| .. | .. |
|---|
| 9 | 9 | #include "xfs_format.h" |
|---|
| 10 | 10 | #include "xfs_log_format.h" |
|---|
| 11 | 11 | #include "xfs_trans_resv.h" |
|---|
| 12 | | -#include "xfs_bit.h" |
|---|
| 13 | | -#include "xfs_sb.h" |
|---|
| 14 | 12 | #include "xfs_mount.h" |
|---|
| 15 | 13 | #include "xfs_defer.h" |
|---|
| 16 | 14 | #include "xfs_trans.h" |
|---|
| .. | .. |
|---|
| 18 | 16 | #include "xfs_inode.h" |
|---|
| 19 | 17 | #include "xfs_inode_item.h" |
|---|
| 20 | 18 | #include "xfs_trace.h" |
|---|
| 19 | +#include "xfs_icache.h" |
|---|
| 20 | +#include "xfs_log.h" |
|---|
| 21 | 21 | |
|---|
| 22 | 22 | /* |
|---|
| 23 | 23 | * Deferred Operations in XFS |
|---|
| .. | .. |
|---|
| 172 | 172 | * reoccur. |
|---|
| 173 | 173 | */ |
|---|
| 174 | 174 | |
|---|
| 175 | | -static const struct xfs_defer_op_type *defer_op_types[XFS_DEFER_OPS_TYPE_MAX]; |
|---|
| 175 | +static const struct xfs_defer_op_type *defer_op_types[] = { |
|---|
| 176 | + [XFS_DEFER_OPS_TYPE_BMAP] = &xfs_bmap_update_defer_type, |
|---|
| 177 | + [XFS_DEFER_OPS_TYPE_REFCOUNT] = &xfs_refcount_update_defer_type, |
|---|
| 178 | + [XFS_DEFER_OPS_TYPE_RMAP] = &xfs_rmap_update_defer_type, |
|---|
| 179 | + [XFS_DEFER_OPS_TYPE_FREE] = &xfs_extent_free_defer_type, |
|---|
| 180 | + [XFS_DEFER_OPS_TYPE_AGFL_FREE] = &xfs_agfl_free_defer_type, |
|---|
| 181 | +}; |
|---|
| 182 | + |
|---|
| 183 | +static void |
|---|
| 184 | +xfs_defer_create_intent( |
|---|
| 185 | + struct xfs_trans *tp, |
|---|
| 186 | + struct xfs_defer_pending *dfp, |
|---|
| 187 | + bool sort) |
|---|
| 188 | +{ |
|---|
| 189 | + const struct xfs_defer_op_type *ops = defer_op_types[dfp->dfp_type]; |
|---|
| 190 | + |
|---|
| 191 | + if (!dfp->dfp_intent) |
|---|
| 192 | + dfp->dfp_intent = ops->create_intent(tp, &dfp->dfp_work, |
|---|
| 193 | + dfp->dfp_count, sort); |
|---|
| 194 | +} |
|---|
| 176 | 195 | |
|---|
| 177 | 196 | /* |
|---|
| 178 | 197 | * For each pending item in the intake list, log its intent item and the |
|---|
| .. | .. |
|---|
| 183 | 202 | xfs_defer_create_intents( |
|---|
| 184 | 203 | struct xfs_trans *tp) |
|---|
| 185 | 204 | { |
|---|
| 186 | | - struct list_head *li; |
|---|
| 187 | 205 | struct xfs_defer_pending *dfp; |
|---|
| 188 | 206 | |
|---|
| 189 | 207 | list_for_each_entry(dfp, &tp->t_dfops, dfp_list) { |
|---|
| 190 | | - dfp->dfp_intent = dfp->dfp_type->create_intent(tp, |
|---|
| 191 | | - dfp->dfp_count); |
|---|
| 192 | 208 | trace_xfs_defer_create_intent(tp->t_mountp, dfp); |
|---|
| 193 | | - list_sort(tp->t_mountp, &dfp->dfp_work, |
|---|
| 194 | | - dfp->dfp_type->diff_items); |
|---|
| 195 | | - list_for_each(li, &dfp->dfp_work) |
|---|
| 196 | | - dfp->dfp_type->log_item(tp, dfp->dfp_intent, li); |
|---|
| 209 | + xfs_defer_create_intent(tp, dfp, true); |
|---|
| 197 | 210 | } |
|---|
| 198 | 211 | } |
|---|
| 199 | 212 | |
|---|
| .. | .. |
|---|
| 204 | 217 | struct list_head *dop_pending) |
|---|
| 205 | 218 | { |
|---|
| 206 | 219 | struct xfs_defer_pending *dfp; |
|---|
| 220 | + const struct xfs_defer_op_type *ops; |
|---|
| 207 | 221 | |
|---|
| 208 | 222 | trace_xfs_defer_trans_abort(tp, _RET_IP_); |
|---|
| 209 | 223 | |
|---|
| 210 | 224 | /* Abort intent items that don't have a done item. */ |
|---|
| 211 | 225 | list_for_each_entry(dfp, dop_pending, dfp_list) { |
|---|
| 226 | + ops = defer_op_types[dfp->dfp_type]; |
|---|
| 212 | 227 | trace_xfs_defer_pending_abort(tp->t_mountp, dfp); |
|---|
| 213 | 228 | if (dfp->dfp_intent && !dfp->dfp_done) { |
|---|
| 214 | | - dfp->dfp_type->abort_intent(dfp->dfp_intent); |
|---|
| 229 | + ops->abort_intent(dfp->dfp_intent); |
|---|
| 215 | 230 | dfp->dfp_intent = NULL; |
|---|
| 216 | 231 | } |
|---|
| 217 | 232 | } |
|---|
| .. | .. |
|---|
| 228 | 243 | struct xfs_log_item *lip; |
|---|
| 229 | 244 | struct xfs_buf *bplist[XFS_DEFER_OPS_NR_BUFS]; |
|---|
| 230 | 245 | struct xfs_inode *iplist[XFS_DEFER_OPS_NR_INODES]; |
|---|
| 246 | + unsigned int ordered = 0; /* bitmap */ |
|---|
| 231 | 247 | int bpcount = 0, ipcount = 0; |
|---|
| 232 | 248 | int i; |
|---|
| 233 | 249 | int error; |
|---|
| 250 | + |
|---|
| 251 | + BUILD_BUG_ON(NBBY * sizeof(ordered) < XFS_DEFER_OPS_NR_BUFS); |
|---|
| 234 | 252 | |
|---|
| 235 | 253 | list_for_each_entry(lip, &tp->t_items, li_trans) { |
|---|
| 236 | 254 | switch (lip->li_type) { |
|---|
| .. | .. |
|---|
| 242 | 260 | ASSERT(0); |
|---|
| 243 | 261 | return -EFSCORRUPTED; |
|---|
| 244 | 262 | } |
|---|
| 245 | | - xfs_trans_dirty_buf(tp, bli->bli_buf); |
|---|
| 263 | + if (bli->bli_flags & XFS_BLI_ORDERED) |
|---|
| 264 | + ordered |= (1U << bpcount); |
|---|
| 265 | + else |
|---|
| 266 | + xfs_trans_dirty_buf(tp, bli->bli_buf); |
|---|
| 246 | 267 | bplist[bpcount++] = bli->bli_buf; |
|---|
| 247 | 268 | } |
|---|
| 248 | 269 | break; |
|---|
| .. | .. |
|---|
| 283 | 304 | /* Rejoin the buffers and dirty them so the log moves forward. */ |
|---|
| 284 | 305 | for (i = 0; i < bpcount; i++) { |
|---|
| 285 | 306 | xfs_trans_bjoin(tp, bplist[i]); |
|---|
| 307 | + if (ordered & (1U << i)) |
|---|
| 308 | + xfs_trans_ordered_buf(tp, bplist[i]); |
|---|
| 286 | 309 | xfs_trans_bhold(tp, bplist[i]); |
|---|
| 287 | 310 | } |
|---|
| 288 | 311 | |
|---|
| 289 | 312 | if (error) |
|---|
| 290 | 313 | trace_xfs_defer_trans_roll_error(tp, error); |
|---|
| 291 | 314 | return error; |
|---|
| 292 | | -} |
|---|
| 293 | | - |
|---|
| 294 | | -/* |
|---|
| 295 | | - * Reset an already used dfops after finish. |
|---|
| 296 | | - */ |
|---|
| 297 | | -static void |
|---|
| 298 | | -xfs_defer_reset( |
|---|
| 299 | | - struct xfs_trans *tp) |
|---|
| 300 | | -{ |
|---|
| 301 | | - ASSERT(list_empty(&tp->t_dfops)); |
|---|
| 302 | | - |
|---|
| 303 | | - /* |
|---|
| 304 | | - * Low mode state transfers across transaction rolls to mirror dfops |
|---|
| 305 | | - * lifetime. Clear it now that dfops is reset. |
|---|
| 306 | | - */ |
|---|
| 307 | | - tp->t_flags &= ~XFS_TRANS_LOWMODE; |
|---|
| 308 | 315 | } |
|---|
| 309 | 316 | |
|---|
| 310 | 317 | /* |
|---|
| .. | .. |
|---|
| 319 | 326 | struct xfs_defer_pending *pli; |
|---|
| 320 | 327 | struct list_head *pwi; |
|---|
| 321 | 328 | struct list_head *n; |
|---|
| 329 | + const struct xfs_defer_op_type *ops; |
|---|
| 322 | 330 | |
|---|
| 323 | 331 | /* |
|---|
| 324 | 332 | * Free the pending items. Caller should already have arranged |
|---|
| 325 | 333 | * for the intent items to be released. |
|---|
| 326 | 334 | */ |
|---|
| 327 | 335 | list_for_each_entry_safe(dfp, pli, dop_list, dfp_list) { |
|---|
| 336 | + ops = defer_op_types[dfp->dfp_type]; |
|---|
| 328 | 337 | trace_xfs_defer_cancel_list(mp, dfp); |
|---|
| 329 | 338 | list_del(&dfp->dfp_list); |
|---|
| 330 | 339 | list_for_each_safe(pwi, n, &dfp->dfp_work) { |
|---|
| 331 | 340 | list_del(pwi); |
|---|
| 332 | 341 | dfp->dfp_count--; |
|---|
| 333 | | - dfp->dfp_type->cancel_item(pwi); |
|---|
| 342 | + ops->cancel_item(pwi); |
|---|
| 334 | 343 | } |
|---|
| 335 | 344 | ASSERT(dfp->dfp_count == 0); |
|---|
| 336 | 345 | kmem_free(dfp); |
|---|
| 337 | 346 | } |
|---|
| 347 | +} |
|---|
| 348 | + |
|---|
| 349 | +/* |
|---|
| 350 | + * Prevent a log intent item from pinning the tail of the log by logging a |
|---|
| 351 | + * done item to release the intent item; and then log a new intent item. |
|---|
| 352 | + * The caller should provide a fresh transaction and roll it after we're done. |
|---|
| 353 | + */ |
|---|
| 354 | +static int |
|---|
| 355 | +xfs_defer_relog( |
|---|
| 356 | + struct xfs_trans **tpp, |
|---|
| 357 | + struct list_head *dfops) |
|---|
| 358 | +{ |
|---|
| 359 | + struct xlog *log = (*tpp)->t_mountp->m_log; |
|---|
| 360 | + struct xfs_defer_pending *dfp; |
|---|
| 361 | + xfs_lsn_t threshold_lsn = NULLCOMMITLSN; |
|---|
| 362 | + |
|---|
| 363 | + |
|---|
| 364 | + ASSERT((*tpp)->t_flags & XFS_TRANS_PERM_LOG_RES); |
|---|
| 365 | + |
|---|
| 366 | + list_for_each_entry(dfp, dfops, dfp_list) { |
|---|
| 367 | + /* |
|---|
| 368 | + * If the log intent item for this deferred op is not a part of |
|---|
| 369 | + * the current log checkpoint, relog the intent item to keep |
|---|
| 370 | + * the log tail moving forward. We're ok with this being racy |
|---|
| 371 | + * because an incorrect decision means we'll be a little slower |
|---|
| 372 | + * at pushing the tail. |
|---|
| 373 | + */ |
|---|
| 374 | + if (dfp->dfp_intent == NULL || |
|---|
| 375 | + xfs_log_item_in_current_chkpt(dfp->dfp_intent)) |
|---|
| 376 | + continue; |
|---|
| 377 | + |
|---|
| 378 | + /* |
|---|
| 379 | + * Figure out where we need the tail to be in order to maintain |
|---|
| 380 | + * the minimum required free space in the log. Only sample |
|---|
| 381 | + * the log threshold once per call. |
|---|
| 382 | + */ |
|---|
| 383 | + if (threshold_lsn == NULLCOMMITLSN) { |
|---|
| 384 | + threshold_lsn = xlog_grant_push_threshold(log, 0); |
|---|
| 385 | + if (threshold_lsn == NULLCOMMITLSN) |
|---|
| 386 | + break; |
|---|
| 387 | + } |
|---|
| 388 | + if (XFS_LSN_CMP(dfp->dfp_intent->li_lsn, threshold_lsn) >= 0) |
|---|
| 389 | + continue; |
|---|
| 390 | + |
|---|
| 391 | + trace_xfs_defer_relog_intent((*tpp)->t_mountp, dfp); |
|---|
| 392 | + XFS_STATS_INC((*tpp)->t_mountp, defer_relog); |
|---|
| 393 | + dfp->dfp_intent = xfs_trans_item_relog(dfp->dfp_intent, *tpp); |
|---|
| 394 | + } |
|---|
| 395 | + |
|---|
| 396 | + if ((*tpp)->t_flags & XFS_TRANS_DIRTY) |
|---|
| 397 | + return xfs_defer_trans_roll(tpp); |
|---|
| 398 | + return 0; |
|---|
| 399 | +} |
|---|
| 400 | + |
|---|
| 401 | +/* |
|---|
| 402 | + * Log an intent-done item for the first pending intent, and finish the work |
|---|
| 403 | + * items. |
|---|
| 404 | + */ |
|---|
| 405 | +static int |
|---|
| 406 | +xfs_defer_finish_one( |
|---|
| 407 | + struct xfs_trans *tp, |
|---|
| 408 | + struct xfs_defer_pending *dfp) |
|---|
| 409 | +{ |
|---|
| 410 | + const struct xfs_defer_op_type *ops = defer_op_types[dfp->dfp_type]; |
|---|
| 411 | + struct xfs_btree_cur *state = NULL; |
|---|
| 412 | + struct list_head *li, *n; |
|---|
| 413 | + int error; |
|---|
| 414 | + |
|---|
| 415 | + trace_xfs_defer_pending_finish(tp->t_mountp, dfp); |
|---|
| 416 | + |
|---|
| 417 | + dfp->dfp_done = ops->create_done(tp, dfp->dfp_intent, dfp->dfp_count); |
|---|
| 418 | + list_for_each_safe(li, n, &dfp->dfp_work) { |
|---|
| 419 | + list_del(li); |
|---|
| 420 | + dfp->dfp_count--; |
|---|
| 421 | + error = ops->finish_item(tp, dfp->dfp_done, li, &state); |
|---|
| 422 | + if (error == -EAGAIN) { |
|---|
| 423 | + /* |
|---|
| 424 | + * Caller wants a fresh transaction; put the work item |
|---|
| 425 | + * back on the list and log a new log intent item to |
|---|
| 426 | + * replace the old one. See "Requesting a Fresh |
|---|
| 427 | + * Transaction while Finishing Deferred Work" above. |
|---|
| 428 | + */ |
|---|
| 429 | + list_add(li, &dfp->dfp_work); |
|---|
| 430 | + dfp->dfp_count++; |
|---|
| 431 | + dfp->dfp_done = NULL; |
|---|
| 432 | + dfp->dfp_intent = NULL; |
|---|
| 433 | + xfs_defer_create_intent(tp, dfp, false); |
|---|
| 434 | + } |
|---|
| 435 | + |
|---|
| 436 | + if (error) |
|---|
| 437 | + goto out; |
|---|
| 438 | + } |
|---|
| 439 | + |
|---|
| 440 | + /* Done with the dfp, free it. */ |
|---|
| 441 | + list_del(&dfp->dfp_list); |
|---|
| 442 | + kmem_free(dfp); |
|---|
| 443 | +out: |
|---|
| 444 | + if (ops->finish_cleanup) |
|---|
| 445 | + ops->finish_cleanup(tp, state, error); |
|---|
| 446 | + return error; |
|---|
| 338 | 447 | } |
|---|
| 339 | 448 | |
|---|
| 340 | 449 | /* |
|---|
| .. | .. |
|---|
| 350 | 459 | struct xfs_trans **tp) |
|---|
| 351 | 460 | { |
|---|
| 352 | 461 | struct xfs_defer_pending *dfp; |
|---|
| 353 | | - struct list_head *li; |
|---|
| 354 | | - struct list_head *n; |
|---|
| 355 | | - void *state; |
|---|
| 356 | 462 | int error = 0; |
|---|
| 357 | | - void (*cleanup_fn)(struct xfs_trans *, void *, int); |
|---|
| 358 | 463 | LIST_HEAD(dop_pending); |
|---|
| 359 | 464 | |
|---|
| 360 | 465 | ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES); |
|---|
| .. | .. |
|---|
| 363 | 468 | |
|---|
| 364 | 469 | /* Until we run out of pending work to finish... */ |
|---|
| 365 | 470 | while (!list_empty(&dop_pending) || !list_empty(&(*tp)->t_dfops)) { |
|---|
| 366 | | - /* log intents and pull in intake items */ |
|---|
| 367 | | - xfs_defer_create_intents(*tp); |
|---|
| 368 | | - list_splice_tail_init(&(*tp)->t_dfops, &dop_pending); |
|---|
| 369 | | - |
|---|
| 370 | 471 | /* |
|---|
| 371 | | - * Roll the transaction. |
|---|
| 472 | + * Deferred items that are created in the process of finishing |
|---|
| 473 | + * other deferred work items should be queued at the head of |
|---|
| 474 | + * the pending list, which puts them ahead of the deferred work |
|---|
| 475 | + * that was created by the caller. This keeps the number of |
|---|
| 476 | + * pending work items to a minimum, which decreases the amount |
|---|
| 477 | + * of time that any one intent item can stick around in memory, |
|---|
| 478 | + * pinning the log tail. |
|---|
| 372 | 479 | */ |
|---|
| 480 | + xfs_defer_create_intents(*tp); |
|---|
| 481 | + list_splice_init(&(*tp)->t_dfops, &dop_pending); |
|---|
| 482 | + |
|---|
| 373 | 483 | error = xfs_defer_trans_roll(tp); |
|---|
| 374 | 484 | if (error) |
|---|
| 375 | | - goto out; |
|---|
| 485 | + goto out_shutdown; |
|---|
| 376 | 486 | |
|---|
| 377 | | - /* Log an intent-done item for the first pending item. */ |
|---|
| 487 | + /* Possibly relog intent items to keep the log moving. */ |
|---|
| 488 | + error = xfs_defer_relog(tp, &dop_pending); |
|---|
| 489 | + if (error) |
|---|
| 490 | + goto out_shutdown; |
|---|
| 491 | + |
|---|
| 378 | 492 | dfp = list_first_entry(&dop_pending, struct xfs_defer_pending, |
|---|
| 379 | 493 | dfp_list); |
|---|
| 380 | | - trace_xfs_defer_pending_finish((*tp)->t_mountp, dfp); |
|---|
| 381 | | - dfp->dfp_done = dfp->dfp_type->create_done(*tp, dfp->dfp_intent, |
|---|
| 382 | | - dfp->dfp_count); |
|---|
| 383 | | - cleanup_fn = dfp->dfp_type->finish_cleanup; |
|---|
| 384 | | - |
|---|
| 385 | | - /* Finish the work items. */ |
|---|
| 386 | | - state = NULL; |
|---|
| 387 | | - list_for_each_safe(li, n, &dfp->dfp_work) { |
|---|
| 388 | | - list_del(li); |
|---|
| 389 | | - dfp->dfp_count--; |
|---|
| 390 | | - error = dfp->dfp_type->finish_item(*tp, li, |
|---|
| 391 | | - dfp->dfp_done, &state); |
|---|
| 392 | | - if (error == -EAGAIN) { |
|---|
| 393 | | - /* |
|---|
| 394 | | - * Caller wants a fresh transaction; |
|---|
| 395 | | - * put the work item back on the list |
|---|
| 396 | | - * and jump out. |
|---|
| 397 | | - */ |
|---|
| 398 | | - list_add(li, &dfp->dfp_work); |
|---|
| 399 | | - dfp->dfp_count++; |
|---|
| 400 | | - break; |
|---|
| 401 | | - } else if (error) { |
|---|
| 402 | | - /* |
|---|
| 403 | | - * Clean up after ourselves and jump out. |
|---|
| 404 | | - * xfs_defer_cancel will take care of freeing |
|---|
| 405 | | - * all these lists and stuff. |
|---|
| 406 | | - */ |
|---|
| 407 | | - if (cleanup_fn) |
|---|
| 408 | | - cleanup_fn(*tp, state, error); |
|---|
| 409 | | - goto out; |
|---|
| 410 | | - } |
|---|
| 411 | | - } |
|---|
| 412 | | - if (error == -EAGAIN) { |
|---|
| 413 | | - /* |
|---|
| 414 | | - * Caller wants a fresh transaction, so log a |
|---|
| 415 | | - * new log intent item to replace the old one |
|---|
| 416 | | - * and roll the transaction. See "Requesting |
|---|
| 417 | | - * a Fresh Transaction while Finishing |
|---|
| 418 | | - * Deferred Work" above. |
|---|
| 419 | | - */ |
|---|
| 420 | | - dfp->dfp_intent = dfp->dfp_type->create_intent(*tp, |
|---|
| 421 | | - dfp->dfp_count); |
|---|
| 422 | | - dfp->dfp_done = NULL; |
|---|
| 423 | | - list_for_each(li, &dfp->dfp_work) |
|---|
| 424 | | - dfp->dfp_type->log_item(*tp, dfp->dfp_intent, |
|---|
| 425 | | - li); |
|---|
| 426 | | - } else { |
|---|
| 427 | | - /* Done with the dfp, free it. */ |
|---|
| 428 | | - list_del(&dfp->dfp_list); |
|---|
| 429 | | - kmem_free(dfp); |
|---|
| 430 | | - } |
|---|
| 431 | | - |
|---|
| 432 | | - if (cleanup_fn) |
|---|
| 433 | | - cleanup_fn(*tp, state, error); |
|---|
| 434 | | - } |
|---|
| 435 | | - |
|---|
| 436 | | -out: |
|---|
| 437 | | - if (error) { |
|---|
| 438 | | - xfs_defer_trans_abort(*tp, &dop_pending); |
|---|
| 439 | | - xfs_force_shutdown((*tp)->t_mountp, SHUTDOWN_CORRUPT_INCORE); |
|---|
| 440 | | - trace_xfs_defer_finish_error(*tp, error); |
|---|
| 441 | | - xfs_defer_cancel_list((*tp)->t_mountp, &dop_pending); |
|---|
| 442 | | - xfs_defer_cancel(*tp); |
|---|
| 443 | | - return error; |
|---|
| 494 | + error = xfs_defer_finish_one(*tp, dfp); |
|---|
| 495 | + if (error && error != -EAGAIN) |
|---|
| 496 | + goto out_shutdown; |
|---|
| 444 | 497 | } |
|---|
| 445 | 498 | |
|---|
| 446 | 499 | trace_xfs_defer_finish_done(*tp, _RET_IP_); |
|---|
| 447 | 500 | return 0; |
|---|
| 501 | + |
|---|
| 502 | +out_shutdown: |
|---|
| 503 | + xfs_defer_trans_abort(*tp, &dop_pending); |
|---|
| 504 | + xfs_force_shutdown((*tp)->t_mountp, SHUTDOWN_CORRUPT_INCORE); |
|---|
| 505 | + trace_xfs_defer_finish_error(*tp, error); |
|---|
| 506 | + xfs_defer_cancel_list((*tp)->t_mountp, &dop_pending); |
|---|
| 507 | + xfs_defer_cancel(*tp); |
|---|
| 508 | + return error; |
|---|
| 448 | 509 | } |
|---|
| 449 | 510 | |
|---|
| 450 | 511 | int |
|---|
| .. | .. |
|---|
| 468 | 529 | return error; |
|---|
| 469 | 530 | } |
|---|
| 470 | 531 | } |
|---|
| 471 | | - xfs_defer_reset(*tp); |
|---|
| 532 | + |
|---|
| 533 | + /* Reset LOWMODE now that we've finished all the dfops. */ |
|---|
| 534 | + ASSERT(list_empty(&(*tp)->t_dfops)); |
|---|
| 535 | + (*tp)->t_flags &= ~XFS_TRANS_LOWMODE; |
|---|
| 472 | 536 | return 0; |
|---|
| 473 | 537 | } |
|---|
| 474 | 538 | |
|---|
| .. | .. |
|---|
| 490 | 554 | struct list_head *li) |
|---|
| 491 | 555 | { |
|---|
| 492 | 556 | struct xfs_defer_pending *dfp = NULL; |
|---|
| 557 | + const struct xfs_defer_op_type *ops; |
|---|
| 493 | 558 | |
|---|
| 494 | 559 | ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES); |
|---|
| 560 | + BUILD_BUG_ON(ARRAY_SIZE(defer_op_types) != XFS_DEFER_OPS_TYPE_MAX); |
|---|
| 495 | 561 | |
|---|
| 496 | 562 | /* |
|---|
| 497 | 563 | * Add the item to a pending item at the end of the intake list. |
|---|
| .. | .. |
|---|
| 501 | 567 | if (!list_empty(&tp->t_dfops)) { |
|---|
| 502 | 568 | dfp = list_last_entry(&tp->t_dfops, |
|---|
| 503 | 569 | struct xfs_defer_pending, dfp_list); |
|---|
| 504 | | - if (dfp->dfp_type->type != type || |
|---|
| 505 | | - (dfp->dfp_type->max_items && |
|---|
| 506 | | - dfp->dfp_count >= dfp->dfp_type->max_items)) |
|---|
| 570 | + ops = defer_op_types[dfp->dfp_type]; |
|---|
| 571 | + if (dfp->dfp_type != type || |
|---|
| 572 | + (ops->max_items && dfp->dfp_count >= ops->max_items)) |
|---|
| 507 | 573 | dfp = NULL; |
|---|
| 508 | 574 | } |
|---|
| 509 | 575 | if (!dfp) { |
|---|
| 510 | 576 | dfp = kmem_alloc(sizeof(struct xfs_defer_pending), |
|---|
| 511 | | - KM_SLEEP | KM_NOFS); |
|---|
| 512 | | - dfp->dfp_type = defer_op_types[type]; |
|---|
| 577 | + KM_NOFS); |
|---|
| 578 | + dfp->dfp_type = type; |
|---|
| 513 | 579 | dfp->dfp_intent = NULL; |
|---|
| 514 | 580 | dfp->dfp_done = NULL; |
|---|
| 515 | 581 | dfp->dfp_count = 0; |
|---|
| .. | .. |
|---|
| 519 | 585 | |
|---|
| 520 | 586 | list_add_tail(li, &dfp->dfp_work); |
|---|
| 521 | 587 | dfp->dfp_count++; |
|---|
| 522 | | -} |
|---|
| 523 | | - |
|---|
| 524 | | -/* Initialize a deferred operation list. */ |
|---|
| 525 | | -void |
|---|
| 526 | | -xfs_defer_init_op_type( |
|---|
| 527 | | - const struct xfs_defer_op_type *type) |
|---|
| 528 | | -{ |
|---|
| 529 | | - defer_op_types[type->type] = type; |
|---|
| 530 | 588 | } |
|---|
| 531 | 589 | |
|---|
| 532 | 590 | /* |
|---|
| .. | .. |
|---|
| 548 | 606 | * that behavior. |
|---|
| 549 | 607 | */ |
|---|
| 550 | 608 | dtp->t_flags |= (stp->t_flags & XFS_TRANS_LOWMODE); |
|---|
| 609 | + stp->t_flags &= ~XFS_TRANS_LOWMODE; |
|---|
| 610 | +} |
|---|
| 551 | 611 | |
|---|
| 552 | | - xfs_defer_reset(stp); |
|---|
| 612 | +/* |
|---|
| 613 | + * Prepare a chain of fresh deferred ops work items to be completed later. Log |
|---|
| 614 | + * recovery requires the ability to put off until later the actual finishing |
|---|
| 615 | + * work so that it can process unfinished items recovered from the log in |
|---|
| 616 | + * correct order. |
|---|
| 617 | + * |
|---|
| 618 | + * Create and log intent items for all the work that we're capturing so that we |
|---|
| 619 | + * can be assured that the items will get replayed if the system goes down |
|---|
| 620 | + * before log recovery gets a chance to finish the work it put off. The entire |
|---|
| 621 | + * deferred ops state is transferred to the capture structure and the |
|---|
| 622 | + * transaction is then ready for the caller to commit it. If there are no |
|---|
| 623 | + * intent items to capture, this function returns NULL. |
|---|
| 624 | + * |
|---|
| 625 | + * If capture_ip is not NULL, the capture structure will obtain an extra |
|---|
| 626 | + * reference to the inode. |
|---|
| 627 | + */ |
|---|
| 628 | +static struct xfs_defer_capture * |
|---|
| 629 | +xfs_defer_ops_capture( |
|---|
| 630 | + struct xfs_trans *tp, |
|---|
| 631 | + struct xfs_inode *capture_ip) |
|---|
| 632 | +{ |
|---|
| 633 | + struct xfs_defer_capture *dfc; |
|---|
| 634 | + |
|---|
| 635 | + if (list_empty(&tp->t_dfops)) |
|---|
| 636 | + return NULL; |
|---|
| 637 | + |
|---|
| 638 | + /* Create an object to capture the defer ops. */ |
|---|
| 639 | + dfc = kmem_zalloc(sizeof(*dfc), KM_NOFS); |
|---|
| 640 | + INIT_LIST_HEAD(&dfc->dfc_list); |
|---|
| 641 | + INIT_LIST_HEAD(&dfc->dfc_dfops); |
|---|
| 642 | + |
|---|
| 643 | + xfs_defer_create_intents(tp); |
|---|
| 644 | + |
|---|
| 645 | + /* Move the dfops chain and transaction state to the capture struct. */ |
|---|
| 646 | + list_splice_init(&tp->t_dfops, &dfc->dfc_dfops); |
|---|
| 647 | + dfc->dfc_tpflags = tp->t_flags & XFS_TRANS_LOWMODE; |
|---|
| 648 | + tp->t_flags &= ~XFS_TRANS_LOWMODE; |
|---|
| 649 | + |
|---|
| 650 | + /* Capture the remaining block reservations along with the dfops. */ |
|---|
| 651 | + dfc->dfc_blkres = tp->t_blk_res - tp->t_blk_res_used; |
|---|
| 652 | + dfc->dfc_rtxres = tp->t_rtx_res - tp->t_rtx_res_used; |
|---|
| 653 | + |
|---|
| 654 | + /* Preserve the log reservation size. */ |
|---|
| 655 | + dfc->dfc_logres = tp->t_log_res; |
|---|
| 656 | + |
|---|
| 657 | + /* |
|---|
| 658 | + * Grab an extra reference to this inode and attach it to the capture |
|---|
| 659 | + * structure. |
|---|
| 660 | + */ |
|---|
| 661 | + if (capture_ip) { |
|---|
| 662 | + ihold(VFS_I(capture_ip)); |
|---|
| 663 | + dfc->dfc_capture_ip = capture_ip; |
|---|
| 664 | + } |
|---|
| 665 | + |
|---|
| 666 | + return dfc; |
|---|
| 667 | +} |
|---|
| 668 | + |
|---|
| 669 | +/* Release all resources that we used to capture deferred ops. */ |
|---|
| 670 | +void |
|---|
| 671 | +xfs_defer_ops_release( |
|---|
| 672 | + struct xfs_mount *mp, |
|---|
| 673 | + struct xfs_defer_capture *dfc) |
|---|
| 674 | +{ |
|---|
| 675 | + xfs_defer_cancel_list(mp, &dfc->dfc_dfops); |
|---|
| 676 | + if (dfc->dfc_capture_ip) |
|---|
| 677 | + xfs_irele(dfc->dfc_capture_ip); |
|---|
| 678 | + kmem_free(dfc); |
|---|
| 679 | +} |
|---|
| 680 | + |
|---|
| 681 | +/* |
|---|
| 682 | + * Capture any deferred ops and commit the transaction. This is the last step |
|---|
| 683 | + * needed to finish a log intent item that we recovered from the log. If any |
|---|
| 684 | + * of the deferred ops operate on an inode, the caller must pass in that inode |
|---|
| 685 | + * so that the reference can be transferred to the capture structure. The |
|---|
| 686 | + * caller must hold ILOCK_EXCL on the inode, and must unlock it before calling |
|---|
| 687 | + * xfs_defer_ops_continue. |
|---|
| 688 | + */ |
|---|
| 689 | +int |
|---|
| 690 | +xfs_defer_ops_capture_and_commit( |
|---|
| 691 | + struct xfs_trans *tp, |
|---|
| 692 | + struct xfs_inode *capture_ip, |
|---|
| 693 | + struct list_head *capture_list) |
|---|
| 694 | +{ |
|---|
| 695 | + struct xfs_mount *mp = tp->t_mountp; |
|---|
| 696 | + struct xfs_defer_capture *dfc; |
|---|
| 697 | + int error; |
|---|
| 698 | + |
|---|
| 699 | + ASSERT(!capture_ip || xfs_isilocked(capture_ip, XFS_ILOCK_EXCL)); |
|---|
| 700 | + |
|---|
| 701 | + /* If we don't capture anything, commit transaction and exit. */ |
|---|
| 702 | + dfc = xfs_defer_ops_capture(tp, capture_ip); |
|---|
| 703 | + if (!dfc) |
|---|
| 704 | + return xfs_trans_commit(tp); |
|---|
| 705 | + |
|---|
| 706 | + /* Commit the transaction and add the capture structure to the list. */ |
|---|
| 707 | + error = xfs_trans_commit(tp); |
|---|
| 708 | + if (error) { |
|---|
| 709 | + xfs_defer_ops_release(mp, dfc); |
|---|
| 710 | + return error; |
|---|
| 711 | + } |
|---|
| 712 | + |
|---|
| 713 | + list_add_tail(&dfc->dfc_list, capture_list); |
|---|
| 714 | + return 0; |
|---|
| 715 | +} |
|---|
| 716 | + |
|---|
| 717 | +/* |
|---|
| 718 | + * Attach a chain of captured deferred ops to a new transaction and free the |
|---|
| 719 | + * capture structure. If an inode was captured, it will be passed back to the |
|---|
| 720 | + * caller with ILOCK_EXCL held and joined to the transaction with lockflags==0. |
|---|
| 721 | + * The caller now owns the inode reference. |
|---|
| 722 | + */ |
|---|
| 723 | +void |
|---|
| 724 | +xfs_defer_ops_continue( |
|---|
| 725 | + struct xfs_defer_capture *dfc, |
|---|
| 726 | + struct xfs_trans *tp, |
|---|
| 727 | + struct xfs_inode **captured_ipp) |
|---|
| 728 | +{ |
|---|
| 729 | + ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES); |
|---|
| 730 | + ASSERT(!(tp->t_flags & XFS_TRANS_DIRTY)); |
|---|
| 731 | + |
|---|
| 732 | + /* Lock and join the captured inode to the new transaction. */ |
|---|
| 733 | + if (dfc->dfc_capture_ip) { |
|---|
| 734 | + xfs_ilock(dfc->dfc_capture_ip, XFS_ILOCK_EXCL); |
|---|
| 735 | + xfs_trans_ijoin(tp, dfc->dfc_capture_ip, 0); |
|---|
| 736 | + } |
|---|
| 737 | + *captured_ipp = dfc->dfc_capture_ip; |
|---|
| 738 | + |
|---|
| 739 | + /* Move captured dfops chain and state to the transaction. */ |
|---|
| 740 | + list_splice_init(&dfc->dfc_dfops, &tp->t_dfops); |
|---|
| 741 | + tp->t_flags |= dfc->dfc_tpflags; |
|---|
| 742 | + |
|---|
| 743 | + kmem_free(dfc); |
|---|
| 553 | 744 | } |
|---|