* [PATCH 1/2] btrfs: move lockdep class helpers to locking.*
2022-07-26 20:24 [PATCH 0/2] Fix relocation lockdep splat Josef Bacik
@ 2022-07-26 20:24 ` Josef Bacik
2022-07-27 6:47 ` Johannes Thumshirn
2022-07-26 20:24 ` [PATCH 2/2] btrfs: fix lockdep splat with reloc root extent buffers Josef Bacik
2022-08-02 17:10 ` [PATCH 0/2] Fix relocation lockdep splat David Sterba
2 siblings, 1 reply; 5+ messages in thread
From: Josef Bacik @ 2022-07-26 20:24 UTC (permalink / raw)
To: linux-btrfs, kernel-team
These definitions exist in disk-io.c, which is not related to the
locking. Move this over to locking.h/c where it makes more sense.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
---
fs/btrfs/disk-io.c | 82 ----------------------------------------------
fs/btrfs/disk-io.h | 10 ------
fs/btrfs/locking.c | 82 ++++++++++++++++++++++++++++++++++++++++++++++
fs/btrfs/locking.h | 10 ++++++
4 files changed, 92 insertions(+), 92 deletions(-)
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 3fac429cf8a4..b0345aa16c01 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -86,88 +86,6 @@ struct async_submit_bio {
blk_status_t status;
};
-/*
- * Lockdep class keys for extent_buffer->lock's in this root. For a given
- * eb, the lockdep key is determined by the btrfs_root it belongs to and
- * the level the eb occupies in the tree.
- *
- * Different roots are used for different purposes and may nest inside each
- * other and they require separate keysets. As lockdep keys should be
- * static, assign keysets according to the purpose of the root as indicated
- * by btrfs_root->root_key.objectid. This ensures that all special purpose
- * roots have separate keysets.
- *
- * Lock-nesting across peer nodes is always done with the immediate parent
- * node locked thus preventing deadlock. As lockdep doesn't know this, use
- * subclass to avoid triggering lockdep warning in such cases.
- *
- * The key is set by the readpage_end_io_hook after the buffer has passed
- * csum validation but before the pages are unlocked. It is also set by
- * btrfs_init_new_buffer on freshly allocated blocks.
- *
- * We also add a check to make sure the highest level of the tree is the
- * same as our lockdep setup here. If BTRFS_MAX_LEVEL changes, this code
- * needs update as well.
- */
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# if BTRFS_MAX_LEVEL != 8
-# error
-# endif
-
-#define DEFINE_LEVEL(stem, level) \
- .names[level] = "btrfs-" stem "-0" #level,
-
-#define DEFINE_NAME(stem) \
- DEFINE_LEVEL(stem, 0) \
- DEFINE_LEVEL(stem, 1) \
- DEFINE_LEVEL(stem, 2) \
- DEFINE_LEVEL(stem, 3) \
- DEFINE_LEVEL(stem, 4) \
- DEFINE_LEVEL(stem, 5) \
- DEFINE_LEVEL(stem, 6) \
- DEFINE_LEVEL(stem, 7)
-
-static struct btrfs_lockdep_keyset {
- u64 id; /* root objectid */
- /* Longest entry: btrfs-free-space-00 */
- char names[BTRFS_MAX_LEVEL][20];
- struct lock_class_key keys[BTRFS_MAX_LEVEL];
-} btrfs_lockdep_keysets[] = {
- { .id = BTRFS_ROOT_TREE_OBJECTID, DEFINE_NAME("root") },
- { .id = BTRFS_EXTENT_TREE_OBJECTID, DEFINE_NAME("extent") },
- { .id = BTRFS_CHUNK_TREE_OBJECTID, DEFINE_NAME("chunk") },
- { .id = BTRFS_DEV_TREE_OBJECTID, DEFINE_NAME("dev") },
- { .id = BTRFS_CSUM_TREE_OBJECTID, DEFINE_NAME("csum") },
- { .id = BTRFS_QUOTA_TREE_OBJECTID, DEFINE_NAME("quota") },
- { .id = BTRFS_TREE_LOG_OBJECTID, DEFINE_NAME("log") },
- { .id = BTRFS_TREE_RELOC_OBJECTID, DEFINE_NAME("treloc") },
- { .id = BTRFS_DATA_RELOC_TREE_OBJECTID, DEFINE_NAME("dreloc") },
- { .id = BTRFS_UUID_TREE_OBJECTID, DEFINE_NAME("uuid") },
- { .id = BTRFS_FREE_SPACE_TREE_OBJECTID, DEFINE_NAME("free-space") },
- { .id = 0, DEFINE_NAME("tree") },
-};
-
-#undef DEFINE_LEVEL
-#undef DEFINE_NAME
-
-void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb,
- int level)
-{
- struct btrfs_lockdep_keyset *ks;
-
- BUG_ON(level >= ARRAY_SIZE(ks->keys));
-
- /* find the matching keyset, id 0 is the default entry */
- for (ks = btrfs_lockdep_keysets; ks->id; ks++)
- if (ks->id == objectid)
- break;
-
- lockdep_set_class_and_name(&eb->lock,
- &ks->keys[level], ks->names[level]);
-}
-
-#endif
-
/*
* Compute the csum of a btree block and store the result to provided buffer.
*/
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index 8993b428e09c..47ad8e0a2d33 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -137,14 +137,4 @@ int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags);
int btrfs_get_free_objectid(struct btrfs_root *root, u64 *objectid);
int btrfs_init_root_free_objectid(struct btrfs_root *root);
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-void btrfs_set_buffer_lockdep_class(u64 objectid,
- struct extent_buffer *eb, int level);
-#else
-static inline void btrfs_set_buffer_lockdep_class(u64 objectid,
- struct extent_buffer *eb, int level)
-{
-}
-#endif
-
#endif
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index 33461b4f9c8b..a4b671c5e678 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -13,6 +13,88 @@
#include "extent_io.h"
#include "locking.h"
+/*
+ * Lockdep class keys for extent_buffer->lock's in this root. For a given
+ * eb, the lockdep key is determined by the btrfs_root it belongs to and
+ * the level the eb occupies in the tree.
+ *
+ * Different roots are used for different purposes and may nest inside each
+ * other and they require separate keysets. As lockdep keys should be
+ * static, assign keysets according to the purpose of the root as indicated
+ * by btrfs_root->root_key.objectid. This ensures that all special purpose
+ * roots have separate keysets.
+ *
+ * Lock-nesting across peer nodes is always done with the immediate parent
+ * node locked thus preventing deadlock. As lockdep doesn't know this, use
+ * subclass to avoid triggering lockdep warning in such cases.
+ *
+ * The key is set by the readpage_end_io_hook after the buffer has passed
+ * csum validation but before the pages are unlocked. It is also set by
+ * btrfs_init_new_buffer on freshly allocated blocks.
+ *
+ * We also add a check to make sure the highest level of the tree is the
+ * same as our lockdep setup here. If BTRFS_MAX_LEVEL changes, this code
+ * needs update as well.
+ */
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# if BTRFS_MAX_LEVEL != 8
+# error
+# endif
+
+#define DEFINE_LEVEL(stem, level) \
+ .names[level] = "btrfs-" stem "-0" #level,
+
+#define DEFINE_NAME(stem) \
+ DEFINE_LEVEL(stem, 0) \
+ DEFINE_LEVEL(stem, 1) \
+ DEFINE_LEVEL(stem, 2) \
+ DEFINE_LEVEL(stem, 3) \
+ DEFINE_LEVEL(stem, 4) \
+ DEFINE_LEVEL(stem, 5) \
+ DEFINE_LEVEL(stem, 6) \
+ DEFINE_LEVEL(stem, 7)
+
+static struct btrfs_lockdep_keyset {
+ u64 id; /* root objectid */
+ /* Longest entry: btrfs-free-space-00 */
+ char names[BTRFS_MAX_LEVEL][20];
+ struct lock_class_key keys[BTRFS_MAX_LEVEL];
+} btrfs_lockdep_keysets[] = {
+ { .id = BTRFS_ROOT_TREE_OBJECTID, DEFINE_NAME("root") },
+ { .id = BTRFS_EXTENT_TREE_OBJECTID, DEFINE_NAME("extent") },
+ { .id = BTRFS_CHUNK_TREE_OBJECTID, DEFINE_NAME("chunk") },
+ { .id = BTRFS_DEV_TREE_OBJECTID, DEFINE_NAME("dev") },
+ { .id = BTRFS_CSUM_TREE_OBJECTID, DEFINE_NAME("csum") },
+ { .id = BTRFS_QUOTA_TREE_OBJECTID, DEFINE_NAME("quota") },
+ { .id = BTRFS_TREE_LOG_OBJECTID, DEFINE_NAME("log") },
+ { .id = BTRFS_TREE_RELOC_OBJECTID, DEFINE_NAME("treloc") },
+ { .id = BTRFS_DATA_RELOC_TREE_OBJECTID, DEFINE_NAME("dreloc") },
+ { .id = BTRFS_UUID_TREE_OBJECTID, DEFINE_NAME("uuid") },
+ { .id = BTRFS_FREE_SPACE_TREE_OBJECTID, DEFINE_NAME("free-space") },
+ { .id = 0, DEFINE_NAME("tree") },
+};
+
+#undef DEFINE_LEVEL
+#undef DEFINE_NAME
+
+void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb,
+ int level)
+{
+ struct btrfs_lockdep_keyset *ks;
+
+ BUG_ON(level >= ARRAY_SIZE(ks->keys));
+
+ /* find the matching keyset, id 0 is the default entry */
+ for (ks = btrfs_lockdep_keysets; ks->id; ks++)
+ if (ks->id == objectid)
+ break;
+
+ lockdep_set_class_and_name(&eb->lock,
+ &ks->keys[level], ks->names[level]);
+}
+
+#endif
+
/*
* Extent buffer locking
* =====================
diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h
index bbc45534ae9a..394264bdac3d 100644
--- a/fs/btrfs/locking.h
+++ b/fs/btrfs/locking.h
@@ -131,4 +131,14 @@ void btrfs_drew_write_unlock(struct btrfs_drew_lock *lock);
void btrfs_drew_read_lock(struct btrfs_drew_lock *lock);
void btrfs_drew_read_unlock(struct btrfs_drew_lock *lock);
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+void btrfs_set_buffer_lockdep_class(u64 objectid,
+ struct extent_buffer *eb, int level);
+#else
+static inline void btrfs_set_buffer_lockdep_class(u64 objectid,
+ struct extent_buffer *eb, int level)
+{
+}
+#endif
+
#endif
--
2.26.3
^ permalink raw reply related [flat|nested] 5+ messages in thread* [PATCH 2/2] btrfs: fix lockdep splat with reloc root extent buffers
2022-07-26 20:24 [PATCH 0/2] Fix relocation lockdep splat Josef Bacik
2022-07-26 20:24 ` [PATCH 1/2] btrfs: move lockdep class helpers to locking.* Josef Bacik
@ 2022-07-26 20:24 ` Josef Bacik
2022-08-02 17:10 ` [PATCH 0/2] Fix relocation lockdep splat David Sterba
2 siblings, 0 replies; 5+ messages in thread
From: Josef Bacik @ 2022-07-26 20:24 UTC (permalink / raw)
To: linux-btrfs, kernel-team
We have been hitting the following lockdep splat with btrfs/187 recently
======================================================
WARNING: possible circular locking dependency detected
5.19.0-rc8+ #775 Not tainted
------------------------------------------------------
btrfs/752500 is trying to acquire lock:
ffff97e1875a97b8 (btrfs-treloc-02#2){+.+.}-{3:3}, at: __btrfs_tree_lock+0x24/0x110
but task is already holding lock:
ffff97e1875a9278 (btrfs-tree-01/1){+.+.}-{3:3}, at: __btrfs_tree_lock+0x24/0x110
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #2 (btrfs-tree-01/1){+.+.}-{3:3}:
down_write_nested+0x41/0x80
__btrfs_tree_lock+0x24/0x110
btrfs_init_new_buffer+0x7d/0x2c0
btrfs_alloc_tree_block+0x120/0x3b0
__btrfs_cow_block+0x136/0x600
btrfs_cow_block+0x10b/0x230
btrfs_search_slot+0x53b/0xb70
btrfs_lookup_inode+0x2a/0xa0
__btrfs_update_delayed_inode+0x5f/0x280
btrfs_async_run_delayed_root+0x24c/0x290
btrfs_work_helper+0xf2/0x3e0
process_one_work+0x271/0x590
worker_thread+0x52/0x3b0
kthread+0xf0/0x120
ret_from_fork+0x1f/0x30
-> #1 (btrfs-tree-01){++++}-{3:3}:
down_write_nested+0x41/0x80
__btrfs_tree_lock+0x24/0x110
btrfs_search_slot+0x3c3/0xb70
do_relocation+0x10c/0x6b0
relocate_tree_blocks+0x317/0x6d0
relocate_block_group+0x1f1/0x560
btrfs_relocate_block_group+0x23e/0x400
btrfs_relocate_chunk+0x4c/0x140
btrfs_balance+0x755/0xe40
btrfs_ioctl+0x1ea2/0x2c90
__x64_sys_ioctl+0x88/0xc0
do_syscall_64+0x38/0x90
entry_SYSCALL_64_after_hwframe+0x63/0xcd
-> #0 (btrfs-treloc-02#2){+.+.}-{3:3}:
__lock_acquire+0x1122/0x1e10
lock_acquire+0xc2/0x2d0
down_write_nested+0x41/0x80
__btrfs_tree_lock+0x24/0x110
btrfs_lock_root_node+0x31/0x50
btrfs_search_slot+0x1cb/0xb70
replace_path+0x541/0x9f0
merge_reloc_root+0x1d6/0x610
merge_reloc_roots+0xe2/0x260
relocate_block_group+0x2c8/0x560
btrfs_relocate_block_group+0x23e/0x400
btrfs_relocate_chunk+0x4c/0x140
btrfs_balance+0x755/0xe40
btrfs_ioctl+0x1ea2/0x2c90
__x64_sys_ioctl+0x88/0xc0
do_syscall_64+0x38/0x90
entry_SYSCALL_64_after_hwframe+0x63/0xcd
other info that might help us debug this:
Chain exists of:
btrfs-treloc-02#2 --> btrfs-tree-01 --> btrfs-tree-01/1
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(btrfs-tree-01/1);
lock(btrfs-tree-01);
lock(btrfs-tree-01/1);
lock(btrfs-treloc-02#2);
*** DEADLOCK ***
7 locks held by btrfs/752500:
#0: ffff97e292fdf460 (sb_writers#12){.+.+}-{0:0}, at: btrfs_ioctl+0x208/0x2c90
#1: ffff97e284c02050 (&fs_info->reclaim_bgs_lock){+.+.}-{3:3}, at: btrfs_balance+0x55f/0xe40
#2: ffff97e284c00878 (&fs_info->cleaner_mutex){+.+.}-{3:3}, at: btrfs_relocate_block_group+0x236/0x400
#3: ffff97e292fdf650 (sb_internal#2){.+.+}-{0:0}, at: merge_reloc_root+0xef/0x610
#4: ffff97e284c02378 (btrfs_trans_num_writers){++++}-{0:0}, at: join_transaction+0x1a8/0x5a0
#5: ffff97e284c023a0 (btrfs_trans_num_extwriters){++++}-{0:0}, at: join_transaction+0x1a8/0x5a0
#6: ffff97e1875a9278 (btrfs-tree-01/1){+.+.}-{3:3}, at: __btrfs_tree_lock+0x24/0x110
stack backtrace:
CPU: 1 PID: 752500 Comm: btrfs Not tainted 5.19.0-rc8+ #775
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-2.fc32 04/01/2014
Call Trace:
dump_stack_lvl+0x56/0x73
check_noncircular+0xd6/0x100
? lock_is_held_type+0xe2/0x140
__lock_acquire+0x1122/0x1e10
lock_acquire+0xc2/0x2d0
? __btrfs_tree_lock+0x24/0x110
down_write_nested+0x41/0x80
? __btrfs_tree_lock+0x24/0x110
__btrfs_tree_lock+0x24/0x110
btrfs_lock_root_node+0x31/0x50
btrfs_search_slot+0x1cb/0xb70
? lock_release+0x137/0x2d0
? _raw_spin_unlock+0x29/0x50
? release_extent_buffer+0x128/0x180
replace_path+0x541/0x9f0
merge_reloc_root+0x1d6/0x610
merge_reloc_roots+0xe2/0x260
relocate_block_group+0x2c8/0x560
btrfs_relocate_block_group+0x23e/0x400
btrfs_relocate_chunk+0x4c/0x140
btrfs_balance+0x755/0xe40
btrfs_ioctl+0x1ea2/0x2c90
? lock_is_held_type+0xe2/0x140
? lock_is_held_type+0xe2/0x140
? __x64_sys_ioctl+0x88/0xc0
__x64_sys_ioctl+0x88/0xc0
do_syscall_64+0x38/0x90
entry_SYSCALL_64_after_hwframe+0x63/0xcd
This isn't necessarily new, it's just tricky to hit in practice. There
are two competing things going on here. With relocation we create a
snapshot of every fs tree with a reloc tree. Any extent buffers that
get initialized here are initialized with the reloc root lockdep key.
However since it is a snapshot, any blocks that are currently in cache
that originally belonged to the fs tree will have the normal tree
lockdep key set. This creates the lock dependency of
reloc tree -> normal tree
for the extent buffer locking during the first phase of the relocation
as we walk down the reloc root to relocate blocks.
However this is problematic because the final phase of the relocation is
merging the reloc root into the original fs root. This involves
searching down to any keys that exist in the original fs root and then
swapping the relocated block and the original fs root block. We have to
search down to the fs root first, and then go search the reloc root for
the block we need to replace. This creates the dependency of
normal tree -> reloc tree
which is why lockdep complains.
Additionally even if we were to fix this particular mismatch with a
different nesting for the merge case, we're still slotting in a block
that has a owner of the reloc root objectid into a normal tree, so that
block will have its lockdep key set to the tree reloc root, and create a
lockdep splat later on when we wander into that block from the fs root.
Unfortunately the only solution here is to make sure we do not set the
lockdep key to the reloc tree lockdep key normally, and then reset any
blocks we wander into from the reloc root when we're doing the merged.
This solves the problem of having mixed tree reloc keys intermixed with
normal tree keys, and then allows us to make sure in the merge case we
maintain the lock order of
normal tree -> reloc tree
We handle this by setting a bit on the reloc root when we do the search
for the block we want to relocate, and any block we search into or cow
at that point gets set to the reloc tree key. This works correctly
because we only ever cow down to the parent node, so we aren't resetting
the key for the block we're linking into the fs root.
With this patch we no longer have the lockdep splat in btrfs/187.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
---
fs/btrfs/ctree.c | 3 +++
fs/btrfs/ctree.h | 2 ++
fs/btrfs/extent-tree.c | 18 +++++++++++++++++-
fs/btrfs/extent_io.c | 11 ++++++++++-
fs/btrfs/locking.c | 13 +++++++++++++
fs/btrfs/locking.h | 6 ++++++
fs/btrfs/relocation.c | 2 ++
7 files changed, 53 insertions(+), 2 deletions(-)
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 6e556031a8f3..ebfa35fe1c38 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -2075,6 +2075,9 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
if (!p->skip_locking) {
level = btrfs_header_level(b);
+
+ btrfs_maybe_reset_lockdep_class(root, b);
+
if (level <= write_lock_level) {
btrfs_tree_lock(b);
p->locks[level] = BTRFS_WRITE_LOCK;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 4db85b9dc7ed..89942284cb8e 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1173,6 +1173,8 @@ enum {
BTRFS_ROOT_ORPHAN_CLEANUP,
/* This root has a drop operation that was started previously. */
BTRFS_ROOT_UNFINISHED_DROP,
+ /* This reloc root needs to have it's buffers lockdep class reset. */
+ BTRFS_ROOT_RESET_LOCKDEP_CLASS,
};
static inline void btrfs_wake_unfinished_drop(struct btrfs_fs_info *fs_info)
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index ea3ec1e761e8..ab944d1f94ef 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4867,6 +4867,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
{
struct btrfs_fs_info *fs_info = root->fs_info;
struct extent_buffer *buf;
+ u64 lockdep_owner = owner;
buf = btrfs_find_create_tree_block(fs_info, bytenr, owner, level);
if (IS_ERR(buf))
@@ -4885,12 +4886,27 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
return ERR_PTR(-EUCLEAN);
}
+ /*
+ * The reloc trees are just snapshots, so we need them to appear to be
+ * just like any other fs tree WRT lockdep.
+ *
+ * The exception however is in replace_path() in relocation, where we
+ * hold the lock on the original fs root and then search for the reloc
+ * root. At that point we need to make sure any reloc root buffers are
+ * set to the BTRFS_TREE_RELOC_OBJECTID lockdep class in order to make
+ * lockdep happy.
+ */
+ if (lockdep_owner == BTRFS_TREE_RELOC_OBJECTID &&
+ !test_bit(BTRFS_ROOT_RESET_LOCKDEP_CLASS, &root->state))
+ lockdep_owner = BTRFS_FS_TREE_OBJECTID;
+
/*
* This needs to stay, because we could allocate a freed block from an
* old tree into a new tree, so we need to make sure this new block is
* set to the appropriate level and owner.
*/
- btrfs_set_buffer_lockdep_class(owner, buf, level);
+ btrfs_set_buffer_lockdep_class(lockdep_owner, buf, level);
+
__btrfs_tree_lock(buf, nest);
btrfs_clean_tree_block(buf);
clear_bit(EXTENT_BUFFER_STALE, &buf->bflags);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index b290bd1b38b0..6e8e936a8a1e 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -6140,6 +6140,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
struct extent_buffer *exists = NULL;
struct page *p;
struct address_space *mapping = fs_info->btree_inode->i_mapping;
+ u64 lockdep_owner = owner_root;
int uptodate = 1;
int ret;
@@ -6164,7 +6165,15 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
eb = __alloc_extent_buffer(fs_info, start, len);
if (!eb)
return ERR_PTR(-ENOMEM);
- btrfs_set_buffer_lockdep_class(owner_root, eb, level);
+
+ /*
+ * The reloc trees are just snapshots, so we need them to appear to be
+ * just like any other fs tree WRT lockdep.
+ */
+ if (lockdep_owner == BTRFS_TREE_RELOC_OBJECTID)
+ lockdep_owner = BTRFS_FS_TREE_OBJECTID;
+
+ btrfs_set_buffer_lockdep_class(lockdep_owner, eb, level);
num_pages = num_extent_pages(eb);
for (i = 0; i < num_pages; i++, index++) {
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index a4b671c5e678..b80f4e07f331 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -93,6 +93,14 @@ void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb,
&ks->keys[level], ks->names[level]);
}
+void btrfs_maybe_reset_lockdep_class(struct btrfs_root *root,
+ struct extent_buffer *eb)
+{
+ if (unlikely(test_bit(BTRFS_ROOT_RESET_LOCKDEP_CLASS, &root->state)))
+ btrfs_set_buffer_lockdep_class(root->root_key.objectid,
+ eb, btrfs_header_level(eb));
+}
+
#endif
/*
@@ -246,6 +254,9 @@ struct extent_buffer *btrfs_lock_root_node(struct btrfs_root *root)
while (1) {
eb = btrfs_root_node(root);
+
+ btrfs_maybe_reset_lockdep_class(root, eb);
+
btrfs_tree_lock(eb);
if (eb == root->node)
break;
@@ -267,6 +278,8 @@ struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root)
while (1) {
eb = btrfs_root_node(root);
+
+ btrfs_maybe_reset_lockdep_class(root, eb);
btrfs_tree_read_lock(eb);
if (eb == root->node)
break;
diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h
index 394264bdac3d..42f3f17baee3 100644
--- a/fs/btrfs/locking.h
+++ b/fs/btrfs/locking.h
@@ -134,11 +134,17 @@ void btrfs_drew_read_unlock(struct btrfs_drew_lock *lock);
#ifdef CONFIG_DEBUG_LOCK_ALLOC
void btrfs_set_buffer_lockdep_class(u64 objectid,
struct extent_buffer *eb, int level);
+void btrfs_maybe_reset_lockdep_class(struct btrfs_root *root,
+ struct extent_buffer *eb);
#else
static inline void btrfs_set_buffer_lockdep_class(u64 objectid,
struct extent_buffer *eb, int level)
{
}
+static inline void btrfs_maybe_reset_lockdep_class(struct btrfs_root *root,
+ struct extent_buffer *eb)
+{
+}
#endif
#endif
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index a6dc827e75af..6f8c3b23b673 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -1326,7 +1326,9 @@ int replace_path(struct btrfs_trans_handle *trans, struct reloc_control *rc,
btrfs_release_path(path);
path->lowest_level = level;
+ set_bit(BTRFS_ROOT_RESET_LOCKDEP_CLASS, &src->state);
ret = btrfs_search_slot(trans, src, &key, path, 0, 1);
+ clear_bit(BTRFS_ROOT_RESET_LOCKDEP_CLASS, &src->state);
path->lowest_level = 0;
if (ret) {
if (ret > 0)
--
2.26.3
^ permalink raw reply related [flat|nested] 5+ messages in thread* Re: [PATCH 0/2] Fix relocation lockdep splat
2022-07-26 20:24 [PATCH 0/2] Fix relocation lockdep splat Josef Bacik
2022-07-26 20:24 ` [PATCH 1/2] btrfs: move lockdep class helpers to locking.* Josef Bacik
2022-07-26 20:24 ` [PATCH 2/2] btrfs: fix lockdep splat with reloc root extent buffers Josef Bacik
@ 2022-08-02 17:10 ` David Sterba
2 siblings, 0 replies; 5+ messages in thread
From: David Sterba @ 2022-08-02 17:10 UTC (permalink / raw)
To: Josef Bacik; +Cc: linux-btrfs, kernel-team
On Tue, Jul 26, 2022 at 04:24:02PM -0400, Josef Bacik wrote:
> Hello,
>
> This fixes the long standing lockdep splat we were getting in btrfs/187. The
> detailed description of the fix can be found in the changelog in the second
> patch. The first patch simply moves the lockdep related code into locking.c
> where it more logically fits in. Thanks,
Added to misc-next, thanks.
^ permalink raw reply [flat|nested] 5+ messages in thread