diff options
Diffstat (limited to 'fs/xfs')
| -rw-r--r-- | fs/xfs/Makefile | 1 | ||||
| -rw-r--r-- | fs/xfs/libxfs/xfs_ag.c | 8 | ||||
| -rw-r--r-- | fs/xfs/libxfs/xfs_ag.h | 6 | ||||
| -rw-r--r-- | fs/xfs/libxfs/xfs_inode_buf.c | 3 | ||||
| -rw-r--r-- | fs/xfs/xfs_icache.c | 3 | ||||
| -rw-r--r-- | fs/xfs/xfs_inode.c | 570 | ||||
| -rw-r--r-- | fs/xfs/xfs_inode.h | 7 | ||||
| -rw-r--r-- | fs/xfs/xfs_iunlink_item.c | 180 | ||||
| -rw-r--r-- | fs/xfs/xfs_iunlink_item.h | 27 | ||||
| -rw-r--r-- | fs/xfs/xfs_log_recover.c | 171 | ||||
| -rw-r--r-- | fs/xfs/xfs_super.c | 10 | ||||
| -rw-r--r-- | fs/xfs/xfs_trace.h | 1 | ||||
| -rw-r--r-- | fs/xfs/xfs_trans.c | 91 | ||||
| -rw-r--r-- | fs/xfs/xfs_trans.h | 6 |
14 files changed, 539 insertions, 545 deletions
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile index b056cfc6398e..1131dd01e4fe 100644 --- a/fs/xfs/Makefile +++ b/fs/xfs/Makefile @@ -106,6 +106,7 @@ xfs-y += xfs_log.o \ xfs_icreate_item.o \ xfs_inode_item.o \ xfs_inode_item_recover.o \ + xfs_iunlink_item.o \ xfs_refcount_item.o \ xfs_rmap_item.o \ xfs_log_recover.o \ diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c index 71f5dae7ad6c..bb0c700afe3c 100644 --- a/fs/xfs/libxfs/xfs_ag.c +++ b/fs/xfs/libxfs/xfs_ag.c @@ -194,7 +194,6 @@ xfs_free_perag( XFS_IS_CORRUPT(pag->pag_mount, atomic_read(&pag->pag_ref) != 0); cancel_delayed_work_sync(&pag->pag_blockgc_work); - xfs_iunlink_destroy(pag); xfs_buf_hash_destroy(pag); call_rcu(&pag->rcu_head, __xfs_free_perag); @@ -323,10 +322,6 @@ xfs_initialize_perag( if (error) goto out_remove_pag; - error = xfs_iunlink_init(pag); - if (error) - goto out_hash_destroy; - /* first new pag is fully initialized */ if (first_initialised == NULLAGNUMBER) first_initialised = index; @@ -349,8 +344,6 @@ xfs_initialize_perag( mp->m_ag_prealloc_blocks = xfs_prealloc_blocks(mp); return 0; -out_hash_destroy: - xfs_buf_hash_destroy(pag); out_remove_pag: radix_tree_delete(&mp->m_perag_tree, index); out_free_pag: @@ -362,7 +355,6 @@ out_unwind_new_pags: if (!pag) break; xfs_buf_hash_destroy(pag); - xfs_iunlink_destroy(pag); kmem_free(pag); } return error; diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h index 75f7c10c110a..517a138faa66 100644 --- a/fs/xfs/libxfs/xfs_ag.h +++ b/fs/xfs/libxfs/xfs_ag.h @@ -103,12 +103,6 @@ struct xfs_perag { /* background prealloc block trimming */ struct delayed_work pag_blockgc_work; - /* - * Unlinked inode information. This incore information reflects - * data stored in the AGI, so callers must hold the AGI buffer lock - * or have some other means to control concurrency. - */ - struct rhashtable pagi_unlinked_hash; #endif /* __KERNEL__ */ }; diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 3a12bd3c7c97..806f209defed 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -229,7 +229,8 @@ xfs_inode_from_disk( ip->i_nblocks = be64_to_cpu(from->di_nblocks); ip->i_extsize = be32_to_cpu(from->di_extsize); ip->i_forkoff = from->di_forkoff; - ip->i_diflags = be16_to_cpu(from->di_flags); + ip->i_diflags = be16_to_cpu(from->di_flags); + ip->i_next_unlinked = be32_to_cpu(from->di_next_unlinked); if (from->di_dmevmask || from->di_dmstate) xfs_iflags_set(ip, XFS_IPRESERVE_DM_FIELDS); diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 2609825d53ee..aef4097ffd3e 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -111,6 +111,8 @@ xfs_inode_alloc( INIT_WORK(&ip->i_ioend_work, xfs_end_io); INIT_LIST_HEAD(&ip->i_ioend_list); spin_lock_init(&ip->i_ioend_lock); + ip->i_next_unlinked = NULLAGINO; + ip->i_prev_unlinked = NULLAGINO; return ip; } @@ -912,6 +914,7 @@ reclaim: ip->i_checked = 0; spin_unlock(&ip->i_flags_lock); + ASSERT(!ip->i_itemp || ip->i_itemp->ili_item.li_buf == NULL); xfs_iunlock(ip, XFS_ILOCK_EXCL); XFS_STATS_INC(ip->i_mount, xs_ig_reclaims); diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 296e253bcfcd..622953791ddd 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -20,6 +20,7 @@ #include "xfs_trans.h" #include "xfs_buf_item.h" #include "xfs_inode_item.h" +#include "xfs_iunlink_item.h" #include "xfs_ialloc.h" #include "xfs_bmap.h" #include "xfs_bmap_util.h" @@ -1801,195 +1802,69 @@ out: * because we must walk that list to find the inode that points to the inode * being removed from the unlinked hash bucket list. * - * What if we modelled the unlinked list as a collection of records capturing - * "X.next_unlinked = Y" relations? If we indexed those records on Y, we'd - * have a fast way to look up unlinked list predecessors, which avoids the - * slow list walk. That's exactly what we do here (in-core) with a per-AG - * rhashtable. + * Hence we keep an in-memory double linked list to link each inode on an + * unlinked list. Because there are 64 unlinked lists per AGI, keeping pointer + * based lists would require having 64 list heads in the perag, one for each + * list. This is expensive in terms of memory (think millions of AGs) and cache + * misses on lookups. Instead, use the fact that inodes on the unlinked list + * must be referenced at the VFS level to keep them on the list and hence we + * have an existence guarantee for inodes on the unlinked list. * - * Because this is a backref cache, we ignore operational failures since the - * iunlink code can fall back to the slow bucket walk. The only errors that - * should bubble out are for obviously incorrect situations. - * - * All users of the backref cache MUST hold the AGI buffer lock to serialize - * access or have otherwise provided for concurrency control. + * Given we have an existence guarantee, we can use lockless inode cache lookups + * to resolve aginos to xfs inodes. This means we only need 8 bytes per inode + * for the double linked unlinked list, and we don't need any extra locking to + * keep the list safe as all manipulations are done under the AGI buffer lock. + * Keeping the list up to date does not require memory allocation, just finding + * the XFS inode and updating the next/prev unlinked list aginos. */ -/* Capture a "X.next_unlinked = Y" relationship. */ -struct xfs_iunlink { - struct rhash_head iu_rhash_head; - xfs_agino_t iu_agino; /* X */ - xfs_agino_t iu_next_unlinked; /* Y */ -}; - -/* Unlinked list predecessor lookup hashtable construction */ -static int -xfs_iunlink_obj_cmpfn( - struct rhashtable_compare_arg *arg, - const void *obj) -{ - const xfs_agino_t *key = arg->key; - const struct xfs_iunlink *iu = obj; - - if (iu->iu_next_unlinked != *key) - return 1; - return 0; -} - -static const struct rhashtable_params xfs_iunlink_hash_params = { - .min_size = XFS_AGI_UNLINKED_BUCKETS, - .key_len = sizeof(xfs_agino_t), - .key_offset = offsetof(struct xfs_iunlink, - iu_next_unlinked), - .head_offset = offsetof(struct xfs_iunlink, iu_rhash_head), - .automatic_shrinking = true, - .obj_cmpfn = xfs_iunlink_obj_cmpfn, -}; - /* - * Return X, where X.next_unlinked == @agino. Returns NULLAGINO if no such - * relation is found. + * Find an inode on the unlinked list. This does not take references to the + * inode as we have existence guarantees by holding the AGI buffer lock and that + * only unlinked, referenced inodes can be on the unlinked inode list. If we + * don't find the inode in cache, then let the caller handle the situation. */ -static xfs_agino_t -xfs_iunlink_lookup_backref( +static struct xfs_inode * +xfs_iunlink_lookup( struct xfs_perag *pag, xfs_agino_t agino) { - struct xfs_iunlink *iu; - - iu = rhashtable_lookup_fast(&pag->pagi_unlinked_hash, &agino, - xfs_iunlink_hash_params); - return iu ? iu->iu_agino : NULLAGINO; -} + struct xfs_inode *ip; -/* - * Take ownership of an iunlink cache entry and insert it into the hash table. - * If successful, the entry will be owned by the cache; if not, it is freed. - * Either way, the caller does not own @iu after this call. - */ -static int -xfs_iunlink_insert_backref( - struct xfs_perag *pag, - struct xfs_iunlink *iu) -{ - int error; + rcu_read_lock(); + ip = radix_tree_lookup(&pag->pag_ici_root, agino); - error = rhashtable_insert_fast(&pag->pagi_unlinked_hash, - &iu->iu_rhash_head, xfs_iunlink_hash_params); /* - * Fail loudly if there already was an entry because that's a sign of - * corruption of in-memory data. Also fail loudly if we see an error - * code we didn't anticipate from the rhashtable code. Currently we - * only anticipate ENOMEM. + * Inode not in memory or in RCU freeing limbo should not happen. + * Warn about this and let the caller handle the failure. */ - if (error) { - WARN(error != -ENOMEM, "iunlink cache insert error %d", error); - kmem_free(iu); + if (WARN_ON_ONCE(!ip || !ip->i_ino)) { + rcu_read_unlock(); + return NULL; } - /* - * Absorb any runtime errors that aren't a result of corruption because - * this is a cache and we can always fall back to bucket list scanning. - */ - if (error != 0 && error != -EEXIST) - error = 0; - return error; + ASSERT(!xfs_iflags_test(ip, XFS_IRECLAIMABLE | XFS_IRECLAIM)); + rcu_read_unlock(); + return ip; } -/* Remember that @prev_agino.next_unlinked = @this_agino. */ +/* Update the prev pointer of the next agino. */ static int -xfs_iunlink_add_backref( +xfs_iunlink_update_backref( struct xfs_perag *pag, xfs_agino_t prev_agino, - xfs_agino_t this_agino) -{ - struct xfs_iunlink *iu; - - if (XFS_TEST_ERROR(false, pag->pag_mount, XFS_ERRTAG_IUNLINK_FALLBACK)) - return 0; - - iu = kmem_zalloc(sizeof(*iu), KM_NOFS); - iu->iu_agino = prev_agino; - iu->iu_next_unlinked = this_agino; - - return xfs_iunlink_insert_backref(pag, iu); -} - -/* - * Replace X.next_unlinked = @agino with X.next_unlinked = @next_unlinked. - * If @next_unlinked is NULLAGINO, we drop the backref and exit. If there - * wasn't any such entry then we don't bother. - */ -static int -xfs_iunlink_change_backref( - struct xfs_perag *pag, - xfs_agino_t agino, - xfs_agino_t next_unlinked) + xfs_agino_t next_agino) { - struct xfs_iunlink *iu; - int error; - - /* Look up the old entry; if there wasn't one then exit. */ - iu = rhashtable_lookup_fast(&pag->pagi_unlinked_hash, &agino, - xfs_iunlink_hash_params); - if (!iu) - return 0; - - /* - * Remove the entry. This shouldn't ever return an error, but if we - * couldn't remove the old entry we don't want to add it again to the - * hash table, and if the entry disappeared on us then someone's - * violated the locking rules and we need to fail loudly. Either way - * we cannot remove the inode because internal state is or would have - * been corrupt. - */ - error = rhashtable_remove_fast(&pag->pagi_unlinked_hash, - &iu->iu_rhash_head, xfs_iunlink_hash_params); - if (error) - return error; + struct xfs_inode *ip; - /* If there is no new next entry just free our item and return. */ - if (next_unlinked == NULLAGINO) { - kmem_free(iu); + /* No update necessary if we are at the end of the list. */ + if (next_agino == NULLAGINO) return 0; - } - - /* Update the entry and re-add it to the hash table. */ - iu->iu_next_unlinked = next_unlinked; - return xfs_iunlink_insert_backref(pag, iu); -} - -/* Set up the in-core predecessor structures. */ -int -xfs_iunlink_init( - struct xfs_perag *pag) -{ - return rhashtable_init(&pag->pagi_unlinked_hash, - &xfs_iunlink_hash_params); -} - -/* Free the in-core predecessor structures. */ -static void -xfs_iunlink_free_item( - void *ptr, - void *arg) -{ - struct xfs_iunlink *iu = ptr; - bool *freed_anything = arg; - *freed_anything = true; - kmem_free(iu); -} - -void -xfs_iunlink_destroy( - struct xfs_perag *pag) -{ - bool freed_anything = false; - - rhashtable_free_and_destroy(&pag->pagi_unlinked_hash, - xfs_iunlink_free_item, &freed_anything); - - ASSERT(freed_anything == false || xfs_is_shutdown(pag->pag_mount)); + ip = xfs_iunlink_lookup(pag, next_agino); + if (!ip) + return -EFSCORRUPTED; + ip->i_prev_unlinked = prev_agino; + return 0; } /* @@ -2031,88 +1906,53 @@ xfs_iunlink_update_bucket( return 0; } -/* Set an on-disk inode's next_unlinked pointer. */ -STATIC void -xfs_iunlink_update_dinode( - struct xfs_trans *tp, - struct xfs_perag *pag, - xfs_agino_t agino, - struct xfs_buf *ibp, - struct xfs_dinode *dip, - struct xfs_imap *imap, - xfs_agino_t next_agino) -{ - struct xfs_mount *mp = tp->t_mountp; - int offset; - - ASSERT(xfs_verify_agino_or_null(pag, next_agino)); - - trace_xfs_iunlink_update_dinode(mp, pag->pag_agno, agino, - be32_to_cpu(dip->di_next_unlinked), next_agino); - - dip->di_next_unlinked = cpu_to_be32(next_agino); - offset = imap->im_boffset + - offsetof(struct xfs_dinode, di_next_unlinked); - - /* need to recalc the inode CRC if appropriate */ - xfs_dinode_calc_crc(mp, dip); - xfs_trans_inode_buf(tp, ibp); - xfs_trans_log_buf(tp, ibp, offset, offset + sizeof(xfs_agino_t) - 1); -} - -/* Set an in-core inode's unlinked pointer and return the old value. */ -STATIC int -xfs_iunlink_update_inode( +static int +xfs_iunlink_insert_inode( struct xfs_trans *tp, - struct xfs_inode *ip, struct xfs_perag *pag, - xfs_agino_t next_agino, - xfs_agino_t *old_next_agino) + struct xfs_buf *agibp, + struct xfs_inode *ip) { struct xfs_mount *mp = tp->t_mountp; - struct xfs_dinode *dip; - struct xfs_buf *ibp; - xfs_agino_t old_value; + struct xfs_agi *agi = agibp->b_addr; + xfs_agino_t next_agino; + xfs_agino_t agino = XFS_INO_TO_AGINO(mp, ip->i_ino); + short bucket_index = agino % XFS_AGI_UNLINKED_BUCKETS; int error; - ASSERT(xfs_verify_agino_or_null(pag, next_agino)); - - error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &ibp); - if (error) - return error; - dip = xfs_buf_offset(ibp, ip->i_imap.im_boffset); - - /* Make sure the old pointer isn't garbage. */ - old_value = be32_to_cpu(dip->di_next_unlinked); - if (!xfs_verify_agino_or_null(pag, old_value)) { - xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, dip, - sizeof(*dip), __this_address); - error = -EFSCORRUPTED; - goto out; + /* + * Get the index into the agi hash table for the list this inode will + * go on. Make sure the pointer isn't garbage and that this inode + * isn't already on the list. + */ + next_agino = be32_to_cpu(agi->agi_unlinked[bucket_index]); + if (next_agino == agino || + !xfs_verify_agino_or_null(pag, next_agino)) { + xfs_buf_mark_corrupt(agibp); + return -EFSCORRUPTED; } /* - * Since we're updating a linked list, we should never find that the - * current pointer is the same as the new value, unless we're - * terminating the list. + * Update the prev pointer in the next inode to point back to this + * inode. */ - *old_next_agino = old_value; - if (old_value == next_agino) { - if (next_agino != NULLAGINO) { - xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, - dip, sizeof(*dip), __this_address); - error = -EFSCORRUPTED; - } - goto out; + error = xfs_iunlink_update_backref(pag, agino, next_agino); + if (error) + return error; + + if (next_agino != NULLAGINO) { + /* + * There is already another inode in the bucket, so point this + * inode to the current head of the list. + */ + error = xfs_iunlink_log_inode(tp, ip, pag, next_agino); + if (error) + return error; + ip->i_next_unlinked = next_agino; } - /* Ok, update the new pointer. */ - xfs_iunlink_update_dinode(tp, pag, XFS_INO_TO_AGINO(mp, ip->i_ino), - ibp, dip, &ip->i_imap, next_agino); - return 0; -out: - xfs_trans_brelse(tp, ibp); - return error; + /* Point the head of the list to point to this inode. */ + return xfs_iunlink_update_bucket(tp, pag, agibp, bucket_index, agino); } /* @@ -2129,11 +1969,7 @@ xfs_iunlink( { struct xfs_mount *mp = tp->t_mountp; struct xfs_perag *pag; - struct xfs_agi *agi; struct xfs_buf *agibp; - xfs_agino_t next_agino; - xfs_agino_t agino = XFS_INO_TO_AGINO(mp, ip->i_ino); - short bucket_index = agino % XFS_AGI_UNLINKED_BUCKETS; int error; ASSERT(VFS_I(ip)->i_nlink == 0); @@ -2146,193 +1982,29 @@ xfs_iunlink( error = xfs_read_agi(pag, tp, &agibp); if (error) goto out; - agi = agibp->b_addr; - /* - * Get the index into the agi hash table for the list this inode will - * go on. Make sure the pointer isn't garbage and that this inode - * isn't already on the list. - */ - next_agino = be32_to_cpu(agi->agi_unlinked[bucket_index]); - if (next_agino == agino || - !xfs_verify_agino_or_null(pag, next_agino)) { - xfs_buf_mark_corrupt(agibp); - error = -EFSCORRUPTED; - goto out; - } - - if (next_agino != NULLAGINO) { - xfs_agino_t old_agino; - - /* - * There is already another inode in the bucket, so point this - * inode to the current head of the list. - */ - error = xfs_iunlink_update_inode(tp, ip, pag, next_agino, - &old_agino); - if (error) - goto out; - ASSERT(old_agino == NULLAGINO); - - /* - * agino has been unlinked, add a backref from the next inode - * back to agino. - */ - error = xfs_iunlink_add_backref(pag, agino, next_agino); - if (error) - goto out; - } - - /* Point the head of the list to point to this inode. */ - error = xfs_iunlink_update_bucket(tp, pag, agibp, bucket_index, agino); + error = xfs_iunlink_insert_inode(tp, pag, agibp, ip); out: xfs_perag_put(pag); return error; } -/* Return the imap, dinode pointer, and buffer for an inode. */ -STATIC int -xfs_iunlink_map_ino( - struct xfs_trans *tp, - xfs_agnumber_t agno, - xfs_agino_t agino, - struct xfs_imap *imap, - struct xfs_dinode **dipp, - struct xfs_buf **bpp) -{ - struct xfs_mount *mp = tp->t_mountp; - int error; - - imap->im_blkno = 0; - error = xfs_imap(mp, tp, XFS_AGINO_TO_INO(mp, agno, agino), imap, 0); - if (error) { - xfs_warn(mp, "%s: xfs_imap returned error %d.", - __func__, error); - return error; - } - - error = xfs_imap_to_bp(mp, tp, imap, bpp); - if (error) { - xfs_warn(mp, "%s: xfs_imap_to_bp returned error %d.", - __func__, error); - return error; - } - - *dipp = xfs_buf_offset(*bpp, imap->im_boffset); - return 0; -} - -/* - * Walk the unlinked chain from @head_agino until we find the inode that - * points to @target_agino. Return the inode number, map, dinode pointer, - * and inode cluster buffer of that inode as @agino, @imap, @dipp, and @bpp. - * - * @tp, @pag, @head_agino, and @target_agino are input parameters. - * @agino, @imap, @dipp, and @bpp are all output parameters. - * - * Do not call this function if @target_agino is the head of the list. - */ -STATIC int -xfs_iunlink_map_prev( - struct xfs_trans *tp, - struct xfs_perag *pag, - xfs_agino_t head_agino, - xfs_agino_t target_agino, - xfs_agino_t *agino, - struct xfs_imap *imap, - struct xfs_dinode **dipp, - struct xfs_buf **bpp) -{ - struct xfs_mount *mp = tp->t_mountp; - xfs_agino_t next_agino; - int error; - - ASSERT(head_agino != target_agino); - *bpp = NULL; - - /* See if our backref cache can find it faster. */ - *agino = xfs_iunlink_lookup_backref(pag, target_agino); - if (*agino != NULLAGINO) { - error = xfs_iunlink_map_ino(tp, pag->pag_agno, *agino, imap, - dipp, bpp); - if (error) - return error; - - if (be32_to_cpu((*dipp)->di_next_unlinked) == target_agino) - return 0; - - /* - * If we get here the cache contents were corrupt, so drop the - * buffer and fall back to walking the bucket list. - */ - xfs_trans_brelse(tp, *bpp); - *bpp = NULL; - WARN_ON_ONCE(1); - } - - trace_xfs_iunlink_map_prev_fallback(mp, pag->pag_agno); - - /* Otherwise, walk the entire bucket until we find it. */ - next_agino = head_agino; - while (next_agino != target_agino) { - xfs_agino_t unlinked_agino; - - if (*bpp) - xfs_trans_brelse(tp, *bpp); - - *agino = next_agino; - error = xfs_iunlink_map_ino(tp, pag->pag_agno, next_agino, imap, - dipp, bpp); - if (error) - return error; - - unlinked_agino = be32_to_cpu((*dipp)->di_next_unlinked); - /* - * Make sure this pointer is valid and isn't an obvious - * infinite loop. - */ - if (!xfs_verify_agino(pag, unlinked_agino) || - next_agino == unlinked_agino) { - XFS_CORRUPTION_ERROR(__func__, - XFS_ERRLEVEL_LOW, mp, - *dipp, sizeof(**dipp)); - error = -EFSCORRUPTED; - return error; - } - next_agino = unlinked_agino; - } - - return 0; -} - -/* - * Pull the on-disk inode from the AGI unlinked list. - */ -STATIC int -xfs_iunlink_remove( +static int +xfs_iunlink_remove_inode( struct xfs_trans *tp, struct xfs_perag *pag, + struct xfs_buf *agibp, struct xfs_inode *ip) { struct xfs_mount *mp = tp->t_mountp; - struct xfs_agi *agi; - struct xfs_buf *agibp; - struct xfs_buf *last_ibp; - struct xfs_dinode *last_dip = NULL; + struct xfs_agi *agi = agibp->b_addr; xfs_agino_t agino = XFS_INO_TO_AGINO(mp, ip->i_ino); - xfs_agino_t next_agino; xfs_agino_t head_agino; short bucket_index = agino % XFS_AGI_UNLINKED_BUCKETS; int error; trace_xfs_iunlink_remove(ip); - /* Get the agi buffer first. It ensures lock ordering on the list. */ - error = xfs_read_agi(pag, tp, &agibp); - if (error) - return error; - agi = agibp->b_addr; - /* * Get the index into the agi hash table for the list this inode will * go on. Make sure the head pointer isn't garbage. @@ -2349,52 +2021,60 @@ xfs_iunlink_remove( * the old pointer value so that we can update whatever was previous * to us in the list to point to whatever was next in the list. */ - error = xfs_iunlink_update_inode(tp, ip, pag, NULLAGINO, &next_agino); + error = xfs_iunlink_log_inode(tp, ip, pag, NULLAGINO); if (error) return error; /* - * If there was a backref pointing from the next inode back to this - * one, remove it because we've removed this inode from the list. - * - * Later, if this inode was in the middle of the list we'll update - * this inode's backref to point from the next inode. + * Update the prev pointer in the next inode to point back to previous + * inode in the chain. */ - if (next_agino != NULLAGINO) { - error = xfs_iunlink_change_backref(pag, next_agino, NULLAGINO); - if (error) - return error; - } + error = xfs_iunlink_update_backref(pag, ip->i_prev_unlinked, + ip->i_next_unlinked); + if (error) + return error; if (head_agino != agino) { - struct xfs_imap imap; - xfs_agino_t prev_agino; - - /* We need to search the list for the inode being freed. */ - error = xfs_iunlink_map_prev(tp, pag, head_agino, agino, - &prev_agino, &imap, &last_dip, &last_ibp); - if (error) - return error; + struct xfs_inode *prev_ip; - /* Point the previous inode on the list to the next inode. */ - xfs_iunlink_update_dinode(tp, pag, prev_agino, last_ibp, - last_dip, &imap, next_agino); + prev_ip = xfs_iunlink_lookup(pag, ip->i_prev_unlinked); + if (!prev_ip) + return -EFSCORRUPTED; - /* - * Now we deal with the backref for this inode. If this inode - * pointed at a real inode, change the backref that pointed to - * us to point to our old next. If this inode was the end of - * the list, delete the backref that pointed to us. Note that - * change_backref takes care of deleting the backref if - * next_agino is NULLAGINO. - */ - return xfs_iunlink_change_backref(agibp->b_pag, agino, - next_agino); + error = xfs_iunlink_log_inode(tp, prev_ip, pag, + ip->i_next_unlinked); + prev_ip->i_next_unlinked = ip->i_next_unlinked; + } else { + /* Point the head of the list to the next unlinked inode. */ + error = xfs_iunlink_update_bucket(tp, pag, agibp, bucket_index, + ip->i_next_unlinked); } - /* Point the head of the list to the next unlinked inode. */ - return xfs_iunlink_update_bucket(tp, pag, agibp, bucket_index, - next_agino); + ip->i_next_unlinked = NULLAGINO; + ip->i_prev_unlinked = NULLAGINO; + return error; +} + +/* + * Pull the on-disk inode from the AGI unlinked list. + */ +STATIC int +xfs_iunlink_remove( + struct xfs_trans *tp, + struct xfs_perag *pag, + struct xfs_inode *ip) +{ + struct xfs_buf *agibp; + int error; + + trace_xfs_iunlink_remove(ip); + + /* Get the agi buffer first. It ensures lock ordering on the list. */ + error = xfs_read_agi(pag, tp, &agibp); + if (error) + return error; + + return xfs_iunlink_remove_inode(tp, pag, agibp, ip); } /* diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 7be6f8e705ab..8d8cce61e5ba 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -68,6 +68,10 @@ typedef struct xfs_inode { uint64_t i_diflags2; /* XFS_DIFLAG2_... */ struct timespec64 i_crtime; /* time created */ + /* unlinked list pointers */ + xfs_agino_t i_next_unlinked; + xfs_agino_t i_prev_unlinked; + /* VFS inode */ struct inode i_vnode; /* embedded VFS inode */ @@ -505,9 +509,6 @@ extern struct kmem_cache *xfs_inode_cache; bool xfs_inode_needs_inactive(struct xfs_inode *ip); -int xfs_iunlink_init(struct xfs_perag *pag); -void xfs_iunlink_destroy(struct xfs_perag *pag); - void xfs_end_io(struct work_struct *work); int xfs_ilock2_io_mmap(struct xfs_inode *ip1, struct xfs_inode *ip2); diff --git a/fs/xfs/xfs_iunlink_item.c b/fs/xfs/xfs_iunlink_item.c new file mode 100644 index 000000000000..43005ce8bd48 --- /dev/null +++ b/fs/xfs/xfs_iunlink_item.c @@ -0,0 +1,180 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2020-2022, Red Hat, Inc. + * All Rights Reserved. + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_inode.h" +#include "xfs_trans.h" +#include "xfs_trans_priv.h" +#include "xfs_ag.h" +#include "xfs_iunlink_item.h" +#include "xfs_trace.h" +#include "xfs_error.h" + +struct kmem_cache *xfs_iunlink_cache; + +static inline struct xfs_iunlink_item *IUL_ITEM(struct xfs_log_item *lip) +{ + return container_of(lip, struct xfs_iunlink_item, item); +} + +static void +xfs_iunlink_item_release( + struct xfs_log_item *lip) +{ + struct xfs_iunlink_item *iup = IUL_ITEM(lip); + + xfs_perag_put(iup->pag); + kmem_cache_free(xfs_iunlink_cache, IUL_ITEM(lip)); +} + + +static uint64_t +xfs_iunlink_item_sort( + struct xfs_log_item *lip) +{ + return IUL_ITEM(lip)->ip->i_ino; +} + +/* + * Look up the inode cluster buffer and log the on-disk unlinked inode change + * we need to make. + */ +static int +xfs_iunlink_log_dinode( + struct xfs_trans *tp, + struct xfs_iunlink_item *iup) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_inode *ip = iup->ip; + struct xfs_dinode *dip; + struct xfs_buf *ibp; + int offset; + int error; + + error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &ibp); + if (error) + return error; + /* + * Don't log the unlinked field on stale buffers as this may be the + * transaction that frees the inode cluster and relogging the buffer + * here will incorrectly remove the stale state. + */ + if (ibp->b_flags & XBF_STALE) + goto out; + + dip = xfs_buf_offset(ibp, ip->i_imap.im_boffset); + + /* Make sure the old pointer isn't garbage. */ + if (be32_to_cpu(dip->di_next_unlinked) != iup->old_agino) { + xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, dip, + sizeof(*dip), __this_address); + error = -EFSCORRUPTED; + goto out; + } + + trace_xfs_iunlink_update_dinode(mp, iup->pag->pag_agno, + XFS_INO_TO_AGINO(mp, ip->i_ino), + be32_to_cpu(dip->di_next_unlinked), iup->next_agino); + + dip->di_next_unlinked = cpu_to_be32(iup->next_agino); + offset = ip->i_imap.im_boffset + + offsetof(struct xfs_dinode, di_next_unlinked); + + xfs_dinode_calc_crc(mp, dip); + xfs_trans_inode_buf(tp, ibp); + xfs_trans_log_buf(tp, ibp, offset, offset + sizeof(xfs_agino_t) - 1); + return 0; +out: + xfs_trans_brelse(tp, ibp); + return error; +} + +/* + * On precommit, we grab the inode cluster buffer for the inode number we were + * passed, then update the next unlinked field for that inode in the buffer and + * log the buffer. This ensures that the inode cluster buffer was logged in the + * correct order w.r.t. other inode cluster buffers. We can then remove the + * iunlink item from the transaction and release it as it is has now served it's + * purpose. + */ +static int +xfs_iunlink_item_precommit( + struct xfs_trans *tp, + struct xfs_log_item *lip) +{ + struct xfs_iunlink_item *iup = IUL_ITEM(lip); + int error; + + error = xfs_iunlink_log_dinode(tp, iup); + list_del(&lip->li_trans); + xfs_iunlink_item_release(lip); + return error; +} + +static const struct xfs_item_ops xfs_iunlink_item_ops = { + .iop_release = xfs_iunlink_item_release, + .iop_sort = xfs_iunlink_item_sort, + .iop_precommit = xfs_iunlink_item_precommit, +}; + + +/* + * Initialize the inode log item for a newly allocated (in-core) inode. + * + * Inode extents can only reside within an AG. Hence specify the starting + * block for the inode chunk by offset within an AG as well as the + * length of the allocated extent. + * + * This joins the item to the transaction and marks it dirty so + * that we don't need a separate call to do this, nor does the + * caller need to know anything about the iunlink item. + */ +int +xfs_iunlink_log_inode( + struct xfs_trans *tp, + struct xfs_inode *ip, + struct xfs_perag *pag, + xfs_agino_t next_agino) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_iunlink_item *iup; + + ASSERT(xfs_verify_agino_or_null(pag, next_agino)); + ASSERT(xfs_verify_agino_or_null(pag, ip->i_next_unlinked)); + + /* + * Since we're updating a linked list, we should never find that the + * current pointer is the same as the new value, unless we're + * terminating the list. + */ + if (ip->i_next_unlinked == next_agino) { + if (next_agino != NULLAGINO) + return -EFSCORRUPTED; + return 0; + } + + iup = kmem_cache_zalloc(xfs_iunlink_cache, GFP_KERNEL | __GFP_NOFAIL); + xfs_log_item_init(mp, &iup->item, XFS_LI_IUNLINK, + &xfs_iunlink_item_ops); + + iup->ip = ip; + iup->next_agino = next_agino; + iup->old_agino = ip->i_next_unlinked; + + atomic_inc(&pag->pag_ref); + iup->pag = pag; + + xfs_trans_add_item(tp, &iup->item); + tp->t_flags |= XFS_TRANS_DIRTY; + set_bit(XFS_LI_DIRTY, &iup->item.li_flags); + return 0; +} + diff --git a/fs/xfs/xfs_iunlink_item.h b/fs/xfs/xfs_iunlink_item.h new file mode 100644 index 000000000000..c793cdcaccde --- /dev/null +++ b/fs/xfs/xfs_iunlink_item.h @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2020-2022, Red Hat, Inc. + * All Rights Reserved. + */ +#ifndef XFS_IUNLINK_ITEM_H +#define XFS_IUNLINK_ITEM_H 1 + +struct xfs_trans; +struct xfs_inode; +struct xfs_perag; + +/* in memory log item structure */ +struct xfs_iunlink_item { + struct xfs_log_item item; + struct xfs_inode *ip; + struct xfs_perag *pag; + xfs_agino_t next_agino; + xfs_agino_t old_agino; +}; + +extern struct kmem_cache *xfs_iunlink_cache; + +int xfs_iunlink_log_inode(struct xfs_trans *tp, struct xfs_inode *ip, + struct xfs_perag *pag, xfs_agino_t next_agino); + +#endif /* XFS_IUNLINK_ITEM_H */ diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 3e8c62c6c2b1..9e0e7ff76e02 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -2667,55 +2667,57 @@ out_error: return; } -STATIC xfs_agino_t -xlog_recover_process_one_iunlink( - struct xfs_perag *pag, - xfs_agino_t agino, - int bucket) +static int +xlog_recover_iunlink_bucket( + struct xfs_perag *pag, + struct xfs_agi *agi, + int bucket) { - struct xfs_buf *ibp; - struct xfs_dinode *dip; - struct xfs_inode *ip; - xfs_ino_t ino; - int error; - - ino = XFS_AGINO_TO_INO(pag->pag_mount, pag->pag_agno, agino); - error = xfs_iget(pag->pag_mount, NULL, ino, 0, 0, &ip); - if (error) - goto fail; + struct xfs_mount *mp = pag->pag_mount; + struct xfs_inode *prev_ip = NULL; + struct xfs_inode *ip; + xfs_agino_t prev_agino, agino; + int error = 0; - /* - * Get the on disk inode to find the next inode in the bucket. - */ - error = xfs_imap_to_bp(pag->pag_mount, NULL, &ip->i_imap, &ibp); - if (error) - goto fail_iput; - dip = xfs_buf_offset(ibp, ip->i_imap.im_boffset); + agino = be32_to_cpu(agi->agi_unlinked[bucket]); + while (agino != NULLAGINO) { + error = xfs_iget(mp, NULL, + XFS_AGINO_TO_INO(mp, pag->pag_agno, agino), + 0, 0, &ip); + if (error) + break; - xfs_iflags_clear(ip, XFS_IRECOVERY); - ASSERT(VFS_I(ip)->i_nlink == 0); - ASSERT(VFS_I(ip)->i_mode != 0); + ASSERT(VFS_I(ip)->i_nlink == 0); + ASSERT(VFS_I(ip)->i_mode != 0); + xfs_iflags_clear(ip, XFS_IRECOVERY); + agino = ip->i_next_unlinked; - /* setup for the next pass */ - agino = be32_to_cpu(dip->di_next_unlinked); - xfs_buf_relse(ibp); + if (prev_ip) { + ip->i_prev_unlinked = prev_agino; + xfs_irele(prev_ip); + + /* + * Ensure the inode is removed from the unlinked list + * before we continue so that it won't race with + * building the in-memory list here. This could be + * serialised with the agibp lock, but that just + * serialises via lockstepping and it's much simpler + * just to flush the inodegc queue and wait for it to + * complete. + */ + xfs_inodegc_flush(mp); + } - xfs_irele(ip); - return agino; + prev_agino = agino; + prev_ip = ip; + } - fail_iput: - xfs_irele(ip); - fail: - /* - * We can't read in the inode this bucket points to, or this inode - * is messed up. Just ditch this bucket of inodes. We will lose - * some inodes and space, but at least we won't hang. - * - * Call xlog_recover_clear_agi_bucket() to perform a transaction to - * clear the inode pointer in the bucket. - */ - xlog_recover_clear_agi_bucket(pag, bucket); - return NULLAGINO; + if (prev_ip) { + ip->i_prev_unlinked = prev_agino; + xfs_irele(prev_ip); + } + xfs_inodegc_flush(mp); + return error; } /* @@ -2741,59 +2743,70 @@ xlog_recover_process_one_iunlink( * scheduled on this CPU to ensure other scheduled work can run without undue * latency. */ -STATIC void -xlog_recover_process_iunlinks( - struct xlog *log) +static void +xlog_recover_iunlink_ag( + struct xfs_perag *pag) { - struct xfs_mount *mp = log->l_mp; - struct xfs_perag *pag; - xfs_agnumber_t agno; struct xfs_agi *agi; struct xfs_buf *agibp; - xfs_agino_t agino; int bucket; int error; - for_each_perag(mp, agno, pag) { - error = xfs_read_agi(pag, NULL, &agibp); + error = xfs_read_agi(pag, NULL, &agibp); + if (error) { + /* + * AGI is b0rked. Don't process it. + * + * We should probably mark the filesystem as corrupt after we've + * recovered all the ag's we can.... + */ + return; + } + + /* + * Unlock the buffer so that it can be acquired in the normal course of + * the transaction to truncate and free each inode. Because we are not + * racing with anyone else here for the AGI buffer, we don't even need + * to hold it locked to read the initial unlinked bucket entries out of + * the buffer. We keep buffer reference though, so that it stays pinned + * in memory while we need the buffer. + */ + agi = agibp->b_addr; + xfs_buf_unlock(agibp); + + for (bucket = 0; bucket < XFS_AGI_UNLINKED_BUCKETS; bucket++) { + error = xlog_recover_iunlink_bucket(pag, agi, bucket); if (error) { /* - * AGI is b0rked. Don't process it. - * - * We should probably mark the filesystem as corrupt - * after we've recovered all the ag's we can.... + * Bucket is unrecoverable, so only a repair scan can + * free the remaining unlinked inodes. Just empty the + * bucket and remaining inodes on it unreferenced and + * unfreeable. */ - continue; + xfs_inodegc_flush(pag->pag_mount); + xlog_recover_clear_agi_bucket(pag, bucket); } - /* - * Unlock the buffer so that it can be acquired in the normal - * course of the transaction to truncate and free each inode. - * Because we are not racing with anyone else here for the AGI - * buffer, we don't even need to hold it locked to read the - * initial unlinked bucket entries out of the buffer. We keep - * buffer reference though, so that it stays pinned in memory - * while we need the buffer. - */ - agi = agibp->b_addr; - xfs_buf_unlock(agibp); - - for (bucket = 0; bucket < XFS_AGI_UNLINKED_BUCKETS; bucket++) { - agino = be32_to_cpu(agi->agi_unlinked[bucket]); - while (agino != NULLAGINO) { - agino = xlog_recover_process_one_iunlink(pag, - agino, bucket); - cond_resched(); - } - } - xfs_buf_rele(agibp); } + xfs_buf_rele(agibp); +} + +static void +xlog_recover_process_iunlinks( + struct xlog *log) +{ + struct xfs_perag *pag; + xfs_agnumber_t agno; + + for_each_perag(log->l_mp, agno, pag) + xlog_recover_iunlink_ag(pag); + /* * Flush the pending unlinked inodes to ensure that the inactivations * are fully completed on disk and the incore inodes can be reclaimed * before we signal that recovery is complete. */ - xfs_inodegc_flush(mp); + xfs_inodegc_flush(log->l_mp); } STATIC void diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 1e02ec67c3a0..4edee1d3784a 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -40,6 +40,7 @@ #include "xfs_defer.h" #include "xfs_attr_item.h" #include "xfs_xattr.h" +#include "xfs_iunlink_item.h" #include <linux/magic.h> #include <linux/fs_context.h> @@ -2096,8 +2097,16 @@ xfs_init_caches(void) if (!xfs_attri_cache) goto out_destroy_attrd_cache; + xfs_iunlink_cache = kmem_cache_create("xfs_iul_item", + sizeof(struct xfs_iunlink_item), + 0, 0, NULL); + if (!xfs_iunlink_cache) + goto out_destroy_attri_cache; + return 0; + out_destroy_attri_cache: + kmem_cache_destroy(xfs_attri_cache); out_destroy_attrd_cache: kmem_cache_destroy(xfs_attrd_cache); out_destroy_bui_cache: @@ -2148,6 +2157,7 @@ xfs_destroy_caches(void) * destroy caches. */ rcu_barrier(); + kmem_cache_destroy(xfs_iunlink_cache); kmem_cache_destroy(xfs_attri_cache); kmem_cache_destroy(xfs_attrd_cache); kmem_cache_destroy(xfs_bui_cache); diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 0fa1b7a2918c..926543f01335 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -3672,7 +3672,6 @@ DEFINE_EVENT(xfs_ag_inode_class, name, \ TP_ARGS(ip)) DEFINE_AGINODE_EVENT(xfs_iunlink); DEFINE_AGINODE_EVENT(xfs_iunlink_remove); -DEFINE_AG_EVENT(xfs_iunlink_map_prev_fallback); DECLARE_EVENT_CLASS(xfs_fs_corrupt_class, TP_PROTO(struct xfs_mount *mp, unsigned int flags), diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index ec347717ce78..7bd16fbff534 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -845,6 +845,90 @@ xfs_trans_committed_bulk( } /* + * Sort transaction items prior to running precommit operations. This will + * attempt to order the items such that they will always be locked in the same + * order. Items that have no sort function are moved to the end of the list + * and so are locked last. + * + * This may need refinement as different types of objects add sort functions. + * + * Function is more complex than it needs to be because we are comparing 64 bit + * values and the function only returns 32 bit values. + */ +static int +xfs_trans_precommit_sort( + void *unused_arg, + const struct list_head *a, + const struct list_head *b) +{ + struct xfs_log_item *lia = container_of(a, + struct xfs_log_item, li_trans); + struct xfs_log_item *lib = container_of(b, + struct xfs_log_item, li_trans); + int64_t diff; + + /* + * If both items are non-sortable, leave them alone. If only one is + * sortable, move the non-sortable item towards the end of the list. + */ + if (!lia->li_ops->iop_sort && !lib->li_ops->iop_sort) + return 0; + if (!lia->li_ops->iop_sort) + return 1; + if (!lib->li_ops->iop_sort) + return -1; + + diff = lia->li_ops->iop_sort(lia) - lib->li_ops->iop_sort(lib); + if (diff < 0) + return -1; + if (diff > 0) + return 1; + return 0; +} + +/* + * Run transaction precommit functions. + * + * If there is an error in any of the callouts, then stop immediately and + * trigger a shutdown to abort the transaction. There is no recovery possible + * from errors at this point as the transaction is dirty.... + */ +static int +xfs_trans_run_precommits( + struct xfs_trans *tp) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_log_item *lip, *n; + int error = 0; + + /* + * Sort the item list to avoid ABBA deadlocks with other transactions + * running precommit operations that lock multiple shared items such as + * inode cluster buffers. + */ + list_sort(NULL, &tp->t_items, xfs_trans_precommit_sort); + + /* + * Precommit operations can remove the log item from the transaction + * if the log item exists purely to delay modifications until they + * can be ordered against other operations. Hence we have to use + * list_for_each_entry_safe() here. + */ + list_for_each_entry_safe(lip, n, &tp->t_items, li_trans) { + if (!test_bit(XFS_LI_DIRTY, &lip->li_flags)) + continue; + if (lip->li_ops->iop_precommit) { + error = lip->li_ops->iop_precommit(tp, lip); + if (error) + break; + } + } + if (error) + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + return error; +} + +/* * Commit the given transaction to the log. * * XFS disk error handling mechanism is not based on a typical @@ -869,6 +953,13 @@ __xfs_trans_commit( trace_xfs_trans_commit(tp, _RET_IP_); + error = xfs_trans_run_precommits(tp); + if (error) { + if (tp->t_flags & XFS_TRANS_PERM_LOG_RES) + xfs_defer_cancel(tp); + goto out_unreserve; + } + /* * Finish deferred items on final commit. Only permanent transactions * should ever have deferred ops. diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h index 29927ceecf82..55819785941c 100644 --- a/fs/xfs/xfs_trans.h +++ b/fs/xfs/xfs_trans.h @@ -72,10 +72,12 @@ struct xfs_item_ops { void (*iop_format)(struct xfs_log_item *, struct xfs_log_vec *); void (*iop_pin)(struct xfs_log_item *); void (*iop_unpin)(struct xfs_log_item *, int remove); - uint (*iop_push)(struct xfs_log_item *, struct list_head *); + uint64_t (*iop_sort)(struct xfs_log_item *lip); + int (*iop_precommit)(struct xfs_trans *tp, struct xfs_log_item *lip); void (*iop_committing)(struct xfs_log_item *lip, xfs_csn_t seq); - void (*iop_release)(struct xfs_log_item *); xfs_lsn_t (*iop_committed)(struct xfs_log_item *, xfs_lsn_t); + uint (*iop_push)(struct xfs_log_item *, struct list_head *); + void (*iop_release)(struct xfs_log_item *); int (*iop_recover)(struct xfs_log_item *lip, struct list_head *capture_list); bool (*iop_match)(struct xfs_log_item *item, uint64_t id); |