mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-23 01:10:04 +00:00
![Liu Shixin](/assets/img/avatar_default.png)
Syzbot found a kernel BUG in hfs_bnode_put(): kernel BUG at fs/hfs/bnode.c:466! invalid opcode: 0000 [#1] PREEMPT SMP KASAN CPU: 0 PID: 3634 Comm: kworker/u4:5 Not tainted 6.1.0-rc7-syzkaller-00190-g97ee9d1c1696 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022 Workqueue: writeback wb_workfn (flush-7:0) RIP: 0010:hfs_bnode_put+0x46f/0x480 fs/hfs/bnode.c:466 Code: 8a 80 ff e9 73 fe ff ff 89 d9 80 e1 07 80 c1 03 38 c1 0f 8c a0 fe ff ff 48 89 df e8 db 8a 80 ff e9 93 fe ff ff e8 a1 68 2c ff <0f> 0b e8 9a 68 2c ff 0f 0b 0f 1f 84 00 00 00 00 00 55 41 57 41 56 RSP: 0018:ffffc90003b4f258 EFLAGS: 00010293 RAX: ffffffff825e318f RBX: 0000000000000000 RCX: ffff8880739dd7c0 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: ffffc90003b4f430 R08: ffffffff825e2d9b R09: ffffed10045157d1 R10: ffffed10045157d1 R11: 1ffff110045157d0 R12: ffff8880228abe80 R13: ffff88807016c000 R14: dffffc0000000000 R15: ffff8880228abe00 FS: 0000000000000000(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fa6ebe88718 CR3: 000000001e93d000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> hfs_write_inode+0x1bc/0xb40 write_inode fs/fs-writeback.c:1440 [inline] __writeback_single_inode+0x4d6/0x670 fs/fs-writeback.c:1652 writeback_sb_inodes+0xb3b/0x18f0 fs/fs-writeback.c:1878 __writeback_inodes_wb+0x125/0x420 fs/fs-writeback.c:1949 wb_writeback+0x440/0x7b0 fs/fs-writeback.c:2054 wb_check_start_all fs/fs-writeback.c:2176 [inline] wb_do_writeback fs/fs-writeback.c:2202 [inline] wb_workfn+0x827/0xef0 fs/fs-writeback.c:2235 process_one_work+0x877/0xdb0 kernel/workqueue.c:2289 worker_thread+0xb14/0x1330 kernel/workqueue.c:2436 kthread+0x266/0x300 kernel/kthread.c:376 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:306 </TASK> The BUG_ON() is triggered at here: /* Dispose of resources used by a node */ void hfs_bnode_put(struct hfs_bnode *node) { if (node) { <skipped> BUG_ON(!atomic_read(&node->refcnt)); <- we have issue here!!!! <skipped> } } By tracing the refcnt, I found the node is created by hfs_bmap_alloc() with refcnt 1. Then the node is used by hfs_btree_write(). There is a missing of hfs_bnode_get() after find the node. The issue happened in following path: <alloc> hfs_bmap_alloc hfs_bnode_find __hfs_bnode_create <- allocate a new node with refcnt 1. hfs_bnode_put <- decrease the refcnt <write> hfs_btree_write hfs_bnode_find __hfs_bnode_create hfs_bnode_findhash <- find the node without refcnt increased. hfs_bnode_put <- trigger the BUG_ON() since refcnt is 0. Link: https://lkml.kernel.org/r/20221212021627.3766829-1-liushixin2@huawei.com Reported-by: syzbot+5b04b49a7ec7226c7426@syzkaller.appspotmail.com Signed-off-by: Liu Shixin <liushixin2@huawei.com> Cc: Fabio M. De Francesco <fmdefrancesco@gmail.com> Cc: Viacheslav Dubeyko <slava@dubeyko.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
485 lines
12 KiB
C
485 lines
12 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* linux/fs/hfs/bnode.c
|
|
*
|
|
* Copyright (C) 2001
|
|
* Brad Boyer (flar@allandria.com)
|
|
* (C) 2003 Ardis Technologies <roman@ardistech.com>
|
|
*
|
|
* Handle basic btree node operations
|
|
*/
|
|
|
|
#include <linux/pagemap.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/swap.h>
|
|
|
|
#include "btree.h"
|
|
|
|
void hfs_bnode_read(struct hfs_bnode *node, void *buf, int off, int len)
|
|
{
|
|
struct page *page;
|
|
int pagenum;
|
|
int bytes_read;
|
|
int bytes_to_read;
|
|
|
|
off += node->page_offset;
|
|
pagenum = off >> PAGE_SHIFT;
|
|
off &= ~PAGE_MASK; /* compute page offset for the first page */
|
|
|
|
for (bytes_read = 0; bytes_read < len; bytes_read += bytes_to_read) {
|
|
if (pagenum >= node->tree->pages_per_bnode)
|
|
break;
|
|
page = node->page[pagenum];
|
|
bytes_to_read = min_t(int, len - bytes_read, PAGE_SIZE - off);
|
|
|
|
memcpy_from_page(buf + bytes_read, page, off, bytes_to_read);
|
|
|
|
pagenum++;
|
|
off = 0; /* page offset only applies to the first page */
|
|
}
|
|
}
|
|
|
|
u16 hfs_bnode_read_u16(struct hfs_bnode *node, int off)
|
|
{
|
|
__be16 data;
|
|
// optimize later...
|
|
hfs_bnode_read(node, &data, off, 2);
|
|
return be16_to_cpu(data);
|
|
}
|
|
|
|
u8 hfs_bnode_read_u8(struct hfs_bnode *node, int off)
|
|
{
|
|
u8 data;
|
|
// optimize later...
|
|
hfs_bnode_read(node, &data, off, 1);
|
|
return data;
|
|
}
|
|
|
|
void hfs_bnode_read_key(struct hfs_bnode *node, void *key, int off)
|
|
{
|
|
struct hfs_btree *tree;
|
|
int key_len;
|
|
|
|
tree = node->tree;
|
|
if (node->type == HFS_NODE_LEAF ||
|
|
tree->attributes & HFS_TREE_VARIDXKEYS)
|
|
key_len = hfs_bnode_read_u8(node, off) + 1;
|
|
else
|
|
key_len = tree->max_key_len + 1;
|
|
|
|
hfs_bnode_read(node, key, off, key_len);
|
|
}
|
|
|
|
void hfs_bnode_write(struct hfs_bnode *node, void *buf, int off, int len)
|
|
{
|
|
struct page *page;
|
|
|
|
off += node->page_offset;
|
|
page = node->page[0];
|
|
|
|
memcpy_to_page(page, off, buf, len);
|
|
set_page_dirty(page);
|
|
}
|
|
|
|
void hfs_bnode_write_u16(struct hfs_bnode *node, int off, u16 data)
|
|
{
|
|
__be16 v = cpu_to_be16(data);
|
|
// optimize later...
|
|
hfs_bnode_write(node, &v, off, 2);
|
|
}
|
|
|
|
void hfs_bnode_write_u8(struct hfs_bnode *node, int off, u8 data)
|
|
{
|
|
// optimize later...
|
|
hfs_bnode_write(node, &data, off, 1);
|
|
}
|
|
|
|
void hfs_bnode_clear(struct hfs_bnode *node, int off, int len)
|
|
{
|
|
struct page *page;
|
|
|
|
off += node->page_offset;
|
|
page = node->page[0];
|
|
|
|
memzero_page(page, off, len);
|
|
set_page_dirty(page);
|
|
}
|
|
|
|
void hfs_bnode_copy(struct hfs_bnode *dst_node, int dst,
|
|
struct hfs_bnode *src_node, int src, int len)
|
|
{
|
|
struct page *src_page, *dst_page;
|
|
|
|
hfs_dbg(BNODE_MOD, "copybytes: %u,%u,%u\n", dst, src, len);
|
|
if (!len)
|
|
return;
|
|
src += src_node->page_offset;
|
|
dst += dst_node->page_offset;
|
|
src_page = src_node->page[0];
|
|
dst_page = dst_node->page[0];
|
|
|
|
memcpy_page(dst_page, dst, src_page, src, len);
|
|
set_page_dirty(dst_page);
|
|
}
|
|
|
|
void hfs_bnode_move(struct hfs_bnode *node, int dst, int src, int len)
|
|
{
|
|
struct page *page;
|
|
void *ptr;
|
|
|
|
hfs_dbg(BNODE_MOD, "movebytes: %u,%u,%u\n", dst, src, len);
|
|
if (!len)
|
|
return;
|
|
src += node->page_offset;
|
|
dst += node->page_offset;
|
|
page = node->page[0];
|
|
ptr = kmap_local_page(page);
|
|
memmove(ptr + dst, ptr + src, len);
|
|
kunmap_local(ptr);
|
|
set_page_dirty(page);
|
|
}
|
|
|
|
void hfs_bnode_dump(struct hfs_bnode *node)
|
|
{
|
|
struct hfs_bnode_desc desc;
|
|
__be32 cnid;
|
|
int i, off, key_off;
|
|
|
|
hfs_dbg(BNODE_MOD, "bnode: %d\n", node->this);
|
|
hfs_bnode_read(node, &desc, 0, sizeof(desc));
|
|
hfs_dbg(BNODE_MOD, "%d, %d, %d, %d, %d\n",
|
|
be32_to_cpu(desc.next), be32_to_cpu(desc.prev),
|
|
desc.type, desc.height, be16_to_cpu(desc.num_recs));
|
|
|
|
off = node->tree->node_size - 2;
|
|
for (i = be16_to_cpu(desc.num_recs); i >= 0; off -= 2, i--) {
|
|
key_off = hfs_bnode_read_u16(node, off);
|
|
hfs_dbg_cont(BNODE_MOD, " %d", key_off);
|
|
if (i && node->type == HFS_NODE_INDEX) {
|
|
int tmp;
|
|
|
|
if (node->tree->attributes & HFS_TREE_VARIDXKEYS)
|
|
tmp = (hfs_bnode_read_u8(node, key_off) | 1) + 1;
|
|
else
|
|
tmp = node->tree->max_key_len + 1;
|
|
hfs_dbg_cont(BNODE_MOD, " (%d,%d",
|
|
tmp, hfs_bnode_read_u8(node, key_off));
|
|
hfs_bnode_read(node, &cnid, key_off + tmp, 4);
|
|
hfs_dbg_cont(BNODE_MOD, ",%d)", be32_to_cpu(cnid));
|
|
} else if (i && node->type == HFS_NODE_LEAF) {
|
|
int tmp;
|
|
|
|
tmp = hfs_bnode_read_u8(node, key_off);
|
|
hfs_dbg_cont(BNODE_MOD, " (%d)", tmp);
|
|
}
|
|
}
|
|
hfs_dbg_cont(BNODE_MOD, "\n");
|
|
}
|
|
|
|
void hfs_bnode_unlink(struct hfs_bnode *node)
|
|
{
|
|
struct hfs_btree *tree;
|
|
struct hfs_bnode *tmp;
|
|
__be32 cnid;
|
|
|
|
tree = node->tree;
|
|
if (node->prev) {
|
|
tmp = hfs_bnode_find(tree, node->prev);
|
|
if (IS_ERR(tmp))
|
|
return;
|
|
tmp->next = node->next;
|
|
cnid = cpu_to_be32(tmp->next);
|
|
hfs_bnode_write(tmp, &cnid, offsetof(struct hfs_bnode_desc, next), 4);
|
|
hfs_bnode_put(tmp);
|
|
} else if (node->type == HFS_NODE_LEAF)
|
|
tree->leaf_head = node->next;
|
|
|
|
if (node->next) {
|
|
tmp = hfs_bnode_find(tree, node->next);
|
|
if (IS_ERR(tmp))
|
|
return;
|
|
tmp->prev = node->prev;
|
|
cnid = cpu_to_be32(tmp->prev);
|
|
hfs_bnode_write(tmp, &cnid, offsetof(struct hfs_bnode_desc, prev), 4);
|
|
hfs_bnode_put(tmp);
|
|
} else if (node->type == HFS_NODE_LEAF)
|
|
tree->leaf_tail = node->prev;
|
|
|
|
// move down?
|
|
if (!node->prev && !node->next) {
|
|
printk(KERN_DEBUG "hfs_btree_del_level\n");
|
|
}
|
|
if (!node->parent) {
|
|
tree->root = 0;
|
|
tree->depth = 0;
|
|
}
|
|
set_bit(HFS_BNODE_DELETED, &node->flags);
|
|
}
|
|
|
|
static inline int hfs_bnode_hash(u32 num)
|
|
{
|
|
num = (num >> 16) + num;
|
|
num += num >> 8;
|
|
return num & (NODE_HASH_SIZE - 1);
|
|
}
|
|
|
|
struct hfs_bnode *hfs_bnode_findhash(struct hfs_btree *tree, u32 cnid)
|
|
{
|
|
struct hfs_bnode *node;
|
|
|
|
if (cnid >= tree->node_count) {
|
|
pr_err("request for non-existent node %d in B*Tree\n", cnid);
|
|
return NULL;
|
|
}
|
|
|
|
for (node = tree->node_hash[hfs_bnode_hash(cnid)];
|
|
node; node = node->next_hash) {
|
|
if (node->this == cnid) {
|
|
return node;
|
|
}
|
|
}
|
|
return NULL;
|
|
}
|
|
|
|
static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid)
|
|
{
|
|
struct hfs_bnode *node, *node2;
|
|
struct address_space *mapping;
|
|
struct page *page;
|
|
int size, block, i, hash;
|
|
loff_t off;
|
|
|
|
if (cnid >= tree->node_count) {
|
|
pr_err("request for non-existent node %d in B*Tree\n", cnid);
|
|
return NULL;
|
|
}
|
|
|
|
size = sizeof(struct hfs_bnode) + tree->pages_per_bnode *
|
|
sizeof(struct page *);
|
|
node = kzalloc(size, GFP_KERNEL);
|
|
if (!node)
|
|
return NULL;
|
|
node->tree = tree;
|
|
node->this = cnid;
|
|
set_bit(HFS_BNODE_NEW, &node->flags);
|
|
atomic_set(&node->refcnt, 1);
|
|
hfs_dbg(BNODE_REFS, "new_node(%d:%d): 1\n",
|
|
node->tree->cnid, node->this);
|
|
init_waitqueue_head(&node->lock_wq);
|
|
spin_lock(&tree->hash_lock);
|
|
node2 = hfs_bnode_findhash(tree, cnid);
|
|
if (!node2) {
|
|
hash = hfs_bnode_hash(cnid);
|
|
node->next_hash = tree->node_hash[hash];
|
|
tree->node_hash[hash] = node;
|
|
tree->node_hash_cnt++;
|
|
} else {
|
|
hfs_bnode_get(node2);
|
|
spin_unlock(&tree->hash_lock);
|
|
kfree(node);
|
|
wait_event(node2->lock_wq, !test_bit(HFS_BNODE_NEW, &node2->flags));
|
|
return node2;
|
|
}
|
|
spin_unlock(&tree->hash_lock);
|
|
|
|
mapping = tree->inode->i_mapping;
|
|
off = (loff_t)cnid * tree->node_size;
|
|
block = off >> PAGE_SHIFT;
|
|
node->page_offset = off & ~PAGE_MASK;
|
|
for (i = 0; i < tree->pages_per_bnode; i++) {
|
|
page = read_mapping_page(mapping, block++, NULL);
|
|
if (IS_ERR(page))
|
|
goto fail;
|
|
node->page[i] = page;
|
|
}
|
|
|
|
return node;
|
|
fail:
|
|
set_bit(HFS_BNODE_ERROR, &node->flags);
|
|
return node;
|
|
}
|
|
|
|
void hfs_bnode_unhash(struct hfs_bnode *node)
|
|
{
|
|
struct hfs_bnode **p;
|
|
|
|
hfs_dbg(BNODE_REFS, "remove_node(%d:%d): %d\n",
|
|
node->tree->cnid, node->this, atomic_read(&node->refcnt));
|
|
for (p = &node->tree->node_hash[hfs_bnode_hash(node->this)];
|
|
*p && *p != node; p = &(*p)->next_hash)
|
|
;
|
|
BUG_ON(!*p);
|
|
*p = node->next_hash;
|
|
node->tree->node_hash_cnt--;
|
|
}
|
|
|
|
/* Load a particular node out of a tree */
|
|
struct hfs_bnode *hfs_bnode_find(struct hfs_btree *tree, u32 num)
|
|
{
|
|
struct hfs_bnode *node;
|
|
struct hfs_bnode_desc *desc;
|
|
int i, rec_off, off, next_off;
|
|
int entry_size, key_size;
|
|
|
|
spin_lock(&tree->hash_lock);
|
|
node = hfs_bnode_findhash(tree, num);
|
|
if (node) {
|
|
hfs_bnode_get(node);
|
|
spin_unlock(&tree->hash_lock);
|
|
wait_event(node->lock_wq, !test_bit(HFS_BNODE_NEW, &node->flags));
|
|
if (test_bit(HFS_BNODE_ERROR, &node->flags))
|
|
goto node_error;
|
|
return node;
|
|
}
|
|
spin_unlock(&tree->hash_lock);
|
|
node = __hfs_bnode_create(tree, num);
|
|
if (!node)
|
|
return ERR_PTR(-ENOMEM);
|
|
if (test_bit(HFS_BNODE_ERROR, &node->flags))
|
|
goto node_error;
|
|
if (!test_bit(HFS_BNODE_NEW, &node->flags))
|
|
return node;
|
|
|
|
desc = (struct hfs_bnode_desc *)(kmap_local_page(node->page[0]) +
|
|
node->page_offset);
|
|
node->prev = be32_to_cpu(desc->prev);
|
|
node->next = be32_to_cpu(desc->next);
|
|
node->num_recs = be16_to_cpu(desc->num_recs);
|
|
node->type = desc->type;
|
|
node->height = desc->height;
|
|
kunmap_local(desc);
|
|
|
|
switch (node->type) {
|
|
case HFS_NODE_HEADER:
|
|
case HFS_NODE_MAP:
|
|
if (node->height != 0)
|
|
goto node_error;
|
|
break;
|
|
case HFS_NODE_LEAF:
|
|
if (node->height != 1)
|
|
goto node_error;
|
|
break;
|
|
case HFS_NODE_INDEX:
|
|
if (node->height <= 1 || node->height > tree->depth)
|
|
goto node_error;
|
|
break;
|
|
default:
|
|
goto node_error;
|
|
}
|
|
|
|
rec_off = tree->node_size - 2;
|
|
off = hfs_bnode_read_u16(node, rec_off);
|
|
if (off != sizeof(struct hfs_bnode_desc))
|
|
goto node_error;
|
|
for (i = 1; i <= node->num_recs; off = next_off, i++) {
|
|
rec_off -= 2;
|
|
next_off = hfs_bnode_read_u16(node, rec_off);
|
|
if (next_off <= off ||
|
|
next_off > tree->node_size ||
|
|
next_off & 1)
|
|
goto node_error;
|
|
entry_size = next_off - off;
|
|
if (node->type != HFS_NODE_INDEX &&
|
|
node->type != HFS_NODE_LEAF)
|
|
continue;
|
|
key_size = hfs_bnode_read_u8(node, off) + 1;
|
|
if (key_size >= entry_size /*|| key_size & 1*/)
|
|
goto node_error;
|
|
}
|
|
clear_bit(HFS_BNODE_NEW, &node->flags);
|
|
wake_up(&node->lock_wq);
|
|
return node;
|
|
|
|
node_error:
|
|
set_bit(HFS_BNODE_ERROR, &node->flags);
|
|
clear_bit(HFS_BNODE_NEW, &node->flags);
|
|
wake_up(&node->lock_wq);
|
|
hfs_bnode_put(node);
|
|
return ERR_PTR(-EIO);
|
|
}
|
|
|
|
void hfs_bnode_free(struct hfs_bnode *node)
|
|
{
|
|
int i;
|
|
|
|
for (i = 0; i < node->tree->pages_per_bnode; i++)
|
|
if (node->page[i])
|
|
put_page(node->page[i]);
|
|
kfree(node);
|
|
}
|
|
|
|
struct hfs_bnode *hfs_bnode_create(struct hfs_btree *tree, u32 num)
|
|
{
|
|
struct hfs_bnode *node;
|
|
struct page **pagep;
|
|
int i;
|
|
|
|
spin_lock(&tree->hash_lock);
|
|
node = hfs_bnode_findhash(tree, num);
|
|
spin_unlock(&tree->hash_lock);
|
|
if (node) {
|
|
pr_crit("new node %u already hashed?\n", num);
|
|
WARN_ON(1);
|
|
return node;
|
|
}
|
|
node = __hfs_bnode_create(tree, num);
|
|
if (!node)
|
|
return ERR_PTR(-ENOMEM);
|
|
if (test_bit(HFS_BNODE_ERROR, &node->flags)) {
|
|
hfs_bnode_put(node);
|
|
return ERR_PTR(-EIO);
|
|
}
|
|
|
|
pagep = node->page;
|
|
memzero_page(*pagep, node->page_offset,
|
|
min((int)PAGE_SIZE, (int)tree->node_size));
|
|
set_page_dirty(*pagep);
|
|
for (i = 1; i < tree->pages_per_bnode; i++) {
|
|
memzero_page(*++pagep, 0, PAGE_SIZE);
|
|
set_page_dirty(*pagep);
|
|
}
|
|
clear_bit(HFS_BNODE_NEW, &node->flags);
|
|
wake_up(&node->lock_wq);
|
|
|
|
return node;
|
|
}
|
|
|
|
void hfs_bnode_get(struct hfs_bnode *node)
|
|
{
|
|
if (node) {
|
|
atomic_inc(&node->refcnt);
|
|
hfs_dbg(BNODE_REFS, "get_node(%d:%d): %d\n",
|
|
node->tree->cnid, node->this,
|
|
atomic_read(&node->refcnt));
|
|
}
|
|
}
|
|
|
|
/* Dispose of resources used by a node */
|
|
void hfs_bnode_put(struct hfs_bnode *node)
|
|
{
|
|
if (node) {
|
|
struct hfs_btree *tree = node->tree;
|
|
int i;
|
|
|
|
hfs_dbg(BNODE_REFS, "put_node(%d:%d): %d\n",
|
|
node->tree->cnid, node->this,
|
|
atomic_read(&node->refcnt));
|
|
BUG_ON(!atomic_read(&node->refcnt));
|
|
if (!atomic_dec_and_lock(&node->refcnt, &tree->hash_lock))
|
|
return;
|
|
for (i = 0; i < tree->pages_per_bnode; i++) {
|
|
if (!node->page[i])
|
|
continue;
|
|
mark_page_accessed(node->page[i]);
|
|
}
|
|
|
|
if (test_bit(HFS_BNODE_DELETED, &node->flags)) {
|
|
hfs_bnode_unhash(node);
|
|
spin_unlock(&tree->hash_lock);
|
|
hfs_bmap_free(node);
|
|
hfs_bnode_free(node);
|
|
return;
|
|
}
|
|
spin_unlock(&tree->hash_lock);
|
|
}
|
|
}
|