1 .. SPDX-License-Identifier: GPL-2.0 1 .. SPDX-License-Identifier: GPL-2.0
2 .. Copyright (C) 2020, Google LLC. 2 .. Copyright (C) 2020, Google LLC.
3 3
4 Kernel Electric-Fence (KFENCE) 4 Kernel Electric-Fence (KFENCE)
5 ============================== 5 ==============================
6 6
7 Kernel Electric-Fence (KFENCE) is a low-overhe 7 Kernel Electric-Fence (KFENCE) is a low-overhead sampling-based memory safety
8 error detector. KFENCE detects heap out-of-bou 8 error detector. KFENCE detects heap out-of-bounds access, use-after-free, and
9 invalid-free errors. 9 invalid-free errors.
10 10
11 KFENCE is designed to be enabled in production 11 KFENCE is designed to be enabled in production kernels, and has near zero
12 performance overhead. Compared to KASAN, KFENC 12 performance overhead. Compared to KASAN, KFENCE trades performance for
13 precision. The main motivation behind KFENCE's 13 precision. The main motivation behind KFENCE's design, is that with enough
14 total uptime KFENCE will detect bugs in code p 14 total uptime KFENCE will detect bugs in code paths not typically exercised by
15 non-production test workloads. One way to quic 15 non-production test workloads. One way to quickly achieve a large enough total
16 uptime is when the tool is deployed across a l 16 uptime is when the tool is deployed across a large fleet of machines.
17 17
18 Usage 18 Usage
19 ----- 19 -----
20 20
21 To enable KFENCE, configure the kernel with:: 21 To enable KFENCE, configure the kernel with::
22 22
23 CONFIG_KFENCE=y 23 CONFIG_KFENCE=y
24 24
25 To build a kernel with KFENCE support, but dis 25 To build a kernel with KFENCE support, but disabled by default (to enable, set
26 ``kfence.sample_interval`` to non-zero value), 26 ``kfence.sample_interval`` to non-zero value), configure the kernel with::
27 27
28 CONFIG_KFENCE=y 28 CONFIG_KFENCE=y
29 CONFIG_KFENCE_SAMPLE_INTERVAL=0 29 CONFIG_KFENCE_SAMPLE_INTERVAL=0
30 30
31 KFENCE provides several other configuration op 31 KFENCE provides several other configuration options to customize behaviour (see
32 the respective help text in ``lib/Kconfig.kfen 32 the respective help text in ``lib/Kconfig.kfence`` for more info).
33 33
34 Tuning performance 34 Tuning performance
35 ~~~~~~~~~~~~~~~~~~ 35 ~~~~~~~~~~~~~~~~~~
36 36
37 The most important parameter is KFENCE's sampl 37 The most important parameter is KFENCE's sample interval, which can be set via
38 the kernel boot parameter ``kfence.sample_inte 38 the kernel boot parameter ``kfence.sample_interval`` in milliseconds. The
39 sample interval determines the frequency with 39 sample interval determines the frequency with which heap allocations will be
40 guarded by KFENCE. The default is configurable 40 guarded by KFENCE. The default is configurable via the Kconfig option
41 ``CONFIG_KFENCE_SAMPLE_INTERVAL``. Setting ``k 41 ``CONFIG_KFENCE_SAMPLE_INTERVAL``. Setting ``kfence.sample_interval=0``
42 disables KFENCE. 42 disables KFENCE.
43 43
44 The sample interval controls a timer that sets 44 The sample interval controls a timer that sets up KFENCE allocations. By
45 default, to keep the real sample interval pred 45 default, to keep the real sample interval predictable, the normal timer also
46 causes CPU wake-ups when the system is complet 46 causes CPU wake-ups when the system is completely idle. This may be undesirable
47 on power-constrained systems. The boot paramet 47 on power-constrained systems. The boot parameter ``kfence.deferrable=1``
48 instead switches to a "deferrable" timer which 48 instead switches to a "deferrable" timer which does not force CPU wake-ups on
49 idle systems, at the risk of unpredictable sam 49 idle systems, at the risk of unpredictable sample intervals. The default is
50 configurable via the Kconfig option ``CONFIG_K 50 configurable via the Kconfig option ``CONFIG_KFENCE_DEFERRABLE``.
51 51
52 .. warning:: 52 .. warning::
53 The KUnit test suite is very likely to fail 53 The KUnit test suite is very likely to fail when using a deferrable timer
54 since it currently causes very unpredictabl 54 since it currently causes very unpredictable sample intervals.
55 55
56 By default KFENCE will only sample 1 heap allo <<
57 interval. *Burst mode* allows to sample succes <<
58 kernel boot parameter ``kfence.burst`` can be <<
59 denotes the *additional* successive allocation <<
60 setting ``kfence.burst=N`` means that ``1 + N` <<
61 attempted through KFENCE for each sample inter <<
62 <<
63 The KFENCE memory pool is of fixed size, and i 56 The KFENCE memory pool is of fixed size, and if the pool is exhausted, no
64 further KFENCE allocations occur. With ``CONFI 57 further KFENCE allocations occur. With ``CONFIG_KFENCE_NUM_OBJECTS`` (default
65 255), the number of available guarded objects 58 255), the number of available guarded objects can be controlled. Each object
66 requires 2 pages, one for the object itself an 59 requires 2 pages, one for the object itself and the other one used as a guard
67 page; object pages are interleaved with guard 60 page; object pages are interleaved with guard pages, and every object page is
68 therefore surrounded by two guard pages. 61 therefore surrounded by two guard pages.
69 62
70 The total memory dedicated to the KFENCE memor 63 The total memory dedicated to the KFENCE memory pool can be computed as::
71 64
72 ( #objects + 1 ) * 2 * PAGE_SIZE 65 ( #objects + 1 ) * 2 * PAGE_SIZE
73 66
74 Using the default config, and assuming a page 67 Using the default config, and assuming a page size of 4 KiB, results in
75 dedicating 2 MiB to the KFENCE memory pool. 68 dedicating 2 MiB to the KFENCE memory pool.
76 69
77 Note: On architectures that support huge pages 70 Note: On architectures that support huge pages, KFENCE will ensure that the
78 pool is using pages of size ``PAGE_SIZE``. Thi 71 pool is using pages of size ``PAGE_SIZE``. This will result in additional page
79 tables being allocated. 72 tables being allocated.
80 73
81 Error reports 74 Error reports
82 ~~~~~~~~~~~~~ 75 ~~~~~~~~~~~~~
83 76
84 A typical out-of-bounds access looks like this 77 A typical out-of-bounds access looks like this::
85 78
86 ========================================== 79 ==================================================================
87 BUG: KFENCE: out-of-bounds read in test_ou 80 BUG: KFENCE: out-of-bounds read in test_out_of_bounds_read+0xa6/0x234
88 81
89 Out-of-bounds read at 0xffff8c3f2e291fff ( 82 Out-of-bounds read at 0xffff8c3f2e291fff (1B left of kfence-#72):
90 test_out_of_bounds_read+0xa6/0x234 83 test_out_of_bounds_read+0xa6/0x234
91 kunit_try_run_case+0x61/0xa0 84 kunit_try_run_case+0x61/0xa0
92 kunit_generic_run_threadfn_adapter+0x16/0 85 kunit_generic_run_threadfn_adapter+0x16/0x30
93 kthread+0x176/0x1b0 86 kthread+0x176/0x1b0
94 ret_from_fork+0x22/0x30 87 ret_from_fork+0x22/0x30
95 88
96 kfence-#72: 0xffff8c3f2e292000-0xffff8c3f2 89 kfence-#72: 0xffff8c3f2e292000-0xffff8c3f2e29201f, size=32, cache=kmalloc-32
97 90
98 allocated by task 484 on cpu 0 at 32.91933 91 allocated by task 484 on cpu 0 at 32.919330s:
99 test_alloc+0xfe/0x738 92 test_alloc+0xfe/0x738
100 test_out_of_bounds_read+0x9b/0x234 93 test_out_of_bounds_read+0x9b/0x234
101 kunit_try_run_case+0x61/0xa0 94 kunit_try_run_case+0x61/0xa0
102 kunit_generic_run_threadfn_adapter+0x16/0 95 kunit_generic_run_threadfn_adapter+0x16/0x30
103 kthread+0x176/0x1b0 96 kthread+0x176/0x1b0
104 ret_from_fork+0x22/0x30 97 ret_from_fork+0x22/0x30
105 98
106 CPU: 0 PID: 484 Comm: kunit_try_catch Not 99 CPU: 0 PID: 484 Comm: kunit_try_catch Not tainted 5.13.0-rc3+ #7
107 Hardware name: QEMU Standard PC (i440FX + 100 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014
108 ========================================== 101 ==================================================================
109 102
110 The header of the report provides a short summ 103 The header of the report provides a short summary of the function involved in
111 the access. It is followed by more detailed in 104 the access. It is followed by more detailed information about the access and
112 its origin. Note that, real kernel addresses a 105 its origin. Note that, real kernel addresses are only shown when using the
113 kernel command line option ``no_hash_pointers` 106 kernel command line option ``no_hash_pointers``.
114 107
115 Use-after-free accesses are reported as:: 108 Use-after-free accesses are reported as::
116 109
117 ========================================== 110 ==================================================================
118 BUG: KFENCE: use-after-free read in test_u 111 BUG: KFENCE: use-after-free read in test_use_after_free_read+0xb3/0x143
119 112
120 Use-after-free read at 0xffff8c3f2e2a0000 113 Use-after-free read at 0xffff8c3f2e2a0000 (in kfence-#79):
121 test_use_after_free_read+0xb3/0x143 114 test_use_after_free_read+0xb3/0x143
122 kunit_try_run_case+0x61/0xa0 115 kunit_try_run_case+0x61/0xa0
123 kunit_generic_run_threadfn_adapter+0x16/0 116 kunit_generic_run_threadfn_adapter+0x16/0x30
124 kthread+0x176/0x1b0 117 kthread+0x176/0x1b0
125 ret_from_fork+0x22/0x30 118 ret_from_fork+0x22/0x30
126 119
127 kfence-#79: 0xffff8c3f2e2a0000-0xffff8c3f2 120 kfence-#79: 0xffff8c3f2e2a0000-0xffff8c3f2e2a001f, size=32, cache=kmalloc-32
128 121
129 allocated by task 488 on cpu 2 at 33.87132 122 allocated by task 488 on cpu 2 at 33.871326s:
130 test_alloc+0xfe/0x738 123 test_alloc+0xfe/0x738
131 test_use_after_free_read+0x76/0x143 124 test_use_after_free_read+0x76/0x143
132 kunit_try_run_case+0x61/0xa0 125 kunit_try_run_case+0x61/0xa0
133 kunit_generic_run_threadfn_adapter+0x16/0 126 kunit_generic_run_threadfn_adapter+0x16/0x30
134 kthread+0x176/0x1b0 127 kthread+0x176/0x1b0
135 ret_from_fork+0x22/0x30 128 ret_from_fork+0x22/0x30
136 129
137 freed by task 488 on cpu 2 at 33.871358s: 130 freed by task 488 on cpu 2 at 33.871358s:
138 test_use_after_free_read+0xa8/0x143 131 test_use_after_free_read+0xa8/0x143
139 kunit_try_run_case+0x61/0xa0 132 kunit_try_run_case+0x61/0xa0
140 kunit_generic_run_threadfn_adapter+0x16/0 133 kunit_generic_run_threadfn_adapter+0x16/0x30
141 kthread+0x176/0x1b0 134 kthread+0x176/0x1b0
142 ret_from_fork+0x22/0x30 135 ret_from_fork+0x22/0x30
143 136
144 CPU: 2 PID: 488 Comm: kunit_try_catch Tain 137 CPU: 2 PID: 488 Comm: kunit_try_catch Tainted: G B 5.13.0-rc3+ #7
145 Hardware name: QEMU Standard PC (i440FX + 138 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014
146 ========================================== 139 ==================================================================
147 140
148 KFENCE also reports on invalid frees, such as 141 KFENCE also reports on invalid frees, such as double-frees::
149 142
150 ========================================== 143 ==================================================================
151 BUG: KFENCE: invalid free in test_double_f 144 BUG: KFENCE: invalid free in test_double_free+0xdc/0x171
152 145
153 Invalid free of 0xffff8c3f2e2a4000 (in kfe 146 Invalid free of 0xffff8c3f2e2a4000 (in kfence-#81):
154 test_double_free+0xdc/0x171 147 test_double_free+0xdc/0x171
155 kunit_try_run_case+0x61/0xa0 148 kunit_try_run_case+0x61/0xa0
156 kunit_generic_run_threadfn_adapter+0x16/0 149 kunit_generic_run_threadfn_adapter+0x16/0x30
157 kthread+0x176/0x1b0 150 kthread+0x176/0x1b0
158 ret_from_fork+0x22/0x30 151 ret_from_fork+0x22/0x30
159 152
160 kfence-#81: 0xffff8c3f2e2a4000-0xffff8c3f2 153 kfence-#81: 0xffff8c3f2e2a4000-0xffff8c3f2e2a401f, size=32, cache=kmalloc-32
161 154
162 allocated by task 490 on cpu 1 at 34.17532 155 allocated by task 490 on cpu 1 at 34.175321s:
163 test_alloc+0xfe/0x738 156 test_alloc+0xfe/0x738
164 test_double_free+0x76/0x171 157 test_double_free+0x76/0x171
165 kunit_try_run_case+0x61/0xa0 158 kunit_try_run_case+0x61/0xa0
166 kunit_generic_run_threadfn_adapter+0x16/0 159 kunit_generic_run_threadfn_adapter+0x16/0x30
167 kthread+0x176/0x1b0 160 kthread+0x176/0x1b0
168 ret_from_fork+0x22/0x30 161 ret_from_fork+0x22/0x30
169 162
170 freed by task 490 on cpu 1 at 34.175348s: 163 freed by task 490 on cpu 1 at 34.175348s:
171 test_double_free+0xa8/0x171 164 test_double_free+0xa8/0x171
172 kunit_try_run_case+0x61/0xa0 165 kunit_try_run_case+0x61/0xa0
173 kunit_generic_run_threadfn_adapter+0x16/0 166 kunit_generic_run_threadfn_adapter+0x16/0x30
174 kthread+0x176/0x1b0 167 kthread+0x176/0x1b0
175 ret_from_fork+0x22/0x30 168 ret_from_fork+0x22/0x30
176 169
177 CPU: 1 PID: 490 Comm: kunit_try_catch Tain 170 CPU: 1 PID: 490 Comm: kunit_try_catch Tainted: G B 5.13.0-rc3+ #7
178 Hardware name: QEMU Standard PC (i440FX + 171 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014
179 ========================================== 172 ==================================================================
180 173
181 KFENCE also uses pattern-based redzones on the 174 KFENCE also uses pattern-based redzones on the other side of an object's guard
182 page, to detect out-of-bounds writes on the un 175 page, to detect out-of-bounds writes on the unprotected side of the object.
183 These are reported on frees:: 176 These are reported on frees::
184 177
185 ========================================== 178 ==================================================================
186 BUG: KFENCE: memory corruption in test_kma 179 BUG: KFENCE: memory corruption in test_kmalloc_aligned_oob_write+0xef/0x184
187 180
188 Corrupted memory at 0xffff8c3f2e33aff9 [ 0 181 Corrupted memory at 0xffff8c3f2e33aff9 [ 0xac . . . . . . ] (in kfence-#156):
189 test_kmalloc_aligned_oob_write+0xef/0x184 182 test_kmalloc_aligned_oob_write+0xef/0x184
190 kunit_try_run_case+0x61/0xa0 183 kunit_try_run_case+0x61/0xa0
191 kunit_generic_run_threadfn_adapter+0x16/0 184 kunit_generic_run_threadfn_adapter+0x16/0x30
192 kthread+0x176/0x1b0 185 kthread+0x176/0x1b0
193 ret_from_fork+0x22/0x30 186 ret_from_fork+0x22/0x30
194 187
195 kfence-#156: 0xffff8c3f2e33afb0-0xffff8c3f 188 kfence-#156: 0xffff8c3f2e33afb0-0xffff8c3f2e33aff8, size=73, cache=kmalloc-96
196 189
197 allocated by task 502 on cpu 7 at 42.15930 190 allocated by task 502 on cpu 7 at 42.159302s:
198 test_alloc+0xfe/0x738 191 test_alloc+0xfe/0x738
199 test_kmalloc_aligned_oob_write+0x57/0x184 192 test_kmalloc_aligned_oob_write+0x57/0x184
200 kunit_try_run_case+0x61/0xa0 193 kunit_try_run_case+0x61/0xa0
201 kunit_generic_run_threadfn_adapter+0x16/0 194 kunit_generic_run_threadfn_adapter+0x16/0x30
202 kthread+0x176/0x1b0 195 kthread+0x176/0x1b0
203 ret_from_fork+0x22/0x30 196 ret_from_fork+0x22/0x30
204 197
205 CPU: 7 PID: 502 Comm: kunit_try_catch Tain 198 CPU: 7 PID: 502 Comm: kunit_try_catch Tainted: G B 5.13.0-rc3+ #7
206 Hardware name: QEMU Standard PC (i440FX + 199 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014
207 ========================================== 200 ==================================================================
208 201
209 For such errors, the address where the corrupt 202 For such errors, the address where the corruption occurred as well as the
210 invalidly written bytes (offset from the addre 203 invalidly written bytes (offset from the address) are shown; in this
211 representation, '.' denote untouched bytes. In 204 representation, '.' denote untouched bytes. In the example above ``0xac`` is
212 the value written to the invalid address at of 205 the value written to the invalid address at offset 0, and the remaining '.'
213 denote that no following bytes have been touch 206 denote that no following bytes have been touched. Note that, real values are
214 only shown if the kernel was booted with ``no_ 207 only shown if the kernel was booted with ``no_hash_pointers``; to avoid
215 information disclosure otherwise, '!' is used 208 information disclosure otherwise, '!' is used instead to denote invalidly
216 written bytes. 209 written bytes.
217 210
218 And finally, KFENCE may also report on invalid 211 And finally, KFENCE may also report on invalid accesses to any protected page
219 where it was not possible to determine an asso 212 where it was not possible to determine an associated object, e.g. if adjacent
220 object pages had not yet been allocated:: 213 object pages had not yet been allocated::
221 214
222 ========================================== 215 ==================================================================
223 BUG: KFENCE: invalid read in test_invalid_ 216 BUG: KFENCE: invalid read in test_invalid_access+0x26/0xe0
224 217
225 Invalid read at 0xffffffffb670b00a: 218 Invalid read at 0xffffffffb670b00a:
226 test_invalid_access+0x26/0xe0 219 test_invalid_access+0x26/0xe0
227 kunit_try_run_case+0x51/0x85 220 kunit_try_run_case+0x51/0x85
228 kunit_generic_run_threadfn_adapter+0x16/0 221 kunit_generic_run_threadfn_adapter+0x16/0x30
229 kthread+0x137/0x160 222 kthread+0x137/0x160
230 ret_from_fork+0x22/0x30 223 ret_from_fork+0x22/0x30
231 224
232 CPU: 4 PID: 124 Comm: kunit_try_catch Tain 225 CPU: 4 PID: 124 Comm: kunit_try_catch Tainted: G W 5.8.0-rc6+ #7
233 Hardware name: QEMU Standard PC (i440FX + 226 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1 04/01/2014
234 ========================================== 227 ==================================================================
235 228
236 DebugFS interface 229 DebugFS interface
237 ~~~~~~~~~~~~~~~~~ 230 ~~~~~~~~~~~~~~~~~
238 231
239 Some debugging information is exposed via debu 232 Some debugging information is exposed via debugfs:
240 233
241 * The file ``/sys/kernel/debug/kfence/stats`` 234 * The file ``/sys/kernel/debug/kfence/stats`` provides runtime statistics.
242 235
243 * The file ``/sys/kernel/debug/kfence/objects` 236 * The file ``/sys/kernel/debug/kfence/objects`` provides a list of objects
244 allocated via KFENCE, including those alread 237 allocated via KFENCE, including those already freed but protected.
245 238
246 Implementation Details 239 Implementation Details
247 ---------------------- 240 ----------------------
248 241
249 Guarded allocations are set up based on the sa 242 Guarded allocations are set up based on the sample interval. After expiration
250 of the sample interval, the next allocation th 243 of the sample interval, the next allocation through the main allocator (SLAB or
251 SLUB) returns a guarded allocation from the KF 244 SLUB) returns a guarded allocation from the KFENCE object pool (allocation
252 sizes up to PAGE_SIZE are supported). At this 245 sizes up to PAGE_SIZE are supported). At this point, the timer is reset, and
253 the next allocation is set up after the expira 246 the next allocation is set up after the expiration of the interval.
254 247
255 When using ``CONFIG_KFENCE_STATIC_KEYS=y``, KF 248 When using ``CONFIG_KFENCE_STATIC_KEYS=y``, KFENCE allocations are "gated"
256 through the main allocator's fast-path by rely 249 through the main allocator's fast-path by relying on static branches via the
257 static keys infrastructure. The static branch 250 static keys infrastructure. The static branch is toggled to redirect the
258 allocation to KFENCE. Depending on sample inte 251 allocation to KFENCE. Depending on sample interval, target workloads, and
259 system architecture, this may perform better t 252 system architecture, this may perform better than the simple dynamic branch.
260 Careful benchmarking is recommended. 253 Careful benchmarking is recommended.
261 254
262 KFENCE objects each reside on a dedicated page 255 KFENCE objects each reside on a dedicated page, at either the left or right
263 page boundaries selected at random. The pages 256 page boundaries selected at random. The pages to the left and right of the
264 object page are "guard pages", whose attribute 257 object page are "guard pages", whose attributes are changed to a protected
265 state, and cause page faults on any attempted 258 state, and cause page faults on any attempted access. Such page faults are then
266 intercepted by KFENCE, which handles the fault 259 intercepted by KFENCE, which handles the fault gracefully by reporting an
267 out-of-bounds access, and marking the page as 260 out-of-bounds access, and marking the page as accessible so that the faulting
268 code can (wrongly) continue executing (set ``p 261 code can (wrongly) continue executing (set ``panic_on_warn`` to panic instead).
269 262
270 To detect out-of-bounds writes to memory withi 263 To detect out-of-bounds writes to memory within the object's page itself,
271 KFENCE also uses pattern-based redzones. For e 264 KFENCE also uses pattern-based redzones. For each object page, a redzone is set
272 up for all non-object memory. For typical alig 265 up for all non-object memory. For typical alignments, the redzone is only
273 required on the unguarded side of an object. B 266 required on the unguarded side of an object. Because KFENCE must honor the
274 cache's requested alignment, special alignment 267 cache's requested alignment, special alignments may result in unprotected gaps
275 on either side of an object, all of which are 268 on either side of an object, all of which are redzoned.
276 269
277 The following figure illustrates the page layo 270 The following figure illustrates the page layout::
278 271
279 ---+-----------+-----------+-----------+-- 272 ---+-----------+-----------+-----------+-----------+-----------+---
280 | xxxxxxxxx | O : | xxxxxxxxx | 273 | xxxxxxxxx | O : | xxxxxxxxx | : O | xxxxxxxxx |
281 | xxxxxxxxx | B : | xxxxxxxxx | 274 | xxxxxxxxx | B : | xxxxxxxxx | : B | xxxxxxxxx |
282 | x GUARD x | J : RED- | x GUARD x | R 275 | x GUARD x | J : RED- | x GUARD x | RED- : J | x GUARD x |
283 | xxxxxxxxx | E : ZONE | xxxxxxxxx | 276 | xxxxxxxxx | E : ZONE | xxxxxxxxx | ZONE : E | xxxxxxxxx |
284 | xxxxxxxxx | C : | xxxxxxxxx | 277 | xxxxxxxxx | C : | xxxxxxxxx | : C | xxxxxxxxx |
285 | xxxxxxxxx | T : | xxxxxxxxx | 278 | xxxxxxxxx | T : | xxxxxxxxx | : T | xxxxxxxxx |
286 ---+-----------+-----------+-----------+-- 279 ---+-----------+-----------+-----------+-----------+-----------+---
287 280
288 Upon deallocation of a KFENCE object, the obje 281 Upon deallocation of a KFENCE object, the object's page is again protected and
289 the object is marked as freed. Any further acc 282 the object is marked as freed. Any further access to the object causes a fault
290 and KFENCE reports a use-after-free access. Fr 283 and KFENCE reports a use-after-free access. Freed objects are inserted at the
291 tail of KFENCE's freelist, so that the least r 284 tail of KFENCE's freelist, so that the least recently freed objects are reused
292 first, and the chances of detecting use-after- 285 first, and the chances of detecting use-after-frees of recently freed objects
293 is increased. 286 is increased.
294 287
295 If pool utilization reaches 75% (default) or a 288 If pool utilization reaches 75% (default) or above, to reduce the risk of the
296 pool eventually being fully occupied by alloca 289 pool eventually being fully occupied by allocated objects yet ensure diverse
297 coverage of allocations, KFENCE limits current 290 coverage of allocations, KFENCE limits currently covered allocations of the
298 same source from further filling up the pool. 291 same source from further filling up the pool. The "source" of an allocation is
299 based on its partial allocation stack trace. A 292 based on its partial allocation stack trace. A side-effect is that this also
300 limits frequent long-lived allocations (e.g. p 293 limits frequent long-lived allocations (e.g. pagecache) of the same source
301 filling up the pool permanently, which is the 294 filling up the pool permanently, which is the most common risk for the pool
302 becoming full and the sampled allocation rate 295 becoming full and the sampled allocation rate dropping to zero. The threshold
303 at which to start limiting currently covered a 296 at which to start limiting currently covered allocations can be configured via
304 the boot parameter ``kfence.skip_covered_thres 297 the boot parameter ``kfence.skip_covered_thresh`` (pool usage%).
305 298
306 Interface 299 Interface
307 --------- 300 ---------
308 301
309 The following describes the functions which ar 302 The following describes the functions which are used by allocators as well as
310 page handling code to set up and deal with KFE 303 page handling code to set up and deal with KFENCE allocations.
311 304
312 .. kernel-doc:: include/linux/kfence.h 305 .. kernel-doc:: include/linux/kfence.h
313 :functions: is_kfence_address 306 :functions: is_kfence_address
314 kfence_shutdown_cache 307 kfence_shutdown_cache
315 kfence_alloc kfence_free __kfen 308 kfence_alloc kfence_free __kfence_free
316 kfence_ksize kfence_object_star 309 kfence_ksize kfence_object_start
317 kfence_handle_page_fault 310 kfence_handle_page_fault
318 311
319 Related Tools 312 Related Tools
320 ------------- 313 -------------
321 314
322 In userspace, a similar approach is taken by ` 315 In userspace, a similar approach is taken by `GWP-ASan
323 <http://llvm.org/docs/GwpAsan.html>`_. GWP-ASa 316 <http://llvm.org/docs/GwpAsan.html>`_. GWP-ASan also relies on guard pages and
324 a sampling strategy to detect memory unsafety 317 a sampling strategy to detect memory unsafety bugs at scale. KFENCE's design is
325 directly influenced by GWP-ASan, and can be se 318 directly influenced by GWP-ASan, and can be seen as its kernel sibling. Another
326 similar but non-sampling approach, that also i 319 similar but non-sampling approach, that also inspired the name "KFENCE", can be
327 found in the userspace `Electric Fence Malloc 320 found in the userspace `Electric Fence Malloc Debugger
328 <https://linux.die.net/man/3/efence>`_. 321 <https://linux.die.net/man/3/efence>`_.
329 322
330 In the kernel, several tools exist to debug me 323 In the kernel, several tools exist to debug memory access errors, and in
331 particular KASAN can detect all bug classes th 324 particular KASAN can detect all bug classes that KFENCE can detect. While KASAN
332 is more precise, relying on compiler instrumen 325 is more precise, relying on compiler instrumentation, this comes at a
333 performance cost. 326 performance cost.
334 327
335 It is worth highlighting that KASAN and KFENCE 328 It is worth highlighting that KASAN and KFENCE are complementary, with
336 different target environments. For instance, K 329 different target environments. For instance, KASAN is the better debugging-aid,
337 where test cases or reproducers exists: due to 330 where test cases or reproducers exists: due to the lower chance to detect the
338 error, it would require more effort using KFEN 331 error, it would require more effort using KFENCE to debug. Deployments at scale
339 that cannot afford to enable KASAN, however, w 332 that cannot afford to enable KASAN, however, would benefit from using KFENCE to
340 discover bugs due to code paths not exercised 333 discover bugs due to code paths not exercised by test cases or fuzzers.
Linux® is a registered trademark of Linus Torvalds in the United States and other countries.
TOMOYO® is a registered trademark of NTT DATA CORPORATION.