From 4751832da990a927c37526ae67b9226ea01eb99e Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Fri, 7 Apr 2017 10:43:15 +0800 Subject: [PATCH 1/9] btrfs: fiemap: Cache and merge fiemap extent before submit it to user [BUG] Cycle mount btrfs can cause fiemap to return different result. Like: # mount /dev/vdb5 /mnt/btrfs # dd if=/dev/zero bs=16K count=4 oflag=dsync of=/mnt/btrfs/file # xfs_io -c "fiemap -v" /mnt/btrfs/file /mnt/test/file: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..127]: 25088..25215 128 0x1 # umount /mnt/btrfs # mount /dev/vdb5 /mnt/btrfs # xfs_io -c "fiemap -v" /mnt/btrfs/file /mnt/test/file: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..31]: 25088..25119 32 0x0 1: [32..63]: 25120..25151 32 0x0 2: [64..95]: 25152..25183 32 0x0 3: [96..127]: 25184..25215 32 0x1 But after above fiemap, we get correct merged result if we call fiemap again. # xfs_io -c "fiemap -v" /mnt/btrfs/file /mnt/test/file: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..127]: 25088..25215 128 0x1 [REASON] Btrfs will try to merge extent map when inserting new extent map. btrfs_fiemap(start=0 len=(u64)-1) |- extent_fiemap(start=0 len=(u64)-1) |- get_extent_skip_holes(start=0 len=64k) | |- btrfs_get_extent_fiemap(start=0 len=64k) | |- btrfs_get_extent(start=0 len=64k) | | Found on-disk (ino, EXTENT_DATA, 0) | |- add_extent_mapping() | |- Return (em->start=0, len=16k) | |- fiemap_fill_next_extent(logic=0 phys=X len=16k) | |- get_extent_skip_holes(start=0 len=64k) | |- btrfs_get_extent_fiemap(start=0 len=64k) | |- btrfs_get_extent(start=16k len=48k) | | Found on-disk (ino, EXTENT_DATA, 16k) | |- add_extent_mapping() | | |- try_merge_map() | | Merge with previous em start=0 len=16k | | resulting em start=0 len=32k | |- Return (em->start=0, len=32K) << Merged result |- Stripe off the unrelated range (0~16K) of return em |- fiemap_fill_next_extent(logic=16K phys=X+16K len=16K) ^^^ Causing split fiemap extent. And since in add_extent_mapping(), em is already merged, in next fiemap() call, we will get merged result. [FIX] Here we introduce a new structure, fiemap_cache, which records previous fiemap extent. And will always try to merge current fiemap_cache result before calling fiemap_fill_next_extent(). Only when we failed to merge current fiemap extent with cached one, we will call fiemap_fill_next_extent() to submit cached one. So by this method, we can merge all fiemap extents. It can also be done in fs/ioctl.c, however the problem is if fieinfo->fi_extents_max == 0, we have no space to cache previous fiemap extent. So I choose to merge it in btrfs. Signed-off-by: Qu Wenruo Reviewed-by: Liu Bo Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/extent_io.c | 124 ++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 122 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index d8da3edf2ac3..4317ed3ad830 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4377,6 +4377,123 @@ static struct extent_map *get_extent_skip_holes(struct inode *inode, return NULL; } +/* + * To cache previous fiemap extent + * + * Will be used for merging fiemap extent + */ +struct fiemap_cache { + u64 offset; + u64 phys; + u64 len; + u32 flags; + bool cached; +}; + +/* + * Helper to submit fiemap extent. + * + * Will try to merge current fiemap extent specified by @offset, @phys, + * @len and @flags with cached one. + * And only when we fails to merge, cached one will be submitted as + * fiemap extent. + * + * Return value is the same as fiemap_fill_next_extent(). + */ +static int emit_fiemap_extent(struct fiemap_extent_info *fieinfo, + struct fiemap_cache *cache, + u64 offset, u64 phys, u64 len, u32 flags) +{ + int ret = 0; + + if (!cache->cached) + goto assign; + + /* + * Sanity check, extent_fiemap() should have ensured that new + * fiemap extent won't overlap with cahced one. + * Not recoverable. + * + * NOTE: Physical address can overlap, due to compression + */ + if (cache->offset + cache->len > offset) { + WARN_ON(1); + return -EINVAL; + } + + /* + * Only merges fiemap extents if + * 1) Their logical addresses are continuous + * + * 2) Their physical addresses are continuous + * So truly compressed (physical size smaller than logical size) + * extents won't get merged with each other + * + * 3) Share same flags except FIEMAP_EXTENT_LAST + * So regular extent won't get merged with prealloc extent + */ + if (cache->offset + cache->len == offset && + cache->phys + cache->len == phys && + (cache->flags & ~FIEMAP_EXTENT_LAST) == + (flags & ~FIEMAP_EXTENT_LAST)) { + cache->len += len; + cache->flags |= flags; + goto try_submit_last; + } + + /* Not mergeable, need to submit cached one */ + ret = fiemap_fill_next_extent(fieinfo, cache->offset, cache->phys, + cache->len, cache->flags); + cache->cached = false; + if (ret) + return ret; +assign: + cache->cached = true; + cache->offset = offset; + cache->phys = phys; + cache->len = len; + cache->flags = flags; +try_submit_last: + if (cache->flags & FIEMAP_EXTENT_LAST) { + ret = fiemap_fill_next_extent(fieinfo, cache->offset, + cache->phys, cache->len, cache->flags); + cache->cached = false; + } + return ret; +} + +/* + * Sanity check for fiemap cache + * + * All fiemap cache should be submitted by emit_fiemap_extent() + * Iteration should be terminated either by last fiemap extent or + * fieinfo->fi_extents_max. + * So no cached fiemap should exist. + */ +static int check_fiemap_cache(struct btrfs_fs_info *fs_info, + struct fiemap_extent_info *fieinfo, + struct fiemap_cache *cache) +{ + int ret; + + if (!cache->cached) + return 0; + + /* Small and recoverbale problem, only to info developer */ +#ifdef CONFIG_BTRFS_DEBUG + WARN_ON(1); +#endif + btrfs_warn(fs_info, + "unhandled fiemap cache detected: offset=%llu phys=%llu len=%llu flags=0x%x", + cache->offset, cache->phys, cache->len, cache->flags); + ret = fiemap_fill_next_extent(fieinfo, cache->offset, cache->phys, + cache->len, cache->flags); + cache->cached = false; + if (ret > 0) + ret = 0; + return ret; +} + int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len, get_extent_t *get_extent) { @@ -4394,6 +4511,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, struct extent_state *cached_state = NULL; struct btrfs_path *path; struct btrfs_root *root = BTRFS_I(inode)->root; + struct fiemap_cache cache = { 0 }; int end = 0; u64 em_start = 0; u64 em_len = 0; @@ -4573,8 +4691,8 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, flags |= FIEMAP_EXTENT_LAST; end = 1; } - ret = fiemap_fill_next_extent(fieinfo, em_start, disko, - em_len, flags); + ret = emit_fiemap_extent(fieinfo, &cache, em_start, disko, + em_len, flags); if (ret) { if (ret == 1) ret = 0; @@ -4582,6 +4700,8 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, } } out_free: + if (!ret) + ret = check_fiemap_cache(root->fs_info, fieinfo, &cache); free_extent_map(em); out: btrfs_free_path(path); From 8d91012528b3c95c159e6b6779e367421df9cbb5 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 2 May 2017 17:03:50 +0200 Subject: [PATCH 2/9] btrfs: Make flush bios explicitely sync Commit b685d3d65ac7 "block: treat REQ_FUA and REQ_PREFLUSH as synchronous" removed REQ_SYNC flag from WRITE_{FUA|PREFLUSH|...} definitions. generic_make_request_checks() however strips REQ_FUA and REQ_PREFLUSH flags from a bio when the storage doesn't report volatile write cache and thus write effectively becomes asynchronous which can lead to performance regressions Fix the problem by making sure all bios which are synchronous are properly marked with REQ_SYNC. CC: David Sterba CC: linux-btrfs@vger.kernel.org Fixes: b685d3d65ac791406e0dfd8779cc9b3707fea5a3 Signed-off-by: Jan Kara Reviewed-by: Liu Bo Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 683194242deb..b3579d11fb26 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3488,10 +3488,12 @@ static int write_dev_supers(struct btrfs_device *device, * we fua the first super. The others we allow * to go down lazy. */ - if (i == 0) - ret = btrfsic_submit_bh(REQ_OP_WRITE, REQ_FUA, bh); - else + if (i == 0) { + ret = btrfsic_submit_bh(REQ_OP_WRITE, + REQ_SYNC | REQ_FUA, bh); + } else { ret = btrfsic_submit_bh(REQ_OP_WRITE, REQ_SYNC, bh); + } if (ret) errors++; } @@ -3556,7 +3558,7 @@ static int write_dev_flush(struct btrfs_device *device, int wait) bio->bi_end_io = btrfs_end_empty_barrier; bio->bi_bdev = device->bdev; - bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH; + bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH; init_completion(&device->flush_wait); bio->bi_private = &device->flush_wait; device->flush_bio = bio; From bff5baf8aa37a97293725a16c03f49872249c07e Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 9 May 2017 18:14:01 +0100 Subject: [PATCH 3/9] btrfs: fix incorrect error return ret being passed to mapping_set_error The setting of return code ret should be based on the error code passed into function end_extent_writepage and not on ret. Thanks to Liu Bo for spotting this mistake in the original fix I submitted. Detected by CoverityScan, CID#1414312 ("Logically dead code") Fixes: 5dca6eea91653e ("Btrfs: mark mapping with error flag to report errors to userspace") Signed-off-by: Colin Ian King Reviewed-by: Liu Bo Signed-off-by: David Sterba --- fs/btrfs/extent_io.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 4317ed3ad830..d3619e010005 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2458,7 +2458,7 @@ void end_extent_writepage(struct page *page, int err, u64 start, u64 end) if (!uptodate) { ClearPageUptodate(page); SetPageError(page); - ret = ret < 0 ? ret : -EIO; + ret = err < 0 ? err : -EIO; mapping_set_error(page->mapping, ret); } } From cc2b702c52094b637a351d7491ac5200331d0445 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Fri, 12 May 2017 01:03:52 +0200 Subject: [PATCH 4/9] btrfs: use correct types for page indices in btrfs_page_exists_in_range Variables start_idx and end_idx are supposed to hold a page index derived from the file offsets. The int type is not the right one though, offsets larger than 1 << 44 will get silently trimmed off the high bits. (1 << 44 is 16TiB) What can go wrong, if start is below the boundary and end gets trimmed: - if there's a page after start, we'll find it (radix_tree_gang_lookup_slot) - the final check "if (page->index <= end_idx)" will unexpectedly fail The function will return false, ie. "there's no page in the range", although there is at least one. btrfs_page_exists_in_range is used to prevent races in: * in hole punching, where we make sure there are not pages in the truncated range, otherwise we'll wait for them to finish and redo truncation, but we're going to replace the pages with holes anyway so the only problem is the intermediate state * lock_extent_direct: we want to make sure there are no pages before we lock and start DIO, to prevent stale data reads For practical occurence of the bug, there are several constaints. The file must be quite large, the affected range must cross the 16TiB boundary and the internal state of the file pages and pending operations must match. Also, we must not have started any ordered data in the range, otherwise we don't even reach the buggy function check. DIO locking tries hard in several places to avoid deadlocks with buffered IO and avoids waiting for ranges. The worst consequence seems to be stale data read. CC: Liu Bo CC: stable@vger.kernel.org # 3.16+ Fixes: fc4adbff823f7 ("btrfs: Drop EXTENT_UPTODATE check in hole punching and direct locking") Reviewed-by: Liu Bo Signed-off-by: David Sterba --- fs/btrfs/inode.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 17cbe9306faf..3fc3e10594a4 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7483,8 +7483,8 @@ bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end) int found = false; void **pagep = NULL; struct page *page = NULL; - int start_idx; - int end_idx; + unsigned long start_idx; + unsigned long end_idx; start_idx = start >> PAGE_SHIFT; From 896533a7da929136d0432713f02a3edffece2826 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Wed, 17 May 2017 09:49:37 -0400 Subject: [PATCH 5/9] btrfs: fix memory leak in update_space_info failure path If we fail to add the space_info kobject, we'll leak the memory for the percpu counter. Fixes: 6ab0a2029c (btrfs: publish allocation data in sysfs) Cc: # v3.14+ Signed-off-by: Jeff Mahoney Reviewed-by: Liu Bo Signed-off-by: David Sterba --- fs/btrfs/extent-tree.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index e390451c72e6..27ca5b81ed22 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3993,6 +3993,7 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags, info->space_info_kobj, "%s", alloc_name(found->flags)); if (ret) { + percpu_counter_destroy(&found->total_bytes_pinned); kfree(found); return ret; } From a9b3311ef36b670909ea4443f306c8318082c8f0 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Wed, 17 May 2017 11:38:34 -0400 Subject: [PATCH 6/9] btrfs: fix race with relocation recovery and fs_root setup If we have to recover relocation during mount, we'll ultimately have to evict the orphan inode. That goes through the reservation dance, where priority_reclaim_metadata_space and flush_space expect fs_info->fs_root to be valid. That's the next thing to be set up during mount, so we crash, almost always in flush_space trying to join the transaction but priority_reclaim_metadata_space is possible as well. This call path has been problematic in the past WRT whether ->fs_root is valid yet. Commit 957780eb278 (Btrfs: introduce ticketed enospc infrastructure) added new users that are called in the direct path instead of the async path that had already been worked around. The thing is that we don't actually need the fs_root, specifically, for anything. We either use it to determine whether the root is the chunk_root for use in choosing an allocation profile or as a root to pass btrfs_join_transaction before immediately committing it. Anything that isn't the chunk root works in the former case and any root works in the latter. A simple fix is to use a root we know will always be there: the extent_root. Cc: # v4.8+ Fixes: 957780eb278 (Btrfs: introduce ticketed enospc infrastructure) Signed-off-by: Jeff Mahoney Reviewed-by: Liu Bo Signed-off-by: David Sterba --- fs/btrfs/extent-tree.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 27ca5b81ed22..33d979e9ea2a 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4845,7 +4845,7 @@ static int may_commit_transaction(struct btrfs_fs_info *fs_info, spin_unlock(&delayed_rsv->lock); commit: - trans = btrfs_join_transaction(fs_info->fs_root); + trans = btrfs_join_transaction(fs_info->extent_root); if (IS_ERR(trans)) return -ENOSPC; @@ -4863,7 +4863,7 @@ static int flush_space(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, u64 num_bytes, u64 orig_bytes, int state) { - struct btrfs_root *root = fs_info->fs_root; + struct btrfs_root *root = fs_info->extent_root; struct btrfs_trans_handle *trans; int nr; int ret = 0; @@ -5063,7 +5063,7 @@ static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info, int flush_state = FLUSH_DELAYED_ITEMS_NR; spin_lock(&space_info->lock); - to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info->fs_root, + to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info->extent_root, space_info); if (!to_reclaim) { spin_unlock(&space_info->lock); From 286b92f43c0d0ae2c29a61769b66219fe5ae6701 Mon Sep 17 00:00:00 2001 From: Su Yue Date: Wed, 24 May 2017 09:31:32 +0800 Subject: [PATCH 7/9] btrfs: tree-log.c: Wrong printk information about namelen In verify_dir_item, it wants to printk name_len of dir_item but printk data_len acutally. Fix it by calling btrfs_dir_name_len instead of btrfs_dir_data_len. Signed-off-by: Su Yue Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/dir-item.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index 60a750678a82..c24d615e3d7f 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -468,7 +468,7 @@ int verify_dir_item(struct btrfs_fs_info *fs_info, if (btrfs_dir_name_len(leaf, dir_item) > namelen) { btrfs_crit(fs_info, "invalid dir item name len: %u", - (unsigned)btrfs_dir_data_len(leaf, dir_item)); + (unsigned)btrfs_dir_name_len(leaf, dir_item)); return 1; } From 452e62b71fbbefe2646fad3a968371a026936c6d Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Fri, 26 May 2017 17:44:23 -0600 Subject: [PATCH 8/9] Btrfs: clear EXTENT_DEFRAG bits in finish_ordered_io Before this, we use 'filled' mode here, ie. if all range has been filled with EXTENT_DEFRAG bits, get to clear it, but if the defrag range joins the adjacent delalloc range, then we'll have EXTENT_DEFRAG bits in extent_state until releasing this inode's pages, and that prevents extent_data from being freed. This clears the bit if any was found within the ordered extent. Signed-off-by: Liu Bo Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 3fc3e10594a4..ef3c98c527c1 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -2952,7 +2952,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) ret = test_range_bit(io_tree, ordered_extent->file_offset, ordered_extent->file_offset + ordered_extent->len - 1, - EXTENT_DEFRAG, 1, cached_state); + EXTENT_DEFRAG, 0, cached_state); if (ret) { u64 last_snapshot = btrfs_root_last_snapshot(&root->root_item); if (0 && last_snapshot >= BTRFS_I(inode)->generation) From 70e7af244f24c94604ef6eca32ad297632018583 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Fri, 2 Jun 2017 01:20:01 -0700 Subject: [PATCH 9/9] Btrfs: fix delalloc accounting leak caused by u32 overflow btrfs_calc_trans_metadata_size() does an unsigned 32-bit multiplication, which can overflow if num_items >= 4 GB / (nodesize * BTRFS_MAX_LEVEL * 2). For a nodesize of 16kB, this overflow happens at 16k items. Usually, num_items is a small constant passed to btrfs_start_transaction(), but we also use btrfs_calc_trans_metadata_size() for metadata reservations for extent items in btrfs_delalloc_{reserve,release}_metadata(). In drop_outstanding_extents(), num_items is calculated as inode->reserved_extents - inode->outstanding_extents. The difference between these two counters is usually small, but if many delalloc extents are reserved and then the outstanding extents are merged in btrfs_merge_extent_hook(), the difference can become large enough to overflow in btrfs_calc_trans_metadata_size(). The overflow manifests itself as a leak of a multiple of 4 GB in delalloc_block_rsv and the metadata bytes_may_use counter. This in turn can cause early ENOSPC errors. Additionally, these WARN_ONs in extent-tree.c will be hit when unmounting: WARN_ON(fs_info->delalloc_block_rsv.size > 0); WARN_ON(fs_info->delalloc_block_rsv.reserved > 0); WARN_ON(space_info->bytes_pinned > 0 || space_info->bytes_reserved > 0 || space_info->bytes_may_use > 0); Fix it by casting nodesize to a u64 so that btrfs_calc_trans_metadata_size() does a full 64-bit multiplication. While we're here, do the same in btrfs_calc_trunc_metadata_size(); this can't overflow with any existing uses, but it's better to be safe here than have another hard-to-debug problem later on. Cc: stable@vger.kernel.org Signed-off-by: Omar Sandoval Reviewed-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/ctree.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 1e82516fe2d8..43a8c42cdf07 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2564,7 +2564,7 @@ u64 btrfs_csum_bytes_to_leaves(struct btrfs_fs_info *fs_info, u64 csum_bytes); static inline u64 btrfs_calc_trans_metadata_size(struct btrfs_fs_info *fs_info, unsigned num_items) { - return fs_info->nodesize * BTRFS_MAX_LEVEL * 2 * num_items; + return (u64)fs_info->nodesize * BTRFS_MAX_LEVEL * 2 * num_items; } /* @@ -2574,7 +2574,7 @@ static inline u64 btrfs_calc_trans_metadata_size(struct btrfs_fs_info *fs_info, static inline u64 btrfs_calc_trunc_metadata_size(struct btrfs_fs_info *fs_info, unsigned num_items) { - return fs_info->nodesize * BTRFS_MAX_LEVEL * num_items; + return (u64)fs_info->nodesize * BTRFS_MAX_LEVEL * num_items; } int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans,