6119418f94
To avoid deadlock in case watchers can be interrupted, we need to ensure that producers of the struct other_info can never be blocked by an unrelated consumer. (Likely to occur with KCSAN_INTERRUPT_WATCHER.) There are several cases that can lead to this scenario, for example: 1. A watchpoint A was set up by task T1, but interrupted by interrupt I1. Some other thread (task or interrupt) finds watchpoint A consumes it, and sets other_info. Then I1 also finds some unrelated watchpoint B, consumes it, but is blocked because other_info is in use. T1 cannot consume other_info because I1 never returns -> deadlock. 2. A watchpoint A was set up by task T1, but interrupted by interrupt I1, which also sets up a watchpoint B. Some other thread finds watchpoint A, and consumes it and sets up other_info with its information. Similarly some other thread finds watchpoint B and consumes it, but is then blocked because other_info is in use. When I1 continues it sees its watchpoint was consumed, and that it must wait for other_info, which currently contains information to be consumed by T1. However, T1 cannot unblock other_info because I1 never returns -> deadlock. To avoid this, we need to ensure that producers of struct other_info always have a usable other_info entry. This is obviously not the case with only a single instance of struct other_info, as concurrent producers must wait for the entry to be released by some consumer (which may be locked up as illustrated above). While it would be nice if producers could simply call kmalloc() and append their instance of struct other_info to a list, we are very limited in this code path: since KCSAN can instrument the allocators themselves, calling kmalloc() could lead to deadlock or corrupted allocator state. Since producers of the struct other_info will always succeed at try_consume_watchpoint(), preceding the call into kcsan_report(), we know that the particular watchpoint slot cannot simply be reused or consumed by another potential other_info producer. If we move removal of a watchpoint after reporting (by the consumer of struct other_info), we can see a consumed watchpoint as a held lock on elements of other_info, if we create a one-to-one mapping of a watchpoint to an other_info element. Therefore, the simplest solution is to create an array of struct other_info that is as large as the watchpoints array in core.c, and pass the watchpoint index to kcsan_report() for producers and consumers, and change watchpoints to be removed after reporting is done. With a default config on a 64-bit system, the array other_infos consumes ~37KiB. For most systems today this is not a problem. On smaller memory constrained systems, the config value CONFIG_KCSAN_NUM_WATCHPOINTS can be reduced appropriately. Overall, this change is a simplification of the prepare_report() code, and makes some of the checks (such as checking if at least one access is a write) redundant. Tested: $ tools/testing/selftests/rcutorture/bin/kvm.sh \ --cpus 12 --duration 10 --kconfig "CONFIG_DEBUG_INFO=y \ CONFIG_KCSAN=y CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC=n \ CONFIG_KCSAN_REPORT_VALUE_CHANGE_ONLY=n \ CONFIG_KCSAN_REPORT_ONCE_IN_MS=100000 CONFIG_KCSAN_VERBOSE=y \ CONFIG_KCSAN_INTERRUPT_WATCHER=y CONFIG_PROVE_LOCKING=y" \ --configs TREE03 => No longer hangs and runs to completion as expected. Reported-by: Paul E. McKenney <paulmck@kernel.org> Signed-off-by: Marco Elver <elver@google.com> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
143 lines
3.2 KiB
C
143 lines
3.2 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
|
|
/*
|
|
* The Kernel Concurrency Sanitizer (KCSAN) infrastructure. For more info please
|
|
* see Documentation/dev-tools/kcsan.rst.
|
|
*/
|
|
|
|
#ifndef _KERNEL_KCSAN_KCSAN_H
|
|
#define _KERNEL_KCSAN_KCSAN_H
|
|
|
|
#include <linux/kcsan.h>
|
|
|
|
/* The number of adjacent watchpoints to check. */
|
|
#define KCSAN_CHECK_ADJACENT 1
|
|
#define NUM_SLOTS (1 + 2*KCSAN_CHECK_ADJACENT)
|
|
|
|
extern unsigned int kcsan_udelay_task;
|
|
extern unsigned int kcsan_udelay_interrupt;
|
|
|
|
/*
|
|
* Globally enable and disable KCSAN.
|
|
*/
|
|
extern bool kcsan_enabled;
|
|
|
|
/*
|
|
* Initialize debugfs file.
|
|
*/
|
|
void kcsan_debugfs_init(void);
|
|
|
|
enum kcsan_counter_id {
|
|
/*
|
|
* Number of watchpoints currently in use.
|
|
*/
|
|
KCSAN_COUNTER_USED_WATCHPOINTS,
|
|
|
|
/*
|
|
* Total number of watchpoints set up.
|
|
*/
|
|
KCSAN_COUNTER_SETUP_WATCHPOINTS,
|
|
|
|
/*
|
|
* Total number of data races.
|
|
*/
|
|
KCSAN_COUNTER_DATA_RACES,
|
|
|
|
/*
|
|
* Total number of ASSERT failures due to races. If the observed race is
|
|
* due to two conflicting ASSERT type accesses, then both will be
|
|
* counted.
|
|
*/
|
|
KCSAN_COUNTER_ASSERT_FAILURES,
|
|
|
|
/*
|
|
* Number of times no watchpoints were available.
|
|
*/
|
|
KCSAN_COUNTER_NO_CAPACITY,
|
|
|
|
/*
|
|
* A thread checking a watchpoint raced with another checking thread;
|
|
* only one will be reported.
|
|
*/
|
|
KCSAN_COUNTER_REPORT_RACES,
|
|
|
|
/*
|
|
* Observed data value change, but writer thread unknown.
|
|
*/
|
|
KCSAN_COUNTER_RACES_UNKNOWN_ORIGIN,
|
|
|
|
/*
|
|
* The access cannot be encoded to a valid watchpoint.
|
|
*/
|
|
KCSAN_COUNTER_UNENCODABLE_ACCESSES,
|
|
|
|
/*
|
|
* Watchpoint encoding caused a watchpoint to fire on mismatching
|
|
* accesses.
|
|
*/
|
|
KCSAN_COUNTER_ENCODING_FALSE_POSITIVES,
|
|
|
|
KCSAN_COUNTER_COUNT, /* number of counters */
|
|
};
|
|
|
|
/*
|
|
* Increment/decrement counter with given id; avoid calling these in fast-path.
|
|
*/
|
|
extern void kcsan_counter_inc(enum kcsan_counter_id id);
|
|
extern void kcsan_counter_dec(enum kcsan_counter_id id);
|
|
|
|
/*
|
|
* Returns true if data races in the function symbol that maps to func_addr
|
|
* (offsets are ignored) should *not* be reported.
|
|
*/
|
|
extern bool kcsan_skip_report_debugfs(unsigned long func_addr);
|
|
|
|
/*
|
|
* Value-change states.
|
|
*/
|
|
enum kcsan_value_change {
|
|
/*
|
|
* Did not observe a value-change, however, it is valid to report the
|
|
* race, depending on preferences.
|
|
*/
|
|
KCSAN_VALUE_CHANGE_MAYBE,
|
|
|
|
/*
|
|
* Did not observe a value-change, and it is invalid to report the race.
|
|
*/
|
|
KCSAN_VALUE_CHANGE_FALSE,
|
|
|
|
/*
|
|
* The value was observed to change, and the race should be reported.
|
|
*/
|
|
KCSAN_VALUE_CHANGE_TRUE,
|
|
};
|
|
|
|
enum kcsan_report_type {
|
|
/*
|
|
* The thread that set up the watchpoint and briefly stalled was
|
|
* signalled that another thread triggered the watchpoint.
|
|
*/
|
|
KCSAN_REPORT_RACE_SIGNAL,
|
|
|
|
/*
|
|
* A thread found and consumed a matching watchpoint.
|
|
*/
|
|
KCSAN_REPORT_CONSUMED_WATCHPOINT,
|
|
|
|
/*
|
|
* No other thread was observed to race with the access, but the data
|
|
* value before and after the stall differs.
|
|
*/
|
|
KCSAN_REPORT_RACE_UNKNOWN_ORIGIN,
|
|
};
|
|
|
|
/*
|
|
* Print a race report from thread that encountered the race.
|
|
*/
|
|
extern void kcsan_report(const volatile void *ptr, size_t size, int access_type,
|
|
enum kcsan_value_change value_change,
|
|
enum kcsan_report_type type, int watchpoint_idx);
|
|
|
|
#endif /* _KERNEL_KCSAN_KCSAN_H */
|