1 The Kernel Concurrency Sanitizer (KCSAN)
2 ========================================
4 The Kernel Concurrency Sanitizer (KCSAN) is a dynamic race detector, which
5 relies on compile-time instrumentation, and uses a watchpoint-based sampling
6 approach to detect races. KCSAN's primary purpose is to detect `data races`_.
11 KCSAN requires Clang version 11 or later.
13 To enable KCSAN configure the kernel with::
17 KCSAN provides several other configuration options to customize behaviour (see
18 the respective help text in ``lib/Kconfig.kcsan`` for more info).
23 A typical data race report looks like this::
25 ==================================================================
26 BUG: KCSAN: data-race in generic_permission / kernfs_refresh_inode
28 write to 0xffff8fee4c40700c of 4 bytes by task 175 on cpu 4:
29 kernfs_refresh_inode+0x70/0x170
30 kernfs_iop_permission+0x4f/0x90
31 inode_permission+0x190/0x200
32 link_path_walk.part.0+0x503/0x8e0
33 path_lookupat.isra.0+0x69/0x4d0
34 filename_lookup+0x136/0x280
35 user_path_at_empty+0x47/0x60
37 __do_sys_newlstat+0x50/0xb0
38 __x64_sys_newlstat+0x37/0x50
39 do_syscall_64+0x85/0x260
40 entry_SYSCALL_64_after_hwframe+0x44/0xa9
42 read to 0xffff8fee4c40700c of 4 bytes by task 166 on cpu 6:
43 generic_permission+0x5b/0x2a0
44 kernfs_iop_permission+0x66/0x90
45 inode_permission+0x190/0x200
46 link_path_walk.part.0+0x503/0x8e0
47 path_lookupat.isra.0+0x69/0x4d0
48 filename_lookup+0x136/0x280
49 user_path_at_empty+0x47/0x60
50 do_faccessat+0x11a/0x390
51 __x64_sys_access+0x3c/0x50
52 do_syscall_64+0x85/0x260
53 entry_SYSCALL_64_after_hwframe+0x44/0xa9
55 Reported by Kernel Concurrency Sanitizer on:
56 CPU: 6 PID: 166 Comm: systemd-journal Not tainted 5.3.0-rc7+ #1
57 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014
58 ==================================================================
60 The header of the report provides a short summary of the functions involved in
61 the race. It is followed by the access types and stack traces of the 2 threads
62 involved in the data race.
64 The other less common type of data race report looks like this::
66 ==================================================================
67 BUG: KCSAN: data-race in e1000_clean_rx_irq+0x551/0xb10
69 race at unknown origin, with read to 0xffff933db8a2ae6c of 1 bytes by interrupt on cpu 0:
70 e1000_clean_rx_irq+0x551/0xb10
71 e1000_clean+0x533/0xda0
72 net_rx_action+0x329/0x900
73 __do_softirq+0xdb/0x2db
76 ret_from_intr+0x0/0x18
77 default_idle+0x3f/0x220
78 arch_cpu_idle+0x21/0x30
80 cpu_startup_entry+0x14/0x20
82 arch_call_rest_init+0x13/0x2b
83 start_kernel+0x6db/0x700
85 Reported by Kernel Concurrency Sanitizer on:
86 CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.3.0-rc7+ #2
87 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014
88 ==================================================================
90 This report is generated where it was not possible to determine the other
91 racing thread, but a race was inferred due to the data value of the watched
92 memory location having changed. These can occur either due to missing
93 instrumentation or e.g. DMA accesses. These reports will only be generated if
94 ``CONFIG_KCSAN_REPORT_RACE_UNKNOWN_ORIGIN=y`` (selected by default).
99 It may be desirable to disable data race detection for specific accesses,
100 functions, compilation units, or entire subsystems. For static blacklisting,
101 the below options are available:
103 * KCSAN understands the ``data_race(expr)`` annotation, which tells KCSAN that
104 any data races due to accesses in ``expr`` should be ignored and resulting
105 behaviour when encountering a data race is deemed safe.
107 * Disabling data race detection for entire functions can be accomplished by
108 using the function attribute ``__no_kcsan``::
114 To dynamically limit for which functions to generate reports, see the
115 `DebugFS interface`_ blacklist/whitelist feature.
117 * To disable data race detection for a particular compilation unit, add to the
120 KCSAN_SANITIZE_file.o := n
122 * To disable data race detection for all compilation units listed in a
123 ``Makefile``, add to the respective ``Makefile``::
127 Furthermore, it is possible to tell KCSAN to show or hide entire classes of
128 data races, depending on preferences. These can be changed via the following
131 * ``CONFIG_KCSAN_REPORT_VALUE_CHANGE_ONLY``: If enabled and a conflicting write
132 is observed via a watchpoint, but the data value of the memory location was
133 observed to remain unchanged, do not report the data race.
135 * ``CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC``: Assume that plain aligned writes
136 up to word size are atomic by default. Assumes that such writes are not
137 subject to unsafe compiler optimizations resulting in data races. The option
138 causes KCSAN to not report data races due to conflicts where the only plain
139 accesses are aligned writes up to word size.
144 The file ``/sys/kernel/debug/kcsan`` provides the following interface:
146 * Reading ``/sys/kernel/debug/kcsan`` returns various runtime statistics.
148 * Writing ``on`` or ``off`` to ``/sys/kernel/debug/kcsan`` allows turning KCSAN
149 on or off, respectively.
151 * Writing ``!some_func_name`` to ``/sys/kernel/debug/kcsan`` adds
152 ``some_func_name`` to the report filter list, which (by default) blacklists
153 reporting data races where either one of the top stackframes are a function
156 * Writing either ``blacklist`` or ``whitelist`` to ``/sys/kernel/debug/kcsan``
157 changes the report filtering behaviour. For example, the blacklist feature
158 can be used to silence frequently occurring data races; the whitelist feature
159 can help with reproduction and testing of fixes.
164 Core parameters that affect KCSAN's overall performance and bug detection
165 ability are exposed as kernel command-line arguments whose defaults can also be
166 changed via the corresponding Kconfig options.
168 * ``kcsan.skip_watch`` (``CONFIG_KCSAN_SKIP_WATCH``): Number of per-CPU memory
169 operations to skip, before another watchpoint is set up. Setting up
170 watchpoints more frequently will result in the likelihood of races to be
171 observed to increase. This parameter has the most significant impact on
172 overall system performance and race detection ability.
174 * ``kcsan.udelay_task`` (``CONFIG_KCSAN_UDELAY_TASK``): For tasks, the
175 microsecond delay to stall execution after a watchpoint has been set up.
176 Larger values result in the window in which we may observe a race to
179 * ``kcsan.udelay_interrupt`` (``CONFIG_KCSAN_UDELAY_INTERRUPT``): For
180 interrupts, the microsecond delay to stall execution after a watchpoint has
181 been set up. Interrupts have tighter latency requirements, and their delay
182 should generally be smaller than the one chosen for tasks.
184 They may be tweaked at runtime via ``/sys/module/kcsan/parameters/``.
189 In an execution, two memory accesses form a *data race* if they *conflict*,
190 they happen concurrently in different threads, and at least one of them is a
191 *plain access*; they *conflict* if both access the same memory location, and at
192 least one is a write. For a more thorough discussion and definition, see `"Plain
193 Accesses and Data Races" in the LKMM`_.
195 .. _"Plain Accesses and Data Races" in the LKMM: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/tools/memory-model/Documentation/explanation.txt#n1922
197 Relationship with the Linux-Kernel Memory Consistency Model (LKMM)
198 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
200 The LKMM defines the propagation and ordering rules of various memory
201 operations, which gives developers the ability to reason about concurrent code.
202 Ultimately this allows to determine the possible executions of concurrent code,
203 and if that code is free from data races.
205 KCSAN is aware of *marked atomic operations* (``READ_ONCE``, ``WRITE_ONCE``,
206 ``atomic_*``, etc.), but is oblivious of any ordering guarantees and simply
207 assumes that memory barriers are placed correctly. In other words, KCSAN
208 assumes that as long as a plain access is not observed to race with another
209 conflicting access, memory operations are correctly ordered.
211 This means that KCSAN will not report *potential* data races due to missing
212 memory ordering. Developers should therefore carefully consider the required
213 memory ordering requirements that remain unchecked. If, however, missing
214 memory ordering (that is observable with a particular compiler and
215 architecture) leads to an observable data race (e.g. entering a critical
216 section erroneously), KCSAN would report the resulting data race.
218 Race Detection Beyond Data Races
219 --------------------------------
221 For code with complex concurrency design, race-condition bugs may not always
222 manifest as data races. Race conditions occur if concurrently executing
223 operations result in unexpected system behaviour. On the other hand, data races
224 are defined at the C-language level. The following macros can be used to check
225 properties of concurrent code where bugs would not manifest as data races.
227 .. kernel-doc:: include/linux/kcsan-checks.h
228 :functions: ASSERT_EXCLUSIVE_WRITER ASSERT_EXCLUSIVE_WRITER_SCOPED
229 ASSERT_EXCLUSIVE_ACCESS ASSERT_EXCLUSIVE_ACCESS_SCOPED
230 ASSERT_EXCLUSIVE_BITS
232 Implementation Details
233 ----------------------
235 KCSAN relies on observing that two accesses happen concurrently. Crucially, we
236 want to (a) increase the chances of observing races (especially for races that
237 manifest rarely), and (b) be able to actually observe them. We can accomplish
238 (a) by injecting various delays, and (b) by using address watchpoints (or
241 If we deliberately stall a memory access, while we have a watchpoint for its
242 address set up, and then observe the watchpoint to fire, two accesses to the
243 same address just raced. Using hardware watchpoints, this is the approach taken
245 <http://usenix.org/legacy/events/osdi10/tech/full_papers/Erickson.pdf>`_.
246 Unlike DataCollider, KCSAN does not use hardware watchpoints, but instead
247 relies on compiler instrumentation and "soft watchpoints".
249 In KCSAN, watchpoints are implemented using an efficient encoding that stores
250 access type, size, and address in a long; the benefits of using "soft
251 watchpoints" are portability and greater flexibility. KCSAN then relies on the
252 compiler instrumenting plain accesses. For each instrumented plain access:
254 1. Check if a matching watchpoint exists; if yes, and at least one access is a
255 write, then we encountered a racing access.
257 2. Periodically, if no matching watchpoint exists, set up a watchpoint and
258 stall for a small randomized delay.
260 3. Also check the data value before the delay, and re-check the data value
261 after delay; if the values mismatch, we infer a race of unknown origin.
263 To detect data races between plain and marked accesses, KCSAN also annotates
264 marked accesses, but only to check if a watchpoint exists; i.e. KCSAN never
265 sets up a watchpoint on marked accesses. By never setting up watchpoints for
266 marked operations, if all accesses to a variable that is accessed concurrently
267 are properly marked, KCSAN will never trigger a watchpoint and therefore never
273 1. **Memory Overhead:** The overall memory overhead is only a few MiB
274 depending on configuration. The current implementation uses a small array of
275 longs to encode watchpoint information, which is negligible.
277 2. **Performance Overhead:** KCSAN's runtime aims to be minimal, using an
278 efficient watchpoint encoding that does not require acquiring any shared
279 locks in the fast-path. For kernel boot on a system with 8 CPUs:
281 - 5.0x slow-down with the default KCSAN config;
282 - 2.8x slow-down from runtime fast-path overhead only (set very large
283 ``KCSAN_SKIP_WATCH`` and unset ``KCSAN_SKIP_WATCH_RANDOMIZE``).
285 3. **Annotation Overheads:** Minimal annotations are required outside the KCSAN
286 runtime. As a result, maintenance overheads are minimal as the kernel
289 4. **Detects Racy Writes from Devices:** Due to checking data values upon
290 setting up watchpoints, racy writes from devices can also be detected.
292 5. **Memory Ordering:** KCSAN is *not* explicitly aware of the LKMM's ordering
293 rules; this may result in missed data races (false negatives).
295 6. **Analysis Accuracy:** For observed executions, due to using a sampling
296 strategy, the analysis is *unsound* (false negatives possible), but aims to
297 be complete (no false positives).
299 Alternatives Considered
300 -----------------------
302 An alternative data race detection approach for the kernel can be found in the
303 `Kernel Thread Sanitizer (KTSAN) <https://github.com/google/ktsan/wiki>`_.
304 KTSAN is a happens-before data race detector, which explicitly establishes the
305 happens-before order between memory operations, which can then be used to
306 determine data races as defined in `Data Races`_.
308 To build a correct happens-before relation, KTSAN must be aware of all ordering
309 rules of the LKMM and synchronization primitives. Unfortunately, any omission
310 leads to large numbers of false positives, which is especially detrimental in
311 the context of the kernel which includes numerous custom synchronization
312 mechanisms. To track the happens-before relation, KTSAN's implementation
313 requires metadata for each memory location (shadow memory), which for each page
314 corresponds to 4 pages of shadow memory, and can translate into overhead of
315 tens of GiB on a large system.