out ... |
1007 |
struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc; |
1d3576fd1 ceph: address spa... |
1008 1009 1010 1011 |
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; |
1d3576fd1 ceph: address spa... |
1012 |
int r; |
80e755fed ceph: allow write... |
1013 |
struct ceph_snap_context *snapc, *oldest; |
1d3576fd1 ceph: address spa... |
1014 |
|
1d3576fd1 ceph: address spa... |
1015 1016 1017 1018 1019 1020 1021 1022 |
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); |
80e755fed ceph: allow write... |
1023 1024 |
snapc = (void *)page->private; if (snapc && snapc != ci->i_head_snapc) { |
1d3576fd1 ceph: address spa... |
1025 1026 1027 1028 |
/* * this page is already dirty in another (older) snap * context! is it writeable now? */ |
80e755fed ceph: allow write... |
1029 |
oldest = get_oldest_context(inode, NULL); |
1d3576fd1 ceph: address spa... |
1030 |
up_read(&mdsc->snap_rwsem); |
80e755fed ceph: allow write... |
1031 |
if (snapc->seq > oldest->seq) { |
6298a3375 ceph: fix snap co... |
1032 |
ceph_put_snap_context(oldest); |
1d3576fd1 ceph: address spa... |
1033 1034 |
dout(" page %p snapc %p not current or oldest ", |
6298a3375 ceph: fix snap co... |
1035 |
page, snapc); |
1d3576fd1 ceph: address spa... |
1036 1037 1038 1039 |
/* * queue for writeback, and wait for snapc to * be writeable or written */ |
6298a3375 ceph: fix snap co... |
1040 |
snapc = ceph_get_snap_context(snapc); |
1d3576fd1 ceph: address spa... |
1041 |
unlock_page(page); |
3c6f6b79a ceph: cleanup asy... |
1042 |
ceph_queue_writeback(inode); |
8f883c24d ceph: make write_... |
1043 |
r = wait_event_interruptible(ci->i_cap_wq, |
1d3576fd1 ceph: address spa... |
1044 1045 |
context_is_writeable_or_written(inode, snapc)); ceph_put_snap_context(snapc); |
8f883c24d ceph: make write_... |
1046 1047 |
if (r == -ERESTARTSYS) return r; |
4af6b2257 ceph: refactor ce... |
1048 |
return -EAGAIN; |
1d3576fd1 ceph: address spa... |
1049 |
} |
6298a3375 ceph: fix snap co... |
1050 |
ceph_put_snap_context(oldest); |
1d3576fd1 ceph: address spa... |
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 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 |
/* yay, writeable, do it now (without dropping page lock) */ dout(" page %p snapc %p not current, but oldest ", 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 ", 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 ", 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; } /* |
4af6b2257 ceph: refactor ce... |
1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 |
* 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) { struct inode *inode = file->f_dentry->d_inode; struct page *page; pgoff_t index = pos >> PAGE_CACHE_SHIFT; int r; do { |
8f883c24d ceph: make write_... |
1123 |
/* get a page */ |
4af6b2257 ceph: refactor ce... |
1124 1125 1126 1127 1128 1129 1130 |
page = grab_cache_page_write_begin(mapping, index, 0); if (!page) return -ENOMEM; *pagep = page; dout("write_begin file %p inode %p page %p %d~%d ", file, |
213c99ee0 ceph: whitespace ... |
1131 |
inode, page, (int)pos, (int)len); |
4af6b2257 ceph: refactor ce... |
1132 1133 1134 1135 1136 1137 1138 1139 |
r = ceph_update_writeable_page(file, pos, len, page); } while (r == -EAGAIN); return r; } /* |
1d3576fd1 ceph: address spa... |
1140 1141 1142 1143 1144 1145 1146 1147 1148 |
* 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) { struct inode *inode = file->f_dentry->d_inode; |
3d14c5d2b ceph: factor out ... |
1149 1150 |
struct ceph_fs_client *fsc = ceph_inode_to_client(inode); struct ceph_mds_client *mdsc = fsc->mdsc; |
1d3576fd1 ceph: address spa... |
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 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 |
unsigned from = pos & (PAGE_CACHE_SIZE - 1); int check_cap = 0; dout("write_end file %p inode %p page %p %d~%d (%d) ", 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) { struct inode *inode = vma->vm_file->f_dentry->d_inode; struct page *page = vmf->page; |
3d14c5d2b ceph: factor out ... |
1220 |
struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc; |
1d3576fd1 ceph: address spa... |
1221 1222 |
loff_t off = page->index << PAGE_CACHE_SHIFT; loff_t size, len; |
1d3576fd1 ceph: address spa... |
1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 |
int ret; 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 ", inode, off, len, page, page->index); |
4af6b2257 ceph: refactor ce... |
1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 |
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. */ |
1d3576fd1 ceph: address spa... |
1245 1246 |
set_page_dirty(page); up_read(&mdsc->snap_rwsem); |
1d3576fd1 ceph: address spa... |
1247 1248 |
ret = VM_FAULT_LOCKED; } else { |
4af6b2257 ceph: refactor ce... |
1249 1250 1251 1252 |
if (ret == -ENOMEM) ret = VM_FAULT_OOM; else ret = VM_FAULT_SIGBUS; |
1d3576fd1 ceph: address spa... |
1253 |
} |
4af6b2257 ceph: refactor ce... |
1254 |
out: |
1d3576fd1 ceph: address spa... |
1255 1256 |
dout("page_mkwrite %p %llu~%llu = %d ", inode, off, len, ret); |
4af6b2257 ceph: refactor ce... |
1257 1258 |
if (ret != VM_FAULT_LOCKED) unlock_page(page); |
1d3576fd1 ceph: address spa... |
1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 |
return ret; } static struct vm_operations_struct ceph_vmops = { .fault = filemap_fault, .page_mkwrite = ceph_page_mkwrite, }; 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; vma->vm_flags |= VM_CAN_NONLINEAR; return 0; } |