forked from Minki/linux
fd8f58c40b
Add a test which shows a race in the multi-order iteration code. This
test reliably hits the race in under a second on my machine, and is the
result of a real bug report against kernel a production v4.15 based
kernel (4.15.6-300.fc27.x86_64). With a real kernel this issue is hit
when using order 9 PMD DAX radix tree entries.
The race has to do with how we tear down multi-order sibling entries
when we are removing an item from the tree. Remember that an order 2
entry looks like this:
struct radix_tree_node.slots[] = [entry][sibling][sibling][sibling]
where 'entry' is in some slot in the struct radix_tree_node, and the
three slots following 'entry' contain sibling pointers which point back
to 'entry.'
When we delete 'entry' from the tree, we call :
radix_tree_delete()
radix_tree_delete_item()
__radix_tree_delete()
replace_slot()
replace_slot() first removes the siblings in order from the first to the
last, then at then replaces 'entry' with NULL. This means that for a
brief period of time we end up with one or more of the siblings removed,
so:
struct radix_tree_node.slots[] = [entry][NULL][sibling][sibling]
This causes an issue if you have a reader iterating over the slots in
the tree via radix_tree_for_each_slot() while only under
rcu_read_lock()/rcu_read_unlock() protection. This is a common case in
mm/filemap.c.
The issue is that when __radix_tree_next_slot() => skip_siblings() tries
to skip over the sibling entries in the slots, it currently does so with
an exact match on the slot directly preceding our current slot.
Normally this works:
V preceding slot
struct radix_tree_node.slots[] = [entry][sibling][sibling][sibling]
^ current slot
This lets you find the first sibling, and you skip them all in order.
But in the case where one of the siblings is NULL, that slot is skipped
and then our sibling detection is interrupted:
V preceding slot
struct radix_tree_node.slots[] = [entry][NULL][sibling][sibling]
^ current slot
This means that the sibling pointers aren't recognized since they point
all the way back to 'entry', so we think that they are normal internal
radix tree pointers. This causes us to think we need to walk down to a
struct radix_tree_node starting at the address of 'entry'.
In a real running kernel this will crash the thread with a GP fault when
you try and dereference the slots in your broken node starting at
'entry'.
In the radix tree test suite this will be caught by the address
sanitizer:
==27063==ERROR: AddressSanitizer: heap-buffer-overflow on address
0x60c0008ae400 at pc 0x00000040ce4f bp 0x7fa89b8fcad0 sp 0x7fa89b8fcac0
READ of size 8 at 0x60c0008ae400 thread T3
#0 0x40ce4e in __radix_tree_next_slot /home/rzwisler/project/linux/tools/testing/radix-tree/radix-tree.c:1660
#1 0x4022cc in radix_tree_next_slot linux/../../../../include/linux/radix-tree.h:567
#2 0x4022cc in iterator_func /home/rzwisler/project/linux/tools/testing/radix-tree/multiorder.c:655
#3 0x7fa8a088d50a in start_thread (/lib64/libpthread.so.0+0x750a)
#4 0x7fa8a03bd16e in clone (/lib64/libc.so.6+0xf516e)
Link: http://lkml.kernel.org/r/20180503192430.7582-5-ross.zwisler@linux.intel.com
Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: CR, Sapthagirish <sapthagirish.cr@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
67 lines
2.5 KiB
C
67 lines
2.5 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#include <linux/gfp.h>
|
|
#include <linux/types.h>
|
|
#include <linux/radix-tree.h>
|
|
#include <linux/rcupdate.h>
|
|
|
|
struct item {
|
|
struct rcu_head rcu_head;
|
|
unsigned long index;
|
|
unsigned int order;
|
|
};
|
|
|
|
struct item *item_create(unsigned long index, unsigned int order);
|
|
int __item_insert(struct radix_tree_root *root, struct item *item);
|
|
int item_insert(struct radix_tree_root *root, unsigned long index);
|
|
void item_sanity(struct item *item, unsigned long index);
|
|
int item_insert_order(struct radix_tree_root *root, unsigned long index,
|
|
unsigned order);
|
|
int item_delete(struct radix_tree_root *root, unsigned long index);
|
|
int item_delete_rcu(struct radix_tree_root *root, unsigned long index);
|
|
struct item *item_lookup(struct radix_tree_root *root, unsigned long index);
|
|
|
|
void item_check_present(struct radix_tree_root *root, unsigned long index);
|
|
void item_check_absent(struct radix_tree_root *root, unsigned long index);
|
|
void item_gang_check_present(struct radix_tree_root *root,
|
|
unsigned long start, unsigned long nr,
|
|
int chunk, int hop);
|
|
void item_full_scan(struct radix_tree_root *root, unsigned long start,
|
|
unsigned long nr, int chunk);
|
|
void item_kill_tree(struct radix_tree_root *root);
|
|
|
|
int tag_tagged_items(struct radix_tree_root *, pthread_mutex_t *,
|
|
unsigned long start, unsigned long end, unsigned batch,
|
|
unsigned iftag, unsigned thentag);
|
|
unsigned long find_item(struct radix_tree_root *, void *item);
|
|
|
|
void tag_check(void);
|
|
void multiorder_checks(void);
|
|
void iteration_test(unsigned order, unsigned duration);
|
|
void benchmark(void);
|
|
void idr_checks(void);
|
|
void ida_checks(void);
|
|
void ida_thread_tests(void);
|
|
|
|
struct item *
|
|
item_tag_set(struct radix_tree_root *root, unsigned long index, int tag);
|
|
struct item *
|
|
item_tag_clear(struct radix_tree_root *root, unsigned long index, int tag);
|
|
int item_tag_get(struct radix_tree_root *root, unsigned long index, int tag);
|
|
void tree_verify_min_height(struct radix_tree_root *root, int maxindex);
|
|
void verify_tag_consistency(struct radix_tree_root *root, unsigned int tag);
|
|
|
|
extern int nr_allocated;
|
|
|
|
/* Normally private parts of lib/radix-tree.c */
|
|
struct radix_tree_node *entry_to_node(void *ptr);
|
|
void radix_tree_dump(struct radix_tree_root *root);
|
|
int root_tag_get(struct radix_tree_root *root, unsigned int tag);
|
|
unsigned long node_maxindex(struct radix_tree_node *);
|
|
unsigned long shift_maxindex(unsigned int shift);
|
|
int radix_tree_cpu_dead(unsigned int cpu);
|
|
struct radix_tree_preload {
|
|
unsigned nr;
|
|
struct radix_tree_node *nodes;
|
|
};
|
|
extern struct radix_tree_preload radix_tree_preloads;
|