diff options
| -rw-r--r-- | fs/btrfs/file.c | 58 |
1 files changed, 46 insertions, 12 deletions
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index df958fdb140c..8786b2b8f0a1 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -523,6 +523,7 @@ void btrfs_drop_extent_cache(struct btrfs_inode *inode, u64 start, u64 end, testend = 0; } while (1) { + bool ends_after_range = false; int no_splits = 0; modified = false; @@ -539,10 +540,12 @@ void btrfs_drop_extent_cache(struct btrfs_inode *inode, u64 start, u64 end, write_unlock(&em_tree->lock); break; } + if (testend && em->start + em->len > start + len) + ends_after_range = true; flags = em->flags; gen = em->generation; if (skip_pinned && test_bit(EXTENT_FLAG_PINNED, &em->flags)) { - if (testend && em->start + em->len >= start + len) { + if (ends_after_range) { free_extent_map(em); write_unlock(&em_tree->lock); break; @@ -592,7 +595,7 @@ void btrfs_drop_extent_cache(struct btrfs_inode *inode, u64 start, u64 end, split = split2; split2 = NULL; } - if (testend && em->start + em->len > start + len) { + if (ends_after_range) { u64 diff = start + len - em->start; split->start = start + len; @@ -630,14 +633,42 @@ void btrfs_drop_extent_cache(struct btrfs_inode *inode, u64 start, u64 end, } else { ret = add_extent_mapping(em_tree, split, modified); - ASSERT(ret == 0); /* Logic error */ + /* Logic error, shouldn't happen. */ + ASSERT(ret == 0); + if (WARN_ON(ret != 0) && modified) + btrfs_set_inode_full_sync(inode); } free_extent_map(split); split = NULL; } next: - if (extent_map_in_tree(em)) + if (extent_map_in_tree(em)) { + /* + * If the extent map is still in the tree it means that + * either of the following is true: + * + * 1) It fits entirely in our range (doesn't end beyond + * it or starts before it); + * + * 2) It starts before our range and/or ends after our + * range, and we were not able to allocate the extent + * maps for split operations, @split and @split2. + * + * If we are at case 2) then we just remove the entire + * extent map - this is fine since if anyone needs it to + * access the subranges outside our range, will just + * load it again from the subvolume tree's file extent + * item. However if the extent map was in the list of + * modified extents, then we must mark the inode for a + * full fsync, otherwise a fast fsync will miss this + * extent if it's new and needs to be logged. + */ + if ((em->start < start || ends_after_range) && modified) { + ASSERT(no_splits); + btrfs_set_inode_full_sync(inode); + } remove_extent_mapping(em_tree, em); + } write_unlock(&em_tree->lock); /* once for us */ @@ -2261,14 +2292,6 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) atomic_inc(&root->log_batch); /* - * Always check for the full sync flag while holding the inode's lock, - * to avoid races with other tasks. The flag must be either set all the - * time during logging or always off all the time while logging. - */ - full_sync = test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, - &BTRFS_I(inode)->runtime_flags); - - /* * Before we acquired the inode's lock and the mmap lock, someone may * have dirtied more pages in the target range. We need to make sure * that writeback for any such pages does not start while we are logging @@ -2293,6 +2316,17 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) } /* + * Always check for the full sync flag while holding the inode's lock, + * to avoid races with other tasks. The flag must be either set all the + * time during logging or always off all the time while logging. + * We check the flag here after starting delalloc above, because when + * running delalloc the full sync flag may be set if we need to drop + * extra extent map ranges due to temporary memory allocation failures. + */ + full_sync = test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, + &BTRFS_I(inode)->runtime_flags); + + /* * We have to do this here to avoid the priority inversion of waiting on * IO of a lower priority task while holding a transaction open. * |