linux/fs/btrfs/backref.h

382 lines
10 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (C) 2011 STRATO. All rights reserved.
*/
#ifndef BTRFS_BACKREF_H
#define BTRFS_BACKREF_H
#include <linux/btrfs.h>
#include "ulist.h"
#include "disk-io.h"
#include "extent_io.h"
struct inode_fs_paths {
struct btrfs_path *btrfs_path;
struct btrfs_root *fs_root;
struct btrfs_data_container *fspath;
};
typedef int (iterate_extent_inodes_t)(u64 inum, u64 offset, u64 root,
void *ctx);
int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical,
struct btrfs_path *path, struct btrfs_key *found_key,
u64 *flags);
int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb,
struct btrfs_key *key, struct btrfs_extent_item *ei,
u32 item_size, u64 *out_root, u8 *out_level);
int iterate_extent_inodes(struct btrfs_fs_info *fs_info,
u64 extent_item_objectid,
u64 extent_offset, int search_commit_root,
btrfs: add a flag to iterate_inodes_from_logical to find all extent refs for uncompressed extents The LOGICAL_INO ioctl provides a backward mapping from extent bytenr and offset (encoded as a single logical address) to a list of extent refs. LOGICAL_INO complements TREE_SEARCH, which provides the forward mapping (extent ref -> extent bytenr and offset, or logical address). These are useful capabilities for programs that manipulate extents and extent references from userspace (e.g. dedup and defrag utilities). When the extents are uncompressed (and not encrypted and not other), check_extent_in_eb performs filtering of the extent refs to remove any extent refs which do not contain the same extent offset as the 'logical' parameter's extent offset. This prevents LOGICAL_INO from returning references to more than a single block. To find the set of extent references to an uncompressed extent from [a, b), userspace has to run a loop like this pseudocode: for (i = a; i < b; ++i) extent_ref_set += LOGICAL_INO(i); At each iteration of the loop (up to 32768 iterations for a 128M extent), data we are interested in is collected in the kernel, then deleted by the filter in check_extent_in_eb. When the extents are compressed (or encrypted or other), the 'logical' parameter must be an extent bytenr (the 'a' parameter in the loop). No filtering by extent offset is done (or possible?) so the result is the complete set of extent refs for the entire extent. This removes the need for the loop, since we get all the extent refs in one call. Add an 'ignore_offset' argument to iterate_inodes_from_logical, [...several levels of function call graph...], and check_extent_in_eb, so that we can disable the extent offset filtering for uncompressed extents. This flag can be set by an improved version of the LOGICAL_INO ioctl to get either behavior as desired. There is no functional change in this patch. The new flag is always false. Signed-off-by: Zygo Blaxell <ce3g8jdj@umail.furryterror.org> Reviewed-by: David Sterba <dsterba@suse.com> [ minor coding style fixes ] Signed-off-by: David Sterba <dsterba@suse.com>
2017-09-23 01:58:45 +08:00
iterate_extent_inodes_t *iterate, void *ctx,
bool ignore_offset);
int iterate_inodes_from_logical(u64 logical, struct btrfs_fs_info *fs_info,
struct btrfs_path *path, void *ctx,
btrfs: add a flag to iterate_inodes_from_logical to find all extent refs for uncompressed extents The LOGICAL_INO ioctl provides a backward mapping from extent bytenr and offset (encoded as a single logical address) to a list of extent refs. LOGICAL_INO complements TREE_SEARCH, which provides the forward mapping (extent ref -> extent bytenr and offset, or logical address). These are useful capabilities for programs that manipulate extents and extent references from userspace (e.g. dedup and defrag utilities). When the extents are uncompressed (and not encrypted and not other), check_extent_in_eb performs filtering of the extent refs to remove any extent refs which do not contain the same extent offset as the 'logical' parameter's extent offset. This prevents LOGICAL_INO from returning references to more than a single block. To find the set of extent references to an uncompressed extent from [a, b), userspace has to run a loop like this pseudocode: for (i = a; i < b; ++i) extent_ref_set += LOGICAL_INO(i); At each iteration of the loop (up to 32768 iterations for a 128M extent), data we are interested in is collected in the kernel, then deleted by the filter in check_extent_in_eb. When the extents are compressed (or encrypted or other), the 'logical' parameter must be an extent bytenr (the 'a' parameter in the loop). No filtering by extent offset is done (or possible?) so the result is the complete set of extent refs for the entire extent. This removes the need for the loop, since we get all the extent refs in one call. Add an 'ignore_offset' argument to iterate_inodes_from_logical, [...several levels of function call graph...], and check_extent_in_eb, so that we can disable the extent offset filtering for uncompressed extents. This flag can be set by an improved version of the LOGICAL_INO ioctl to get either behavior as desired. There is no functional change in this patch. The new flag is always false. Signed-off-by: Zygo Blaxell <ce3g8jdj@umail.furryterror.org> Reviewed-by: David Sterba <dsterba@suse.com> [ minor coding style fixes ] Signed-off-by: David Sterba <dsterba@suse.com>
2017-09-23 01:58:45 +08:00
bool ignore_offset);
int paths_from_inode(u64 inum, struct inode_fs_paths *ipath);
int btrfs_find_all_leafs(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info, u64 bytenr,
u64 time_seq, struct ulist **leafs,
const u64 *extent_item_pos, bool ignore_offset);
int btrfs_find_all_roots(struct btrfs_trans_handle *trans,
Btrfs: rework qgroup accounting Currently qgroups account for space by intercepting delayed ref updates to fs trees. It does this by adding sequence numbers to delayed ref updates so that it can figure out how the tree looked before the update so we can adjust the counters properly. The problem with this is that it does not allow delayed refs to be merged, so if you say are defragging an extent with 5k snapshots pointing to it we will thrash the delayed ref lock because we need to go back and manually merge these things together. Instead we want to process quota changes when we know they are going to happen, like when we first allocate an extent, we free a reference for an extent, we add new references etc. This patch accomplishes this by only adding qgroup operations for real ref changes. We only modify the sequence number when we need to lookup roots for bytenrs, this reduces the amount of churn on the sequence number and allows us to merge delayed refs as we add them most of the time. This patch encompasses a bunch of architectural changes 1) qgroup ref operations: instead of tracking qgroup operations through the delayed refs we simply add new ref operations whenever we notice that we need to when we've modified the refs themselves. 2) tree mod seq: we no longer have this separation of major/minor counters. this makes the sequence number stuff much more sane and we can remove some locking that was needed to protect the counter. 3) delayed ref seq: we now read the tree mod seq number and use that as our sequence. This means each new delayed ref doesn't have it's own unique sequence number, rather whenever we go to lookup backrefs we inc the sequence number so we can make sure to keep any new operations from screwing up our world view at that given point. This allows us to merge delayed refs during runtime. With all of these changes the delayed ref stuff is a little saner and the qgroup accounting stuff no longer goes negative in some cases like it was before. Thanks, Signed-off-by: Josef Bacik <jbacik@fb.com> Signed-off-by: Chris Mason <clm@fb.com>
2014-05-14 08:30:47 +08:00
struct btrfs_fs_info *fs_info, u64 bytenr,
u64 time_seq, struct ulist **roots,
btrfs: fix lock inversion problem when doing qgroup extent tracing At btrfs_qgroup_trace_extent_post() we call btrfs_find_all_roots() with a NULL value as the transaction handle argument, which makes that function take the commit_root_sem semaphore, which is necessary when we don't hold a transaction handle or any other mechanism to prevent a transaction commit from wiping out commit roots. However btrfs_qgroup_trace_extent_post() can be called in a context where we are holding a write lock on an extent buffer from a subvolume tree, namely from btrfs_truncate_inode_items(), called either during truncate or unlink operations. In this case we end up with a lock inversion problem because the commit_root_sem is a higher level lock, always supposed to be acquired before locking any extent buffer. Lockdep detects this lock inversion problem since we switched the extent buffer locks from custom locks to semaphores, and when running btrfs/158 from fstests, it reported the following trace: [ 9057.626435] ====================================================== [ 9057.627541] WARNING: possible circular locking dependency detected [ 9057.628334] 5.14.0-rc2-btrfs-next-93 #1 Not tainted [ 9057.628961] ------------------------------------------------------ [ 9057.629867] kworker/u16:4/30781 is trying to acquire lock: [ 9057.630824] ffff8e2590f58760 (btrfs-tree-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x24/0x110 [btrfs] [ 9057.632542] but task is already holding lock: [ 9057.633551] ffff8e25582d4b70 (&fs_info->commit_root_sem){++++}-{3:3}, at: iterate_extent_inodes+0x10b/0x280 [btrfs] [ 9057.635255] which lock already depends on the new lock. [ 9057.636292] the existing dependency chain (in reverse order) is: [ 9057.637240] -> #1 (&fs_info->commit_root_sem){++++}-{3:3}: [ 9057.638138] down_read+0x46/0x140 [ 9057.638648] btrfs_find_all_roots+0x41/0x80 [btrfs] [ 9057.639398] btrfs_qgroup_trace_extent_post+0x37/0x70 [btrfs] [ 9057.640283] btrfs_add_delayed_data_ref+0x418/0x490 [btrfs] [ 9057.641114] btrfs_free_extent+0x35/0xb0 [btrfs] [ 9057.641819] btrfs_truncate_inode_items+0x424/0xf70 [btrfs] [ 9057.642643] btrfs_evict_inode+0x454/0x4f0 [btrfs] [ 9057.643418] evict+0xcf/0x1d0 [ 9057.643895] do_unlinkat+0x1e9/0x300 [ 9057.644525] do_syscall_64+0x3b/0xc0 [ 9057.645110] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 9057.645835] -> #0 (btrfs-tree-00){++++}-{3:3}: [ 9057.646600] __lock_acquire+0x130e/0x2210 [ 9057.647248] lock_acquire+0xd7/0x310 [ 9057.647773] down_read_nested+0x4b/0x140 [ 9057.648350] __btrfs_tree_read_lock+0x24/0x110 [btrfs] [ 9057.649175] btrfs_read_lock_root_node+0x31/0x40 [btrfs] [ 9057.650010] btrfs_search_slot+0x537/0xc00 [btrfs] [ 9057.650849] scrub_print_warning_inode+0x89/0x370 [btrfs] [ 9057.651733] iterate_extent_inodes+0x1e3/0x280 [btrfs] [ 9057.652501] scrub_print_warning+0x15d/0x2f0 [btrfs] [ 9057.653264] scrub_handle_errored_block.isra.0+0x135f/0x1640 [btrfs] [ 9057.654295] scrub_bio_end_io_worker+0x101/0x2e0 [btrfs] [ 9057.655111] btrfs_work_helper+0xf8/0x400 [btrfs] [ 9057.655831] process_one_work+0x247/0x5a0 [ 9057.656425] worker_thread+0x55/0x3c0 [ 9057.656993] kthread+0x155/0x180 [ 9057.657494] ret_from_fork+0x22/0x30 [ 9057.658030] other info that might help us debug this: [ 9057.659064] Possible unsafe locking scenario: [ 9057.659824] CPU0 CPU1 [ 9057.660402] ---- ---- [ 9057.660988] lock(&fs_info->commit_root_sem); [ 9057.661581] lock(btrfs-tree-00); [ 9057.662348] lock(&fs_info->commit_root_sem); [ 9057.663254] lock(btrfs-tree-00); [ 9057.663690] *** DEADLOCK *** [ 9057.664437] 4 locks held by kworker/u16:4/30781: [ 9057.665023] #0: ffff8e25922a1148 ((wq_completion)btrfs-scrub){+.+.}-{0:0}, at: process_one_work+0x1c7/0x5a0 [ 9057.666260] #1: ffffabb3451ffe70 ((work_completion)(&work->normal_work)){+.+.}-{0:0}, at: process_one_work+0x1c7/0x5a0 [ 9057.667639] #2: ffff8e25922da198 (&ret->mutex){+.+.}-{3:3}, at: scrub_handle_errored_block.isra.0+0x5d2/0x1640 [btrfs] [ 9057.669017] #3: ffff8e25582d4b70 (&fs_info->commit_root_sem){++++}-{3:3}, at: iterate_extent_inodes+0x10b/0x280 [btrfs] [ 9057.670408] stack backtrace: [ 9057.670976] CPU: 7 PID: 30781 Comm: kworker/u16:4 Not tainted 5.14.0-rc2-btrfs-next-93 #1 [ 9057.672030] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 [ 9057.673492] Workqueue: btrfs-scrub btrfs_work_helper [btrfs] [ 9057.674258] Call Trace: [ 9057.674588] dump_stack_lvl+0x57/0x72 [ 9057.675083] check_noncircular+0xf3/0x110 [ 9057.675611] __lock_acquire+0x130e/0x2210 [ 9057.676132] lock_acquire+0xd7/0x310 [ 9057.676605] ? __btrfs_tree_read_lock+0x24/0x110 [btrfs] [ 9057.677313] ? lock_is_held_type+0xe8/0x140 [ 9057.677849] down_read_nested+0x4b/0x140 [ 9057.678349] ? __btrfs_tree_read_lock+0x24/0x110 [btrfs] [ 9057.679068] __btrfs_tree_read_lock+0x24/0x110 [btrfs] [ 9057.679760] btrfs_read_lock_root_node+0x31/0x40 [btrfs] [ 9057.680458] btrfs_search_slot+0x537/0xc00 [btrfs] [ 9057.681083] ? _raw_spin_unlock+0x29/0x40 [ 9057.681594] ? btrfs_find_all_roots_safe+0x11f/0x140 [btrfs] [ 9057.682336] scrub_print_warning_inode+0x89/0x370 [btrfs] [ 9057.683058] ? btrfs_find_all_roots_safe+0x11f/0x140 [btrfs] [ 9057.683834] ? scrub_write_block_to_dev_replace+0xb0/0xb0 [btrfs] [ 9057.684632] iterate_extent_inodes+0x1e3/0x280 [btrfs] [ 9057.685316] scrub_print_warning+0x15d/0x2f0 [btrfs] [ 9057.685977] ? ___ratelimit+0xa4/0x110 [ 9057.686460] scrub_handle_errored_block.isra.0+0x135f/0x1640 [btrfs] [ 9057.687316] scrub_bio_end_io_worker+0x101/0x2e0 [btrfs] [ 9057.688021] btrfs_work_helper+0xf8/0x400 [btrfs] [ 9057.688649] ? lock_is_held_type+0xe8/0x140 [ 9057.689180] process_one_work+0x247/0x5a0 [ 9057.689696] worker_thread+0x55/0x3c0 [ 9057.690175] ? process_one_work+0x5a0/0x5a0 [ 9057.690731] kthread+0x155/0x180 [ 9057.691158] ? set_kthread_struct+0x40/0x40 [ 9057.691697] ret_from_fork+0x22/0x30 Fix this by making btrfs_find_all_roots() never attempt to lock the commit_root_sem when it is called from btrfs_qgroup_trace_extent_post(). We can't just pass a non-NULL transaction handle to btrfs_find_all_roots() from btrfs_qgroup_trace_extent_post(), because that would make backref lookup not use commit roots and acquire read locks on extent buffers, and therefore could deadlock when btrfs_qgroup_trace_extent_post() is called from the btrfs_truncate_inode_items() code path which has acquired a write lock on an extent buffer of the subvolume btree. CC: stable@vger.kernel.org # 4.19+ Reviewed-by: Qu Wenruo <wqu@suse.com> Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-22 00:31:48 +08:00
bool skip_commit_root_sem);
char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
u32 name_len, unsigned long name_off,
struct extent_buffer *eb_in, u64 parent,
char *dest, u32 size);
struct btrfs_data_container *init_data_container(u32 total_bytes);
struct inode_fs_paths *init_ipath(s32 total_bytes, struct btrfs_root *fs_root,
struct btrfs_path *path);
void free_ipath(struct inode_fs_paths *ipath);
int btrfs_find_one_extref(struct btrfs_root *root, u64 inode_objectid,
u64 start_off, struct btrfs_path *path,
struct btrfs_inode_extref **ret_extref,
u64 *found_off);
int btrfs_check_shared(struct btrfs_root *root, u64 inum, u64 bytenr,
struct ulist *roots, struct ulist *tmp_ulist);
int __init btrfs_prelim_ref_init(void);
void __cold btrfs_prelim_ref_exit(void);
struct prelim_ref {
struct rb_node rbnode;
u64 root_id;
struct btrfs_key key_for_search;
int level;
int count;
struct extent_inode_elem *inode_list;
u64 parent;
u64 wanted_disk_byte;
};
/*
* Iterate backrefs of one extent.
*
* Now it only supports iteration of tree block in commit root.
*/
struct btrfs_backref_iter {
u64 bytenr;
struct btrfs_path *path;
struct btrfs_fs_info *fs_info;
struct btrfs_key cur_key;
u32 item_ptr;
u32 cur_ptr;
u32 end_ptr;
};
struct btrfs_backref_iter *btrfs_backref_iter_alloc(
struct btrfs_fs_info *fs_info, gfp_t gfp_flag);
static inline void btrfs_backref_iter_free(struct btrfs_backref_iter *iter)
{
if (!iter)
return;
btrfs_free_path(iter->path);
kfree(iter);
}
static inline struct extent_buffer *btrfs_backref_get_eb(
struct btrfs_backref_iter *iter)
{
if (!iter)
return NULL;
return iter->path->nodes[0];
}
/*
* For metadata with EXTENT_ITEM key (non-skinny) case, the first inline data
* is btrfs_tree_block_info, without a btrfs_extent_inline_ref header.
*
* This helper determines if that's the case.
*/
static inline bool btrfs_backref_has_tree_block_info(
struct btrfs_backref_iter *iter)
{
if (iter->cur_key.type == BTRFS_EXTENT_ITEM_KEY &&
iter->cur_ptr - iter->item_ptr == sizeof(struct btrfs_extent_item))
return true;
return false;
}
int btrfs_backref_iter_start(struct btrfs_backref_iter *iter, u64 bytenr);
int btrfs_backref_iter_next(struct btrfs_backref_iter *iter);
static inline bool btrfs_backref_iter_is_inline_ref(
struct btrfs_backref_iter *iter)
{
if (iter->cur_key.type == BTRFS_EXTENT_ITEM_KEY ||
iter->cur_key.type == BTRFS_METADATA_ITEM_KEY)
return true;
return false;
}
static inline void btrfs_backref_iter_release(struct btrfs_backref_iter *iter)
{
iter->bytenr = 0;
iter->item_ptr = 0;
iter->cur_ptr = 0;
iter->end_ptr = 0;
btrfs_release_path(iter->path);
memset(&iter->cur_key, 0, sizeof(iter->cur_key));
}
/*
* Backref cache related structures
*
* The whole objective of backref_cache is to build a bi-directional map
* of tree blocks (represented by backref_node) and all their parents.
*/
/*
* Represent a tree block in the backref cache
*/
struct btrfs_backref_node {
struct {
struct rb_node rb_node;
u64 bytenr;
}; /* Use rb_simple_node for search/insert */
u64 new_bytenr;
/* Objectid of tree block owner, can be not uptodate */
u64 owner;
/* Link to pending, changed or detached list */
struct list_head list;
/* List of upper level edges, which link this node to its parents */
struct list_head upper;
/* List of lower level edges, which link this node to its children */
struct list_head lower;
/* NULL if this node is not tree root */
struct btrfs_root *root;
/* Extent buffer got by COWing the block */
struct extent_buffer *eb;
/* Level of the tree block */
unsigned int level:8;
/* Is the block in a non-shareable tree */
unsigned int cowonly:1;
/* 1 if no child node is in the cache */
unsigned int lowest:1;
/* Is the extent buffer locked */
unsigned int locked:1;
/* Has the block been processed */
unsigned int processed:1;
/* Have backrefs of this block been checked */
unsigned int checked:1;
/*
* 1 if corresponding block has been COWed but some upper level block
* pointers may not point to the new location
*/
unsigned int pending:1;
/* 1 if the backref node isn't connected to any other backref node */
unsigned int detached:1;
/*
* For generic purpose backref cache, where we only care if it's a reloc
* root, doesn't care the source subvolid.
*/
unsigned int is_reloc_root:1;
};
#define LOWER 0
#define UPPER 1
/*
* Represent an edge connecting upper and lower backref nodes.
*/
struct btrfs_backref_edge {
/*
* list[LOWER] is linked to btrfs_backref_node::upper of lower level
* node, and list[UPPER] is linked to btrfs_backref_node::lower of
* upper level node.
*
* Also, build_backref_tree() uses list[UPPER] for pending edges, before
* linking list[UPPER] to its upper level nodes.
*/
struct list_head list[2];
/* Two related nodes */
struct btrfs_backref_node *node[2];
};
struct btrfs_backref_cache {
/* Red black tree of all backref nodes in the cache */
struct rb_root rb_root;
/* For passing backref nodes to btrfs_reloc_cow_block */
struct btrfs_backref_node *path[BTRFS_MAX_LEVEL];
/*
* List of blocks that have been COWed but some block pointers in upper
* level blocks may not reflect the new location
*/
struct list_head pending[BTRFS_MAX_LEVEL];
/* List of backref nodes with no child node */
struct list_head leaves;
/* List of blocks that have been COWed in current transaction */
struct list_head changed;
/* List of detached backref node. */
struct list_head detached;
u64 last_trans;
int nr_nodes;
int nr_edges;
/* List of unchecked backref edges during backref cache build */
struct list_head pending_edge;
/* List of useless backref nodes during backref cache build */
struct list_head useless_node;
struct btrfs_fs_info *fs_info;
/*
* Whether this cache is for relocation
*
* Reloction backref cache require more info for reloc root compared
* to generic backref cache.
*/
unsigned int is_reloc;
};
void btrfs_backref_init_cache(struct btrfs_fs_info *fs_info,
struct btrfs_backref_cache *cache, int is_reloc);
struct btrfs_backref_node *btrfs_backref_alloc_node(
struct btrfs_backref_cache *cache, u64 bytenr, int level);
struct btrfs_backref_edge *btrfs_backref_alloc_edge(
struct btrfs_backref_cache *cache);
#define LINK_LOWER (1 << 0)
#define LINK_UPPER (1 << 1)
static inline void btrfs_backref_link_edge(struct btrfs_backref_edge *edge,
struct btrfs_backref_node *lower,
struct btrfs_backref_node *upper,
int link_which)
{
ASSERT(upper && lower && upper->level == lower->level + 1);
edge->node[LOWER] = lower;
edge->node[UPPER] = upper;
if (link_which & LINK_LOWER)
list_add_tail(&edge->list[LOWER], &lower->upper);
if (link_which & LINK_UPPER)
list_add_tail(&edge->list[UPPER], &upper->lower);
}
static inline void btrfs_backref_free_node(struct btrfs_backref_cache *cache,
struct btrfs_backref_node *node)
{
if (node) {
btrfs: add asserts for deleting backref cache nodes A weird KASAN problem that Zygo reported could have been easily caught if we checked for basic things in our backref freeing code. We have two methods of freeing a backref node - btrfs_backref_free_node: this just is kfree() essentially. - btrfs_backref_drop_node: this actually unlinks the node and cleans up everything and then calls btrfs_backref_free_node(). We should mostly be using btrfs_backref_drop_node(), to make sure the node is properly unlinked from the backref cache, and only use btrfs_backref_free_node() when we know the node isn't actually linked to the backref cache. We made a mistake here and thus got the KASAN splat. Make this style of issue easier to find by adding some ASSERT()'s to btrfs_backref_free_node() and adjusting our deletion stuff to properly init the list so we can rely on list_empty() checks working properly. BUG: KASAN: use-after-free in btrfs_backref_cleanup_node+0x18a/0x420 Read of size 8 at addr ffff888112402950 by task btrfs/28836 CPU: 0 PID: 28836 Comm: btrfs Tainted: G W 5.10.0-e35f27394290-for-next+ #23 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014 Call Trace: dump_stack+0xbc/0xf9 ? btrfs_backref_cleanup_node+0x18a/0x420 print_address_description.constprop.8+0x21/0x210 ? record_print_text.cold.34+0x11/0x11 ? btrfs_backref_cleanup_node+0x18a/0x420 ? btrfs_backref_cleanup_node+0x18a/0x420 kasan_report.cold.10+0x20/0x37 ? btrfs_backref_cleanup_node+0x18a/0x420 __asan_load8+0x69/0x90 btrfs_backref_cleanup_node+0x18a/0x420 btrfs_backref_release_cache+0x83/0x1b0 relocate_block_group+0x394/0x780 ? merge_reloc_roots+0x4a0/0x4a0 btrfs_relocate_block_group+0x26e/0x4c0 btrfs_relocate_chunk+0x52/0x120 btrfs_balance+0xe2e/0x1900 ? check_flags.part.50+0x6c/0x1e0 ? btrfs_relocate_chunk+0x120/0x120 ? kmem_cache_alloc_trace+0xa06/0xcb0 ? _copy_from_user+0x83/0xc0 btrfs_ioctl_balance+0x3a7/0x460 btrfs_ioctl+0x24c8/0x4360 ? __kasan_check_read+0x11/0x20 ? check_chain_key+0x1f4/0x2f0 ? __asan_loadN+0xf/0x20 ? btrfs_ioctl_get_supported_features+0x30/0x30 ? kvm_sched_clock_read+0x18/0x30 ? check_chain_key+0x1f4/0x2f0 ? lock_downgrade+0x3f0/0x3f0 ? handle_mm_fault+0xad6/0x2150 ? do_vfs_ioctl+0xfc/0x9d0 ? ioctl_file_clone+0xe0/0xe0 ? check_flags.part.50+0x6c/0x1e0 ? check_flags.part.50+0x6c/0x1e0 ? check_flags+0x26/0x30 ? lock_is_held_type+0xc3/0xf0 ? syscall_enter_from_user_mode+0x1b/0x60 ? do_syscall_64+0x13/0x80 ? rcu_read_lock_sched_held+0xa1/0xd0 ? __kasan_check_read+0x11/0x20 ? __fget_light+0xae/0x110 __x64_sys_ioctl+0xc3/0x100 do_syscall_64+0x37/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7f4c4bdfe427 RSP: 002b:00007fff33ee6df8 EFLAGS: 00000202 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007fff33ee6e98 RCX: 00007f4c4bdfe427 RDX: 00007fff33ee6e98 RSI: 00000000c4009420 RDI: 0000000000000003 RBP: 0000000000000003 R08: 0000000000000003 R09: 0000000000000078 R10: fffffffffffff59d R11: 0000000000000202 R12: 0000000000000001 R13: 0000000000000000 R14: 00007fff33ee8a34 R15: 0000000000000001 Allocated by task 28836: kasan_save_stack+0x21/0x50 __kasan_kmalloc.constprop.18+0xbe/0xd0 kasan_kmalloc+0x9/0x10 kmem_cache_alloc_trace+0x410/0xcb0 btrfs_backref_alloc_node+0x46/0xf0 btrfs_backref_add_tree_node+0x60d/0x11d0 build_backref_tree+0xc5/0x700 relocate_tree_blocks+0x2be/0xb90 relocate_block_group+0x2eb/0x780 btrfs_relocate_block_group+0x26e/0x4c0 btrfs_relocate_chunk+0x52/0x120 btrfs_balance+0xe2e/0x1900 btrfs_ioctl_balance+0x3a7/0x460 btrfs_ioctl+0x24c8/0x4360 __x64_sys_ioctl+0xc3/0x100 do_syscall_64+0x37/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Freed by task 28836: kasan_save_stack+0x21/0x50 kasan_set_track+0x20/0x30 kasan_set_free_info+0x1f/0x30 __kasan_slab_free+0xf3/0x140 kasan_slab_free+0xe/0x10 kfree+0xde/0x200 btrfs_backref_error_cleanup+0x452/0x530 build_backref_tree+0x1a5/0x700 relocate_tree_blocks+0x2be/0xb90 relocate_block_group+0x2eb/0x780 btrfs_relocate_block_group+0x26e/0x4c0 btrfs_relocate_chunk+0x52/0x120 btrfs_balance+0xe2e/0x1900 btrfs_ioctl_balance+0x3a7/0x460 btrfs_ioctl+0x24c8/0x4360 __x64_sys_ioctl+0xc3/0x100 do_syscall_64+0x37/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xa9 The buggy address belongs to the object at ffff888112402900 which belongs to the cache kmalloc-128 of size 128 The buggy address is located 80 bytes inside of 128-byte region [ffff888112402900, ffff888112402980) The buggy address belongs to the page: page:0000000028b1cd08 refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff888131c810c0 pfn:0x112402 flags: 0x17ffe0000000200(slab) raw: 017ffe0000000200 ffffea000424f308 ffffea0007d572c8 ffff888100040440 raw: ffff888131c810c0 ffff888112402000 0000000100000009 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888112402800: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff888112402880: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc >ffff888112402900: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff888112402980: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff888112402a00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Link: https://lore.kernel.org/linux-btrfs/20201208194607.GI31381@hungrycats.org/ CC: stable@vger.kernel.org # 5.10+ Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-01-15 03:02:45 +08:00
ASSERT(list_empty(&node->list));
ASSERT(list_empty(&node->lower));
ASSERT(node->eb == NULL);
cache->nr_nodes--;
btrfs_put_root(node->root);
kfree(node);
}
}
static inline void btrfs_backref_free_edge(struct btrfs_backref_cache *cache,
struct btrfs_backref_edge *edge)
{
if (edge) {
cache->nr_edges--;
kfree(edge);
}
}
static inline void btrfs_backref_unlock_node_buffer(
struct btrfs_backref_node *node)
{
if (node->locked) {
btrfs_tree_unlock(node->eb);
node->locked = 0;
}
}
static inline void btrfs_backref_drop_node_buffer(
struct btrfs_backref_node *node)
{
if (node->eb) {
btrfs_backref_unlock_node_buffer(node);
free_extent_buffer(node->eb);
node->eb = NULL;
}
}
/*
* Drop the backref node from cache without cleaning up its children
* edges.
*
* This can only be called on node without parent edges.
* The children edges are still kept as is.
*/
static inline void btrfs_backref_drop_node(struct btrfs_backref_cache *tree,
struct btrfs_backref_node *node)
{
btrfs: add asserts for deleting backref cache nodes A weird KASAN problem that Zygo reported could have been easily caught if we checked for basic things in our backref freeing code. We have two methods of freeing a backref node - btrfs_backref_free_node: this just is kfree() essentially. - btrfs_backref_drop_node: this actually unlinks the node and cleans up everything and then calls btrfs_backref_free_node(). We should mostly be using btrfs_backref_drop_node(), to make sure the node is properly unlinked from the backref cache, and only use btrfs_backref_free_node() when we know the node isn't actually linked to the backref cache. We made a mistake here and thus got the KASAN splat. Make this style of issue easier to find by adding some ASSERT()'s to btrfs_backref_free_node() and adjusting our deletion stuff to properly init the list so we can rely on list_empty() checks working properly. BUG: KASAN: use-after-free in btrfs_backref_cleanup_node+0x18a/0x420 Read of size 8 at addr ffff888112402950 by task btrfs/28836 CPU: 0 PID: 28836 Comm: btrfs Tainted: G W 5.10.0-e35f27394290-for-next+ #23 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014 Call Trace: dump_stack+0xbc/0xf9 ? btrfs_backref_cleanup_node+0x18a/0x420 print_address_description.constprop.8+0x21/0x210 ? record_print_text.cold.34+0x11/0x11 ? btrfs_backref_cleanup_node+0x18a/0x420 ? btrfs_backref_cleanup_node+0x18a/0x420 kasan_report.cold.10+0x20/0x37 ? btrfs_backref_cleanup_node+0x18a/0x420 __asan_load8+0x69/0x90 btrfs_backref_cleanup_node+0x18a/0x420 btrfs_backref_release_cache+0x83/0x1b0 relocate_block_group+0x394/0x780 ? merge_reloc_roots+0x4a0/0x4a0 btrfs_relocate_block_group+0x26e/0x4c0 btrfs_relocate_chunk+0x52/0x120 btrfs_balance+0xe2e/0x1900 ? check_flags.part.50+0x6c/0x1e0 ? btrfs_relocate_chunk+0x120/0x120 ? kmem_cache_alloc_trace+0xa06/0xcb0 ? _copy_from_user+0x83/0xc0 btrfs_ioctl_balance+0x3a7/0x460 btrfs_ioctl+0x24c8/0x4360 ? __kasan_check_read+0x11/0x20 ? check_chain_key+0x1f4/0x2f0 ? __asan_loadN+0xf/0x20 ? btrfs_ioctl_get_supported_features+0x30/0x30 ? kvm_sched_clock_read+0x18/0x30 ? check_chain_key+0x1f4/0x2f0 ? lock_downgrade+0x3f0/0x3f0 ? handle_mm_fault+0xad6/0x2150 ? do_vfs_ioctl+0xfc/0x9d0 ? ioctl_file_clone+0xe0/0xe0 ? check_flags.part.50+0x6c/0x1e0 ? check_flags.part.50+0x6c/0x1e0 ? check_flags+0x26/0x30 ? lock_is_held_type+0xc3/0xf0 ? syscall_enter_from_user_mode+0x1b/0x60 ? do_syscall_64+0x13/0x80 ? rcu_read_lock_sched_held+0xa1/0xd0 ? __kasan_check_read+0x11/0x20 ? __fget_light+0xae/0x110 __x64_sys_ioctl+0xc3/0x100 do_syscall_64+0x37/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7f4c4bdfe427 RSP: 002b:00007fff33ee6df8 EFLAGS: 00000202 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007fff33ee6e98 RCX: 00007f4c4bdfe427 RDX: 00007fff33ee6e98 RSI: 00000000c4009420 RDI: 0000000000000003 RBP: 0000000000000003 R08: 0000000000000003 R09: 0000000000000078 R10: fffffffffffff59d R11: 0000000000000202 R12: 0000000000000001 R13: 0000000000000000 R14: 00007fff33ee8a34 R15: 0000000000000001 Allocated by task 28836: kasan_save_stack+0x21/0x50 __kasan_kmalloc.constprop.18+0xbe/0xd0 kasan_kmalloc+0x9/0x10 kmem_cache_alloc_trace+0x410/0xcb0 btrfs_backref_alloc_node+0x46/0xf0 btrfs_backref_add_tree_node+0x60d/0x11d0 build_backref_tree+0xc5/0x700 relocate_tree_blocks+0x2be/0xb90 relocate_block_group+0x2eb/0x780 btrfs_relocate_block_group+0x26e/0x4c0 btrfs_relocate_chunk+0x52/0x120 btrfs_balance+0xe2e/0x1900 btrfs_ioctl_balance+0x3a7/0x460 btrfs_ioctl+0x24c8/0x4360 __x64_sys_ioctl+0xc3/0x100 do_syscall_64+0x37/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Freed by task 28836: kasan_save_stack+0x21/0x50 kasan_set_track+0x20/0x30 kasan_set_free_info+0x1f/0x30 __kasan_slab_free+0xf3/0x140 kasan_slab_free+0xe/0x10 kfree+0xde/0x200 btrfs_backref_error_cleanup+0x452/0x530 build_backref_tree+0x1a5/0x700 relocate_tree_blocks+0x2be/0xb90 relocate_block_group+0x2eb/0x780 btrfs_relocate_block_group+0x26e/0x4c0 btrfs_relocate_chunk+0x52/0x120 btrfs_balance+0xe2e/0x1900 btrfs_ioctl_balance+0x3a7/0x460 btrfs_ioctl+0x24c8/0x4360 __x64_sys_ioctl+0xc3/0x100 do_syscall_64+0x37/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xa9 The buggy address belongs to the object at ffff888112402900 which belongs to the cache kmalloc-128 of size 128 The buggy address is located 80 bytes inside of 128-byte region [ffff888112402900, ffff888112402980) The buggy address belongs to the page: page:0000000028b1cd08 refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff888131c810c0 pfn:0x112402 flags: 0x17ffe0000000200(slab) raw: 017ffe0000000200 ffffea000424f308 ffffea0007d572c8 ffff888100040440 raw: ffff888131c810c0 ffff888112402000 0000000100000009 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888112402800: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff888112402880: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc >ffff888112402900: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff888112402980: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff888112402a00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Link: https://lore.kernel.org/linux-btrfs/20201208194607.GI31381@hungrycats.org/ CC: stable@vger.kernel.org # 5.10+ Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-01-15 03:02:45 +08:00
ASSERT(list_empty(&node->upper));
btrfs_backref_drop_node_buffer(node);
btrfs: add asserts for deleting backref cache nodes A weird KASAN problem that Zygo reported could have been easily caught if we checked for basic things in our backref freeing code. We have two methods of freeing a backref node - btrfs_backref_free_node: this just is kfree() essentially. - btrfs_backref_drop_node: this actually unlinks the node and cleans up everything and then calls btrfs_backref_free_node(). We should mostly be using btrfs_backref_drop_node(), to make sure the node is properly unlinked from the backref cache, and only use btrfs_backref_free_node() when we know the node isn't actually linked to the backref cache. We made a mistake here and thus got the KASAN splat. Make this style of issue easier to find by adding some ASSERT()'s to btrfs_backref_free_node() and adjusting our deletion stuff to properly init the list so we can rely on list_empty() checks working properly. BUG: KASAN: use-after-free in btrfs_backref_cleanup_node+0x18a/0x420 Read of size 8 at addr ffff888112402950 by task btrfs/28836 CPU: 0 PID: 28836 Comm: btrfs Tainted: G W 5.10.0-e35f27394290-for-next+ #23 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014 Call Trace: dump_stack+0xbc/0xf9 ? btrfs_backref_cleanup_node+0x18a/0x420 print_address_description.constprop.8+0x21/0x210 ? record_print_text.cold.34+0x11/0x11 ? btrfs_backref_cleanup_node+0x18a/0x420 ? btrfs_backref_cleanup_node+0x18a/0x420 kasan_report.cold.10+0x20/0x37 ? btrfs_backref_cleanup_node+0x18a/0x420 __asan_load8+0x69/0x90 btrfs_backref_cleanup_node+0x18a/0x420 btrfs_backref_release_cache+0x83/0x1b0 relocate_block_group+0x394/0x780 ? merge_reloc_roots+0x4a0/0x4a0 btrfs_relocate_block_group+0x26e/0x4c0 btrfs_relocate_chunk+0x52/0x120 btrfs_balance+0xe2e/0x1900 ? check_flags.part.50+0x6c/0x1e0 ? btrfs_relocate_chunk+0x120/0x120 ? kmem_cache_alloc_trace+0xa06/0xcb0 ? _copy_from_user+0x83/0xc0 btrfs_ioctl_balance+0x3a7/0x460 btrfs_ioctl+0x24c8/0x4360 ? __kasan_check_read+0x11/0x20 ? check_chain_key+0x1f4/0x2f0 ? __asan_loadN+0xf/0x20 ? btrfs_ioctl_get_supported_features+0x30/0x30 ? kvm_sched_clock_read+0x18/0x30 ? check_chain_key+0x1f4/0x2f0 ? lock_downgrade+0x3f0/0x3f0 ? handle_mm_fault+0xad6/0x2150 ? do_vfs_ioctl+0xfc/0x9d0 ? ioctl_file_clone+0xe0/0xe0 ? check_flags.part.50+0x6c/0x1e0 ? check_flags.part.50+0x6c/0x1e0 ? check_flags+0x26/0x30 ? lock_is_held_type+0xc3/0xf0 ? syscall_enter_from_user_mode+0x1b/0x60 ? do_syscall_64+0x13/0x80 ? rcu_read_lock_sched_held+0xa1/0xd0 ? __kasan_check_read+0x11/0x20 ? __fget_light+0xae/0x110 __x64_sys_ioctl+0xc3/0x100 do_syscall_64+0x37/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7f4c4bdfe427 RSP: 002b:00007fff33ee6df8 EFLAGS: 00000202 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007fff33ee6e98 RCX: 00007f4c4bdfe427 RDX: 00007fff33ee6e98 RSI: 00000000c4009420 RDI: 0000000000000003 RBP: 0000000000000003 R08: 0000000000000003 R09: 0000000000000078 R10: fffffffffffff59d R11: 0000000000000202 R12: 0000000000000001 R13: 0000000000000000 R14: 00007fff33ee8a34 R15: 0000000000000001 Allocated by task 28836: kasan_save_stack+0x21/0x50 __kasan_kmalloc.constprop.18+0xbe/0xd0 kasan_kmalloc+0x9/0x10 kmem_cache_alloc_trace+0x410/0xcb0 btrfs_backref_alloc_node+0x46/0xf0 btrfs_backref_add_tree_node+0x60d/0x11d0 build_backref_tree+0xc5/0x700 relocate_tree_blocks+0x2be/0xb90 relocate_block_group+0x2eb/0x780 btrfs_relocate_block_group+0x26e/0x4c0 btrfs_relocate_chunk+0x52/0x120 btrfs_balance+0xe2e/0x1900 btrfs_ioctl_balance+0x3a7/0x460 btrfs_ioctl+0x24c8/0x4360 __x64_sys_ioctl+0xc3/0x100 do_syscall_64+0x37/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Freed by task 28836: kasan_save_stack+0x21/0x50 kasan_set_track+0x20/0x30 kasan_set_free_info+0x1f/0x30 __kasan_slab_free+0xf3/0x140 kasan_slab_free+0xe/0x10 kfree+0xde/0x200 btrfs_backref_error_cleanup+0x452/0x530 build_backref_tree+0x1a5/0x700 relocate_tree_blocks+0x2be/0xb90 relocate_block_group+0x2eb/0x780 btrfs_relocate_block_group+0x26e/0x4c0 btrfs_relocate_chunk+0x52/0x120 btrfs_balance+0xe2e/0x1900 btrfs_ioctl_balance+0x3a7/0x460 btrfs_ioctl+0x24c8/0x4360 __x64_sys_ioctl+0xc3/0x100 do_syscall_64+0x37/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xa9 The buggy address belongs to the object at ffff888112402900 which belongs to the cache kmalloc-128 of size 128 The buggy address is located 80 bytes inside of 128-byte region [ffff888112402900, ffff888112402980) The buggy address belongs to the page: page:0000000028b1cd08 refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff888131c810c0 pfn:0x112402 flags: 0x17ffe0000000200(slab) raw: 017ffe0000000200 ffffea000424f308 ffffea0007d572c8 ffff888100040440 raw: ffff888131c810c0 ffff888112402000 0000000100000009 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888112402800: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff888112402880: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc >ffff888112402900: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff888112402980: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff888112402a00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Link: https://lore.kernel.org/linux-btrfs/20201208194607.GI31381@hungrycats.org/ CC: stable@vger.kernel.org # 5.10+ Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-01-15 03:02:45 +08:00
list_del_init(&node->list);
list_del_init(&node->lower);
if (!RB_EMPTY_NODE(&node->rb_node))
rb_erase(&node->rb_node, &tree->rb_root);
btrfs_backref_free_node(tree, node);
}
void btrfs_backref_cleanup_node(struct btrfs_backref_cache *cache,
struct btrfs_backref_node *node);
void btrfs_backref_release_cache(struct btrfs_backref_cache *cache);
static inline void btrfs_backref_panic(struct btrfs_fs_info *fs_info,
u64 bytenr, int errno)
{
btrfs_panic(fs_info, errno,
"Inconsistency in backref cache found at offset %llu",
bytenr);
}
int btrfs_backref_add_tree_node(struct btrfs_backref_cache *cache,
struct btrfs_path *path,
struct btrfs_backref_iter *iter,
struct btrfs_key *node_key,
struct btrfs_backref_node *cur);
int btrfs_backref_finish_upper_links(struct btrfs_backref_cache *cache,
struct btrfs_backref_node *start);
void btrfs_backref_error_cleanup(struct btrfs_backref_cache *cache,
struct btrfs_backref_node *node);
#endif