linux_dsm_epyc7002/fs/btrfs/backref.h
Josef Bacik a1a5cc2548 btrfs: add asserts for deleting backref cache nodes
commit eddda68d97732ce05ca145f8e85e8a447f65cdad upstream.

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>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2021-03-04 11:38:29 +01:00

382 lines
10 KiB
C

/* 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,
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,
iterate_extent_inodes_t *iterate, void *ctx,
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,
struct btrfs_fs_info *fs_info, u64 bytenr,
u64 time_seq, struct ulist **roots, bool ignore_offset);
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) {
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)
{
ASSERT(list_empty(&node->upper));
btrfs_backref_drop_node_buffer(node);
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